Improved measurement accuracy and reliability

Abstract

In particular, the present invention relates to devices and methods for improving the accuracy and reliability of an assay, even when the assay device and / or the operation of the assay device has some errors, and in some embodiments the errors are random.

Description

[0001] Cross-references

[0002] This application claims the benefit of priority to U.S. Provisional Patent Application No. 62 / 830,311, filed on April 5, 2019, and is a continuation-in-part of International Patent Application No. PCT / US2019 / 048678, filed on August 28, 2019, which claims priority to U.S. Provisional Application Serial No. 62 / 742,247, filed on October 5, 2018, and U.S. Provisional Application Serial No. 62 / 742,247, filed on August 28, 2018. This application is also a continuation-in-part of International Patent Application No. PCT / US2019 / 046971, filed on August 16, 2019, which claims the benefit of U.S. Provisional Application Serial No. 62 / 764,886, filed on August 16, 2018, and U.S. Provisional Application Serial No. 62 / 719,129, filed on August 16, 2018, the contents of which are incorporated herein by reference in their entirety. The entire disclosure of any publication or patent document mentioned herein is incorporated by reference in its entirety. Technical Field

[0003] The present invention relates particularly to apparatus and methods for performing biological and chemical assays, and more particularly to improving assay detection accuracy and reliability when the assays are performed under imperfect conditions with distortion and random variation (eg, limited resource settings). Background Art

[0004] When measuring biomarkers in samples from subjects (e.g., humans) for diagnosing conditions or diseases, the accuracy of the measurement is essential. False results may be harmful to the subject. Traditionally, the accuracy of the measurement is achieved by a "perfect protocol paradigm" (i.e., accurately executing everything including sample processing). This method requires complex machines, professional operations, ideal environments, etc., in order to ensure a "perfect" measurement device and "perfect" measurement performance and operation. However, it is highly desirable to develop a system and method for improving the accuracy of the measurement, which includes at least one parameter, each parameter having an error that can come from the measurement device or device operation, and the error can be random according to a specific device or a specific operation. Summary of the invention

[0005] In particular, the present invention relates to devices and methods for improving the accuracy and reliability of an assay, even when the assay device and / or the operation of the assay device has certain errors, and in some embodiments the errors are random.

[0006] One aspect of the present invention is to overcome random errors or imperfections in the operation of an assay device or an assay device by measuring the confidence of an analyte test result in addition to measuring the analyte in a sample to generate an analyte test result. The analyte test result is reported only if the confidence meets a predetermined threshold, otherwise the analyte test result is discarded.

[0007] In some embodiments, the confidence level is measured by imaging one or more parameters of the sample being assayed and processing the image using an algorithm.

[0008] In some embodiments, one or more monitoring structures (ie, arrays of posts) are placed on the sample contacting area of ​​the sample holder to provide information for confidence measurements.

[0009] One aspect of the invention is to overcome distortion of an optical system in an image-based assay by having monitoring marks on a sample holder, wherein one or more optical properties of the monitoring marks of an optical system without distortion are determined prior to the assay test. The monitoring marks are imaged with the sample using an optical system with distortion. An algorithm is used to compare the monitoring marks in the optical system with distortion to the monitoring marks without distortion, correcting for distortion in the image-based assay.

[0010] In some embodiments, the algorithm is a machine learning model.

[0011] In some embodiments, a method for improving the accuracy of an assay for detecting an analyte in a sample, wherein one or more parameters of the assay have stochastic variation, the method comprising:

[0012] detecting an analyte in the sample using the assay and generating a test result;

[0013] determining the confidence level of the detection result by (i) imaging the sample in the assay and (ii) processing the image using an algorithm; and

[0014] The detection result is reported only when the confidence level meets a predetermined threshold.

[0015] In some embodiments, an apparatus for improving the accuracy of an assay for detecting an analyte in a sample, wherein one or more parameters of the assay have stochastic variation, comprises:

[0016] an assay for detecting an analyte in the sample to produce a test result, wherein the assay has a sample holder; and

[0017] an imager that images the sample in the sample holder; and

[0018] A non-transitory storage medium stores an algorithm that uses the image to determine the confidence level of the detection result.

[0019] In some embodiments, the method as described in any of the foregoing embodiments further comprises using one or more monitoring marks on a sample holder for the assay and imaging the monitoring marks in the image to determine the credibility, wherein the monitoring marks have predetermined optical properties in the manufacture of the sample holder.

[0020] In some embodiments, the apparatus as described in any of the preceding embodiments further comprises one or more monitoring marks on the sample holder, wherein the monitoring marks have predetermined optical properties during the manufacture of the sample holder and are imaged in the image to determine the credibility.

[0021] In some embodiments, a method for improving the accuracy of an image-based assay for detecting an analyte in a sample, wherein the assay has an optical system with distortion, the method comprising:

[0022] having a sample holder having a sample contacting surface, wherein (i) a sample forms a thin layer of 200 nm thick or less on the sample contacting surface, and (ii) one or more monitoring marks on the sample contacting surface of the sample, wherein the monitoring marks have a first set of parameters predetermined during manufacture of the sample holder;

[0023] capturing one or more images of the sample in the sample holder together with the monitoring marker using an optical system of the assay, wherein the monitoring marker has a second set of parameters in the images;

[0024] The one or more images are processed using a processor, wherein the processor detects distortion of the optical system by using the algorithm and the first set of parameters and the second set of parameters.

[0025] In some embodiments, an apparatus for improving the accuracy of an image-based assay for detecting an analyte in a sample, wherein the assay has an optical system with distortion, the apparatus comprising:

[0026] A sample holder having a sample contacting surface, wherein (i) a sample forms a thin layer of 200 nm thick or less on the sample contacting surface, and (ii) one or more monitoring marks on the sample contacting surface of the sample, wherein the monitoring marks have a first set of parameters predetermined during manufacture of the sample holder;

[0027] an optical system of the assay for capturing one or more images of the sample in the sample holder together with the monitoring marker, wherein the monitoring marker has a second set of parameters in the image;

[0028] A processor having a non-transitory storage medium storing an algorithm that processes the one or more images and corrects distortion of the optical system by using the algorithm and the first set of parameters and the second set of parameters.

[0029] In some embodiments, the method as described in any of the preceding embodiments, wherein the algorithm is a machine learning model.

[0030] In some embodiments, the method as described in any of the above embodiments, wherein the confidence level includes (1) blood margin, (2) bubbles in the blood, (3) blood volume is too small or blood volume is too large, (4) blood cells under the spacer, (5) aggregated blood cells, (6) lysed blood cells, (7) overexposed image of the sample, (8) underexposed image of the sample, (8) poor focus of the sample, (9) optical system error with wrong lever position, (10) unclosed card, (12) wrong card due to card without spacer, (12) dust in the card, (14) oil in the card, (14) stains on the card outside the focal plane, (15) card not in the correct position in the reader, (16) empty card, (17) manufacturing error in the card, (18) wrong card for other applications, (19) dried blood, (20) expired card, (21) large changes in blood cell distribution, (22) non-blood sample, or (23) non-target blood sample.

[0031] In some embodiments, the method as described in any of the preceding embodiments, wherein the algorithm is machine learning.

[0032] In some embodiments, the method as described in any of the preceding embodiments, wherein the sample contains at least one of the parameters having random variations, wherein the parameter contains dust, bubbles, non-sample material, or any combination thereof.

[0033] In some embodiments, the method of any one of the preceding embodiments, wherein the assay is a cellular assay, an immunoassay, a nucleic acid assay, a colorimetric assay, a luminescent assay, or any combination thereof.

[0034] In some embodiments, the method as described in any of the preceding embodiments, wherein the assay device comprises two plates facing each other with a gap, and at least a portion of the sample is within the gap.

[0035] In some embodiments, the method of any of the preceding embodiments, wherein the assay device comprises a QMAX comprising two plates movable relative to each other and a spacer to adjust the spacing between the plates.

[0036] In some embodiments, the method as in any of the preceding embodiments, wherein some of the monitoring structures are arranged at fixed intervals.

[0037] In some embodiments, the method as described in any of the preceding embodiments, wherein the sample is selected from cells, tissues, body fluids and feces.

[0038] The apparatus and method of any of the preceding claims, wherein the sample is amniotic fluid, aqueous humor, vitreous humor, blood (e.g., whole blood, fractionated blood, plasma, serum), breast milk, cerebrospinal fluid (CSF), cerumen (ear wax), chyle, chyme, endolymph, perilymph, feces, gastric acid, gastric juice, lymph, mucus (including nasal drainage and sputum), pericardial fluid, peritoneal fluid, pleural fluid, pus, rheumatic fluid, saliva, sebum (skin oil), semen, sputum, sweat, synovial fluid, tears, vomitus, urine, or exhaled condensate.

[0039] The apparatus and method of any of the preceding claims, wherein the analyte comprises molecules (eg, proteins, peptides, DNA, RNA, nucleic acids or other molecules), cells, tissues, viruses and nanoparticles.

[0040] Apparatus and method as claimed in any preceding claim, wherein the sample is a non-flowable but deformable sample.

[0041] The apparatus and method of any of the preceding claims, wherein the algorithm is machine learning, artificial intelligence, statistical methods or a combination thereof.

[0042] The apparatus and method as in any of the preceding embodiments, wherein the spacers are the monitoring marks, wherein the spacers have a substantially uniform height equal to or less than 200 microns and a fixed spacer spacing (ISD).

[0043] Apparatus and method as claimed in any one of the preceding claims, wherein the monitoring markers are used for estimating TLD (true lateral dimension) as well as true volume estimation.

[0044] Apparatus and method as claimed in any preceding claim, wherein step (b) further comprises image segmentation for image-based determination.

[0045] In some embodiments, the method as described in any of the preceding embodiments, wherein step (b) further comprises focus checking in an image-based assay.

[0046] In some embodiments, the method as described in any of the preceding embodiments, wherein step (b) further comprises the uniformity of the distribution of the analyte in the sample.

[0047] In some embodiments, the method as described in any of the preceding embodiments, wherein step (b) further comprises analyzing and detecting aggregated analytes in the sample.

[0048] In some embodiments, the method as described in any of the preceding embodiments, wherein step (b) further comprises analyzing the dry texture structure in the image of the sample.

[0049] In some embodiments, the method as described in any of the preceding embodiments, wherein step (b) further comprises analyzing defects in the sample.

[0050] In some embodiments, the method as described in any of the above embodiments, wherein step (b) further comprises correction of camera parameters and conditions such as distortion elimination, temperature correction, brightness correction, and contrast correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Those skilled in the art will appreciate that the drawings described below are for illustrative purposes only. The drawings are not intended to limit the scope of the present invention in any way. The drawings are not drawn to scale. In the drawings where experimental data points are given, the lines connecting the data points are only used to guide the observation of the data and have no other purpose.

[0052] Figure 1 A flow chart showing an image-based assay using a special sample holder is shown.

[0053] Figure 2 Shown are side and top views of a sample holder Q card with monitoring marker posts.

[0054] Figure 3 A block diagram with parallel credible risk estimation is shown.

[0055] Figure 4 The control flow of an imaging-based assay with credible risk estimates is shown.

[0056] Figure 5 A flow chart of true lateral dimension correction using a machine learning model trained for pillar detection is shown.

[0057] Figure 6 A flow chart for training a machine learning (ML) model for detecting pillars from an image of a sample is shown.

[0058] Figure 7 A schematic diagram showing the relationship between training a machine learning model and applying the trained machine learning model in prediction (inference) is shown.

[0059] Figure 8 A schematic diagram showing defects (such as dust, bubbles, etc.) that may appear in the sample.

[0060] Fig. 9 A real image from a blood test is shown with defects in the sample image used for the assay.

[0061] Fig.10 Defect detection and segmentation are shown on images of samples using the described method.

[0062] Fig.11 shows an autofocus diagram in photomicrography;

[0063] Fig.12 A schematic diagram showing distortion cancellation with known distortion parameters is shown;

[0064] Fig.13 A schematic diagram showing distortion removal and camera adjustment in the case of unknown distortion parameters is shown;

[0065] Fig.14 The distorted position of the monitoring marker post in the sample image due to the distortion of the imager is shown. DETAILED DESCRIPTION

[0066] The following detailed description illustrates some embodiments of the present invention by way of example and not limitation. The section headings and any subtitles used herein are for organizational purposes only and should not be interpreted as limiting the subject matter described in any way. The content under the section headings and / or subheadings is not limited to the section headings and / or subheadings, but applies to the entire description of the present invention.

[0067] The citation of any publication is for its disclosure prior to the filing date and should not be construed as an admission that the present claims are not entitled to antedate such publication by virtue of prior invention. Further, the publication dates provided may be different from the actual publication dates which may need to be independently confirmed.

[0068] The terms "confidence", "risk of error", "error risk factor" and "risk factor" are interchangeable terms to describe the likelihood that a test result is inaccurate. More "confidence" means less "likelihood" (i.e., less risk), and therefore a lower "risk factor".

[0069] The terms "instructions" and "algorithm" are interchangeable.

[0070] The term "imaging-based assay" refers to an assay that comprises an imager for detecting an analyte in a sample.

[0071] Improve measurement accuracy by checking the confidence of test results

[0072] Example of a reliability-based test report to improve test accuracy. In many assay situations, there are random variations in the assay operation, sample handling, and other processes associated with the assay operation, and these random variations can affect the test result accuracy of the assay.

[0073] According to the present invention, monitoring structures for monitoring the operating parameters of the assay are placed on the sample holder (in some embodiments, in the area of ​​the sample being tested). Figure 1 In the example shown in the flowchart of , during the test, both the analyte in the sample and the monitoring structure are measured (in parallel or sequentially), and the confidence of the analyte measurement is determined from the monitoring structure measurement by instructions (a non-transitory storage medium storing the instructions). If the confidence is above a threshold (i.e., the risk factor is below a threshold), the analyte measurement result will be reported, otherwise the analyte measurement result will not be reported.

[0074] If no analyte measurement result is reported due to poor confidence (above a threshold), optionally, a second sample and / or second test will be tested in the same manner as in the first sample and / or first test. If the second sample and / or second test still has poor confidence, a third sample and / or third test will be performed. This process can continue until a reliable analyte measurement result is reported.

[0075] Examples of monitoring structures include, but are not limited to, spacers, scale marks, imaging marks, and position marks on a Q card (ie, a QMAX card). Figure 2 is a schematic diagram of a sample holder Q card. Monitoring parameters include, but are not limited to, monitoring the image of the structure, light transmission, light scattering, color (wavelength spectrum), polarization, etc. Monitoring parameters also include the sample image on the Q card. Determining whether the instruction is credible or not can be determined by testing under various conditions that deviate from ideal conditions. In some embodiments, machine learning is used to learn how to determine a credibility threshold.

[0076] In some embodiments, the monitored parameters are related to sample holder operation and conditions, sample conditions, or reagent conditions, or measurement instrument conditions.

[0077] A method for improving the accuracy of a test result of an assay, the method comprising:

[0078] having a sample holder with monitoring markings;

[0079] having a sample on a sample holder, wherein the sample is suspected of containing an analyte;

[0080] measuring the analyte in parallel or sequentially to produce an analyte measurement result (i.e., a test result), and measuring the monitoring marker to produce a monitoring parameter;

[0081] Use instructions and monitoring parameters to determine the confidence of analyte measurement results;

[0082] Determine the publication of analyte measurement results.

[0083] Figure 3 A schematic diagram of an assay with a credibility check is shown, and in some embodiments, the analyte measurement result is published only when the credibility is high (risk factor is low). In some embodiments, when the credibility is low, the analyte measurement result will not be published. In some embodiments, when the credibility is low, the analyte measurement result of the first sample will not be published, and the second sample will be used to undergo the same process as described above. In some embodiments, the process is repeated until a high credibility analyte measurement result is obtained.

[0084] A device for improving test accuracy by measuring monitoring parameters comprises: a sample card with a monitoring structure, an imager and a medium storing instructions for determining the reliability of test results.

[0085] Examples of methods and devices for mobile assays (using QMAX cards) - concentration estimation (CBC), segmentation, etc. using image processing and machine learning.

[0086] AA-1. A method for correcting systematic errors of an imaging system containing a thin layer of a sample, the method comprising:

[0087] receiving, by a processing device of the imaging system, an image associated with a sample card containing a sample and a monitoring standard and a first parameter;

[0088] determining, by the processing device, a systematic error of the imaging system using a first machine learning model by comparing a first parameter to a second parameter associated with a monitoring standard determined during manufacture of the sample card;

[0089] Correcting, by a processing device, the image of the sample card to account for systematic errors; and

[0090] The corrected image is used by a processing device to determine a biological characteristic of the sample.

[0091] AA-2. The method of example AA-1, wherein the monitoring standard comprises a plurality of nanostructures on a plate of the sample card, and wherein the sample is deposited on the plate.

[0092] AA-3. A method as described in Example AA-1, wherein the sample is a biological sample collected from an animal.

[0093] Figure 5 A flow chart is shown for true lateral dimension (TLD) estimation using pillars and image correction from Q-card imaging using markers (pillars).

[0094] BA-1. An intelligent measurement and monitoring method, comprising:

[0095] receiving, by a processing device, an image encoding first information of a biological sample deposited in a sample card and second information of a plurality of monitoring tags;

[0096] executing, by a processing device, a first machine learning model on the image to determine measurements of geometric features associated with a plurality of monitoring markers;

[0097] determining, by the processing device, a change between the measured value of the geometric feature and a ground truth value of the geometric feature provided by the sample card;

[0098] correcting, by the processing device, the image encoding the first information and the second information based on the change; and

[0099] The corrected image is used by a processing device to determine a biological characteristic of the biological sample.

[0100] BA-2. A method as described in example BA-1, wherein the sample card comprises a first plate, a plurality of columns integrated substantially vertically to a surface of the first plate, and a second plate capable of surrounding the first plate to form a thin layer, wherein the biological sample is deposited in the thin layer.

[0101] BA-3. A method as described in Example BA-2, wherein multiple monitoring markers correspond to multiple columns.

[0102] BA-4. A method as described in Example BA-3, wherein at least two of the plurality of columns are separated by a true lateral dimension (TLD), and wherein measurements of geometric features associated with the plurality of monitoring markers are determined by executing a first machine learning model on the image by a processing device, the measurements including determining the TLD by the processing device executing the first machine learning model on the image.

[0103] Figure 6 A flow chart for training a machine learning model for column detection in TLD correction using monitoring marker columns is shown. Figure 7 The relationship between training a machine learning model and applying the trained machine learning model in prediction (inference) is shown.

[0104] BB-1 is an imaging system that includes:

[0105] A sample card comprising a first plate, a plurality of posts integrated substantially vertically to a surface of the first plate, and a second plate capable of surrounding the first plate to form a thin layer, wherein the biological sample is deposited in the thin layer;

[0106] A computing device comprising:

[0107] A processing device communicatively coupled to the optical sensor to:

[0108] receiving an image encoding first information of a biological sample deposited in a sample card and second information of a plurality of monitoring tags from an optical sensor;

[0109] determining, using a first machine learning model for the image, measurements of geometric features associated with a plurality of monitoring markers;

[0110] determining a change between a measured value of a geometric feature and a ground truth value of the geometric feature provided by a sample card;

[0111] correcting an image encoding the first information and the second information based on the change; and

[0112] A biological characteristic of the biological sample is determined based on the corrected image.

[0113] Object detection on poles to detect incorrect card closure during assays

[0114] CA-1. A method for correcting human error recorded in a measurement image of a thin layer sample, the method comprising:

[0115] receiving, by a processing device of the imaging system, an image of a sample card comprising a sample and a monitoring standard, wherein the monitoring standard comprises a plurality of nanostructures integrated on a first plate of the sample card, and wherein the sample is deposited on the first plate of the sample card in an open configuration and surrounded by a second plate of the sample card in a closed configuration;

[0116] segmenting the image into a first sub-region corresponding to the sample and a second sub-region corresponding to the plurality of nanostructures by a processing device;

[0117] comparing, by the processing device, the second sub-regions with a monitoring standard provided during manufacture of the sample to determine whether at least one of the second sub-regions contains foreign objects other than nanostructures;

[0118] In response to determining that at least one of the second sub-regions contains foreign objects other than nanostructures, determining an error associated with operating the sample card; and

[0119] The image of the sample card is corrected by removing at least one sub-region from the image.

[0120] CA-2. The method of embodiment CA-1, wherein the foreign object is one of a part of the sample, a bubble, or an impurity.

[0121] Examples of defects (e.g., bubbles, dust, etc.) and auxiliary structures (e.g., pillars) removed during measurement

[0122] DA-1. A method for measuring the volume of a sample in a thin layer sample card, the method comprising:

[0123] receiving, by a processing device of an imaging system, an image of a sample card comprising a sample and a monitoring standard, wherein the monitoring standard comprises a plurality of posts vertically integrated to a first plate of the sample, and each of the plurality of posts has substantially the same height (H);

[0124] determining, by a processing device, a plurality of non-sample sub-regions using a machine learning model, wherein the plurality of non-sample sub-regions correspond to at least one of pillars, bubbles, or impurity elements;

[0125] calculating, by the processing means, an area occupied by the sample by removing a plurality of non-sample sub-regions from the image;

[0126] calculating, by a processing device, the volume of the sample based on the calculated area and height (H), and

[0127] A biological characteristic of the sample is determined based on the volume by a processing device.

[0128] Example of determining the confidence level of a measurement result

[0129] a. Shape segmentation combining ML-based bounding box detection and image processing-based shape determination

[0130] b. Uniformity of analyte detection in the assay (IQR-based outlier detection)

[0131] c. Aggregated analyte detection using ML

[0132] d. Dry texture structure on the card using ML

[0133] e. Use ML to detect defects such as dust, oil, etc.

[0134] f. Bubble detection using ML

[0135] EA-1. A method for determining the confidence of a measurement associated with an image measurement result, the method comprising:

[0136] receiving, by a processing device of an imaging system, an image of a sample card comprising a sample and a monitoring standard comprising a plurality of nanostructures integrated into a first plate of the sample;

[0137] segmenting the image into a first sub-region corresponding to the sample and a second sub-region corresponding to the plurality of nanostructures by a processing device;

[0138] determining, by the processing device, a noncompliant element in at least one of the first sub-region or the second sub-region using the first machine learning model;

[0139] determining, by a processing device, a biological characteristic of the sample based on the first sub-region and the second sub-region;

[0140] calculating, by the processing device, a confidence measure associated with the biological characteristic based on a statistical analysis of the non-compliant elements; and

[0141] Further action on the sample is determined by the processing device based on the confidence measure.

[0142] EA-2. The method of Example EA-1, further comprising:

[0143] determining, by the processing device, that the biological characteristic is reliable based on the confidence measure; and

[0144] The biological characteristic is provided to the display device by the processing device.

[0145] EA-3. The method of Example EA-1, further comprising:

[0146] determining, by the processing device based on the confidence measure, that the biological characteristic is not reliable; and

[0147] The biological characteristic and the corresponding confidence measure are provided to the display means by the processing means to allow the user to determine whether to accept or reject the biological characteristic.

[0148] EA-4. The method of Example EA-1, wherein the image is segmented into a first sub-region corresponding to the sample and a second sub-region corresponding to the plurality of nanostructures by a processing device;

[0149] Performing a first image segmentation on the image by using an image processing method through a processing device to generate a first segmentation result;

[0150] Performing a second image segmentation on the image using a second machine learning model by the processing device to generate a second segmentation result; and

[0151] The first segmentation result and the second segmentation result are combined by a processing device to segment the image into a first sub-region corresponding to the sample and a second sub-region corresponding to the plurality of nanostructures.

[0152] EA-5. The method of example EA-1, wherein determining, by the processing device, using the first machine learning model, a noncompliant element in at least one of the first sub-region or the second sub-region comprises: at least one of the following

[0153] determining, by a processing device, a noncompliant element based on a distribution heterogeneity of at least one analyte in the sample;

[0154] Determining non-compliant elements by processing means based on polymerized analyte detection of the sample;

[0155] Determine the non-compliant elements based on the detection of dry texture structure in the sample by the processing device;

[0156] Determination of non-compliant elements based on detection of impurities in the sample by a processing device; or

[0157] The non-compliant element is determined by the processing device based on the detection of bubbles in the sample.

[0158] Multi-segment testing for a single card with segmentation-based content

[0159] FA-1. A method for determining measurement values ​​of multiple analytes using a single sample card, the method comprising:

[0160] receiving, by a processing device of an imaging system, an image of a sample card comprising a sample and a monitoring standard, wherein the monitoring standard comprises a plurality of nanostructures integrated into a first plate of the sample;

[0161] segmenting, by a processing device, the image into a first sub-region associated with a first analyte contained in the sample, a second region associated with a second analyte contained in the sample, and a third sub-region corresponding to a plurality of nanostructures using a first machine learning model;

[0162] determining, by a processing device, a true lateral distance (TLD) between two adjacent nanostructures based on a third sub-region corresponding to the plurality of nanostructures;

[0163] determining, by a processing device, a first cumulative area of ​​the first sub-region based on the TLD, and further determining a first volume based on the first cumulative area and heights associated with the plurality of nanostructures;

[0164] determining, by the processing device, a second cumulative area of ​​the sub-region based on the TLD, and further determining a second volume based on the second cumulative area and heights associated with the plurality of nanostructures;

[0165] determining, by the processing device, a first measurement of the first analyte based on the count of the first analyte in the first volume; and

[0166] A second measurement of the second analyte is determined by the processing device based on the count of the second analyte in the second volume.

[0167] Column-based spectrophotometer systems and devices

[0168] GA-1. A method for measuring a biological property of a sample provided in a sample card comprising a plurality of nanopillars, the method comprising:

[0169] receiving, by a processing device of an imaging system, an image of a sample card comprising a sample and a monitoring standard comprising a plurality of nanostructures integrated into a first plate of the sample;

[0170] Segmenting the image into a first sub-region corresponding to the sample and a second sub-region corresponding to the plurality of nanorods by a processing device;

[0171] determining, by the processing device, a first spectrophotometric measurement value of the first sub-region;

[0172] determining, by the processing device, a second spectrophotometric measurement of the second sub-region; and

[0173] A biological characteristic of the sample is determined by the processing device based on a ratio between the first spectrophotometric measurement and the second spectrophotometric measurement.

[0174] GA-2. A method for analyzing the concentration of a compound using a measured response of the compound at a specific wavelength of light or multiple wavelengths of light, the method comprising:

[0175] receiving, by a processing device of an imaging system, an image or images captured on a sample card having a specific or multiple wavelengths of light, wherein the sample card comprises a sample and a monitoring standard, the monitoring standard comprising a plurality of nanostructures integrated into a first plate of the sample;

[0176] segmenting each image into a first sub-region corresponding to the sample and a second sub-region corresponding to the plurality of nanorods by a processing device;

[0177] determining the absorption of light at a first sub-region of the sample from images of the sample taken at different wavelengths;

[0178] determining the absorption of light at the second sub-region from the nanorods from images of the sample taken at different wavelengths; and

[0179] The compound concentration is determined from light absorption measurements of the two sub-regions at one or more wavelengths.

[0180] Furthermore, in some embodiments of the present invention, the detection and segmentation of each image into a first sub-region corresponding to the sample and a second sub-region corresponding to a plurality of nanopillars is based on a machine learning model trained on a sample of training images with labeled nanopillars.

[0181] Marking large numbers of small, repeated objects

[0182] HA-1. A method for labeling a plurality of objects in an image to prepare training data, the method comprising:

[0183] receiving, by a processing device, an image in a graphical user interface;

[0184] receiving, by the processing device via the graphical user interface, a selection of a location in the image;

[0185] calculating, by a processing device, a bounding box surrounding the location based on a plurality of pixels local to the location;

[0186] providing, by the processing device, display of the bounding box superimposed on the image in a graphical user interface; and

[0187] In response to receiving the user confirmation, the area within the bounding box is marked as training data.

[0188] IA-1. A method for preparing an assay image, the method comprising:

[0189] Providing a sample card containing multiple marker elements;

[0190] depositing a sample on a first plate of a sample card in an open configuration;

[0191] closing the sample card to press the second panel of the sample card against the first panel to form a closed configuration, wherein the first panel and the second panel in the closed configuration form a thin layer having a substantially uniform thickness including the sample and the plurality of marker elements; and

[0192] An imaging system is provided, comprising a processing device and a non-transitory storage medium storing instructions, which when executed by the processing device will:

[0193] capturing an image of the sample card, the image comprising a substantially uniform thickness of the sample and the plurality of marker elements;

[0194] detecting multiple marker elements in an image;

[0195] comparing the detected plurality of marker elements to a monitoring standard associated with the sample card to determine a geometric mapping between the plurality of marker elements and the monitoring standard;

[0196] determining non-ideal factors of the imaging system based on the geometric mapping; and processing the image of the sample card to correct for the non-ideal factors.

[0197] IB-1. A method for preparing an assay image, the method comprising:

[0198] Providing a sample card containing multiple marker elements;

[0199] depositing a sample on a first plate of a sample card in an open configuration;

[0200] closing the sample card to press the second panel of the sample card against the first panel to form a closed configuration, wherein the first panel and the second panel in the closed configuration form a thin layer having a substantially uniform thickness including the sample and the plurality of marker elements; and

[0201] An imaging system is provided, comprising a processing device and a non-transitory storage medium storing instructions, which when executed by the processing device will:

[0202] capturing an image of the sample card, the image comprising a substantially uniform thickness of the sample and the plurality of marker elements;

[0203] Segment the image into multiple sub-regions;

[0204] determining whether each of the plurality of sub-regions meets the requirements of the imaging system using a machine learning model and a plurality of marker elements;

[0205] In response to determining that the sub-region does not comply with the requirement, marking the first sub-region as noncompliant;

[0206] In response to determining that the sub-region meets the requirement, marking the first sub-region as compliant; and

[0207] Perform assay analysis using the compliant sub-region of the image.

[0208] IC-1. A method for correcting non-ideal factors of an image system, the method comprising:

[0209] receiving, by a processing device of the imaging system, an image of the sample card, the image comprising a substantially uniform layer of sample deposited on a plate of the sample card and a plurality of marker elements associated with the sample card;

[0210] detecting, by a processing device, a plurality of marker elements in the image;

[0211] comparing the detected plurality of marker elements to a monitoring standard associated with the sample card to determine a geometric mapping between the plurality of marker elements and the monitoring standard;

[0212] determining non-ideality factors of the image system based on the geometric mapping; and

[0213] The image of the sample card is processed to correct for non-ideality factors.

[0214] ID-1. A method for correcting non-ideal factors of an image system, the method comprising:

[0215] receiving, by a processing device of the imaging system, an image of a sample card comprising a substantially uniform layer of sample deposited on a plate of the sample card and a plurality of marker elements associated with the sample card;

[0216] dividing the image into a plurality of sub-regions by a processing device;

[0217] determining, by a processing device, using the machine learning model and the plurality of marker elements, whether each of the plurality of sub-regions meets requirements of the imaging system;

[0218] In response to determining that the sub-region does not comply with the requirement, marking, by the processing device, the first sub-region as noncompliant;

[0219] In response to determining that the sub-region meets the requirement, marking, by the processing device, the first sub-region as compliant; and

[0220] A determination analysis is performed by the processing device using the compliance sub-region of the image.

[0221] IE-1. An image system comprising:

[0222] an adapter for holding a sample card, the sample card comprising a first plate, a second plate, and a plurality of marker elements;

[0223] A mobile computing device coupled to the adapter, the mobile computing device comprising:

[0224] an optical sensor for capturing an image of the plurality of marker elements and the sample card, the image comprising a substantially uniform layer of sample deposited between the first plate and the second plate of the sample card;

[0225] A processing device communicatively coupled to the optical sensor to:

[0226] receiving an image captured by an optical sensor;

[0227] detecting multiple marker elements in an image;

[0228] comparing the detected plurality of marker elements to a monitoring standard associated with the sample card to determine a geometric mapping between the plurality of marker elements and the monitoring standard;

[0229] determining non-ideality factors of the image system based on the geometric mapping; and

[0230] The image of the sample card is processed to correct for non-ideality factors.

[0231] IF-1. An imaging system comprising:

[0232] an adapter for holding a sample card, the sample card comprising a first plate, a second plate, and a plurality of marker elements;

[0233] A mobile computing device coupled to the adapter, the mobile computing device comprising:

[0234] an optical sensor for capturing an image of the plurality of marker elements and the sample card, the image comprising a substantially uniform layer of sample deposited between the first plate and the second plate of the sample card;

[0235] A processing device communicatively coupled to the optical sensor to:

[0236] receiving an image captured by an optical sensor;

[0237] Segment the image into multiple sub-regions;

[0238] determining whether each of the plurality of sub-regions meets the requirements of the imaging system using a machine learning model and a plurality of marker elements;

[0239] In response to determining that the sub-region does not comply with the requirement, marking the first sub-region as noncompliant;

[0240] In response to determining that the sub-region meets the requirement, marking the first sub-region as compliant; and

[0241] Perform assay analysis using the compliant sub-region of the image.

[0242] IG-1. A mobile imaging device comprising:

[0243] Optical sensors; and

[0244] A processing device communicatively coupled to the optical sensor to:

[0245] receiving an image captured by the optical sensor, the image comprising a plurality of marker elements and a substantially uniform layer of sample deposited between the first plate and the second plate of the sample card;

[0246] detecting multiple marker elements in an image;

[0247] comparing the detected plurality of marker elements to a monitoring standard associated with the sample card to determine a geometric mapping between the plurality of marker elements and the monitoring standard;

[0248] determining non-ideality factors of the image system based on the geometric mapping; and

[0249] The image of the sample card is processed to correct for non-ideality factors.

[0250] IH-1. A mobile imaging device, comprising:

[0251] Optical sensors; and

[0252] A processing device communicatively coupled to the optical sensor to:

[0253] receiving an image captured by the optical sensor, the image comprising a plurality of marker elements and a substantially uniform layer of sample deposited between the first plate and the second plate of the sample card;

[0254] Segment the image into multiple sub-regions;

[0255] determining whether each of the plurality of sub-regions meets the requirements of the imaging system using a machine learning model and a plurality of marker elements;

[0256] In response to determining that the sub-region does not comply with the requirement, marking the first sub-region as noncompliant;

[0257] In response to determining that the sub-region meets the requirement, marking the first sub-region as compliant; and

[0258] Perform assay analysis using the compliant sub-region of the image.

[0259] II-1. An intelligent measurement and monitoring method, comprising:

[0260] receiving, by a processing device, an image encoding first information of a biological sample deposited in a sample card and second information of a plurality of monitoring tags;

[0261] executing, by a processing device, a first machine learning model on the image to determine measurements of geometric features associated with a plurality of monitoring markers;

[0262] determining, by the processing device, a change between the measured value of the geometric feature and a ground truth value of the geometric feature provided by the sample card;

[0263] correcting, by the processing device, the image encoding the first information and the second information based on the change; and

[0264] The corrected image is used by a processing device to determine a biological characteristic of the biological sample.

[0265] II-2. A method as described in Example II-1, wherein the sample card comprises a first plate, a plurality of columns integrated substantially vertically to a surface of the first plate, and a second plate capable of surrounding the first plate to form a thin layer, wherein the biological sample is deposited in the thin layer.

[0266] II-3. The method of claim II-2, wherein a plurality of monitoring markers correspond to a plurality of columns.

[0267] II-4. The method of claim II-2, wherein a plurality of monitoring marks are disposed in at least one of the first plate or the second plate.

[0268] II-5. The method of example II-1, wherein executing a first machine learning model on an image by a processing device to determine a measurement of geometric features associated with a plurality of monitoring markers further comprises:

[0269] executing, by the processing device, a first machine learning model to identify a plurality of monitoring markers from the image; and

[0270] A measurement of the geometric feature is determined by a processing device based on the identified plurality of monitoring markers.

[0271] II-6. The method of claim II-1, wherein determining by the processing device the change between the measured value of the geometric feature and the ground truth value of the geometric feature provided by the sample card further comprises:

[0272] determining, by the processing device, one of a system error or a human operator error; and

[0273] A determination of one of a system error or a human operator error is presented on a display device associated with the processing device.

[0274] II-7. An imaging system comprising:

[0275] A sample card comprising a first plate, a plurality of posts integrated substantially vertically to a surface of the first plate, and a second plate capable of surrounding the first plate to form a thin layer, wherein the biological sample is deposited in the thin layer;

[0276] A computing device comprising:

[0277] A processing device communicatively coupled to the optical sensor to:

[0278] receiving an image encoding first information of a biological sample deposited in a sample card and second information of a plurality of monitoring tags from an optical sensor;

[0279] determining, using a first machine learning model for the image, measurements of geometric features associated with a plurality of monitoring markers;

[0280] determining a change between a measured value of a geometric feature and a ground truth value of the geometric feature provided by a sample card;

[0281] correcting an image encoding the first information and the second information based on the change; and

[0282] A biological characteristic of the biological sample is determined based on the corrected image.

[0283] IJ-1. A method for correcting non-ideal factors in a measurement image of a thin layer sample, the method comprising:

[0284] providing a sample card comprising a monitoring standard, the monitoring standard comprising a plurality of nanostructures on a plate of the sample card;

[0285] depositing a sample onto a plate of a sample card; and

[0286] An imaging system is provided, the imaging system comprising a processing device and a non-transitory storage medium storing instructions, the instructions when executed by the processing device will:

[0287] capturing an image of a sample card containing a sample and a monitoring standard;

[0288] determining a non-ideality factor of the imaging system by comparing an image of the sample card to a plurality of geometric values ​​of a monitoring standard determined during manufacture of the sample card; and

[0289] The image of the sample card is corrected to take into account non-ideal factors.

[0290] IJ-2. A method for correcting non-ideal factors in a measurement image of a thin layer sample, the method comprising:

[0291] receiving, by a processing device of the imaging system, an image of a sample card comprising a sample and a monitoring standard, wherein the monitoring standard comprises a plurality of nanostructures on a plate of the sample card, and wherein the sample is deposited on the plate;

[0292] determining, by the processing device, a non-ideality factor of the imaging system by comparing the image of the sample card to a plurality of geometric values ​​of the monitoring standard determined during manufacture of the sample card; and

[0293] The image of the sample card is corrected to take into account non-ideal factors.

[0294] IJ-3. A method for correcting non-ideal factors in a measurement image of a thin layer sample, the method comprising:

[0295] receiving, by a processing device of the imaging system, an image of a sample card comprising a sample and a monitoring standard, wherein the monitoring standard comprises a plurality of nanostructures on a plate of the sample card, and wherein the sample is deposited on the plate;

[0296] determining, by the processing device, a non-ideality factor of the image system using a machine learning model, wherein the machine learning model is trained by comparing images of the sample card to geometric values ​​of monitoring standards determined during manufacture of the sample card; and

[0297] The image of the sample card is corrected to take into account non-ideal factors.

[0298] IJ-4. A mobile imaging device, comprising:

[0299] Optical sensors; and

[0300] A processing device communicatively coupled to the optical sensor to:

[0301] receiving an image of a sample card comprising a sample and a monitoring standard, wherein the monitoring standard comprises a plurality of nanostructures on a plate of the sample card, and wherein the sample is deposited on the plate;

[0302] determining a non-ideality factor of the mobile imaging system by comparing an image of the sample card to a plurality of geometric values ​​of a monitoring standard determined during manufacture of the sample card; and

[0303] The image of the sample card is corrected to take into account non-ideal factors.

[0304] IJ-5. An imaging system comprising:

[0305] an adapter for holding a sample card comprising a monitoring standard, wherein the monitoring standard comprises a plurality of nanostructures on a plate of the sample card, and wherein the sample is deposited on the plate;

[0306] A mobile computing device coupled to the adapter, the mobile device comprising:

[0307] Optical sensors; and

[0308] A processing device communicatively coupled to the optical sensor to:

[0309] receiving an image of a sample card;

[0310] determining a non-ideality factor of the imaging system by comparing an image of a sample card containing the sample deposited on the plate to a plurality of geometric values ​​of a monitoring standard determined during manufacture of the sample card; and

[0311] The image of the sample card is corrected to take into account non-ideal factors.

[0312] IJ-6. A sample card comprising:

[0313] A monitoring standard comprising a plurality of nanostructures on a plate of a sample card, wherein a sample is deposited on the plate, and wherein the sample card is inserted into an adapter coupled to an imaging system, the imaging system comprising a processing device and an optical sensor for capturing an image of the sample card, the processing device for:

[0314] receiving an image of a sample card;

[0315] determining a non-ideality factor of the imaging system by comparing an image of a sample card containing the sample deposited on the plate to a plurality of geometric values ​​of a monitoring standard determined during manufacture of the sample card; and

[0316] The image of the sample card is corrected to take into account non-ideal factors.

[0317] IJ-7. A method for correcting systematic errors of an imaging system containing a thin layer of a sample, the method comprising:

[0318] receiving, by a processing device of the imaging system, an image and a first parameter associated with a sample card comprising a sample and a monitoring standard, wherein the monitoring standard comprises a plurality of nanostructures on a plate of the sample card, and wherein the sample is deposited on the plate;

[0319] determining, by the processing device, a systematic error of the imaging system by comparing the first parameter to a second parameter associated with the monitoring standard determined during manufacture of the sample card;

[0320] The image of the sample card is corrected to take into account systematic errors.

[0321] IJ-8. A method for correcting human error recorded in a measured image of a thin layer sample, the method comprising:

[0322] receiving, by a processing device of the imaging system, an image of a sample card comprising a sample and a monitoring standard, wherein the monitoring standard comprises a plurality of nanostructures on a plate of the sample card, and wherein the sample is deposited on the plate;

[0323] determining, by a processing device using a machine learning model, a human operator error reflected in the image by comparing the image of the sample card to a plurality of geometric values ​​of a monitoring standard determined during manufacture of the sample card, wherein the human operator error comprises erroneous processing of the imaging system; and

[0324] Correct the image of the sample card by removing human operating errors reflected in the image.

[0325] Monitoring and correction of measuring device operating errors

[0326] A method of monitoring and correcting errors occurring in operating an assay device, comprising:

[0327] (a) Q-CARD with monitoring markers on the plate (inside the sample);

[0328] (b) performing sample deposition,

[0329] (c) imaging the monitoring marker using an imager during the measurement;

[0330] (d) determining the operation error by comparing the image of the monitoring mark with the ideal image of the monitoring mark;

[0331] The ideal image of the monitoring mark is the image of the monitoring mark when the operation is performed correctly;

[0332] The monitoring markers are prefabricated.

[0333] A method of monitoring defects in an operating assay device, comprising:

[0334] (a) Q-CARD with monitoring markers on the plate (inside the sample);

[0335] (b) performing sample deposition,

[0336] (c) imaging the monitoring marker using an imager during the measurement;

[0337] (d) determining the operation error by comparing the image of the monitoring mark with the ideal image of the monitoring mark;

[0338] The ideal image of the monitoring mark is the image of the monitoring mark when the operation is performed correctly;

[0339] The monitoring markers are prefabricated.

[0340] OA-1 In some embodiments of the present invention, a method for improving the accuracy of an assay having one or more unpredictable and random operating conditions comprises:

[0341] (a) detecting an analyte in a sample containing or suspected of containing the analyte, comprising:

[0342] (i) feeding the sample into the detection instrument, and

[0343] (ii) measuring the sample using a detection instrument to detect the analyte and generate a detection result of the detection;

[0344] (B) determining the credibility of the test result in step (a), comprising:

[0345] (i) capturing one or more images of (1) a portion of the sample and / or (2) a portion of a detection instrument surrounding the portion of the sample, wherein the images substantially represent the conditions under which the portion of the sample was measured when the detection result was generated in step (a); and

[0346] (ii) analyzing the image captured in step (b)(i) using a computing device having an algorithm to determine the reliability of the detection result in step (a); and

[0347] (c) reporting both test results and confidence levels;

[0348] Wherein step (a) has one or more unpredictable and random operating conditions.

[0349] In some embodiments, method OA-1 further comprises the following step: if the confidence level determined in step (b) is lower than a threshold, discarding the detection result generated in step (a).

[0350] In some embodiments, method OA-1 further comprises the step of modifying the detection result generated in step (a) if the confidence level determined in step (b) is lower than a threshold.

[0351] OA-2. An apparatus for improving the accuracy of an assay having one or more unpredictable and random operating conditions, comprising:

[0352] (1) a detection device that detects an analyte in a sample to produce a test result, wherein the sample contains or is suspected of containing the analyte;

[0353] (2) A checking device for checking the credibility of a specific test result produced by a testing device, comprising:

[0354] (i) an imager capable of capturing one or more images of (1) a portion of the sample and / or (2) a portion of a detection instrument surrounding the portion of the sample, wherein the images substantially represent the conditions under which the portion of the sample was measured when the detection result was generated in step (a); and

[0355] (ii) a computing unit having an algorithm capable of analyzing features in the image captured in step (b)(i) to determine the confidence level of the detection result;

[0356] (c) if step (b) determines that the test result is unreliable, discarding the test result generated in step (a);

[0357] Wherein step (a) has one or more unpredictable and random operating conditions.

[0358] In some embodiments, the algorithm in OA-1 is machine learning, artificial intelligence, statistical methods, etc. or a combination thereof.

[0359] The term "operating conditions" when performing a measurement refers to the conditions under which the measurement is performed. Operating conditions include, but are not limited to, at least three categories: (1) sample-related defects, (2) sample holder-related defects, and (3) measurement process-related defects. The term "defect" refers to deviations from ideal conditions.

[0360] Examples of sample-related defects include, but are not limited to, bubbles in the sample, dust in the sample, foreign objects (i.e., objects that did not come from the original sample but entered the sample later), dry texture in the sample where a portion of the sample has dried out, insufficient sample, incorrect sample, no sample, sample with an incorrect matrix (e.g., blood, saliva), reagents that react incorrectly with the sample, sample with an incorrect detection range, sample with incorrect signal uniformity, sample with incorrect distribution, sample holder with incorrect sample position (e.g., blood cells under a spacer), etc.

[0361] Examples of defects related to sample holders include, but are not limited to, missing spacers in the sample holder, sample holder not closed properly, damaged sample holder, contaminated sample holder surface, reagents on the sample not prepared properly, sample holder in an incorrect position, sample holder having incorrect spacer height, large surface roughness, incorrect transparency, incorrect absorbance, no sample holder, sample holder having incorrect optical properties, sample holder having incorrect electrical properties, incorrect geometry (size), thickness of the sample holder, etc.

[0362] Examples of defects associated with the measurement process include, but are not limited to, light intensity, camera conditions, unfocused samples in the image captured by the imager, temperature of the light, color of the light, leakage of ambient light, distribution of light, lens conditions, filter conditions, optical component conditions, electrical component conditions, assembly conditions of the instrument, relative position of the sample, sample holder and instrument, etc.

[0363] A. Thin layer sample on solid phase.

[0364] A1. A method for measuring a sample having one or more operating conditions that are random and unpredictable, comprising:

[0365] (a) providing a sample containing or suspected of containing an analyte;

[0366] (b) depositing the sample onto a solid surface;

[0367] (c) measuring the sample after step (b) to detect the analyte and produce a result of the detection, wherein the result is achieved by one or more operating conditions when performing the assay, and wherein the operating conditions are random and unpredictable;

[0368] (d) imaging a portion of the sample area / volume at which the analyte in the sample was measured in step (c); and

[0369] (e) determining a probability of error risk of the result measured in step (c) by analyzing one or more operating conditions shown in the one or more images generated in step (d).

[0370] Furthermore, if step (e) determines that the result measured in step (c) has a high probability of error risk, the result will be discarded.

[0371] AD1. A device for determining an analyte present in a sample under one or more operating variables, comprising:

[0372] (a) a solid surface having a sample contact area for receiving a thin layer of a sample containing an analyte to be measured;

[0373] (b) an imager configured to image a portion of the sample contact area to measure analyte; and

[0374] (c) A non-transitory computer readable medium having instructions which, when executed, perform a determination of the confidence level of the assay result by analyzing an operational variable displayed in an image of the portion of the sample.

[0375] B. Thin layer sample between two plates

[0376] B1. A method for measuring a sample having one or more operating variables, comprising:

[0377] (a) depositing a sample containing an analyte between a first plate and a second plate; wherein the sample is sandwiched between the first plate and the second plate which are substantially parallel;

[0378] (b) measuring an analyte contained in the sample to produce a result, wherein the measurement involves one or more random and unpredictable operating variables;

[0379] (c) imaging the area portions of the first plate and the second plate to produce an image, wherein the area portions contain the sample and measuring an analyte contained in the sample; and

[0380] (d) Determine whether the results measured in step (b) are reliable by analyzing the operating variables shown in the image of the area containing the sample.

[0381] Furthermore, if the analysis in step (d) determines that the result measured in step (b) is not plausible, the result is discarded.

[0382] C. Thin layer sample with a spacer between two plates

[0383] C1. A method for measuring a sample having one or more operating variables, comprising:

[0384] (a) depositing a sample containing or suspected of containing an analyte between a first plate and a second plate, wherein the sample is sandwiched between the first plate and the second plate, and the first plate and the second plate are movable relative to each other into a first configuration or a second configuration;

[0385] (b) measuring an analyte in a sample to produce a result, wherein the measurement involves one or more random and unpredictable operating variables;

[0386] (c) imaging a portion of the sample in which the analyte is measured; and

[0387] (d) Determine whether the results measured in step (b) are reliable by analyzing the operating variables shown in the image of the regional portion.

[0388] wherein the first configuration is an open configuration in which the two plates are partially or completely separated, the spacing between the plates is not adjusted by a spacer, and the sample is deposited on one or both of the plates; and

[0389] wherein the second configuration is a closed configuration, which is configured after the sample is deposited in an open configuration and the plates are forced to reach the closed configuration by applying an imprecise pressing force on the force area; and in the closed configuration, at least a portion of the sample is compressed by the two plates into a layer of highly uniform thickness and is essentially stagnant relative to the plates, wherein the uniform thickness of the layer is limited by the sample contact area of ​​the two plates and adjusted by the plates and spacers.

[0390] Furthermore, if step (d) determines that the result measured in step (b) is not credible, the result is discarded.

[0391] D. Reliability check of all devices described

[0392] D1. A method for measuring a sample having one or more operating variables, comprising:

[0393] (a) depositing a sample containing or suspected of containing an analyte, wherein the sample is deposited in a region in the device of any embodiment described in the present disclosure;

[0394] (b) measuring an analyte in a sample, wherein the measurement involves one or more random and unpredictable operating variables;

[0395] (c) imaging a portion of the sample area where the analyte is measured; and

[0396] (d) Determining whether the results measured in step (b) are reliable by analyzing the operating variables shown in the image of the portion of the sample.

[0397] Furthermore, if the analysis in step (d) determines that the result measured in step (b) is not plausible, the result is discarded.

[0398] E. Determination of the weight measuring device

[0399] E.1 In certain embodiments, an assay is performed using multiple assay devices, wherein the assay has a step of using image analysis to check whether the assay result is trustworthy, and wherein if a first assay device is found to be untrustworthy, a second assay device is used until the assay result is found to be trustworthy.

[0400] In some embodiments, the sample is a biological or chemical sample.

[0401] In certain embodiments, in step (d), the analysis uses machine learning with a training set to determine whether the result is plausible, wherein the training set uses manipulated variables with known analytes in the sample.

[0402] In certain embodiments, in step (d), the analysis uses a lookup table to determine whether the result is plausible, wherein the lookup table contains the manipulated variables for known analytes in the sample.

[0403] In certain embodiments, in step (d), the analysis uses a neural network to determine whether the result is plausible, wherein the neural network is trained using manipulated variables having known analytes in the sample.

[0404] In certain embodiments, in step (d), the analysis uses thresholds on the operational variables to determine whether the results are plausible.

[0405] In certain embodiments, in step (d), the analysis uses machine learning, lookup tables, or neural work to determine whether the result is credible, where the operating variables include the condition of bubbles and / or dust in the image of the portion of the sample.

[0406] In certain embodiments, in step (d), the analysis uses machine learning (which determines whether the result is credible), using machine learning, a lookup table, or a neural network to determine operating variables for bubbles and / or dust in the image of the portion of the sample.

[0407] In some embodiments, in step (b) of measuring the analyte, the measuring uses imaging.

[0408] In some embodiments, in step (b) of measuring the analyte, the measurement uses imaging, and the same image used for the analyte measurement is used for the confidence determination in step (d).

[0409] In some embodiments, in step (b) of measuring the analyte, the measurement uses imaging, and the same imager used for the analyte measurement is used for the confidence determination in step (d).

[0410] In some embodiments, the device used in A1, B1 and / or C1 further comprises a monitoring marker.

[0411] A method, apparatus, computer program product or system as described in any of the preceding embodiments, wherein the monitoring marker is used as a parameter together with an imaging processing method in an algorithm that (i) adjusts the image, (ii) processes the image of the sample, (iii) determines characteristics associated with the microfeature, or (iv) any combination of the above.

[0412] A method, apparatus, computer program product or system as described in any of the preceding embodiments, wherein the monitoring marker is used as a parameter together with step (b).

[0413] The method, apparatus, computer program product, or system of any of the preceding embodiments, wherein spacers are the monitoring marks, wherein the spacers have a substantially uniform height equal to or less than 200 microns and a fixed spacer spacing (ISD);

[0414] In some embodiments of the invention, monitoring markers are used to estimate TLD (true lateral dimension) as well as true volume estimation.

[0415] In certain embodiments, step (b) further comprises image segmentation for image-based determination.

[0416] In certain embodiments, step (b) further comprises focus checking in an image-based assay.

[0417] In certain embodiments, step (b) further comprises the uniformity of the distribution of the analyte in the sample.

[0418] In certain embodiments, step (b) further comprises analyzing and detecting aggregated analytes in the sample.

[0419] In certain embodiments, step (b) further comprises analyzing a dry texture structure in the sample in the sample image.

[0420] In certain embodiments, step (b) further comprises analyzing the sample for defects.

[0421] In some embodiments, step (b) further includes correction of camera parameters and conditions such as distortion removal, temperature correction, brightness correction, contrast correction, etc.

[0422] In some embodiments, step (b) further comprises methods and operations having histogram-based operations, mathematical-based operations, convolution-based operations, smoothing operations, derivative-based operations, and morphology-based operations.

[0423] F. System for reliability inspection

[0424] Figure 8 is a schematic diagram of possible defects (such as dust, bubbles, etc.) in the sample at the sample holder. Fig. 9 is an image of a real blood sample that contains several imperfections that occur in image-based assays.

[0425] F1. A system for measuring a sample having one or more unknown operating conditions, comprising:

[0426] a) adding the sample to a sample holding device, such as a QMAX device, whose gaps are proportional to the size of the analyte to be analyzed, or the analyte forms a monolayer between the gaps;

[0427] b) taking an image of the sample in the sample holding device over an area of ​​interest (AoI) for determination using an imager;

[0428] c) dividing the image of the sample captured by the imager from (b) into sub-image slices of equal size and non-overlapping (e.g., 8×8 small image slices of equal size);

[0429] d) performing machine learning-based inferences on analyte detection and segmentation of each image spot using the trained machine learning model to determine, but not limited to, analyte counts and their concentrations;

[0430] e) sorting the analyte concentrations of the constructed sub-image spots in ascending order, and determining the 25% quantile Q1 and the 75% quantile Q3 thereof;

[0431] f) determining the uniformity of the analyte in the sample image using a confidence measure based on the quantile range: Confidence-IQR = (Q3-Q1) / (Q3+Q1); and

[0432] g) If the confidence-IQR from (f) exceeds a certain threshold (eg, 30%), then a flag is raised and the assay result is not trustworthy, wherein the threshold is derived from training / evaluation data or from physical rules governing the distribution of the analyte.

[0433] F2. A system for measuring a sample having one or more unknown operating conditions, comprising:

[0434] a) adding the analyte to a sample holding device, such as a QMAX device, whose gaps are proportional to the size of the analyte to be analyzed, or the analyte forms a monolayer between the gaps;

[0435] b) taking an image of the sample in the sample holding device over an area of ​​interest (AoI) for determination using an imager;

[0436] c) performing machine learning based inference using the trained machine learning model for dry texture detection and segmentation to detect dry texture regions and determine the area of ​​the dry texture in the AoI associated with the segmentation contour mask of those dry texture regions in the area of ​​the image covering the sample;

[0437] d) determining the area ratio between the area of ​​the dry texture structure in the AoI and the area of ​​the AoI: Area ratio of the dry texture structure in the AoI=Area of ​​the dry texture structure in the AoI / Area of ​​the AoI; and

[0438] h) If the area fraction of dry texture from (d) AoI exceeds a certain threshold (e.g. 10%), a flag is raised and the assay result is not trustworthy, wherein the threshold is derived from training / evaluation data or from physical rules governing analyte distribution.

[0439] F3. A system for measuring a sample having one or more unknown operating conditions, comprising:

[0440] a) adding the analyte to a sample holding device, such as a QMAX device, whose gaps are proportional to the size of the analyte to be analyzed, or the analyte forms a monolayer between the gaps;

[0441] b) taking an image of the sample in the sample holding device over an area of ​​interest (AoI) for determination using an imager;

[0442] c) performing machine learning-based inferences for clustered analyte detection and segmentation using the trained machine learning model to detect clustered analytes and determine an area associated with a segmentation contour mask covering the clustered analytes in its AOI (clustered analyte area in AoI);

[0443] d) determining the area ratio between the area of ​​aggregated analyte in the AoI and the area of ​​the AoI: area ratio of aggregated analyte in the AoI=area of ​​aggregated analyte in the AoI / area of ​​the AoI; and

[0444] i) If the ratio of aggregated analyte areas from (d) AoI exceeds a certain threshold (e.g. 40%), a flag is raised and the assay result is not trustworthy, where the threshold is derived from training / evaluation data or from physical rules governing analyte distribution.

[0445] F4. A system for measuring a sample having one or more unknown operating conditions, comprising:

[0446] a) adding the analyte to a sample holding device, such as a QMAX device, whose gaps are proportional to the size of the analyte to be analyzed, or the analyte forms a monolayer between the gaps;

[0447] b) taking an image of the sample in the sample holding device over an area of ​​interest (AoI) for determination using an imager;

[0448] c) performing machine learning-based inference using the trained machine learning model for detecting and segmenting defects in an image of a sample, wherein the defects include (but are not limited to) dust, oil, etc., thereby detecting the defects and determining an area associated with a segmentation contour mask covering the defect in its AoI (defect area in AoI);

[0449] d) determining the ratio of the defect area in the AoI to the area of ​​the AoI: defect area ratio in the AoI = defect area in the AoI / area of ​​the AoI; and

[0450] e) If the defect area ratio in the AoI from (d) exceeds a certain threshold (e.g. 15%), then a flag is raised and the assay result is not trustworthy, where the threshold is derived from training / evaluation data or from physical rules governing analyte distribution.

[0451] F5. A system for measuring a sample having one or more unknown operating conditions, comprising:

[0452] a) adding the analyte to a sample holding device, such as a QMAX device, whose gaps are proportional to the size of the analyte to be analyzed, or the analyte forms a monolayer between the gaps;

[0453] b) taking an image of the sample in the sample holding device over an area of ​​interest (AoI) for determination using an imager;

[0454] c) performing machine learning based inference using the trained machine learning model for bubble and air gap detection and segmentation to detect bubbles and air gaps and determine the areas of the bubble air gaps in the AoI associated with the segmentation contour masks covering them in their AoI;

[0455] d) Determine the area ratio between the area of ​​the bubble gaps in the AoI and the area of ​​the AoI:

[0456] Bubble gap area ratio in AoI=bubble gap area in AoI / area of ​​AoI; and

[0457] k) If the ratio of the bubble interstitial area in the AoI from (d) exceeds a certain threshold (e.g. 10%), then a flag is raised and the assay result is not trustworthy, where the threshold is derived from training / evaluation data or from physical rules governing analyte distribution.

[0458] F6. A system for measuring a sample having one or more unknown operating conditions, comprising:

[0459] a) loading the analyte into a sample holding device, such as a QMAX device, wherein the sample holding device has gaps proportional to the size of the analyte to be analyzed, or the analyte forms a monolayer between the gaps, and there are monitoring labels (such as pillars) that reside in the device and are not immersed and can be imaged together with the sample on the sample holding device by an imager;

[0460] b) taking an image of the sample in the sample holding device over an area of ​​interest (AoI) for determination using an imager;

[0461] c) performing machine learning-based inference using the trained machine learning model to detect and segment the monitoring marker (column) with the analyte on top, and determining the area associated with the detected monitoring marker (column) (analyte area on AoI column) based on the segmentation contour mask of the detected monitoring marker (column) in the AoI;

[0462] d) Determine the area ratio between the area of ​​the analyte on the column in the AoI and the area of ​​the AoI:

[0463] Analyte on column area ratio in AoI = Analyte on column area in AoI / Area of ​​AoI; and

[0464] 1) If the ratio of the on-column analyte area in Ao1 from (d) exceeds a certain threshold (e.g. 10%), a flag is raised and the assay result is not trustworthy, wherein the threshold is derived from training / evaluation data or from physical rules governing analyte distribution.

[0465] F7. A system for measuring a sample having one or more unknown operating conditions, comprising:

[0466] a) adding an analyte to a sample holding device, such as a QMAX device;

[0467] b) taking an image of the sample in the sample holding device over an area of ​​interest (AoI) for determination using an imager;

[0468] c) performing a machine learning based focus check to detect whether an image of the sample taken by the imager is in focus of the sample, wherein a machine learning model for detecting the focus of the imager is constructed from a plurality of images of the imager with known in-focus and out-of-focus conditions; and

[0469] d) If the image of the sample taken by the imager is detected to be out of focus in (c), then a flag is raised and the image-based determination results are not trustworthy.

[0470] F8. A system for measuring a sample having one or more unknown operating conditions, comprising:

[0471] a) loading the analyte into a sample holding device, such as a QMAX device;

[0472] b) taking an image of the sample in the sample holding device over an area of ​​interest (AoI) for determination using an imager;

[0473] c) performing machine learning based analyte detection; and

[0474] d) If the analyte count is too low outside a preset acceptable range, a flag is raised and the result is unreliable, where the acceptable range is specified based on the physical or biological conditions of the assay.

[0475] F9. A system for measuring a sample having one or more unknown operating conditions, comprising:

[0476] a) adding an analyte to a sample holding device, such as a QMAX device;

[0477] b) taking an image of the sample in the sample holding device over an area of ​​interest (AoI) for determination using an imager;

[0478] c) dividing the image of the sample into non-overlapping sub-image spots of equal size;

[0479] d) performing machine learning based analyte detection on each sub-image spot thereof; and

[0480] e) If for some sub-image spots the counts of the detected analyte are unrealistically low (e.g., in a complete blood count, the number of red blood cells in the sample is below the human acceptable range), the flag is raised and the result is unreliable for assays with insufficient sample or uneven distribution of samples.

[0481] F10. The methods, devices, and embodiments described in all preceding claims, wherein detecting and segmenting anomalies from an image of a sample taken by an imager in an image-based assay is based on image processing, machine learning, or a combination of image processing and machine learning.

[0482] F11. In the methods, devices and embodiments of all the preceding claims, the estimation of the area covered by the segmented contour mask in the area of ​​interest (AoI) of the image of the sample is utilized to compensate for distortions in microscopic imaging based on an estimation of the true lateral size (or field of view (FoV)) of each image or each sub-image spot, including but not limited to spherical distortion from the lens, defects at the microscopic level, misalignment in focusing, etc.

[0483] F12. In the methods, apparatus and embodiments described in F11, monitoring marks (e.g., posts) are built into the sample holding device (e.g., QMAX card); and the monitoring marks (e.g., posts) are used as detectable anchor points to make the estimate of the true lateral size (or field of view (FoV)) accurate in the face of distortions in microscopic imaging.

[0484] F13. In the methods, apparatus and embodiments described in F12, the monitoring marks (e.g., posts) of the sample holding device have some known configuration, such as a QMAX card, distributed at prescribed fixed intervals in the sample holding device so that the detection and positioning of the monitoring marks as anchor points in the estimation of the true lateral dimension (TLD) (or field of view (FoV)) are reliable and robust.

[0485] F14. In the methods, devices and embodiments described in F1, the detection and characterization of outliers in image-based measurements are based on non-overlapping sub-image spots of the input image of the sample described herein, and the determination of outliers can be based on non-parametric methods, parametric methods, and a combination of the two during the measurement process.

[0486] G-1 is a method comprising:

[0487] (a) detecting an analyte in a sample containing or suspected of containing the analyte, the detecting comprising:

[0488] (i) depositing the sample into a detection instrument, and

[0489] (ii) measuring the sample using a detection instrument to detect the analyte, thereby generating a test result;

[0490] (B) determining the reliability of the test result, the determination comprising:

[0491] (i) capturing one or more images of a portion of the sample and / or a portion of the portion of the sample adjacent to the portion in the detection instrument, wherein the one or more images reflect one or more operating conditions that produced the detection result; and

[0492] (ii) analyzing one or more images using a computing device having an algorithm to determine the reliability of the detection result in step (a); and

[0493] (c) reporting of test results and the reliability of test results;

[0494] One or more of the operating conditions are unpredictable and / or random.

[0495] The term "unreliable" in the assay result means that for the assay of a given sample, the assay result is not always accurate: sometimes the assay result is accurate, but sometimes the result is inaccurate, where the inaccurate result is substantially different from the accurate result. Such an inaccurate result is called an "erroneous result". In some literature, an erroneous result is also called an "outlier".

[0496] The term "accurate" in the context of an assay result means that the assay result agrees, within acceptable limits, with the result obtained for the same sample when measured by a trained professional using a gold standard instrument operated under ideal conditions.

[0497] Traditionally, diagnostic assays are often performed using complex (and often expensive) instrumentation and require highly trained personnel and sophisticated infrastructure that is not available in limited resource settings.

[0498] The term "limited resource setting" or "LRS" for assaying samples refers to a setting in which the assay is performed, wherein it uses a simplified / low-cost assay procedure or simplified / low-cost instrumentation, is performed by untrained personnel, is used in a hostile environment (e.g., an open and non-laboratory environment with dust), or any combination thereof.

[0499] The term "LRS assay" refers to an assay performed under LRS.

[0500] The term "confidence" describing the reliability of a particular assay result (or data) means that a reliability analysis of a particular assay result determines that there is a low probability that the result is inaccurate.

[0501] The term "uncertainty" describing the reliability of a particular assay result (or data) means that a reliability analysis of the particular assay result determines that the result has a high probability of being inaccurate.

[0502] The term "operating conditions" when performing an assay refers to the conditions under which the assay is performed. Operating conditions include, but are not limited to, bubbles in the sample, dust in the sample, foreign objects (i.e., objects that did not come from the original sample but entered the sample later), defects on the solid surface, and / or processing conditions of the assay.

[0503] When samples are assayed in a limited resource setting (LRS), the assay results may be unreliable. However, traditionally, the reliability of a particular result is not checked during or after a particular test on a given sample.

[0504] The present invention observes that in LRS assays (or even in a laboratory testing environment), one or more unpredictable random operating conditions may occur and affect the assay results. When this occurs, even with the same sample, the assay may be substantially different from one particular assay to the next. However, instead of taking the assay results as is, the reliability of a particular result in a particular test of a given sample can be assessed by analyzing one or more factors associated with the assay operating conditions in the particular assay.

[0505] The present inventors have observed that in LRS assays with one or more unpredictable random operating conditions, the overall accuracy of the assay can be significantly improved by using an analysis of the reliability of each specific assay and by rejecting implausible assay results.

[0506] One aspect of the present invention is an apparatus, system, and method that performs an analysis by not only measuring the analyte in a particular test, but also by analyzing the operating conditions of the particular test to check the reliability of the measurement results.

[0507] In some embodiments of the invention, checking of the plausibility of assayed measurement results is modeled in a machine learning framework, and machine learning algorithms and models are designed and applied to handle unpredictable random operating conditions that occur and affect assay results.

[0508] The term "machine learning" refers to algorithms, systems, and devices in the field of artificial intelligence that typically use statistical techniques and artificial neural networks to provide computers with the ability to "learn" from data (i.e., gradually improve performance on a specific task) without being explicitly programmed.

[0509] The term "artificial neural network" refers to a hierarchically connected system inspired by biological networks that can "learn" to perform tasks by considering examples, typically without being programmed with any task-specific rules.

[0510] The term "convolutional neural network" refers to a class of multi-layer feed-forward artificial neural networks that are most commonly used to analyze visual images.

[0511] The term "deep learning" refers to a broad class of machine learning methods in artificial intelligence (AI) that learn from data with a network structure consisting of many connected layers.

[0512] The term "machine learning model" refers to a trained computational model built from a training process in machine learning of data. A machine learning model trained by a computer application during the derivation phase gives the computer the ability to perform specific tasks (e.g., detecting and classifying objects). Examples of machine learning models include ResNet, DenseNet, etc., which are also called "deep learning models" due to the layered depth in their network structure.

[0513] The term "image segmentation" refers to the image analysis process of dividing a digital image into multiple segments (sets of pixels with bitmap masks covering the image segments along their segment boundary contours). Image segmentation can be achieved by image segmentation algorithms in image processing such as watershed, iterative graph cuts, mean shift, etc., or by machine learning algorithms such as MaskRCNN.

[0514] The term "object" or "object of interest" in an image refers to an object that is visible in the image and has a fixed shape or form.

[0515] In the present invention, the innovative use of machine learning has the advantage of automating the process of determining the confidence of assay results in the face of unpredictable random operating conditions in the assay directly from the data, without making explicit assumptions about the unpredictable conditions, which may be complex, difficult to predict, and prone to errors.

[0516] The machine learning framework in the present invention involves a process comprising:

[0517] (a) Collect training task data;

[0518] (b) prepare labeled data;

[0519] (c) Selecting a machine learning model;

[0520] (d) training the selected machine learning model using the training data;

[0521] (e) Using the training and evaluation data, tune the hyperparameters and model architecture until the model achieves satisfactory performance on the evaluation and test data; and

[0522] (f) Perform inference on test data using the trained machine learning model from (e).

[0523] Image segmentation for image-based assays: In some embodiments of the present invention for verifying the credibility of test results, it is necessary to segment objects of interest from images of samples for analysis. Although machine learning-based image segmentation algorithms (e.g., Mask RCNN) are powerful, they require precise contour labeling of the shapes of objects in microscopic images of samples to train machine learning models, which has become a bottleneck for many applications. In addition, they are very sensitive to the shapes of objects in images. For image-based assays, it is difficult to perform such labeling of the shape contours of objects because the objects in the sample can be very small, their appearance is random, and they have huge variations in shape, size, and color (e.g., dust, bubbles, etc.).

[0524] In some embodiments of the present invention, a fine image segmentation algorithm is designed based on a combination of a coarse bounding box segmentation based on machine learning and a fine shape determination based on image processing. It is applied to image segmentation in image-based assays, where each object only needs to be marked in a coarse bounding box, independent of its shape and shape contour details. Thus, the need for fine marking of shape-related contours of objects in the image of the sample is eliminated, which is difficult, complex, expensive and difficult to be precise. The fine image segmentation algorithm comprises:

[0525] a) collecting a plurality of images of the sample taken by the imager, the plurality of images containing the object to be detected in the image of the sample for further analysis;

[0526] b) labeling each object in the collected images with a rough bounding box containing the object for model training;

[0527] c) training a machine learning model (e.g., FRCNN) to detect objects in images with samples of rough bounding boxes containing objects;

[0528] d) using an image of the sample as input in a measurement;

[0529] e) applying the trained machine learning model to detect objects with their rough bounding boxes in the sample images;

[0530] f) transforming each image patch corresponding to a detected bounding box into gray and then into binary with an adaptive threshold;

[0531] g) Perform morphological dilation (7x7) and erosion (3x3) to enhance the outline of the shape based on the background noise;

[0532] h) performing convex contour analysis on each image patch, taking the longest connected contour found in the image patch as the contour of the object shape, thereby determining an image mask of the object (e.g., a binary bitmap covering the object in the sample image); and

[0533] i) Image segmentation is completed by collecting all image masks from (h).

[0534] (If an additional segmentation mask with a margin of Δ is required, each detected contour is dilated in (h) with the margin Δ as the new mask)

[0535] Fig.10 is applied in image-based determination Fig. 9 An example of the described fine image segmentation algorithm for an image of a blood sample is depicted in FIG. As shown in the example, the described fine image segmentation algorithm can appropriately handle objects of different sizes and shapes in an image-based assay, where a very tight mask covers the objects in the sample image.

[0536] Focus check in image-based assays: In image-based assays, the image of the sample taken by the imager needs to be focused on the sample by the imager for the assay, and defocus in the image of the sample taken by the imager blurs the analyte in the image of the sample, and thus the assay result becomes unreliable. However, there are many random factors that can cause the image of the sample to be partially or even completely out of focus, including but not limited to vibration / hand shake during the image taken, misalignment of the sample holding device with the image sensor plane, etc. In addition, the existing technology mainly relies on certain edge content-based measurements, such as Tenengrad et al., and some preset content-related thresholds, which are unreliable, fragile, and insufficient for the requirements in microscopic imaging-based assays.

[0537] In some embodiments of the present invention, a machine learning-based validation process is designed and applied to determine whether an image of a sample captured by an imager is in focus or out of focus in an image-based assay, wherein images of the sample captured by the imager under in-focus and out-of-focus conditions are collected as training data and are labeled based on their known focus conditions. A machine learning model is selected and trained with the labeled training data. During the assay, the trained machine learning model is applied to the image of the sample captured by the imager to deduce / predict whether the image of the sample captured by the imager for the assay is in focus and to determine whether the assay result is trustworthy without the need for a preset content-related threshold in the prior art.

[0538] In some embodiments, monitoring marks in the form of pillars are located on the sample holding QMAX card to keep the gap between the two parallel plates of the sample holding QMAX card uniform. In this way, the sample volume under the area of ​​interest (AoI) in the image on the sample holding QMAX card taken by the imager can be determined by the AoI and the gap between its two parallel plates.

[0539] Uniformity of analyte distribution in the sample: One factor that can affect the reliability of the assay results is the uniformity of the analyte distribution in the sample, and even experienced technicians may have difficulty detecting them by visual inspection.

[0540] In some embodiments of the present invention, an algorithm with a dedicated process based on machine learning is designed and applied to determine whether an analyte is uniformly distributed in a sample for determination from an image of the sample taken by an imager, wherein a plurality of images of the sample taken by the imager are collected, thereby identifying and labeling the analyte in the image of the sample. A machine learning model (e.g., F-RCNN) is selected and trained with labeled training images to detect the analyte in the sample image.

[0541] During the determination process, the algorithm with its dedicated processes includes:

[0542] a) using as input an image of a sample from an imager;

[0543] b) dividing the sample image into image spots of equal size and non-overlapping (e.g., 8×8 small image spots of equal size);

[0544] c) applying the trained machine learning model to each constructed image spot to determine, without limitation, the analyte concentration in each spot;

[0545] d) sorting the analyte concentrations of the constructed image spots in ascending order, and determining the 25% quantile Q1 and the 75% quantile Q3 thereof in the sorted concentration sequence of the constructed image spots;

[0546] e) applying a robust, non-parametric outlier detection algorithm to determine the uniformity / homogeneity of the analyte in the sample for the assay based on the constructed analyte concentration distribution of the image spots, wherein in some of the inventions a quantile range-based confidence measure is constructed and applied:

[0547] Confidence-IQR = (Q3-Q1) / (Q3+Q1); and

[0548] If the Confidence-IQR exceeds a certain threshold (eg, 30%), a flag is raised and the result is considered untrustworthy, where the threshold depends on the effect of the non-uniform distribution on the final estimate, which can be estimated from the training and evaluation data.

[0549] Aggregated analytes in the sample: In addition, aggregated analytes in the sample can affect the accuracy of the assay results, especially if they occupy a significant portion of the sample. For example, in a complete blood count, some fraction of the red blood cells can aggregate in the sample, especially if they have been exposed to open air for a period of time. Aggregated analytes in the sample have various sizes and shapes depending on how they aggregate together. If the fraction of aggregated analytes in the sample exceeds a certain percentage, the sample should not be used for the assay.

[0550] In some embodiments of the present invention, a machine learning based process is designed and applied to determine whether analytes are aggregated / clustered in a sample for analysis from an image of the sample taken by an imager, wherein images of good samples and images of samples with different degrees of aggregated analytes in the sample are taken by the imager and collected as training data. According to the fine image segmentation algorithm described in the present invention, the aggregated analytes in the image are first roughly marked by a bounding box, regardless of their shape and shape contour details. A machine learning model (e.g., Fast RCNN) is selected and trained with the labeled training images to detect the aggregated analyte clusters in the image of the sample with its bounding box, and then, additional processing steps are performed to determine its fine segmentation based on the fine segmentation image segmentation algorithm described in the present invention.

[0551] During the assay, operations to aggregate the analyte are performed, including:

[0552] a) using as input an image of a sample from an imager;

[0553] b) applying the trained machine learning model for aggregated analytes to detect aggregated analytes in an image of a sample to be analyzed in a binding frame;

[0554] c) determining their segmentation contour masks in the images of the samples following the fine image segmentation algorithm of the present invention;

[0555] d) determining the total area occupied by aggregated analytes in a region of interest (AoI) in the sample image (aggregated analyte area in AoI) by summing all areas associated with the segmented contour masks covering them from (c);

[0556] e) Determining the area ratio between the area of ​​aggregated analyte in the AoI and the area of ​​the AoI in the sample image:

[0557] Aggregated analyte area ratio in AoI = aggregated analyte area in AoI / area of ​​AoI; and

[0558] f) if the aggregated analyte area ratio in A01 exceeds a certain threshold, a flag is raised for the confidence in the assay result, wherein in some embodiments of the method, the threshold is about 10-20%, wherein the threshold depends on the impact of the aggregated analyte area on the final estimate, which can be estimated from the training and evaluation data.

[0559] Dry texture in the image of the sample: Dry texture in the image of the sample is another factor that affects the confidence of the measurement results in image-based measurements. This occurs when the amount of sample used for the measurement is lower than the required amount or some parts of the sample in the image holding device become dry due to some unpredictable factors.

[0560] In some embodiments of the present invention, a machine learning-based process is designed and applied to detect dry texture regions in images of samples taken by an imager in an image-based assay, wherein images of good samples without dry texture regions and images of samples with various degrees of dry texture regions in the samples are collected as training data, according to which the dry texture regions in the images are roughly marked by a bounding box, regardless of the shape and shape contour details. A machine learning model (e.g., Fast RCNN) is selected and trained using the labeled training images to detect dry texture regions in images of samples with bounding boxes, and then the fine image segmentation algorithm described in the present invention is followed to determine the segmentation contour masks covering them.

[0561] During image-based determination, it performs the following processing operations, including:

[0562] a) using as input an image of a sample from an imager;

[0563] b) applying a machine learning model trained for dry texture structure (e.g., Fast RCNN) to the image of the sample for determination, and detecting its dry texture region in the binding frame;

[0564] c) if a dry texture region is detected in the image of the sample in (b), determining a segmentation contour mask by a fine image segmentation algorithm of the present invention;

[0565] d) determining the total area occupied by the dry texture structure in the area of ​​interest (AoI) in the image of the sample for measurement (the dry texture structure area in the AOI) by summing all areas of the detected dry texture structure based on the segmented contour mask covering the dry texture structure in (c);

[0566] e) Determine the area ratio between the area of ​​the dry texture structure in the AoI and the area of ​​the AoI in the sample image:

[0567] Dry texture structure area ratio in AoI=dry texture structure area in AoI / area of ​​AoI; and

[0568] f) if the dry texture area ratio in the AoI exceeds a certain threshold, then raising a flag for the confidence in the determination result, wherein in some embodiments of the method, the threshold is about 10%, wherein the threshold depends on the impact of the dry texture area on the final estimate, which can be estimated from the training and evaluation data.

[0569] Sample defects: Defects in the sample can seriously affect the reliability of the measurement results, where these defects can be any unwanted objects in the sample, including but not limited to dust, oil, etc. They are difficult to handle with existing technologies because their appearance and shape in the sample are random.

[0570] In some embodiments of the present invention, a dedicated process for defect detection is designed and applied to image-based determination, where images of good samples without defects and images of samples with varying degrees of defects in the samples are collected as training data, according to which defect areas in the images are labeled with coarse bounding box labels. A machine learning model (e.g., Fast RCNN) is selected and trained using the labeled training images to detect defects in images of samples in the bounding boxes, and then a fine image segmentation algorithm described in the present invention is applied to determine the segmentation contour masks covering them.

[0571] During the image-based measurement process, defect detection and area determination are performed to verify the confidence of the measurement results, including:

[0572] a) using as input an image of a sample from an imager;

[0573] b) applying a machine learning model trained for defects (e.g., Fast RCNN) to the image of the sample for determination and detecting its defects in the binding frame;

[0574] c) determining their segmentation contour masks in a refined image segmentation algorithm according to the present invention;

[0575] d) determining the total area occupied by defects in an area of ​​interest (AoI) in the image of the sample for measurement (defect area in AoI) by summing all areas of detected defects based on the segmented contour mask covering the defect from (c);

[0576] e) Determine the area ratio between the defect area in the AoI and the area of ​​the AoI in the image of the sample:

[0577] Defect area ratio in AoI=defect area in AoI / area of ​​AoI; and

[0578] f) if the defect ratio in A01 exceeds a certain threshold, a confidence flag is raised for the determination result, wherein in some embodiments of the method, the threshold is about 15%, wherein the threshold depends on the impact of the defect area on the final estimate, which can be estimated from the training and evaluation data.

[0579] Bubbles in the sample: Bubbles in the sample are a special type of defect that can occur in an assay. Their appearance is random and can result from the operating procedure and reactions between the analyte and other reagents in the sample. Unlike solid dust, their appearance is more random because their number, size and shape can vary over time.

[0580] In some embodiments of the present invention, a dedicated process is designed and applied to detect bubbles in samples in an image-based assay, where images of good samples without bubbles and images of samples with various degrees of bubbles are collected as training data, according to which bubbles in the images are only roughly marked by bounding boxes, regardless of their shape and shape contour details. A machine learning model (e.g., FastRCNN) is selected and trained with the labeled training images to detect bubbles in sample images in a bonded binding box. Then, following the fine image segmentation algorithm described in the present invention, a segmentation contour mask covering them in the image of the sample is determined.

[0581] In the image-based measurement process, bubble detection and area determination are performed in some embodiments of the present invention to verify the credibility of the measurement results, including:

[0582] a) using as input an image of a sample from an imager;

[0583] b) applying a machine learning model trained for bubbles (e.g., Fast RCNN) to the image of the sample for determination and detecting the bubbles in the binding box;

[0584] c) determining their segmentation contour masks in applying the fine image segmentation algorithm of the present invention;

[0585] d) determining the total area occupied by bubbles in an area of ​​interest (AoI) in the image of the sample used for the assay (defect area in AoI) by summing all areas of the detected bubbles based on the segmented contour mask covering the bubbles from (c);

[0586] e) Determine the area ratio between the area of ​​the bubbles in the AoI and the area of ​​the AoI in the sample image:

[0587] Bubble area ratio in AoI=bubble area in AoI / area of ​​AoI; and

[0588] f) if the bubble ratio in the AoI exceeds a certain threshold, then raising a flag for the confidence in the determination result, wherein in some embodiments of the method, the threshold is about 10%, wherein the threshold depends on the impact of the bubble area on the final estimate, which can be estimated from the training and evaluation data.

[0589] In some embodiments of the invention, a more stringent threshold is applied for bubbles, since a large amount of area occupied by bubbles is an indication of some chemical or biological reaction between components in the sample for assay or some defect / problem in the sample holding device.

[0590] Imaging-based assays using monitoring markers

[0591] In image-based assays for determining an analyte in a sample, an imager is used to generate an image of the sample on a sample holder, and the image is used to determine the identity of the analyte.

[0592] However, many factors may distort the image (i.e., different from the image of the real sample or perfect conditions). Image distortion can lead to inaccuracies in the determination of analyte properties. For example, one fact is poor focus, because the biological sample itself does not have the preferred sharp edges in focus. When the focus is poor, the object size will be different from the real object, and other objects (e.g., blood cells) may become unrecognizable. Another example is that the lens may be perfect, resulting in different distortions at different locations of the sample. Yet another example is that the sample holder is not in the same plane as the optical imaging system, resulting in good focus in one area and poor focus in other areas.

[0593] The present invention relates to an apparatus and method capable of obtaining a "true" image from a distorted image, thereby improving the accuracy of the measurement.

[0594] One aspect of the present invention is an apparatus and method for using a monitoring marker having an optically observable planar surface that is parallel to adjacent surfaces.

[0595] Another aspect of the invention is an apparatus and method for using a QMAX card to uniformly layer at least a portion of a sample and using monitoring markers on the card to improve assay accuracy.

[0596] Another aspect of the invention is an apparatus and method for monitoring markers using computational imaging, artificial intelligence, and / or machine learning.

[0597] The term "lateral dimension" refers to the linear dimension in the plane of the thin sample layer being imaged.

[0598] The terms "true lateral dimension (TLD)" and "field of view (FoV)" are interchangeable.

[0599] The term "microfeatures in a sample" may refer to analytes, microstructures, and / or microvariations of matter in a sample. Analytes refer to particles, cells, macromolecules such as proteins, nucleic acids, and other moieties. Microstructures may refer to microscopic scale differences in different materials. Microvariations refer to microscopic changes in local properties of a sample. Examples of microvariations are changes in local optical index and / or local mass. Examples of cells are blood cells, such as white blood cells, red blood cells, and platelets.

[0600] A. Monitoring labels on solid surfaces

[0601] A1-1. An apparatus for measuring microfeatures in a sample using an imager, the apparatus comprising:

[0602] (a) a solid surface comprising a sample contact area for contacting a sample containing microfeatures; and

[0603] (B) one or more monitoring markers, wherein the monitoring marker:

[0604] i. Made of a different material from the sample;

[0605] ii. being located inside a sample during measurement of the microstructure, wherein the sample forms a thin layer having a thickness of less than 200 μm on the sample contact area; and

[0606] iii. have their lateral linear dimensions of about 1 μm (micrometer) or more, and

[0607] iv. having at least one lateral linear dimension of 300 μm or less; and

[0608] wherein at least one monitoring marker is imaged by an imager during the assay;

[0609] wherein the monitoring markers are used during the determination of the analyte; and the geometric parameters (e.g., shape and size) of the monitoring markers and / or the spacing between the monitoring markers (a) are predetermined and known prior to the determination of the analyte, and (b) are used as parameters in an algorithm for determining properties associated with the microfeatures.

[0610] A1-2. An apparatus for determining microfeatures in a sample using an imager, the apparatus comprising:

[0611] a solid surface comprising a sample contact area for contacting a sample containing microfeatures; and

[0612] One or more monitoring marks, wherein each monitoring mark comprises a protrusion or a groove from the solid surface, wherein:

[0613] v. The protrusion or groove comprises a flat surface, which is substantially parallel to an adjacent surface, the adjacent surface being a portion of a solid surface adjacent to the protrusion or groove;

[0614] vi. The distance between the flat surface and the adjacent surface is about 200 micrometers (μm) or less;

[0615] vii. The planar surface has (a) a linear dimension of at least about 1 μm or greater, and (b) an area of ​​at least one linear dimension of 150 μm or less;

[0616] viii. imaging the planar surface of at least one monitoring mark by an imager used during determination of microfeatures; and

[0617] ix. The shape of the planar surface, the size of the planar surface, the distance between the planar surface and an adjacent surface, and / or the spacing between monitoring marks are (a) predetermined and known before the microfeatures are measured, and (b) used as parameters in an algorithm for determining a property associated with the microfeatures;

[0618] B. Monitoring mark on QMAX card

[0619] A2-1. An apparatus for analyzing microfeatures in a sample using an imager, the apparatus comprising:

[0620] A first plate, a second plate, a spacer, and one or more monitoring marks, wherein:

[0621] i. The first plate and the second plate are movable relative to each other into different configurations;

[0622] ii. Each of the first plate and the second plate comprises an inner surface comprising a sample contact area for contacting a sample containing microfeatures;

[0623] iii. one or both of the first plate and the second plate comprises a spacer permanently fixed to the inner surface of the corresponding plate;

[0624] iv. The spacers have a substantially uniform height equal to or less than 200 microns and a fixed spacer spacing (ISD).

[0625] v. The monitoring marker is made of a different material from the sample;

[0626] vi. During the measurement of the microstructure, the monitoring mark is located inside the sample, wherein the sample forms a thin layer with a thickness of less than 200 μm on the sample contact area; and

[0627] vii. The monitoring mark has a lateral linear dimension of about 1 μm (micrometer) or more and has at least one lateral linear dimension of 300 μm or less;

[0628] wherein at least one monitoring marker is imaged by an imager during the assay;

[0629] wherein microfeatures are used during the determination; and the shape of the planar surface, the size of the planar surface, the distance between the planar surface and an adjacent surface, and / or the spacing between monitoring marks are (a) predetermined and known before the determination of the microfeatures is performed, and (b) used as parameters in an algorithm that determines a property associated with the microfeatures;

[0630] wherein one of the configurations is an open configuration in which the two plates are partially or completely separated, the spacing between the plates is not adjusted by the spacer, and the sample is deposited on one or both of the plates; and

[0631] wherein another of the configurations is a closed configuration, which is configured after the sample is deposited in an open configuration and the plates are forced to reach the closed configuration by applying a compressive force on the force area; and in the closed configuration, at least a portion of the sample is compressed by the two plates into a layer of highly uniform thickness and is essentially stagnant relative to the plates, wherein the uniform thickness of the layer is limited by the sample contact area of ​​the two plates and adjusted by the plates and spacers.

[0632] The monitoring marker is (i) a different structure from the spacer, or (ii) the same structure as the spacer.

[0633] A2-2. An apparatus for analyzing microfeatures in a sample using an imager, the apparatus comprising:

[0634] A first plate, a second plate, a spacer, and one or more monitoring marks, wherein:

[0635] viii. The first plate and the second plate are movable relative to each other into different configurations;

[0636] ix. Each of the first plate and the second plate comprises an inner surface comprising a sample contact area for contacting a sample containing microfeatures;

[0637] x. One or both of the first plate and the second plate comprises a spacer permanently fixed to the inner surface of the corresponding plate;

[0638] xi. The spacers have a substantially uniform height equal to or less than 200 microns and a fixed spacer spacing (ISD).

[0639] xii. Each monitoring mark comprises a protrusion or groove on one or both sample contact areas;

[0640] xiii. The protrusion or groove comprises a flat surface that is substantially parallel to an adjacent surface that is a portion of a solid surface adjacent to the protrusion or groove;

[0641] xiv. The distance between the flat surface and the adjacent surface is about 200 micrometers (μm) or less;

[0642] xv. The planar surface has (a) a linear dimension of at least about 1 μm or greater, and (b) an area of ​​at least one linear dimension of 150 μm or less;

[0643] xvi. imaging the planar surface of at least one monitoring mark by an imager used during determination of microfeatures; and

[0644] xvii. The shape of the planar surface, the size of the planar surface, the distance between the planar surface and an adjacent surface, and / or the spacing between monitoring marks are (a) predetermined and known before measuring the microfeatures, and (b) used as parameters in an algorithm for determining a property associated with the microfeatures;

[0645] wherein one of the configurations is an open configuration in which the two plates are partially or completely separated, the spacing between the plates is not adjusted by the spacer, and the sample is deposited on one or both of the plates; and

[0646] wherein another of the configurations is a closed configuration, which is configured after the sample is deposited in an open configuration and the plates are forced to reach the closed configuration by applying a compressive force on the force area; and in the closed configuration, at least a portion of the sample is compressed by the two plates into a layer of highly uniform thickness and is essentially stagnant relative to the plates, wherein the uniform thickness of the layer is limited by the sample contact area of ​​the two plates and adjusted by the plates and spacers.

[0647] The monitoring marker is (i) a different structure from the spacer, or (ii) the same structure as the spacer.

[0648] A3. An apparatus for image-based determination, comprising:

[0649]

[00136] The device of any preceding embodiment, wherein the device has at least five monitoring marks, wherein at least three of the monitoring marks are not aligned in a straight line.

[0650] A4. A device for determining an analyte in a sample using an imager, the system comprising:

[0651] (a) a device as described in any of the preceding device embodiments; and

[0652] (b) An imager for measuring a sample containing an analyte.

[0653] A5. A system for performing an imaging-based assay, the system comprising:

[0654] (a) A device as described in any of the preceding embodiments;

[0655] (b) an imager for measuring a sample containing an analyte; and

[0656] (c) An algorithm that utilizes the monitoring markers of the device to determine a property associated with the analyte.

[0657] In some embodiments, the thickness of the thin layer is configured so that for a given analyte concentration, there is a monolayer of analytes in the thin layer. The term "monolayer" means that in the thin sample layer, there is substantially no overlap between two adjacent analytes in a direction perpendicular to the plane of the sample layer.

[0658] C. Monitoring markers with computational imaging artificial intelligence and / or machine learning

[0659] Another aspect of the present invention is to combine monitoring tags with computational imaging, artificial intelligence and / or machine learning. It exploits the process of forming images from measurements, using algorithms to process the images and map the objects in the images to their physical dimensions in the real world. Machine learning (ML) is applied in the present invention to learn the salient features of objects in the sample, which are embedded in the ML model, which is built and trained based on images of the sample taken by the imager. Intelligent decision logic is built and applied in the derivation process of the present invention to detect and classify target objects in the sample based on the knowledge embedded in the ML model. Computational imaging is the process of indirectly forming images from measurements using algorithms that rely on a lot of calculations.

[0660] A6. A system for determining an analyte in a sample using an imager, the system comprising:

[0661] (a) A device as described in any of the preceding embodiments;

[0662] (b) an imager for measuring a sample containing an analyte; and

[0663] (c) An algorithm that utilizes the monitoring markers of the device to determine a property associated with the analyte, wherein the algorithm uses machine learning.

[0664] A7. A method for determining an analyte in a sample using an imager, comprising:

[0665] (a) obtaining a device, apparatus or system as described in any one of the preceding embodiments;

[0666] (b) obtaining a sample and depositing the sample onto a sample contacting area of ​​the device, apparatus or system of (a), wherein the sample comprises an analyte; and

[0667] (c) Determining the analyte.

[0668] 8. A method for determining an analyte in a sample using an imager, comprising:

[0669] (a) obtaining a device, apparatus or system as described in any one of the preceding embodiments;

[0670] (b) obtaining a sample and depositing the sample onto a sample contacting area of ​​the device, apparatus or system of (a), wherein the sample comprises an analyte; and

[0671] (c) determining the analyte, wherein the determining comprises the step of using machine learning.

[0672] A key idea of ​​the present invention is to use posts in a sample holding device (e.g., a QMAX device) as detectable anchor points for calibration and improving the accuracy of image-based assays. In a QMAX device, posts are monitoring marks to keep the gap between the two plates holding the sample in the sample holding device uniform. However, accurately detecting posts in a sample holding device as anchor points for calibration and improving the accuracy of the assay is a challenge because the posts are penetrated and surrounded by the analyte within the sample holding device. In addition, their images are distorted and blurred in microscope imaging due to spherical (barrel) distortion of the lens, diffraction of light from the microscope object, defects in the microscope level, misalignment of focus, noise in the sample image, etc. Moreover, it becomes even more difficult if imaging is performed by commercial devices (e.g., cameras from smartphones) because these cameras do not have dedicated hardware calibration once they are manufactured.

[0673] In the present invention, pillar detection is formulated into a machine learning framework to detect pillars in sample holding devices (e.g., QMAX devices) with an accuracy suitable for calibration and accuracy improvement in image-based assays. Since the distribution and physical configuration of the pillars are known a priori and controlled by sophisticated nanoscale fabrication (e.g., QMAX devices), it makes this innovative approach of using detectable monitoring markers (e.g., pillars) as anchors in image-based assays not only feasible but also effective.

[0674] In some embodiments, the algorithm as described in any of the preceding embodiments includes algorithms of computational imaging, artificial intelligence and / or machine learning.

[0675] In some embodiments, the algorithm as described in any of the preceding embodiments comprises a machine learning algorithm.

[0676] In some embodiments, the algorithm as described in any of the preceding embodiments comprises an algorithm of artificial intelligence and / or machine learning.

[0677] In some embodiments, the algorithm as described in any of the preceding embodiments comprises an algorithm for computational imaging and / or machine learning.

[0678] In some embodiments, it designs machine learning based pillar detection to detect pillars from an image of a sample, and thus, it applies the known configuration and distribution of pillars from card manufacturing to construct a good set of points, i.e., points at the image plane and at the physical plane of the card that correspond to each other. Then, based on the detected good set of points, a corresponding (perspective) transformation is calculated, which maps the distorted image plane to the physical plane of the sample with the correct TLD (true lateral dimension). Figure 6 is a flow chart of true lateral dimension (TLD) estimation and correction using column-based machine learning, and embodiments of the present invention include:

[0679] (1) using a sample addition device, such as a QMAX device, in an image-based assay, wherein monitoring markers of known configuration are present in the device, which are not immersed in the sample and can be imaged from the top by an imager in an image-based assay;

[0680] (2) capturing an image of a sample in a sample addition device including the analyte and the monitor marker;

[0681] (3) building and training a machine learning (ML) model for detecting monitoring marks in the sample holding device from images captured by the imager;

[0682] (4) using the ML detection model in (3), detecting and locating the monitoring mark in the sample addition device from the sample image captured by the imager;

[0683] (5) generating a marker grid from the monitoring markers detected in (4);

[0684] (6) calculating a homography transformation based on the generated monitoring marker grid; and

[0685] (7) Estimate TLD and determine the area, size, and concentration of imaged analytes in image-based assays.

[0686] The present invention can be further improved to perform region-based TLD estimation and calibration to improve the accuracy of image-based determination. An embodiment of this method includes:

[0687] (1) using a sample addition device, such as a QMAX device, in an image-based assay, where there are monitoring markers that are not immersed in the sample and reside in the device and can be imaged from the top by an imager in an image-based assay;

[0688] (2) capturing an image of the sample in the sample holding device including the analyte and the monitoring marker;

[0689] (3) building and training a machine learning (ML) model for detecting monitoring marks in the sample holding device from images captured by the imager;

[0690] (4) segmenting an image of the sample captured by the imager into non-overlapping regions;

[0691] (5) using the ML model of (3) to detect and locate the monitoring marker from the sample image captured by the imager;

[0692] (6) generating a region-based marker grid for each of the regions having more than five non-collinear monitoring markers detected in the local region;

[0693] (7) generating a marker grid for all regions not in (6) in an image of the sample taken by the imager based on the detected monitoring markers;

[0694] (8) computing a region-specific homography transform for each region in (6) based on its own region-based marker grid generated in (6);

[0695] (9) Compute homography transformations for all other regions based on the marker grid generated in (7);

[0696] (10) estimating the region-based TLD for each region in (6) based on the region-based homography transformation generated in (8);

[0697] (11) estimating TLDs for other regions based on the homography transformation from (9); and

[0698] (12) Apply the estimated TLDs from (10) and (11) to determine the area and concentration of the imaged analyte in each partition in the image-based assay.

[0699] In some embodiments, the monitoring mark has sharp edges and flat surfaces.

[0700] In some embodiments, monitoring markers are used to determine local characteristics of the image and / or local operating conditions (eg, gap size, plate quality).

[0701] In some embodiments, the monitoring mark has the same shape as the spacer.

[0702] Monitoring assay operation using monitoring tags

[0703] One aspect of the present invention is for performing an assay using a QMAX card having two movable plates, monitoring marks placed within the thin sample can be used to monitor the operating conditions of the QMAX card. The operating conditions may include whether the sample is added correctly, whether the two plates are closed correctly, and whether the gap between the two plates is the same or approximately the same as a predetermined value.

[0704] In some embodiments, for a QMAX card comprising two movable plates and having a predetermined gap between the two plates in a closed configuration, the operating conditions of the QMAX assay are monitored by taking an image of the monitoring mark in the closed configuration. For example, if the two plates are not closed correctly, the monitoring mark will appear different in the image compared to when the two plates are closed correctly. A monitoring mark surrounded by a sample will have a different appearance than a monitoring mark not surrounded by a sample. Thus, it can provide information about the sample addition conditions.

[0705] Z-1.1 A device for monitoring an operating condition of a device using a monitoring tag, the device comprising:

[0706] A first plate, a second plate, a spacer, and one or more monitoring marks, wherein:

[0707] i. The first plate and the second plate are movable relative to each other into different configurations;

[0708] ii. Each of the first plate and the second plate comprises an inner surface comprising a sample contact area for contacting a sample being analyzed;

[0709] iii. one or both of the first plate and the second plate comprises a spacer permanently fixed to the inner surface of the corresponding plate;

[0710] iv. The monitoring marker has (a) at least one of its dimensions that is predetermined and known, and (b) observable by the imager;

[0711] v. The microstructure having at least one lateral linear dimension of 300 μm or less; and

[0712] vi. Monitoring markers are inside the sample;

[0713] wherein one of the configurations is an open configuration in which the two plates are partially or completely separated, the spacing between the plates is not adjusted by the spacer, and the sample is deposited on one or both of the plates; and

[0714] wherein another of the configurations is a closed configuration, which is configured after the sample is deposited in an open configuration and the plates are forced to reach the closed configuration by applying a compressive force on the force area; and in the closed configuration, at least a portion of the sample is compressed by the two plates into a layer of highly uniform thickness and is essentially stagnant relative to the plates, wherein the uniform thickness of the layer is limited by the sample contact area of ​​the two plates and adjusted by the plates and spacers.

[0715] Wherein, after forcing the two plates to a closed configuration, the monitoring mark is imaged to determine (i) whether the two plates have reached the desired closed configuration, thereby adjusting the sample thickness to approximately a predetermined thickness, and / or (ii) whether the sample has been added as required.

[0716] In some embodiments, the image of the monitoring mark is used to determine whether the two panels have reached the desired closed configuration, wherein the sample is adjusted to have a thickness of approximately a predetermined thickness.

[0717] In some embodiments, images of monitoring markers are used to determine whether sample has been added as desired.

[0718] In some embodiments, monitoring marks are imaged to determine whether the two plates have reached the desired closed configuration, wherein the sample thickness is adjusted to a predetermined thickness, and to determine whether sample has been added as desired.

[0719] In some embodiments, the spacer is used as a monitoring marker.

[0720] In some embodiments, the system includes an apparatus, a computing device, and a non-transitory computer-readable medium having instructions that, when executed, perform the determination.

[0721] In some embodiments, a non-transitory computer-readable medium having instructions that, when executed, perform a method comprising using a thin sample layer in conjunction with one or more images of a monitoring mark to determine (i) whether two plates have reached an intended closed configuration, thereby adjusting the sample thickness to approximately a predetermined thickness, or (ii) whether sample has been added as desired.

[0722] In some embodiments, the system includes a non-transitory computer-readable medium having instructions that, when executed, perform any of the methods of the present disclosure.

[0723] W-1. A method for monitoring an operating condition of a device using a monitoring tag, the method comprising:

[0724] (a) obtaining the device of any preceding embodiment, wherein the device comprises two movable plates, a spacer, and one or more monitoring marks, wherein the monitoring marks are in the sample contacting area;

[0725] (b) obtaining an imager;

[0726] (c) depositing a sample in a sample contact area of ​​the device of (a) and forcing the two plates into a closed configuration;

[0727] (d) taking one or more images of the thin sample layer together with the monitoring markers using an imager; and

[0728] (e) Using the image of the monitoring mark to determine (i) whether the two plates have reached the desired closed configuration, thereby adjusting the sample thickness to approximately a predetermined thickness, or (ii) whether sample has been added as desired.

[0729] In some embodiments, the image of the monitoring mark is used to determine whether the two panels have reached the desired closed configuration, wherein the sample is adjusted to have a thickness of approximately a predetermined thickness.

[0730] In some embodiments, images of monitoring markers are used to determine whether sample has been added as desired.

[0731] In some embodiments, monitoring marks are imaged to determine whether the two plates have reached the desired closed configuration, wherein the sample thickness is adjusted to a predetermined thickness, and to determine whether sample has been added as desired.

[0732] In some embodiments, the system includes an apparatus, a computing device, and a non-transitory computer-readable medium having instructions that, when executed, perform the determination.

[0733] Select regions of interest and / or remove defective image areas

[0734] In some embodiments, the sample has a defect, and a method for eliminating the effect of the defect on measurement includes: identifying the defect in an image, taking an image of the defect, or selecting a good image area of ​​the image that is not caused by the defect.

[0735] In some embodiments, the captured area removed from the image is larger than the area of ​​the defective image area.

[0736] In some embodiments, the thickness of the sample is configured to be thin so that the objects of interest (eg, cells) form a monolayer (ie, there is no significant overlap between objects in a direction perpendicular to the sample layer).

[0737] A method for determining manufacturing quality of a QMAX card using an imager, the method comprising:

[0738] (f) obtaining the device of any preceding embodiment, wherein the device comprises two movable plates, a spacer, and one or more monitoring marks, wherein the monitoring marks are in the sample contacting area;

[0739] (g) obtaining an imager;

[0740] (h) depositing a sample in a sample contact area of ​​the device of (a) and forcing the two plates into a closed configuration;

[0741] (i) taking one or more images of the thin sample layer using an imager; and

[0742] (j) Using images of monitoring marks to determine the manufacturing quality of QMAX cards.

[0743] In the method of any of the foregoing embodiments, determining the manufacturing quality includes measuring characteristics (e.g., length, width, spacing, thick edge) of one or more monitoring marks, and comparing the measured characteristics with reference values ​​to determine the manufacturing quality of the QMAX card.

[0744] In a method as described in any of the foregoing embodiments, determining the manufacturing quality includes measuring a first characteristic (e.g., quantity, length, width, spacing, thick edge) of one or more first monitoring marks, and comparing the measured first characteristic with a second characteristic (e.g., quantity, length, width, spacing, thick edge) of one or more second monitoring marks to determine the manufacturing quality of the QMAX card.

[0745] In the method of any preceding embodiment, the determining is performed during analysis of a sample using the device of any previous embodiment.

[0746] Another aspect of the present invention is to have the monitoring marks in a sample holding device, such as in a QMAX device, with a fixed-spaced pattern so that they appear at fixed intervals with a certain spacing in the image of the sample taken by the imager. Based on this fixed-spaced property, the monitoring mark detection can become very reliable because when the monitoring marks are positioned at fixed intervals in a predetermined configuration, all monitoring marks can be identified and derived from only a few detected monitoring marks. In addition, this configuration can be made precise by nano-fabrication techniques such as nano-imprinting. Thus, due to the fixed-spaced pattern of the monitoring marks, both sample image-based and image area-based TLD estimation can become more accurate and robust.

[0747] A. Sample holder with micro markings

[0748] Single board

[0749] AA-1.1 An apparatus for determining microfeatures in a thin sample using an imager, the apparatus comprising:

[0750] (a) a solid surface comprising a sample contact area for contacting a thin sample, the thin sample having a thickness of 200 μm or less and comprising or suspected of comprising microfeatures; and

[0751] (b) one or more markers, wherein the markers:

[0752] x. having sharp edges that (i) have a predetermined and known shape and size and (ii) are observable by an imager imaging the microfeatures;

[0753] xi. is a microstructure having at least one lateral linear dimension of 300 μm or less; and

[0754] xii. In the sample;

[0755] At least one of the labels is imaged by the imager during the assay.

[0756] AA-1.2 An apparatus for determining microfeatures in a thin sample using an imager, the apparatus comprising:

[0757] (a) a solid surface comprising a sample contact area for contacting a thin sample, the thin sample (i) having a thickness of 200 μm or less and (ii) comprising or suspected of comprising microfeatures; and

[0758] (b) one or more markers, wherein the markers:

[0759] i. Contains protrusions or grooves from the solid surface

[0760] ii. having sharp edges that are observable by an imager imaging the microfeatures;

[0761] iii. a microstructure having at least one lateral linear dimension of 300 μm or less; and

[0762] iv. within the sample;

[0763] At least one of the labels is imaged by the imager during the assay.

[0764] Two plates with constant spacing

[0765] AA-2.1 An apparatus for determining microfeatures in a thin sample using an imager, the apparatus comprising:

[0766] a first plate, a second plate, and one or more spacers wherein:

[0767] xviii. Each of the first plate and the second plate comprises an inner surface comprising a sample contact area for contacting a sample comprising or suspected of comprising microfeatures;

[0768] xix. At least a portion of the sample is limited to a thin layer having a substantially constant thickness of 200 μm or less by the first and second plates;

[0769] xx. The monitoring mark has a sharp edge that (a) has a predetermined and known shape and size and (b) is observable by an imager imaging the microfeature;

[0770] xxi. The monitoring mark is a microstructure having at least one lateral linear dimension of 300 μm or less; and

[0771] xxii. The monitoring mark is inside the sample;

[0772] At least one of the labels is imaged by the imager during the assay.

[0773] Two moving plates

[0774] AA-3. An apparatus for determining microfeatures in a thin sample using an imager, the apparatus comprising:

[0775] A first plate, a second plate, a spacer, and one or more detection marks, wherein:

[0776] vii. The first plate and the second plate are movable relative to each other into different configurations;

[0777] viii. Each of the first plate and the second plate comprises an inner surface comprising a sample contact area for contacting a sample comprising or suspected of comprising microfeatures;

[0778] ix. One or both of the first plate and the second plate comprises a spacer permanently fixed to the inner surface of the respective plate;

[0779] x. The monitoring mark has a sharp edge that (a) has a predetermined and known shape and size and (b) is observable by an imager imaging the microfeature;

[0780] xi. monitoring marks are microstructures having at least one lateral linear dimension of 300 μm or less; and

[0781] xii. Monitoring markers are inside the sample;

[0782] At least one of the labels is imaged by the imager during the assay.

[0783] wherein one of the configurations is an open configuration in which the two plates are partially or completely separated, the spacing between the plates is not adjusted by the spacer, and the sample is deposited on one or both of the plates; and

[0784] wherein another of the configurations is a closed configuration, which is configured after the sample is deposited in an open configuration and the plates are forced to reach the closed configuration by applying a compressive force on the force area; and in the closed configuration, at least a portion of the sample is compressed by the two plates into a layer of highly uniform thickness and is essentially stagnant relative to the plates, wherein the uniform thickness of the layer is limited by the sample contact area of ​​the two plates and adjusted by the plates and spacers.

[0785] Where the monitoring mark is (i) a different structure than the spacer, or (ii) the same structure as the spacer. B. Image capture improvements using a sample holder with micro-marks

[0786] BB-1. An apparatus for improving image capture of microfeatures in a sample, the apparatus comprising:

[0787] (c) a device as described in any of the preceding embodiments; and

[0788] (d) an imager for analyzing a sample containing or suspected of containing microfeatures;

[0789] The imager captures images, wherein at least one image includes both a portion of the sample and the monitoring marker.

[0790] BB-2. A system for improving image capture of microfeatures in a sample, the system comprising:

[0791] (a) A device as described in any of the preceding device embodiments;

[0792] (e) an imager for analyzing a sample containing or suspected of containing microfeatures; and

[0793] (f) A non-transitory computer readable medium having instructions that, when executed, use the marker as a parameter with an imaging processing method to adjust settings of an imager for a next image.

[0794] C. Imaging Analysis Using a Sample Holder with Micro-labeling

[0795] CC-1: An apparatus for improving analysis of images of microfeatures in a sample, the apparatus comprising:

[0796] (a) a device as described in any of the preceding device embodiments; and

[0797] (B) a computing device for receiving a label and an image of a sample containing or suspected of containing a microfeature;

[0798] Therein, the computing device runs an algorithm that uses the markers as parameters together with an imaging processing method to improve image quality in the image.

[0799] CC-2: A system for improving analysis of images of microfeatures in a sample, the system comprising:

[0800] (a) A device as described in any of the preceding embodiments;

[0801] (b) an imager for determining whether a sample contains or is suspected of containing microfeatures by taking one or more images of the sample and the markings; and

[0802] (c) A non-transitory computer-readable medium having instructions that, when executed, use the marker as a parameter with an imaging processing method to improve image quality in at least one image captured in (c).

[0803] CC-3: A computer program product for determining microfeatures in a sample, the program comprising computer program code means applied and adapted to:

[0804] (a) receiving an image of a sample and one or more monitoring markers, wherein the sample is added to the apparatus of any preceding apparatus claim, and wherein the image is captured by an imager; and

[0805] (b) Processing and analyzing the image to calculate the amount of microfeatures, wherein the analysis uses a detection model based on machine learning and information from monitoring markers provided by the image.

[0806] CC-4: A computing device for determining microfeatures in a sample, the computing device comprising a computing device that operates the algorithm in any embodiment of the present invention.

[0807] CC-5: A method, device, computer program product, or system as described in any of the preceding embodiments, wherein the improvement in image quality includes at least one selected from the group consisting of: denoising, image normalization, image sharpening, image scaling, alignment (e.g., for face detection), super-resolution, deblurring, and any combination thereof.

[0808] CC-6: A method, apparatus, computer program product or system as described in any of the preceding embodiments, wherein the imaging processing method includes at least one selected from the group consisting of: histogram-based operations, mathematical-based operations, convolution-based operations, smoothing operations, derivative-based operations, morphology-based operations, shading correction, image enhancement and / or restoration, segmentation, feature extraction and / or matching, object detection and / or classification and / or localization, image understanding and any combination thereof.

[0809] CC-6.1: A method, device, computer program product or system as described in any of the preceding embodiments, wherein the histogram-based operation includes at least one selected from the group consisting of: contrast stretching, equalization, minimum filtering, median filtering, maximum filtering and any combination thereof.

[0810] CC-6.2: A method, device, computer program product, or system as described in any of the preceding embodiments, wherein the mathematical-based operation includes at least one selected from the group consisting of: binary operations (e.g., NOT, OR, AND, XOR, and SUB), arithmetic-based operations (e.g., ADD, SUB, MUL, DIV, LOG, EXP, SQRT, TRIG, and INVERT), and any combination thereof.

[0811] CC-6.3: A method, apparatus, computer program product, or system as described in any of the preceding embodiments, wherein the convolution-based operation includes at least one selected from the group consisting of: an operation in the spatial domain, a Fourier transform, a DCT, an integer transform, an operation in the frequency domain, and any combination thereof.

[0812] CC-6.4: A method, device, computer program product or system as described in any of the preceding embodiments, wherein the smoothing operation includes at least one selected from the group consisting of: a linear filter, a uniform filter, a triangular filter, a Gaussian filter, a nonlinear filter, a median filter, a Kuwahara filter and any combination thereof.

[0813] CC-6.5: A method, device, computer program product or system as described in any of the preceding embodiments, wherein the derivative-based operation includes at least one selected from the group consisting of: first-order derivative operations, gradient filters, basic derivative filters, Prewitt gradient filters, Sobel gradient filters, variable gradient filters, Gaussian gradient filters, second-order derivative filters, basic second-order derivative filters, frequency-domain Laplacian operators, Gaussian second-order derivative filters, variable Laplacian filters, gradient-directed second-order derivative (SDGD) filters, third-order derivative filters, higher-order derivative filters (e.g., greater than third-order derivative filters), and any combination thereof.

[0814] CC-6.6: A method, apparatus, computer program product or system as described in any of the preceding embodiments, wherein the morphological-based operation includes at least one selected from the group consisting of: dilation, erosion, Boolean convolution, opening and / or closing, hit-miss operations, contours, skeletons, propagation, gray value morphological processing, grayscale dilation, grayscale erosion, grayscale opening, grayscale closing, morphological smoothing, morphological gradient, state Laplacian operator and any combination thereof.

[0815] CC-6.7: A method, device, computer program product, or system as described in any of the preceding embodiments, wherein image enhancement and / or restoration includes at least one selected from the group consisting of: sharpening, unsharpening, noise suppression, distortion suppression, and any combination thereof.

[0816] CC-6.8: A method, apparatus, computer program product or system as described in any of the preceding embodiments, wherein the segmentation comprises at least one selected from the group consisting of: threshold conversion, fixed threshold conversion, histogram-derived threshold conversion, Isodata algorithm, background symmetry algorithm, triangle algorithm, edge finding, gradient-based procedure, zero-crossing-based procedure, PLUS-based procedure, binary mathematical morphology, salt and pepper filtering, separation of objects with holes, filling holes in objects, removal of edge-contacting objects, exoskeleton, contacting objects, gray value mathematical morphology, top-hat transform, threshold processing, local contrast stretching and any combination thereof.

[0817] CC-6.9: A method, apparatus, computer program product or system as described in any of the preceding embodiments, wherein feature extraction and / or matching comprises at least one selected from the group consisting of: independent component analysis, contour plots, kernel principal component analysis, latent semantic analysis, partial least squares, principal component analysis, multifactor dimensionality reduction, nonlinear dimensionality reduction, multilinear principal component analysis, multilinear subspace learning, semidefinite embedding, autoencoders and any combination thereof.

[0818] NN1. An apparatus for analyzing microfeatures in a sample using an imager, the apparatus comprising:

[0819] (a) a solid surface comprising a sample contact area for contacting a sample comprising microfeatures; and

[0820] (B) one or more monitoring markers, wherein the monitoring marker:

[0821] v. Made of a different material from the sample;

[0822] vi. During the measurement of the microstructure, the sample is located inside the sample, wherein the sample forms a thin layer with a thickness of less than 200 μm on the sample contact area;

[0823] vii. have their lateral linear dimensions of about 1 μm (micrometer) or more, and

[0824] viii. having their lateral linear dimensions of about 1 μm (micrometer) or more, and

[0825] wherein at least one monitoring marker is imaged by an imager during the assay;

[0826] wherein the monitoring markers are used during the determination of the analyte; and the geometric parameters (e.g., shape and size) of the monitoring markers and / or the spacing between the monitoring markers (a) are predetermined and known prior to the determination of the analyte, and (b) are used as parameters in an algorithm for determining properties associated with the microfeatures.

[0827] NN2. An apparatus for analyzing microfeatures in a sample using an imager, the apparatus comprising:

[0828] a solid surface comprising a sample contact area for contacting a sample comprising microfeatures; and

[0829] One or more monitoring marks, wherein each monitoring mark comprises a protrusion or a groove from the solid surface, wherein:

[0830] ix. The protrusion or groove comprises a flat surface, which is substantially parallel to an adjacent surface, which is a portion of the solid surface adjacent to the protrusion or groove;

[0831] x. The distance between the flat surface and the adjacent surface is about 200 micrometers (μm) or less;

[0832] xi. The planar surface has (a) a linear dimension of at least about 1 μm or greater, and (b) an area having at least one linear dimension of 150 μm or less;

[0833] xii. imaging the planar surface of at least one monitoring mark by an imager used during determination of microfeatures; and

[0834] xiii. The shape of the planar surface, the size of the planar surface, the distance between the planar surface and an adjacent surface, and / or the spacing between monitoring marks are (a) predetermined and known before measuring the microfeatures, and (b) used as parameters in an algorithm for determining a property associated with the microfeatures;

[0835] NN3. An apparatus for analyzing microfeatures in a sample using an imager, the apparatus comprising:

[0836] A first plate, a second plate, a spacer, and one or more detection marks, wherein:

[0837] xiii. The first plate and the second plate are movable relative to each other into different configurations;

[0838] xiv. Each of the first plate and the second plate comprises an inner surface comprising a sample contact area for contacting a sample comprising microfeatures;

[0839] xv. One or both of the first plate and the second plate comprises a spacer permanently fixed to the inner surface of the respective plate;

[0840] xvi. Each of the first plate and the second plate comprises an inner surface comprising a sample contact area for contacting a sample comprising microfeatures;

[0841] xvii. The monitoring mark is made of a different material from the sample;

[0842] xviii. During the measurement of the microstructure, the monitoring mark is located inside the sample, wherein the sample forms a thin layer with a thickness of less than 200 μm on the sample contact area; and

[0843] xix. The monitoring mark has a lateral linear dimension of about 1 μm (micrometer) or more and has at least one lateral linear dimension of 300 μm or less;

[0844] wherein at least one monitoring marker is imaged by an imager during the assay;

[0845] wherein microfeatures are used during the determination; and the shape of the planar surface, the size of the planar surface, the distance between the planar surface and an adjacent surface, and / or the spacing between monitoring marks are (a) predetermined and known before the determination of the microfeatures is performed, and (b) used as parameters in an algorithm that determines a property associated with the microfeatures;

[0846] wherein one of the configurations is an open configuration in which the two plates are partially or completely separated, the spacing between the plates is not adjusted by the spacer, and the sample is deposited on one or both of the plates; and

[0847] wherein another of the configurations is a closed configuration, which is configured after the sample is deposited in an open configuration and the plates are forced to reach the closed configuration by applying a compressive force on the force area; and in the closed configuration, at least a portion of the sample is compressed by the two plates into a layer of highly uniform thickness and is essentially stagnant relative to the plates, wherein the uniform thickness of the layer is limited by the sample contact area of ​​the two plates and adjusted by the plates and spacers.

[0848] The monitoring marker is (i) a different structure from the spacer, or (ii) the same structure as the spacer.

[0849] NN4. An apparatus for analyzing microfeatures in a sample using an imager, the apparatus comprising:

[0850] A first plate, a second plate, a spacer, and one or more detection marks, wherein:

[0851] xx. The first plate and the second plate are movable relative to each other into different configurations;

[0852] xxi. Each of the first plate and the second plate comprises an inner surface comprising a sample contact area for contacting a sample comprising microfeatures;

[0853] xxii. One or both of the first plate and the second plate comprises a spacer permanently fixed to the inner surface of the respective plate;

[0854] xxiii. The spacers have a substantially uniform height equal to or less than 200 microns and a fixed spacer spacing (ISD).

[0855] xxiv. Each monitoring mark comprises a protrusion or groove on one or both sample contact areas;

[0856] xxv. The protrusion or groove comprises a flat surface that is substantially parallel to an adjacent surface that is a portion of a solid surface adjacent to the protrusion or groove;

[0857] xxvi. The distance between the flat surface and the adjacent surface is about 200 micrometers (μm) or less;

[0858] xxvii. The planar surface has (a) a linear dimension of at least about 1 μm or greater, and (b) an area having at least one linear dimension of 150 μm or less;

[0859] xxviii. imaging the planar surface of at least one monitoring mark by an imager used during determination of microfeatures; and

[0860] xxix. The shape of the planar surface, the size of the planar surface, the distance between the planar surface and an adjacent surface, and / or the spacing between monitoring marks are (a) predetermined and known prior to measuring the microfeatures, and (b) used as parameters in an algorithm for determining a property associated with the microfeatures;

[0861] wherein one of the configurations is an open configuration in which the two plates are partially or completely separated, the spacing between the plates is not adjusted by the spacer, and the sample is deposited on one or both of the plates; and

[0862] wherein another of the configurations is a closed configuration, which is configured after the sample is deposited in an open configuration and the plates are forced to reach the closed configuration by applying a compressive force on the force area; and in the closed configuration, at least a portion of the sample is compressed by the two plates into a layer of highly uniform thickness and is essentially stagnant relative to the plates, wherein the uniform thickness of the layer is limited by the sample contact area of ​​the two plates and adjusted by the plates and spacers.

[0863] The monitoring marker is (i) a different structure from the spacer, or (ii) the same structure as the spacer.

[0864] NN5. An apparatus for image-based determination, comprising:

[0865]

[00136] The device of any preceding embodiment, wherein the device has at least five monitoring marks, wherein at least three of the monitoring marks are not aligned in a straight line.

[0866] NN6. An apparatus for analyzing microfeatures in a sample using an imager, the apparatus comprising:

[0867] (c) a device as described in any of the preceding embodiments; and

[0868] (d) Imager for measuring samples containing microfeatures.

[0869] NN7. A system for performing an imaging-based assay, the system comprising:

[0870] (d) A device as described in any of the preceding device embodiments;

[0871] (e) an imager for measuring a sample comprising microfeatures; and

[0872] (f) A non-transitory computer-readable medium containing instructions that, when executed, utilize monitoring signatures of the device to determine a characteristic associated with a micro-feature.

[0873] NN8. A system for analyzing microfeatures in a sample using an imager, the system comprising:

[0874] (a) A device as described in any of the preceding device embodiments;

[0875] (h) an imager for measuring a sample comprising microfeatures; and

[0876] (i) A non-transitory computer-readable medium comprising instructions that, when executed, utilize monitoring signatures of the device to determine a property associated with a micro-feature, wherein the instructions comprise machine learning.

[0877] NN9. A method for determining microfeatures in a sample using an imager, comprising:

[0878] (d) obtaining the device, apparatus or system described in any one of the preceding embodiments;

[0879] (e) obtaining a sample and depositing the sample on a sample contact area in the device, apparatus, or system of (a), wherein the sample comprises microfeatures; and

[0880] (f) Determination of microfeatures.

[0881] NN10. A method for determining microfeatures in a sample using an imager, comprising:

[0882] (d) obtaining the device, apparatus or system described in any one of the preceding embodiments;

[0883] (e) obtaining a sample and depositing the sample on a sample contact area in the device, apparatus, or system of (a), wherein the sample comprises microfeatures; and

[0884] (f) determining microfeatures, wherein the determining comprises the step of using machine learning.

[0885] T1. A method for determining a true lateral dimension (TLD) of a sample on a sample holder from a distorted image, the method comprising:

[0886] (a) obtaining the device of any preceding embodiment, wherein the device comprises one or more monitoring markers in the sample contacting area;

[0887] (b) obtaining an imager, computing hardware, and a non-transitory computer-readable medium containing an algorithm;

[0888] (c) depositing a thin sample layer comprising microfeatures in a sample contact region of the device of (a);

[0889] (d) taking one or more images of the thin sample layer together with the monitoring markers using an imager, wherein the imager is positioned above the thin sample layer; and

[0890] (e) using an algorithm to determine the true lateral dimensions of the sample;

[0891] in,

[0892] (i) the algorithm is a computer code executed on a computer system; and

[0893] (ii) The algorithm uses images of monitoring markers as parameters.

[0894] T2. A method for determining a true lateral dimension (TLD) of a sample on a sample holder from a distorted image, the method comprising:

[0895] (a) obtaining the device of any preceding embodiment, wherein the device comprises one or more monitoring markers in the sample contacting area;

[0896] (b) obtaining an imager, computing hardware, and a non-transitory computer-readable medium containing an algorithm;

[0897] (c) depositing a thin sample layer comprising microfeatures in a sample contact region of the device of (a);

[0898] (d) taking one or more images of the thin sample layer together with the monitoring markers using an imager, wherein the imager is positioned above the thin sample layer; and

[0899] (e) using the algorithm to determine the real lateral dimensions and coordinates of the imaged sample in the real world by physical measurements (e.g., micrometers);

[0900] in,

[0901] (i) the algorithm is a computer code executed on a computer system; and

[0902] (ii) The algorithm uses images of monitoring markers as parameters.

[0903] T3. A device, method or system as described in any of the preceding embodiments, wherein microfeatures and monitoring marks from the sample are disposed within a sample holding device.

[0904] T4. An apparatus, method or system as described in any of the preceding embodiments, wherein the determining comprises detecting and locating a monitoring marker in an image of the sample captured by an imager.

[0905] T5. An apparatus, method or system as described in any of the preceding embodiments, wherein the determining includes generating a monitoring marker grid based on monitoring markers detected from an image of the sample captured by the imager.

[0906] T6. An apparatus, method or system as described in any of the preceding embodiments, wherein the determining comprises calculating a homography transformation based on a generated monitoring marker grid.

[0907] T7. An apparatus, method or system as described in any of the preceding embodiments, wherein the determining comprises estimating the TLD based on a homography transformation and determining the area, size and concentration of the detected microfeatures in an image-based measurement.

[0908] T8. A method, apparatus or system as described in any of the preceding embodiments, wherein the TLD estimation is based on a region in a sample image captured by an imager, comprising:

[0909] (a) obtaining a sample;

[0910] (b) adding the sample to a sample holding device such as a QMAX device, wherein a monitoring marker is present, wherein the monitoring marker is not immersed in the sample and resides in the device, which can be imaged from the top by an imager in an image-based assay;

[0911] (c) capturing an image of the sample in the sample addition device including the microfeatures and monitoring marks;

[0912] (d) detecting the monitoring mark in the sample image captured by the imager;

[0913] (e) segmenting the sample image into non-overlapping regions;

[0914] (f) generating a region-based marker grid for each of the non-overlapping regions having more than five non-collinear monitoring markers detected in the local region;

[0915] (g) generating a marker grid for all other regions not in (f) based on the monitoring markers detected from the sample image captured by the imager;

[0916] (h) computing a region-specific homography transform for each region in (f) based on its own region-based labeling grid generated by (f);

[0917] (i) Based on the label grid generated in (g), compute homography transformations for all other regions not in (f);

[0918] (j) Estimate the region-based TLD for each region in (f) based on the region-based homography transformation of (g);

[0919] (k) estimating TLDs for other regions not in (f) based on the homography transformation of (i); and

[0920] (L) Application of the estimated TLDs from (j) and (k) to determine the area and concentration of microfeatures imaged in each image partition in an image-based assay.

[0921] T9. A method, device or system as described in any of the preceding embodiments, wherein the monitoring marks in the sample holding device are distributed according to a fixed spacing pattern with a defined spacing period.

[0922] T10. The method, device or system of any of the preceding embodiments, wherein the monitoring marker is detected and used as a detectable anchor point for calibrating and improving measurement accuracy in image-based assays.

[0923] T11. A method, device or system as described in any of the above embodiments, wherein the detection of the monitoring marks in the sample image captured by the imager utilizes the fixed intervals of the distribution of the monitoring marks in the sample holding device to perform error correction and / or detection reliability.

[0924] T12. A method, device or system as described in any of the preceding embodiments, wherein detection, identification, area and / or shape contour estimation of monitoring markers in image-based assays is performed by machine learning (ML), and machine learning uses ML-based monitoring marker detection models and equipment, which are constructed or trained based on images captured by an imager on the device in the image-based assay.

[0925] T13. A method, device or system as described in any of the preceding embodiments, wherein detection, identification, area and / or shape contour estimation of the monitoring marker in an image-based assay is performed by image processing or image processing combined with machine learning.

[0926] T14. A method, apparatus or system as described in any of the preceding embodiments, wherein the detected monitoring marker is applied to TLD estimation in an image-based assay to calibrate the system and / or improve measurement accuracy in the image-based assay.

[0927] T15. A method, device or system as described in any of the preceding embodiments, wherein the detected monitoring markers are applied in image-based determinations to calibrate the system and / or improve measurement accuracy, without limitation to microfeature size, volume and / or concentration estimation.

[0928] T16. A method, device or system as described in any of the preceding embodiments, wherein detection of monitoring marks and / or TLD estimation is applied to fault detection in image-based measurements, including but not limited to detecting defects in the sample holding device, misalignment of the sample holding device in the imager, and / or focusing failure of the imager.

[0929] T17. A method, apparatus or system as described in any of the preceding embodiments, wherein the monitoring marker is detected as an anchor point for application in a system for estimating the area of ​​an object in an image-based measurement, comprising:

[0930] i. adding a sample to a sample holding device having a monitoring marker resident in the device in an image-based assay;

[0931] ii. capturing an image of the sample in the sample holding device including micro-features and monitoring marks; and

[0932] iii. Detect monitoring marks in an image of the sample taken by an imager on a sample holding device, determine the TLD and calculate an area estimate in an image-based assay to determine the size of the imaged object based on physical dimensions from pixels in the image to microns in the real world.

[0933] T18. A method, device or system as described in any of the preceding embodiments, wherein the system comprises:

[0934] i. Detect monitoring marks in digital images;

[0935] ii. Generate monitoring mark grid;

[0936] iii. Calculating image transformation based on monitoring marker grid; and

[0937] iv. Estimation of the area of ​​objects in sample images and their physical size in the real world in image-based measurements.

[0938] T19. A method, device or system as described in any of the preceding embodiments, wherein a monitoring mark grid generated based on the detected monitoring marks is used to calculate a homography transformation to estimate the TLD, the area of ​​the object in the image of the sample taken by the imager, and the physical size of the object in the real world.

[0939] T20. A method, device or system as described in any of the preceding embodiments, wherein the method comprises:

[0940] i. segmenting an image of a sample captured by an imager in an image-based assay into non-overlapping regions;

[0941] ii. Detect local monitoring markers in the image;

[0942] iii. If more than 5 non-collinear monitoring markers are detected in the region, a region-based marker grid is generated for the region;

[0943] iv. generating a marker grid for all other regions based on the monitoring markers detected in the image of the sample taken by the imager;

[0944] v. For each region in (iii), calculate the region-based homography transformation based on the generated region-based label grid;

[0945] vi. Based on the label grid generated in (iv), calculate the homography transformation for all other regions in (iii); and

[0946] vii. Estimate the TLD of each region based on the homography transformation generated by (v) and (vi), and determine the object area of ​​each region in the sample image and its size in the real world in the image-based measurement.

[0947] T21. The method, device or system of any of the preceding embodiments, wherein the assay is a medical, diagnostic, chemical or biological test.

[0948] T22. The method, device or system of any of the preceding embodiments, wherein the microfeatures are cells.

[0949] T23. A method, device or system as described in any of the preceding embodiments, wherein the microfeatures are blood cells.

[0950] T24. A method, device or system as described in any of the preceding embodiments, wherein the microfeature is a protein, peptide, DNA, RNA, nucleic acid, small molecule, cell or nanoparticle.

[0951] T25. A method, device or system as described in any of the preceding embodiments, wherein the microfeature comprises a tag.

[0952] T26. A method, apparatus or system as described in any of the preceding embodiments, wherein the algorithm comprises a computer program product, the computer program product comprising computer program code means, the computer program code means being adapted to:

[0953] (a) receiving an image of a sample, wherein the sample is added to the QMAX device and the image is captured by an imager connected to the QMAX device, wherein the image includes the sample and the monitoring marker;

[0954] (b) analyzing the image using the detection model and generating a 2D data array of the image, wherein the 2D data array includes probability data of the micro-feature at each position in the image, and the detection model is established through a training process, the training process comprising:

[0955] i. feeding an annotated dataset to a convolutional neural network, wherein the annotated dataset is from samples of the same type and for the same microfeatures as the test sample; and

[0956] ii. Train and build a detection model through convolution; and

[0957] (c) analyzing the 2D data array to detect local signal peaks by:

[0958] i. Signal list processing, or

[0959] ii. Local search processing; and

[0960] (g) Calculate the amount of micro-features based on the local signal peak information.

[0961] T27. A method, apparatus or system as described in any of the preceding embodiments, wherein the algorithm comprises a computer program product, the computer program product comprising computer program code means, the computer program code means being applied and adapted to:

[0962] (a) a pattern representing the derivation between a pixel contour map of an object in a sample and an object in an image of the sample, the image being taken by an imager on a sample holding device,

[0963] (b) numerically reconstructing an image of at least one object detected from the derived pattern in the image of the sample and generating a contour mask surrounding the object identified by the derivation module, said object being in focus in the derivation module,

[0964] (c) identifying at least one portion of the image of the sample with respect to at least one object in the selected portion of the image of the sample, and

[0965] (d) computing at least one feature unique to the at least one portion to identify an object in a selected portion of an image of the sample captured by the imager,

[0966] (e) calculating the count and concentration of the detection object in the selected portion of the image of the sample based on the selected portion,

[0967] In this case, the program runs on the computing device or in a computing cloud via a network connection.

[0968] T28. A method, apparatus or system as described in any of the preceding embodiments, wherein the algorithm comprises a computer program product, the computer program product comprising computer program code means, the computer program code means being adapted to:

[0969] (a) receiving an image of a sample, wherein the sample is added to the QMAX device and the image is captured by an imager connected to the QMAX device, wherein the image includes the sample and the monitoring marker; and

[0970] (b) analyzing the image to calculate the amount of microfeatures, wherein the analysis uses a detection model based on machine learning and information from monitoring markers provided by the image.

[0971] The method, apparatus or system as described in any of the preceding embodiments further comprises a computer-readable storage medium or a memory storage unit, which comprises the computer program described in any of the preceding embodiments.

[0972] The method, device or system as described in any of the preceding embodiments further includes a computing device or a mobile device of the computing device described in any of the preceding embodiments.

[0973] The method, apparatus or system as described in any of the preceding embodiments further comprises a computing device or a mobile device, which comprises the computer program product described in any of the preceding embodiments.

[0974] The method, apparatus or system as described in any of the preceding embodiments further comprises a computing device or a mobile device comprising a computer-readable storage medium or a storage unit as described in any of the preceding embodiments.

[0975] A device for analyzing a sample, comprising:

[0976] a first plate, a second plate, a surface amplification layer, and a capture agent, wherein

[0977] (a) the first and second plates are movable relative to each other into different configurations and have sample contact areas on their respective surfaces for contacting a sample containing a target analyte,

[0978] (b) a surface amplification layer on one of the sample contact areas,

[0979] (c) immobilizing a capture reagent on the surface amplification layer, wherein the capture reagent specifically binds to the target analyte,

[0980] When the target analyte is close to the surface amplification layer, the surface amplification layer amplifies the optical signal from the target analyte or the label attached to the target analyte more strongly than when the distance is micrometers or farther.

[0981] One of the configurations is an open configuration, wherein the average spacing between the inner surfaces of the two plates is at least 200 μm; and

[0982] Another of these configurations is a closed configuration, wherein at least a portion of the sample is between two plates, and the average spacing between the inner surfaces of the plates is less than 200 μm.

[0983] A device for analyzing a sample, comprising:

[0984] a first plate, a second plate, a surface amplification layer, and a capture agent, wherein

[0985] (d) the first and second plates are movable relative to each other into different configurations and have sample contact areas on their respective surfaces for contacting a sample containing a target analyte,

[0986] (e) a surface amplification layer on one of the sample contact areas,

[0987] (f) immobilizing a capture reagent on the surface amplification layer, wherein the capture reagent specifically binds to the target analyte,

[0988] When the target analyte is close to the surface amplification layer, the surface amplification layer amplifies the optical signal from the label attached to the target analyte more strongly than when the distance is micrometers or more.

[0989] One of the configurations is an open configuration in which the average spacing between the inner surfaces of the two plates is at least 200 μm;

[0990] Another of the configurations is a closed configuration, wherein at least a portion of the sample is between two plates, and the average spacing between the inner surfaces of the plates is less than 200 μm;

[0991] Wherein the thickness of the sample in the closed configuration, the concentration of dissolved labels in the sample in the closed configuration, and the magnification factor of the surface magnification layer are configured such that any labels directly or indirectly bound to the capture agent are visible in the closed configuration without washing away unbound labels.

[0992] An apparatus comprises the device according to any one of the preceding embodiments and a reader for reading the device.

[0993] A homogeneous assay method using the device of any of the preceding embodiments, wherein the thickness of the sample in the closed configuration, the concentration of the label and the magnification factor of the amplification surface are configured to make the label bound to the amplification surface visible without washing away unbound label.

[0994] A method as described in any of the preceding embodiments, wherein the method is performed by:

[0995] Obtain the device according to any one of the embodiments;

[0996] When the plates are in the open configuration, the sample is deposited on one or both of the plates.

[0997] closing the panels to a closed configuration; and

[0998] The sample contact area is read using a reading device to generate a signal image.

[0999] A device or method as in any of the preceding embodiments, wherein the label bound to the magnifying surface is visible within 60 seconds.

[1000] A device or method as in any of the preceding embodiments, wherein the method is a homogeneous assay, wherein the signal is read without using a wash step to remove any biological material or label not bound to the amplification surface.

[1001] An apparatus or method as described in any of the preceding embodiments, wherein the tag bound to the magnification surface is read by a pixelated reading method.

[1002] An apparatus or method as described in any of the preceding embodiments, wherein the labels bound to the amplification surface are read by a one-time lumped reading method.

[1003] The device or method of any preceding embodiment, wherein the assay has a detection sensitivity of 0.1 nM or less.

[1004] The device or method of any of the preceding embodiments, wherein the method removes biological material or labels not bound to the amplification surface by sponging prior to reading.

[1005] A device or method as in any of the preceding embodiments, wherein the signal amplification layer comprises D2PA.

[1006] As in any one of the aforementioned embodiments, the signal amplification layer comprises a metal material layer.

[1007] A device or method as described in any of the preceding embodiments, wherein the signal amplifying layer comprises a continuous metal film made of a material selected from the group consisting of gold, silver, copper, aluminum, alloys thereof, and combinations thereof.

[1008] An apparatus or method as in any of the preceding embodiments, wherein the different metal layers locally enhance or act as reflectors, or both, to enhance the optical signal.

[1009] As in any of the aforementioned embodiments, the device or method, wherein the signal amplification layer comprises a metal material layer and a dielectric material on the metal material layer, wherein the capture agent is on the dielectric material.

[1010] The device or method as described in any of the preceding embodiments, wherein the metal material layer is a uniform metal layer, a nanostructured metal layer, or a combination thereof.

[1011] An apparatus or method as described in any of the preceding embodiments, wherein the signal is amplified by plasma enhancement.

[1012] The device or method of any preceding embodiment, wherein the determining comprises detecting the label by Raman scattering.

[1013] The device or method of any preceding embodiment, wherein the capture agent is an antibody.

[1014] The device or method of any preceding embodiment, wherein the capture agent is a polynucleotide.

[1015]

[00136] The device or method of any of the preceding embodiments, wherein the device further comprises a spacer secured to one of the plates, wherein the spacer adjusts the spacing between the first plate and the second plate in the closed configuration.

[1016] A device or method as in any of the preceding embodiments, wherein the amplification factor of the surface amplification layer is adjusted to make visible the optical signal from a single tag directly or indirectly bound to the capture agent.

[1017] The device or method of any of the preceding embodiments, wherein the amplification factor of the surface amplification layer is adjusted to make visible the optical signal from single tags directly or indirectly bound to the capture agent, wherein the visible single tags bound to the capture agent are individually counted.

[1018] The device or method of any of the preceding embodiments, wherein the spacing between the first plate and the second plate in the closed configuration is configured to provide a saturation binding time of the target analyte to the capture agent of 300 seconds or less.

[1019] The device or method of any of the preceding embodiments, wherein the spacing between the first plate and the second plate in the closed configuration is configured to provide a saturation binding time of the target analyte to the capture agent of 60 seconds or less.

[1020] A device or method as in any of the preceding embodiments, wherein the amplification factor of the surface amplification layer is adjusted to make the optical signal from a single tag visible.

[1021] The method and device of any of the preceding embodiments, wherein the capture agent is a nucleic acid.

[1022] The device or method of any preceding embodiment, wherein the capture agent is a protein.

[1023] The device or method of any preceding embodiment, wherein the capture agent is an antibody.

[1024] A device or method as in any of the preceding embodiments, wherein the sample contact area of ​​the second plate has a reagent storage site, and in the closed configuration, the storage site is approximately above the binding site on the first plate.

[1025] A device or method as described in any of the preceding embodiments, wherein the reagent storage site comprises a detection agent that binds to the target analyte.

[1026] The device or method of any preceding embodiment, wherein the detection agent comprises a label.

[1027] The device or method of any of the preceding embodiments, wherein both the capture agent and the detection agent are bound to the target analyte to form a sandwich comprising a tag.

[1028] As in any one of the aforementioned embodiments, the signal amplification layer comprises a metal material layer.

[1029] As in any of the aforementioned embodiments, the device or method, wherein the signal amplification layer comprises a metal material layer and a dielectric material on the metal material layer, wherein the capture agent is on the dielectric material.

[1030] The device or method as described in any of the preceding embodiments, wherein the metal material layer is a uniform metal layer, a nanostructured metal layer, or a combination thereof.

[1031] A device or method as described in any of the foregoing embodiments, wherein the amplification layer comprises a metal material layer and a dielectric material above the metal material layer, wherein the capture agent is on the dielectric material, and the dielectric material layer has a thickness of: 0.5nm, 1nm, 5nm, 10nm, 20nm, 50nm, 100nm, 200nm, 500nm, 1000nm, 2μm, 3μm, 5μm, 10μm, 20μm, 30μm, 50μm, 100μm, 200μm, 500μm, or in a range between any two of the values.

[1032] An apparatus or method as in any of the preceding embodiments, wherein the method further comprises quantifying the signal in the image region to provide an estimate of the amount of one or more analytes in the sample.

[1033] A device or method as in any of the preceding embodiments, wherein the method comprises identifying and counting individual binding events between analytes and capture agents in an image region, thereby providing an estimate of the amount of one or more analytes in the sample.

[1034] A device or method as described in any of the preceding embodiments, wherein the identification and counting steps include: (1) determining the local intensity of the background signal, (2) determining the local signal intensity of one label, two labels, three labels, and four or more labels; and (3) determining the total number of labels in the imaging area.

[1035] An apparatus or method as described in any of the preceding embodiments, wherein the identification and counting steps comprise: (1) determining the local spectrum of the background signal, (2) determining the local signal spectrum of one tag, two tags, three tags, and four or more tags; and (3) determining the total number of tags in the imaging area.

[1036] An apparatus or method as described in any of the preceding embodiments, wherein the identification and counting steps comprise: (1) determining the local Raman signature of the background signal, (2) determining the local signal Raman signature of one tag, two tags, three tags, and four or more tags; and (3) determining the total number of tags in the imaging area.

[1037] An apparatus or method as described in any of the preceding embodiments, wherein the identifying and counting steps include determining one or more of local intensity, spectral and Raman characteristics.

[1038] An apparatus or method as described in any of the preceding embodiments, wherein the method comprises quantifying a one-time lumped signal in an image region, thereby providing an estimate of the amount of one or more analytes in the sample.

[1039] A device or method as described in any of the preceding embodiments, wherein the sample contact area of ​​the second plate has a reagent storage site, and in the closed configuration, the storage site is located substantially above the binding site on the first plate.

[1040] The device or method as described in any of the preceding embodiments, wherein the method further comprises the step of labeling the target analyte with a detection agent.

[1041] The device or method of any preceding embodiment, wherein the detection agent comprises a label.

[1042] A device or method as in any of the preceding embodiments, wherein both the capture agent and the detection agent are bound to the target analyte to form a sandwich.

[1043]

[00136] The device or method of any of the preceding embodiments, wherein the method further comprises measuring the volume of the sample in the area imaged by the reader.

[1044] The device or method of any of the preceding embodiments, wherein the target analyte is a protein, a peptide, a DNA, an RNA, a nucleic acid, a small molecule, a cell, or a nanoparticle.

[1045] An apparatus or method as described in any of the preceding embodiments, wherein the image shows the location, local intensity and local spectrum of the signal.

[1046] The device or method of any preceding embodiment, wherein the signal is a luminescent signal selected from the group consisting of fluorescent, electroluminescent, chemiluminescent, and electrochemiluminescent signals.

[1047] A device or method as described in any of the preceding embodiments, wherein the signal is a Raman scattering signal.

[1048] A device or method as in any of the preceding embodiments, wherein the signal is a force due to local electrical, local mechanical, local biological, or local optical interaction between the plate and a reading device.

[1049] The method and apparatus according to any of the above embodiments, wherein the spacer has a cylindrical shape and a nearly uniform cross-section.

[1050] The method or apparatus as in any of the above embodiments, wherein the spacer pitch (SD) is equal to or less than about 120 μm (micrometers).

[1051] The method or apparatus as in any of the above embodiments, wherein a spacer pitch (SD) is equal to or less than about 100 μm (micrometers).

[1052] The method and apparatus according to any of the above embodiments, wherein the fourth power of the spacer spacing (ISD) divided by the thickness (h) and Young's modulus (E) of the flexible board (ISD 4 / (hE)) is 5x10 6 μm 3 / GPa or less.

[1053] The method and apparatus according to any of the above embodiments, wherein the fourth power of the spacer spacing (ISD) divided by the thickness (h) and Young's modulus (E) of the flexible board (ISD 4 / (hE)) is 5x10 5 μm 3 / GPa or less.

[1054] A method and apparatus according to any of the above embodiments, wherein the spacers have a columnar shape, a substantially flat top surface, a predetermined substantially uniform height, and a predetermined constant spacer spacing, the spacer spacing being at least about 2 times larger than the size of the analyte, wherein the Young's modulus of the spacer multiplied by the filling factor of the spacer is equal to or greater than 2 MPa, wherein the filling factor is the ratio of the spacer contact area to the total plate area, and wherein for each spacer, the ratio of the lateral dimension of the spacer to its height is at least 1 (one).

[1055] The method and apparatus according to any of the above embodiments, wherein the spacers have a columnar shape, a substantially flat top surface, a predetermined substantially uniform height, and a predetermined constant spacer spacing, the spacer spacing being at least about 2 times greater than the size of the analyte, wherein the Young's modulus of the spacer multiplied by the packing factor of the spacer is equal to or greater than 2 MPa, wherein the packing factor is the ratio of the spacer contact area to the total plate area, and wherein for each spacer, the ratio of the lateral dimension of the spacer to its height is at least 1 (one), wherein the fourth power of the spacer spacing (ISD) divided by the thickness (h) of the flexible plate and the Young's modulus (E) (ISD) 4 / (hE)) is 5x10 6 μm 3 / GPa or less.

[1056] The method and apparatus according to any of the above embodiments, wherein the ratio of the spacer pitch of the spacers to the average width of the spacers is 2 or greater, and the filling factor of the spacers multiplied by the Young's modulus of the spacers is 2 MPa or greater.

[1057] The method and device according to any of the above embodiments, wherein the analyte is a protein, a peptide, a nucleic acid, a synthetic compound or an inorganic compound.

[1058] The method and device according to any of the above embodiments, wherein the sample is selected from the following biological samples: amniotic fluid, aqueous humor, vitreous humor, blood (e.g., whole blood, fractionated blood, plasma or serum), breast milk, cerebrospinal fluid (CSF), cerumen (ear wax), chyle, chyme, endolymph, perilymph, feces, breath, gastric acid, gastric juice, lymph, mucus (including nasal drainage and sputum), pericardial fluid, peritoneal fluid, pleural fluid, pus, rheumatic fluid, saliva, exhaled condensate, sebum, semen, sputum, sweat, synovial fluid, tears, vomitus and urine.

[1059] The method and apparatus according to any of the above embodiments, wherein the spacer has a pillar shape, and a ratio of a width to a height of the pillar is equal to or greater than 1.

[1060] A method and apparatus according to any preceding embodiment, wherein the sample deposited on one or both plates has an unknown volume.

[1061] The method and apparatus according to any of the above embodiments, wherein the spacers have the shape of pillars, and the pillars have a substantially uniform cross-section.

[1062] The method and device according to any of the above embodiments, wherein the sample is used to detect, purify and quantify chemical compounds or biomolecules associated with the stage of certain diseases.

[1063] A method and device according to any of the above embodiments, wherein the sample is related to infectious and parasitic diseases, injuries, cardiovascular diseases, cancer, mental disorders, neuropsychiatric disorders, lung diseases, kidney diseases, and other and organic diseases.

[1064] A method and device according to any of the above embodiments, wherein the sample involves detection, purification and quantification of microorganisms.

[1065] A method and apparatus according to any of the above embodiments, wherein the sample involves viruses, fungi and bacteria from the environment (eg, food, water, soil).

[1066] According to the method and device described in any of the above embodiments, the sample involves the detection and quantification of chemical compounds or biological samples (e.g., toxic waste, anthrax) that pose a threat to food safety or national security.

[1067] A method and apparatus as in any preceding embodiment, wherein the sample is related to quantification of a vital parameter in a medical or physiological monitor.

[1068] A method and device according to any of the above embodiments, wherein the sample is related to glucose, blood, oxygen level, complete blood count.

[1069] The method and device according to any of the above embodiments, wherein the sample involves detecting and quantifying specific DNA or RNA from a biological sample.

[1070] A method and apparatus according to any of the above embodiments, wherein the sample involves sequencing and comparison of genetic sequences in DNA in chromosomes and mitochondria for genomic analysis.

[1071] A method or apparatus according to any preceding embodiment, wherein the sample involves detecting a reaction product, such as during drug synthesis or purification.

[1072] According to any of the above embodiments, the method and device, wherein the sample is cells, tissues, body fluids and feces.

[1073] According to the method and device described in any of the above embodiments, the sample is a sample in the fields of human, veterinary, agriculture, food, environment and drug testing.

[1074] The method and device according to any of the above embodiments, wherein the sample is a biological sample selected from hair, nail, earwax, breath, connective tissue, muscle tissue, neural tissue, epithelial tissue, cartilage, cancerous sample or bone.

[1075] The method and apparatus as in any of the above embodiments, wherein the spacer pitch is in the range of 5 μm to 120 μm.

[1076] The method and apparatus according to any of the above embodiments, wherein the spacer pitch is in the range of 120 μm to 200 μm.

[1077] The method and apparatus according to any of the above embodiments, wherein the flexible plate has a thickness in the range of 20 μm to 250 μm and a Young's modulus in the range of 0.1 GPa to 5 GPa.

[1078] The method and apparatus according to any of the above embodiments, wherein for the flexible board, the thickness of the flexible board multiplied by the Young's modulus of the flexible board is in the range of 60 to 750 GPa-μm.

[1079] The method and apparatus according to any of the above embodiments, wherein the uniform thickness of the sample layer is at least 1 mm 2 The lateral area is uniform.

[1080] The method and apparatus according to any of the above embodiments, wherein the uniform thickness of the sample layer is at least 3 mm 2 The lateral area is uniform.

[1081] The method and apparatus according to any of the above embodiments, wherein the uniform thickness of the sample layer is at least 5 mm 2 is uniform over the lateral area.

[1082] The method and apparatus according to any of the above embodiments, wherein the uniform thickness sample layer is at least 10 mm 2 is uniform over the lateral area.

[1083] The method and apparatus according to any of the above embodiments, wherein the uniform thickness of the sample layer is at least 20 mm 2 is uniform over the lateral area.

[1084] The method and apparatus as described in any of the preceding embodiments, wherein the uniform thickness of the sample layer is at least 20-100 mm 2 is uniform over the lateral area.

[1085] A method or apparatus as in any preceding embodiment, wherein the uniform thickness sample layer has a thickness uniformity of up to + / - 5% or better.

[1086] A method or apparatus as in any preceding embodiment, wherein the uniform thickness sample layer has a thickness uniformity of up to + / - 10% or better.

[1087] A method or apparatus as in any preceding embodiment, wherein the uniform thickness sample layer has a thickness uniformity of up to + / - 20% or better.

[1088] A method or apparatus as in any of the preceding embodiments, wherein the uniform thickness sample layer has a thickness uniformity of up to + / - 30% or better.

[1089] A method, apparatus, computer program product or system as described in any of the above embodiments, having five or more monitoring marks, wherein at least three of the monitoring marks are not in a straight line.

[1090] A method, apparatus, computer program product or system as described in any of the preceding embodiments, wherein each of the plates includes a force zone on its respective outer surface for applying an imprecise pressing force to press the plates together.

[1091] The method, apparatus, computer program product, or system of any of the preceding embodiments, wherein one or both of the plates are flexible;

[1092] A method, apparatus, computer program product or system as described in any of the preceding embodiments, wherein the fourth power of the spacer spacing (ISD) divided by the thickness (h) of the flexible board and the Young's modulus (E) (ISD 4 / (hE)) is 5x10 6 μm 3 / GPa or less.

[1093] The method, apparatus, computer program product, or system of any of the preceding embodiments, wherein at least one of the spacers is within the sample contacting region;

[1094] A method, apparatus, computer program product or system as described in any of the preceding embodiments, wherein a broad specification of analytes.

[1095] A method, apparatus, computer program product or system as described in any of the preceding embodiments, wherein the algorithm has a wide specification.

[1096] A method, apparatus, computer program product or system as described in any of the preceding embodiments, wherein the wide format of the stamping is forced and pressed by hand.

[1097] A device, system or method as described in any of the above embodiments, wherein the algorithm is stored on a non-transitory computer readable medium, and wherein the algorithm includes instructions that, when executed, perform a method for determining a characteristic corresponding to an analyte using a monitoring marker of the device.

[1098] Some examples of tags

[1099] In the present invention, in some embodiments, the mark has the same shape as the spacer.

[1100] In some embodiments, the markings are regularly spaced or non-regularly spaced.

[1101] In some embodiments, the distance between two marks is predetermined and known, but the absolute coordinates on the board are unknown.

[1102] In some embodiments, the marking has a predetermined and known shape.

[1103] In some embodiments, the markings are configured to have a distribution in the plate such that regardless of the position of the plate, the markings are always present in the field of view of the imaging optics.

[1104] In some embodiments, the markings are configured to have a distribution in the plate such that regardless of the position of the plate, there are always markings in the field of view of the imaging optics and the number of markings is sufficient for local optical information.

[1105] In some embodiments, the markers are used to control the optical properties of a localized region of the sample, with the region size being 1 μm 2 , 5μm 2 , 10μm 2 , 20μm 2 , 50μm 2 , 100μm 2 , 200μm 2 , 500μm 2 , 1000μm2 , 2000μm 2 , 5000μm 2 , 10000μm 2 , 100000μm 2 , 500000μm 2 , or in a range between any two of the values.

[1106] Using "finite imaging optics"

[1107] In the present invention, in some embodiments, the optical system used to image the measurement has a "finite imaging optics". Some embodiments of finite imaging optics include, but are not limited to:

[1108] 1. A limited imaging optical system, comprising:

[1109] Imaging lens;

[1110] Imaging sensors;

[1111] Wherein the imaging sensor is part of a camera of a smartphone;

[1112] wherein at least one of the imaging lenses is part of a camera of a smartphone;

[1113] 2. A finite imaging optical system as described in any of the preceding embodiments, wherein the physical optical resolution is worse than 1 μm, 2 μm, 3 μm, 5 μm, 10 μm, 50 μm, or in a range between any two of the values.

[1114] 3. A finite imaging optical system as described in any of the preceding embodiments, wherein each physical optical resolution is worse than 1 μm, 2 μm, 3 μm, 5 μm, 10 μm, 50 μm, or in a range between any two of the values.

[1115] 4. The finite imaging optical system of any preceding embodiment, wherein the preferred physical optical resolution is between 1 μm and 3 μm.

[1116] 5. A finite imaging optical system as described in any of the preceding embodiments, wherein the numerical aperture is less than 0.1, 0.15, 0.2, 0.2, 0.25, 0.3, 0.35, 0.4, 0.45, 0.5, or in a range between any two of the values.

[1117] 6. A finite imaging optical system as described in any of the preceding embodiments, wherein the preferred numerical aperture is between 0.2 and 0.25.

[1118] 7. A finite imaging optical system as described in any of the preceding embodiments, wherein the working distance is 0.2 mm, 0.5 mm, 1 mm, 2 mm, 5 mm, 10 mm, 20 mm, or in a range between any two of the values.

[1119] 8. The constrained imaging optical system of any of the preceding embodiments, wherein the working distance is 0.2 mm, 0.5 mm, 1 mm, 2 mm, 5 mm, 10 mm, 20 mm, or in a range between any two of the values.

[1120] 9. A finite imaging optical system as described in any of the preceding embodiments, wherein the preferred working distance is between 0.5 mm and 1 mm.

[1121] 10. The finite imaging optical system of any of the preceding embodiments, wherein the depth of focus is 100 nm, 500 nm, 1 μm, 2 μm, 10 μm, 100 μm, 1 mm, or in a range between any two of the values.

[1122] 11. The finite imaging optical system of any of the preceding embodiments, wherein the depth of focus is 100 nm, 500 nm, 1 μm, 2 μm, 10 μm, 100 μm, 1 mm, or in a range between any two of the values.

[1123] 12. The finite imaging optical system of any preceding embodiment, wherein the image sensor is part of a smartphone camera module.

[1124] 13. A finite imaging optical system as described in any of the preceding embodiments, wherein the diagonal length of the image sensor is less than 1 inch, 1 / 2 inch, 1 / 3 inch, 1 / 4 inch, or in a range between any two of the values.

[1125] 14. The finite imaging optical system of any preceding embodiment, wherein the imaging lens comprises at least two lenses, and one lens is part of a smartphone camera module.

[1126] 15. The finite imaging optical system of any preceding embodiment, wherein at least one external lens is paired with an internal lens of a smartphone.

[1127] 16. A finite imaging optical system as described in any of the preceding embodiments, wherein the optical axis of the external lens is aligned with the internal lens of the smart phone, and the alignment tolerance is less than 0.1 mm, 0.2 mm, 0.5 mm, 1 mm, or in a range between any two of the values.

[1128] 17. A finite imaging optical system as described in any of the preceding embodiments, wherein the height of the external lens is less than 2 mm, 5 mm, 10 mm, 15 mm, 20 mm, or in a range between any two of the values.

[1129] 18. A finite imaging optical system as described in any of the preceding embodiments, wherein the preferred height of the external lens is between 3 mm and 8 mm.

[1130] 19. A finite imaging optical system as described in any of the preceding embodiments, wherein the preferred height of the external lens is between 3 mm and 8 mm.

[1131] 20. The finite imaging optical system of any of the preceding embodiments, wherein the diameter of the external lens is less than 2 mm, 4 mm, 8 mm, 10 mm, 15 mm, 20 mm, or in a range between any two of the values.

[1132] 21. A finite imaging optical system as described in any of the preceding embodiments, wherein the physical optical magnification is less than 0.1X, 0.5X, 1X, 2X, 4X, 5X, 10X, or in a range between any two of the values.

[1133] 22. A finite imaging optical system as described in any of the preceding embodiments, wherein the physical preferred optical magnification is less than 0.1X, 0.5X, 1X, 2X, 4X, 5X, 10X, or in a range between any two of the values.

[1134] The term "image-based assay" refers to an assay procedure that utilizes an image of a sample captured by an imager, wherein the sample may be, but is not limited to, medical, biological, and chemical samples.

[1135] The term "imager" refers to any device that is capable of taking an image of an object. This includes, but is not limited to, cameras in microscopes, smartphones, or special devices that can take images at various wavelengths.

[1136] The term "sample feature" refers to some property of a sample that represents a condition of potential interest. In certain embodiments, a sample feature is a feature that appears in an image of a sample and can be segmented and classified by a machine learning model. Examples of sample features include, but are not limited to, the type of analyte in the sample, e.g., red blood cells, white blood cells, and tumor cells, and include analyte count, size, volume, concentration, etc.

[1137] The term "machine learning" refers to algorithms, systems, and devices in the field of artificial intelligence that typically use statistical techniques and artificial neural networks to provide computers with the ability to "learn" from data (i.e., gradually improve performance on a specific task) without being explicitly programmed.

[1138] The term "artificial neural network" refers to a hierarchically connected system inspired by biological networks that can "learn" to perform tasks by considering examples, typically without being programmed with any task-specific rules.

[1139] The term "convolutional neural network" refers to a class of multi-layer feed-forward artificial neural networks that are most commonly used to analyze visual images.

[1140] The term "deep learning" refers to a large class of machine learning methods in artificial intelligence (AI) that learn from data with a certain deep network structure.

[1141] The term "machine learning model" refers to a trained computational model built from a training process in machine learning of data. A machine learning model trained by a computer application during the derivation phase gives the computer the ability to perform specific tasks (e.g., detecting and classifying objects). Examples of machine learning models include ResNet, DenseNet, etc., which are also called "deep learning models" due to the layered depth in their network structure.

[1142] The term "image segmentation" refers to the image analysis process of dividing a digital image into multiple segments (sets of pixels, usually with bitmapped masks covering the image segments enclosed by their segment boundary outlines). Image segmentation can be achieved by image segmentation algorithms in image processing such as watershed, iterative graph cuts, mean shift, etc., or by machine learning algorithms such as MaskRCNN.

[1143] The term "defects in the sample" refers to phenomena that should not exist under ideal sample conditions or should not be considered in the characteristics of the sample. They can come from, but are not limited to, contaminants, such as dust, bubbles, etc., and from peripheral objects in the sample, such as monitoring markers in the sample holding device (e.g., columns). Defects can have significant dimensions and occupy a significant amount of volume in the sample, such as bubbles. In addition to their distribution and amount in the sample, which is sample dependent, they can have different shapes.

[1144] The term "threshold" herein refers to any number used as a cutoff value, for example, for classifying a sample feature as a particular type of analyte or the ratio of abnormal cells to normal cells in a sample. The threshold can be identified empirically or analytically.

[1145] Use "Limited Sample Manipulation"

[1146] In the present invention, in some embodiments, the sample positioning system used to image the assay has "limited sample manipulation". Some examples of limited sample manipulation include, but are not limited to:

[1147] Finite Sample Manipulation System Description:

[1148] 1. A limited sample manipulation system, comprising:

[1149] Sample holder;

[1150] The sample holder has a container for receiving the sample card.

[1151] 2. A finite sample manipulation system as described in any of the preceding embodiments, wherein the accuracy of positioning the sample in a direction along the optical axis is worse than 0.1 μm, 1 μm, 10 μm, 100 μm, 1 mm, or in a range between any two of the values.

[1152] 3. A finite sample manipulation system as described in any of the preceding embodiments, wherein the preferred accuracy of positioning the sample in a direction along the optical axis is between 50 μm and 200 μm.

[1153] 4. A finite sample manipulation system as described in any of the preceding embodiments, wherein the accuracy of positioning the sample in a plane perpendicular to the optical axis is worse than 0.01 μm, 0.1 μm, 1 μm, 10 μm, 100 μm, 1 mm, or in a range between any two of the values.

[1154] 5. The finite sample manipulation system of any preceding embodiment, wherein the preferred accuracy of positioning the sample in a plane perpendicular to the optical axis is between 100 μm and 1 mm.

[1155] 6. A limited sample manipulation system as described in any of the preceding embodiments, wherein the horizontal error of positioning the sample card is worse than 0.01 degrees, 0.1 degrees, 0.5 degrees, 1 degree, 10 degrees, or in a range between any two of the values.

[1156] 7. A limited sample manipulation system as described in any of the preceding embodiments, wherein the preferred horizontal difference for positioning the sample card is between 0.5 degrees and 10 degrees.

[1157] 8. A limited sample manipulation system as described in any of the preceding embodiments, wherein the preferred horizontal difference for positioning the sample card is between 0.5 degrees and 10 degrees.

[1158] TLD and volume estimation using monitoring tags

[1159] Figure 2An embodiment of a sample holding device, a QMAX device and its monitoring markers, and a column used in some embodiments of the present invention is shown. The column in the QMAX device makes the gap between the two parallel plates of the sample holding device uniform. The gap is narrow and is related to the size of the analyte that forms a monolayer in the gap. In addition, the monitoring markers in the QMAX device are a special form of column, so they are not immersed in the sample and can be imaged with the sample by the imager in an image-based assay.

[1160] Example of TLD (True Lateral Size) estimation using monitoring markers

[1161] In some embodiments of the present invention, TLD and true volume are estimated. Monitoring markers (columns) are used as detectable anchor points. However, it is difficult to detect monitoring markers with an accuracy suitable for TLD estimation in image-based determinations. This is because these monitoring markers are infiltrated and surrounded by the analyte in the sample holding device, and due to distortion from the lens, light diffraction from microscopic objects, defects at the microscopic level, misalignment of focusing, noise in the sample image, etc., they are distorted and blurred in the image. And if the imager is a camera from a commercial device (e.g., a camera from a smart phone), it becomes even more difficult because these cameras are no longer calibrated with dedicated hardware once they leave manufacturing.

[1162] In the present invention, the detection and positioning of monitoring markers as detectable anchors for TLD estimation are formulated in a machine learning framework, and a dedicated machine learning model is built / trained to detect them in microscopic imaging. In addition, in some embodiments of the present invention, the distribution of monitoring markers is intentionally made fixed-spaced and distributed in a predetermined pattern. This makes the method in the present invention more robust and reliable.

[1163] In particular, embodiments of the present invention include:

[1164] (8) adding the sample to a sample holding device, such as a QMAX device, wherein monitoring markers of known configuration are present in the device, which are not immersed in the sample and can be imaged by an imager;

[1165] (9) capturing an image of the sample in the sample holding device including the analyte and the monitoring marker;

[1166] (10) building and training a machine learning (ML) model to detect monitoring markers in sample images;

[1167] (11) detecting and locating monitoring marks in the sample holding device from an image of the sample using the ML detection model from (3);

[1168] (12) generating a marker grid based on the monitoring markers detected in (4);

[1169] (13) calculating homography transformation based on the generated monitoring marker grid;

[1170] (14) estimating and preserving the true lateral dimension of the image of the sample from the homography transformation from (6); and

[1171] (15) The estimated TLD from (7) was applied in subsequent image-based assays to determine the area, size, volume, and concentration of the analyte.

[1172] In some embodiments of the present invention, region-based TLD estimation and calibration is employed in image-based determination. It comprises:

[1173] (13) adding the sample to a sample holding device, such as a QMAX device, wherein a monitoring marker is present in the device, the monitoring marker is not immersed in the sample and can be imaged by an imager in an image-based assay;

[1174] (14) capturing an image of the sample in the sample holding device including the analyte and the monitoring marker;

[1175] (15) building and training a machine learning (ML) model for detecting monitoring markers from images of the sample captured by an imager;

[1176] (16) segmenting an image of the sample captured by the imager into non-overlapping regions;

[1177] (17) using the ML model of (3) to detect and locate monitoring markers from an image of the sample captured by the imager;

[1178] (18) generating a region-based marker grid for each of the regions having more than five non-collinear monitoring markers detected in the local region;

[1179] (19) generating a marker grid for all regions not in (6) in an image of the sample taken by the imager based on the detected monitoring markers;

[1180] (20) computing a region-specific homography transform for each region in (6) based on its own region-based label grid generated in (6);

[1181] (21) Compute homography transformations for all other regions based on the marker grid generated in (7);

[1182] (22) estimating the region-based TLD for each region in (6) based on the region-based homography transformation generated in (8);

[1183] (23) estimating TLDs for other regions based on the homography transformation from (9); and

[1184] (24) The estimated TLD in (10) and (11) is saved and applied to subsequent image-based detection of segmented regions.

[1185] When the monitoring marks are distributed in a predefined fixed-interval pattern, such as in a QMA device, they appear and are distributed at fixed intervals with a certain pitch, and as a result, detecting the monitoring marks in the above process becomes more robust and reliable. This is because in the case of fixed intervals, if the detected position and configuration do not follow the predefined fixed-interval pattern, all monitoring marks can be identified and determined from only a few detected monitoring marks, and detection errors can be corrected and eliminated.

[1186] Volume estimation using monitoring markers

[1187] In order to estimate the true volume of the sample under measurement, it is necessary to remove the volume from defects and peripheral objects in the sample. An embodiment of the present invention comprises:

[1188] (1) adding a sample to a sample holding device with monitoring marks, such as a QMAX device, and taking an image of the sample by an imager;

[1189] (2) using the above method and apparatus, estimating the true lateral dimension (TLD) of the image by detecting monitoring marks in the sample image as anchor points;

[1190] (3) Using a machine learning (ML) inspection model built and trained based on sample images to detect and locate defects in sample images, such as bubbles, dust, monitoring marks, etc.;

[1191] (4) determining a coverage mask of detected defects in the image of the sample using a machine learning (ML) segmentation model constructed and trained based on the image of the sample;

[1192] (5) determining a margin distance Δ based on the size of the sample and the analyte / object in the sample holding device (e.g., 2× the largest analyte diameter);

[1193] (6) Determine the Δ+ mask of all detected defects, i.e., the mask obtained by extending the coverage mask of (4) by an additional margin Δ;

[1194] (7) removing the detected defects according to the Δ+ mask in the sample image (6);

[1195] (8) saving the image in (7), and in a subsequent image-based determination, saving the corresponding volume after removing the volume using the corresponding Δ+ mask in (7); and

[1196] (9) If the area of ​​the removed Δ+ mask or the remaining true volume of the sample exceeds a certain preset threshold, the sample is rejected.

[1197] In the present invention, an additional margin Δ+ mask is used to remove defects from the sample image. This is important because defects affect their environment. For example, some defects can change the height of the gap in the sample holding device, and the local volume or concentration distribution around the defect can become different.

[1198] The terms "monitoring marker" and "marker" are interchangeable in the description of the present invention.

[1199] The terms "imager" and "camera" are interchangeable in the description of the present invention.

[1200] The term "denoising" refers to the process of removing noise from a received signal. An example is removing noise from a sample image, since images from an imager / camera can pick up noise from various sources, including but not limited to white noise, salt and pepper noise, Gaussian noise, etc. Denoising methods include but are not limited to: linear and nonlinear filtering, wavelet transforms, statistical methods, deep learning, and more.

[1201] The term "image normalization" refers to algorithms, methods, and devices that change the range of pixel intensity values ​​in a processed image. For example, it includes but is not limited to increasing contrast by histogram stretching, subtracting the average pixel value from each image, etc.

[1202] The term "image sharpening" refers to the process of enhancing the edge contrast and edge content of an image.

[1203] The term "image scaling" refers to the process of adjusting the size of an image. For example, if an object is too small in an image of a sample, image scaling can be applied to enlarge the image to aid detection. In some embodiments of the present invention, for training or derivation purposes, images need to be resized to a specified size before being input into a deep learning model.

[1204] The term "alignment" refers to transforming different data sets into a common coordinate system so that they can be compared and combined. For example, in image processing, the different data sets come from, but are not limited to, images from multiple imager sensors and images from the same sensor but at different times, focus depths, etc.

[1205] The term "super-resolution" refers to the process of obtaining a higher-resolution image from one or more lower-resolution images.

[1206] The term "deblurring" refers to the process of removing blurring artifacts from an image, such as blur caused by defocus, jitter, motion, etc. during the imaging process.

[1207] In some embodiments of the invention, methods and algorithms are designed to utilize monitoring markers in a sample holding device (e.g., a QMAX device). This includes, but is not limited to, estimation and adjustment of the following parameters in an imaging device:

[1208] 1. Shutter speed,

[1209] 2. Sensitivity

[1210] 3. Focus (lens position),

[1211] 4. Exposure compensation,

[1212] 5. White balance: temperature, tint, and

[1213] 6. Scaling (scale factor).

[1214] Examples of image processing / analysis algorithms used with markers

[1215] In some embodiments of the present invention, the monitoring markers of the present invention are used to apply and enhance image processing / analysis. They include but are not limited to the following image processing algorithms and methods:

[1216] 1. Histogram-based operations include but are not limited to:

[1217] a. Contrast expansion;

[1218] b. Equalization;

[1219] c.Minimum filtering;

[1220] d. Median filtering; and

[1221] e. Maximum filtering.

[1222] 2. Mathematical operations include but are not limited to:

[1223] a. Binary operations: NOT, OR, AND, XOR, SUB, etc., and

[1224] b. Arithmetic operations: ADD, SUB, MUL, DIV, LOG, EXP, SQRT, TRIG, INVERT, etc.

[1225] 3. Convolution-based operations in the spatial domain and frequency domain include but are not limited to Fourier transform, DCT, integer transform, wavelet transform, etc.

[1226] 4. Smooth operations include but are not limited to:

[1227] a. Linear filtering: uniform filter, triangular filter, Gaussian filter, etc., and

[1228] b. Nonlinear filtering: median filter, Kuwahara filter, etc.

[1229] 5. Operations based on derivative instruments include but are not limited to:

[1230] a. First-order derivative: gradient filter, basic derivative filter, prewitt gradient filter, sobel gradient filter, alternating gradient filter, Gaussian gradient filter, etc.;

[1231] b. Second-order derivatives: basic second-order derivative filter, frequency domain Laplace operator, Gaussian second-order derivative filter, variable Laplace filter, gradient-directed second-order derivative (SDGD) filter, etc., and

[1232] c. Other filters with higher derivatives, etc.

[1233] 6. Morphology-based operations include but are not limited to:

[1234] a. Expansion and erosion;

[1235] b. Boolean convolution;

[1236] c. Open and closed;

[1237] d. Hit-miss operation;

[1238] e. Segmentation and contouring;

[1239] f. Skeleton;

[1240] g. proliferation;

[1241] h. Gray value morphological processing: grayscale expansion, grayscale erosion, grayscale opening, grayscale closing, etc.; and

[1242] i. Morphological smoothing, morphological gradient, morphological Laplacian operator, etc.

[1243] Other Examples of Image Processing / Analysis Techniques

[1244] In some embodiments of the invention, image processing / analysis algorithms are used with and enhanced by the monitoring markers described in this disclosure. They include but are not limited to the following:

[1245] 1. Image enhancement and restoration including but not limited to

[1246] a. Sharpen and unsharpen,

[1247] b. Noise suppression, and

[1248] c. Distortion suppression.

[1249] 2. Image segmentation includes but is not limited to:

[1250] a.Threshold - fixed threshold, histogram export threshold, contour algorithm, background symmetry algorithm, triangulation algorithm, etc.;

[1251] b. Edge finding - gradient-based procedures, zero-crossing-based procedures, PLUS-based procedures, etc.

[1252] c. Binary mathematical morphology - salt and pepper filtering, separation of objects with holes, filling holes in objects, removal of boundary contact objects, exoskeleton, contact objects, etc.; and

[1253] d. Gray value mathematical morphology - top hat transformation, adaptive threshold processing, local contrast stretching, etc.

[1254] 3. Feature extraction and matching include but are not limited to:

[1255] a. Independent component analysis;

[1256] b.Contour map;

[1257] c. Principal component analysis and core principal component analysis;

[1258] d. Latent semantic analysis;

[1259] e. Least squares and partial least squares;

[1260] f. Multi-factor dimensionality reduction and nonlinear dimensionality reduction;

[1261] g. Multilinear principal component analysis;

[1262] h. Multilinear subspace learning;

[1263] i. semidefinite embedding; and

[1264] J. Autoencoder / decoder.

[1265] 4. Object detection, classification and localization

[1266] 5. Image Understanding

[1267] Improvements in microscopic imaging using monitoring markers

[1268] The monitoring marks can be used to improve focus in microscopic imaging. In particular, marks with sharp edges will provide a detectable (visible) feature for the focus assessment algorithm to analyze the focus condition of certain focus settings, especially in low light environments and microscopic imaging. In some embodiments of the present invention, the monitoring marks on the card are used to perform microscopic image correction and enhancement. For example, the focus assessment algorithm in e.g. Fig.11 The core part of the auto-focus implementation shown.

[1269] For some diagnostic applications (e.g., colorimetric, absorbance-based hemoglobin testing, and CBC for samples with very low cell concentrations), the detectable features provided by the analyte in the image of the sample are often insufficient for the focus assessment algorithm to run accurately and smoothly. Markers with sharp edges, such as the monitoring marks in the QMAX device, provide additional detectable features for the focus assessment procedure, thereby achieving the accuracy and reliability required in image-based assays.

[1270] For some diagnostic applications, the analytes in the sample are not uniformly distributed. Relying purely on features provided by the analytes tends to produce some unfair focus settings, which give high weight to focusing on some local high concentration areas, while low analyte concentration areas are off target. In some embodiments of the present invention, this effect is controlled by focusing adjustments using information from monitoring markers, which have strong edges and are uniformly distributed in a precisely processed fixed-spaced pattern.

[1271] Use super-resolution to generate a higher resolution image from a single image.

[1272] Each imager has an imaging resolution limited in part by the number of pixels in its sensor, which varies from one million pixels to several million pixels. For some microscopic imaging applications, the analytes have small or tiny sizes in the sample, such as the size of platelets in human blood, which have a diameter of approximately 1.4 μm. When the target detection procedure requires a certain number of pixels, in addition to the available size of the FOV, the limited resolution in the image sensor imposes significant limitations on the capabilities of the device in image-based assays.

[1273] Single Image Super Resolution (SISR) is a technique that uses image processing and / or machine learning techniques to upsample the original source image to a higher resolution and remove as much blur caused by interpolation as possible, so that object detection routines can also be run on the newly generated image. This will significantly reduce the limitations mentioned above and allow some applications that would otherwise be impossible. Markers with known shapes and structures (such as monitoring markers in QMAX) can be used as local references to evaluate SISR algorithms, avoiding the over-sharpening effect produced by most state-of-the-art algorithms.

[1274] In some embodiments of the invention, image fusion is performed to overcome the physical SNR (signal-to-noise ratio) limitations in image-based assays.

[1275] The signal-to-noise ratio measures the quality of the image of a sample captured by an imager in microscopy imaging. There are practical limitations on imaging devices due to cost, technology, manufacturing, etc. In some cases, such as in mobile health care, the application requires a higher SNR than the imaging device can provide. In some embodiments of the present invention (using the same and / or different imaging settings, such as embodiments of 3D fusion that merges multiple images focused at different focus depths into one super-focused image) multiple images are captured and processed to produce an output image with a higher SNR, thereby enabling such applications.

[1276] However, images captured by an imager or multiple imagers often have some defects and flaws caused by physical limitations and implementation constraints. Since the analytes in the sample have tiny sizes and usually do not have clear edge features, the situation becomes very acute in microscopic imaging of samples in image-based assays. In some embodiments of the present invention, monitoring markers in the image holding device (e.g., QMAX device) are used for enhanced resolution.

[1277] One such embodiment is to deal with distortion in images of a sample taken by an imager. Fig.12 is an improvement over the general camera model. When the distortion parameters are known, the situation is relatively simple (most manufacturers give curves / tables for their lenses to describe ratio distortion, other distortions can be measured in well-defined experiments). However, when the distortion parameters are unknown for the monitoring marks, it is possible to iteratively estimate the distortion parameters using regularly or even regularly spaced monitoring marks of a sample holding device (e.g. a QMAX device), without the need for such a Fig.13 The single coordinate reference shown.

[1278] Some additional embodiments

[1279] In the present invention, in some embodiments, in order to analyze micro features in image-based determination, the sample holding device has a flat surface with some special monitoring marks. Some embodiments of the present invention are listed as follows:

[1280] A1: Estimation of the true lateral dimension (TLD) of a microscopic image of a sample in an image-based assay. The true lateral dimension (TLD) determines the physical size of the imaged analyte in the real world, and it also determines the image coordinates of the sample in the real world that are relevant to the concentration estimation in the image-based assay. The monitoring marker can be used as a detectable anchor point to determine the TLD and improve the accuracy of the image-based assay. In one embodiment of the present invention, a machine learning model of the monitoring marker is used to detect the monitoring marker, and the TLD of the sample image is derived from the model. In addition, if the monitoring marker has a fixed-spaced distribution pattern on the flat surface of the sample holding device, the detection of the monitoring marker and the TLD estimation based on each sample can become more robust and robust in the image-based assay.

[1281] A2: Analyze the analyte using the measured response from the analyte compound at a specific wavelength of light or at multiple wavelengths of light to predict the analyte concentration. Monitoring markers that are not immersed in the sample can be used to determine the light absorption corresponding to the background without the analyte compound so that the analyte concentration can be determined by light absorption, such as the HgB test in a complete blood test. In addition, each monitoring marker can act as an independent detector of background absorption to make the concentration estimate robust and reliable.

[1282] A3: Focusing in microscopic images for image-based assays. Evenly distributed monitor marks can be used to improve focus accuracy. (a) It can be used to provide a minimum amount of visual features for samples with no / less than the necessary number of features for reliable focusing, and this can be done in low light due to the edge content of the monitor marks. (b) When features in the sample are not evenly distributed, it can be used to provide visual features to make focus decisions more accurate. (c) It can provide a reference for local lighting conditions that are not affected / less affected / different from the sample content to adjust weights in the focus assessment algorithm.

[1283] A4: The monitoring markers can be used as a reference to detect and / or correct image defects caused by, but not limited to, unevenly distributed lighting, various types of image distortion, noise, and imperfect image pre-processing operations. (a) For example, Fig.14 As shown, when a straight line in the 3D world is mapped to an image as a curve, the position of the marker in the sample image can be used to detect and / or correct the ratio distortion. The ratio distribution parameter of the whole image can be estimated based on the position change of the marker. And the ratio distortion parameter value can be iteratively estimated by performing linear tests on horizontal / vertical lines in the reproduced image with distortion removal based on the assumed ratio distortion parameter.

[1284] Examples of machine learning (ML) calculations

[1285] B1: One way to use machine learning is to detect analytes in sample images and calculate bounding boxes covering their locations and perform them using trained machine learning models in the derivation of processing. Another way to use machine learning methods to detect and locate analytes in sample images is to build and train detection and segmentation models that involve annotating analytes in sample images at the pixel level. In this approach, analytes in sample images can be detected and located in image-based assays using sealed binary pixel masks covering them.

[1286] B2: When testing hemoglobin in human blood, images are taken at a given narrowband wavelength, and then the average energy passing through the analyte area and the reference area is analyzed. Based on the known absorbance of the analyte at a given wavelength and the height of the analyte sample area, the concentration can be estimated. However, this measurement is noisy. In order to eliminate noise, multiple images can be taken using light of different wavelengths, and machine learning regression is used to achieve a more accurate and robust estimate. In some embodiments of the present invention, multiple input images of samples taken at different wavelengths are taken based on machine learning derivation, and a single concentration number is output.

[1287] Example of identifying error risks to improve measurement reliability

[1288] In some embodiments, a method for improving the reliability of an assay, the method comprising:

[1289] (a) Image the sample on a QMAX card;

[1290] (b) analyzing error risk factors; and

[1291] (c) rejecting the measurement result of the card report card if the error risk factor is above a threshold value;

[1292] The error risk factor is one of the following factors or any combination thereof. These factors are, but are not limited to, (1) blood margin, (2) air bubbles in the blood, (3) too little blood volume or too much blood volume, (4) blood cells under the spacer, (5) aggregated blood cells, (6) lysed blood cells, (7) overexposed image of the sample, (8) underexposed image of the sample, (8) poor focus of the sample, (10) optical system error with wrong lever position, (11) unclosed card, (12) wrong card due to card without spacer, (13) dust in the card, (14) oil in the card, (15) stains on the card outside the focal plane, (16) card not in the correct position in the reader, (17) empty card, (18) manufacturing error in the card, (19) wrong card for other applications, (20) dried blood, (21) expired card, (22) large changes in blood cell distribution, (23) non-blood sample or non-target blood sample, etc.

[1293] In some embodiments, the error risk analyzer is capable of detecting, distinguishing, classifying, correcting and / or correcting the following situations in biological and chemical applications in the device: (1) sample edge, (2) bubbles in the sample, (3) sample volume is too small or sample volume is too large, (4) sample under the spacer, (5) aggregated sample, (6) lysed sample, (7) overexposed image of the sample, (8) underexposed image of the sample, (8) poor focus of the sample, (10) optical system error with wrong lever position, (11) unclosed card, (12) wrong card due to card without spacer, (13) dust in the card, (14) oil in the card, (15) stains on the card outside the focal plane, (16) card not in the correct position in the reader, (17) empty card, (18) manufacturing error in the card, (19) wrong card for other applications, (20) dried sample, (21) expired card, (22) large changes in blood cell distribution, (23) wrong sample, etc.

[1294] The threshold is determined by group testing.

[1295] The threshold is determined based on machine learning.

[1296] The monitoring markers are used as controls to identify error risk factors.

[1297] The monitoring markers are used as comparisons to assess thresholds for error risk factors.

[1298] The following brief summary is not intended to include all features and aspects of the invention.

[1299] Disclosed herein are methods and systems for image-based assays for analyzing morphological, molecular, physical, colorimetric, and pathological characteristics of samples in biological, chemical, and medical diagnostics. For example, in CBC (complete blood count) testing, it is based on the image of the sample to characterize blood cells, such as red blood cells, white blood cells, etc.; molecular and nucleic acid testing is to capture the combination of antigens and antibodies or particles in the sample image taken under various conditions together with reagents; and colorimetric testing is to determine sample characteristics and particle concentrations based on the light absorption of various wavelengths captured in the sample image.

[1300] However, all these tests are conducted under many unknown factors from sample preparation to device operation during the test, which may affect the reliability of the test results. For example, in blood testing, common unknown factors include but are not limited to cell aggregation, dust, bubbles, uneven distribution, dry texture structure, etc. In addition to conventional testing procedures, methods and systems that can control these unknown factors are urgently needed.

[1301] One aspect of the methods and systems disclosed herein is a trust framework in image-based assays. It runs in parallel with conventional image-based assays, but it analyzes meta-features of the tested sample based on the same image used for the image-based assay. These meta-features of the tested sample provide key information for determining the trustworthiness of the test results. In addition, in some embodiments, these meta-features of the image-based assay are captured and characterized by a dedicated machine learning model that can be executed in a noisy and diverse environment.

[1302] Specifically, a key method and system for verifying the credibility of test results are disclosed, including:

[1303] (a) Methods and systems for detecting uneven distribution of samples in image-based assays. Unevenly distributed (smeared) samples are a source of inaccuracies and errors.

[1304] (b) In methods and systems for detecting the dry texture of a sample in an image-based assay, partially dried (eg, blood) samples may affect the accuracy of the test results.

[1305] (c) In methods and systems for detecting sample aggregation in image-based assays, the degree of aggregation in a test sample is a strong indicator of the quality of the sample, the reagents used for the assay, etc.

[1306] (d) In the method and system for detecting defects in a sample for image-based measurement, the defects in the sample include but are not limited to dust, bubbles, fibers, etc.

[1307] The proposed credibility testing framework for image-based assays is powered by machine learning, where a dedicated machine learning model is built for fast and robust estimation of the credibility of assay results. It has been applied to real-world applications such as blood and colorimetric tests.

[1308] In addition, a dedicated segmentation method is disclosed herein for obtaining fine contour mask-level segmentation of objects in image-based assays. It is applied to cell detection and characterization, and also to confidence assays to detect and characterize defects and anomalies in samples.

[1309] The proposed method applies machine learning-based segmentation to bounding box level segmentation, which is fast and easy to build. Then, for each object in the bounding box, a dedicated morphological analysis method is designed to obtain a fine contour mask segmentation. The method is widely used in image-based validity analysis.

[1310] Another aspect of the methods and systems disclosed herein is a framework for image-based assays with a specially designed sample holder having monitoring marker structures in the form of pillars that are visible from an image of a sample in the sample holder during an image-based assay. The specially designed sample holder exhibits a number of new capabilities and features in image-based assays, including:

[1311] (a) In methods and systems for true lateral dimension (TLD) correction for image-based assays, TLD determines the size of cells in an image to their true size in the physical world, which is a key parameter affecting the accuracy of the assay results due to distortions in the image of the sample taken by the imager.

[1312] (b) Methods and systems for a spectrophotometer in an image system based on an image of a sample with a sample holder, wherein the image of the sample is divided into two sub-regions using a machine learning model. The first sub-region corresponds to the sample and the second sub-region corresponds to the column. Spectrochemical measurements are performed on the two types of sub-regions based on one or more images taken at single or multiple wavelengths of light, and these data are collected and applied to derive chemical and physical properties of the sample, such as compound concentrations.

[1313] (c) Method and system for determining sample volume based on monitoring marker posts with uniform height, where the volume of the sample can be determined by the surface area of ​​the sample in the image, because the sample is sandwiched between two parallel plates of the sample holder with a uniform gap controlled by the posts. The proposed structure is able to practically remove any visible defects, posts, dust, bubbles, etc. from the sample and still have precise control over the sample volume after removal for determination.

[1314] (d) Methods and systems for improving the quality of microscopic imaging in image-based assays using monitoring marker columns, wherein local illumination, uniformity of illumination, and ratio distortion control can be based on images of the columns detected in the image-based assay. These parameters are difficult to control in microscopic imaging, particularly for different types of samples being imaged for the assay.

[1315] In general, detecting, localizing, and segmenting pillars in sample images is a challenging problem, especially in microscopic images, such as those from image-based assays. In the described methods and embodiments, a dedicated machine learning model for pillar detection is also constructed, and the above-mentioned segmentation method is combined with a true lateral dimension (TLD) correction for high-accuracy estimation of pillar position, shape profile, and size, making the above-mentioned method effective for image-based assays.

Claims

1. A method for improving the accuracy of an assay device for detecting an analyte in a sample, wherein the sample, the assay device, or the operation of the assay device has one or more imperfect conditions, the method comprising: (a) using the assay device to detect the analyte in the sample and generate a test result, wherein the assay device comprises a sample holder, the sample holder comprises a sample contact surface, and a monitoring mark is disposed on the sample contact surface; (b) determining the confidence level of the test result by (i) imaging the sample together with the monitoring marker in the assay device and (ii) using an algorithm to compare the monitoring marker with distortion to the monitoring marker without distortion; as well as (c) reporting the detection result only when the confidence level meets a predetermined threshold.

2. An apparatus for improving the accuracy of an assay device for detecting an analyte in a sample, wherein the sample, the assay device, or the operation of the assay device has one or more imperfect conditions, the apparatus comprising: (a) an assay device for detecting the analyte in the sample to produce a test result, wherein the assay device has a sample holder, the sample holder has a sample contact surface, and a monitoring mark is provided on the sample contact surface; as well as (b) an imager that images the sample in the sample holder together with the monitoring marker; as well as (c) A non-transitory storage medium storing an algorithm for comparing a monitoring signature with distortion with a monitoring signature without distortion to determine the credibility of the detection result.

3. The method of claim 1, wherein the algorithm is a machine learning model.

4. The method of claim 3, and the apparatus of claim 2, wherein the algorithm is a machine learning model.

5. The method of claim 1 or 3, and the apparatus of claim 2, wherein the confidence level is associated with a defect comprising (1) blood edge, (2) air bubbles in the blood, (3) too little blood volume or too much blood volume, (4) blood cells below the monitoring mark, (5) aggregated blood cells, (6) lysed blood cells, (7) overexposed image of the sample, (8) underexposed image of the sample, (8) poor focus of the sample, (9) optical system error with wrong lever position, (10) unclosed card, (11) wrong card without monitoring mark, (12) dust in the card, (14) oil in the card, (15) stains on the card outside the focal plane, (16) card not in the correct position in the reader, (17) empty card, (18) manufacturing error in the card, (19) wrong card for other applications, (20) dried blood, (21) expired card, (22) large changes in blood cell distribution, (23) non-blood sample, or (24) non-target blood sample.

6. The method of claim 1 or 3, and the apparatus of claim 2, wherein the imperfect conditions include non-sample materials, the non-sample materials comprising dust and / or air bubbles.

7. The method of claim 1 or 3, and the apparatus of claim 2, wherein the assay is a cellular assay, an immunoassay, a nucleic acid assay, a colorimetric assay, a luminescent assay, or any combination thereof.

8. The method of claim 1 or 3, and the apparatus of claim 2, wherein the assay device comprises two plates facing each other with a gap, and at least a portion of the sample is within the gap.

9. The method of claim 1 or 3, and the apparatus of claim 2, wherein the assay device comprises a Q card comprising two plates movable relative to each other and a monitoring mark for adjusting the spacing between the plates.

10. The method of claim 1 or 3, and the apparatus of claim 2, wherein some of the monitoring marks are arranged at fixed intervals.

11. The method of claim 1 or 3, and the device of claim 2, wherein the sample is selected from the group consisting of cells, tissues, body fluids and feces.

12. The method of claim 1 or 3, and the apparatus of claim 2, wherein the sample is amniotic fluid, aqueous humor, vitreous humor, blood, breast milk, cerebrospinal fluid, cerumen, chyle, chyme, endolymph, perilymph, feces, gastric acid, gastric juice, lymph, mucus, pericardial fluid, peritoneal fluid, pleural fluid, pus, rheumatic fluid, saliva, sebum, semen, sputum, sweat, synovial fluid, tears, vomitus, urine, or exhaled condensate.

13. The method of claim 1 or 3, and the device of claim 2, wherein the analyte comprises molecules, cells, tissues, viruses and nanoparticles, wherein the molecules include proteins, peptides, nucleic acids, synthetic compounds, inorganic compounds, or other molecules.

14. The method of claim 1 or 3, and the device of claim 2, wherein the sample is a non-flowable but deformable sample.

15. The method of claim 1 or 3, and the apparatus of claim 2, wherein the algorithm is machine learning, artificial intelligence, statistical methods, or a combination thereof.

16. The method or apparatus of claim 9, wherein the monitoring marks have a substantially uniform height equal to or less than 200 microns and a fixed spacing.

17. The method of claim 1 or 3, and the apparatus of claim 2, wherein the monitoring markers are used for estimating the true lateral dimension and the true volume estimation.

18. The method of claim 1 or 3, and the apparatus of claim 2, wherein step (b) further comprises image segmentation for image-based determination.

19. The method of claim 1 or 3, and the apparatus of claim 2, wherein step (b) further comprises checking focus in an image-based assay.

20. The method of claim 1 or 3, and the apparatus of claim 2, wherein step (b) further comprises the uniformity of the distribution of the analyte in the sample.

21. The method of claim 1 or 3, and the device of claim 2, wherein step (b) further comprises analyzing and detecting aggregated analytes in the sample.

22. The method of claim 1 or 3, and the apparatus of claim 2, wherein step (b) further comprises analyzing a dry texture structure in the image of the sample in the sample.

23. The method of claim 1 or 3, and the apparatus of claim 2, wherein step (b) further comprises analyzing defects in the sample.

24. The method of claim 1 or 3, and the device of claim 2, wherein step (b) further comprises correction of camera parameters and conditions, wherein the camera parameters comprise: distortion elimination, temperature correction, brightness correction, and contrast.

25. The method of claim 1 or 3, and the apparatus of claim 2, wherein the monitoring mark has predetermined optical properties during manufacture of the sample holder and is imaged in an image for determining the reliability.

26. The method of claim 1 or 3, and the apparatus of claim 2, wherein the monitoring marker is a pillar array.

27. The method or apparatus of claim 9, wherein the spacing 15 is equal to or less than 120 um.

28. The method of claim 1 or 3, and the device of claim 2, wherein the signal is a luminescent signal selected from the group consisting of fluorescence, electroluminescence, chemiluminescence and electrochemiluminescence.

29. The method or apparatus of claim 9, wherein the fourth power of the spacing divided by the thickness (h) and Young's modulus (E) of the flexible board is 5x10 5 um 3 / GPa or less, wherein the thickness of the flexible board multiplied by the Young's modulus of the flexible board is in the range of 60 to 750 GPa·um.

30. The method of claim 1 or 3, and the apparatus of claim 2, wherein: Imperfect conditions of the assay device include sample holder operating conditions, sample conditions, or reagent conditions, or measuring instrument conditions.

Images