Systems and methods for analyzing a porous plate

Abstract

The present disclosure relates to analyzing a perforated plate used in an analyzer. In one aspect, a method includes analyzing a sample inserted in an analyzer using a machine learning model to determine whether a plate insert matches a perforated plate (MWP). The method further includes, in response to the machine learning model a mismatch between the board insert and the MWP, generating an alert on the analyzer to inform a user that the mismatch is indicated. The method further includes, in response to the machine learning model determining that the plate insert matches the MWP, analyzing the sample using the machine learning model to determine whether the MWP is sealed with a foil. The method includes, in response to the machine learning model determining that the MWP is not sealed with a foil, generating an alert on the analyzer, and, in addition, enabling the analyzer to perform an analysis of the sample by the analyzer.

Description

Technical Field

[0001] Embodiments of the present disclosure relate generally to analyzers, and more particularly to multiwell plates used in analytical analyzers. Background Art

[0002] In some cases, the foil on a test sample, such as a multi-well plate (MWP), may not be properly applied before the sample is run through an analyzer, such as a polymerase chain reaction (PCR) analyzer, or an incorrect plate insert may be used for a given MWP. For example, a laboratory technician may not properly apply the foil on the MWP before running the sample on the analyzer. In addition, some analyzers may be configured to analyze more than one type of MWP. For example, the MWP may be a ninety-six (96) well plate or a three hundred and eighty-four (396) well plate. However, in some cases, a plate insert for a 96-well plate may be applied to a 384-well plate, and vice versa. If the foil or plate insert is not applied correctly, sample material may evaporate during thermal cycling, and temperatures may be as high as 95°C. This may result in a loss of the sample results being measured, and the analyzer itself may be contaminated with the sample. Cleaning of the analyzer is required because contaminants within the optical path may result in incorrect results. In addition, spillage caused by the movement of samples within the analyzer may result in cross-contamination and, thereby, erroneous results.

[0003] It would therefore be desirable to provide new systems and methods for identifying whether the correct insert has been used or whether the foil has been correctly applied to a sample prior to using an analyzer. Summary of the invention

[0004] Embodiments of the present disclosure relate generally to analyzers, and more particularly to multiwell plates used in analytical analyzers.

[0005] In one aspect, a method includes analyzing a sample inserted into an analyzer using a machine learning model to determine whether a plate insert matches a multi-well plate (MWP). The method further includes: in response to the machine learning model determining that the plate insert matches the MWP, generating an alarm on the analyzer to notify a user indicating the mismatch. The method also includes: in response to the machine learning model determining that the plate insert matches the MWP, analyzing the sample using the machine learning model to determine whether the MWP is sealed with foil. The method includes: in response to the machine learning model determining that the MWP is not sealed with foil, generating an alarm on the analyzer, and in addition enabling the analyzer to perform analysis of the sample by the analyzer.

[0006] In some aspects, a combination of real images and augmented images is used to train a machine learning model.

[0007] In some aspects, the machine learning model is trained using a training dataset comprising images of MWPs having at least two different numbers of pores.

[0008] In some aspects, images of the MWP having at least two different numbers of apertures include images with and without foil on the MWP.

[0009] In some aspects, the machine learning model is trained using a training dataset that includes images of both correct MWP and foil combinations and incorrect MWP and foil combinations.

[0010] In some aspects, a machine learning model is trained using a training dataset that includes images of MWPs with various fill volumes, various dyes, and various foil types.

[0011] In some aspects, a machine learning model is trained using a training dataset that includes images of MWPs with a variety of different fill patterns.

[0012] In some aspects, a machine learning model is trained using a training dataset that includes images of MWPs with user errors.

[0013] In some aspects, analyzing the sample to determine if a mismatch exists between the plate insert and the MWP includes calculating a confidence score, and generating an alert when the confidence score is below a threshold.

[0014] In some aspects, analyzing the sample to determine whether the plate MWP is sealed with foil includes calculating a confidence score, and wherein an alarm is generated when the confidence score is below a threshold.

[0015] In some aspects, the method further includes receiving an instruction from a user to continue operation of the analyzer when any alarm is generated.

[0016] In some aspects, the machine learning model includes multiple machine learning sub-models, and wherein a first machine learning sub-model in the multiple machine learning sub-models is trained to determine whether a plate insert matches the MWP, and a second machine learning sub-model in the multiple machine learning sub-models is trained to determine whether a sample is sealed with foil.

[0017] In some aspects, different data sets are used to train the first machine learning sub-model and the second machine learning sub-model.

[0018] In some aspects, multiple enhancement techniques are used to generate an enhanced image.

[0019] On the other hand, a system includes a memory and a processor coupled to the memory. The processor is configured to analyze a sample inserted into an analyzer using a machine learning model to determine whether a plate insert matches a multi-well plate (MWP). The processor is further configured to generate an alarm on the analyzer to notify a user indicating the mismatch in response to a mismatch between the plate insert and the MWP by the machine learning model. The processor is also configured to analyze the sample using the machine learning model to determine whether the MWP is sealed with foil in response to the machine learning model determining that the plate insert matches the MWP. The processor is also configured to generate an alarm on the analyzer in response to the machine learning model determining that the MWP is not sealed with foil, and in addition enable the analyzer to perform the analyzer's analysis of the sample. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The novel features of the present disclosure are particularly set forth in the appended claims. The features and advantages of the present disclosure will be better understood by reference to the following detailed description of illustrative embodiments in which the principles of the present disclosure are utilized, and the accompanying drawings, in which:

[0021] Figure 1 is a block diagram of an embodiment of an optical system of an illustrative analyzer according to aspects of the present disclosure.

[0022] Figure 2 Depicted are diagrams illustrating examples of machine learning models in accordance with aspects of the present disclosure.

[0023] Figure 3 is a block diagram illustrating an embodiment of a method 300 for analyzing a MWP inserted into an analyzer, according to aspects of the present disclosure.

[0024] Figure 4 is a block diagram of an embodiment of an example computer system according to aspects of the present disclosure. DETAILED DESCRIPTION

[0025] The disclosure described herein is a system and method for analyzing a sample inserted into an analyzer based on a machine learning algorithm.

[0026] Figure 1 is a block diagram of an example analyzer embodiment according to aspects of the present disclosure. Figure 1As shown, the analyzer 1000 includes an optical system 100 and a computing system 150. In some embodiments, the optical system 100 includes an imaging system 110, a first reflective surface 115 and a second reflective surface 120, a lens 125, and an imaging surface 130. In some embodiments, the imaging system 110 may include a light source 110a configured to generate a light beam, an illumination lens 110b configured to focus the light beam, and an exciter 110c configured to transmit the focused light beam to the first reflective surface 115. In some embodiments, the focused light beam is reflected off the first reflective surface 115 to the second reflective surface 120, and the focused light beam is then transmitted to the imaging surface 130 through the lens 125.

[0027] Then, the light is reflected from the imaging surface 130 through the lens 125 and exits the first reflective surface 115 and the second reflective surface 120 onto the imaging system 110. In some embodiments, the imaging system 110 may further include an emitter 110d configured to receive the reflected light from the imaging surface 130, an imaging lens 110e configured to focus the reflected light, and a camera 110f configured to capture the reflected light from the imaging surface 130. In some embodiments, the camera 110f may be used for fluorescence imaging due to its high sensitivity, low noise, and high temporal stability.

[0028] In some embodiments, computing system 150 may execute machine learning model 155 to determine: 1) whether the plate insert matches the MWP; and 2) whether the foil is properly applied to the MWP. For example, machine learning model 155 may analyze images captured by camera 110f based on epifluorescence imaging, which is a dark field method for achieving high signal to background ratios. Epifluorescence imaging is based on analyzing bright images of positive samples illuminated in front of a dark scene.

[0029] Figure 2 A diagram depicting an example of an example machine learning model according to various aspects of the present disclosure. In some embodiments, the machine learning model 200 may include a first machine learning sub-model 210 and a second machine learning sub-model 220. The first machine learning sub-model 210 may be trained to identify mismatched plates, and the second machine learning sub-model 220 may be trained to identify whether the foil is correctly applied to the MWP. In some embodiments, the machine learning model 200 may be a supervised machine learning model. For example, the first machine learning sub-model 210 and the second machine learning sub-model 220 may be convolutional neural networks trained for object classification. That is, object classification may be considered as a binary classification problem at each of the first machine learning sub-model 210 and the second machine learning sub-model 220, that is, whether the plate at the first machine learning sub-model 210 is correct and whether the foil is correctly applied at the second machine learning sub-model 220).

[0030] In some embodiments, various conditions may be used to train the machine learning sub-models 210, 200. For example, some conditions to generate greater depth of data variation may include: MWPs with different numbers of sample wells, such as MWPs with a 96-well format and / or MWPs with a 384-well format; MWPs with or without sealing foils; MWPs with different types of sealing foils; MWPs with different batches of samples; MWPs with boundary cases (e.g., bubbles in the fluid); MWPs with different volumes in the wells; images of MWPs with different settings for the analyzer 1000 (e.g., PCR excitation and emission filters); images captured using different types of analyzers; and images of MWPs with both correct and incorrect plate combinations.

[0031] In some embodiments, different images of the training dataset may be used to train the first machine learning sub-model 210 and the second machine learning sub-model 220. For example, images with mismatched plates used to train the first machine learning sub-model 210 may be excluded from the training dataset used to train the second machine learning sub-model 220. Similarly, images with different foil applications used to train the second machine learning sub-model 220 may be excluded from the training dataset used to train the first machine learning sub-model 210. In some embodiments, for the machine learning sub-models 210, 200, images in the training dataset that include 96-well MWPs may also include one or more eight (8) well inserts.

[0032] In some embodiments, for the first machine learning sub-model 210, the ground truth value may be zero (0) for images depicting unmatched plates, and one (1) for images with matching plates. In further embodiments, for the second machine learning sub-model 220, the ground truth value may be zero (0) for images where the foil is incorrectly applied, and one (1) for images where the foil is correctly applied.

[0033] In some embodiments, the training data set may also include images with any number of fill patterns. That is, the image may include some holes filled with samples, while other holes may remain empty in the designed pattern. For example, the training data set may include two, four, six, or eight different designed patterns. It will be appreciated by those of ordinary skill in the art that these are merely example fill patterns, and other fill patterns may be used in accordance with aspects of the present disclosure.

[0034] In some embodiments, a combination of real images and simulated images (or enhanced images) can be used to train machine learning sub-models 210, 220. In some embodiments, data enhancement can be used during preprocessing of real images to imitate the remaining different filling patterns. Enhanced images can be created using a variety of different enhancement techniques to generate variability across training data. For example, a first technique can be used to blacken individual rectangles of various sizes from a real image. As another example, a second technique can be used to blacken small squares of different numbers and angles scattered on a real image. In a further example, a third technique can be used to remove individual rectangles of various sizes from a first image and replace it with a rectangle from a second image of the same size. In yet another example, a fourth technique can use a weighted average of the first image and the second image, where the weights vary randomly. In some embodiments, two or more of the enhancement techniques can be combined with each other. For example, a third technique and a fourth technique can be used to combine two real images from a training data set to create two images of a new batch. In some embodiments, the data enhancement techniques described herein are used to generate thousands of images.

[0035] In some embodiments, when two or more augmentation techniques are combined, a real image pair may have a common ground truth. To achieve this, an augmented image may be created using two images from a common training dataset, e.g., the two images may depict a matching plate and an unmatched plate. Thus, the ground truth of the augmented image may be the same as the original image.

[0036] Furthermore, images with eight-hole inserts can be processed separately during data augmentation. That is, in any batch of two images, one image with unfilled eight-hole inserts is paired with one image with filled eight-hole inserts before data augmentation is applied.

[0037] In further embodiments, the images in the training data set for the second machine learning submodel 200 may include images with user errors, including but not limited to wrinkles, shakes, bubbles, etc. In addition, the images in the training data set for the first machine learning submodel 210 and / or the second machine learning submodel 200 may include modifications to the MWP to simulate the variability of different instrument and plate placements by lifting each of the four corners of the MWP upward and / or sliding the MWP in a horizontal plane during the experiment. In addition, the images in the training data set for the first machine learning submodel 210 and / or the second machine learning submodel 200 may include images with physical changes to the MWP. As some examples, the physical changes may include placing an adhesive material (e.g., tape) and / or a solid covering (e.g., a plastic layer) on a section of the MWP. By modifying the images in the training set as described herein, the machine learning model 200 can be implemented on different analyzers, such as analyzers of different models, analyzers from different manufacturers, or analyzers of the same type with different serial numbers.

[0038] In some embodiments, the images used in the training data set may also be preprocessed. Preprocessing may include scaling the pixel values ​​of the original image to convert the original image from a 16-bit image to grayscale pixel values ​​less than or equal to 255. In addition, preprocessing may include removing overexposed portions of the real image. For example, for blurred portions of a given real image, preprocessing may include removing those blurred portions. In addition, a subset of pixels may be used as input to the model. For example, for both 96MWP and 384MWP, the border region of a given image may be removed. This may be achieved by cropping one or more edges of the image, and the remaining center rectangle may be subdivided into nine (9) equal rectangles. In some embodiments, a single region may be used to train the machine learning model 200, and the remaining region may be discarded. The region used to train the machine learning model may be downsampled to a 224×224 square using linear interpolation so that the region is in the correct format for use with the machine learning model 200. In some embodiments, overexposure correction may be implemented before any modification is made to the image, such as before any image cropping or image enhancement.

[0039] In some embodiments, the first machine learning submodel 210 and the second machine learning submodel 220 can calculate a confidence score. For example, the confidence score can be in the range of 0.0 to 1.0. When the confidence score is below a first threshold level (e.g., 0.8), the first machine learning submodel 210 and the second machine learning submodel 220 can generate an alarm, such as a visual alarm or an audio alarm. When the confidence score is below a second threshold (e.g., 0.5), the first machine learning submodel 210 and the second machine learning submodel 220 can generate a command to prevent the analyzer 1000 from analyzing the sample, thereby preventing the analyzer 1000 from any potential contamination.

[0040] In operation, the analyzer 1000 is configured to analyze a 96-well MWP or a 384-well MWP so that the first machine learning sub-model 210 knows which type of MWP is being analyzed. Once the MWP is inserted, the analyzer 1000 captures an image of the MWP using the optical system 100. The first machine learning sub-model 210 then analyzes the captured image to determine whether the middle plate matches the top and bottom plates, e.g., whether there is a plate mismatch. Some mismatch indicators may include, but are not limited to, partial circles, such as semicircles or crescents, based on the angle of the MWP relative to the optical system 100, caused by misalignment of the top and middle layers. That is, the first machine learning sub-model 210 analyzes the holes of the MWP to identify any semicircles or crescents in the captured image that are at incorrect angles, thereby indicating a mismatch between the top layer and the plate insert.

[0041] In some embodiments, when the first machine learning sub-model 210 determines that there is a plate mismatch, the analyzer 1000 can generate an alarm, such as a visual alarm or an audible alarm. Conversely, when the first machine learning sub-model 210 determines that there is no plate mismatch, the second machine learning sub-model 220 further analyzes the MWP to determine whether the foil is applied correctly. For example, using the same captured image, the second machine learning sub-model 220 analyzes each hole of the MWP to ensure that the foil is applied correctly. To this end, the second machine learning sub-model 220 analyzes the intensity of the light reflected at each hole. In some embodiments, the reduced light intensity may indicate that the foil is not applied correctly. In other words, when the foil is not tightened against the MWP, the intensity of the light reflected off the foil is low, indicating that the foil is not applied correctly. In some embodiments, when the second machine learning sub-model 220 determines that the foil is not applied correctly, the analyzer 1000 can generate an alarm, such as a visual alarm or an audible alarm.

[0042] The present disclosure advantageously uses existing hardware components of the analyzer. That is, no hardware modifications are required to implement the methods described herein. In addition, the methods described herein can be used without any changes to consumables (e.g., foils and / or MWPs).

[0043] Using the techniques described herein, the present disclosure improves the functionality of the analyzer 1000 and the computing resources required to perform MWP board analysis. For example, the present disclosure reduces the data required to execute a machine learning model to less than 10 megabytes, while a traditional machine learning model requires more than 20 megabytes of data. Similarly, the present disclosure reduces the runtime required to execute a machine learning model to less than 500 milliseconds, while a traditional machine learning model requires more than 2000 milliseconds.

[0044] Figure 3 is a block diagram illustrating an embodiment of a method 300 for analyzing MWP in an insertion analyzer according to aspects of the present disclosure. At step 310, the method 300 may include using a machine learning model to analyze the insertion analyzer (e.g., Figure 1 For example, the first machine learning sub-model (e.g., Figure 2 The first machine learning sub-model 210 of the method can analyze the captured sample image to determine whether the middle plate matches the top plate and the bottom plate. Plate mismatch may occur when the image includes indicators that the plate insert and the top layer are not aligned. For example, some indicators are, but are not limited to, partial circles, such as the semicircle or crescent shapes described herein.

[0045] At 320, method 300 may further include, in response to a mismatch between the machine learning model board insert and the MWP, generating an alarm on the analyzer to notify a user indicating the mismatch. For example, the alarm may include a visual alarm and an audio alarm.

[0046] At 330, method 300 may include, in response to the machine learning model determining that the plate insert matches the MWP, analyzing the sample using the machine learning model to determine whether the MWP is sealed with foil. For example, using the same captured image, a second machine learning sub-model (e.g., Figure 2 The second machine learning sub-model 220 of the MWP can analyze each hole of the MWP to ensure that the foil is applied correctly. The second machine learning sub-model 220 can analyze the light intensity reflected at each hole, and reduced light intensity can indicate that the foil is not applied correctly.

[0047] At 340, method 300 further includes generating an alarm on the analyzer in response to the machine learning model determining that the MWP is not sealed with foil, otherwise enabling the analyzer 1000 to perform its analysis of the sample. For example, the alarm may include a visual alarm and an audio alarm.

[0048] Figure 4 is a block diagram illustrating one embodiment of a computer system 400 configured to implement one or more aspects of the present disclosure. For example, Figure 3The machine learning model 200 and / or method 300 can be implemented using a computer system 400 .

[0049] like Figure 4 As shown, the computing system 400 may include a processor 410, a memory 420, a storage device 430, and an input / output device 440. The processor 410, the memory 420, the storage device 430, and the input / output device 440 may be interconnected via a system bus 450. The processor 410 is capable of processing instructions for execution within the computing system 400. In some exemplary embodiments, the processor 410 may be a single-threaded processor. Alternatively, the processor 410 may be a multi-threaded processor. The processor 410 is capable of processing instructions stored on the memory 420 and / or the storage device 430 to display graphical information for a user interface provided via the input / output device 440.

[0050] Memory 420 is a computer-readable medium, such as a volatile or non-volatile computer-readable medium, that stores information within computing system 400. For example, memory 420 may store a data structure representing a configuration object database. Storage device 430 is capable of providing persistent storage for computing system 400. Storage device 430 may be a floppy disk device, a hard disk device, an optical disk device, a tape device, or other suitable persistent storage device. Input / output device 440 provides input / output operations for computing system 400. In some exemplary embodiments, input / output device 440 includes a keyboard and / or a pointing device. In various specific implementations, input / output device 440 includes a display unit for displaying a graphical user interface.

[0051] According to some exemplary embodiments, the input / output device 440 can provide input / output operations for network devices. For example, the input / output device 440 can include an Ethernet port or other networking port to communicate with one or more wired and / or wireless networks (e.g., a local area network (LAN), a wide area network (WAN), the Internet).

[0052] In some exemplary embodiments, computing system 400 can be used to execute various interactive computer software applications that can be used to organize, analyze and / or store data in various formats. Alternatively, computing system 400 can be used to execute any type of software application. These applications can be used to perform various functions, such as planning functions (e.g., generating, managing, editing electronic spreadsheet documents, word processing documents and / or any other objects, etc.), computing functions, communication functions, etc. The application can include various additional functions or can be independent computing products and / or functions. After activation within the application, the function can be used to generate a user interface provided via input / output device 440. The user interface can be generated by computing system 400 and presented to the user (e.g., on a computer screen monitor, etc.).

[0053] One or more aspects or features of the subject matter described herein may be implemented in digital electronic circuits, integrated circuits, specially designed application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) computer hardware, firmware, software, and / or combinations thereof. These various aspects or features may include a specific implementation in one or more computer programs, which are executable and / or interpretable on a programmable system, which includes at least one programmable processor (which may be dedicated or general, coupled to receive data and instructions from it and to send data and instructions to it), a storage system, at least one input device, and at least one output device. A programmable system or computing system may include a client and a server. Typically, the client and the server are remotely arranged from each other and generally interact through a communication network. The relationship between the client and the server is generated by means of computer programs running on respective computers and the client-server relationship between each other.

[0054] These computer programs may also be referred to as programs, software, software applications, applications, components or codes, including machine instructions for programmable processors, and may be implemented in high-level procedural and / or object-oriented programming languages ​​and / or in assembly / machine languages. As used herein, the term "machine-readable medium" refers to any computer product, device and / or equipment (such as, for example, disks, optical disks, memories and programmable logic devices (PLDs)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor. A machine-readable medium may store such machine instructions non-temporarily (such as, for example, a non-temporary solid-state memory or a magnetic hard drive or any equivalent storage medium). A machine-readable medium may store such machine instructions in a temporary manner (such as, for example, a processor cache or other random access memory associated with one or more physical processor cores) alternatively or additionally.

[0055] To provide interaction with a user, one or more aspects or features of the subject matter described herein may be implemented on a computer having a display device (such as, for example, a cathode ray tube (CRT) or a liquid crystal display (LCD) or a light emitting diode (LED) monitor for displaying information to a user) and a keyboard and a pointing device (such as, for example, a mouse or trackball, through which a user can provide input to the computer). Other types of devices may also be used to provide interaction with a user. For example, the feedback provided to the user may be any form of sensory feedback, such as, for example, visual feedback, auditory feedback, or tactile feedback; input from the user may be received in any form, including sound, voice, or tactile input. Other possible input devices include touch screens or other touch-sensitive devices, such as single-point or multi-point resistive or capacitive tracking pads, voice recognition hardware and software, optical scanners, optical pointers, digital image capture devices and associated interpretation software, and the like.

[0056] When a feature or element is referred to herein as being "on" another feature or element, it can be directly on another feature or element, or there can also be intermediate features and / or elements. On the contrary, when a feature or element is referred to as being "directly on" another feature or element, there are no intermediate features or elements. It will also be understood that when a feature or element is referred to as being "connected," "attached" or "coupled" to another feature or element, it can be directly connected, attached or coupled to another feature or element, or there can be intermediate features or elements. On the contrary, when a feature or element is referred to as being "directly connected," "directly attached" or "directly coupled" to another feature or element, there are no intermediate features or elements. Although described or shown for one embodiment, the features and elements described or shown in this way can be applied to other embodiments. Those skilled in the art will also recognize that the structure or feature mentioned to be arranged "near" another feature can have a portion overlapping or located below an adjacent feature.

[0057] The terms used herein are only for the purpose of describing specific embodiments, and are not intended to limit the present disclosure. For example, as used herein, the singular forms "one", "a kind of" and "the" are also intended to include plural forms, unless the context clearly indicates otherwise. It will also be further understood that when the terms "include" and / or "comprise" are used in this specification, they specify the presence of specified features, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components and / or their groups. As used herein, the term "and / or" includes any combination and all combinations of one or more of the associated listed items, and can be abbreviated as " / ".

[0058] For ease of description, spatially relative terms such as "below", "below", "below", "above", "above", etc. may be used herein to describe the relationship between an element or feature and another element or feature, as shown in the accompanying drawings. It should be understood that, in addition to the orientations depicted in the accompanying drawings, spatially relative terms are also intended to cover different orientations of the device in use or operation. For example, if the device in the accompanying drawings is inverted, the elements described as "below" or "below" other elements or features will then be oriented to be "above" other elements or features. Therefore, the exemplary term "below" can cover the two orientations of "above" and "below". The device can be oriented in other ways (rotated 90 degrees or in other orientations), and the spatially relative descriptors used in this article are interpreted accordingly. Similarly, unless otherwise specifically noted, terms such as "upward", "downward", "vertical", "horizontal" are used herein only for the purpose of explanation.

[0059] Although the terms "first" and "second" may be used herein to describe various features / elements (including steps), these features / elements should not be limited by these terms unless the context otherwise indicates. These terms may be used to distinguish one feature / element from another feature / element. Therefore, without departing from the teachings of the present disclosure, the first feature / element discussed below may be referred to as the second feature / element, and similarly, the second feature / element discussed below may be referred to as the first feature / element.

[0060] Throughout this specification and the claims that follow, unless the context requires otherwise, the word "comprise" and variations such as "comprising" and "containing" mean that various components can be employed together in methods and articles (e.g., compositions and devices including apparatus and methods). For example, the term "comprising" will be understood to imply the inclusion of any specified elements or steps, but not the exclusion of any other elements or steps.

[0061] As used herein in the specification and claims, including as used in the examples, and unless otherwise expressly specified, all numbers can be interpreted as if preceded by the word "about" or "approximately", even if the term does not appear explicitly. When describing amplitude and / or position, the phrase "about" or "approximately" can be used to indicate that the value and / or position described is within the reasonable expected range of value and / or position. For example, a numerical value can have a value of + / -0.1% of a specified value (or range of values), + / -1% of a specified value (or range of values), + / -2% of a specified value (or range of values), + / -5% of a specified value (or range of values), + / -10% of a specified value (or range of values), etc. Unless the context indicates otherwise, any numerical value given herein should also be understood to include about or approximately that value. For example, if the value "10" is disclosed, "about 10" is also disclosed. Any numerical range described herein is intended to include all subranges contained therein. It should also be understood that when a value is disclosed, "less than or equal to" the value, "greater than or equal to the value," and possible ranges between values ​​are also disclosed, as appropriately understood by those skilled in the art. For example, if the value "X" is disclosed, "less than or equal to X" and "greater than or equal to X" are also disclosed (e.g., where X is a numerical value). It should also be understood that throughout this application, data is provided in a variety of different formats, and that the data represents endpoints and starting points and ranges for any combination of data points. For example, if a specific data point "10" and a specific data point "15" are disclosed, it should be understood that values ​​greater than, greater than or equal to, less than, less than or equal to, and equal to 10 and 15 and between 10 and 15 are considered disclosed. It should also be understood that every unit between two specific units is also disclosed. For example, if 10 and 15 are disclosed, 11, 12, 13, and 14 are also disclosed.

[0062] Although various illustrative embodiments are described above, any of a number of changes may be made to the various embodiments without departing from the scope of the present disclosure as described in the claims. For example, in alternative embodiments, the order in which the various method steps described are performed may often be changed, while in other alternative embodiments, one or more method steps may be skipped entirely. In some embodiments, optional features of various device and system embodiments may be included, while in other embodiments, they may not be included. Therefore, the foregoing description is provided primarily for exemplary purposes and should not be construed as limiting the scope of the present disclosure set forth in the claims.

[0063] The examples and illustrations included herein show, by way of illustration and not limitation, specific embodiments in which this theme can be practiced. As mentioned, other embodiments can be utilized and derived therefrom, so that structural and logical substitutions and changes can be made without departing from the scope of the present disclosure. These embodiments of the subject matter of the present invention may be referred to herein individually or collectively by the term "the present invention", which is merely for convenience, and is not intended to actively limit the scope of the present application to any single inventive concept when more than one inventive concept is actually disclosed. Therefore, although specific embodiments have been shown and described herein, any arrangement calculated to achieve the same purpose may replace the specific embodiments shown. The present disclosure is intended to cover any and all modifications or variations of various embodiments. After reviewing the above description, the combination of the above embodiments and other embodiments not explicitly described herein will be apparent to those skilled in the art.

Claims

1. A method, comprising: analyzing a sample inserted into an analyzer (1000) using a machine learning model (200) to determine whether the plate insert matches a multi-well plate (MWP); responsive to the machine learning model (200) detecting a mismatch between the plate insert and the MWP, generating an alert on the analyzer to notify a user indicating the mismatch; In response to the machine learning model (200) determining that the plate insert matches the MWP, analyzing the sample using the machine learning model to determine whether the MWP is sealed with foil; as well as In response to the machine learning model (200) determining that the MWP is not sealed with foil, an alarm is generated on the analyzer and the analyzer is otherwise enabled to perform analysis of the sample by the analyzer.

2. The method of claim 1, wherein the machine learning model (200) is trained using a combination of real images and augmented images.

3. The method of claim 1, wherein the machine learning model (200) is trained using a training dataset, the training dataset comprising images of MWPs having at least two different numbers of pores.

4. The method of claim 3, wherein the images of MWPs having at least two different numbers of holes include images with and without foil on the MWP.

5. The method of claim 1, wherein the machine learning model (200) is trained using a training data set comprising images of both correct and incorrect MWP and foil combinations.

6. The method of claim 1, wherein the machine learning model (200) is trained using a training data set comprising images of MWPs with multiple fill volumes, multiple dyes, and multiple foil types.

7. The method of claim 1, wherein the machine learning model (200) is trained using a training dataset comprising images of MWPs having a variety of different filling patterns.

8. The method of claim 1, wherein the machine learning model (200) is trained using a training dataset, the training dataset comprising images of MWPs with user errors.

9. The method of claim 1, wherein analyzing the sample using the machine learning model (200) to determine whether the mismatch between the plate insert and the MWP exists includes calculating a confidence score and generating an alert when the confidence score is below a threshold.

10. The method of claim 1, wherein analyzing the sample using the machine learning model (200) to determine whether the MWP is sealed with the foil comprises calculating a confidence score, and wherein an alert is generated when the confidence score is below a threshold.

11. The method of claim 1, when any alarm is generated, receiving an instruction from a user to continue operation of the analyzer.

12. The method of claim 1 , wherein the machine learning model comprises a plurality of machine learning sub-models (210, 220), and wherein a first machine learning sub-model (210) of the plurality of machine learning sub-models is trained to determine whether the plate insert matches the MWP, and a second machine learning sub-model (220) of the plurality of machine learning sub-models is trained to determine whether the sample is sealed with the foil.

13. The method of claim 12, wherein the first machine learning sub-model (210) and the second machine learning sub-model (220) are trained using different data sets. The method of claim 2 , wherein a plurality of enhancement techniques are used to generate the enhanced image.

15. A system, comprising: Memory (420); and a processor (410) coupled to the memory (420) and configured to: analyzing a sample inserted into an analyzer (1000) using a machine learning model (200) to determine whether the plate insert matches a multi-well plate (MWP); responsive to the machine learning model (200) detecting a mismatch between the plate insert and the MWP, generating an alert on the analyzer to notify a user indicating the mismatch; In response to the machine learning model (200) determining that the plate insert matches the MWP, analyzing the sample using the machine learning model to determine whether the MWP is sealed with foil; as well as In response to the machine learning model (200) determining that the MWP is not sealed with foil, an alarm is generated on the analyzer and the analyzer is otherwise enabled to perform analysis of the sample by the analyzer.

Images