Systems and methods of field of observation filtering

Abstract

Variations in the quality of images captured by a biological analysis system may be addressed using a method which determines a field of observation that can be used for filtering data for generating results. Such a method may include obtaining a plurality of images of particles from a field of view, analyzing the plurality of images, determining a focal parameter associated with the images, and utilizing the focal parameter to determine the field of observation. In such a case, the field of view may represent a first imaging area of a flowcell, and the field of observation may represent a second, smaller, imaging area of the flowcell.

Description

SYSTEMS AND METHODS OF FIELD OF OBSERVATION FILTERINGCROSS REFERENCE TO RELATED APPLICATIONS

[0001] This is an international application which claims the benefit of provisional patent application 63 / 650,220, filed with the United States Patent Office on May 21,2024 for “Systems and Methods of Field of Operation Filtering,” the disclosure of which is hereby incorporated by reference in its entirety.BACKGROUND

[0002] Blood cell analysis is one of the most commonly performed medical tests for providing an overview of a patient's health status. A sample (e.g., a blood sample) can be drawn from a patient's body and stored in a test tube containing an anticoagulant to prevent clotting. The sample can then be processed to determine information such as the number or percent of cells of various different categories that it includes. This information, in turn, can be applied in treatment and / or diagnosis of a patient.

[0003] Recent advances in the technology have incorporated imaging as part of the analytical process, however the use of images has its own challenges. In an imaging context, it is important to have high quality images (e.g., with good focal quality) in order to extract information about particular cell types, such as proper identification of the type of cell that is imaged. Quality of images can vary due to various reasons - including a) imperfections in manufacturing, installation, or operation, b) imperfections that develop over time (e g., curvature, warped surfaces, or other mechanical imperfections), or c) imperfections associated with a field of view (e.g., whereby a portion of a larger field of view may have better focal quality due to its positioning relative to a camera). This image quality importance is heightened where flow imaging is involved, that is the use of a camera used to capture pictures of a flowing (rather than a static) sample, where it can be difficult to capture high quality images when the sample is in motion.

[0004] Some variations may be addressed by replacing or recalibrating an analyzer or its components, however, this calibration can be difficult and time consuming, and may prevent an analyzerfrom being used to process actual samples, which can have a direct impact on the health of the patients whose samples are required to wait while the calibration takes place.

[0005] Therefore there is a need for a solution that can assess image focal quality quickly, for instance by establishing an optimal focal area (e.g., a field of observation) within a broader imaging field (e.g., a field of view).SUMMARY

[0006] Described herein are devices, systems and methods which can be used for determining a field of observation which can be used to address variation in quality of images captured by a biological analysis system. In some embodiments the biological analysis system comprises a hematology (blood) analyzer. In some embodiments, the biological analysis system comprises a urine analyzer.

[0007] An illustrative implementation of such technology relates to a method which comprises obtaining a plurality of images of particles from a field of view, analyzing the plurality of images, determining a focal parameter associated with the images, and utilizing the focal parameter to determine the field of observation. In such a case, the field of view may represent a first imaging area of a flowcell, and the field of observation may represent a second, smaller, imaging area of the flowcell. Corresponding systems or computer readable media may also be implemented based on this disclosure.

[0008] While multiple examples are described herein, still other examples of the described subject matter will become apparent to those skilled in the art from the following detailed description and drawings, which show and describe illustrative examples of disclosed subject matter. As will be realized, the disclosed subject matter is capable of modifications in various aspects, all without departing from the spirit and scope of the described subject matter. Accordingly, the drawings and detailed description are to be regarded as illustrative in nature and not restrictive.BRIEF DESCRIPTION OF THE DRAWINGS

[0009] While the specification concludes with claims which particularly point out and distinctly claim the invention, it is believed the present invention will be better understood from the followingdescription of certain examples taken in conjunction with the accompanying drawings, in which like reference numerals identify the same elements and in which:

[0010] FIG. 1 is a schematic illustration, partly in section and not to scale, showing operational aspects of an exemplary flow cell and high optical resolution imaging device for sample image analysis using digital image processing.

[0011] FIG. 2 illustrates a method for addressing focus issues.

[0012] FIG. 3 illustrates an example machine learning model.

[0013] FIG. 4 illustrates an example of a layer such as may be included in a machine learning model as shown in FIG. 3.

[0014] FIG. 5 illustrates a misalignment in the Y direction between a sample stream and a camera’s depth of field.

[0015] FIG. 6 illustrates a misalignment in the X direction between a sample stream and a camera’s depth of field.

[0016] FIG. 7 illustrates a graph corresponding to the misalignment of FIG. 5.

[0017] FIG. 8 illustrates a graph corresponding to the misalignment of FIG. 6.

[0018] FIG. 9 illustrates a field of view (FOV) and smaller field of observation (FOO).

[0019] FIG. 10 illustrates how pixels in a cell image may be grouped.

[0020] FIG. 11 illustrates a process which may be used to determine focal distance for an image.

[0021] FIG. 12 illustrates a process which may be used to determine focal distance for an image.

[0022] FIG. 13 illustrates a method which may be used to determine focal parameters in the form of aggregate focus values for each of a plurality of portions of a camera’s field of view.

[0023] FIG. 14 illustrates steps which may be performed after a field of observation has been determined.

[0024] The drawings are not intended to be limiting in any way, and it is contemplated that various embodiments of the invention may be carried out in a variety of other ways, including those not necessarily depicted in the drawings. The accompanying drawings incorporated in and forming a part of the specification illustrate several aspects of the present invention, and together with the description serve to explain the principles of the invention; it being understood, however, that this invention is not limited to the precise arrangements shown.DETAILED DESCRIPTION

[0025] The present disclosure relates to apparatus, systems, compositions, and methods for analyzing a sample containing particles. In one embodiment, the invention relates to an automated particle imaging system which comprises an analyzer which may be, for example, a visual analyzer. In some embodiments, the visual analyzer may further comprise a processor to facilitate automated analysis of the images.

[0026] According to some aspects of this disclosure, a system comprising a visual analyzer may be provided for obtaining images of a sample comprising particles suspended in a liquid. Such a system may be useful, for example, in characterizing particles in biological fluids. In one example detecting and quantifying erythrocytes, reticulocytes, nucleated red blood cells, platelets, and white blood cells, including white blood cell differential counting, categorization and subcategorization and analysis. Other similar uses such as characterizing blood cells from other fluids are also contemplated.

[0027] According to some aspects of this disclosure, a system includes a flowing biological sample, a flowcell that the biological sample flows through, and a camera configured to take images of contents of the biological sample as the sample passes an imaging region of the flowcell.

[0028] The classification of blood cells in a blood sample is an exemplary application for which the subject matter is particularly well suited, though other types of body fluid samples may be used. For example, aspects of the disclosed technology may be used in analysis of a non-blood body fluid sample comprising blood cells (e.g., white blood cells and / or red blood cells), such as serum, bone marrow, lavage fluid, effusions, exudates, cerebrospinal fluid, pleural fluid, peritoneal fluid, and amniotic fluid. It is also possible that the sample can be a solid tissuesample, e.g., a biopsy sample that has been treated to produce a cell suspension. The sample may also be a suspension obtained from treating a fecal sample. A sample may also be a laboratory or production line sample comprising particles, such as a cell culture sample. The term sample may be used to refer to a sample obtained from a patient or laboratory or any fraction, portion or aliquot thereof. The sample can be diluted, divided into portions, or stained in some processes. Other exemplary applications can utilize a urine sample, and analysis of urine particles (including blood cells) that are in a urine sample.

[0029] Though the embodiments presented herein may primarily utilize blood samples and blood cells in an exemplary manner, such embodiments should not be construed as limiting, as the techniques can be used in a variety of biological samples.

[0030] In some aspects, samples are presented, imaged and analyzed in an automated manner. In the case of blood samples, the sample may be substantially diluted with a suitable diluent or saline solution, which reduces the extent to which the view of some cells might be hidden by other cells in an undiluted or less-diluted sample. The cells can be treated with agents that enhance the contrast of some cell aspects, for example using permeabilizing agents to render cell membranes permeable, and histological stains to adhere in and to reveal features, such as granules and the nucleus. In some cases, it may be desirable to stain an aliquot of the sample for counting and characterizing particles which include reticulocytes, nucleated red blood cells, and platelets, and for white blood cell differential, characterization and analysis. In other cases, samples containing red blood cells may be diluted before introduction to the flow cell and / or imaging in the flow cell or otherwise.

[0031] The particulars of sample preparation apparatus and methods for sample dilution, permeabilizing and histological staining, generally may be accomplished using precision pumps and valves operated by one or more programmable controllers. Examples can be found in patents such as U.S. Pat. No. 7,319,907. Likewise, techniques for distinguishing among certain cell categories and / or subcategories by their attributes such as relative size and color can be found in U.S. Pat. No. 5,436,978 in connection with white blood cells. The disclosures of these patents are hereby incorporated by reference in their entirety.

[0032] Turning now to the drawings, FIG. 1 schematically shows an exemplary flow cell 22 for conveying a sample fluid through a viewing zone 23 of a high optical resolution imaging device 24 in a configuration for imaging microscopic particles in a sample flow stream 32 using digital image processing. Flow cell 22 is coupled to a source 25 of sample fluid which may have been subjected to processing, such as contact with a particle contrast agent composition and heating. Flow cell 22 is also coupled to one or more sources 27 of a particle and / or intracellular organelle alignment liquid (PIOAL), such as a clear glycerol solution having a viscosity that is greater than the viscosity of the sample fluid.

[0033] The sample fluid is injected through a flattened opening at a distal end 28 of a sample feed tube 29, and into the interior of the flow cell 22 at a point where the PIOAL flow has been substantially established resulting in a stable and symmetric laminar flow of the PIOAL around / surrounding (e.g., circumferentially in a circular cross-sectional arrangement, or surrounding a plurality of sides of in a non-circular (e.g., rectangular) cross-sectional arrangement) the ribbon-shaped sample stream. The sample and PIOAL streams may be supplied by precision metering pumps that move the PIOAL with the injected sample fluid along a flowpath that narrows substantially. The PIOAL envelopes and compresses the sample fluid in the zone 21 where the flowpath narrows. Hence, the decrease in flowpath thickness at zone 21 can contribute to a geometric focusing of the sample stream 32. The sample fluid ribbon 32 is enveloped and carried along with the PIOAL downstream of the narrowing zone 21, passing in front of, or otherwise through the viewing zone 23 of, the high optical resolution imaging device 24 where images are collected, for example, using a charge coupled device (CCD) 48. In this way, flow imaging is performed where images from the flowing sample stream and the cellular material contained therein are collected. Processor 18 can receive, as input, pixel data from CCD 48. The sample fluid ribbon flows together with the PIOAL to a discharge 33.

[0034] As shown here, the narrowing zone 21 can have a proximal flowpath portion 21a having a proximal thickness PT and a distal flowpath portion 21b having a distal thickness DT, such that distal thickness DT is less than proximal thickness PT. The sample fluid can therefore be injected through the distal end 28 of sample tube 29 at a location that is distal to the proximal portion 21a and proximal to the distal portion 21b. Hence, the sample fluid can enter thePIOAL envelope as the PIOAL stream is compressed by the zone 21 . wherein the sample fluid injection tube has a distal exit port through which sample fluid is injected into flowing sheath fluid, the distal exit port bounded by the decrease in flowpath size of the flow cell.

[0035] The digital high optical resolution imaging device 24 with objective lens 46 is directed along an optical axis that intersects the ribbon-shaped sample stream 32. The relative distance between the objective 46 and the flow cell 33 is variable by operation of a motor drive 54, for resolving and collecting a focused digitized image on a photosensor array. In one example, objective 46 can be thought of as a microscope or a part of a microscope, in that it magnifies an imaging area. In various examples, such relative distance is achieved whereby the motor drive 54 can move the objective relative to the fixed flow cell, the flow cell relative to the fixed objective, or the camera relative to at least one of the fixed objective or fixed flowcell. Additional information regarding the construction and operation of an exemplary flow cell such as shown in FIG. 1 is provided in U.S. Patent 9,322,752, entitled “Flow cell Systems and Methods for Particle Analysis in Blood Samples,” filed on March 17, 2014, the disclosure of which is hereby incorporated by reference in its entirety. Descriptions of approaches which may be used for focusing in an imaging system such as shown in FIG. 1 are provided in Published App. No. 2024 / 0357232 titled “Focus Quality Determination through Multi-Layer Processing,” filed on June 11, 2024, U.S. Patent 9,857,361 titled “Flowcell, Sheath fluid, and Autofocus Systems and Methods for Particle Analysis in Urine Samples”, filed on March 17, 2014, U.S. Patent 10,705,008 titled “Autofocus Systems and Methods for Particle Analysis in Blood Samples”, filed on March 17, 2014, U.S. Patent 10,705,011, titled “Dynamic Focus System and Methods”, filed October 5, 2017, and international application W02023 / 150064 titled “Measure Image Quality of Blood Cell Images”, filed January 27, 2023, the disclosures of each of which are hereby incorporated by reference in their entirety. Descriptions of approaches which may be used for focusing in an imaging system such as shown in FIG. 1 are provided in Published App. No. 2024 / 0357232 titled “Focus Quality Determination through Multi-Layer Processing,” filed on June 11, 2024, U.S. Patent 9,857,361 titled “Flowcell, Sheath fluid, and Autofocus Systems and Methods for Particle Analysis in Urine Samples”, filed on March 17, 2014, U.S. Patent 10,705,008 titled “Autofocus Systems and Methods for Particle Analysis in Blood Samples”, filed on March 17, 2014, U.S. Patent 10,705,011, titled “Dynamic Focus System and Methods”, filed October 5, 2017, and international applicationWO2023 / 150064 titled “Measure Image Quality of Blood Cell Images”, fded January 27, 2023, the disclosures of each of which are hereby incorporated by reference in their entirety.

[0036] Systems such as shown in FIG. 1 may be used to analyze samples (e.g., blood samples, or urine samples) and, based on that analysis, provide biological analysis results, such as the numbers of cells of particular types are included in the samples (e.g., white blood cell counts, red blood cell counts) or relative proportions of different types of cells in a sample (e.g., immature granulocyte fraction). For the purpose of performing such analysis, systems such as shown in FIG. 1 may capture images of cells which can form the raw data that would ultimately provide the analysis results. However, as noted previously, maintaining the quality of such images, e.g., through calibration, can be problematic. For example, as shown in FIGS. 5 and 6, it is possible that a sample stream may not align with the depth of field of the camera used to capture images, which can result in sample images being out of focus. To address this, the disclosed technology may be used to implement a method which would detect such mismatches between the sample stream and depth of field, and respond to them by identifying a portion of the camera’s field of view in which pictures of the sample stream could be expected to be in focus - (for example, in the scenario of FIGS. 5 and 6, the portion of the field of view falling within the region defined by the values of X_a, X_b, Y_a and Y_b). This type of approach could give rise to a data classification such as shown in FIG. 9, in which a subset of an imaging device (e.g., camera’s) field of view (“FOV”) is identified as the field of observation (“FOO”), and only particles imaged in the field of observation are used to generate a biological result (e.g., a cell count) for a sample. An example method which could be used to implement this type of approach is shown in FIG. 2, discussed below.

[0037] Turning now to FIG. 2, as shown in that figure, a method for addressing focus issues may include obtaining 201 a plurality of images. This may include, for example, capturing a particle image (e.g., using the imaging device 24 of FIG. 1), and then segmenting out the individual particles in the image, thereby resulting in multiple images, each of which depicts a single particle. In implementations where it takes place, the segmentation may be performed in a variety of manners. For example, in some cases, pixels in an image may be compared to a brightness threshold, and all pixels below (or above, depending on the implementation and encoding of the images) the threshold could be treated as cell pixels while all other pixels couldbe treated as background pixels. Then, in a case where an image depicted multiple particles, the foreground pixels could be subjected to image processing (e.g., blob analysis) to identify which pixels were associated with which particles, and then separate the particles into their own images. Other approaches, however, are also possible and may be used in some cases. For example, in some cases, rather than simply classifying pixels by comparing them to a brightness threshold, pixels may be classified as background or foreground pixels by comparing their neighbors to a brightness threshold, and then classifying the pixels based on whether their neighbors were above or below the threshold. For instance, in some cases, if all of a pixel’s neighboring pixels were foreground pixels (based on the threshold comparison), then that pixel may be treated as a foreground pixel, if all of a pixel’s neighbors were background pixels (again, based on the threshold comparison), that pixel may be treated as a background pixel, and if some of a pixel’s neighbors were foreground pixels and some were background pixels, that pixel may be treated as a border pixel (which, depending on the implementation, may or may not be treated as included in the particle represented by the foreground pixels). Alternatively, a machine learning model (e.g., deep learning) can be used where an analysis program is trained to identify a cell region as a foreground region of an image and isolate it for image analysis purposes. Other approaches are also possible, and so the neighboring pixel based on approach to segmentation should also be understood as being illustrative of a potential approach to segmentation, and should not be treated as limiting on the scope of protection provided by this document.

[0038] Whatever steps are involved in obtaining 201 images, once the images had been obtained 201, they may be analyzed 202. This analysis 202 may include, for example, determining a focus value or focal parameter for each of the images, shown as a step 203. Various techniques readily ascertainable to those of ordinary skill in the art can be used to determine the focal value / focal parameter.

[0039] In some examples, the focal parameter can be established, for example, using pixel binning, where pixels in an image are grouped (i.e., binned) based on location, and then a curve based on values for the different groups of pixels is analyzed to generate a focal distance. An illustration of how pixels in a cell image may be grouped is provided in FIG. 10, where rings surrounding a cell border 1001 are calculated to identify the corresponding bins (e g., bin 0,bin 1, bin 2, bin 3, bin -1, bin -2, and bin -3). The border pixels should generate a ring, being the border or boundary ring of the cell, shown as the solid border line 405. Bin 0 is identified by moving inward 1 pixel from the border pixels to get the next inner ring. Bin 0 is the area between the border ring and the ring 1 pixel inward from the border. Bin -1 is the area between the ring 1 pixel inward from the border and the ring 2 pixels inward from the border. The process continues inward by an additional pixel to identify bins -2 and -3. Similarly, bin 1 is identified by moving outward 1 pixel from the border ring to get the ring 1 pixel outward from the border. Bin 1 is the area between the border ring and the ring 1 pixel outward from the border ring. The process can be continued outward by 1 pixel to identify bins 2 and 3. Bins may also be defined using image morphological erosion / dilution. Once each bin is identified, an average intensity value (e.g., the V value for pixels encoded using the HSV format) can be calculated for each bin. The average intensity value for each bin can be calculated by identifying the intensity value for each pixel within the bin and calculating the average (e.g., the average intensity value of all the pixels between the boundary and the 1 pixel inward ring is the average intensity value at bin 0). The average intensity value for each bin can be plotted to generate an intensity-distance function for the imaged particle.

[0040] Once the pixel bins had been used to create a distance-intensity function, that function can be analyzed to determine the focal distance for the image. A process which may be used for this analysis is shown in FIG. 11, which begins with calculating 1101 a pixel intensity ratio for the image (e.g., by dividing the average intensity value for the bin at the edge of the cell by the average intensity value for the bin at the center of the cell). Once the pixel intensity ratio has been calculated 1101, it may be used to determine 1102 a focal distance direction. This may be done, for example, by using a previously defined equation which relates focal distance to pixel intensity ratio (e.g., an equation determined by the manufacturer of the biological analysis system by using curve fitting with a set of images of cells having known focal distances). The direction may then be determined 1103 based on the sign of the focal distance (i.e., negative focal distance is one direction, positive focal distance is another) and, depending on the direction, the focal distance may be determined 1103 as equal to the focal distance calculated in the previous determination 1102, or may be determined 1103 using a different equation, such as an equation which relates width of a cell border to focal distance (e.g., focal distancemay be determined using the pixel intensity ratio if the focal direction is positive, while it may be determined using the border width if the focal direction is negative).

[0041] Other types of function analysis are also possible, and may be implemented in some cases. For instance, in some cases, rather than using an approach such as shown in FIG. 11, a process such as shown in FIG. 12 may be used to determine a focal distance. In that process, rather than calculating a 1101 pixel intensity ratio, initially a determination 1201 would be made of an inflection point (e.g., point of fastest change, which may be identified by taking a first order derivative) in the function representing intensity of pixels relative to their location. Once the inflection point is known, the process of FIG. 12 would continue with determining 1202 a left mark and determining 1203 a right mark. These determinations 1202-03 may be identifications of points to the left and right of the inflection point on a curve defined by the function which could subsequently be used in calculating a focal distance. For example, a left mark may be the bottom of a valley to the left of the inflection point or, if there was no such valley, the peak of the second order derivative to the left of the inflection point. Similarly, a right mark may be the top of a peak to the right of the inflection point or, if there is no such peak, a trough of the second order derivative to the right of the inflection point. These marks may then be used to determine 1204 the focal distance for the image. For example, the values of the marks, as well as their respective distances from the inflection point may be used as variables in a focal distance equation (e.g., an equation determined by the manufacturer of the biological analysis system using images with known focal distances as described previously), or they may be used as characteristics to match the intensity-distance curve for an image to a set of predefined intensity-distance curves corresponding to known focal distances, with the focal distance corresponding to the closest predefined curve being treated as the focal distance for the image in question.

[0042] Approaches to determining a focus value which do not involve curve analysis or pixel binning such as described in the context of FIGS. 10-12 are also possible, and may be used in some cases. For example, in some cases, an image of a particle may be provided to a machine learning model which had been trained to provide a value showing a displacement of the depicted particle relative to the focal plane of the imaging device (e.g., a value of 0 for a perfectly in focus image, or values of 1pm or -1pm for particles that were one micron awayfrom the focal plane at the time of imaging). An example of such a model is depicted in FIGS. 3 and 4, discussed below.

[0043] In some embodiments, machine learning techniques can be used to assess a focus value. Turning now to FIG. 3, that figure illustrates a machine learning model which can be used in some embodiments in identifying focus values for images captured by an analyzer such as shown in FIG. 1. In the architecture of FIG. 3, an input image 301 would be analyzed in a series of stages 302a-302n, each of which may be referred to as a “layer,” and which are illustrated in more detail in FIG. 4. As shown in FIG. 4, an input 401 (which, in the initial layer 402a of FIG. 4 would be the input image 301, and otherwise would be the output of the preceding layer) is provided to a layer 402 where it would be processed to generate one or more transformed images 403a-403n. This processing may include convolving the input 401 with a set of filters 404a-404n, each of which would identify a type of feature from the underlying image that would then be captured in that filter’ s corresponding transformed image. For instance, as a simple example, convolving an image with the filter shown in table 1 could generate a transformed image capturing the edges from the input image 401.[ -1 -1 -1 ] [ -1 8 -1 ] [ -1 -1 -1 ] Table 1

[0044] As shown in FIG. 4, in addition to generating transformed images 403a-403n a layer may also generate a pooled image 405a-405n for each of the transformed images 403a-403n. This may be done, for example, by organizing the appropriate transformed image into a set of regions, and then replacing the values in that region with a single value, such as the maximum value for the region or the average of the values for the region. The result would be a pooled image whose resolution would be reduced relative to its corresponding transformed image based on the size of the regions it was split into (e g., if the transformed image had NxN dimensions, and it was split into 2x2 regions, then the pooled image would have size (N / 2)x(N / 2)). These pooled images 405a-405n could then be combined into a single output image 406, in which each of the pooled images 405a-405n is treated as a separate channel in the output image 406. This output image 406 can then be provided as input to the next layer as shown in FIG. 3.

[0045] Returning to the discussion of FIG. 3, after a final output image 303 has been created through the various stages 302a-302n of processing, the final output image 303 could be provided as input to a neural network 304. This may be done, for example, by providing the value of each channel of each pixel in the output image 303 to an input node of a densely connected single layer network. The output of the neural network 304 could then be treated a focus value for the original input image 301. Training for a machine learning model such as shown in FIGS. 3-4 may include for example, capturing images at various distances from optimum focus, annotating the captured images with the known distances, and then comparing the known distance values with the values provided by the model when the annotated images are provided to it as inputs. The differences between these provided and known values may then be used to create loss values, and those loss values could be used to update the values of the model (e.g., weights in the neural network 304 or the filters 404a-404n) so that the loss would be minimized over time. The training can also include splitting the annotated images into multiple subsets, or folds, and then training and evaluating the model multiple times, with a different fold of training images being held back as a validation set each time (i.e., K-fold cross validation). In this way, performance metrics from each training instance can be averaged to verify the model’s generalization performance and, assuming the performance is acceptable, a final trained version of the model (e.g., whichever trained model had the best individual performance) can be used to make inferences (e.g., generate focus values) in production.

[0046] Combinations of approaches such as described above, are also possible. For example, in some cases, a system based on this technology may be implemented to use one approach (e.g., the function analysis approach of FIG. 11) when determining 203 a focal parameter for an image of one type of particle (e.g., a red blood cell), and use another approach (e.g., the function analysis approach of FIG. 12) when determining 203 a focal parameter for an image of another type of particle (e.g., a white blood cell). Alternative types of approaches which do not use either intensity-distance curves such as described in the context of FIGS. 11 and 12 or machine learning such as described in the context of FIGS. 3 and 4 may also be used in some cases. For instance, some implementations of the disclosed technology may determine a focus value for an image using sharpness of an image, as measured by the contrast between the image’ s pixels. An image’s focus may also be determined using approaches such as described in U.S. patent 10,705,011 for dynamic focus system and methods, international patent applicationPCT / US0222 / 052702 for focus quality determination through multi-layer process, or international application PCT / US23 / 11759 for measuring image quality of blood cell images, the disclosures of which are hereby incorporated by reference in their entirety. Accordingly, the discussion of how images may be analyzed 202 using trained machine learning models such as shown in FIGS. 3 and 4 or pixel binning and function analysis as shown in FIGS. 9-12 should be understood as being illustrative only, and should not be treated as implying limitations on the protection provided by this document or any related document.

[0047] However the image analysis 202 is performed, once it is complete the information derived from the image analysis 202 (e.g., focal distances for individual particle images) may be used to determine 203 focal parameters associated with the images. An example of how this determination may take place is provided in FIG. 13, which illustrates a method which may be used to determine 203 focal parameters in the form of aggregate focus values for each of a plurality of portions of a camera’s field of view. As shown in that figure, the determination 203 of focal parameters may begin with organizing 1301 the camera’s field of view into bins. To illustrate, consider an exemplary scenario in which the field of view is a 5000x4000 pixel rectangle. In such a scenario, organizing the field of view into bins may include splitting the field of view into rectangular or square, non-overlapping bin regions (e.g., a square bin measuring 200 pixels on a side by way of example). The method may then continue with organizing 1302 the previously analyzed images into those bin regions. For example, for each image, the bin region which includes the center of that image may be identified, and the image may then be allocated to that bin region. These bin region allocations may then be used to calculate an aggregate parameter value for each bin. For example, for each bin, the focal distances of the images allocated to that bin could be averaged to provide an aggregated (in this case averaged) focal distance for that bin, which is then considered the focal parameter value for that particular bin. Please note, the particular field of view and bin sizes are exemplary and illustrative in nature, and various field of view sizes and shapes and various bin sizes and shapes are contemplated depending on the circumstances and needs of the systems / methods contemplated herein.

[0048] Other approaches to determining 203 focal parameters are also possible, and may be used in some cases. For example, while it is possible that bin regions could be defined in a non-overlapping manner, in some implementations it may be possible that one or more overlapping bins may be used as well (e.g., to provide finer resolution for determining the extents of the field of observation). In such a case, when organizing 1302 images into bin regions, an image may be organized into whatever bin region it had the greatest overlap with, or may be associated with each of the overlapping bin regions which contained its center. Similarly, it is possible that calculating 1303 aggregate parameter values for bin regions may not be performed by averaging values of images organized into those bin regions, but instead may include calculations of values such as the median focal distance, the standard deviation of focal distances, a percentile (e.g., 25thpercentile focal distance, 75thpercentile focal distance), or calculating a range (10thpercentile - 90thpercentile, 25thpercentile to 75thpercentile, etc.).

[0049] Once the focal parameters had been determined 203, those parameters could be used to determine 204 the field of observation (“FOO”). To illustrate how this may be done, consider the example from the preceding paragraph of a camera with a 5000x4000 pixel field of view which was organized into 500 non-overlapping 200x200 pixel bin regions. In such a case, if the camera had a 2pm depth of field, then an aggregate focal distance for each bin region could be compared with a set of thresholds (e.g., -1pm and 1pm) to determine if that bin region was in focus. Graphs illustrating this type of comparison are provided in FIGS. 7 and 8, with FIG. 7 corresponding to the misalignment shown in FIG. 5, and FIG. 8 corresponding to the misalignment show in FIG. 6. Once the comparisons had been made, the minimum and maximum X and Y values of the centers of the bins whose mean focal distances were within the depth of field (or, in some cases, the minimum and maximum X and Y extents of the bin regions whose mean focal distances were within the depth of field) could then be used to define the extents of the field of observation which, in this case, would be a rectangle with minimum and maximum X values of 700 and 4300, and minimum and maximum Y values of 1100 and 3300.

[0050] While the example above illustrates how the disclosed technology can be used to determine 204 a field of observation, such as that shown in FIG. 9, which may be smaller than the field of view, but which would only include images which are suitable for use in generating biological results, in some implementations other ways of determining 204 a field of observation may be used. For example, in some cases, afield of observation may be determined204 without bin regions, whether using overlapping bin regions or otherwise. For instance, in some cases a field of observation may be defined as the portion(s) of the field of view which are covered by at least one patch (i.e., portion of an image which depicts a particle, such as could be extracted during segmentation) having a focal parameter between first and second thresholds (which thresholds may or may not correspond to a depth of field as described previously). It is also possible that a field of observation may be determined 204 using logic that goes beyond comparison with one or more thresholds. For example, in some cases a bin region may be treated as within the field of observation if its average focal distance is within a first set of thresholds, and the standard deviation of its focal distances is within a second set of thresholds (which second set of thresholds may be determined in part based on the average, such as increasing the distance between the thresholds in the second set if the average was closer to zero focal offset). Similarly, in some cases the extents of a field of observation may be based on using information like centers of bins as data points which can be used to generate a curve showing relationships between coordinates and parameter values, and then using the point(s) where such a curve goes outside the relevant threshold(s) as the bounds of a field of observation. Accordingly, the description above of how a field of observation may be determined 204, like the other examples provided in the context of FIG. 2, should be understood as being illustrative only, and should not be treated as limiting.

[0051] Turning now to FIG. 14, that figure illustrates additional steps which may be performed in some cases after a field of observation has been determined. As shown in that figure, after a field of observation has been determined 1401 (e.g., using a method such as discussed above in the context of FIG. 2), a further determination 1402 may be made of whether the field of observation is suitable for generating biological analysis results. This may include, for instance, determining if the field of observation was so small (e.g., if only a small number of bin regions had been below an out of focus threshold) that it is unlikely enough data could be gathered from the field of observation for the analysis results. For example, a system implemented based on this disclosure may be configured with a minimum field of observation area value, and if the actual area of the field of observation was below that minimum value, the determination 1402 could be that the field of observation was not suitable for generating biological analysis results. Other approaches to determining 1402 whether the field of observation was suitable for generating biological analysis results may also be used. Forexample, in some cases, if the field of observation was discontinuous (e g., there were nonadj acent portions of the field of view below an out of focus threshold) it could be treated as indicating an underlying issue with the system that should be addressed before using data (e.g., images) from the system for generating biological analysis results. However the determination 1402 was made, if it was determined that the field of observation as not suitable, then a system flag could be generated 1403 indicating that troubleshooting (e.g., calling maintenance) should be performed, thereby allowing the underlying issue leading to the unsuitable field of observation to be corrected before generating biological analysis results. Alternatively, if the field of observation was suitable, then data from that field could be used to generate 1404 the biological analysis result, as discussed below.

[0052] As shown in FIG. 14, to generate 1404 a biological analysis result, a determination 1405 could be made for each image depicting a particle of whether that image is within the field of observation. For example, in a case where images are organized 1302 into bin regions, the determination of whether an image is or is not within the field of observation may be made based on whether the bin region containing that image is or is not within the field of observation. Alternatively, it is also possible that an overlap could be determined between each of the images and the field of observation, and images with an overlap that exceeded a threshold amount (e g., 50%) could be treated as within the field of observation, even if they had not already been organized into bin regions within the field. Once the determination 1405 had been made, the images which were not within the field of observation could be excluded 1406 from the result generation (e.g., discarded, or archived without being used), and the biological analysis result (e.g., blood cell count, etc.) could be generated 1404 based on the images determined to be within the field of observation. In this way, a method such as shown in FIG. 14 could be used to flag issues as needed, even while ensuring that, where practical, a portion of a camera’s field of view is used as a field of observation so that reliable results are created using good quality images, even though some portion of the field of a view of the camera that captured those images may have been unacceptably out of focus.

[0053] Variations may also be possible in how a field of observation can be applied once it has been determined. For instance, while FIG. 14 illustrates generating 1403 a flag if it is determined 1402 that the field of observation is not suitable for generating biological analysis results, insome cases a flag may be generated even if the field of observation is suitable. For example, in some cases, there may be a set of flagging thresholds (e.g., thresholds which are looser than those which could be used to determine if the field was suitable at all) which could be used to identify if the field of observation indicates there may be an underlying issue that requires attention, even if it may be suitable for gathering data for generating results. By using this type of approach, a user may be alerted to an issue before it becomes critical, so that he or she can take action to address the issue in a manner that would minimize the disruption caused by such remediation (e.g., scheduling maintenance or recalibration during a time of relatively low demand for tests).

[0054] It is also possible that the physical components used to implement the disclosed technology may vary from case to case. For instance, in some cases, a method such as shown and described in the context of FIGS. 2 and / or 14 may be performed by executing instructions using one or more processors which are resident on, or local (e.g., connected to, either directly or over a local area network) to a system such as shown in FIG. 1. However, in other cases, a system such as shown in FIG. 1 may be used to gather images, but additional processing steps (e.g., analyzing those images, determining a field of observation based on those images) may be performed using a remote system, such as using a cloud server accessed via a wide area network. Other variations are also possible, and could be implemented by those of ordinary skill in the art without undue experimentation based on this disclosure. Accordingly, the above variations, like the description which preceded them, should be understood as being illustrative only, and should not be treated as limiting.

[0055] As a further illustration of potential implementations and applications of the disclosed technology, the following examples are provided of non-exhaustive ways in which the teachings herein may be combined or applied. It should be understood that the following examples are not intended to restrict the coverage of any claims that may be presented at any time in this application or in subsequent filings of this application. No disclaimer is intended. The following examples are being provided for nothing more than merely illustrative purposes. It is contemplated that the various teachings herein may be arranged and applied in numerous other ways. It is also contemplated that some variations may omit certain features referred to in the below examples. Therefore, none of the aspects or features referred to below should bedeemed critical unless otherwise explicitly indicated as such at a later date by the inventors or by a successor in interest to the inventors. If any claims are presented in this application or in subsequent filings related to this application that include additional features beyond those referred to below, those additional features shall not be presumed to have been added for any reason relating to patentability.

[0056] Example 1

[0057] A method of determining a field of observation for a biological analysis flowcell, comprising: obtaining a plurality of images of particles from a field of view of a flowcell, the field of view representing a first imaging area of a flowcell; analyzing a plurality of images of particles from the field of view; determining a focal parameter associated with each of the plurality of images; and utilizing the focal parameter to determine the field of observation, wherein the field of observation is a second imaging area smaller than the first imaging area.

[0058] Example 2

[0059] The method of example 1, wherein the focal parameter is a numerical value representing a focal quality.

[0060] Example 3

[0061] The method of any of examples 1-2, wherein utilizing the focal parameter to determine the field of observation comprises performing a comparison with a focal parameter threshold.

[0062] Example 4

[0063] The method of any of examples 1-3, wherein determining the focal parameter associated with each of the plurality of images comprises: organizing the plurality of images of particles into a plurality of bin regions, wherein each image from the plurality of images of particles corresponds to a bin region from the plurality of bin regions, and wherein each bin region from the plurality of bin regions is a portion of the field of view; for each bin region from the plurality of bin regions, calculating an aggregate parameter value for that bin region; and for each image from the plurality of images of particles, determining the focal parameterassociated with that image as having a value equal to the aggregate parameter value for the bin region corresponding to that image.

[0064] Example 5

[0065] The method of example 4, wherein, for each bin region from the plurality of bin regions, the aggregate parameter value for that bin region is an average parameter value.

[0066] Example 6

[0067] The method of any of examples 4-5, wherein utilizing the focal parameter to determine the field of observation comprises, for each bin region from the plurality of bin regions, determining if the aggregate parameter value for that bin region is between a first threshold and a second threshold, and adding that bin region to the field of observation when the aggregate parameter value for that bin region is between the first threshold and the second threshold.

[0068] Example 7

[0069] The method of any of examples 1-6, wherein obtaining the plurality of images of particles from the field of view comprises one or more acts comprising: capturing a particle image, wherein the particle image depicts two or more particles; and for each particle from the set of two or more particles, obtaining an image of that particle based on segmenting that particle out of the particle image.

[0070] Example 8

[0071] The method of any of examples 1-7, wherein the method comprises: determining if the field of observation is unsuitable for generating biological analysis results; and based on determining that the field of observation is unsuitable for generating biological analysis results, generating a system flag.

[0072] Example 9

[0073] The method of any of examples 1-8, wherein the method comprises: for each image from the plurality of images of particles, determine if that image is within the field of observation; and for each image from the plurality of images of particles which is not determined to be within the field of observation, excluding that image from generation of a biological analysis result based on it not being determined to be within the field of observation; and generating the biological analysis result based on images from the plurality of image determined to be within the field of observation.

[0074] Example 10

[0075] The method of any of examples 1-9, wherein the method comprises obtaining the plurality of images of particles from the field of view by performing one or more acts comprising: establishing a flow of alignment fluid from an alignment fluid reservoir into the flowcell; creating a sample stream comprising sample fluid from a patient sample and a sheath of alignment fluid surrounding the sample fluid based on injecting the sample fluid from a channel into the flow of alignment fluid; and using a camera configured to capture images of the sample stream as it flows through the flowcell, capturing images comprising the particles depicted in the plurality of particle images, wherein the first imaging area is an imaging area captured by the camera of an imaging region of the flowcell.

[0076] Example 11

[0077] The method of example 1, wherein analyzing the plurality of images comprises using a machine learning model.

[0078] Example 12

[0079] The method of example 11, wherein the machine learning model comprises a deep learning model trained to identify cell regions within the plurality of images and isolate the identified cell regions as foreground regions by using a pixel-based approach.

[0080] Example 13

[0081] A system for determining a field of observation for a biological analysis flowcell, comprising: one or more processors; and one or more non-transitory computer readable mediums storinginstructions operable to, when executed by the one or more processors, perform the method of any preceding examples 1-12.

[0082] Example 14

[0083] A non-transitory computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of any one of the methods of examples 1 to 12.

[0084] Example 15

[0085] A computer program product comprising: instructions which, when the program is executed by a computer, cause the computer to carry out the steps of any one of the methods of examples 1 to 12.

[0086] Example 16

[0087] A system for determining a field of observation for a biological analysis flowcell, comprising: one or more processors; and one or more non-transitory computer readable mediums storing instructions operable to, when executed by the one or more processors, perform a method comprising: obtaining a plurality of images of particles from a field of view of a flowcell, the field of view representing a first imaging area of a flowcell; analyzing a plurality of images of particles from the field of view; determining a focal parameter associated with each of the plurality of images; and utilizing the focal parameter to determine the field of observation, wherein the field of observation is a second imaging area smaller than the first imaging area.

[0088] Example 17

[0089] The system of example 16, wherein the focal parameter is a numerical value representing a focal quality.

[0090] Example 18

[0091] The system of any of examples 16-17, wherein utilizing the focal parameter to determine the field of observation comprises performing a comparison with a focal parameter threshold.

[0092] Example 19

[0093] The system of any of examples 16-17, wherein determining the focal parameter associated with each of the plurality of images comprises: organizing the plurality of images of particles into a plurality of bin regions, wherein each image from the plurality of images of particles corresponds to a bin region from the plurality of bin regions, and wherein each bin region from the plurality of bin regions is a portion of the field of view; for each bin region from the plurality of bin regions, calculating an aggregate parameter value for that bin region; and for each image from the plurality of images of particles, determining the focal parameter associated with that image as having a value equal to the aggregate parameter value for the bin region corresponding to that image.

[0094] Example 20

[0095] The system of example 19, wherein, for each bin region from the plurality of bin regions, the aggregate parameter value for that bin region is an average parameter value.

[0096] Example 21

[0097] The system of any of examples 19-20, wherein utilizing the focal parameter to determine the field of observation comprises, for each bin region from the plurality of bin regions, determining if the aggregate parameter value for that bin region is between a first threshold and a second threshold, and adding that bin region to the field of observation when the aggregate parameter value for that bin region is between the first threshold and the second threshold.

[0098] Example 22

[0099] The system of any of examples 16-21, wherein obtaining the plurality of images of particles from the field of view comprises one or more acts comprising: capturing a particle image, wherein the particle image depicts two or more particles; and for each particle from the set of two or more particles, obtaining an image of that particle based on segmenting that particle out of the particle image.

[0100] Example 23

[0101] The system of any of examples 16-22, wherein the method comprises: determining if the field of observation is unsuitable for generating biological analysis results; and based on determining that the file do observation is unsuitable for generating biological analysis results, generating a system flag.

[0102] Example 24

[0103] The system of any of examples 16-23, wherein the method comprises: for each image from the plurality of images of particles, determine if that image is within the field of observation; and for each image from the plurality of images of particles which is not determined to be within the field of observation, excluding that image from generation of a biological analysis result based on it not being determined to be within the field of observation; and generating the biological analysis result based on images from the plurality of image determined to be within the field of observation.

[0104] Example 25

[0105] The system of any of examples 16-23, wherein the method comprises obtaining the plurality of images of particles from the field of view by performing one or more acts comprising: establishing a flow of alignment fluid from an alignment fluid reservoir into the flowcell; creating a sample stream comprising sample fluid from a patient sample and a sheath of alignment fluid surrounding the sample fluid based on injecting the sample fluid from a channel into the flow of alignment fluid; and using a camera configured to capture images of the sample stream as it flows through the flowcell, capturing images comprising the particles depicted in the plurality of particle images, wherein the first imaging area is an imaging area captured by the camera of an imaging region of the flowcell.

[0106] Example 26

[0107] The system of example 16, wherein analyzing the plurality of images comprises using a machine learning model.

[0108] Example 27

[0109] The system of example 26, wherein the machine learning model comprises a deep learning model trained to identify cell regions within the plurality of images and isolate the identified cell regions as foreground regions by using a pixel-based approach.

[0110] Example 28

[0111] A method of determining a field of observation for a biological analysis flowcell comprising performing the set of acts the instructions stored on the non-transitory computer readable medium of the system of any of examples 16-27 are to perform when executed.

[0112] Example 29

[0113] A non-transitory computer readable medium storage medium comprising instructions to perform the set of acts which the instructions stored on the non-transitory computer readable medium of the system of any of examples 16-27 are to perform when executed.

[0114] Example 30

[0115] A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the set of acts which the instructions stored on the non-transitory computer readable medium of the system of any of examples 16- 27 are to perform when executed.

[0116] Each of the calculations or operations described herein may be performed using a computer or other processor having hardware, software, and / or firmware. The various method steps may be performed by modules, and the modules may comprise any of a wide variety of digital and / or analog data processing hardware and / or software arranged to perform the method steps described herein. The modules optionally comprising data processing hardware adapted to perform one or more of these steps by having appropriate machine programming code associated therewith, the modules for two or more steps (or portions of two or more steps) being integrated into a single processor board or separated into different processor boards in any of a wide variety of integrated and / or distributed processing architectures. These methods and systems will often employ a tangible media embodying machine-readable code withinstructions for performing the method steps described above. Suitable tangible media may comprise a memory (including a volatile memory and / or a non-volatile memory), a storage media (such as a magnetic recording on a floppy disk, a hard disk, a tape, or the like; on an optical memory such as a CD, a CD-R / W, a CD-ROM, a DVD, or the like; or any other digital or analog storage media), or the like.

[0117] All patents, patent publications, patent applications, journal articles, books, technical references, and the like discussed in the instant disclosure are incorporated herein by reference in their entirety for all purposes.

[0118] Different arrangements of the components depicted in the drawings or described above, as well as components and steps not shown or described are possible. Similarly, some features and sub-combinations are useful and may be employed without reference to other features and sub-combinations. Embodiments of the invention have been described for illustrative and not restrictive purposes, and alternative embodiments will become apparent to readers of this patent. In certain cases, method steps or operations may be performed or executed in differing order, or operations may be added, deleted or modified. It can be appreciated that, in certain aspects of the invention, a single component may be replaced by multiple components, and multiple components may be replaced by a single component, to provide an element or structure or to perform a given function or functions. Except where such substitution would not be operative to practice certain embodiments of the invention, such substitution is considered within the scope of the invention. Accordingly, the claims should not be treated as limited to the examples, drawings, embodiments and illustrations provided above, but instead should be understood as having the scope provided when their terms are given their broadest reasonable interpretation as provided by a general purpose dictionary, except that when a term or phrase is indicated as having a particular meaning under the heading Explicit Definitions, it should be understood as having that meaning when used in the claims.

[0119] Explicit Definitions

[0120] It should be understood that, in the above examples and the claims, a statement that something is “based on” something else should be understood to mean that it is determined at least in part by the thing that it is indicated as being based on. To indicate that something mustbe completely determined based on something else, it is described as being “based EXCLUSIVELY on” whatever it must be completely determined by.

[0121] It should be understood that, in the above examples and claims, the term “set” should be understood as one or more things which are grouped together.

Claims

What is claimed is:

1. A method of determining a field of observation for a biological analysis flowcell, comprising: obtaining a plurality of images of particles from a field of view of a flowcell, the field of view representing a first imaging area of a flowcell; analyzing a plurality of images of particles from the field of view; determining a focal parameter associated with each of the plurality of images; and utilizing the focal parameter to determine the field of observation, wherein the field of observation is a second imaging area smaller than the first imaging area.

2. The method of claim 1, wherein the focal parameter is a numerical value representing a focal quality.

3. The method of any of claims 1-2, wherein utilizing the focal parameter to determine the field of observation comprises performing a comparison with a focal parameter threshold.

4. The method of any of claims 1-3, wherein determining the focal parameter associated with each of the plurality of images comprises: organizing the plurality of images of particles into a plurality of bin regions, wherein each image from the plurality of images of particles corresponds to a bin region from the plurality of bin regions, and wherein each bin region from the plurality of bin regions is a portion of the field of view; for each bin region from the plurality of bin regions, calculating an aggregate parameter value for that bin region; and for each image from the plurality of images of particles, determining the focal parameter associated with that image as having a value equal to the aggregate parameter value for the bin region corresponding to that image.

5. The method of claim 4, wherein, for each bin region from the plurality of bin regions, the aggregate parameter value for that bin region is an average parameter value.

6. The method of any of claims 4-5, wherein utilizing the focal parameter to determine the field of observation comprises, for each bin region from the plurality of bin regions, determining if the aggregate parameter value for that bin region is between a first threshold and a second threshold, and adding that bin region to the field of observation when the aggregate parameter value for that bin region is between the first threshold and the second threshold.

7. The method of any of claims 1-6, wherein obtaining the plurality of images of particles from the field of view comprises one or more acts comprising: capturing a particle image, wherein the particle image depicts two or more particles; and for each particle from the set of two or more particles, obtaining an image of that particle based on segmenting that particle out of the particle image.

8. The method of any of claims 1-7, wherein the method comprises: determining if the field of observation is unsuitable for generating biological analysis results; and based on determining that the field of observation is unsuitable for generating biological analysis results, generating a system flag.

9. The method of any of claims 1-8, wherein the method comprises: for each image from the plurality of images of particles, determine if that image is within the field of observation; and for each image from the plurality of images of particles which is not determined to be within the field of observation, excluding that image from generation of a biological analysis result based on it not being determined to be within the field of observation; and generating the biological analysis result based on images from the plurality of image determined to be within the field of observation.

10. The method of any of claims 1-9, wherein the method comprises obtaining the plurality of images of particles from the field of view by performing one or more acts comprising: establishing a flow of alignment fluid from an alignment fluid reservoir into the flowcell;creating a sample stream comprising sample fluid from a patient sample and a sheath of alignment fluid surrounding the sample fluid based on injecting the sample fluid from a channel into the flow of alignment fluid; and using a camera configured to capture images of the sample stream as it flows through the flowcell, capturing images comprising the particles depicted in the plurality of particle images, wherein the first imaging area is an imaging area captured by the camera of an imaging region of the flowcell.

11. The method of claim 1, wherein analyzing the plurality of images comprises using a machine learning model.

12. The method of claim 11, wherein the machine learning model comprises a deep learning model trained to identify cell regions within the plurality of images and isolate the identified cell regions as foreground regions by using a pixel-based approach.

13. A system for determining a field of observation for a biological analysis flowcell, comprising: one or more processors; and one or more non-transitory computer readable mediums storing instructions operable to, when executed by the one or more processors, perform the method of any preceding claims 1-12.

14. A non-transitory computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of any one of the methods of claims 1 to 12.

15. A computer program product comprising: instructions which, when the program is executed by a computer, cause the computer to carry out the steps of any one of the methods of claims 1 to 12.

16. A system for determining a field of observation for a biological analysis flowcell, comprising:one or more processors; and one or more non-transitory computer readable mediums storing instructions operable to, when executed by the one or more processors, perform a method comprising: obtaining a plurality of images of particles from a field of view of a flowcell, the field of view representing a first imaging area of a flowcell; analyzing a plurality of images of particles from the field of view; determining a focal parameter associated with each of the plurality of images; and utilizing the focal parameter to determine the field of observation, wherein the field of observation is a second imaging area smaller than the first imaging area.

17. The system of claim 16, wherein the focal parameter is a numerical value representing a focal quality.

18. The system of any of claims 16-17, wherein utilizing the focal parameter to determine the field of observation comprises performing a comparison with a focal parameter threshold.

19. The system of any of claims 16-17, wherein determining the focal parameter associated with each of the plurality of images comprises: organizing the plurality of images of particles into a plurality of bin regions, wherein each image from the plurality of images of particles corresponds to a bin region from the plurality of bin regions, and wherein each bin region from the plurality of bin regions is a portion of the field of view; for each bin region from the plurality of bin regions, calculating an aggregate parameter value for that bin region; and for each image from the plurality of images of particles, determining the focal parameter associated with that image as having a value equal to the aggregate parameter value for the bin region corresponding to that image.

20. The system of claim 19, wherein, for each bin region from the plurality of bin regions, the aggregate parameter value for that bin region is an average parameter value.21 . The system of any of claims 19-20, wherein utilizing the focal parameter to determine the field of observation comprises, for each bin region from the plurality of bin regions, determining if the aggregate parameter value for that bin region is between a first threshold and a second threshold, and adding that bin region to the field of observation when the aggregate parameter value for that bin region is between the first threshold and the second threshold.

22. The system of any of claims 16-21, wherein obtaining the plurality of images of particles from the field of view comprises one or more acts comprising: capturing a particle image, wherein the particle image depicts two or more particles; and for each particle from the set of two or more particles, obtaining an image of that particle based on segmenting that particle out of the particle image.

23. The system of any of claims 16-22, wherein the method comprises: determining if the field of observation is unsuitable for generating biological analysis results; and based on determining that the field of observation is unsuitable for generating biological analysis results, generating a system flag.

24. The system of any of claims 16-23, wherein the method comprises: for each image from the plurality of images of particles, determine if that image is within the field of observation; and for each image from the plurality of images of particles which is not determined to be within the field of observation, excluding that image from generation of a biological analysis result based on it not being determined to be within the field of observation; and generating the biological analysis result based on images from the plurality of image determined to be within the field of observation.

25. The system of any of claims 16-23, wherein the method comprises obtaining the plurality of images of particles from the field of view by performing one or more acts comprising: establishing a flow of alignment fluid from an alignment fluid reservoir into the flowcell;creating a sample stream comprising sample fluid from a patient sample and a sheath of alignment fluid surrounding the sample fluid based on injecting the sample fluid from a channel into the flow of alignment fluid; and using a camera configured to capture images of the sample stream as it flows through the flowcell, capturing images comprising the particles depicted in the plurality of particle images, wherein the first imaging area is an imaging area captured by the camera of an imaging region of the flowcell.

26. The system of claim 16, wherein analyzing the plurality of images comprises using a machine learning model.

27. The system of claim 26, wherein the machine learning model comprises a deep learning model trained to identify cell regions within the plurality of images and isolate the identified cell regions as foreground regions by using a pixel-based approach.

28. A method of determining a field of observation for a biological analysis flowcell comprising performing the set of acts the instructions stored on the non-transitory computer readable medium of the system of any of claims 16-27 are to perform when executed.

29. A non-transitory computer readable medium storage medium comprising instructions to perform the set of acts which the instructions stored on the non-transitory computer readable medium of the system of any of claims 16-27 are to perform when executed.

30. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the set of acts which the instructions stored on the non-transitory computer readable medium of the system of any of claims 16-27 are to perform when executed.

Images