Method and system for developing imaging configurations to optimize performance of a microscopy system

Abstract

A method and system for operating a microscopy system is disclosed. A first image of a sample acquired using a first imaging configuration is received. A second image is developed from the first image, the second image associated with the second imaging configuration. A series of image processing steps is applied to the first image to develop a first classification of a first object represented in the first image, and to the second image to develop a second classification of a second object represented in the second image. A score associated with the second imaging configuration is developed that represents the difference between the first and second classifications. The image acquisition time or component requirements of operating the microscopy system are less when operated using the second imaging configuration than when operated using the first imaging configuration.

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims the benefit of U.S. Provisional Patent Application No. 63 / 081,019 (Cohen et al.), entitled "Method and System of Developing an Imaging Configuration to Optimize Performance of a Microscopy System," filed September 21, 2020, the entire contents of which are incorporated herein by reference.

[0002] FIELD OF THE DISCLOSURE The present subject matter relates to microscopy systems, and more particularly to methods and systems for developing imaging configurations to optimize the operation of microscopy systems. [Background technology]

[0003] Microscopy systems, e.g., high-content imaging systems, can be used to conduct experiments in which microscopy images of biological samples are obtained and analyzed. Such images can be processed using image analysis systems to identify pixels of the image associated with objects of interest (cells, organelles, etc.) represented in the image, classify or characterize different types of such objects of interest represented in the image, obtain metrics related to the objects of interest or portions thereof, etc. For each biological sample, such metrics can include, for example, the number of objects of interest in the sample, the number of each type of object of interest represented in the biological sample, the size of the objects of interest (area, perimeter, volume), statistics of the size of the objects of interest (mean, mode, median, standard deviation, etc.), characteristics of the objects of interest (e.g., whether the objects are alive or dead, whether the objects contain a particular protein, etc.), etc.

[0004] To conduct an experiment, a researcher may develop a trial assay protocol, the trial assay protocol comprising a trial imaging configuration that specifies values ​​associated with imaging parameters (e.g., objective lens, magnification, exposure time, focus accuracy, etc.) for operating a microscopy system to acquire one or more images of a biological sample, and an image analysis step for analyzing such images. Such values ​​of the imaging parameters may specify a magnification level (e.g., a high magnification level), a number of images of the biological sample to acquire, a number of focal planes (i.e., different z-planes) for acquiring images of the biological sample, an exposure time (e.g., a high exposure time to use the full dynamic range of the microscopy system), the use of confocal imaging, the use of specialized optics (e.g., water or oil immersion optics), etc. Furthermore, if the trial population of biological samples is placed in wells of a microplate, the imaging parameters may specify acquiring one or more images of different portions of each well at high resolution and / or different focus positions.

[0005] After researchers develop a pilot assay protocol, a suitable production assay protocol is developed to acquire and analyze production images of a production population of biological samples to confirm the findings of experiments conducted using the pilot assay. As will be understood by those skilled in the art, a production population of biological samples will comprise significantly more samples than a pilot population of biological samples. In some cases, the pilot imaging configuration used to acquire high-quality images of a pilot population of biological samples may not be practical for acquiring images of the larger production population. For example, acquiring multiple images of each biological sample in the production population at high resolution using long exposure times, multiple images per location, etc. may require excessive time. Furthermore, acquisition of images of the larger population may be distributed among multiple microscopy systems, and it may not be feasible to equip all such microscopy systems with expensive, high-quality components, such as confocal imagers and specialized optics, as dictated by the pilot imaging configuration. Summary of the Invention [Means for solving the problem]

[0006] According to one aspect, a method of operating a microscopy system includes receiving a first image of a sample acquired using a first imaging configuration and developing a second image from the first image, the second image associated with the second imaging configuration. The method further includes applying a series of image processing steps to the first image to develop a first classification of a first object represented in the first image, applying a series of image processing steps to the second image to develop a second classification of a second object represented in the second image, and developing a score associated with the second imaging configuration that represents the difference between the first classification and the second classification. Image acquisition time or component requirements for operating the microscopy system are less when operated using the second imaging configuration than when operated using the first imaging configuration.

[0007] According to another aspect, a system for operating a microscopy system includes an imaging configuration optimizer, a low-quality image generator, an image analyzer, and an imaging configuration scorer, all running on one or more processors. The imaging configuration optimizer receives a first image of a sample acquired using a first imaging configuration. The low-quality image generator develops a second image from the first image, the second image associated with the second imaging configuration. The image analyzer applies a series of image processing steps to the first and second images to develop a first classification, the first classification associated with a first object represented in the first image. The imaging configuration scorer applies a series of image processing steps to the second image to develop a second classification associated with a second object represented in the second image, and develops a score associated with the second imaging configuration representing a difference between the first classification and the second classification. The image acquisition time or component requirements to operate the microscopy system are less when operated using the second imaging configuration than when operated using the first imaging configuration.

[0008] Other aspects and advantages will become apparent from a consideration of the following detailed description and accompanying drawings, in which like numerals designate like structure throughout. The present invention provides, for example, the following items. (Item 1) 1. A method of operating a microscopy system, the method comprising: receiving a first image of the sample obtained using a first imaging configuration; developing a second image from the first image, the second image being associated with a second imaging configuration; applying a series of image processing steps to the first image to develop a first classification of a first object represented in the first image; applying the sequence of image processing steps to the second image to develop a second classification of a second object represented in the second image; developing a score associated with the second imaging configuration; Including, the score represents the difference between the first classification and the second classification; A method wherein image acquisition time or component requirements to operate the microscopy system are less when operated using the second imaging configuration than when operated using the first imaging configuration. (Item 2) Item 10. The method of claim 1, wherein the first classification of the first object is associated with an identification of one or more objects represented in the first image, the identification of the one or more objects having a particular characteristic or metric associated with the one or more objects represented in the first image. (Item 3) The score comprises a first score, and the method comprises: developing a third image from the first image, the third image being associated with a third imaging configuration; applying said sequence of image processing steps to said third image to develop a third classification; developing a second score representing the difference between the first classification and the third classification; automatically selecting a recommended production imaging configuration; further comprising Item 10. The method of claim 1, wherein the recommended production imaging configuration is the second imaging configuration if the first score is better than the second score, and the recommended production imaging configuration is the third imaging configuration if the second score is better than the first score. (Item 4) selecting a set of training parameters according to an image processing step of said sequence of image processing steps; configuring an untrained machine learning system with the selected set of training parameters to develop a trained machine learning system; operating the trained machine learning system to develop the first classification; Item 1, the method of claim 1 further comprising: (Item 5) Item 10. The method of item 1, further comprising developing the second imaging configuration from the first imaging configuration. (Item 6) Item 6. The method of item 5, wherein the first imaging configuration defines a first value associated with an imaging parameter and the second imaging configuration defines a second value associated with the imaging parameter, the first value and the second value being different. (Item 7) selecting training parameters of an untrained machine learning system according to the difference between the first imaging configuration and the second imaging configuration; training the untrained machine learning system using the selected training parameters to develop a trained machine learning system; operating the trained machine learning system using the first image as an input to generate the second image; Item 7. The method of item 6, further comprising: (Item 8) Item 10. The method of claim 1, wherein receiving the first image includes obtaining the first image using a first microscopy system, and the method includes the further step of obtaining a third image using a second microscopy system according to the second imaging configuration. (Item 9) Item 10. The method of item 1, wherein the second image simulates an image of the sample that would be obtained if the microscopy system were operated using the second imaging configuration. (Item 10) Item 10. The method of item 1, wherein the second imaging configuration is one of a plurality of candidate production imaging configurations, a score is developed for each of the plurality of candidate production imaging configurations, and the method further comprises selecting a recommended production imaging configuration from those candidate production imaging configurations having a score above a predetermined amount. (Item 11) the second imaging configuration is one of a plurality of candidate production imaging configurations, and a classification and score are developed for each of the plurality of candidate production imaging configurations, the method comprising: selecting a recommended production imaging configuration from the plurality of candidate production imaging configurations; instructing a computer to display information regarding each candidate production imaging configuration of the plurality of candidate production imaging configurations and an indicator identifying the candidate production imaging configuration selected as the recommended production imaging configuration; further comprising Item 10. The method of item 1, wherein the information displayed for each candidate production imaging configuration includes one or more of the score, time savings estimate, image, and object classification associated with the candidate production imaging configuration. (Item 12) Item 12. The method of item 11, further comprising receiving from the computer a selection of one of the candidate production imaging configurations in which to configure the imaging system. (Item 13) 1. A system for operating a microscopy system, the system comprising: an imaging configuration optimizer operating on one or more processors that receives a first image of the sample acquired using the first imaging configuration; a low-quality image generator operating on one of the one or more processors that develops a second image from the first image, the second image being associated with a second imaging configuration; and an image analyzer operating on the one or more processors that applies a series of image processing steps to the first image and the second image to develop a first classification, the first classification being associated with a first object represented in the first image; and an imaging configuration scorer operating on said one or more processors; Including, the imaging configuration scorer applies the sequence of image processing steps to the second image to develop a second classification associated with the second object represented in a second object and to develop a score associated with the second imaging configuration, the score representing a difference between the first classification and the second classification; A system wherein the image acquisition time or component requirements to operate the microscopy system are less when operated using the second imaging configuration than when operated using the first imaging configuration. (Item 14) Item 14. The system of item 13, wherein the first classification of the first object is associated with an identification of the one or more objects represented in the first image, an identification of a characteristic of one or more objects, or a metric associated with the one or more objects represented in the first image. (Item 15) Item 14. The system of item 13, wherein the score comprises a first score, the low-quality image generator develops a third image from the first image, the third image being associated with a third imaging configuration, the imaging configuration scorer applies the series of image processing steps to the third image to develop a third classification, and develops a second score representing a difference between the first classification and the third classification, and the system further includes a recommendation generator operating on the one or more processors that automatically selects a recommended production imaging configuration, the recommended production imaging configuration being the second imaging configuration if the first score is better than the second score, and the recommended production imaging configuration being the third imaging configuration if the second score is better than the first score. (Item 16) Item 14. The system of item 13, further comprising an untrained machine learning system, wherein the image analyzer selects training parameters associated with a step in the sequence of image processing steps, uses the training parameters to configure the untrained machine learning system, develops a trained machine learning system, operates the trained machine learning system, and develops the first classification. (Item 17) Item 14. The system of item 13, further comprising a candidate configuration generator operating on the one or more processors that automatically develops the second imaging configuration based on the first imaging configuration. (Item 18) Item 18. The system of item 17, wherein the first imaging configuration defines a first value associated with an imaging parameter, and the second imaging configuration developed by the candidate configuration generator automatically defines a second value associated with the imaging parameter, the first value and the second value being different. (Item 19) Item 19. The system of item 18, further comprising an untrained machine learning system, wherein the low-quality image generator selects a set of training parameters according to a difference between the first imaging configuration and the second imaging configuration, trains the untrained machine learning system using the selected training parameters, develops a trained machine learning system, and operates the trained machine learning system using the first image as an input to generate the second image. (Item 20) The system of item 13, wherein the microscopy system comprises a first microscopy system operated according to the first imaging configuration to obtain the first image, and a second microscopy system operated according to the second imaging configuration to obtain a third image. (Item 21) Item 14. The system of item 13, wherein the second image simulates an image of the sample that would be obtained if the microscopy system were operated using the second imaging configuration. (Item 22) Item 14. The system of item 13, wherein the second imaging configuration is one of a plurality of candidate production imaging configurations, and the system further includes a candidate configuration generator and a recommendation generator, wherein the candidate configuration generator develops the plurality of candidate imaging configurations, the imaging configuration scorer develops a score for each of the candidate production imaging configurations, and the recommendation generator selects a recommended production imaging configuration from those candidate production imaging configurations having a score above a predetermined amount. (Item 23) the second imaging configuration is one of a plurality of candidate production imaging configurations, a classification and a score are developed for each of the plurality of candidate production imaging configurations, and the system: a recommendation generator that selects a recommended production imaging configuration from the plurality of candidate production imaging configurations; a user interface generator that instructs a computer to display information regarding each candidate production imaging configuration of the plurality of candidate production imaging configurations and an indicator that identifies the candidate production imaging configuration selected as the recommended production imaging configuration; further comprising Item 14. The system of item 13, wherein the information displayed for each candidate production imaging configuration includes one or more of the score, time savings estimate, image, and object classification associated with the candidate production imaging configuration. (Item 24) 24. The system of claim 23, wherein the user interface generator receives from the computer a selection of one of the candidate production imaging configurations in which to configure the imaging system. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a schematic diagram of a microscopy system.

[0010] [Figure 2] FIG. 2 is a block diagram of an image analysis system that can be used to develop an imaging configuration for operating the microscopy system of FIG.

[0011] [Figure 3] FIG. 3 is a flow chart of the steps performed by the image analysis system of FIG. 2 to develop an imaging configuration.

[0012] [Figure 4] FIG. 4 is a block diagram of an imaging configuration optimizer of the image analysis system of FIG.

[0013] [Figure 5] FIG. 5 is a flowchart of the steps performed by the imaging configuration optimizer of FIG. 4 to develop an imaging configuration.

[0014] [Figure 6] FIG. 6 is a graphical user interface generated by the imaging analysis system of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0015] According to embodiments disclosed herein, an image analysis system facilitates the development of a trial assay protocol, the trial assay protocol comprising a trial imaging configuration and a sequence of image analysis steps used to analyze images from a microscopy system operated according to the trial imaging configuration.

[0016] Additionally, the image analysis system receives high-quality images of the biological sample obtained using the trial imaging configuration. An imaging configuration optimizer of the image analysis system develops multiple additional imaging configurations (i.e., candidate production imaging configurations) from the trial imaging configurations and the high-quality images. Each candidate production imaging configuration is such that operating the microscopy system using the candidate production imaging configuration requires one or both of a shorter time to obtain an image and less specialized equipment than operating using the trial imaging configuration. Additionally, for each candidate production imaging configuration, the imaging configuration optimizer develops a lower-quality image from the high-quality image, where the lower-quality image simulates an image that would be obtained if the microscopy system were operated using the candidate production imaging configuration. Furthermore, each candidate production imaging configuration is evaluated by the imaging configuration optimizer to develop a score, where the score represents how well an object or object property can be identified in an image obtained using the candidate production imaging configuration compared to that obtained using the trial imaging configuration. In particular, the imaging configuration optimizer analyzes low-quality images associated with the candidate production imaging configurations, identifies a first characteristic of an object in the low-quality image, and compares the first characteristic of the object identified in the low-quality image to a second characteristic of the object identified in the high-quality image. A score associated with the candidate production imaging configuration indicates how closely the first characteristic matches the second characteristic.

[0017] For example, the score may indicate the percentage of features of interest identified in the high-quality images that were also correctly identified in the low-quality images associated with the candidate production imaging configuration. Such features of interest may include cells, where cells have particular properties, organelles, proteins, etc. In some embodiments, the score may indicate how accurately cells classified in the high-quality images (e.g., live cells vs. dead cells, cells to which a treatment has been applied vs. control cells, cells of a first type vs. cells of a second type, etc.) were classified in the low-quality images. In some embodiments, the imaging configuration optimizer analyzes the scores associated with the candidate production imaging configurations and an estimate of the acquisition time saved using the candidate production imaging configurations to select a recommended production imaging configuration for use in the production assay protocol.

[0018] To develop candidate production imaging configurations, the image analyzer applies a series of image analysis steps to the high-quality images to develop classifications of objects represented in the high-quality images. Such classifications may include identification of specific types of objects (e.g., cells, organelles, proteins, etc.) and / or characteristics of such objects (e.g., size, quantity, type, mortality, etc.).

[0019] The imaging configuration optimizer then develops, from the high quality image, a low quality image according to each candidate production imaging configuration, the low quality image simulating the image that would be obtained if the microscopy system were configured using the candidate production imaging configuration associated with such low quality image.

[0020] The imaging configuration optimizer automatically analyzes each low-quality image to identify and classify objects associated with the test biological sample represented in such image. For each low-quality image, the classification of the object identified in the low-quality image is compared to the classification of the object identified in the high-quality image to develop a score representing the accuracy with which the object can be identified and classified in the low-quality image. In some embodiments, the imaging configuration optimizer selects the candidate production imaging configuration associated with the best score as the production imaging configuration for use in the production assay protocol. In other embodiments, the imaging configuration optimizer presents to the researcher one or more lists of the candidate production imaging configurations and the score associated with each such candidate production imaging configuration, and in response, the imaging configuration optimizer receives a selection of one of the presented candidate production imaging configurations for use in the production assay protocol.

[0021] 1 , as will be apparent to one skilled in the art, a microscopy system 100, such as a high-content microscopy system, may include an XY stage 102, one or more objective lenses 104, one or more illumination sources 106, an image capture device 110, and a controller 112. The microscopy system 100 may include one or more mirrors (not shown) that direct light from the illumination source 106 to a sample tray or microplate 116 positioned on the XY stage 102. The light is then transmitted through such microplate 116, through the objective lens 104, and to the image capture device 110. In some embodiments, the microplate 116 includes multiple wells 118, and a biological sample (e.g., biological cells) to be imaged by the microscopy system 100 may be placed in each such well 118.

[0022] During operation, the microplate 116 can be placed on the XY stage 102, either manually or robotically. Additionally, the controller 112 can configure the microscopy system 100 according to an imaging configuration (e.g., the trial or production imaging configuration described above) to use a combination of a particular objective lens 104, illumination generated by the illumination source 106, etc. For example, the controller 112 can operate a positioning device (not shown) to place a selected objective lens 104 in the optical path between the microplate 116 and the image capture device 110. The controller 112 can also direct the illumination source 106 to illuminate the microplate 116 with a particular wavelength of light. In some cases, the sample in the microplate 116 may contain fluorescent molecules, either naturally occurring molecules or molecules created or present in the sample due to processing. The wavelength of light generated by the illumination device can be the excitation wavelength associated with such fluorescent molecules, and the image capture device will capture only the emission spectrum of such fluorescent materials. One or more wavelengths may be used to sequentially or simultaneously illuminate the same sample and generate an image.

[0023] Additionally, in some embodiments, the controller 112 may operate the focus mechanism 120 so that the image capture device 110 may obtain focused images of different focal planes of a biological sample disposed within the microplate 116.

[0024] The controller 112 may then move the XY stage 102 so that the well 118, or a portion thereof, is within the field of view of the image capture device 110, and actuate the image capture device 110 to obtain an image of the well 118, or a portion thereof. The controller 112 may repeatedly move the XY stage 102 and the image capture device 110 in this manner until images of all of the wells 118 of the microplate 116 of interest have been captured. Furthermore, the controller 112 may capture several images of the same well 118 or the same portion of the same well, with each such image captured using a different objective lens 104, illumination wavelength, and / or focal position of the image biological sample.

[0025] The microscopy system illustrated in FIG. 1 is exemplary and other types of imaging or microscopy systems apparent to those skilled in the art that can be used to capture high quality images of experimental or production biological samples.

[0026] 1 and 2, a researcher may use an image analysis system 150 in communication with microscopy system 100 to develop a trial assay protocol to analyze biological samples placed on a tray of microscopy system 100. As discussed above, the trial assay protocol comprises a trial imaging configuration for obtaining one or more high-quality images of the biological sample and a series of image processing steps to be performed to analyze the obtained images.

[0027] In particular, the image analysis system includes a user interface 152 in communication with a user computer 154. As will be apparent to one skilled in the art, the user interface 152 instructs the user computer 154 to display a graphical user interface (GUI) that allows a researcher to interact with the image analysis system 150. The image analysis system 150 also includes a microscopy system interface 156 in communication with the microscopy system 100, an image data store 158, an image analyzer 160, a machine learning system 162, a training parameter data store 164 containing a set of training parameters that can be used to configure the machine learning system 162 from an untrained state to a trained state, and an imaging configuration optimizer 166. It will be apparent to one skilled in the art that a trained machine learning system 162 can be returned to an untrained state by reinitializing such machine learning system.

[0028] 3 shows a flowchart 200 of steps performed by image analysis system 150 to develop trial and production assay protocols. Referring to FIGS. 1-3, in step 202, user interface 152 receives from user computer 154 a specification of a trial imaging configuration and instructions for capturing one or more high-quality images of a biological sample disposed in the microscopy system. In some embodiments, the trial imaging configuration may be selected from a plurality of predetermined imaging configurations according to, for example, the type of cell within the biological sample, the object or property of the object to be analyzed in the image of the biological sample, the purpose of the assay being performed, etc.

[0029] In step 204, user interface 152 provides the trial imaging configuration to microscopy system interface 156, which then instructs controller 112 ( FIG. 1 ) of microscopy system 100 to configure components in accordance with the trial imaging configuration. Thereafter, in step 206, microscopy system interface 156 instructs controller 112 to acquire one or more high-quality images of the biological sample in accordance with the trial imaging configuration and transmit the acquired high-quality images to microscopy system interface 156. Microscopy system interface 156 also stores the acquired high-quality images in image data store 158 in step 206. In some embodiments, in step 208, user interface 152 instructs user computer 154 to display the acquired high-quality images.

[0030] After a high quality image has been captured, in step 210 the user interface 152 receives from the user computer 154 a specification of a sequence of image processing steps.

[0031] In step 212, image analyzer 160 performs the image processing steps comprising the sequence received in step 210 to analyze the obtained high-quality images and identify objects and / or characteristics of such objects depicted therein. U.S. Pat. No. 8,577,079, entitled "IMAGE PROCESSING SYSTEM PROVIDING SELECTIVE ARRANGEMENT AND CONFIGURATION FOR AN IMAGE ANALYSIS SEQUENCE" (Cohen et al.) and U.S. Pat. No. 10,706,259, entitled "SYSTEM AND METHOD FOR IMAGE ANALYSIS OF MULTI-DIMENSIONAL DATA" (Cohen et al.), disclose systems and methods for defining and performing such a sequence of image processing steps and analyzing images. The entire contents of these patents are incorporated herein by reference. The sequence of image processing steps is provided to image analyzer 160, which performs the defined image processing steps on one or more of the high-quality images. Such image processing steps may include selecting an image captured using a particular illumination source, thresholding the image, applying one or more filters (e.g., an unsharp mask filter, a smoothing filter, a median filter, etc.), and masking or combining one or more images captured using a different imaging configuration and / or one or more images that were the result of applying imaging processing steps to the images.

[0032] In some embodiments, the sequence of image processing steps may define image processing steps that use machine learning system 162 to analyze high-quality images. In such embodiments, training parameter data store 164 may have one or more sets of predetermined training parameters developed to train machine learning system 162 to predict the presence of particular objects or object characteristics (i.e., classification of such objects) in particular types of images of biological samples. Examples of developing such sets of training parameters are disclosed in U.S. Patent Application No. 16 / 128,798, entitled "SYSTEM AND METHOD FOR LABEL-FREE IDENTIFICATION AND CLASSIFICATION OF BIOLOGICAL SAMPLES" (Cohen et al.) and U.S. Patent No. 10,706,261, entitled "SYSTEM AND METHOD FOR AUTOMATICALLY ANALYZING PHENOTYPICAL RESPONSES OF CELLS" (Cohen et al.), the entire contents of which are incorporated herein by reference.

[0033] 1-3 , to perform the image analysis steps specifying the use of the machine learning system 162, the image analyzer 160, in step 212, configures the untrained machine learning system 162 according to the specified training parameters, develops the trained machine learning system 162, and operates the trained machine learning system 162 using pixels of one or more images (i.e., one or more high-quality images and / or images resulting from previous image processing steps) as input to generate an output that predicts the probability that a corresponding pixel of the image is associated with a particular object type or an object type having a particular characteristic (i.e., a pixel associated with a classification of an object). The output generated by the trained machine learning system 162 can then be used as input in another image analysis step specified as part of the experimental assay protocol.

[0034] It will be apparent that the sequence of image processing steps comprising the test assay protocol may include multiple image processing steps using a machine learning system configured with a corresponding set of training parameters available in the training parameter database 164.

[0035] In step 214, the image analyzer 160 instructs the user interface 152 to instruct the user computer 154 to display the output generated by applying the sequence of image processing steps to the high-quality image obtained in step 206. Thus, researchers can evaluate the results of using the trial imaging configuration to capture high-quality images and analyze the high-quality images using the prescribed sequence of image processing steps.

[0036] In step 216, user interface 152 determines whether the researcher, using user computer 154, has adjusted the trial imaging configuration and / or sequence of image processing steps, e.g., whether the researcher has refined the configuration so that objects depicted in the images of the biological sample are effectively classified (i.e., the identities or characteristics of such objects are determined). If so, image analysis system 150 returns to step 204; otherwise, image analysis system 150 proceeds to step 218. The researcher may instruct image analysis system 150 to repeat steps 204-216 in this manner until a trial imaging configuration and sequence of image processing steps (i.e., a trial assay protocol) has been developed that will capture and analyze images of the trial biological sample as anticipated by the researcher.

[0037] After the pilot assay protocol is developed, the researcher uses the user computer 154 to instruct the image analysis system 150 to develop a production imaging configuration comprising the production assay protocol.

[0038] In response, in step 218, imaging configuration optimizer 166 of image analysis system 150 automatically evaluates the trial assay protocol and develops a plurality of candidate production imaging configurations and a score for each candidate production imaging configuration. The score represents how well objects and / or object properties identified in high-quality images using a sequence of image processing steps can be identified by applying such a sequence to images captured using the candidate production imaging configuration. One of the candidate production imaging configurations (e.g., the candidate production imaging configuration with the highest score) may then be selected as the recommended production imaging configuration.

[0039] Each of the multiple candidate production imaging configurations developed in step 218 requires less time and / or fewer specialized components to capture an image of a biological sample using microscopy system 100 compared to the trial imaging configurations developed by performing steps 204-216.

[0040] Referring to FIG. 4, the imaging configuration optimizer 166 includes a recommendation generator 248 that generates a recommended production imaging configuration, a candidate configuration generator 250 that develops a number of candidate production imaging configurations, a poor quality image generator 252, and an imaging configuration scorer 254.

[0041] 5 shows a flowchart 300 of steps performed by imaging configuration optimizer 166 to develop a recommended production imaging configuration. In step 302, recommendation generator 248 instructs candidate configuration generator 250 to develop multiple candidate production imaging configurations from the trial imaging configurations. In particular, candidate configuration generator 250 identifies imaging parameters of the trial imaging configurations associated with long imaging times (e.g., magnification, exposure time, etc.), the use of specialized imaging equipment (e.g., water immersion or other specific optics, specialized filters, specific illumination sources, fine focus, etc.), and / or the use of specialized microscopy techniques or sample processing (e.g., confocal microscopy, fluorescence imaging, sample labeling, etc.), and develops candidate production imaging configurations in which the imaging parameter values ​​are replaced with alternative imaging parameter values ​​that require shorter imaging times, use conventional imaging equipment and microscopy techniques, and / or do not require specialized sample processing.

[0042] For example, if the trial imaging configuration is specified using a magnification value of 40x, candidate configuration generator 250 develops candidate production imaging configurations that specify magnification values ​​of 20x, 10x, and 4x. Similarly, if the trial imaging configuration specifies using an exposure time of 100 ms, candidate configuration generator 250 develops candidate production imaging configurations that specify exposure times of 80 ms, 50 ms, 20 ms, and 10 ms.

[0043] Other examples of imaging parameter substitution include, for example, using an air objective with higher excitation power and exposure time instead of a water immersion objective to avoid longer laser autofocus times and water requirements; using transmitted light imaging instead of fluorescence imaging; and using wide-field imaging, lower magnification, shorter exposure times, and additional image processing steps instead of confocal imaging with high magnification. It will be apparent to those skilled in the art that candidate configuration generator 250 can be configured to substitute particular imaging parameter combinations in the trial imaging configurations with other parameter combinations to develop candidate production imaging configurations.

[0044] In some embodiments, multiple imaging parameters of a trial imaging configuration can be substituted to develop a candidate production imaging configuration. For example, candidate configuration generator 250 can generate a candidate production imaging configuration from a trial configuration by replacing a high magnification and a long exposure time specified in the trial imaging configuration with a lower magnification and a short exposure time. Those skilled in the art will understand that candidate configuration generator 250 can be configured to substitute a particular combination of imaging parameters specified in the trial imaging configuration to develop a candidate production imaging configuration.

[0045] In some embodiments, the candidate configuration generator 250 may select values ​​for the imaging parameters of the test imaging configuration to be replaced according to the type of cells comprising the biological sample being analyzed or the size of the object detected using the test assay protocol, and develop the candidate production imaging configuration. For example, such information may be used to select an objective lens that may be suitable for replacement. Similarly, the intensity values ​​of pixels in the high-quality image associated with the identified object may be used to select the exposure time.

[0046] Additionally, the candidate configuration generator 250 may be configured with information regarding the effect of substituting particular values ​​of imaging parameters of the trial imaging configurations on the values ​​of other imaging parameters, and candidate production imaging configurations are developed according to such information. For example, changing the objective lens may have known effects on exposure time, focus, Z-step (i.e., focal plane increment) requirements, and acquisition modality.

[0047] After multiple candidate production imaging configurations have been developed, in step 304, candidate configuration generator 250 selects one of the candidate production imaging configurations and instructs low-quality image generator 252 to develop, from the high-quality images, low-quality images associated with the candidate production imaging configuration in step 304, in step 306. In particular, low-quality image generator 252 performs image processing steps associated with substitutions made to one or more of the imaging parameters of the trial imaging configurations to develop candidate production imaging configurations and generate low-quality images associated with such candidate production imaging configurations. The low-quality images predict images that would be generated if microscopy system 100 were operated using the candidate production imaging configuration.

[0048] In some embodiments, the image processing step performed by the low-quality image generator 252 in step 306 includes applying one or more filters to the high-resolution image to generate a low-quality image. For example, a low-quality image associated with a magnification change between a first objective lens defined by the trial imaging configuration and a second objective lens defined by the candidate production imaging configuration may be created by scaling the high-quality image according to the ratio of the magnifications associated with the first and second objective lenses. Similarly, a Gaussian blur filter representing a change in the numerical aperture used to capture the high-quality image may be applied to the high-quality image to develop the low-quality image defined in the candidate production imaging configuration. If multiple imaging parameters are changed between the trial imaging configuration and the candidate production imaging configuration, image processing functions associated with each of these imaging parameter changes may be applied sequentially to the high-quality image to develop the low-quality image.

[0049] In other embodiments, the machine learning training parameter data store 164 includes sets of training parameters associated with substitutions of specific imaging parameters in the trial imaging configurations to develop candidate production imaging configurations. In such cases, the low-quality image generator 252 selects a set of training parameters associated with such substitutions, configures the untrained machine learning system 162 with the selected set of training parameters, develops the trained machine learning system 162, and operates the trained machine learning system 162 using the high-resolution images as input. In response, the trained machine learning system 162 generates low-quality images associated with the candidate production imaging configurations. For example, the data store 165 may include sets of training parameters for training the machine learning system 162 to develop low-quality images from the high-quality imaging to represent images captured by replacing a high-magnification water-immersion objective with a lower-magnification air objective, replacing fluorescence microscopy with transmitted light microscopy, etc.

[0050] In some embodiments, the low-quality image generator 252 also stores the low-quality image in the image data store 158 as associated with the selected candidate production imaging configuration in step 306 .

[0051] After the low quality image is generated (and stored) in step 306, imaging configuration scorer 254 analyzes the low quality image and develops a score for the candidate production imaging configuration selected in step 304 that was used to generate the low quality image. In particular, in step 308, imaging configuration scorer 254 uses image analyzer 160 to apply a series of image processes prescribed by the trial assay protocol to the low quality image to identify objects and / or object properties that are represented in the low quality image.

[0052] Thereafter, in step 310, imaging configuration scorer 254 compares the objects and / or object characteristics identified in the low-quality images with those identified in the high-quality images to develop a score. In some embodiments, imaging configuration scorer 254 calculates a first Z-prime statistic associated with the trial imaging configuration. As will be understood by those skilled in the art, the Z-prime statistic evaluates how well the high-quality images predict differences in the cells of the trial population represented in the high-quality images. These differences may include, for example, cells of the trial population to which a treatment has been applied versus a control group of treated cells, dead cells comprising the trial population versus a control group of live cells, etc. In addition, imaging configuration scorer 254 also calculates a second Z-prime statistic associated with the candidate production imaging configuration in step 310, which indicates how well the low-quality images developed according to the candidate production imaging configuration predict differences in the cells of the trial population. Imaging configuration scorer 254 develops a score associated with the candidate production imaging configuration according to the first and second Z-prime scores. Such a score can be the difference between two Z-prime scores, the ratio of two Z-prime scores, and the like.

[0053] In other embodiments, a series of image processing steps defined by the test assay protocol generates the output image. In such embodiments, those skilled in the art will understand that, in step 212 (FIG. 3), the image analyzer generates a first output image by applying a series of image processing steps to the high-quality image. Additionally, a second output image is generated when, in step 308, the imaging configuration scorer 254 applies a series of image processing steps to the low-quality image. In such embodiments, in step 310, the imaging configuration scorer 252 calculates the error (e.g., mean square error, etc.) between the pixels of the first output image and the pixels of the second output image and develops a score.

[0054] In some embodiments, the imaging configuration scorer, in step 310, compares a first metric (e.g., area, volume, perimeter, pixel intensity, etc.) of an object identified in the high-quality image with a second metric of a corresponding object identified in the low-quality image associated with the candidate production imaging configuration, and develops a score associated with the candidate production imaging configuration according to the error (e.g., mean square error) between the first metric and the second metric.

[0055] In some cases, in step 212 (FIG. 3), a sequence of image processing steps defined by the test assay protocol is applied to one or more high-quality images of wells of a microplate 116 (FIG. 1) placed in the microscopy system 100 to develop information about each well (e.g., whether the biological samples placed in the wells have undergone treatment, the ratio of live to dead cells in each microplate, the presence or absence of particular proteins in each well, etc.). In such a case, in step 306, a low-quality image corresponding to each high-quality image of the wells of the microplate 116 is generated (FIG. 1). In step 308, the imaging configuration scorer 254 applies the sequence of image processing steps to the low-quality images corresponding to such high-quality images. Thereafter, in step 310, the imaging configuration scorer 254 develops a score representing the accuracy with which the results of applying the sequence of image processing steps predict information about the biological samples placed in each well of the microplate 116 (FIG. 1).

[0056] In step 311, the imaging configuration scorer 254 develops an estimate of the time that will be required to develop one or more images of the biological sample according to the candidate production imaging configuration. The time estimate may reflect the time to acquire one or more images of the well 118, a portion of the well 118, or the entire microplate 116 in which the biological sample is placed. It will be apparent to one skilled in the art that the time estimate may be calculated according to imaging parameters defined by the candidate production imaging configuration, including the exposure time to acquire an image at each focal plane at each biological sample location, the number of focal planes at which images of the location should be acquired, the amount of time needed to focus to each focal plane at each location according to the objective lens being used, the time to operate any specialized hardware used to acquire the image, the time to move the microplate 116 to a location within the field of view of the objective lens, the number of biological sample locations to be imaged, etc. The estimated time is compared to the amount of time required to acquire high-quality images according to the trial imaging configuration, and an estimated time savings is calculated for the candidate production imaging configuration.

[0057] In step 312, candidate configuration generator 250 determines whether scores have been generated for all of the candidate production imaging configurations developed in step 302. If so, candidate configuration generator 250 proceeds to step 314; otherwise, candidate configuration generator 250 proceeds to step 304 to select another candidate production imaging configuration.

[0058] In step 313, recommendation generator 248 analyzes the scores and estimated time savings associated with the candidate production imaging configurations developed by candidate configuration generator 250 and selects one of the candidate production imaging configurations with the best score and the greatest time savings as the recommended production imaging configuration. In some cases, recommendation generator 248 selects the candidate production imaging configuration with the greatest time savings from those candidate production imaging configurations with scores above a predetermined amount as the recommended production imaging configuration. In other cases, recommendation generator 248 selects the candidate production imaging configuration with the greatest time savings from a predetermined portion of all candidate production imaging configurations as the recommended production imaging configuration. The predetermined portion may be a predetermined number (e.g., 3, 5, 10, etc.) or percentage (5 percent, 10 percent, etc.) of all candidate production imaging configurations with the best scores. It will be apparent to those skilled in the art that the criteria recommendation generator 248 uses to select the best score will depend on the metric used to develop the scores associated with the candidate production imaging configurations. For example, the best score may be the score with the greatest value. Alternatively, the best score may be the score with the lowest value, the highest absolute value, the lowest absolute value, the value closest to a predetermined value (eg, 0 or 1), etc.

[0059] In step 314, recommendation generator 248 instructs user interface 152 to instruct user computer 154 to display the candidate production imaging configurations, a score associated with each candidate production imaging configuration, and, optionally, an estimate of the time that may be saved by using the candidate production imaging configuration instead of the trial imaging configuration. In some embodiments, user interface 152 may further instruct user computer 154 to also display in step 314, for each candidate production imaging configuration, low-quality images associated with the production imaging configuration, objects identified in the low-quality images, and / or classifications of the objects identified in the low-quality images.

[0060] Also in step 313, the recommendation generator 248 instructs the user interface 152 to instruct the user computer 154 to display an indicator identifying the candidate production imaging configuration selected in step 313 as the recommended production imaging configuration.

[0061] 6 , in one embodiment, user interface 152 instructs user computer 154 to generate GUI 400 in which information regarding the recommended production imaging configuration and other candidate production imaging configurations may be displayed. In particular, a high-quality image is displayed in region 402 of GUI 400. Overlaid on the high-quality image in region 404 of GUI 400 is an estimate of the amount of time required to capture a high-quality image according to the trial imaging configuration, i.e., an information icon in region 406 of GUI 400. When the researcher (or other operator) clicks (or hovers) over region 406, user interface 152 instructs user computer 154 to display the imaging parameters defined by the trial imaging configuration. These imaging parameters may be displayed, for example, in a pop-up window (not shown), overlaid over region 402 of the GUI, or in another region (not shown) of GUI 400.

[0062] In addition, one or more lower quality images are displayed within regions 408a-408f of GUI 400. Although eight lower quality images are shown surrounding the high quality image in Figure 6, it will be apparent to one skilled in the art that more or fewer lower quality images may be shown and may be in different positions relative to the high quality image.

[0063] For each low-quality image displayed in region 408 of GUI 400, an estimate of the time saved calculated in step 311 (FIG. 3) is displayed in region 410 of GUI 400, and an information icon is displayed in region 412 of GUI 400. Selecting or hovering over the information icon displays information about the imaging parameters of the candidate production imaging configuration associated with the low-quality image displayed in region 408. In some embodiments, the differences between the imaging parameters of the candidate production imaging configuration associated with the low-quality image and the trial imaging configuration are displayed when the information icon is selected or hovered over.

[0064] An indicator is displayed in region 414 to indicate that the recommendation generator 248 has selected the candidate production imaging configuration associated with the low quality image displayed in region 408f as the recommended production imaging configuration.

[0065] 1 and 3 , in some embodiments, in step 316, the user interface 152 receives from the user computer 154, e.g., from a researcher (or another operator), instructions to develop a production assay protocol using the recommended production imaging configuration, or a selection of another candidate production imaging configuration for use in the production assay protocol. In response, the imaging configuration optimizer 166 develops, in step 318, a production assay protocol comprising the selected candidate production imaging configuration and sequence of imaging steps from the test imaging protocol. Such production assay protocol may then be used by the image analysis system 150 to automatically analyze additional microplates 116 placed in the microscopy system 100. Furthermore, such production assay protocol may be used with additional image analysis systems 150 in communication with corresponding microscopy systems 100 to automatically analyze microplates 116 placed in such microscopy systems.

[0066] 3 may provide for obtaining multiple high-quality images of a biological sample using multiple corresponding trial imaging configurations, and a series of image processing steps may analyze the multiple high-quality images at 212. It will be apparent to those skilled in the art that the imaging configuration optimizer 166 may create one or more candidate production imaging configurations for each of the multiple imaging configurations, develop one or more low-quality images according to the one or more candidate production imaging configurations, analyze each low-quality image, and develop a score for the candidate production imaging configuration associated with the low-quality image.

[0067] Those skilled in the art will understand that microscopy system 100 may be remote from image analysis system 150, and communication between microscopy system 100 and microscopy system interface 156 may occur over a private or public network (e.g., the Internet, a virtual private network, a local area network, a cellular network, etc.). Similarly, user computer 154 may be remote from image analysis system 150, and communication between user computer 154 and user interface 152 may occur over a private or public network. Furthermore, components of imaging analysis system 150 may be operated on a single computing device or multiple distributed computing devices that communicate with each other over a private or public network. For example, machine learning system 162 may be provided by a cloud service and accessed by image analyzer 160 over the Internet. Similarly, image data store 158 and / or training parameter data store 164 may be implemented using a cloud-based storage service.

[0068] It will be apparent to those skilled in the art that any combination of hardware and / or software can be used to implement the image analysis system 150 described herein. It is understood and appreciated that one or more of the processes, sub-processes, and process steps described with respect to FIGS. 1-5 can be performed by hardware, software, or a combination of hardware and software on one or more electronic or digitally controlled devices. The software may reside in software memory (not shown) within a suitable electronic processing component or system, such as, for example, one or more of the functional systems, controllers, devices, components, modules, or sub-modules depicted diagrammatically in FIGS. 1-5. The software memory may include an ordered list of executable instructions for implementing logical functions (i.e., “logic” that may be implemented in digital form, such as digital circuitry or source code, or in analog form, such as analog sources, such as analog electrical, sound, or video signals). The instructions may be executed within a processing module or controller (e.g., user interface 152, microscopy system interface 156, image analyzer 160, machine learning system 162, and imaging configuration optimizer 166 of FIG. 2 ; recommendation generator 248, candidate configuration generator 250, degraded image generator 252, and imaging configuration scorer 254 of FIG. 4 ), including, for example, one or more microprocessors, general-purpose processors, combinations of processors, digital signal processors (DSPs), field programmable gate arrays (FPGAs), or application-specific integrated circuits (ASICs). Furthermore, the schematic diagrams illustrate logical divisions of functionality with physical (hardware and / or software) implementations that are not limited by the architecture or physical layout of the functionality. The example systems described herein may be implemented in various configurations and operate as hardware / software components within a single hardware / software unit or within separate hardware / software units that are collocated or distributed.

[0069] The executable instructions may be implemented as a computer program product having instructions stored therein that, when executed by a processing module of an electronic system, direct the electronic system to perform the instructions. The computer program product may optionally be embodied in any non-transitory computer-readable storage medium for use by or in connection with an instruction execution system, apparatus, or device, such as an electronic computer-based system, a system including a processor, or other system that may selectively fetch and execute instructions from the instruction execution system, apparatus, or device. In the context of this document, a computer-readable storage medium is any non-transitory means that may store a program for use by or in connection with an instruction execution system, apparatus, or device. The non-transitory computer-readable storage medium may optionally be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device. A non-exhaustive list of more specific examples of non-transitory computer-readable media includes an electrical connection having one or more wires (electronic), a portable computer diskette (magnetic), random access, i.e., volatile, memory (electronic), read-only memory (electronic), erasable programmable read-only memory such as, for example, flash memory (electronic), compact disc memory such as, for example, CD-ROM, CD-R, CD-RW (optical), and digital versatile disc memory, i.e., DVD (optical).

[0070] It should also be understood that the terms "receive and transmit signals" or "transmit data" as used herein mean that two or more systems, devices, components, modules, or sub-modules can communicate with each other via signals traveling over some type of signal path. The signals may be communication, power, data, or energy signals that may communicate information, power, or energy from a first system, device, component, module, or sub-module to a second system, device, component, module, or sub-module along the signal path between the first and second systems, devices, components, modules, or sub-modules. The signal path may include physical, electrical, magnetic, electromagnetic, electrochemical, optical, wired, or wireless connections. The signal path may also include additional systems, devices, components, modules, or sub-modules between the first and second systems, devices, components, modules, or sub-modules.

[0071] All references, including publications, patent applications, and patents, cited in this specification are herein incorporated by reference to the same extent as if each reference was individually and specifically indicated to be incorporated by reference and were set forth herein in its entirety.

[0072] In the context of describing the present invention (particularly in the context of the claims that follow), the use of the terms "a," "an," "the," and similar referents should be construed to cover both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context. The recitation of ranges of values ​​herein is merely intended to serve as a shorthand method of referring individually to each separate value falling within the range, unless otherwise indicated herein, and each separate value is incorporated herein as if it were individually listed herein. All methods described herein can be performed in any suitable order, unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples or exemplary language (e.g., "such as") provided herein is intended merely to further clarify the disclosure and does not impose limitations on the scope of the invention unless otherwise claimed. No language in the specification should be construed as indicating any unclaimed element essential to the practice of the disclosure.

[0073] Numerous modifications to the present disclosure will be apparent to those skilled in the art in light of the foregoing description. It should be understood that the illustrated embodiments are examples only and should not be taken as limiting the scope of the present disclosure.

Claims

1. 1. A method of operating a microscopy system, the method comprising: receiving a first image of the sample obtained using a first imaging configuration; developing a second image from the first image, the second image being associated with a second imaging configuration; applying a series of image processing steps to the first image to develop a first classification of first objects represented in the first image, the first classification of the first objects being associated with an identification of one or more of the first objects in the first image, the identification of one or more of the first objects having a particular characteristic or metric associated with one or more of the first objects represented in the first image; applying the sequence of image processing steps to the second image to develop a second classification of second objects represented in the second image, the second classification of the second objects being associated with an identification of one or more of the second objects in the second image, the identification of one or more of the second objects having a particular characteristic or metric associated with the one or more of the second objects represented in the second image; developing a score associated with the second imaging configuration; Including, the score represents a difference between the first classification and the second classification; image acquisition time or component requirements to operate the microscopy system are less when operated using the second imaging configuration than when operated using the first imaging configuration; the scores comprise a first score; The method comprises: developing a third image from the first image, the third image being associated with a third imaging configuration; applying the sequence of image processing steps to the third image to develop a third classification, the third classification being associated with an identification of one or more objects in the third image, the identification of the one or more objects having a particular characteristic or metric associated with the one or more objects represented in the third image; developing a second score representing the difference between the first classification and the third classification; automatically selecting a recommended production imaging configuration, wherein the recommended production imaging configuration is the second imaging configuration if the first score is better than the second score, and the recommended production imaging configuration is the third imaging configuration if the second score is better than the first score; wherein the selected recommended production imaging configuration is used in a production assay protocol; The method, wherein the production assay protocol is used to automatically analyze additional microplates placed on the microscopy system.

2. selecting a set of training parameters according to an image processing step of said sequence of image processing steps; configuring an untrained machine learning system with the selected set of training parameters to develop a trained machine learning system; operating the trained machine learning system to develop the first classification; The method of claim 1 further comprising:

3. The method of claim 1 , further comprising developing the second imaging configuration from the first imaging configuration.

4. 4. The method of claim 3, wherein the first imaging configuration defines a first value associated with an imaging parameter and the second imaging configuration defines a second value associated with the imaging parameter, the first value and the second value being different.

5. selecting training parameters of an untrained machine learning system according to the difference between the first imaging configuration and the second imaging configuration; training the untrained machine learning system using the selected training parameters to develop a trained machine learning system; operating the trained machine learning system using the first image as input to generate the second image; The method of claim 4 further comprising:

6. 2. The method of claim 1, wherein the step of receiving the first image includes the step of obtaining the first image using a first microscopy system, and the method includes the further step of obtaining a third image using a second microscopy system according to the second imaging configuration.

7. The method of claim 1 , wherein the second image simulates an image of the sample that would be obtained if the microscopy system were operated using the second imaging configuration.

8. 2. The method of claim 1, wherein the second imaging configuration is one of a plurality of candidate production imaging configurations, a score is developed for each of the plurality of candidate production imaging configurations, and the method further comprises selecting a recommended production imaging configuration from those candidate production imaging configurations having a score above a predetermined amount.

9. the second imaging configuration is one of a plurality of candidate production imaging configurations, and a classification and score are developed for each of the plurality of candidate production imaging configurations, the method comprising: selecting a recommended production imaging configuration from the plurality of candidate production imaging configurations; instructing a computer to display information regarding each candidate production imaging configuration of the plurality of candidate production imaging configurations and an indicator identifying the candidate production imaging configuration selected as the recommended production imaging configuration; further comprising The method of claim 1 , wherein the information displayed for each candidate production imaging configuration includes one or more of the score, an estimate of time savings, an image, and an object classification associated with the candidate production imaging configuration.

10. 10. The method of claim 9, further comprising receiving from the computer a selection of one of the candidate production imaging configurations in which to configure the microscopy system.

11. 1. A system for operating a microscopy system, the system comprising: an imaging configuration optimizer operating on one or more processors that receives a first image of the sample acquired using the first imaging configuration; a low-quality image generator operating on the one or more processors that develops a second image from the first image, the second image being associated with a second imaging configuration; and an image analyzer operating on the one or more processors that applies a series of image processing steps to the first image and the second image to develop a first classification, the first classification being associated with a first object represented in the first image, the first classification of the first object being associated with an identification of one or more of the first objects in the first image, the identification of one or more of the first objects having a particular characteristic represented in the first image or metric associated with one or more of the first objects represented in the first image; and an imaging composition scorer operating on said one or more processors; Including, the imaging configuration scorer applies the sequence of image processing steps to the second image to develop a second classification associated with a second object depicted in the second image and to develop a score associated with the second imaging configuration, the score representing a difference between the first classification and the second classification, the second classification of the second object being associated with an identification of one or more of the second objects in the second image, the identification of one or more of the second objects having a particular characteristic depicted in the second image or a metric associated with one or more of the second objects depicted in the second image; image acquisition time or component requirements to operate the microscopy system are less when operated using the second imaging configuration than when operated using the first imaging configuration; the scores comprise a first score; the low-quality image generator develops a third image from the first image, the third image being associated with a third imaging configuration; the imaging configuration scorer applies the sequence of image processing steps to the third image to develop a third classification and develop a second score representing a difference between the first classification and the third classification; the system further includes a recommendation generator operating on the one or more processors that automatically selects a recommended production imaging configuration, the recommended production imaging configuration being the second imaging configuration if the first score is better than the second score, and the recommended production imaging configuration being the third imaging configuration if the second score is better than the first score; the third classification being associated with an identification of one or more objects in the third image, the identification of one or more objects having particular characteristics represented in the third image or metrics associated with the one or more objects represented in the third image; the selected recommended production imaging configuration is used in a production assay protocol; The production assay protocol is used to automatically analyze additional microplates placed in the microscopy system.

12. 12. The system of claim 11, further comprising an untrained machine learning system, wherein the image analyzer selects training parameters associated with a step in the sequence of image processing steps, uses the training parameters to configure the untrained machine learning system, develops a trained machine learning system, operates the trained machine learning system, and develops the first classification.

13. The system of claim 11 , further comprising a candidate configuration generator operating on the one or more processors that automatically develops the second imaging configuration based on the first imaging configuration.

14. 14. The system of claim 13, wherein the first imaging configuration defines a first value associated with an imaging parameter, and the second imaging configuration developed by the candidate configuration generator automatically defines a second value associated with the imaging parameter, the first value and the second value being different.

15. 15. The system of claim 14, further comprising an untrained machine learning system, wherein the low-quality image generator selects a set of training parameters according to differences between the first imaging configuration and the second imaging configuration, trains the untrained machine learning system using the selected training parameters, develops a trained machine learning system, and operates the trained machine learning system using the first image as an input to generate the second image.

16. The system of claim 11, wherein the microscopy system comprises a first microscopy system operated according to the first imaging configuration to obtain the first image, and a second microscopy system operated according to the second imaging configuration to obtain a third image.

17. The system of claim 11 , wherein the second image simulates an image of the sample that would be obtained if the microscopy system were operated using the second imaging configuration.

18. 12. The system of claim 11, wherein the second imaging configuration is one of a plurality of candidate production imaging configurations, the system further comprising a candidate configuration generator and a recommendation generator, wherein the candidate configuration generator develops the plurality of candidate production imaging configurations, the imaging configuration scorer develops a score for each of the candidate production imaging configurations, and the recommendation generator selects as the recommended production imaging configuration from those candidate production imaging configurations having a score above a predetermined amount.

19. the second imaging configuration is one of a plurality of candidate production imaging configurations, a classification and a score are developed for each of the plurality of candidate production imaging configurations, and the system: a recommendation generator that selects a recommended production imaging configuration from the plurality of candidate production imaging configurations; a user interface generator that instructs a computer to display information regarding each candidate production imaging configuration of the plurality of candidate production imaging configurations and an indicator that identifies the candidate production imaging configuration selected as the recommended production imaging configuration; further comprising The system of claim 11 , wherein the information displayed for each candidate production imaging configuration includes one or more of the score, an estimate of time savings, an image, and an object classification associated with the candidate production imaging configuration.

20. 20. The system of claim 19, wherein the user interface generator receives from the computer a selection of one of the candidate production imaging configurations in which to configure the microscopy system.

Images