System and method for biological object evaluation, clone selection, and process management

Abstract

One or more computing devices, systems and / or methods are provided. In an example, one or more images may be received. A biological object segmentation model may analyze the one or more images to generate a biological object map indicative of regions, of the specimen, including biological objects. Sets of features associated with the biological objects may be determined based upon the biological object map. Scores associated with the biological objects may be determined. One or more target regions of the specimen may be determined based upon the scores.

Description

SYSTEM AND METHOD FOR BIOLOGICAL OBJECT EVALUATION, CLONE SELECTION, AND PROCESS MANAGEMENTRELATED APPLICATION

[0001] This application claims priority to U.S. Provisional Patent Application No. 63 / 652,573, filed on May 28, 2024, entitled “Automated Induced Pluripotent Stem Cell (iPSC) Colony Evaluation and Clone Selection System,” which is incorporated herein by reference in its entirety.TECHNICAL FIELD

[0002] The present disclosure relates to evaluating biological objects.BACKGROUND

[0003] Induced pluripotent stem cells (IPSCs) are widely used in development of personalized therapies, disease modeling, drug screening, and other fields. iPSCs are generated by reprogramming adult somatic cells.SUMMARY

[0004] In accordance with the present disclosure, one or more devices, systems and / or methods are provided. In an example, one or more images may be received. A biological object segmentation model may analyze the one or more images to generate a biological object map indicative of regions, of the specimen, including biological objects. Sets of features associated with the biological objects may be determined based upon the biological object map. Scores associated with the biological objects may be determined. One or more target regions of the specimen may be determined based upon the scores. One or more operations (e.g., object-specific actions) may be initiated in association with biological objects based on location and / or scored attributes. The one or more operations may include selective isolation (e.g., picking), selective removal (e.g., weeding), biopsy (e.g., partial isolation for archive and / or testing), transplantation (e.g., for further processing), and / orobservation over time to detect desirable and / or undesirable changes in biological attributes indicative of intrinsic biological potential of the starting material.DESCRIPTION OF THE DRAWINGS

[0005] While the techniques presented herein may be embodied in alternative forms, the particular embodiments illustrated in the drawings are only a few examples that are supplemental of the description provided herein. These embodiments are not to be interpreted in a limiting manner, such as limiting the claims appended hereto.

[0006] Fig. 1 is an illustration of a scenario involving various examples of networks that may connect servers and clients.

[0007] Fig. 2 is an illustration of a scenario involving an example configuration of a server that may utilize and / or implement at least a portion of the techniques presented herein.

[0008] Fig. 3 is an illustration of a scenario involving an example configuration of a client that may utilize and / or implement at least a portion of the techniques presented herein.

[0009] Fig. 4 is a component block diagram illustrating a colony evaluation system, in accordance with some embodiments.

[0010] Fig. 5 is a component block diagram illustrating one or more captured images being processed to generate one or more processed images, in accordance with some embodiments.

[0011] Fig. 6A is a component block diagram illustrating use of a biological object segmentation model to generate a biological object map, in accordance with some embodiments.

[0012] Fig. 6B is a component block diagram illustrating use of a plurality of images and label information to train a biological object segmentation model, in accordance with some embodiments.

[0013] Fig. 6C is a component block diagram illustrating an operation of a feature selection process, in accordance with some embodiments.

[0014] Fig. 6D illustrates data structures associated with features, in accordance with some embodiments.

[0015] Fig. 6E illustrates data structures associated with features, in accordance with some embodiments.

[0016] Fig. 6F illustrates data structures associated with features, in accordance with some embodiments.

[0017] Fig. 7 A is a component block diagram illustrating generation of a target region map, in accordance with some embodiments.

[0018] Fig. 7B is a component block diagram illustrating determination of scoring information associated with biological objects based upon a biological object map, in accordance with some embodiments.

[0019] Fig. 7C illustrates a data structure indicative of features of biological objects, in accordance with some embodiments.

[0020] Fig. 8A illustrates a cell picking scenario, in accordance with some embodiments.

[0021] Fig. 8B illustrates a cell picking scenario, in accordance with some embodiments.

[0022] Fig. 8C illustrates a cell picking scenario, in accordance with some embodiments.

[0023] Fig. 9A illustrates a representation of a specimen and / or a first vessel prior to a selective removal operation, in accordance with some embodiments.

[0024] Fig. 9B illustrates a representation of a specimen and / or a first vessel after a selective removal operation, in accordance with some embodiments.

[0025] Fig. 10A is a component block diagram illustrating a cell monitoring system, in accordance with some embodiments.

[0026] Fig. 10B illustrates a morphology map generated by a cell monitoring system, in accordance with some embodiments.

[0027] Fig. 11 is a flow chart illustrating an example method, in accordance with some embodiments.

[0028] Fig. 12 is an illustration of a scenario featuring an example non- transitory machine readable medium in accordance with one or more of the provisions set forth herein.DETAILED DESCRIPTION

[0029] Subject matter will now be described more fully hereinafter with reference to the accompanying drawings, which form a part hereof, and which show, by way of illustration, specific example embodiments. This description is not intended as an extensive or detailed discussion of known concepts. Details that are known generally to those of ordinary skill in the relevant art may have been omitted, or may be handled in summary fashion.

[0030] The following subject matter may be embodied in a variety of different forms, such as methods, devices, components, and / or systems. Accordingly, this subject matter is not intended to be construed as limited to any example embodiments set forth herein. Rather, example embodiments are provided merely to be illustrative. Such embodiments may, for example, take the form of hardware, software, firmware, customized features (e.g., tips, cell vessels, surface coatings, media composition, mechanical motion and / or fluid movement on a sample before and / or after imaging and / or interventions, etc.), or any combination thereof.

[0031] Fig. 1 is an interaction diagram of a scenario 100 illustrating a service 102 provided by a set of servers 104 to a set of client devices 110 via various types of networks. The servers 104 and / or client devices 1 10 may be capable of transmitting, receiving, processing, and / or storing many types of signals, such as in memory as physical memory states.

[0032] In the scenario 100 of Fig. 1 , the service 102 may be accessed via a wide area network 108 (WAN) by a user 112 of one or more client devices 110, such as a portable media player (e.g., an electronic text reader, an audio device, or a portable gaming, exercise, or navigation device); a portable communication device (e.g., a camera, a phone, a wearable or a text chattingdevice); a workstation; and / or a laptop form factor computer. The respective client devices 110 may communicate with the service 102 via various connections to the wide area network 108.

[0033] One or more client devices 1 10 may comprise a cellular communicator and may communicate with the service 102 by connecting to the wide area network 108 via a wireless local area network 106 (LAN) provided by a cellular provider.

[0034] Alternatively and / or additionally, one or more client devices 110 may communicate with the service 102 by connecting to the wide area network 108 via a wireless local area network 106 provided by a location such as the user’s home or workplace. The wireless local area network 106 may, for example, be a WiFi (Institute of Electrical and Electronics Engineers (IEEE) Standard 802.11 ) network or a Bluetooth (IEEE Standard 802.15.1) personal area network.

[0035] It may be appreciated that the servers 104 and the client devices 110 may communicate over various types of networks. Exemplary types of networks that may be accessed by the servers 104 and / or client devices 110 include mass storage, such as network attached storage (NAS), a storage area network (SAN), or other forms of computer or machine readable media.

[0036] The servers 104 of the service 102 may be interconnected directly, or through one or more other networking devices, such as routers, switches, and / or repeaters. The servers 104 may utilize a variety of physical networking protocols, such as Ethernet and / or Fiber Channel, and / or logical networking protocols, such as variants of an Internet Protocol (IP), a Transmission Control Protocol (TCP), and / or a User Datagram Protocol (UDP).

[0037] The servers 104 of the service 102 may be internally connected via a local area network 106. The local area network 106 may be organized according to one or more network architectures, such as server / client, peer- to-peer, and / or mesh architectures, and / or a variety of roles, such as administrative servers, authentication servers, security monitor servers, data stores for objects such as files and databases, business logic servers, timesynchronization servers, and / or front-end servers providing a user-facing interface for the service 102.

[0038] The local area network 106 may be a wired network where network adapters on the respective servers 104 are interconnected via cables (e.g., coaxial and / or fiber optic cabling), and may be connected in various topologies (e.g., buses, token rings, meshes, and / or trees). The local area network 106 may include, e.g., analog telephone lines, such as a twisted wire pair, a coaxial cable, full or fractional digital lines including T1 , T2, T3, or T4 type lines, Integrated Services Digital Networks (ISDNs), Digital Subscriber Lines (DSLs), wireless links including satellite links, or other communication links or channels, such as may be known to those skilled in the art.

[0039] Alternatively and / or additionally, the local area network 106 may comprise one or more sub-networks, such as may employ differing architectures, may be compliant or compatible with differing protocols and / or may interoperate within the local area network 106. Additionally, a variety of local area networks 106 may be interconnected; e.g., a router may provide a link between otherwise separate and independent local area networks 106.

[0040] In the scenario 100 of Fig. 1 , the local area network 106 of the service 102 is connected to a wide area network 108 that allows the service 102 to exchange data with other services 102 and / or client devices 1 10. The wide area network 108 may encompass various combinations of devices with varying levels of distribution and exposure, such as a public wide-area network (e.g., the Internet) and / or a private network (e.g., a virtual private network (VPN) of a distributed enterprise).

[0041] Fig. 2 presents a schematic architecture diagram 200 of a server 104 that may utilize at least a portion of the techniques provided herein. Such a server 104 may vary widely in configuration or capabilities, alone or in conjunction with other servers, in order to provide a service such as the service 102.

[0042] The server 104 may comprise a variety of peripheral components, such as a wired and / or wireless network adapter 214 connectible to a local area network and / or wide area network; one or more storage components216, such as a hard disk drive, a solid-state storage device (SSD), a flash memory device, and / or a magnetic and / or optical disk reader.

[0043] The server 104 may comprise memory 202 storing various forms of applications, such as an operating system 204; one or more server applications 206, such as a hypertext transport protocol (HTTP) server, a file transfer protocol (FTP) server, or a simple mail transport protocol (SMTP) server; and / or various forms of data, such as a database 208 or a file system.

[0044] The server 104 may comprise one or more processors 210 that process instructions. The one or more processors 210 may optionally include a plurality of cores; one or more coprocessors, such as a mathematics coprocessor or an integrated graphical processing unit (GPU); and / or one or more layers of local cache memory.

[0045] The server 104 may comprise a mainboard featuring one or more communication buses 212 that interconnect the processor 210, the memory 202, and various peripherals, using a variety of bus technologies, such as a variant of a serial or parallel AT Attachment (ATA) bus protocol; a Uniform Serial Bus (USB) protocol; and / or Small Computer System Interface (SCI) bus protocol. In a multibus scenario, a communication bus 212 may interconnect the server 104 with at least one other server.

[0046] The server 104 may operate in various physical enclosures, such as a desktop or tower, and / or may be integrated with a display as an “all-in- one” device. The server 104 may be mounted horizontally and / or in a cabinet or rack, and / or may simply comprise an interconnected set of components.

[0047] The server 104 may provide power to and / or receive power from another server and / or other devices. The server 104 may comprise a dedicated and / or shared power supply 218 that supplies and / or regulates power for the other components. The server 104 may comprise a shared and / or dedicated climate control unit 220 that regulates climate properties, such as temperature, humidity, and / or airflow.

[0048] The server 104 may include one or more other components that are not shown in the schematic diagram 200 of Fig. 2, such as a display; a display adapter, such as a graphical processing unit (GPU); input peripherals, suchas a keyboard and / or mouse; and a flash memory device that may store a basic input / output system (BIOS) routine that facilitates booting the server 104 to a state of readiness. A plurality of such servers 104 may be configured and / or adapted to utilize at least a portion of the techniques presented herein.

[0049] Fig. 3 presents a schematic architecture diagram 300 of a client device 110 whereupon at least a portion of the techniques presented herein may be implemented. Such a client device 110 may vary widely in configuration or capabilities, in order to provide a variety of functionality to a user such as the user 112.

[0050] The client device 110 may comprise memory 301 storing various forms of applications, such as an operating system 303; one or more user applications 302, such as document applications, media applications, file and / or data access applications, communication applications such as web browsers and / or email clients, utilities, and / or games; and / or drivers for various peripherals.

[0051] In some examples, as a user 1 12 interacts with a software application on a client device 1 10 (e.g., an instant messenger and / or electronic mail application), descriptive content in the form of signals or stored physical states within memory (e.g., an email address, instant messenger identifier, phone number, postal address, message content, date, and / or time) may be identified.

[0052] In such examples, descriptive content may be stored, typically along with contextual content. For example, the source of an email address (e.g., a communication received from another user via an instant messenger application) may be stored as contextual content associated with the email address. Contextual content, therefore, may identify circumstances surrounding receipt of an email address (e.g., the date or time that the email address was received), and may be associated with descriptive content. Contextual content, may, for example, be used to subsequently search for associated descriptive content. For example, a search for email addresses received from specific individuals, received via an instant messenger application or at a given date or time, may be initiated.

[0053] The client device 110 may comprise one or more processors 310 that process instructions. The one or more processors 310 may optionally include a plurality of cores; one or more coprocessors, such as a mathematics coprocessor or an integrated graphical processing unit (GPU); and / or one or more layers of local cache memory.

[0054] The client device 110 may comprise a dedicated and / or shared power supply 318 that supplies and / or regulates power for other components, and / or a battery 304 that stores power for use while the client device 110 is not connected to a power source via the power supply 318. The client device 110 may provide power to and / or receive power from other client devices.

[0055] The client device 110 may comprise a variety of peripheral components, such as a wired and / or wireless network adapter 306 connectible to a local area network and / or wide area network; one or more output components, such as a display 308 coupled with a display adapter (optionally including a graphical processing unit (GPU)), a sound adapter coupled with a speaker, and / or a printer; input devices for receiving input from the user, such as a keyboard 311 , a mouse, a microphone, a camera, and / or a touch-sensitive component of the display 308; and / or environmental sensors, such as a global positioning system (GPS) receiver 319 that detects the location, velocity, and / or acceleration of the client device 110, a compass, accelerometer, and / or gyroscope that detects a physical orientation of the client device 110.

[0056] The client device 110 may comprise a mainboard featuring one or more communication buses 312 that interconnect the processor 310, the memory 301 , and various peripherals, using a variety of bus technologies, such as a variant of a serial or parallel AT Attachment (ATA) bus protocol; the Uniform Serial Bus (USB) protocol; and / or the Small Computer System Interface (SCI) bus protocol.

[0057] The client device 110 may include one or more other components that are not shown in the schematic architecture diagram 300 of Fig. 3, such as one or more storage components, such as a hard disk drive, a solid-state storage device (SSD), a flash memory device, and / or a magnetic and / or optical disk reader; and / or a flash memory device that may store a basicinput / output system (BIOS) routine that facilitates booting the client device 110 to a state of readiness. In some examples, the client device 110 may include a climate control unit that regulates climate properties, such as temperature, humidity, and airflow.

[0058] The client device 110 may include one or more servers that may locally serve the client device 110 and / or other client devices of the user 1 12 and / or other individuals. For example, a locally installed webserver may provide web content in response to locally submitted web requests. Many such client devices 110 may be configured and / or adapted to utilize at least a portion of the techniques presented herein.

[0059] The client device 110 may serve the user in a variety of roles, such as a workstation, kiosk, media player, gaming device, and / or appliance. The client device 110 may therefore be provided in a variety of form factors, such as a desktop or tower workstation; an “all-in-one” device integrated with a display 308; a laptop, tablet, convertible tablet, or palmtop device; a wearable device mountable in a headset, eyeglass, earpiece, and / or wristwatch, and / or integrated with an article of clothing; and / or a component of a piece of furniture, such as a tabletop, and / or of another device, such as a vehicle or residence.

[0060] In the present disclosure, the term “vessel” may refer to any container or structure, regardless of shape, size, or material, that is configured to hold, support, culture and / or grow biological specimens. The vessel may comprise one or more walls protruding from a surface upon which a specimen is disposed or may comprise a flat or curved surface upon which the specimen is disposed without walls extending from the flat or curved surface. The vessel may have at least one of a cylindrical shape, a rectangular shape, a polygonal shape, an irregular shape, etc.

[0061] In the present disclosure, the term “biological object” may refer to a group of related cells, including, but not limited to (i) a population of cells resulting from expansion from one or more progenitor cells derived from a native adult, fetal tissues and / or a blastocyst, (ii) a population of cells derived from a biologically relevant event such as mutation or reprogramming (as in the case of induced pluripotent stem cell (iPSC) generation, for example)and / or (iii) a population of cells that were modified (e.g., intentionally modified) to alter biological properties (via gene editing, plasmid transformation, viral transfection, etc., for example).

[0062] The present disclosure provides for a system and / or techniques for detection, analysis, isolation, biopsy, sampling, removal, selective preservation and / or harvest of biological objects. In some examples, the system and / or techniques may utilize large field of view (LFOV, i.e. , whole well) live cell imaging and image analysis tools to automate the process of clone identification, segmentation and morphological assessment and / or to replace subjective decision making and use automated selection of biological objects for selective isolation, weeding, transplantation, expansion and / or cell population management.

[0063] Recent technologies enabling reprogramming of adult somatic cells to induced pluripotent stem cells (IPSCs) provide a useful example of the opportunity to develop new cell-based therapies and bioassays using the methods and device design disclosed here. The development of successful cell therapies demands reproducible large-scale iPSC production and differentiation to desirable cell type. The reprogramming efficiency of adult cells is low. Biological performance varies greatly among clones of reprogrammed cells. iPSCs grown in colonies have characteristic morphological features. A homogeneous, clonal cell population without differentiated cells is one of the desired conditions for their further differentiation to desired cell type. However, variation in appearance and performance of individual clones (e.g., spontaneous differentiation and / or differentiation potential) can be large. Various destructive or invasive molecular methods can be used to assess the state of undifferentiated, healthy colonies. However, the use of invasive assessment methods induces variation, cost and risk, which may preclude the use of cells exposed to invasive or exogenous conditions in clinical practice. iPSC colony morphology is typically considered an important criterion for the noninvasive assessment of cell culture quality. However, large variation in judgement is seen among even skilled investigators. This is often managed by screening large numbers of clones before investing in any one for ongoing iPSC linedevelopment. Using techniques of the present disclosure to automate clone expansion, clone type expansion, clone class expansion and / or clone selection using a system developed from large training sets linked to downstream performance data may accelerate the repeatability, reproducibility and quality of iPSC generation and may reduce waste associated with screening or investing in clones which ultimately fail. The use of a fully automated platform for iPSC derivation, expansion, and / or differentiation may be key in transitioning to large-scale cell culture. The morphological assessment of growing colonies and cells, using non-invasive methods, may allow the best clones for further clinical applications to be safely and efficiently selected. In some examples, the present disclosure may be used for later stages of cell product development, such as during differentiation, in which a population of cells (e.g., iPSC-derived cells) is induced to differentiate and / or transition into a biological state that may be reflected by a manifestation of a defined set of morphological features (e.g., T-Cells, Cardiomyocytes, keratinocytes, pigmented retinal epithelial cells, endothelium, islet cells, etc.). For example, the present disclosure may be used to demonstrate purity and / or homogeneity of the population of cells. Ranking, selection and / or removal operations provided herein may be used as a technique for late stage processing to optimize cell performance, remove contaminating and / or undesirable cells, and / or to enable selective biopsy to document cell state and / or interrogate areas of aberration.

[0064] Human iPSCs are becoming a founding cell source for therapies including autograft therapies and allograft therapies. This technology has effectively replaced the need for generation of embryonic stem cells by disrupting a blastocyst. The cell therapy industry has increasingly explored the promise of iPSCs as a starting material for cellular therapies across virtually all tissues (e.g. cardiomyocytes, neurons, T-Cells, hepatocytes, blood, cartilage, etc.). The first human trial of iPSC-derived hematopoietic stem cells for treatment of sickle cell anemia was recently reported. Ongoing trials are numerous, focusing on CAR-T cells therapies, Parkinson's Dz, CHF, diabetes, and osteoarthritis. However, iPSCs require specialized skills to reprogram, select, and expand, which is intensely manual, time consuming,and costly. Outcomes vary widely from sample to sample and clone to clone. This places a high importance on expert judgement of skilled technicians, for early stage screening and selection of clones that are worthy of investment. Currently, decisions about clone selection are delegated or assigned to trusted and experienced technicians. However, skills vary, and outcomes remain inconsistent. The field recognizes that there are large potential benefits if iPSC processing and decision-making can be automated, and documentation using live cell imaging can be enhanced. For example, in addition to cell therapy development, the disclosed techniques may be used for screening for toxicity and / or therapeutic effects, using a starting cell population which when plated as identical samples into independent culture vessels, become independent population samples subject to independent analysis for changes in biological response and / or composition in response to testing agents.

[0065] In accordance with some embodiments of the present disclosure, a colony evaluation system (e.g., an automated colony evaluation system) is provided. The colony evaluation system may include an imaging system for capturing and / or preparing one or more images of a specimen, and / or a biological object segmentation system for identifying regions, of the specimen, comprising biological objects, such as biological colonies of a first cell type (e.g., IPSC colonies or other type of biological object). The biological objects may be derived from a reprogramming event in a single cell. The colony evaluation system may include a cell targeting system for determining one or more target regions of the specimen, such as by performing clone selection, and / or a cell processing system for triggering and / or performing one or more cell operations based upon the one or more target regions.

[0066] In some examples, a cell operation performed by the cell processing system may comprise a selective removal operation (to remove undesirable portions of the specimen from a first vessel in which the specimen is disposed, for example), an isolation operation (to isolate the one or more target regions from the specimen, for example), a biopsy operation (to test one or more cells of the one or more target regions, for example), a selective isolation operation (e.g., clone picking operation), a sampling operation, aharvesting operation, a cell expansion operation (to transfer cells from the one or more target regions from the first vessel to a new location for cell expansion, for example), a deposition operation, an injection operation and / or other operation.

[0067] In some examples, the cell expansion operation comprises transferring a sample of cells from the one or more target regions to a second vessel (e.g., at least one of a well, a disk, a flask, a dish, etc.) for archiving, testing, processing and / or cell expansion, and / or storing the sample of cells in the second vessel (and / or one or more other vessels) for a period in a controlled environment (e.g., an environment having one or more controlled conditions, such as controlled chemical composition, humidity, gas composition, etc., suitable for proliferation). A cell monitoring system may (periodically, for example) perform a cell monitoring process comprising capturing one or more images of a sample of cells in the second vessel, analyzing the one or more images to determine a status of the sample of cells, and / or triggering one or more operations (e.g., at least one of a selective removal operation which may comprise removal of undesired cells, a selective isolation operation which may comprise selective transplantation of desired cells, etc.) based upon the status.

[0068] The analysis may include checking for regions of cells having morphological deviation indicative of undesirable performance (e.g., iPSC spontaneous differentiation regions) or unstable morphology (e.g., a deviation from a phenotype of the first cell type and / or a deviation from a morphology of cells in the second vessel at an earlier time in the cell expansion operation). In response to detecting a region with cells having an unstable morphology, the cell monitoring system may trigger a selective removal operation (e.g., a weeding operation) to remove undesirable or unstable cells from the region.

[0069] The analysis may include determining one or more measurements associated with the sample of cells, such as a confluence of the sample of cells (e.g., a proportion of a surface area of the second vessel that is covered by stable cells), a density of the sample of cells (e.g., a quantity of cells per unit area or volume), or other measurement. In some examples, the cell monitoring system may trigger a harvesting operation to harvest at least somecells from the sample in response to a determination that a condition has been met, such as a condition that the confluence meets a threshold confluence, the density meets a threshold density, and / or a score determined based upon the one or more measurements meets a threshold score. The cell monitoring system may schedule a cell operation (e.g., the harvesting operation or other operation) for a later time in the future, for example, at a time by which the cell monitoring system expects the condition to be met.

[0070] In some examples, one, some or all of the operations provided herein are performed automatically and / or without human intervention, thereby providing for automated management, monitoring, handling and / or administration of cells (e.g., iPSCs and / or other types of cells). In some examples, one, some or all of the operations provided herein are performed with limited human intervention, for example, receiving authorization from an expert to perform a cell operation triggered by the colony evaluation system and / or the cell monitoring system. For example, in response to triggering the cell operation, a message (e.g., email, text message, push notification, etc.) may be transmitted (by the colony evaluation system and / or the cell monitoring system) to a device associated with an agent (e.g., the expert) tasked with providing authorization to perform and / or schedule the cell operation. The message may comprise a link to a resource (e.g., a webpage, a mobile application, etc.) usable for the expert to provide authorization to perform or schedule the cell operation.

[0071] Fig. 4 illustrates a colony evaluation system 401 , in accordance with some embodiments. The colony evaluation system 401 may comprise a first imaging system 402 for capturing and / or preparing one or more images of a specimen. The colony evaluation system 401 may comprise a biological object segmentation system 404 for identifying regions, of the specimen, comprising biological objects. The biological objects may comprise biological colonies of a first cell type (e.g., iPSC colonies or other type of biological object). The biological objects may be derived from a reprogramming event in a single cell. The colony evaluation system 401 may comprise a cell targeting system 406 for determining one or more target regions of the specimen, such as by performing clone selection, and / or a first cell processing system 408 fortriggering and / or performing one or more cell operations based upon the one or more target regions.

[0072] Fig. 5 illustrates aspects of the first imaging system 402, in accordance with some embodiments. In some examples, the first imaging system 402 may capture and / or receive one or more first images 502 of a specimen. In some examples, the specimen is stored in a first vessel (e.g., at least one of a well, a disk, a flask, a dish, etc.). The one or more first images 502 may be captured using one or more cameras positioned proximal the specimen and / or the first vessel. The one or more first images 502 may be processed using an image processing module 504 to generate one or more second images 508, which may comprise a first image 506 and / or one or more other images.

[0073] In some examples, an image of the one or more first images 502 may have a view of an entirety or at least a threshold proportion (e.g., 75%) of the first vessel and / or the specimen. In some examples, an image of the one or more first images 502 may have a view of a portion, of the first vessel and / or the specimen, that is smaller than the threshold proportion. In some examples, the one or more first images 502 may include a subset of data from the portion of the first vessel and / or the specimen. In some examples, the one or more first images 502 may include data derived from one or more live cell imaging modality.

[0074] In some examples, the image processing module 504 may perform one or more first image processing operations on the one or more first images 502 to generate the one or more second images 508. In some examples, the one or more first images 502 and / or the one or more second images 508 may comprise one or more large field of view (LFOV) images. In some examples, the one or more first images 502 may comprise a single image or a plurality of images captured over time. In some examples, the image processing module 504 may analyze images (of the one or more first images 502 and / or the one or more second images 508, for example) captured at two or more time points to assess one or more changes in one or more regions and / or one or more biological objects during a defined interval of time. The one or more changes may comprise one or more changes in object size, confluence, density,shape, and / or morphology, which may be may be interpreted as indicators of biological attributes and / or state changes within a given region or object. In some examples, the one or more changes may be provided to the cell targeting system 406 (for use in determining one or more target regions for at least one of selective removal, selective isolation, etc., for example). In some examples, the image processing module 504 may generate an image of the one or more second images 508 using one or more image stitching techniques, such as by stitching two or more images together. In some examples, the one or more second images 508 may comprise a montage image representing a view (e.g., whole well view, partial well view, etc.) of the first vessel and / or the specimen.

[0075] In some examples, the one or more first image processing operations may comprise applying a high-pass filter to the one or more first images 502 to correct for meniscus effects. In some examples, the one or more first image processing operations may comprise flat field correction, background correction, stitching, z-stacking, subsampling, filtering, and / or smoothing. In some examples, the one or more first image processing operations may be performed on individual images and / or on montage images generated from multiple images. In some examples, the one or more first image processing operations may comprise using one image capture modality per location. In some examples, a same location may be processed using multiple imaging modes, such as z-stacking, quantitative phase imaging, fluorescent imaging, bright field imaging, and / or dark field imaging.

[0076] In some examples, the specimen represented by the one or more first images 502 may comprise biological objects. The biological objects may comprise biological colonies of a first cell type. The biological objects may be derived from a reprogramming event in a single cell. Biological objects may be derived from one or more gene editing events in a cell and / or cell population. Biological objects may be derived from transient or permanent transfection events in a cell and / or cell population. Biological objects may be derived from differentiation events in a cell or cell population that may be induced by endogenous cell behavior or exogenous chemical, biological or biophysical stimuli. In some examples, the biological colonies of the first cell type maycomprise iPSC colonies. In some examples, the iPSC colonies are clones of one or more cells (e.g., one or more adult somatic cells), such as a single cell (e.g., a single adult somatic cell). The iPSC colonies may comprise reprogrammed iPSC clones, for example, iPSC clones reprogrammed within about a day and / or about two weeks prior to the one or more first images 502 being captured. Embodiments are contemplated in which the biological objects comprise one or more other types of biological objects other than iPSC colonies, such as such as primary cultures, expanded fibroblasts, connective tissue progenitors, mesenchymal stromal cells, hepatocytes, cardiomyocytes, keratinocytes, neural progenitors, endothelial progenitors, differentiated cell types derived from a starting population of iPSCs or embryonic stem cells (ESCs), ectodermal, endodermal or mesodermal progenitors, and / or other types of biological objects.

[0077] The first image 506 of the one or more second images 508 may comprise a LFOV image. In some examples, the first image 506 may be generated based upon a single image of the one or more first images 502 or a plurality of images of the one or more first images 502 (captured over time, for example). The first image 506 may comprise a montage image representing a view (e.g., whole well view, partial well view, etc.) of the first vessel and / or the specimen.

[0078] Figs. 6A-6F illustrates aspects of the biological object segmentation system 404, in accordance with some embodiments. In some examples, the biological object segmentation system 404 may comprise a biological object segmentation model 604 configured to receive the one or more second images 508 as input and generate, based upon the one or more second images 508, a biological object map indicative of regions, of the specimen, comprising biological objects (e.g., biological colonies of the first cell type). The biological objects may be derived from a reprogramming event in a single cell.

[0079] Fig. 6A illustrates use of the biological object segmentation model 604 to generate the biological object map (shown with reference number 605) based upon an input image 602, which may correspond to a portion 510 (shown in Fig. 5) of the first image 506. Embodiments are contemplated inwhich the input image 602 input to the biological object segmentation model 604 has a view of an entirety or at least the threshold proportion of the first vessel and / or the specimen, wherein the biological object map 605 may be representative of biological objects (e.g., biological colonies of the first cell type) throughout the entirety or at least the threshold proportion of the first vessel and / or the specimen. The biological objects indicated by the biological object map 605 may be derived from a reprogramming event in a single cell. In some examples, portions of the first image 506 may be processed by the biological object segmentation model 604 to generate a plurality of biological object maps associated with portions of the first vessel and / or the specimen, and the plurality of biological object maps which may be combined to generate the biological object map 605 that is representative of biological objects throughout at least a portion of the first vessel and / or the specimen (e.g., the biological object map 605 generated by combining the plurality of biological object maps may be representative of biological objects throughout the entirety and / or at least the threshold proportion of the first vessel and / or the specimen).

[0080] In some examples, the biological object map 605 may be representative of a first biological object 610, a second biological object 612, a third biological object 698, a fourth biological object 616, a fifth biological object 618, a sixth biological object 620, a seventh biological object 622, an eighth biological object 696, and / or a ninth biological object 626. In some examples, the biological objects identified by the biological object map 605 may comprise cells of the first cell type. For example, the biological objects may comprise iPSC colonies.

[0081] The specimen may comprise first biological material (e.g., cells of the first cell type) from which the biological objects (e.g., biological colonies of the first cell type) identified by the biological object map are formed. The specimen may comprise second biological material that may reside in regions outside (e.g., spatially outside) the biological objects. The second biological material may comprise fibroblasts and / or other biological material. In some examples, the first biological material and the second biological material may be adjacent and / or in contact with each other, and / or may be interspersedwithin overlapping regions of the specimen. In some examples, the biological object map may be used to distinguish regions of the specimen comprising the first biological material from regions comprising the second biological material. In some examples, the specimen may comprise one or more other biological materials (in addition to the first biological material and / or the second biological material, for example).

[0082] In some examples, the biological object map 605 may be generated using a trained biological object segmentation model 632 (shown in Fig. 6B) of the biological object segmentation system 404. The trained biological object segmentation model 632 may be trained to identify regions of an input image (e.g., the input image 602 and / or one or more other images of the one or more second images 508) that correspond to the first biological material. The trained biological object segmentation model 632 may be trained to classify a pixel of an input image (e.g., the input image 602 and / or one or more other images of the one or more second images 508) as corresponding to the first biological material or corresponding to a different material different than the first biological material, wherein the classification of the pixel may be used to generate the biological object map 605. The trained biological object segmentation model 632 may be trained to classify a pixel of an input image (e.g., the input image 602 and / or one or more other images of the one or more second images 508) as corresponding to the first biological material or corresponding to second biological material, wherein the classification of the pixel may be used to generate the biological object map 605.

[0083] Fig. 6B illustrates training a machine learning model to generate the trained biological object segmentation model 632, in accordance with some embodiments. In some examples, the training module 418 trains the machine learning model to generate the trained biological object segmentation model 632 using a plurality of images 634 and / or label information 642 associated with the plurality of images 634. The plurality of images 634 may comprise images associated with a plurality of sources (which may include, for example, cell sources, individuals and / or persons). For example, the plurality of images 634 may comprise views of specimens associated with the plurality of sources. The specimens may comprise biological objects, such asbiological colonies of the first cell type. In some examples, the specimens may comprise iPSC colonies associated with the plurality of sources (e.g., each of the specimens may comprise iPSC colonies comprising clones of an adult somatic cell of a person of the plurality of sources).

[0084] iPSC colonies represented by an image of the plurality of images 634 may comprise reprogrammed iPSC clones, for example, iPSC clones reprogrammed within about a day and / or about two weeks prior to the image being captured. In some examples, an image of the plurality of images 634 may have a view of an entirety or at least the threshold proportion (e.g., 75%) of a vessel and / or a specimen. In some examples, an image of the plurality of images 634 may have a view of a portion, of the vessel and / or the specimen, that is smaller than the threshold proportion. The specimens associated with the plurality of sources may comprise the first biological material (e.g., iPSC colonies) and the second biological material (e.g., fibroblasts).

[0085] In some examples, the first label information 642 (e.g., ground truth information) may identify respective segments of the plurality of images 634 that correspond to the first biological material and / or biological objects of the first cell type. Alternatively and / or additionally, the first label information 642 may identify respective segments of the plurality of images 634 that correspond to the second biological material, or biological objects of the second type. Alternatively and / or additionally, the second biological material may be determined (by the training module 630, for example) to be located in regions outside (e.g., spatially outside) respective segments identified by the first label information 642 as corresponding to the first biological material and / or biological objects of the first cell type.

[0086] In some examples, the first label information 642 may comprise a plurality of iPSC pick masks 636 created for clone picking processes performed on the specimens represented by the plurality of images 634. In some examples, one, some or all of the plurality of iPSC pick masks 636 may be created manually (by an expert for use in treatment of a patient, for example). In some examples, one, some or all of the plurality of iPSC pick masks 636 may be generated using a computer. A mask of the plurality of iPSC pick masks 636 may identify one or more regions, of a specimenrepresented by an image of the plurality of images 634, that was selected for a clone picking process. In some examples, the first label information 642 may comprise a plurality of iPSC masks 638 generated based upon the plurality of iPSC pick masks 636. In some examples, the first label information 642 may comprise a plurality of fibroblast masks 640. A mask of the plurality of fibroblast masks 640 may identify one or more regions, of a specimen represented by an image of the plurality of images 634, that comprises fibroblasts.

[0087] In some examples, the plurality of images 634 may be selected to include one or more processed images that underwent the one or more first image processing operations and / or one or more images that did not undergo the one or more first image processing operations. In some examples, by selecting the plurality of images 634 may be selected to include the one or more processed images and the one or more images that did not undergo the one or more first image processing operations, the trained biological object segmentation model 632 may be generated with increased robustness to make classifications for images of varying processing and / or quality levels with increased accuracy.

[0088] In some examples, the biological object segmentation system 404 may screen for features, such as texture and / or morphological features and / or other types of features, for the trained biological object segmentation model 632 to use in differentiating regions of images with the first biological material (and / or biological objects of the first cell type) from regions of images with the second biological material and / or other material. For example, the biological object segmentation system 404 may perform a feature extraction process to extract a first plurality of features that are candidates for use by the trained biological object segmentation model 632 to differentiate between regions of images with the first biological material (and / or biological objects of the first cell type) from regions of images with the second biological material.

[0089] The feature extraction process may comprise extracting features comprising texture and / or morphological features and / or other features from images (e.g., the plurality of images 634 and / or other images). In some examples, the features may comprise radiomics features and / or customfeatures. In some examples, the radiomics features may comprise features (e.g., standard radiomics features) defined in a radiomics package, such as first order features, shape features, gray level co-occurrence matrix (GLCM) features, gray level size zone matrix (GLSZM) features, gray level run length matrix (GLRLM) features, neighboring gray tone difference matrix (NGTDM) features, and / or gray level dependence matrix (GLDM) features. In some examples, the radiomics features may comprise a first quantity (e.g., 93) of features extracted across a second quantity (e.g., 15) of different preprocessing configurations (with differences in at least one of intensity scaling, spatial downsampling, combinations, etc.), resulting in features amounting to a product of the first quantity and the second quantity. In some examples, the feature extraction process may comprise applying Gabor filters to extract a quantity (e.g., 60) of features by varying parameters such as frequency, angulation, and / or blurring. In some examples, the feature extraction process may comprise applying one or more custom filtering techniques to extract custom features (e.g., 108 custom features). In some examples, the custom features may be based upon relative frequency of local minima in x-direction, relative frequency of local minima in y-direction, and / or both local minima in x-direction and local minima in y-direction with an intensity threshold after image blurring.

[0090] In some examples, the biological object segmentation system 404 may perform a feature selection process to select a second plurality of features, from the first plurality of features, for use by the trained biological object segmentation model 632 to differentiate between regions of images with the first biological material (and / or biological colonies of the first cell type) from regions of images with the second biological material. In some examples, the feature selection process may comprise selecting, from the first plurality of features, a subset of features (e.g., the second plurality of features) that are most discriminating between the first biological material and the second biological material. In some examples, the first plurality of features may comprise greater than 1 ,500 features (e.g., texture and / or morphological features and / or other features) and / or the second plurality of features maycomprise less than 100 features (e.g., texture and / or morphological features and / or other features).

[0091] The feature selection process may comprise applying a decision tree-based method to predict whether a region of the specimen comprises the first biological material (e.g., iPSCs) or the second biological material (e.g., fibroblasts) based upon a given feature. In some examples, the feature selection process may be repeated multiple times using different initializations and / or different numbers of estimators (e.g., 25, 50, and / or 100 estimators). In some examples, in each repetition, a quantity (e.g., 50) of top-performing features may be awarded a point. In some examples, a total of k (e.g., 24 or other quantity) features that received the greatest number of points across the repetitions may be selected. In some examples, the selected features (e.g., the second plurality of features) may be used by the trained biological object segmentation model 632 to differentiate morphology of the first biological material (e.g., iPSC colonies) from the morphology of the second biological material (e.g., fibroblasts).

[0092] Fig. 6C illustrates an operation of the feature selection process, in accordance with some embodiments. A decision module 656 provided with images 652 may attempt to distinguish, based upon a candidate feature 654 of the first plurality of images 652, between images showing the first biological material (e.g., iPSCs) and the second biological material (e.g., fibroblasts). In some examples, the decision module 656 may classify images 658 as corresponding to the first biological material (e.g., iPSCs) and may classify images 660 as corresponding to the second biological material (e.g., fibroblasts). In some examples, whether to include the candidate feature 654 in the second plurality of features may be determined based upon a performance (e.g., accuracy) of the classifications of the images 652.

[0093] Figs. 6D-6F illustrate data structures associated with respective subsets of features of the second plurality of features (selected for use by the trained biological object segmentation model 632 to differentiate morphology of the first biological material from morphology of the second biological material), in accordance with some embodiments. Fig. 6D illustrates data structures 680 associated with a first subset of features of the second pluralityof features, in accordance with some embodiments. Fig. 6E illustrates data structures 682 associated with a second subset of features of the second plurality of features, in accordance with some embodiments. Fig. 6F illustrates data structures 684 associated with a third subset of features of the second plurality of features, in accordance with some embodiments.

[0094] In some examples, each of the data structures in Figs. 6D-6F is representative of a comparison between the first biological material (e.g., iPSCs) and the second biological material (e.g., fibroblasts) for the corresponding feature. In some examples, each of the data structures may include a white portion representing the second biological material and a black portion representing the first biological material. In some examples, the diagrams may visually illustrate a statistical distribution (e.g., a box plot or other data visualization) of the respective feature values across samples of the first biological material and the second biological material. In some examples, the diagrams in Figs. 6D-6F may support the use of the corresponding features by the trained biological object segmentation model 632 to differentiate between the morphology of the first biological material and the morphology of the second biological material.

[0095] The second plurality of features may comprise a first feature (e.g., sigma-1 _thresh-45_y_min) associated with a Laplacian of Gaussian (LoG) filter with a sigma value of 1 , a thresholding operation (associated with a threshold pixel intensity of 45, for example) and / or a minimum coordinate along a y-axis.

[0096] The second plurality of features may comprise a second feature (e.g., sigma-1_thresh-45_x_min) associated with a LoG filter with a sigma value of 1 , a thresholding operation (associated with a threshold pixel intensity of 45, for example) and / or a minimum coordinate along an x-axis.

[0097] The second plurality of features may comprise a third feature (e.g., orig_ds1_orginal_glrlm_GrayLevelNonUniformity) associated with a GLRLM- based texture analysis performed on a first original image dataset (e.g., dataset 1 ). The third feature may quantify a non-uniformity of gray-level intensities within a defined region of interest by evaluating a distribution and frequency of runs of consecutive pixels sharing a same gray level. The thirdfeature comprising a higher GrayLevelNonllniformity value may indicate greater heterogeneity in gray-level patterns, while the third feature comprising a lower value may indicate a more uniform texture and / or morphology, potentially reflecting underlying tissue characteristics or pathological variability.

[0098] The second plurality of features may comprise a fourth feature (e.g., orig_ds2_original_glcm_lmc1 ) associated with a Gray Level Co-occurrence Matrix (GLCM)-based texture analysis performed on an original image dataset (e.g., dataset 2). The fourth feature, which may be referred to as Low- Magnitude Component 1 (LMC1 ), may capture a specific aspect of a spatial relationship between pixel intensities by analyzing how often pairs of gray levels co-occur at a defined distance and orientation. The LMC1 value may reflect local texture patterns and contrast variations within a region of interest, with potential implications for identifying subtle tissue differences or structural irregularities in medical imaging data.

[0099] The second plurality of features may comprise a fifth feature (e.g., orig_ds4_original_glrlm_RunEntropy) associated with a GLRLM texture analysis performed on an original image downsampled by a factor of four.The fifth feature may comprise a RunEntropy metric, which may quantify a randomness or complexity of a run length distribution within a region of interest, thereby reflecting a heterogeneity of texture patterns present in image data.

[0100] The second plurality of features may comprise a sixth feature (e.g., orig_ds2_original_ngtdm_Coarseness) associated with a neighborhood gray-tone difference matrix (NGTDM) analysis performed on an original image downsampled by a factor of two. The sixth feature may comprise a Coarseness metric, which may quantify a spatial rate of change in intensity values, where higher values typically may indicate more homogeneous and less textured regions within the original image.

[0101] The second plurality of features may comprise a seventh feature (e.g., sigma-1_thresh-45_x_max) associated with a LoG filter with a sigma value of 1 , a thresholding operation (associated with a threshold pixel intensity of 45, for example), and / or a maximum coordinate along an x-axis. Theseventh feature may represent a furthest horizontal extent of structures identified after edge detection and intensity thresholding, providing information on a spatial distribution and potential localization of image regions of interest.

[0102] The second plurality of features may comprise an eighth feature (e.g., orig-g064_ds1_original_glcm_lmc1 ) associated with a gray level cooccurrence matrix (GLCM) analysis performed on an original image that may be normalized using gray-level binning (e.g., 64 gray levels, denoted as g064) and downsampled by a factor of one. The eighth feature may comprise a feature Imc1 , which may refer to a low-moment coefficient or a related statistical measure derived from the GLCM, and may capture localized texture patterns or intensity transitions within the original image that may reflect underlying structural or pathological heterogeneity.

[0103] The second plurality of features may comprise a ninth feature (e.g., orig_ds4_original_ngtdm_Coarseness) associated with a neighborhood gray-tone difference matrix (NGTDM) analysis performed on an original image that may be downsampled by a factor of four. The ninth feature may comprise a Coarseness metric, which may reflect a level of spatial rate change in gray-tone intensity values, with higher values indicating more uniform or less textured regions. The ninth feature may serve to quantify a degree of homogeneity within a given region of interest, potentially capturing relevant tissue characteristics or image-based phenotypes.

[0104] The second plurality of features may comprise a tenth feature (e.g., orig_ds1_original_glrlm_RunEntropy) associated with a GLRLM analysis performed on an original image that may be downsampled by a factor of one. The tenth feature may comprise a RunEntropy metric, which may quantify an uncertainty or randomness in a distribution of run lengths and gray levels, thereby capturing a complexity or heterogeneity of texture patterns within the original image. The tenth feature may be indicative of finegrained structural variability present in a region of interest.

[0105] The second plurality of features may comprise an eleventh feature (e.g., orig_ds1_original_glcm_lmc1 ) associated with a gray level cooccurrence matrix (GLCM) analysis performed on an original image that may be downsampled by a factor of one. The eleventh feature may comprise aImc1 metric, which may refer to a first-order low moment coefficient or a related texture descriptor derived from a GLCM, capturing local intensity dependencies and textural uniformity within a region of interest. The eleventh feature may provide insight into a structural regularity or granularity present in the image data.

[0106] The second plurality of features may comprise a twelfth feature (e.g., orig_g064_ds1_original_glszm_ZonePercentage) associated with a gray level size zone matrix (GLSZM) analysis performed on an original image that may be quantized to 64 gray levels (denoted by g064) and downsampled by a factor of one. The twelfth feature may comprise a ZonePercentage metric, which may reflect a proportion of homogeneous zones relative to a total number of possible zones within a region of interest, thereby capturing a prevalence of uniform intensity regions and contributing to a characterization of tissue texture or structural patterns.

[0107] The second plurality of features may comprise a thirteenth feature (e.g., orig-g064_ds4_original_glszm_SizeZoneNonUniformity) associated with a gray level size zone matrix (GLSZM) analysis performed on an original image that may be quantized to 64 gray levels (as indicated by g064) and downsampled by a factor of four. The thirteenth feature may comprise a SizeZoneNonllniformity metric, which may measure a variability in a size of homogeneous zones across the original image, with higher values indicating greater heterogeneity in zone sizes. The thirteenth feature may reflect irregularity or complexity in tissue texture, potentially serving as an indicator of underlying structural or pathological variation.

[0108] The second plurality of features may comprise a fourteenth feature (e.g., orig-g128_ds4_original_glcm_lmc2) associated with a gray level co-occurrence matrix (GLCM) analysis performed on an original image that may be quantized to 128 gray levels (denoted by g128) and downsampled by a factor of four. The fourteenth feature may comprise a Imc2 metric, which may represent a second-order low moment coefficient or a related textural and / or morphological feature derived from the GLCM, capturing more nuanced spatial relationships between gray levels within a region of interest.The fourteenth feature may provide insight into a fine-grained heterogeneity and complexity of tissue structure.

[0109] The second plurality of features may comprise a fifteenth feature (e.g., orig ds1 original glcm Inversevariance) associated with a gray level co-occurrence matrix (GLCM) analysis performed on an original image that may be downsampled by a factor of one. The fifteenth feature may comprise an Inversevariance metric, which may quantify a local homogeneity of gray level intensities, with higher values indicating less contrast and more uniform neighboring pixel intensities within a region of interest. The fifteenth feature may capture subtle texture and / or morphology characteristics relevant to structural consistency or pathological uniformity.

[0110] The second plurality of features may comprise a sixteenth feature (e.g., orig_g128_ds2_original_glrlm_RunEntropy) associated with a GLRLM analysis performed on an original image that may be quantized to 128 gray levels (denoted by g128) and downsampled by a factor of two. The sixteenth feature may comprise a RunEntropy metric, which may capture a randomness or complexity in a distribution of run lengths and gray levels, with higher values indicating greater textural and / or morphological heterogeneity. The sixteenth feature may be used to characterize fine-grained structural variability within the original image, which may be relevant to identifying patterns associated with specific tissue types or pathologies.

[0111] The second plurality of features may comprise a seventeenth feature (e.g., orig_ds4_original_glcm_lmc1 ) associated with a gray level cooccurrence matrix (GLCM) analysis performed on an original image that may be downsampled by a factor of four. The seventeenth feature may comprise a Imc1 metric, which may represent a first-order low moment coefficient or a related statistical descriptor derived from the GLCM, capturing a degree of uniformity or correlation between neighboring pixel intensities. The seventeenth feature may provide insights into an underlying texture patterns and spatial organization present within a region of interest.

[0112] The second plurality of features may comprise an eighteenth feature (e.g., sigma- 1_thresh-45_y_max) associated with a LoG filter with a sigma value of 1 , a thresholding operation (associated with a threshold pixelintensity of 45, for example), and / or a maximum coordinate along a y-axis. The eighteenth feature may represent an uppermost spatial extent of regions identified through LoG-based edge detection and intensity thresholding, providing information on a vertical distribution and localization of prominent structures within an original image.

[0113] The second plurality of features may comprise a nineteenth feature (e.g., orig_g128_ds1_original_gldm_DependenceNonllniformityNormalized) associated with a GLDM analysis performed on an original image that may be quantized to 128 gray levels (denoted by g128) and downsampled by a factor of one. The nineteenth feature may comprise a DependenceNonUniformityNormalized metric, which may measure a variability of dependence sizes normalized against a total number of dependencies, with lower values indicating more uniform dependence structures. The nineteenth feature may capture a degree of structural regularity or homogeneity within a region of interest, reflecting underlying tissue consistency or variation.

[0114] The second plurality of features may comprise a twentieth feature (e.g., orig_ds2_original_gldm_DependenceVariance) associated with a GLDM analysis performed on an original image that may be downsampled by a factor of two. The twentieth feature may comprise a Dependencevariance metric, which may quantify a variance in sizes of dependent pixel groups, capturing a spread or diversity of local intensity dependencies within a region of interest. The twentieth feature may provide insight into a degree of textural heterogeneity, potentially reflecting complex or irregular tissue structures.

[0115] The second plurality of features may comprise a twenty-first feature (e.g., sigma- 1_thresh-45_2d_local_max) associated with a LoG filter with a sigma value of 1 , a thresholding operation (associated with a threshold pixel intensity of 45, for example), and / or an identification of two-dimensional local maxima within a filtered and thresholded image. The twenty-first feature may represent prominent peaks in pixel intensity that persist after edgeenhancement and thresholding, potentially corresponding to localized structures or salient regions of interest within an image domain.

[0116] The second plurality of features may comprise a twenty-second feature (e.g., sigma-1 thresh-150 y min) associated with a LoG filter with a sigma value of 1 , a thresholding operation (associated with a threshold pixel intensity of 150, for example), and / or a minimum coordinate along a y-axis. The twenty-second feature may denote a lowest vertical position of regions identified through edge-enhanced and intensity-thresholded image processing, potentially reflecting a spatial origin of significant structures within an image frame.

[0117] The second plurality of features may comprise a twenty-third feature (e.g., orig_ds4_original_glrlm_GrayLevelNonUniformity) associated with a GLRLM analysis performed on an original image that may be downsampled by a factor of four. The twenty-third feature may comprise a GrayLevelNonllniformity metric, which may quantify a variability in gray level values across runs within a matrix, with higher values indicating less uniform distribution of gray levels. The twenty-third feature may serve as an indicator of textural heterogeneity and may be relevant for assessing irregularities or inconsistencies in image intensity patterns within a region of interest.

[0118] The second plurality of features may comprise a twenty-fourth feature (e.g., orig- g064_ds1_original_glrlm_RunLengthNonUniformityNormalized) associated with a gray-level run length matrix (GLRLM) analysis performed on an original image, wherein the original image has undergone a downsampling operation (e.g., by a factor of 1 ) and a preprocessing step labeled g064. The twentyfourth feature may quantify a non-uniformity of run lengths across the original image, normalized by a total number of runs, and may be indicative of textural homogeneity within a region of interest.

[0119] Figs. 7A-7B illustrate aspects of the cell targeting system 406, in accordance with some embodiments. In some examples, the cell targeting system 406 may comprise one or more computers. In some examples, the cell targeting system 406 may comprise a biological object selection module 702. Fig. 7A illustrates use of the biological object selection module 702 todetermine one or more target regions of the specimen based upon the biological object map 605, in accordance with some embodiments. In some examples, the biological object selection module 702 may generate a target region map 705 indicative of the one or more target regions. In some examples, the colony evaluation system 401 may comprise a display that displays a representation of the target region map 705 and / or the biological object map 605. In some examples, the one or more target regions may comprise one or more biological objects, of the biological objects indicated by the biological object map 605, selected for one or more cell operations such as selective isolation (e.g., harvesting and / or picking), biopsy, selective removal (e.g., weeding), transplantation, cell expansion, deposition, injection, etc. In some examples, a target region may be defined as at least a portion of a biological object that satisfies one or more defined selection criteria. The identification of target regions may provide a basis for determining subsequent cell operations. For example, a target region may be selected for a selective isolation process and the selective isolation process may be performed to isolate cells of the target region. Alternatively and / or additionally, a target region may be selected for a selective removal process and the selective removal process may be performed to remove cells outside of the target region.

[0120] Fig. 7B illustrates determining scores and / or rankings associated with biological objects (e.g., IPSC colonies) indicated by the biological object map 605. In some examples, the biological object selection module 702 may comprise a feature extraction module 732 to determine feature information 734 comprising sets of features (e.g., sets of one or more features) associated with biological objects based upon the biological object map 605. The biological object selection module 702 may comprise a biological object (e.g., iPSC) scoring module 736 to determine scores associated with the biological objects and / or to rank the biological objects relative to each other based upon the scores. In some examples, the biological object scoring module 736 may output scoring information 738 indicative of the scores and / or the rankings. The one or more target regions may be determined based upon the scores and / or the rankings. In someexamples, features of the feature information 734 may be used in a series of sequential decisions and / or in combination using a computational model of the biological object scoring module 736 to determine the scoring information 738.

[0121] In some examples, the feature information 734 comprises a set of features for each biological object of one, some or all biological objects (e.g., biological colonies of the first cell type) identified by the biological object map 605. For example, the feature information 734 may comprise a first set of features (e.g., a first set of one or more features) associated with the first biological object 610 and / or a second set of features (e.g., a second set of one or more features) associated with the second biological object 612 In some examples, the feature extraction module 732 performs one or more image processing operations on the biological object map 605 to determine a set of features associated with a biological object. Fig. 7C illustrates a data structure 740, generated by the feature extraction module 732, indicative of the first set of features associated with the first biological object 610 and / or the second set of features associated with the second biological object 612.

[0122] The first set of features may comprise one or more first boundary attributes of the first biological object 610, such as a boundary shape (e.g., iPSC colony shape) of the first biological object 610. The first set of features may comprise a first size of the first biological object 610, such as an area (in units of pixels and / or other units of measure, for example) of the first biological object 610. The first set of features may comprise a first maximum length Bi of the first biological object 610 and / or a first minimum length Ai of the first biological object 610. The first set of features may comprise a first aspect ratio of the first biological object 610. The first aspect ratio may be determined based upon the first maximum length Bi and / or the first minimum length Ai (e.g., by dividing the first maximum length Bi by the first minimum length Ai). The first set of features may comprise a first perimeter of the first biological object 610. The first set of features may comprise a first circularity of the first biological object 610. The first set of features may comprise one or more first distances between the first biological object 610 and one or more other biological objects. The one or more firstdistances may comprise a distance 708 between the first biological object 610 and the ninth biological object 626. The first set of features may comprise a one or more interior attributes of the first biological object 610. The first set of features may comprise a first morphological profile “Morphometrics-1 ” indicative of one or more first textural and / or morphological features associated with the first biological object 610. The one or more first textural and / or morphological features indicated by the first morphological profile may comprise one, some or all of the first plurality of features and / or one, some or all of the second plurality of features.

[0123] The second set of features may comprise one or more second boundary attributes of the second biological object 612, such as a boundary shape (e.g., iPSC colony shape) of the second biological object 612. The second set of features may comprise a second size of the second biological object 612, such as an area (in units of pixels and / or other units of measure, for example) of the second biological object 612. The second set of features may comprise a second maximum length B2 of the second biological object 612 and / or a second minimum length A2 of the second biological object 612. The second set of features may comprise a second aspect ratio of the second biological object 612. The second aspect ratio may be determined based upon the second maximum length B2 and / or the second minimum length A2 (e.g., by dividing the second maximum length B2 by the second minimum length A2). The second set of features may comprise a second perimeter of the second biological object 612. The second set of features may comprise a second circularity of the second biological object 612. The second set of features may comprise one or more second distances between the second biological object 612 and one or more other biological objects. The second set of features may comprise a one or more interior attributes of the second biological object 612. The second set of features may comprise a second morphological profile “Morphometrics-2” indicative of one or more second textural and / or morphological features associated with the second biological object 612. The one or more second textural and / or morphological features indicated by the second morphological profile may comprise one, some or allof the first plurality of features and / or one, some or all of the second plurality of features.

[0124] In some examples, the scoring information 738 may comprise a first set of scores (e.g., a first set of one or more scores) associated with the first biological object 610 and / or a second set of scores (e.g., a second set of one or more scores) associated with the second biological object 612. The first set of scores may comprise one or more first feature-level scores associated with one or more features of the first set of features, and / or a first aggregate score associated with the first biological object 610. In some examples, the first aggregate score may be determined based upon the one or more first feature-level scores (such as by combining the one or more first feature-level scores to determine the first aggregate score, for example).

[0125] In some examples, the one or more first feature-level scores may comprise a first boundary attribute score determined based upon the first boundary attribute of the first biological object 610, a first size score determined based upon the first size of the first biological object 610, a first aspect ratio score determined based upon the first aspect ratio of the first biological object 610, a first perimeter score determined based upon the first perimeter of the first biological object 610, a first circularity score determined based upon the first circularity of the first biological object 610, and / or a first proximity score determined based upon the one or more first distances.

[0126] The second set of scores may comprise one or more second feature-level scores associated with one or more features of the second set of features, and / or a second aggregate score associated with the second biological object 612. In some examples, the second aggregate score may be determined based upon the one or more second feature-level scores (such as by combining the one or more first second-level scores to determine the second aggregate score, for example).

[0127] In some examples, the one or more second feature-level scores may comprise a second boundary attribute score determined based upon the second boundary attribute of the second biological object 612, a second size score determined based upon the second size of the first biological object 612, a second aspect ratio score determined based upon the second aspectratio of the second biological object 612, a second perimeter score determined based upon the second perimeter of the second biological object 612, a second circularity score determined based upon the second circularity of the first biological object 612, and / or a second proximity score determined based upon the one or more second distances.

[0128] In some examples, the one or more target regions may comprise one or more first biological objects, of the biological objects indicated by the biological object map 605, selected for a first cell operation. In some examples, the first cell operation may comprise a biopsy operation, a selective isolation operation (e.g., clone picking operation), a sampling operation, a harvesting operation, a cell expansion operation, a deposition operation, an injection operation, and / or one or more other cell operations. In some examples, the one or more first biological objects may be selected based upon a determination that the one or more first biological objects are of a suitable quality to undergo the first cell operation.

[0129] In some examples, the first set of scores may be compared with a set of threshold scores (e.g., a set of one or more threshold scores), respectively, to determine whether to include the first biological object 610 in the one or more first biological objects and / or the one or more target regions (to undergo the first cell operation, for example). In some examples, one or more thresholds of the set of threshold scores may be dynamic. For example, the one or more thresholds may be controlled and / or adjusted based upon one or more conditions associated with the specimen, such as at least one of a quantity of biological objects (e.g., biological colonies of the first cell type) detected in the specimen (e.g., the threshold may be adjusted to be more lenient based upon a greater quantity of biological colonies of the first cell type detected in the specimen), a density of biological colonies of the first cell type detected in the specimen, etc. In some examples, one or more thresholds of the set of threshold scores may each correspond to a threshold range that may be determined to be met based upon a determination that a corresponding score is within the threshold range. In some examples, one or more thresholds of the set of threshold scores may each correspond to a threshold value that may be determined to be met based upon adetermination that a corresponding score is greater than or less than the threshold value.

[0130] In some examples, the first biological object 610 may be included in the one or more first biological objects and / or the one or more target regions (to undergo the first cell operation, for example) based upon a determination that one or more scores of the first set of scores meets one or more respective thresholds of the set of threshold scores. The first biological object 610 may be included in the one or more first biological objects and / or the one or more target regions (to undergo the first cell operation, for example) based upon a determination that at least X scores of the first set of scores meet one or more respective thresholds of the set of threshold scores, wherein X may be predefined and / or adjustable based upon the one or more conditions associated with the specimen (e.g., X may be decreased to be more lenient based upon a greater quantity of biological objects of the first cell type detected in the specimen). In some examples, based upon one or more biological objects (e.g., iPSC colonies) each having a defined quantity of scores and / or features that meet respectively defined thresholds, one or more defined colonies and / or cellular regions may be selected for sampling, in whole or in part (e.g., “biopsied”) to allow further testing using non-destructive or destructive methods, while leaving at least a part of the one or more defined colonies and / or cellular regions in place (e.g., in the first vessel).

[0131] In some examples, the biological object scoring module 736 may compare a feature of the first set of features with a threshold (e.g., a threshold range and / or a threshold value) and / or determine a feature-level score associated with the feature based upon the comparison. In some examples, the biological object scoring module 736 may compare the first size with a first size threshold (e.g., a size threshold range and / or a size threshold value) and / or determine the first size score based upon the comparison. In some examples, the biological object scoring module 736 may flag the first biological object as unsuitable for inclusion in the one or more first biological objects (and / or the one or more target regions) in response to determining that the first size is less than the first size threshold (e.g., 5,000 pixels or other value).

[0132] In some examples, the biological object scoring module 736 may compare the first aspect ratio with a first aspect ratio threshold (e.g., an aspect ratio threshold range and / or a aspect ratio threshold value) and / or determine the first aspect ratio score based upon the comparison. In some examples, the biological object scoring module 736 may flag the first biological object as unsuitable for inclusion in the one or more first biological objects (and / or the one or more target regions) in response to determining that the first aspect ratio is greater than the first aspect ratio threshold (e.g., 1 .5 or other value). In some examples, an aspect ratio being greater than the first aspect ratio threshold may indicate a greater likelihood that a corresponding biological object is a dumbbell colony comprising multiple biological colonies of the first type grown into each other.

[0133] In some examples, the biological object scoring module 736 may compare the first circularity with a first circularity threshold (e.g., a circularity threshold of 0.75 on a scale in which a circularity of 1 corresponds to a perfect circle) and / or determine the first circularity score based upon the comparison. In some examples, the biological object scoring module 736 may flag the first biological object as unsuitable for inclusion in the one or more first biological objects (and / or the one or more target regions) in response to determining that the first circularity is less than the first circularity threshold (e.g., 1 .5 or other value). In some examples, a circularity being less than the first circularity threshold may indicate a greater likelihood that a corresponding biological object is unsuitable for the first cell operation.

[0134] In some examples, the biological object scoring module 736 may rank the biological objects (e.g., biological colonies of the first cell type identified by the biological object map 605) relative to each other based upon the sets of scores associated with the biological objects. In some examples, the cell targeting system 406 may select the top Y ranked biological objects from among the biological objects for inclusion in the one or more target regions, wherein Y may be predefined and / or adjustable based upon the one or more conditions associated with the specimen. Referring back to Fig. 7A, the biological object selection module 702 may select the first biological object 610, the fourth biological object 616, the seventh biological object 622, and / orthe ninth biological object 626 for inclusion in the one or more first biological objects (and / or the one or more target regions). In some examples, the second biological object 612 may not be included in the one or more first biological objects (and / or the second biological object 612 may be flagged as a potential failure and / or as unsuitable for the first cell operation) in response to determination that the second aspect ratio (e.g., 2.29) is greater than the aspect ratio threshold (e.g., 1 .5 or other value), which may indicate a greater likelihood that a corresponding biological object is a dumbbell colony comprising multiple biological colonies of the first type (e.g., multiple iPSC colonies) grown into each other.

[0135] In some examples, the first cell operation may be triggered in response to determining the one or more target regions. The cell targeting system 406 may provide an indication of the one or more target regions (e.g., the one or more first biological objects) to the first cell processing system 408 in response to determining the one or more target regions. In some examples, in response to the indication of the one or more target regions, the first cell processing system 408 may generate instructions to perform the first cell operation. In some examples, the instructions may comprise computer- readable instructions that may be executed by a computer and / or cell handling equipment (e.g., equipment for cell picking, transferring cells to new locations, etc.) to perform the first cell operation. For example, the first cell processing system 408 may transmit the computer-readable instructions to one or more devices to facilitate the first cell operation. In some examples, the instructions may comprise human-readable instructions that may be displayed for a user (via the display of the colony evaluation system 401 , for example). In some examples, the first cell processing system 408 may comprise one or more computers for determining and / or triggering the first cell operation based upon the biological object map 605 and / or generating the instructions. The first cell processing system 408 may comprise the cell handling equipment for carrying out the first cell operation.

[0136] In some examples, the first cell operation may comprise transferring a sample of cells (e.g., at least a portion of the one or more first biological objects) from the one or more target regions to one or morelocations for archiving, testing, processing, cell expansion and / or other operation. In some examples, the first cell operation may comprise a selective isolation operation (e.g., a selective transplantation of desired cells), which may comprise transferring the sample of cells to one new location. Alternatively and / or additionally, the first cell operation may comprise subdividing the sample of cells and transferring portions of the sample of cells to multiple locations, which may share similar environments and / or intended purposes (e.g., for expansion and / or further growth under standard culture conditions). Alternatively and / or additionally, the multiple locations may have a plurality of environments or purposes, for example, to test the cells from a selected colony source under multiple conditions of differentiation or cellular response (at a single point in time, for example). In some examples, a clone may be subdivided into multiple locations to support testing across multiple pathways and / or timepoints. In some examples, the first cell operation may comprise one or more testing processes comprising at least one of karyotyping, whole genome sequencing, analysis of copy number variation, targeted sequencing, SNIP analysis, PCR, ELIZA, RNAseq, single cell RNAseq, proteome, differentiation in a new media, staining analysis of surface markers, proteome analysis, nuclear chromatin analysis, ATAC, lipidome analysis, glycome analysis, tumorigenicity assay, etc. For example, the one or more testing processes may be performed with a biopsy of the first cell operation and / or with a distribution of a single clone to one or more locations.

[0137] Figs. 8A-8C illustrate cell picking scenarios (e.g., image-guided precision microfluidic picking based upon the biological object map 605 and / or the target region map 705) of the selective isolation operation (e.g., the cell picking operation), in accordance with some embodiments. Solid-line circles in representations of Figs. 8A-8C represent pick sites, and dashed-line circles represent sites where a measurement tool of picking equipment that performs the selective isolation operation measures difference in elevation between the picking equipment and the specimen (or the first vessel). In some examples, the solid-line circles and / or the dashed-line circles have diameters of about 500 micrometers. In some examples, pick sites identified in Figs. 8A-8C maybe determined based upon the one or more target regions. For example, the pick sites may be within the one or more target regions (such that the selective isolation operation comprises transferring cells in the one or more target regions to one or more other locations, for example).

[0138] Fig. 8A illustrates a before representation 804 and an after representation 806 of the specimen in a first cell picking scenario 802, in accordance with some embodiments. The before representation 804 shows the specimen prior to the selective isolation operation and / or the after representation 806 shows the specimen after the selective isolation operation. The first cell picking scenario 802 may be associated with four pick sites, a cell pick efficiency of about 103%, and / or a precision of about 99%.

[0139] Fig. 8B illustrates a before representation 814 and an after representation 816 of the specimen in a second cell picking scenario 812, in accordance with some embodiments. The before representation 814 shows the specimen prior to the selective isolation operation and / or the after representation 816 shows the specimen after the selective isolation operation. The second cell picking scenario 812 may be associated with seven pick sites, a cell pick efficiency of about 107%, and / or a precision of about 96%.

[0140] Fig. 8C illustrates a before representation 824 and an after representation 826 of the specimen in a third cell picking scenario 822, in accordance with some embodiments. The before representation 824 shows the specimen prior to the selective isolation operation and / or the after representation 826 shows the specimen after the selective isolation operation. The third cell picking scenario 822 may be associated with 32 pick sites, a cell pick efficiency of about 98%, and / or a precision of about 96%.

[0141] In some examples, the cell targeting system 406 may determine one or more removable regions of the specimen based upon the biological object map 605 and / or the target region map 705, in accordance with some embodiments. In some examples, the biological object selection module 702 may generate a removable region map indicative of the one or more removable regions. In some examples, a representation of the removable region map may be displayed (via the display of the colony evaluation system 401 , for example). In some examples, the one or more removable regionsmay comprise one or more regions comprising the second biological material (e.g., fibroblast), one or more biological colonies of the first cell type that are flagged as a potential failure and / or as unsuitable for a cell operation (e.g., the first cell operation), and / or one or more biological colonies that are determined to have a potential of negatively impacting one or more other biological colonies.

[0142] In some examples, a selective removal operation (e.g., removal of undesired cells) may be performed by the first cell processing system 408 based upon the one or more removable regions. For example, the selective removal operation may comprise removing biological material (e.g., less desirable colonies and / or regions of cells) from the one or more removable regions. The biological material removed via the selective removal operation may comprise iPSCs and / or fibroblasts. In some examples, performing the selective removal operation enhances culture quality, reduces overcrowding, and / or mitigates unwanted differentiation. In some examples, the selective removal operation is performed using a mechanical, microfluidic, and / or laserbased tool, and may be executed in whole or in part, allowing selective removal while preserving adjacent desirable colonies and / or cells. Fig. 9A illustrates a representation 902 of the specimen and / or the first vessel prior to the selective removal operation, in accordance with some embodiments. Fig. 9B illustrates a representation 904 of the specimen and / or the first vessel after the selective removal operation, in accordance with some embodiments.

[0143] In some examples, the cell targeting system 406 may determine the one or more removable regions based upon the feature information 734 and / or the scoring information 738. In some examples, the second biological object 612 may be included in the one or more removable regions based upon a determination that one or more scores of the second set of scores do not meet one or more respective thresholds of the set of threshold scores. The second biological object 612 may be included in the one or more removable regions based upon a determination that at least Z scores of the second set of scores do not meet one or more respective thresholds of the set of threshold scores, wherein Z may be predefined and / or adjustable based upon the one or more conditions associated with the specimen.

[0144] In some examples, the biological object scoring module 736 may compare the second aspect ratio with the first aspect ratio threshold and / or may select the second biological object for inclusion in the one or more removable regions in response to determining that the second aspect ratio is greater than the first aspect ratio threshold. In some examples, the biological object scoring module 736 may compare the second circularity with the first circularity threshold and / or may select the second biological object for inclusion in the one or more removable regions in response to determining that the second circularity is less than the first circularity threshold (e.g., 1 .5 or other value).

[0145] In some examples, the biological object scoring module 736 may rank the biological objects (e.g., biological colonies of the first cell type identified by the biological object map 605) relative to each other based upon the sets of scores associated with the biological objects. In some examples, the cell targeting system 406 may select the lowest P ranked biological objects from among the biological objects for inclusion in the one or more removable regions, wherein P may be predefined and / or adjustable based upon the one or more conditions associated with the specimen.

[0146] In some examples, the cell targeting system 406 may determine one or more first regions (e.g., fibroblast regions) outside (e.g., spatially outside) the biological objects (e.g., biological colonies of the first cell type, such as iPSC colonies) identified by the biological object map 605, and / or may include the one or more first regions in the one or more removable regions. For example, the one or more first regions may correspond to regions, of the specimen, comprising the second biological material (e.g., fibroblast). The one or more first regions may be included in the one or more removable regions based upon a determination that the one or more first regions are outside the biological objects (e.g., biological colonies of the first cell type, such as iPSC colonies) identified by the biological object map 605.

[0147] In some examples, the cell targeting system 406 may determine a set of removable biological objects based upon the scoring information 738. For example, the set of removable biological objects may comprise one or more undesirable biological objects of the first cell type (that were notincluded in the one or more target regions, for example). With respect to the target region map 705 shown in Fig. 7A, the set of removable biological objects may comprise the second biological object 612, the third biological object 698, the fifth biological object 618, the sixth biological object 620, and / or the eighth biological object 696.

[0148] In some examples, the cell targeting system may determine the distance 708 between the first biological object 610 and the ninth biological object 626, and / or may compare the distance 708 with a threshold distance. In some examples, in response to the distance 708 being less than the threshold distance, the first biological object 610 or the ninth biological object 626 may be selected for inclusion in the set of removable biological objects. In some examples, the distance 708 being less than the threshold distance may indicate an increased likelihood that the first biological object 610 and the ninth biological object 626 grow into each other. In some examples, in response to the distance 708 being less than the threshold distance, the first size of the first biological object 610 may be compared with a size of the ninth biological object 626. In some examples, the ninth biological object 626 may be selected for inclusion in the set of removable biological objects in response to a determination that the size of the ninth biological object 626 is smaller than the first size of the first biological object 610.

[0149] In some examples, the first cell operation may comprise a selective isolation operation (e.g., clone picking operation) performed by the first cell processing system 408. The selective isolation operation may comprise isolating a set of biological objects (e.g., a set of one or more desirable biological objects) of the first cell type. The set of biological objects may correspond to biological objects that were included in the one or more target regions. With respect to the target region map 705 shown in Fig. 7A, the set of biological objects may comprise the second biological object 612, the third biological object 698, the fifth biological object 618, the sixth biological object 620 and / or the eighth biological object 696. In some examples, the selective isolation operation may be performed to retain and / or transplant the set of biological objects for ongoing expansion, such as in preparation for transplantation and / or further culture. In some examples, theselective isolation operation may be performed for selective archiving (e.g., preserving defined clones and / or cell populations without ongoing expansion) and / or for use (e.g., immediate use) in one or more selected applications (e.g., therapeutic applications) without ongoing expansion. In some examples, the selective isolation operation may comprise directing a cell handling instrument (comprising a micromanipulator, a robotic arm, a fluid handling device, and / or other instrument) to access and / or remove the set of biological objects (e.g., biological colonies of the first cell type included in the one or more target regions) from the specimen, and / or to transfer the set of biological objects to one or more locations.

[0150] In some examples, the first cell operation may comprise a biopsy operation performed by the first cell processing system 408. For example, determining the one or more target regions of the specimen may comprise selecting the one or more target regions for the biopsy operation based upon the scoring information 738. In some examples, the first cell processing system 408 may generate instructions to perform the biopsy operation, and / or may provide the instructions to equipment configured to perform the biopsy operation. The biopsy operation may comprise partially sampling a set of biological objects of the first cell type. The set of biological objects sampled by the biopsy operation may correspond to biological objects that were included in the one or more target regions. With respect to the target region map 705 shown in Fig. 7A, the set of biological objects sampled by the biopsy operation may comprise the second biological object 612, the third biological object 698, the fifth biological object 618, the sixth biological object 620 and / or the eighth biological object 696. In some examples, the biopsy operation may be performed for selective analysis, such as to evaluate molecular markers, genetic integrity, and / or functional characteristics of the set of biological objects sampled by the biopsy operation. In some examples, the biopsy operation may be performed for selective archiving, such as to preserve representative portions of selected colonies for future reference and / or validation. In some examples, the biopsy operation may comprise directing a cell handling instrument (comprising a micromanipulator, a robotic arm, a fluid handling device, and / or other instrument) to (i) access and / orremove a portion of each of one, some or all of the set of biological objects, while retaining the remainder of one or more respective biologicals object in place within the specimen environment, and / or (ii) transfer the removed portions to one or more one or more locations (for further processing, for example).

[0151] In some examples, the first cell operation may comprise a deposition operation performed by the first cell processing system 408. For example, determining the one or more target regions of the specimen may comprise selecting the one or more target regions for the deposition operation based upon the scoring information 738. In some examples, the first cell processing system 408 may generate instructions to perform the deposition operation, and / or may provide the instructions to equipment configured to perform the deposition operation. The deposition operation may comprise placing or positioning one or more biological objects, or portions thereof, from one or more source regions to the one or more target regions selected for deposition. The one or more deposited biological objects may comprise, for example, biological objects previously isolated, picked, and / or processed from other regions of the specimen or from other specimens.

[0152] In some examples, the first cell operation may comprise an injection operation performed by the first cell processing system 408. For example, determining the one or more target regions of the specimen may comprise selecting the one or more target regions for the injection operation based upon the scoring information 738. In some examples, the first cell processing system 408 may generate instructions to perform the injection operation, and / or may provide the instructions to equipment configured to perform the injection operation. The injection operation may comprise delivering one or more agents (e.g., nucleic acids, proteins, differentiationinducing compounds, and / or other agents) into the one or more target regions. The injection may be performed to induce changes in cell state, introduce markers, and / or evaluate responses to internalized compounds.

[0153] In some examples, the first cell operation comprises transferring a sample of cells (e.g., a clone) from the one or more target regions to one or more vessels comprising a third vessel. The sample of cells may betransferred to the third vessel for cell expansion, archiving, testing and / or processing. For example, the one or more first biological objects may be selected for cell expansion, archiving, testing and / or processing by the biological object selection module 702 based upon the scoring information 738. In some examples, the first cell processing system 408 may generate instructions to transfer the sample of cells from the one or more target regions to the third vessel. In some examples, the instructions may comprise computer-readable instructions that may be executed by a computer and / or cell handling equipment. For example, the first cell processing system 408 may transmit the computer-readable instructions to one or more devices to facilitate the transfer of the sample of cells from the one or more target regions to the third vessel for cell expansion, archiving, testing and / or processing. In some examples, the instructions may comprise human- readable instructions that may be displayed for a user (via the display of the colony evaluation system 401 , for example).

[0154] In some examples, the sample of cells may be stored in the third vessel (and / or one or more other vessels) for a period (e.g., a defined period of time) in a controlled environment (e.g., an environment having one or more controlled conditions, such as controlled humidity, gas composition, etc., suitable for proliferation). Figs. 10A-10B illustrate aspects of a cell monitoring system 1001 , in accordance with some embodiments. The cell monitoring system 1001 may comprise a second imaging system 1002 for capturing and / or preparing one or more images of the sample of cells in the third vessel, such as using one or more of the techniques provided herein with respect to capturing and / or preparing the one or more second images 508. The cell monitoring system 1001 may comprise a cell status determination system 1004 for determining a status of the sample of cells. The cell monitoring system 1001 may comprise a second cell processing system 1008 for triggering and / or performing one or more cell operations based upon the status, such as using one or more of the techniques provided herein with respect to using the first cell processing system 408 for triggering and / or performing the first cell operation and / or the selective removal operation. Thesecond cell processing system 1008 may be the same as or different than the first cell processing system 408.

[0155] The cell monitoring system 1001 may (periodically, for example) perform a cell monitoring process comprising capturing one or more third images of a second specimen comprising the sample of cells in the third vessel using the second imaging system 1002, analyzing the one or more third images using the cell status determination system 1004 to determine a status of the sample of cells, and / or triggering one or more operations (e.g., at least one of a selective removal operation, a selective isolation operation, etc.) based upon the status. In some examples, the cell monitoring system 1001 may include checking for regions (e.g., iPSC spontaneous differentiation regions) with cells (e.g., iPSC cells) having an unstable morphology (e.g., a deviation from a phenotype of the first cell type and / or a deviation from a morphology of cells in the third vessel at an earlier time in the cell expansion operation). In response to detecting a region with cells having an unstable morphology, the cell monitoring system may trigger a selective removal operation to remove (unstable) cells from the region.

[0156] The cell monitoring process may include determining one or more measurements associated with the sample of cells, such as a confluence of the sample of cells (e.g., a proportion of a surface area of the third vessel that is covered by stable cells), a density of the sample of cells (e.g., a quantity of cells per unit area or volume), or other measurement. In some examples, the cell monitoring system 1001 may trigger a cell operation (e.g., harvesting operation to harvest at least some cells from the sample) in response to a determination that a condition has been met, such as a condition that the confluence meets a threshold confluence, the density meets a threshold density, and / or a score determined based upon the one or more measurements meets a threshold score. The cell monitoring system 1001 may trigger and / or perform the cell operation immediately in response to determining that the condition has been met. In some examples, the cell monitoring system 1001 may schedule the cell operation for a later time in the future, for example, at a time by which the cell monitoring system 1001 expects the condition to be met.

[0157] In some examples, the cell status determination system 1004 comprises a trained morphology segmentation model. In some examples, the trained morphology segmentation model may be trained using training information comprising images and label information indicative of segments of the images corresponding to stable morphology and / or segments of the images corresponding to unstable morphology. The trained morphology segmentation model is configured to analyze the one or more third images to determine one or more unstable regions associated with an unstable morphology and / or one or more stable regions associated with a stable morphology, and / or to generate a morphology map 1012 (shown in Fig. 10B) indicative of the one or more unstable regions and the one or more stable regions. In some examples, the morphology map 1012 is determined as part of the cell monitoring process and / or may be included in the status. Fig. 10B illustrates a representation of the morphology map 1012, in accordance with some embodiments. In the representation of the morphology map 1012 shown in Fig. 10B, the one or more stable regions are overlaid by a first pattern 1014 and the one or more unstable regions are overlaid by a second pattern 1016. In some examples, the one or more stable regions may comprise one or more regions with cells that maintained a phenotype corresponding to the first cell type (e.g., iPSC phenotype). In some examples, the one or more unstable regions (e.g., spontaneous differentiation regions) may comprise one or more regions with cells (e.g., iPSC colonies) that differentiated from the phenotype corresponding to the first cell type (e.g., iPSC phenotype) to a phenotype corresponding to a different cell type (e.g., fibroblast phenotype or other phenotype). Fig. 10B illustrates an enlarged map view 1022 of a portion 1018 of the specimen in the third vessel and / or an enlarged image of the portion 1018 of the specimen.

[0158] In some examples, the second cell processing system 1008 may determine one or more second removable regions of the second specimen for a selective removal operation based upon the one or more unstable regions and / or the one or more stable regions. The second cell processing system 1008 may generate instructions to remove the one or more second removable regions from the second specimen. The second cell processing system 1008may perform the selective removal operation to remove the one or more second removable regions from the second specimen. The one or more second removable regions may comprise the one or more unstable regions and / or may exclude the one or more stable regions. The selective removal operation may comprise removing biological material (e.g., biological material with unstable morphology) from the one or more second removable regions.

[0159] In some examples, the second cell processing system 1008 may perform a selective isolation operation (e.g., clone picking operation) based upon the one or more stable regions and / or the one or more unstable regions. The second cell processing system 1008 may generate instructions to perform the selective isolation operation. The selective isolation operation may comprise isolating a set of biological objects (e.g., a set of one or more desirable biological objects) of the first cell type. The set of biological objects may comprise one, some or all of the one or more stable regions. In some examples, the selective isolation operation may be performed to retain and / or transplant the set of biological objects for ongoing expansion, such as in preparation for transplantation and / or further culture. In some examples, the selective isolation operation may be performed for selective archiving (e.g., preserving defined clones and / or cell populations without ongoing expansion) and / or for use (e.g., immediate use) in one or more selected applications (e.g., therapeutic applications) without ongoing expansion. In some examples, the selective isolation operation may comprise directing a cell handling instrument (comprising a micromanipulator, a robotic arm, a fluid handling device, and / or other instrument) to access and / or remove the set of biological objects (e.g., biological colonies of one, some or all of the one or more stable regions) from the specimen, and / or to transfer the set of biological objects to one or more locations.

[0160] In some examples, the cell monitoring system 1001 may include checking for regions associated with features that meet one or more first conditions and / or checking for regions associated with features that do not meet the one or more first conditions. In some examples, a region may be determined to meet the one or more first conditions based upon a determination that one or more features (e.g., a confluence, a density, atextural and / or morphological feature, a score determined based upon one or more features, etc.) associated with the region meet one, some or all of one or more first thresholds (e.g., threshold ranges and / or threshold values) associated with the one or more first conditions, respectively. In some examples, a region may be determined to not meet the one or more first conditions based upon a determination that one or more features (e.g., a confluence, a density, a textural and / or morphological feature, a score determined based upon one or more features, etc.) associated with the region do not meet one, some or all of the one or more first thresholds associated with the one or more first conditions, respectively. The trained morphology segmentation model is configured to analyze the one or more third images to determine one or more third regions associated with features that meet the one or more first conditions and / or one or more fourth regions associated with features that do not meet the one or more first features.

[0161] In some examples, a threshold of the one or more first thresholds associated with the one or more first conditions may be configured based upon an expected and / or acceptable range for a feature, or an expected and / or acceptable upper or lower limit for the feature. The threshold may be determined based upon a duration of the period in which the second specimen comprising the sample of cells is stored in the controlled environment, a humidity level of the controlled environment, and / or a gas composition of the controlled environment. In some examples, the determination of whether a region meets the one or more first conditions may be used to assess a transition of a cell population from a first biological state to a second biological state. For example, the trained morphology segmentation model may detect morphological and / or textural changes indicative of a transition associated with differentiation. In some examples, the transition may occur with or without cell expansion. Detection of a region transitioning to an expected and / or desirable set of attributes may be used as a measure of potency, a measure of a suitability for transition to a subsequent operation in manufacturing and / or processing, and / or as a release criteria for a product. In some examples, identification of one or more regions (e.g., the one or more fourth regions) that fail to transition to the expected and / ordesirable set of attributes may indicate a failure of potency and / or a non- compliant product state. In some examples, a representation of the one or more fourth regions may be displayed (by the display of the colony evaluation system 401 , for example).

[0162] In some examples, the second cell processing system 1008 may determine one or more third removable regions of the second specimen for a selective removal operation based upon the one or more fourth regions and / or the one or more third regions. The second cell processing system 1008 may generate instructions to remove the one or more third removable regions from the second specimen. The second cell processing system 1008 may perform the selective removal operation to remove the one or more third removable regions from the second specimen. The one or more third removable regions may comprise the one or more fourth regions and / or may exclude the one or more third regions. The selective removal operation may comprise removing biological material (e.g., biological material with unexpected and / or undesired morphology) from the one or more third removable regions. The second cell processing system 1008 may generate instructions to remove the one or more third removable regions.

[0163] In some examples, the second cell processing system 1008 may perform a selective isolation operation (e.g., clone picking operation) based upon the one or more third regions and / or the one or more fourth regions. The second cell processing system 1008 may generate instructions to perform the selective isolation operation. The selective isolation operation may comprise isolating a set of biological objects (e.g., a set of one or more desirable biological objects) of the first cell type. The set of biological objects may comprise one, some or all of the one or more third regions. In some examples, the selective isolation operation may be performed to retain and / or transplant the set of biological objects for ongoing expansion, such as in preparation for transplantation and / or further culture. In some examples, the selective isolation operation may be performed for selective archiving (e.g., preserving defined clones and / or cell populations without ongoing expansion) and / or for use (e.g., immediate use) in one or more selected applications (e.g., therapeutic applications) without ongoing expansion. In someexamples, the selective isolation operation may comprise directing a cell handling instrument (comprising a micromanipulator, a robotic arm, a fluid handling device, and / or other instrument) to access and / or remove the set of biological objects (e.g., biological colonies of one, some or all of the one or more third regions) from the specimen, and / or to transfer the set of biological objects to one or more locations.

[0164] In some examples, the present disclosure is implemented in a large scale automated process that may involve limited or zero interaction with a client, and / or may be embedded in a (larger) multi-stage processing system that may be applied to one or more samples at a time. In some examples, the multi-stage processing system may be applied to manage a series of multiple samples using a standardized set of conditions, which may be fixed and / or dynamic for each sample. In some examples, the conditions are adaptable based upon an expected range of sample variation with respect to defined features over time and / or at different stages in a process.

[0165] In some examples, the colony evaluation system 401 and / or the cell monitoring system 1001 may store extracted features (e.g., the feature information 734) in a data store. The colony evaluation system 401 and / or the cell monitoring system 1001 may use the extracted features (as feedback, for example) to update the trained biological object segmentation model and / or the trained morphology segmentation model.

[0166] In some examples, each machine learning model of one, some and / or all machine learning models of the present disclosure (e.g., the trained biological object segmentation model, the trained morphology segmentation model, etc.), may be configured for biomedical image segmentation and / or may comprise at least one of a neural network, such as a convolutional neural network (e.g., a convolutional neural network with a deep learning U-net architecture), a regression model (e.g., a machine learning model used to perform linear regression or logistic regression), a deep learning model, a tree-based model, a decision tree model, a support vector machine (SVM), a Bayesian network model, a k-Nearest Neighbors (k-NN) model, a K-Means model, a random forest model, a machine learning model used to performdimensional reduction, a machine learning model used to perform gradient boosting, etc.

[0167] An embodiment determining one or more target regions of a specimen is illustrated by an example method 1100 of Fig. 1 1. At 1102, one or more images (e.g., the one or more second images 508). At 1 104, a biological object segmentation model (e.g., the trained biological object segmentation model 632) may analyze the one or more images to generate a biological object map (e.g., the biological object map 605) indicative of regions, of the specimen, including biological objects (e.g., biological colonies of the first cell type, such as iPSC colonies). At 1106, sets of features (e.g., the feature information 734) associated with the biological objects may be determined based upon the biological object map. At 1 108, scores (e.g., the scoring information 738) associated with the biological objects may be determined. At 11 10, one or more target regions of the specimen may be determined based upon the scores.

[0168] According to some embodiments, a method is provided. The method includes receiving one or more images of a specimen; analyzing, using a biological object segmentation model, the one or more images to generate a biological object map indicative of regions, of the specimen, including biological objects; determining, based upon the biological object map, sets of features associated with the biological objects; determining, based upon the sets of features, scores associated with the biological objects; and determining one or more target regions of the specimen based upon the scores.

[0169] According to some embodiments, the method includes determining the one or more target regions of the specimen includes determining one or more removable regions of the specimen; and the method includes generating instructions to remove the one or more removable regions from the specimen.

[0170] According to some embodiments, determining the one or more removable regions includes determining, based upon the biological object map, one or more first regions outside the biological objects; and determining, based upon the scores, a set of removable biological objects.

[0171] According to some embodiments, the one or more removable regions includes the one or more first regions and the set of removable biological objects.

[0172] According to some embodiments, determining the set of removable colonies includes determining, using the biological object map, a distance between a first biological object and a second biological object; and in response to the distance being less than a threshold, selecting, based upon a comparison of the first biological object with the second biological object, the first biological object or the second biological object for inclusion in the set of removable biological objects.

[0173] According to some embodiments, determining the scores associated with the biological objects includes determining a circularity of a biological object based upon the biological object map; and determining a score associated with the biological object based upon the circularity.

[0174] According to some embodiments, determining the scores associated with the biological objects includes determining a size of a biological object based upon the biological object map; and determining a score associated with the biological object based upon the size.

[0175] According to some embodiments, determining the scores associated with the biological objects includes determining one or more boundary attributes of a biological object based upon the biological object map; and determining a score associated with the biological object based upon the one or more boundary attributes.

[0176] According to some embodiments, determining the scores associated with the biological objects includes determining an aspect ratio of a biological object based upon the biological object map; and determining a score associated with the biological object based upon the aspect ratio.

[0177] According to some embodiments, determining the scores associated with the biological objects includes determining a perimeter of a biological object based upon the biological object map; and determining a score associated with the biological object based upon the perimeter.

[0178] According to some embodiments, determining the scores associated with the biological objects includes determining one or more morphological features of a biological object based upon the biological object map, and determining a score associated with the biological object based upon those one or more morphological features.

[0179] According to some embodiments, determining the scores associated with the biological objects includes determining, using the biological object map, one or more distances between a first biological object and one or more second biological objects; and determining a score associated with the biological object based upon the one or more distances.

[0180] According to some embodiments, determining the one or more target regions of the specimen includes selecting one or more biological objects for selective isolation based upon the scores, wherein the one or more target regions include the one or more biological objects.

[0181] According to some embodiments, the method includes generating instructions to transfer a sample of cells from the one or more target regions to a location for cell expansion.

[0182] According to some embodiments, the method includes receiving one or more second images of a second specimen including the sample after a period of cell expansion; and analyzing, using a morphology segmentation model, the one or more second images to determine one or more first regions associated with an unstable morphology; and / or one or more second regions associated with a stable morphology.

[0183] According to some embodiments, the method includes determining one or more removable regions of the second specimen based upon the one or more first regions and / or the one or more second regions; and generating instructions to remove the one or more removable regions from the second specimen.

[0184] According to some embodiments, the method includes generating instructions to transfer a sample of cells from the one or more target regions to a location for at least one of archiving, testing, processing, or cell expansion.

[0185] According to some embodiments, the method includes receiving one or more second images of a second specimen comprising the sample after a period of time after the transfer to the location; and analyzing, using a morphology segmentation model, the one or more second images to determine one or more first regions associated with one or more first features that meet one or more first conditions and / or one or more second regions associated with one or more second features that do not meet the one or more first conditions.

[0186] According to some embodiments, the method includes determining one or more removable regions of the second specimen based upon at least one of the one or more first regions or the one or more second regions; and generating instructions to remove the one or more removable regions from the second specimen.

[0187] According to some embodiments, determining the one or more target regions of the specimen includes selecting the one or more target regions for a biopsy operation based upon the scores.

[0188] According to some embodiments, the method includes generating instructions to perform the biopsy operation.

[0189] According to some embodiments, determining the one or more target regions of the specimen includes selecting the one or more target regions for a deposition operation based upon the scores.

[0190] According to some embodiments, the method includes generating instructions to perform the deposition operation.

[0191] According to some embodiments, determining the one or more target regions of the specimen includes selecting the one or more target regions for an injection operation based upon the scores.

[0192] According to some embodiments, the method includes generating instructions to perform the injection operation.

[0193] According to some embodiments, the biological objects include biological colonies of a first cell type.

[0194] According to some embodiments, the biological colonies include Induced Pluripotent Stem Cell (iPSC) colonies.

[0195] According to some embodiments, the method includes identifying a plurality of images associated with a plurality of sources; and training a machine learning model using a plurality of images and label information associated with the plurality of images to generate the biological object segmentation model, wherein the label information is indicative of a segment, of an image of the plurality of images, that corresponds to a biological object of the first cell type; and / or a segment, of the image, that corresponds to a material different than a biological object of the first cell type.

[0196] According to some embodiments, a non-transitory computer- readable medium is provided. The non-transitory computer-readable medium stores instructions that when executed perform operations including receiving one or more images of a specimen; analyzing, using a biological object segmentation model, the one or more images to generate a biological object map indicative of regions, of the specimen, including biological objects; determining, based upon the biological object map, sets of features associated with the biological objects; determining, based upon the sets of features, scores associated with the biological objects; and determining one or more target regions of the specimen based upon the scores.

[0197] According to some embodiments, the operations include performing a cell operation based upon the one or more target regions, wherein the cell operation comprises at least one of a selective isolation operation, a selective removal operation, a biopsy, a deposition, or an injection.

[0198] According to some embodiments, a computing device is provided. The computing device includes a processor; and memory including processor-executable instructions that when executed by the processor cause performance of operations. The operations include receiving one or more images of a specimen; analyzing, using a biological object segmentation model, the one or more images to generate a biological object map indicative of regions, of the specimen, including biological objects; determining, based upon the biological object map, sets of features associated with the biologicalobjects; determining, based upon the sets of features, scores associated with the biological objects; and determining one or more target regions of the specimen based upon the scores.

[0199] According to some embodiments, the operations include performing a cell operation based upon the one or more target regions, wherein the cell operation comprises at least one of a selective isolation operation, a selective removal operation, a biopsy, a deposition, or an injection.

[0200] According to some embodiments, a method including at least one aspect as described in the present disclosure and / or shown in the figures.

[0201] According to some embodiments, a method including plural aspects as described in the present disclosure and / or shown in the figures.

[0202] According to some embodiments, a system including at least one aspect as described in the present disclosure and / or shown in the figures.

[0203] According to some embodiments, a system including plural aspects as described in the present disclosure and / or shown in the figures.

[0204] Fig. 12 is an illustration of a scenario 1200 involving an example non-transitory machine readable medium 1202. The non-transitory machine readable medium 1202 may comprise processor-executable instructions 1212 that when executed by a processor 1216 cause performance (e.g., by the processor 1216) of at least some of the provisions herein (e.g., embodiment 1214).

[0205] The non-transitory machine readable medium 1202 may comprise a memory semiconductor (e.g., a semiconductor utilizing static random access memory (SRAM), dynamic random access memory (DRAM), and / or synchronous dynamic random access memory (SDRAM) technologies), a platter of a hard disk drive, a flash memory device, or a magnetic or optical disc (such as a compact disc (CD), digital versatile disc (DVD), or floppy disk).

[0206] The example non-transitory machine readable medium 1202 stores computer-readable data 1204 that, when subjected to reading 1206 bya reader 1210 of a device 1208 (e.g., a read head of a hard disk drive, or a read operation invoked on a solid-state storage device), express the processor-executable instructions 1212.

[0207] In some embodiments, the processor-executable instructions 1212, when executed, cause performance of operations, such as at least some of the example method 1 100 of Fig. 1 1 , for example. In some embodiments, the processor-executable instructions 1212 are configured to cause implementation of a system, such as at least some of the example colony evaluation system 401 of Figs. 4, the example imaging system 402 of Fig. 5, the example imaging system 404 of Figs. 6A-6F, the example cell targeting system 406 of Figs. 7A-7C, and / or the example cell monitoring system 1001 of Figs. 10A-10B, for example.

[0208] As used in this application, "component," "module," "system", "interface", and / or the like are generally intended to refer to a computer- related entity, either hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and / or a computer. By way of illustration, both an application running on a controller and the controller can be a component. One or more components may reside within a process and / or thread of execution and a component may be localized on one computer and / or distributed between two or more computers.

[0209] Unless specified otherwise, “first,” “second,” and / or the like are not intended to imply a temporal aspect, a spatial aspect, an ordering, etc. Rather, such terms are merely used as identifiers, names, etc. for features, elements, items, etc. For example, a first object and a second object generally correspond to object A and object B or two different or two identical objects or the same object.

[0210] Moreover, "example" is used herein to mean serving as an instance, illustration, etc., and not necessarily as advantageous. As used herein, "or" is intended to mean an inclusive "or" rather than an exclusive "or". In addition, "a" and "an" as used in this application are generally be construed to mean "one or more" unless specified otherwise or clear from context to bedirected to a singular form. Also, at least one of A and B and / or the like generally means A or B or both A and B. Furthermore, to the extent that "includes", "having", "has", "with", and / or variants thereof are used in either the detailed description or the claims, such terms are intended to be inclusive in a manner similar to the term "comprising”.

[0211] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing at least some of the claims.

[0212] Furthermore, the claimed subject matter may be implemented as a method, apparatus, or article of manufacture using standard programming and / or engineering techniques to produce software, firmware, hardware, or any combination thereof to control a computer to implement the disclosed subject matter. The term "article of manufacture" as used herein is intended to encompass a computer program accessible from any computer- readable device, carrier, or media. Of course, many modifications may be made to this configuration without departing from the scope or spirit of the claimed subject matter.

[0213] Various operations of embodiments are provided herein. In an embodiment, one or more of the operations described may constitute computer readable instructions stored on one or more computer and / or machine readable media, which if executed will cause the operations to be performed. The order in which some or all of the operations are described should not be construed as to imply that these operations are necessarily order dependent. Alternative ordering will be appreciated by one skilled in the art having the benefit of this description. Further, it will be understood that not all operations are necessarily present in each embodiment provided herein. Also, it will be understood that not all operations are necessary in some embodiments.

[0214] Also, although the disclosure has been shown and described with respect to one or more implementations, equivalent alterations andmodifications will occur to others skilled in the art based upon a reading and understanding of this specification and the annexed drawings. The disclosure includes all such modifications and alterations and is limited only by the scope of the following claims. In particular regard to the various functions performed by the above described components (e.g., elements, resources, etc.), the terms used to describe such components are intended to correspond, unless otherwise indicated, to any component which performs the specified function of the described component (e.g., that is functionally equivalent), even though not structurally equivalent to the disclosed structure. In addition, while a particular feature of the disclosure may have been disclosed with respect to only one of several implementations, such feature may be combined with one or more other features of the other implementations as may be desired and advantageous for any given or particular application.

Claims

CLAIMSWhat is claimed is:1 . A method, comprising: receiving one or more images of a specimen; analyzing, using a biological object segmentation model, the one or more images to generate a biological object map indicative of regions, of the specimen, comprising biological objects; determining, based upon the biological object map, sets of features associated with the biological objects; determining, based upon the sets of features, scores associated with the biological objects; and determining one or more target regions of the specimen based upon the scores.

2. The method of claim 1 , comprising: determining the one or more target regions of the specimen comprises determining one or more removable regions of the specimen; and the method comprises generating instructions to remove the one or more removable regions from the specimen.

3. The method of claim 2, wherein: determining the one or more removable regions comprises: determining, based upon the biological object map, one or more first regions outside the biological objects; and determining, based upon the scores, a set of removable biological objects; and the one or more removable regions comprises the one or more first regions and the set of removable biological objects.

4. The method claim 3, wherein determining the set of removable colonies comprises: determining, using the biological object map, a distance between a first biological object and a second biological object; andin response to the distance being less than a threshold, selecting, based upon a comparison of the first biological object with the second biological object, the first biological object or the second biological object for inclusion in the set of removable biological objects.

5. The method claim 3, wherein determining the set of removable colonies comprises: determining, using the biological object map, a distance between a first biological object and a second biological object; in response to the distance being less than a threshold distance, comparing a first size of the first biological object with a second size of the second biological object; and selecting, based upon the comparison, the first biological object or the second biological object for inclusion in the set of removable biological objects.

6. The method claim 1 , wherein: determining the scores associated with the biological objects comprises: determining a circularity of a biological object based upon the biological object map; and determining a score associated with the biological object based upon the circularity.

7. The method claim 1 , wherein: determining the scores associated with the biological objects comprises: determining a size of a biological object based upon the biological object map; and determining a score associated with the biological object based upon the size.

8. The method claim 1 , wherein:determining the scores associated with the biological objects comprises: determining one or more boundary attributes of a biological object based upon the biological object map; and determining a score associated with the biological object based upon the one or more boundary attributes.

9. The method claim 1 , wherein: determining the scores associated with the biological objects comprises: determining an aspect ratio of a biological object based upon the biological object map; and determining a score associated with the biological object based upon the aspect ratio.

10. The method claim 1 , wherein: determining the scores associated with the biological objects comprises: determining a perimeter of a biological object based upon the biological object map; and determining a score associated with the biological object based upon the perimeter.

11. The method claim 1 , wherein: determining the scores associated with the biological objects comprises: determining one or more morphological features of a biological object based upon the biological object map; and determining a score associated with the biological object based upon the one or more morphological features.

12. The method claim 1 , wherein: determining the scores associated with the biological objects comprises:determining, using the biological object map, one or more distances between a first biological object and one or more second biological objects; and determining a score associated with the biological object based upon the one or more distances.

14. The method of claim 1 , wherein: determining the one or more target regions of the specimen comprises selecting one or more biological objects for selective isolation based upon the scores, wherein the one or more target regions comprise the one or more biological objects.

15. The method of claim 14, comprising: generating instructions to transfer a sample of cells from the one or more target regions to a location for cell expansion.

16. The method of claim 15, comprising: receiving one or more second images of a second specimen comprising the sample after a period of cell expansion; and analyzing, using a morphology segmentation model, the one or more second images to determine at least one of: one or more first regions associated with an unstable morphology; or one or more second regions associated with a stable morphology.

17. The method of claim 16, comprising: determining one or more removable regions of the second specimen based upon at least one of the one or more first regions or the one or more second regions; and generating instructions to remove the one or more removable regions from the second specimen.

18. The method of claim 14, comprising:generating instructions to transfer a sample of cells from the one or more target regions to a location for at least one of archiving, testing, processing, or cell expansion.

19. The method of claim 18, comprising: receiving one or more second images of a second specimen comprising the sample after a period of time after the transfer to the location; and analyzing, using a morphology segmentation model, the one or more second images to determine at least one of: one or more first regions associated with one or more first features that meet one or more first conditions; or one or more second regions associated with one or more second features that do not meet the one or more first conditions.

20. The method of claim 19, comprising: determining one or more removable regions of the second specimen based upon at least one of the one or more first regions or the one or more second regions; and generating instructions to remove the one or more removable regions from the second specimen.21 . The method of claim 1 , wherein: determining the one or more target regions of the specimen comprises selecting the one or more target regions for a biopsy operation based upon the scores.

22. The method of claim 21 , comprising: generating instructions to perform the biopsy operation.

22. The method of claim 1 , wherein: determining the one or more target regions of the specimen comprises selecting the one or more target regions for a deposition operation based upon the scores.

23. The method of claim 22, comprising: generating instructions to perform the deposition operation.

24. The method of claim 1 , wherein: determining the one or more target regions of the specimen comprises selecting the one or more target regions for an injection operation based upon the scores.

25. The method of claim 24, comprising: generating instructions to perform the injection operation.

26. The method of claim 1 , wherein: the biological objects comprise biological colonies of a first cell type.

27. The method of claim 1 , wherein: the biological colonies comprise Induced Pluripotent Stem Cell (iPSC) colonies.

28. The method of claim 1 , comprising: identifying a plurality of images associated with a plurality of sources; and training a machine learning model using a plurality of images and label information associated with the plurality of images to generate the biological object segmentation model, wherein the label information is indicative of at least one of: a segment, of an image of the plurality of images, that corresponds to a biological object of the first cell type; or a segment, of the image, that corresponds to a material different than a biological object of the first cell type.

29. A non-transitory computer-readable medium storing instructions that when executed perform operations comprising: receiving one or more images of a specimen;analyzing, using a biological object segmentation model, the one or more images to generate a biological object map indicative of regions, of the specimen, comprising biological objects; determining, based upon the biological object map, sets of features associated with the biological objects; determining, based upon the sets of features, scores associated with the biological objects; and determining one or more target regions of the specimen based upon the scores.

30. The non-transitory computer-readable medium of claim 29, the operations comprising: performing a cell operation based upon the one or more target regions, wherein the cell operation comprises at least one of a selective isolation operation, a selective removal operation, a biopsy, a deposition, or an injection.

31. A computing device comprising: a processor; and memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising: receiving one or more images of a specimen; analyzing, using a biological object segmentation model, the one or more images to generate a biological object map indicative of regions, of the specimen, comprising biological objects; determining, based upon the biological object map, sets of features associated with the biological objects; determining, based upon the sets of features, scores associated with the biological objects; and determining one or more target regions of the specimen based upon the scores.

32. The computing device of claim 31 , the operations comprising:performing a cell operation based upon the one or more target regions, wherein the cell operation comprises at least one of a selective isolation operation, a selective removal operation, a biopsy, a deposition, or an injection.

32. A method, comprising: at least one aspect as described in any one of the preceding claims.

33. A method, comprising: at least one aspect as described in any combination of some or all of the preceding claims.

34. A method, comprising: plural aspects as described in any one of the preceding claims.

35. A method, comprising: plural aspects as described in any combination of some or all of the preceding claims.

36. A system, comprising: at least one aspect as described in any one of the preceding claims.

37. A system, comprising: at least one aspect as described in any combination of some or all of the preceding claims.

38. A system, comprising: plural aspects as described in any one of the preceding claims.

39. A system, comprising: plural aspects as described in any combination of some or all of the preceding claims.

Images