Computing system pathology spatial analysis platform for in situ or in vitro multi-parameter cell and subcellular imaging data

Abstract

The present invention relates to a computing system pathology spatial analysis platform comprising: (i) a spatial heterogeneity quantification component configured to generate global quantification of spatial heterogeneity between cells of different phenotypes in multi-parameter cellular and subcellular imaging data; (ii) a microcell identification component configured to identify a plurality of microcells for the plurality of tissue samples based on the global quantization, each microcell associated with one tissue sample; and (iii) a weighted graph component configured to construct a weighted graph for multi-parameter cellular and subcellular imaging data, the weighted graph having a plurality of nodes and a plurality of edges, each edge being located between a pair of nodes, where in the weighted graph, each node is a particular one of the microdomains, and each edge is located between a pair of nodes. An edge between each pair of microcells in the weighted graph indicates a degree of similarity between the pair of microcells.

Description

[0001] This application is a divisional application, and the corresponding parent application has an application number of CN201980084101.2, a filing date of December 16, 2019, and an invention title of "Computational System Pathology Spatial Analysis Platform for In Situ or In Vitro Multi-parameter Cellular and Subcellular Imaging Data". Technical Field

[0002] The present invention relates to digital pathology, and in particular, to an integrated computational system pathology spatial analysis (CSPSA) computer platform capable of integrating, visualizing, and modeling high-dimensional in situ or in vitro cellular and subcellular resolution imaging data. Background Art

[0003] Digital pathology refers to the acquisition, storage, and display of histologically stained tissue samples, and has begun to receive attention in niche applications such as second-opinion telepathology, immunostain interpretation, and intraoperative telepathology. Generally, a large amount of patient data (consisting of 3 to 50 slides) is generated from biopsy samples and visually evaluated by pathologists under a microscope but using digital technology by viewing on a high-definition monitor. Due to the manual labor involved, current workflow practices are time-consuming, error-prone, and subjective.

[0004] Cancer is a heterogeneous disease. In hematoxylin and eosin (H&E) stained tissue images, heterogeneity is characterized by the presence of various histological structures, such as in situ carcinoma, invasive carcinoma, adipose tissue, blood vessels, and normal ducts. In addition, for many malignancies, molecular and cellular heterogeneity is a prominent feature between tumors from different patients, different sites of tumor formation within a single patient, and within a single tumor. Intra-tumor heterogeneity involves phenotypically distinct cancer cell clone subsets and other cell types that make up the tumor microenvironment (TME). These cancer cell clone subsets and other cell types include local and bone marrow-derived stromal stem and progenitor cells, subclasses of immune-inflammatory cells that can promote or kill tumors, cancer-associated fibroblasts, endothelial cells, and pericytes. The TME can be regarded as an evolving ecosystem in which cancer cells engage in heterotypic interactions with these other cell types and utilize available resources for proliferation and survival. Consistent with this view, the spatial relationship (i.e., spatial heterogeneity) between cell types within the TME appears to be one of the main drivers of disease progression and treatment resistance. Therefore, it is necessary to define the spatial heterogeneity in the TME to correctly diagnose specific disease subtypes and determine the best treatment regimen for an individual patient.

[0005] To date, three main methods have been used to explore intratumoral heterogeneity. The first method is to collect core samples from specific regions of the tumor to measure population averages. By using multiple techniques, including whole exome sequencing, epigenetics, proteomics, and metabolomics, multiple cores within the tumor are analyzed to measure the heterogeneity within the sample. The second method involves "single cell analysis" using the above methods, RNA Seq, imaging, or flow cytometry after dissociating cells from the tissue. The third method uses spatially resolved optical microscopy imaging to maintain spatial context and combines it with molecular specific markers to measure biomarkers in cells in situ. Biomarkers can identify cell types, activation states (e.g., phosphorylation of target proteins), and subcellular functions. Although each of these methods provides a certain degree of effectiveness, they all have various drawbacks and limitations.

[0006] In addition, one of the greatest challenges in assessing the clinical significance of tumor heterogeneity is the lack of advanced tools for the spatial analysis of multi-parametric cellular and subcellular imaging data. SUMMARY OF THE INVENTION

[0007] In one embodiment, a method for analyzing disease progression from multi-parametric cellular and subcellular imaging data is provided, the multi-parametric cellular and subcellular imaging data being obtained from multiple tissue samples or multiple multicellular in vitro models from multiple patients. The method includes generating a global quantification of spatial heterogeneity between cells of certain different predetermined phenotypes in the multi-parametric cellular and subcellular imaging data, identifying multiple micro-regions of the multiple tissue samples based on the global quantification, each micro-region being associated with a corresponding one of the tissue samples, and constructing a weighted graph for the multi-parametric cellular and subcellular imaging data. The weighted graph has multiple nodes and multiple edges, each edge being located between a pair of nodes, wherein in the weighted graph, each node is a particular one of the micro-regions, and the edge between each pair of micro-regions in the weighted graph indicates the degree of similarity between the pair of micro-regions.

[0008] In another embodiment, a computerized system for analyzing disease progression from multi-parameter cellular and sub-cellular imaging data is provided, the data being obtained from multiple tissue samples or multiple multi-cellular in vitro models from multiple patients. The system includes a processing device that includes: (i) a spatial heterogeneity quantification component configured to generate a global quantification of spatial heterogeneity between cells of certain different predetermined phenotypes in the multi-parameter cellular and sub-cellular imaging data; (ii) a micro-region identification component configured to identify a plurality of micro-regions for the plurality of tissue samples based on the global quantification, each micro-region being associated with a respective one of the tissue samples; and (iii) a weighted graph component configured to construct a weighted graph for the multi-parameter cellular and sub-cellular imaging data, the weighted graph having a plurality of nodes and a plurality of edges, each edge being located between a pair of nodes, wherein in the weighted graph, each node is a particular one of the micro-regions, and an edge between each pair of micro-regions in the weighted graph indicates the degree of similarity between the pair of micro-regions.

[0009] In yet another embodiment, a method for generating a spatially indicative heterogeneous cell communication representation from multi-parameter cellular and sub-cellular imaging data is provided, the data being obtained from multiple tissue samples or multiple multi-cellular in vitro models from multiple patients. The method includes generating a quantification of spatial heterogeneity between cells of certain different predetermined phenotypes in the multi-parameter cellular and sub-cellular imaging data and identifying a micro-region of one of the tissue samples based on the quantification, including performing cell phenotyping on the multi-parameter cellular and sub-cellular imaging data to identify certain different predetermined phenotypes, and constructing a communication graph for the micro-region. Each phenotype is a node in the communication graph, and an edge between each pair of phenotypes in the communication graph indicates the effect of the presence of one phenotype in the pair on the presence of the other phenotype in the pair.

[0010] In yet another embodiment, a computerized system for generating a spatially indicative heterogeneous cell communication representation from multi-parameter cellular and sub-cellular imaging data is provided, the data being obtained from multiple tissue samples or multiple multi-cellular in vitro models from multiple patients. The system includes a processing device that includes: (i) a spatial heterogeneity quantification component configured to generate a quantification of spatial heterogeneity between cells of certain different predetermined phenotypes in the multi-parameter cellular and sub-cellular imaging data, including performing cell phenotyping on the multi-parameter cellular and sub-cellular imaging data to identify certain different predetermined phenotypes, (ii) a micro-region identification component configured to identify a plurality of micro-regions of the plurality of tissue samples based on the quantification, each micro-region being associated with one of the tissue samples, and (iii) a communication network component configured to construct a communication graph for a selected one of the micro-regions, wherein each phenotype is a node in the communication graph, and an edge between each pair of phenotypes in the communication graph indicates the effect of the presence of one phenotype in the pair on the presence of the other phenotype in the pair.

[0011] In yet another embodiment, a method for creating personalized medicine strategies for a specific patient is provided, where the specific patient is one of a plurality of patients, and where the plurality of patients is associated with multi-parameter cellular and sub-cellular imaging data of a plurality of tissue samples obtained from the plurality of patients. The method includes identifying a plurality of micro-regions in one of the tissue samples associated with the specific patient, where the plurality of micro-regions is based on the multi-parameter cellular and sub-cellular imaging data, generating a heterogeneous cell communication network for each micro-region, where each heterogeneous cell communication network includes a spatially indicative heterogeneous cell communication representation for the micro-region, generating a quantification based on the spatial and temporal interdependence of the micro-regions based on the heterogeneous cell communication network, and designing a medical strategy for the specific patient according to the quantification.

[0012] In yet another embodiment, a method for representing the temporal evolution of disease progression in a specific patient is provided, where the specific patient is one of a plurality of patients, and where the plurality of patients is associated with multi-parameter cellular and sub-cellular imaging data of a plurality of tissue samples obtained from the plurality of patients. The method includes generating a geometric representation of the disease landscape for the specific patient, where the geometric representation includes a plurality of points, where each point on the geometric representation: (i) describes the disease landscape of the specific patient at a specific time and is based on a specific one of the tissue samples associated with the selected patient, (ii) is based on a micro-region in the specific one of the tissue samples, which is based on the multi-parameter cellular and sub-cellular imaging data, and (iii) includes a heterogeneous cell communication network for the micro-region, which includes a spatially indicative heterogeneous cell communication representation for the micro-region. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 is a schematic diagram of an exemplary computational system pathology spatial analysis (CSPSA) platform for in-situ or in-vitro multi-parameter cellular and sub-cellular imaging data according to an embodiment of the disclosed concept;

[0014] Figure 2 is a schematic representation of an exemplary hyper-multiplexed image stack;

[0015] Figure 3 is according to an exemplary embodiment of the disclosed concept, showing a method for analyzing tumor progression / evolution from multi-parameter cellular and sub-cellular imaging data obtained from multiple tumor sections of a patient cohort, which can be implemented in the Figure 1 CSPSA platform;

[0016] Figure 4 is a schematic representation of an exemplary global spatial graph;

[0017] Figure 5Shows a schematic representation of each predetermined major biomarker intensity pattern of an exemplary embodiment of the disclosed concept;

[0018] Figure 6 Shows a schematic representation of a cell spatial-dependence image according to a specific exemplary embodiment of the disclosed concept;

[0019] Figure 7 Is a schematic representation of an exemplary micro-region in an exemplary tissue section according to an exemplary embodiment of the disclosed concept;

[0020] Figure 8 Is a schematic representation of a weighted micro-region map constructed for multi-parameter cell and subcellular imaging data according to an exemplary embodiment of the disclosed concept;

[0021] Figure 9 Is a flow chart showing a method for generating a spatially indicative heterogeneous cell communication representation from multi-parameter cell and subcellular imaging data according to another exemplary embodiment of the disclosed concept;

[0022] Figure 10 Is a schematic representation of an exemplary communication map according to an exemplary embodiment of the disclosed concept;

[0023] Figure 11 Is a schematic diagram of a specific communication map generated according to a specific exemplary embodiment, where the phenotypes are tumor cells, lymphocytes, macrophages, stroma, and necrosis;

[0024] Figure 12 Is a schematic representation of a personalized medicine strategy according to one aspect of the disclosed concept; and

[0025] Figure 13 Is a schematic representation of an exemplary cancer landscape according to one aspect of the disclosed concept. Detailed Description

[0026] As used herein, the singular forms "a", "an", and "the" include plural references unless the context clearly dictates otherwise.

[0027] As used herein, the expression that two or more components or elements are "coupled" shall mean that these components are joined or act together directly or indirectly (i.e., through one or more intermediate components or elements, as long as there is a connection).

[0028] As used herein, the term "number" shall mean an integer of one or greater than one (i.e., a plurality).

[0029] As used herein, the terms "component" and "system" are intended to refer to computer-related entities, either hardware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, 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, an application running on a server and the server can both be components. One or more components can reside within a process and / or thread of execution, and a component can be located on one computer and / or distributed between two or more computers. Although certain ways of presenting information to a user are shown and described with respect to some figures or graphics (as screenshots), those skilled in the relevant art will recognize that various other alternative ways can be employed.

[0030] As used herein, the term "multiparametric cellular and subcellular imaging data" refers to data obtained by generating a large number of images from multiple tissue sections, which provides information on multiple measurable parameters at the cellular or subcellular level of the tissue sections. Multiparametric cellular and subcellular imaging data can be created by a variety of different imaging techniques, such as but not limited to (1) transmission light imaging with IHC using multiple biomarkers, (2) immunofluorescence imaging including multiplex imaging (1 - 7 biomarkers) and hyperplex imaging (>7 biomarkers), (3) toponome imaging, (4) matrix-assisted laser desorption / ionization mass spectrometric imaging (MALDI MSI), (5) complementary spatial imaging such as FISH, MxFISH, FISHSEQ or CyTOF, (6) multiparametric ion beam imaging, and (7) in vitro imaging of experimental models. Additionally, for example but not limited to, multiparametric cellular and subcellular imaging data can be created by generating multiple biomarker images from multiple tissue sections by labeling each tissue section with multiple different biomarkers.

[0031] As used herein, the term "spatial map" shall refer to a collection of data of multiple quantified spatial statistics and / or a representation in a visually perceivable form, which indicates the relationship between cells of different predetermined phenotypes in a set of multi-parameter cellular and subcellular imaging data. By way of example and not limitation, a spatial map can be a point mutual information (PMI) map generated in the manner described in PCT Application No. PCT / US2016 / 036825 and U.S. Patent Application Publication No. 2018 / 0204085, both of which have the invention title "Systems and Methods for Finding Regions of Interest in Hematoxylin and Eosin (H&E) Stained Tissue Images and Quantifying Intratumor Cellular Spatial Heterogeneity in Multiplexed / Hyperplexed Fluorescence Tissue Images", the disclosures of which are incorporated herein by reference.

[0032] As used herein, the term "microdomain" refers to a spatially distinct arrangement (or motif) of phenotypically different cells in a tissue sample, which is generated by spatial intratumoral heterogeneity and is associated with one or more outcome-specific variables (e.g., time to recurrence). Microdomains can be identified from multi-parameter cellular and sub-cellular imaging data according to any of a number of known or later-developed methods, such as, but not limited to, those described in U.S. Provisional Application Serial No. 62 / 675,832 (entitled "Predicting the Recurrence Risk of Cancer Patients From Primary Tumors with Multiplexed Immunofluorescence Biomarkers and Their Spatial Correlation Statistics"), and PCT Application No. PCT / US2019 / 033662 (entitled "System and Method for Predicting the Risk of Cancer Recurrence From Spatial Multi-Parameter Cellular and Sub-Cellular Imaging Data for Tumors by Identifying Emergent Spatial Domain Networks Associated With Recurrence"), each of which is incorporated herein by reference, and / or implemented in the public domain THRIVE (Tumor Heterogeneity Research Interactive Visualization Environment) software described in Spagnolo et al., Platform for Quantitative Evaluation of Spatial Intratumoral Heterogeneity in Multiplexed Fluorescence Images, Cancer Res. 2017 Nov 1;77(21):e71-e74 and / or in the above-referenced Spagnolo et al. reference. In this method, spatially resolved correlations between biomarkers are used as covariates of outcome data (e.g., recurrence) in a multivariable survival model to build a map of the spatial organization of cancer recurrence in multiplex tissue samples. These maps depict microdomains associated with recurrence and metastatic progression.

[0033] Directional phrases used herein, such as but not limited to, top, bottom, left, right, upper, lower, front, back, and derivatives thereof, relate to the orientation of elements shown in the figures and are not limited to the claims unless explicitly stated otherwise.

[0034] For purposes of illustration, the concepts disclosed in the present invention will now be described in connection with numerous specific details in order to provide a thorough understanding of the present invention. However, it will be apparent that the concepts disclosed in the present invention may be practiced without these specific details without departing from the spirit and scope of the present invention.

[0035] The concepts disclosed in the present invention provide a comprehensive computational systems pathology spatial analysis (CSPSA) platform that is capable of integrating, visualizing, and / or modeling high-dimensional in situ cellular and subcellular resolution imaging data. The CSPSA platform of the concepts disclosed in the present invention combines a core set of existing cellular phenotyping and spatial analysis tools, as well as an advanced toolset for inferring spatial heterogeneous cell communication (cell-to-cell) and intracellular communication patterns, and for building a tumor (or other disease) evolutionary tree from pre-cancerous origins to metastatic endpoints (in the case of cancer). Together, these tools can be used for both research and clinical purposes, such as quantifying spatial intratumoral heterogeneity in tissue samples and in vitro models and correlating it with outcome data, building diagnostic and prognostic applications, and designing personalized treatment strategies and drug discovery. In addition, the platform can be enhanced by enriching in situ cellular and subcellular resolution images with region-specific genomics and spatial transcriptomics data.

[0036] Figure 1 is a schematic diagram of an exemplary computational systems pathology spatial analysis (CSPSA) platform 5 for in situ multi-parameter cellular and subcellular imaging data according to an embodiment of the concepts disclosed in the present invention, in which various methodologies described herein can be implemented. As Figure 1 shown, the CSPSA platform 5 is a computing device configured to receive and store certain multi-parameter cellular and subcellular imaging data 10 (e.g., a large patient cohort of tumors including recurrent and non-recurrent cancers, or a single patient or a single tumor) and process such data 10 as described herein. In a non-limiting exemplary embodiment, multiplex or super-multiplex immunofluorescence imaging is used to generate the multi-parameter cellular and subcellular imaging data 10, but it should be understood that other imaging techniques may also be used, such as those described elsewhere herein. For example, the multi-parameter cellular and subcellular imaging data 10 may be based on an exemplary super-multiplex image stack 12 of all patient data in the cohort, as Figure 2 shown.

[0037] The CSPSA platform 5 can be, for example but not limited to, a PC, a laptop computer, a tablet computer, a smart phone, or any other suitable computing device configured to perform the functions described herein. The CSPSA platform 5 includes an input device 15 (such as a keyboard), a display 20 (such as an LCD), and a processing device 25. As described in detail herein, a user is able to provide input to the processing device 25 using the input device 15, and the processing device 25 provides an output signal to the display 20 to enable the display 20 to display information to the user (such as a spatial map or other spatially dependent image, a microzone image, a weighted map image, and / or a communication network map image). The processing device 25 includes a processor and a memory. The processor can be, for example but not limited to, a microprocessor (μP), a microcontroller, an application specific integrated circuit (ASIC), or some other suitable processing device, which interfaces with the memory. The memory can be any one or more of various types of internal and / or external storage media, such as but not limited to RAM, ROM, EPROM, EEPROM, FLASH, etc., which provide storage registers, i.e., machine-readable media, for data storage in a manner such as the internal storage area of a computer, and can be volatile memory or non-volatile memory. Stored in the memory are many routines executable by the processor, including routines for implementing the concepts disclosed herein. In particular, the processing device 25 includes a spatial heterogeneity quantification component 30, which is configured to generate a global quantification of the spatial heterogeneity between certain different predetermined phenotypes of cells in the multi-parameter cellular and sub-cellular imaging data 10 described herein, a microzone identification component 35, which is configured to identify a plurality of microzones (as described herein) from the multi-parameter cellular and sub-cellular imaging data 10 for a plurality of tumor sections, a weighted map component 40, which is configured to construct a weighted map for the multi-parameter cellular and sub-cellular imaging data 10 based on the global quantification generated by the spatial heterogeneity quantification component 30 (as described herein), and a communication network component 45, which is configured to construct a communication network map for the multi-parameter cellular and sub-cellular imaging data 10 (as described herein).

[0038] Figure 3 is a flowchart illustrating a method for analyzing tumor progression / evolution from multi-parameter cellular and sub-cellular imaging data 10 obtained from a plurality of tumor sections of a patient cohort, which can be implemented in the CSPSA platform 5 according to an exemplary embodiment of the disclosed concepts. However, it will be understood that this is merely exemplary, and Figure 3 the steps of the method shown in can be implemented in other configurations and / or platforms.

[0039] The method begins at step 50 where the spatial heterogeneity quantification component 30 generates a global quantification of spatial heterogeneity in the multi-parameter cellular and sub-cellular imaging data 10. In an exemplary embodiment, the global quantification generated at step 50 is a global spatial map of the multi-parameter cellular and sub-cellular imaging data 10. In a particular embodiment, the global spatial map is a global PMI map 52 (as Figure 4 shown), which is generated in the manner described in PCT application number PCT / US2016 / 036825 and US Patent Application Publication number 2018 / 0204085, which are mentioned elsewhere herein and incorporated herein by reference. In this exemplary embodiment, the multi-parameter cellular and sub-cellular imaging data 10 is created by generating multiple biomarker images from multiple tissue sections by labeling each tissue section with a plurality of different biomarkers (e.g., ER, PR, and HER2). As discussed in the foregoing applications, the PMI map 52 is generated by first performing cell segmentation on the multi-parameter cellular and sub-cellular imaging data 10 (i.e., on each “slice” thereof). Any of a number of known or later developed suitable cell segmentation algorithms may be employed. Then, the spatial location and biomarker intensity data of each cell are obtained, and each cell is assigned to one of a predetermined set of phenotypes (each phenotype being a predetermined major biomarker intensity pattern) based on the biomarker intensity composition of the cell. Figure 5 A schematic representation 56 (labeled 1 to 8) of each of the predetermined major biomarker intensity patterns of the exemplary embodiment is shown. In the exemplary embodiment, each schematic representation 56 is provided in a unique one or more colors such that the schematic representations can be easily distinguished from one another. The above-described cell assignment and Figure 5 the schematic representation shown can be used to generate a cell spatial dependence image that visually demonstrates the heterogeneity of the subject's tissue sample. Figure 6 A cell spatial dependence image 58 according to one particular exemplary embodiment of the disclosed concept is shown. As Figure 6 shown, the cell spatial dependence image 58 shows the spatial dependence (using the schematic representation 56) between the cells of the subject's slide. Then, a spatial network is constructed to describe the organization of the major biomarker intensity patterns in the subject's slide. Then, the heterogeneity of the subject's slide is quantified by generating the PMI map 52 (as Figure 4 shown). In the exemplary embodiment, the spatial network and the PMI map 52 are generated as described below.

[0040] To represent the spatial organization of biomarker patterns in biomarker images (i.e., tissue / tumor samples) of a subject's slide, a network is constructed for the subject's slide. The construction of the spatial network for tumor samples essentially couples cell biomarker intensity data (in the nodes of the network) to spatial data (in the edges of the network). The assumption in network construction is that cells have the ability to communicate with nearby cells within a certain limit (e.g., up to 250 μm), and the ability of cells to communicate within this limit depends on the distance of the cells. Thus, a probability distribution is calculated in an exemplary embodiment for the distances between a cell in the subject's slide and its 10 nearest neighbors. A hard limit is selected by multiplying the median of this distribution by 1.5 (to estimate the standard deviation), where cells in the network are only connected within this limit. Then, the edges between cells in the network are weighted by the distances between adjacent cells.

[0041] Next, in an exemplary embodiment, point mutual information (PMI) is used to measure the association between each pair of biomarker patterns in a dictionary in a subject map, and thus to measure the association between different cell phenotypes. This metric captures general statistical associations, both linear and non-linear, where previous studies have used linear metrics such as Spearman's rho coefficient. Once the PMI has been calculated for each pair of biomarker patterns, a measure of all associations in the subject map data is shown in the PMI map 52. It will be understood that the use of PMI in this embodiment is merely exemplary, and other methods of defining spatial relationships, such as but not limited to Spagnolo DM, Al-Kofahi Y, Zhu P, Lezon TR, Gough A, Stern AM, Lee AV, Ginty F, Sarachan B, Taylor DL, Chennubhotla SC, Platform for Quantitative Evaluation of Spatial Intratumoral Heterogeneity in Multiplexed Fluorescence Images, Cancer Res. 2017 Nov 1, and Nguyen, L., Tosun, B., Fine, J., Lee, A., Taylor, L., Chennubhotla, C. (2017), Spatial statistics for segmenting histological structures in H&E stained tissue images, IEEE Trans Med Imaging. 2017 Mar 16 may be employed in conjunction with the concepts disclosed.

[0042] Exemplary PMI Figure 52 describes the relationship between different cell phenotypes in the microenvironment of the subject's figure. In particular, the entry in PMI Figure 52 indicates the frequency of a specific spatial interaction between two phenotypes (with reference to row and column numbers) occurring in a data set (when compared to the interaction predicted by the random (or background) distribution relative to all phenotypes). The entry of the first color (e.g., red) represents a strong spatial association between the phenotypes, while the entry of the second color (e.g., black) represents a lack of any co-localization (weak spatial association between phenotypes). Other colors can be used to represent other associations. For example, the PMI entry of the third color (e.g., green) represents an association that is not stronger than the random distribution of cell phenotypes in the entire data set. In addition, PMI Figure 52 can depict anti-associations (e.g., if phenotype 1 rarely occurs near phenotype 3 in space) with an entry represented by a fourth color (e.g., blue).

[0043] Reference again Figure 3 , after step 50, the method then proceeds to step 55. At step 55, based on the global quantification generated in step 50, the microregion identification component 35 identifies and localizes one or more microregions in each tumor slice in the multi-parameter cellular and subcellular imaging data 10 (e.g., as described elsewhere herein). For example, a cancer cell type and a particular immune cell type that co-localizes with it may have a high spatial co-occurrence value. Using cancer-immune cell combinations as seed points and mining the global quantification (e.g., spatial map) to propagate phenotypic associations, in any given tissue slice, microregions can be generated by growing a spatial network of cells around the seeds based on a cutoff distance (e.g., ~100 cells). Figure 7 Such exemplary micro-domains 62 are shown in the exemplary tissue section 64 shown.

[0044] Next, at step 60, for each microregion identified in step 55, a local quantification of spatial heterogeneity (e.g., a local spatial map, such as a local PMI map) is determined. Furthermore, each determined local quantification in each tissue section is used to define the degree of similarity between pairs of microregions in the tissue section. In particular, in an exemplary embodiment, given two microregions A and B, a distance function is defined as the difference between (i) the relative abundance of cells in microregions A and B and (ii) their local quantification (e.g., a local spatial map, such as a PMI map). A and PMI B , although other methods may also be used as described herein). This process is repeated for each pair of microregions in all multi-parameter cellular and subcellular imaging data 10. This process will result in a weighted similarity being determined for each pair of microregions in each tissue section.

[0045] Next, at step 65, a method is constructed for constructing the multi-parameter cell and subcellular imaging data 10. Figure 8The weighted micro-region map 66 shown in the exemplary form in []. Each node 68 in the weighted micro-region map 66 is one of the micro-regions generated in step 55, and the edges 72 connecting each pair of micro-regions are weighted by the determined similarity (e.g., the weighted similarity value as described above). Then, the weighted micro-region map 66 can be displayed on the display 20.

[0046] Then, as Figure 3 shown in step 70 of [], the weighted micro-region map 66 can be further analyzed to understand the progression of phenotypes during the metastasis process. It is noted that each whole tissue section in the multi-parametric cellular and sub-cellular imaging data 10 (from relapsed (R) or non-relapsed (NR) patients) has a ground truth label, but there is no prior knowledge to determine which micro-regions best distinguish the two categories. In an exemplary embodiment, the labels R and NR are transferred from the tissue sections to the corresponding micro-regions. Then, some iterations of belief propagation are performed to refine the labels, and then micro-region groups (unified as R or NR) are isolated on the weighted micro-region map 66. By increasing the confidence of label assignment, a betweenness centrality measure can be used to identify the micro-regions most frequently traversed on the path from NR to R. To simulate the evolutionary trajectory, a random walk can be performed on the weighted micro-region map 66, as some micro-regions are known to be found only in the observed or unobserved metastasis data. The relative probabilities of the paths from NR to R can be compared to identify the categories of events important in metastasis. Then, the average first-passage time of the random walk can be used to identify the micro-regions prone to metastasis as a node set, from which the probability of a random walk to R or NR is 0.5. Note that the micro-regions with metastasis potential are the midpoints of the evolutionary trajectories from NR to R. In an exemplary embodiment, the foregoing steps will be performed by the components of the CSPSA platform 5 and displayed to the user on the display screen 20 of the CSPSA platform 5. Thus, this aspect of the disclosed concept provides the ability to define, identify, and compare phenotypes important for metastasis ("phenotypic evolution") as described herein. Additionally, it will be appreciated that cancer is merely one example field to which the disclosed concept can be applied, and the disclosed concept can also be applied to other diseased tissues, such as neurodegenerative diseases, metabolic diseases, and inflammatory diseases, etc.

[0047] Figure 9 is a flowchart showing a method for generating a spatially indicative heterogeneous cell communication representation from multi-parametric cellular and sub-cellular imaging data 10, which in this embodiment is obtained from multiple tumor sections of a patient and can be implemented in the CSPSA platform according to another exemplary embodiment of the disclosed concept. However, it will be understood that this is merely exemplary, andFigure 9 The steps of the method shown can be implemented in other configurations and / or platforms.

[0048] The method begins at step 75, where the spatial heterogeneity quantification component 30 generates a quantification of spatial heterogeneity in the multi-parameter cellular and sub-cellular imaging data 10, as detailed elsewhere herein. As noted elsewhere herein, the quantification of spatial heterogeneity performed at step 75 includes performing cell phenotyping on the multi-parameter cellular and sub-cellular imaging data 10 to identify certain distinct, predetermined phenotypes. In an exemplary embodiment, the quantification generated at step 75 is a spatial map of the multi-parameter cellular and sub-cellular imaging data 10. In a particular implementation, the spatial map is generated in the manner described in PCT application number PCT / US2016 / 036825 and U.S. Patent Application Publication number 2018 / 0204085, which are mentioned elsewhere herein and incorporated herein by reference. In this exemplary embodiment, the multi-parameter cellular and sub-cellular imaging data 10 is created by generating multiple biomarker images from multiple tissue sections by labeling each tissue section with multiple different biomarkers (e.g., ER, PR, and HER2). In a non-limiting exemplary embodiment, multiplex or hyper-multiplex immunofluorescence imaging is used to generate the multi-parameter cellular and sub-cellular imaging data 10, although it will be understood that other imaging techniques, such as those described elsewhere herein, may also be used.

[0049] Next, at step 80, the micro-region identification component 35 identifies and locates one or more micro-regions (as described herein) in each tumor section of the multi-parameter cellular and sub-cellular imaging data 10 based on the quantification generated at step 75. Then, at step 85, one or more of the identified micro-regions are selected. The method then proceeds to step 90.

[0050] At step 90, the communication network component 45 constructs a communication graph for each of the selected micro-regions. The communication graph can be displayed on the display 20. In Figure 10 An exemplary communication graph 92 is shown in Figure 10As shown, in an exemplary embodiment, each phenotype is a node 94 in the communication graph 92, and an edge 96 between each pair of phenotypes (each pair of nodes 94) in the communication graph 92 indicates the effect of one phenotype in the pair on the presence of the other phenotype in the pair. In this exemplary embodiment, each phenotype (each node 94) in the communication graph 92 is represented by a data vector obtained from the multi-parameter cell and subcellular imaging data 10. Additionally, for each pair of phenotypes, a numerical relationship between the pair of phenotypes is established by determining the linear or non-linear correlation coefficient value between the data vectors of the pair of phenotypes (after removing the confounding effects of phenotypes other than the phenotypes in the pair), and the edge 96 in the communication graph 92 in the exemplary embodiment is generated. Further, a directionality is established for each numerical relationship, preferably based on multiple receptor-ligand databases for relevant biomarkers. Thus, in this embodiment, the edge 96 between each pair of nodes 94 indicates the determined numerical relationship and the determined directionality. In the exemplary embodiment, the edge 96 can be colored to represent certain correlation coefficient values (e.g., positive or negative correlation degrees).

[0051] Additionally, in an exemplary embodiment, each data vector of each node 94 is a vector of expression values for multiple predetermined biomarkers, where the predetermined biomarkers are specific biomarkers used to generate the multi-parameter cell and subcellular imaging data 10. For example, each expression value vector can be the biomarker intensity pattern of the predetermined biomarkers determined in step 75. Each data vector can also be analyzed and biologically interpreted to determine multiple activation states 98 of each phenotype (each node 94), and the activation states 98 are included in the communication graph 92. For example, the biomarker ALDH1 is a surrogate for the stemness of tumor cells, and the biomarker PD-L1 determines the mutation burden.

[0052] Figure 11 is a schematic diagram of a specific communication graph 92 generated according to a specific exemplary embodiment, where the phenotypes (nodes 94) are tumor cells, lymphocytes, macrophages, stroma, and necrosis. Various edge effects 96 and activation states 98 are also shown.

[0053] One result of the figures described herein is to infer the pathway of disease progression based on the local tumor microenvironment (TME), and subsequently list the known molecular targets in that pathway. Thereafter, machine learning tools (such as Balestra Web) can be used to predict drug-target interactions based on spatial relationships. This can lead to new uses of drugs and the development of new treatment methods. In addition, multiple exemplary specific clinical applications are described in detail below, which can incorporate aspects of the disclosed concepts (such as the application of the CSPA platform 5), including: (1) drug discovery and personalized medicine strategies (using spatially modulated computational systems pathology), (2) cancer / disease landscapes, which are geometric representations of multi-parameter readings of a patient's cancer / disease state, and (3) the CSPA platform for in vitro models for basic research and clinical translation.

[0054] In a specific exemplary embodiment, the disclosed concepts can be used for drug discovery and personalized medicine strategies (using spatially modulated computational systems pathology). More specifically, spatial intratumoral heterogeneity is a key aspect in determining the temporal evolution of cancer and the fate of patients. This heterogeneity is reflected in the diversity of heterogeneous cell communication networks embedded in microregions, and thus the resulting systems biology is patient-dependent. Current treatment strategies are designed for the general patient and thus cannot reflect the patient-specific systems biology. Patient-specific systems pathology begins with the identification of target microregions / areas, the characterization of the underlying communication network, and the accurate quantification of the interdependence of microregions in space and time. This knowledge is also necessary for new drug design strategies. This strategy can also be enhanced by using region-specific genomics.

[0055] Figure 12 is a schematic representation of a personalized medicine strategy according to this aspect of the disclosed concept, which extends from tissue sectioning to personalized drug treatment. Figure 12 Shown from left to right are i) multi-parameter images at the cellular / subcellular resolution level, ii) identification of target regions (microregions) in the images, iii) reconstruction of the intra-microregion communication network with specific connection weights and spatial relationships between cells / microregions, iv) combining information to extract precise systems biology, and v) defining personalized treatment strategies.

[0056] As Figure 12As shown, in the exemplary embodiment shown, for an individual patient, it was found that sample microregions 1 and 2 are phenotypically different. For this tissue sample, the cell phenotyping algorithm described herein was applied. Next, as described herein, a heterogeneous cell network was constructed for each microregion. Prognostic tests performed separately on microregions 1 and 2 showed that the recurrence risk was low for both microregions. However, when those microregions are very close, the risk of recurrence increases significantly, indicating that there is an information flow between microregions 1 and 2. Thus, in this aspect of the disclosed concept, the heterogeneous cell network indicates which pathways are activated and what the relationship is between the two networks. For example, WNT signaling is upregulated in microregion 2 and downregulated in microregion 1, and TGFβ is upregulated in microregion 1 and downregulated in microregion 2. In this aspect of the disclosed concept, the pathways and microregion networks were identified, and thus the information flow that must be inhibited to slow the cancer progression of a particular patient was also identified. Using this information, personalized medical strategies can be designed.

[0057] In another specific exemplary embodiment, the disclosed concept can be used to precisely describe the temporal evolution of a disease such as cancer in a particular patient. Thus, the disclosed concept defines a cancer landscape, which is a geometric representation of a multi-parameter readout of a patient's cancer state. Each point in the cancer landscape represents the cancer state of the patient, such as pre-cancerous, early stage, invasive stage, etc. The path followed in this landscape describes the temporal evolution of the disease in that particular patient. Current treatment practices use a cancer landscape averaged across the entire patient population. Predictions made using the average model may be inaccurate unless the individual patient profile exactly matches the average profile.

[0058] Figure 13 An exemplary cancer landscape including a geometric representation is shown, where the positioning on the landscape represents the condition of a particular exemplary patient. Figure 13 Taking colon cancer progression as an example, where the basin with label 1 represents the pre-cancerous state, the basin with label 2 represents the small polyp state, the basin with label 3 represents the large polyp state, and the basin with label 4 represents the state of invasive colon cancer. The arrows in the geometric representation show the path that the patient follows from pre-cancer to invasive cancer. From this model, the kinetics of cancer evolution can be inferred.

[0059] In one aspect of this embodiment of the disclosed concept, a traceable patient cohort is tracked (sue) to construct a comprehensive library of microregions as described herein for tissue progression from pre-cancer to metastasis. A specific heterogeneous cell communication network as described herein is associated with each microregion. Additionally, each heterogeneous cell communication network has a systems biology model in the form of a system of ordinary differential equations. The system of ordinary differential equations defines the dynamics of the cancer landscape. For prospective studies, the dynamics help predict the temporal evolution of microregions from pre-cancer to metastasis. Additionally, the dynamics model is a proxy for the synthetic tissue generation model.

[0060] In yet another specific exemplary embodiment, the disclosed concept can be used in conjunction with in vitro models for basic research and clinical translation. More specifically, in two specific applications of the disclosed concept as described above, the platform of the disclosed concept is applied to in situ super-multiplexed single-cell resolved solid tumor imaging. In this embodiment, the same platform is applied to image data from in vitro microphysiological models. Multicellular in vitro models allow for the study of spatiotemporal cell heterogeneity and heterogeneous cell communication, which recapitulate human tissue and can be used to study the mechanisms of disease progression in vitro, test drugs, and characterize the structural organization and content of these models for potential applications in transplantation.

[0061] In vitro models come in the form of 2D cultures, 3D spheroids, organoids, and biomimetic microphysiological systems. The goal of these systems is to be closer to physiologically relevant biomimicry. 2D cultures are cell cultures grown on an adhesive surface. 2D communication networks are developed, so information exchange is limited to two dimensions. 3D spheroids are clusters of cells grown in space. Although the cells are grown in an artificial environment, they better mimic in vivo growth conditions because the cells are allowed to interact and grow in all directions. Organoids are very small but self-organizing three-dimensional tissue cultures. They typically derive from stem cells. Organoids can be made to replicate many of the complexities of an organ, or they can be directed to express a selected aspect of it, such as only producing certain types of cells. The regeneration of organ function, even locally, implies the regeneration of systems biology and heterogeneous cell communication under in vitro controlled conditions. In the case of organoids, the biomimetic microphysiological system is a step towards mimicking organ function. 3D microfluidic channel cell culture chips simulate all the activities, mechanics, and physiological responses of an entire organ. This allows for a more accurate representation of systems biology and heterogeneous cell communication networks.

[0062] In one or more aspects of this particular embodiment, spatiotemporal cellular heterogeneity and heterogeneous cell communication can be monitored by establishing a timeline of images and comparing the evolution of the inferred network in the model. The complexity of the in vitro system from 2D culture to the biomimetic MPS is reflected in the complexity of the systems biology models that can be developed. Although applicable to all possible in vitro models, the biomimetic models constructed by layering or bioprinting different cell types in a suitable 3D tissue will benefit the most by defining the spatial relationships within the model. The same type of system pathology defined in two particular applications of the disclosed concepts described above will be valid here. The aim is to demonstrate that the in vitro model reflects the tissue and spatial relationships of the in situ tissue / organs identified in the study and that systems biology can be generalized in vitro. The model can be established and studied under "normal" healthy conditions or established as a disease model using cells from diseased patients and / or induced pluripotent stem cells (iPSCs) from patients that have been differentiated and matured into the cell types required in the model. After different time points and selected treatments, the model is fixed, embedded, sectioned, and labeled, just like tissue from a patient. Then, hyperplexed imaging modalities are applied to the labeled tissue sections. Then, the computational and systems pathology analysis of the disclosed concepts described herein can be applied to the tissue sections obtained from the model.

[0063] Finally, although the disclosed concepts have been described in connection with imaging data obtained from tumor sections, it should be understood that the disclosed concepts can also be applied to imaging data obtained from other types of tissue sections and / or unsectioned tissue samples (using imaging modalities that can penetrate solid, unsectioned samples).

[0064] In the claims, any reference signs between parentheses shall not be construed as limiting the claim. The words "comprising" or "including" do not exclude the presence of elements or steps other than those listed in the claim. In a device claim enumerating several devices, several of these devices may be embodied by the same hardware. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. In any device claim enumerating several devices, several of these devices may be embodied by the same hardware. The fact that certain elements are recited in mutually different dependent claims does not mean that these elements cannot be used in combination.

[0065] Although the present invention has been described in detail for purposes of illustration based on the currently considered most practical and preferred embodiments, it is to be understood that such details are for illustrative purposes only and that the invention is not limited to the disclosed embodiments, but rather is intended to cover modifications and equivalent arrangements within the spirit and scope of the appended claims. For example, it is understood that the present invention contemplates that, to the extent possible, one or more features of any embodiment may be combined with one or more features of any other embodiment.

[0066] In summary, the present application provides the following embodiments:

[0067] 1. A method for analyzing disease progression from multi-parameter cellular and sub-cellular imaging data, the multi-parameter cellular and sub-cellular imaging data obtained from multiple tissue samples or multiple multi-cellular in vitro models from multiple patients, the method comprising:

[0068] generating a global quantification of spatial heterogeneity between cells of certain different predetermined phenotypes in the multi-parameter cellular and sub-cellular imaging data;

[0069] identifying, based on the global quantification, a plurality of micro-regions for the multiple tissue samples, each micro-region being associated with a respective one of the tissue samples; and

[0070] constructing a weighted graph for the multi-parameter cellular and sub-cellular imaging data, the weighted graph having a plurality of nodes and a plurality of edges, each edge being located between a pair of nodes, wherein in the weighted graph, each node is a particular one of the micro-regions and the edge between each pair of micro-regions in the weighted graph indicates the degree of similarity between the pair of micro-regions.

[0071] 2. The method according to embodiment 1, further comprising, for each pair of micro-regions among the plurality of micro-regions, determining a weighted similarity between the pair of micro-regions, wherein the edge between each pair of micro-regions in the weighted graph is the weighted similarity determined for the pair of micro-regions.

[0072] 3. The method according to embodiment 2, further comprising determining a local quantification of spatial heterogeneity between cells for each identified micro-region, wherein determining the weighted similarity between each pair of micro-regions is based on the local quantification of each micro-region in the pair of micro-regions.

[0073] 4. The method according to embodiment 1, wherein the global quantification is for a spatial graph of the multi-parameter cellular and sub-cellular imaging data.

[0074] 5. The method according to embodiment 4, wherein the spatial graph is a point mutual information (PMI) graph.

[0075] 6. The method according to embodiment 1, wherein the multi-parameter cellular and sub-cellular imaging data includes multiplex or super-multiplex immunofluorescence imaging data.

[0076] 7. The method according to embodiment 1, wherein the predetermined phenotype comprises a predetermined set of patterns of primary biomarker intensities.

[0077] 8. The method according to embodiment 1, wherein a plurality of the identified microregions are associated with an outcome-specific variable in the form of a recurrence time.

[0078] 9. The method according to embodiment 1, wherein a plurality of the identified microregions are associated with an outcome-specific variable indicative of disease progression.

[0079] 10. The method according to embodiment 9, further comprising recommending a treatment strategy based on the outcome-specific variable.

[0080] 11. The method according to embodiment 9, wherein the tissue sample is a tumor sample and wherein the outcome-specific variable indicates metastatic potential.

[0081] 12. A non-transitory computer-readable medium storing one or more programs including instructions that, when executed by a computer, cause the computer to perform the method according to embodiment 1.

[0082] 13. A computerized system for analyzing disease progression from multi-parameter cellular and subcellular imaging data obtained from a plurality of tissue samples or a plurality of multicellular in vitro models from a plurality of patients, the computerized system comprising:

[0083] A processing device, wherein the processing device comprises:

[0084] A spatial heterogeneity quantification component configured to generate a global quantification of spatial heterogeneity between cells of certain different predetermined phenotypes in the multi-parameter cellular and subcellular imaging data;

[0085] A microregion identification component configured to identify a plurality of microregions for the plurality of tissue samples based on the global quantification, each microregion being associated with a respective one of the tissue samples; and

[0086] A weighted graph component configured to construct a weighted graph for the multi-parameter cellular and subcellular imaging data, the weighted graph having a plurality of nodes and a plurality of edges, each edge being located between a pair of nodes, wherein in the weighted graph each node is a particular one of the microregions and an edge between each pair of microregions in the weighted graph indicates the degree of similarity between the pair of microregions.

[0087] 14. The system according to embodiment 13, wherein the weighted graph component is further configured to determine a weighted similarity between each pair of the plurality of microregions, wherein an edge between each pair of microregions in the weighted graph is the weighted similarity determined for the pair of microregions.

[0088] 15. The system according to embodiment 14, wherein the weighted graph component is further configured to determine a local quantification of spatial heterogeneity between cells for each identified micro-region, wherein determining the weighted similarity between each pair of micro-regions is based on the local quantification of each micro-region in the pair of micro-regions.

[0089] 16. The system according to embodiment 13, wherein the global quantification is a spatial graph of the multi-parameter cell and subcellular imaging data.

[0090] 17. The system according to embodiment 16, wherein the spatial graph is a point mutual information (PMI) graph.

[0091] 18. The system according to embodiment 13, wherein the multi-parameter cell and subcellular imaging data includes multiplex or super-multiplex immunofluorescence imaging data.

[0092] 19. The system according to embodiment 13, wherein the predetermined phenotype includes a predetermined set of primary biomarker intensity patterns.

[0093] 20. The system according to embodiment 13, wherein the plurality of identified micro-regions are associated with an outcome-specific variable in the form of recurrence time.

[0094] 21. The system according to embodiment 13, wherein the plurality of identified micro-regions are associated with an outcome-specific variable indicating disease progression.

[0095] 22. The system according to embodiment 21, further comprising a component configured to recommend a treatment strategy based on the outcome-specific variable.

[0096] 23. The system according to embodiment 21, wherein the tissue sample is a tumor sample, and wherein the outcome-specific variable indicates metastatic potential.

[0097] 24. The system according to embodiment 21, further comprising a component configured to guide a treatment strategy based on identifying cell types and activation and evolution states based on the weighted graph.

[0098] 25. A method of generating a spatial indication of heterogeneous cell communication representation from multi-parameter cell and subcellular imaging data, the data obtained from multiple tissue samples or multiple multicellular in vitro models from multiple patients, the method comprising:

[0099] Generate a quantification of spatial heterogeneity between cells of certain different predefined phenotypes in multi-parameter cellular and sub-cellular imaging data, and identify micro-regions of one of the tissue samples based on the quantification, including performing cell phenotype identification on the multi-parameter cellular and sub-cellular imaging data to identify certain different predefined phenotypes; and

[0100] Construct a communication graph for the micro-regions, where each phenotype is a node in the communication graph, and where an edge between each pair of phenotypes in the communication graph indicates the effect of the presence of one phenotype in the pair on the other phenotype in the pair.

[0101] 26. The method according to embodiment 25, wherein each phenotype in the communication graph is represented by a data vector obtained from the multi-parameter cellular and sub-cellular imaging data, and wherein the method includes:

[0102] For each pair of phenotypes, establish a numerical relationship between the pair of phenotypes by determining a correlation coefficient value between the data vectors of the pair of phenotypes, and establish a directionality for each numerical relationship, where an edge between each pair of phenotypes indicates the numerical relationship between the pair of phenotypes and the directionality of the numerical relationship between the pair of phenotypes.

[0103] 27. The method according to embodiment 26, wherein each correlation coefficient value is a linear or non-linear correlation coefficient value.

[0104] 28. The method according to embodiment 26, wherein each data vector is a vector of expression values for a plurality of predefined biomarkers, wherein the predefined biomarkers are used to generate the multi-parameter cellular and sub-cellular imaging data.

[0105] 29. The method according to embodiment 28, wherein each vector of expression values is a biomarker intensity pattern for a plurality of predefined biomarkers.

[0106] 30. The method according to embodiment 28, wherein establishing the directionality for each of the numerical relationships is based on a plurality of receptor-ligand databases for the predefined biomarkers.

[0107] 31. The method according to embodiment 26, further comprising interpreting each data vector to determine a plurality of activation states of each phenotype, and including each of the plurality of activation states in the communication graph.

[0108] 32. The method according to embodiment 26, wherein determining the correlation coefficient value between the data vectors of the pair of phenotypes includes removing the confounding effects of other phenotypes other than the phenotypes in the pair.

[0109] 33. A non - transitory computer - readable medium storing one or more programs including instructions that, when executed by a computer, cause the computer to perform the method according to embodiment 25.

[0110] 34. A non - transitory computer - readable medium storing one or more programs including instructions that, when executed by a computer, cause the computer to perform the method according to embodiment 26.

[0111] 35. A computerized system for generating a spatially - indicative heterogeneous cell - communication representation from multi - parameter cellular and sub - cellular imaging data obtained from multiple tissue samples from multiple patients or multiple multi - cellular in vitro models, the computerized system comprising:

[0112] A processing device, wherein the processing device comprises:

[0113] A spatial - heterogeneity quantification component configured to generate a quantification of spatial heterogeneity between cells of certain different predetermined phenotypes in the multi - parameter cellular and sub - cellular imaging data, including performing cell - phenotype identification on the multi - parameter cellular and sub - cellular imaging data to identify certain different predetermined phenotypes;

[0114] A micro - region identification component configured to identify multiple micro - regions of the multiple tissue samples based on the quantification, each micro - region being associated with one of the tissue samples; and

[0115] A communication - network component configured to construct a communication graph for one of the selected micro - regions, wherein each phenotype is a node in the communication graph, and wherein an edge between each pair of phenotypes in the communication graph indicates the influence of one phenotype in the pair on the presence of the other phenotype in the pair.

[0116] 36. The system according to embodiment 35, wherein each phenotype in the communication graph is represented by a data vector obtained from the multi - parameter cellular and sub - cellular imaging data, and wherein the communication - network component is configured to:

[0117] For each pair of phenotypes, establish a numerical relationship between the pair of phenotypes by determining a correlation - coefficient value between the data vectors of the pair of phenotypes, and establish a directionality for each numerical relationship, wherein an edge between each pair of phenotypes indicates the numerical relationship between the pair of phenotypes and the directionality of the numerical relationship between the pair of phenotypes.

[0118] 37. The system according to embodiment 36, wherein each correlation - coefficient value is a linear or non - linear correlation - coefficient value.

[0119] 38. The system according to embodiment 36, wherein each data vector is a vector of expression values for a plurality of predetermined biomarkers, and wherein the predetermined biomarkers are used to generate the multi-parameter cellular and sub-cellular imaging data.

[0120] 39. The system according to embodiment 38, wherein each expression value vector is a biomarker intensity pattern for a plurality of predetermined biomarkers.

[0121] 40. The system according to embodiment 38, wherein establishing the directionality for each of the numerical relationships is based on a plurality of receptor-ligand databases for the predetermined biomarkers.

[0122] 41. The system according to embodiment 36, wherein the communication network component is further configured to interpret each data vector to determine a plurality of activation states for each phenotype, and include each of the plurality of activation states in a communication graph.

[0123] 42. The system according to embodiment 36, wherein determining the correlation coefficient value between the data vectors of the pair of phenotypes includes removing the confounding effects of other phenotypes other than the phenotypes in the pair.

[0124] 43. A method for creating a personalized medical strategy for a specific patient, wherein the specific patient is one of a plurality of patients, and wherein the plurality of patients are associated with multi-parameter cellular and sub-cellular imaging data of a plurality of tissue samples obtained from the plurality of patients, the method comprising:

[0125] Identifying a plurality of micro-regions in one of the tissue samples associated with the specific patient, wherein the plurality of micro-regions are based on the multi-parameter cellular and sub-cellular imaging data;

[0126] Generating a heterogeneous cell communication network for each micro-region, wherein each heterogeneous cell communication network includes a spatially indicative heterogeneous cell communication representation for the micro-region;

[0127] Generating a quantification of the interdependence of the micro-regions in space and time based on the heterogeneous cell communication network; and

[0128] Designing a medical strategy for the specific patient according to the quantification.

[0129] 44. The method according to embodiment 43, wherein each micro-region is identified by generating a quantification of spatial heterogeneity between cells of certain different predetermined phenotypes in the multi-parameter cellular and sub-cellular imaging data and identifying the micro-regions based on the quantification, including performing cell phenotyping on the multi-parameter cellular and sub-cellular imaging data to identify certain different predetermined phenotypes.

[0130] 45. The method according to embodiment 43, wherein each heterogeneous cell communication network comprises a communication graph for a micro-region, wherein each phenotype is a node in the communication graph, and wherein an edge between each pair of phenotypes in the communication graph indicates the effect of the presence of one phenotype in the pair on the other phenotype in the pair.

[0131] 46. The method according to embodiment 43, wherein each micro-region has a low risk of the target outcome variable, but the spatial proximity and the relationship between the micro-regions increase the overall risk of the target outcome variable.

[0132] 47. The method according to embodiment 43, wherein the heterogeneous cell communication network indicates which pathways are activated within the micro-region and the relationship between the heterogeneous cell communication networks across the micro-regions.

[0133] 48. The method according to embodiment 43, wherein the heterogeneous cell communication network reveals the information flow that must be inhibited by a drug to slow down or reverse the disease progression of a specific patient.

[0134] 49. A method of representing the temporal evolution of disease progression in a specific patient, wherein the specific patient is one of a plurality of patients, and wherein the plurality of patients are associated with multi-parametric cellular and sub-cellular imaging data of a plurality of tissue samples obtained from the plurality of patients, the method comprising:

[0135] Generating a geometric representation of the disease landscape for the specific patient, wherein the geometric representation comprises a plurality of points, and wherein each point on the geometric representation: (i) describes the disease state of the specific patient at a specific time and is based on a specific one of the tissue samples associated with the selected patient, (ii) is based on a micro-region in the specific one of the tissue samples, which is based on the multi-parametric cellular and sub-cellular imaging data, and (iii) comprises a heterogeneous cell communication network for the micro-region, which comprises a spatially indicative heterogeneous cell communication representation for the micro-region.

[0136] 50. The method according to embodiment 49, wherein each heterogeneous cell communication network is associated with a systems biology model comprising a system of ordinary differential equations.

[0137] 51. The method according to embodiment 50, wherein for each heterogeneous cell communication network, the system of ordinary differential equations defines the dynamics of the disease landscape to predict the temporal evolution of the disease landscape for the specific patient.

[0138] 52. The method according to embodiment 49, wherein each microregion is identified by generating a quantification of spatial heterogeneity between cells of certain different predetermined phenotypes in the multi-parameter cellular and subcellular imaging data and identifying the microregion based on the quantification, including performing cell phenotyping on the multi-parameter cellular and subcellular imaging data to identify certain different predetermined phenotypes.

[0139] 53. The method according to embodiment 49, wherein each heterogeneous cell communication network comprises a communication graph for the microregion, wherein each phenotype is a node in the communication graph, and wherein an edge between each pair of phenotypes in the communication graph indicates the influence of the presence of one phenotype in the pair on the other phenotype in the pair.

[0140] 54. The method according to embodiment 1, wherein the plurality of multicellular in vitro models are selected from 2D cultures, 3D spheroids, organoids, and biomimetic microphysiological systems.

[0141] 55. The system according to embodiment 13, wherein the plurality of multicellular in vitro models are selected from 2D cultures, 3D spheroids, organoids, and biomimetic microphysiological systems.

[0142] 56. The method according to embodiment 25, wherein the plurality of multicellular in vitro models are selected from 2D cultures, 3D spheroids, organoids, and biomimetic microphysiological systems.

[0143] 57. The system according to embodiment 35, wherein the plurality of multicellular in vitro models are selected from 2D cultures, 3D spheroids, organoids, and biomimetic microphysiological systems.

Claims

1. A method for generating a spatially indicative heterogeneous cell communication representation from multi-parameter cellular and sub-cellular imaging data, the multi-parameter cellular and sub-cellular imaging data being obtained from multiple tissue samples or multiple multi-cellular in vitro models from multiple patients, the method comprises: identifying micro-regions of one of the tissue samples based on quantification of spatial heterogeneity between cells of multiple predetermined cell types in the multi-parameter cellular and sub-cellular imaging data; and constructing a communication graph for the micro-regions, wherein each predetermined cell type is a node in the communication graph, and wherein an edge between each pair of nodes in the communication graph indicates the influence of one of the predetermined cell types in the pair on the presence of the other predetermined cell type in the pair.

2. The method according to claim 1, wherein each node in the communication graph is represented by a data vector obtained from the multi-parameter cellular and sub-cellular imaging data, and wherein an edge between each pair of nodes in the communication graph indicates one or more statistical and spatial relationships between the data vectors of the pair of nodes.

3. The method according to claim 2, wherein the one or more statistical and spatial relationships between the pair of nodes are linear or non-linear.

4. The method according to claim 2, wherein the one or more statistical and spatial relationships between the pair of nodes are based on point mutual information.

5. The method according to claim 1, wherein each node in the communication graph is represented by a data vector obtained from the multi-parameter cellular and sub-cellular imaging data, and wherein an edge between each pair of nodes in the communication graph indicates the correlation between the data vectors of the pair of nodes.

6. The method according to claim 5, wherein an edge between each pair of nodes in the communication graph indicates a numerical relationship between the data vectors of the pair of nodes, including a determined linear or non-linear correlation coefficient value between the data vectors of the pair of nodes.

7. The method according to claim 6, wherein each numerical relationship has a directionality.

8. The method according to claim 7, wherein each edge is colored to represent the determined linear or non-linear correlation coefficient value of the edge.

9. The method according to claim 2, wherein each data vector is a vector of expression values for multiple predetermined biomarkers, wherein the predetermined biomarkers are used to generate the multi-parameter cellular and sub-cellular imaging data.

10. The method according to claim 9, wherein each expression value vector is a biomarker intensity pattern for the multiple predetermined biomarkers.

11. The method according to claim 9, wherein an edge between each pair of nodes in the communication graph indicates a numerical relationship between the data vectors of the pair of nodes, including a determined linear or non-linear correlation coefficient value between the data vectors of the pair of nodes, and wherein each numerical relationship has a directionality based on multiple receptor-ligand databases for the predetermined biomarkers.

12. The method according to claim 2, further comprising interpreting each data vector to determine multiple activation states of each node, and including each of the multiple activation states in the communication graph.

13. The method according to claim 6, wherein each determined linear or non-linear correlation coefficient value is determined after removing the confounding effects of other cell types other than the cell types in the pair.

14. A non-transitory computer-readable medium storing one or more programs including instructions that, when executed by a computer, cause the computer to perform the method according to claim 1.

15. A computerized system for generating a spatially indicative heterogeneous cell communication representation from multi-parametric cell and subcellular imaging data obtained from multiple tissue samples or multiple multicellular in vitro models from multiple patients, the computerized system comprising: a processing device, wherein the processing device comprises: a spatial heterogeneity quantification component configured to generate a quantification of the spatial heterogeneity between cells of multiple predetermined cell types in multi-parametric cell and subcellular imaging data; a micro-region identification component configured to identify a micro-region for one of the tissue samples based on the quantification; and a communication network component configured to construct a communication graph for the micro-region, wherein each predetermined cell type is a node in the communication graph, and wherein an edge between each pair of nodes in the communication graph indicates the influence of one predetermined cell type in the pair on the presence of the other predetermined cell type in the pair.

16. The system according to claim 15, wherein each node in the communication graph is represented by a data vector obtained from the multi-parametric cell and subcellular imaging data, and wherein an edge between each pair of nodes in the communication graph indicates one or more statistical and spatial relationships between the data vectors of the pair of nodes.

17. The system according to claim 16, wherein the one or more statistical and spatial relationships between the pair of nodes are linear or non-linear.

18. The system according to claim 16, wherein the one or more statistical and spatial relationships between the pair of nodes are based on point mutual information.

19. The system according to claim 15, wherein each node in the communication graph is represented by a data vector obtained from multi-parametric cell and subcellular imaging data, and wherein an edge between each pair of nodes in the communication graph indicates the correlation between the data vectors of the pair of nodes.

20. The system according to claim 19, wherein an edge between each pair of nodes in the communication graph indicates a numerical relationship between the data vectors of the pair of nodes, including a determined linear or non-linear correlation coefficient value between the data vectors of the pair of nodes.

21. The system according to claim 20, wherein each numerical relationship has a directionality.

22. The system according to claim 21, wherein each edge is colored to represent the determined linear or non-linear correlation coefficient value of the edge.

23. The system according to claim 16, wherein each data vector is a vector of expression values for multiple predetermined biomarkers, and wherein the predetermined biomarkers are used to generate the multi-parametric cell and subcellular imaging data.

24. The system according to claim 23, wherein each expression value vector is a biomarker intensity pattern for the multiple predetermined biomarkers.

25. The system according to claim 23, wherein an edge between each pair of nodes in the communication graph indicates a numerical relationship between the data vectors of the pair of nodes, including a determined linear or non-linear correlation coefficient value between the data vectors of the pair of nodes, and wherein each numerical relationship has a directionality based on a plurality of receptor-ligand databases for the predetermined biomarker.

26. The system according to claim 16, wherein the communication network component is configured to interpret each data vector to determine a plurality of activation states of each node, and to include each of the plurality of activation states in the communication graph.

27. The system according to claim 20, wherein each determined linear or non-linear correlation coefficient value is determined after removing the confounding effects of cell types other than the cell types in the pair.

28. A method of representing the temporal evolution of disease progression in a specific patient, wherein the specific patient is one of a plurality of patients, and wherein the plurality of patients is associated with multi-parametric cellular and sub-cellular imaging data of a plurality of tissue samples obtained from the plurality of patients, the method comprises: generating a geometric representation of a disease landscape for a specific patient, wherein the geometric representation includes a plurality of points, and wherein each point on the geometric representation: (i) describes the disease state of the specific patient at a specific time and is based on a specific one of the tissue samples associated with the selected patient, (ii) is based on a micro-region in the specific one of the tissue samples, the micro-region being based on the multi-parametric cellular and sub-cellular imaging data, wherein the micro-region includes a plurality of predetermined cell types, and (iii) includes a heterogeneous cell communication graph for the micro-region, which includes a spatially indicative heterogeneous cell communication representation for the micro-region, wherein each predetermined cell type is a node in the communication graph, and wherein an edge between each pair of nodes in the communication graph indicates the effect of one predetermined cell type in the pair on the presence of the other predetermined cell type in the pair.

29. The method according to claim 28, wherein each node in the communication graph is represented by a data vector obtained from the multi-parametric cellular and sub-cellular imaging data, and wherein an edge between each pair of nodes in the communication graph indicates one or more statistical and spatial relationships between the data vectors of the pair of nodes.

30. The method according to claim 29, wherein the one or more statistical and spatial relationships between the pair of nodes are linear or non-linear.

31. The method according to claim 29, wherein the one or more statistical and spatial relationships between the pair of nodes are based on point mutual information.

32. The method according to claim 28, wherein each node in the communication graph is represented by a data vector obtained from the multi-parametric cellular and sub-cellular imaging data, and wherein an edge between each pair of nodes in the communication graph indicates the correlation between the data vectors of the pair of nodes.

33. The method according to claim 32, wherein an edge between each pair of nodes in the communication graph indicates a numerical relationship between the data vectors of the pair of nodes, including a determined linear or non-linear correlation coefficient value between the data vectors of the pair of nodes.

34. The method according to claim 33, wherein each numerical relationship has a directionality.

35. The method according to claim 28, wherein each heterogeneous cell communication map is associated with a systems biology model comprising a system of ordinary differential equations.

36. The method according to claim 35, wherein for each heterogeneous cell communication map, the system of ordinary differential equations defines the dynamics of the disease landscape to predict the temporal evolution of the disease landscape for the particular patient.

Images