All-in-one liver disease insight system

Abstract

Various techniques related to providing an assessment of a health of a liver are disclosed. Some example embodiments include a method for quantitatively assessing a health of a liver. The method can include obtaining a set of data related to the liver, processing the set of data by implementing at least one of multiple processing tools, determining a value or a characteristic associated with the liver based on results of processing the set of data, and enabling assessment of the health of the liver based on the value or the characteristic.

Description

PCT Patent ApplicationAttorney Docket No.: 009062.8554. WO00ALL-IN-ONE LIVER DISEASE INSIGHT SYSTEMCROSS-REFERENCE TO RELATED APPLICATION

[0001] This patent document claims priority to and benefits of U.S. Provisional Application 63 / 697,417, entitled “ALL-IN-ONE LIVER DISEASE INSIGHT SYSTEM,” and filed on September 20, 2024. The entire content of the above noted patent application is incorporated by reference as pail of the disclosure of this patent document.TECHNICAL FIELD

[0002] Disclosed herein are methods, devices, and systems relating to techniques for assessing liver disease.BRIEF DESCRIPTION OF THE DRAWINGS

[0003] FIG. 1 shows example interfaces and graphical representations related to liver health that can be obtained in an example embodiment of the disclosed technology.

[0004] FIG. 2 shows an example of a hardware platform that can be implemented with embodiments of the disclosed technology.

[0005] FIG. 3 shows a flow diagram of an example method according to an embodiment of the disclosed technology.

[0006] FIG. 4 shows a flow diagram of an example method according to another embodiment of the disclosed technology.DETAILED DESCRIPTION

[0007] In the current state of the art, the gold standard for the assessment of liver-related diseases and conditions is liver biopsy as there is no centralized software for comprehensive non- invasive liver disease assessment. Instead, existing techniques typically comprise multiple nonintegrated, partial solutions.

[0008] In recognition of these challenges, the present patent document discloses various embodiments to provide integrated, robust, and holistic techniques for assessing a broad spectrum of liver disease, including chronic liver conditions and focal liver lesions. Embodiments of the disclosed technology can be employed in various applications including diagnosis, risk stratification, monitoring, treatment response assessment, prognostication, andPCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO prediction. The disclosed embodiments provide non-invasive approaches that can be implemented in diagnosis, liver disease severity and grading, monitoring of disease progression, and guidance of treatment decisions.

[0009] Some example embodiments relate to a computer program product that can extract features from medical data to aid in the diagnosis, assessment, progression monitoring, and / or risk analysis of liver disease.

[0010] Some example embodiments relate to a multi-part software solution for comprehensive liver disease analysis that integrates a centralized database that includes multimodal imaging data, multi -omic data, and electronic health records (EHR) (e.g. Liver Imaging Reporting and Data System, LI-RADS).

[0011] Some example embodiments relate to an omni-liver health diagnostic system, where each part of the system employs specific methods and software for specific data types. Example techniques that can be implemented in the system include: artificial intelligence (Al)-driven techniques for analyzing multimodal imaging, advanced genomics for extracting features from gene expression, proteomics, and metabolomics, and Natural language Processing models for processing both structured and unstructured medical reports.

[0012] The disclosed embodiments, among other features and benefits, include techniques which may utilize an intuitive graphical user interface, provide classification and quantification capabilities, and include a centralized database that seamlessly integrates multimodal imaging data, multi-ohmic data, and EHR records (e.g. LI-RADS).

[0013] Various embodiments of the disclosed technology may be embodied as a computer program product.

[0014] In one aspect, a method for quantitatively assessing a health of a liver is disclosed. The method comprises: providing a platform comprising multiple tools configured to enable processing of a set of data related to the liver, wherein the set of data comprises: (i) measured data of the liver including one or more images of the liver, and (ii) one or both of historical health information of the liver and omic data associated with a biological sample of the liver, wherein the multiple tools include: artificial intelligence (Al) tools configured to analyze the one or more images to extract features of the liver from the one or more images, additional Al tools configured to analyze historical records associated with the liver to obtain the historical healthPCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO information of the liver, and genomic tools configured to determine, based on the omic data, genomic features related to the liver; processing the set of data using at least one of the multiple tools to determine one or both of a value or a characteristic associated with the liver; and enabling assessment of the health of the liver based on the one or both of the value or the characteristic.

[0015] In another aspect, a method for quantitatively assessing a health of a liver is disclosed. The method comprises: obtaining a set of data related to the liver, wherein the set of data comprises: (i) measured data of the liver including one or more images of the liver, and (ii) one or both of historical health information of the liver and omic data associated with a biological sample of the liver, wherein the historical health information is obtained using an artificial intelligence (Al) tool configured to analyze historical records associated with the liver; processing the set of data by implementing at least one of multiple processing tools, wherein the multiple processing tools include: artificial intelligence (Al) tools configured to analyze the one or more images to extract features of the liver from the one or more images, and genomic tools configured to determine, based on the omic data, genomic features related to the liver; determining one or both of a value or a characteristic associated with the liver based on results of processing the set of data; and enabling assessment of the health of the liver based on the one or both of the value or the characteristic.

[0016] In another aspect, a computer program product is disclosed. The computer program product comprises instructions, which, when the computer program product is executed by a computer, cause the computer to implement a method for quantitatively assessing health of a liver as recited in this patent document.

[0017] In another aspect, a data processing apparatus is disclosed. The data processing apparatus is configured to implement a method for quantitatively assessing health of a liver as recited in this patent document.

[0018] In another aspect, a computer system that includes one or more computing platforms may be configured to implement any of the above-described methods.

[0019] In yet another aspect, any of the above-described methods may be embodied in the form of computer-executable code and stored on a storage medium.

[0020] The present patent application discloses some embodiments that can be implemented into systems for quantitatively assessing a health of a liver.PCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO

[0021] These, and other, features and aspects are further disclosed in the present document.

[0022] In an example embodiment, a liver health diagnostic system is provided. The system can be implemented in various applications such as diagnosis, assessment, progression monitoring, and / or risk analysis of liver disease. The system may be implemented to extract features from different types of medical data. Each part of the system may employ various methods and / or software based on data type.

[0023] FIG. 1 shows example interfaces and graphical representations related to liver health that can be obtained in an example embodiment of the disclosed technology. In the example embodiment of FIG. 1, a multi-part software tool is provided. The multi-part software tool provides a myriad of liver quantification features including segmentation, multilabel classification, vasculature visualization, and fat fraction distribution. In some implementations of the multi-part software tool, specific methods and software are provided and implemented for particular' data types. For example, the multi-part software tool may implement one or more of (i) artificial intelligence (Al)-driven techniques for analyzing multimodal liver imaging, (ii) advanced genomics for extracting features from gene expression, proteomics, and metabolomics from various biological samples, including blood, urine, saliva, and stool, and (iii) natural language processing models for extracting data elements from both structured and unstructured medical reports. As shown in FIG. 1, the multi-part software tool can provide both 2D and 3D visualization of liver-related health data.

[0024] In some implementations, the multi-part software tool employs machine learning and Al techniques to extract and visualize important features from multimodal liver images / volumes (e.g., MRI-derived fat fraction images or advanced MRI sequences, such as proton density fat fraction (PDFF) images and magnetic resonance elastography (MRE), along with other imaging modalities like CT and ultrasound) for the diagnosis of liver diseases such as metabolic dysfunction-associated steatotic liver disease (MASLD) and its progressive form, metabolic dysfunction-associated steatohepatitis (MASH). These liver conditions are associated with metabolic syndrome and can lead to cirrhosis if untreated. Another condition, called Hepatocellular carcinoma (HCC), often arises as a complication of chronic liver diseases, including MASLD and MASH, and requires comprehensive examination for effective management and treatment. One example advantage of the disclosed technology, among other features and benefits, is the design of a modality- and vendor-agnostic deep learning model thatPCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO can segment the liver volume, its anatomic components, its vessels, and any focal liver lesions it may contain.

[0025] In another example embodiment, a system to provide multi-modal analysis and quantification of liver health is provided. The system can automatically extract and segment the liver from multimodal liver images / volumes (e.g., MRI-derived fat fraction images or advanced MRI sequences, PDFF images, MRE data, CT images, and ultrasound images). The system can be implemented to calculate features such as liver volume, fat characteristics, and the segmented liver regions. The system can implement various software to enable both 2D and 3D visualizations of the liver, its PDFF, and its vasculature, among other possibilities. The system can be implemented to output morphological characteristics to assess structural changes in the liver and its vasculature with disease progression. In some implementations, the system employs one or more Al agents and multiple Al models can be combined probabilistically to produce an optimized segmentation of the liver, vasculature, and other related structures important for the quantification of liver disease.

[0026] Some disclosed embodiments can be implemented to provide an assessment of liver disease and employ advanced generative Al techniques, such as Generative adversarial networks (GANs), Variational Autoencoders(VAE)s, and diffusion models, or their combination to map CT and other fat quantification modalities, like ultrasound, directly to MR PDFF maps or between different MRI sequences from various vendors, with similar approaches applicable to ultrasound imaging across different manufacturers. By leveraging the strengths of these models — e.g., GANs for realistic cross-modal translation, VAEs for probabilistic mapping in shared latent spaces, and diffusion models for high-fidelity image synthesis — implementations of the disclosed embodiments can transform between imaging modalities used for liver fat quantification accurately. This approach ensures compatibility across diverse imaging technologies, addressing challenges posed by varying acquisition protocols and hardware differences.

[0027] In some example embodiments, a centralized Al platform is provided and includes a dedicated pipeline for the analysis of medical reports of liver patients. In some implementations, the analysis uses NLP models and incorporates large language models (LLMs) using transformers (e.g., BERT, GPT, or similar), to extract, analyze, and synthesize information from large datasets of structured and unstructured medical reports, including clinical notes, imagingPCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO reports, lab results, and patient histories. These models can be used, for example, to identify relevant clinical biomarkers, extract insights on liver disease progression, risk factors, and treatment outcomes, and correlate them with imaging findings like fat fraction information from MRI or related fat quantification modalities such as ultrasound, facilitating enhanced clinical decision-making and personalized treatment strategies.

[0028] By combining the diverse data sources and analytical tools as described in this patent document, the disclosed embodiments can assess and provide a holistic and accurate quantitative analysis of liver health, and the progression of liver disease and deliver risk evaluations with accumulation of enough patients in the database.

[0029] FIG. 2 shows an example hardware platform 200. One or more such platforms 200 may be used to implement a system or method described herein. In various embodiments, the platform(s) 200 may be used for a distributed computing system or may correspond to computing sources located in a computing cloud.

[0030] The platform 200 may include one or more processors 202. The processors 202 may be configured to execute code. The platform 200 may include one or more memories 204 for storage of code, data and intermediate results of execution. The platform 200 may include one or more interfaces 206 for data input or output. For example, the interfaces 206 may be a network connection such as a wired Ethernet or wireless Wi-Fi connection or may be communication ports such as USB, and the like. Various techniques described in the present patent document may be implemented in a cloud-based computing system where multiple hardware platform 200 may be present.

[0031] In an example study, performance of an all-in-one liver disease insight system according to an embodiment of the disclosed technology was cross-validated using ground-truth data extracted by expert radiologists from two patient groups, one with MASLD and the other with MASH. It was demonstrated that the liver disease insight system can automatically extract and segment the liver from various MR modalities across different vendors, including anatomical liver images, PDFF images obtained using techniques like IDEAL or LipoQuant, R2* maps, and water images, and both in-phase and out-of-phase images. The liver disease insight system can also calculate features such as liver volume, fat content, regional iron content, and segmented liver regions, offering a comprehensive analysis of liver health across multiple imaging parameters. In some implementations, the liver disease insight system is embodied as a softwarePCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO and can provide both 2D and 3D visualizations of the liver, its PDFF, and its vasculature. The software may also output morphological characteristics to assess structural changes in the liver and its vasculature with disease progression. Additionally, the software may employ one or more Al agents and multiple Al models can be combined probabilistically to produce an optimized segmentation of the liver, vasculature, and other related structures important for the quantification of liver disease.

[0032] Example embodiments of a liver health assessment tool based on the disclosed technology can be implemented to address the shortage of user-friendly software for real-time liver assessment in NAFLD and NASH.

[0033] An example embodiment of a non-invasive, liver health assessment tool was employed in an example study. The tool utilizes advanced image processing (e.g., of MRI data) and Al techniques which can aid gastroenterologists and radiologists in diagnosing liver abnormalities, reducing the need for invasive liver biopsies. In the example study, MRI data from 114 patients (mean age: 51.2 years, SD: 11.5; mean BMI: 33.6, SD: 5.14) from the FLINT study and 113 patients (mean age: 13.7 years, SD: 11.5; mean BMI: 32, SD: 6.8) from the CyNCh study were utilized. Advanced convolutional neural network (CNN) models, including U-Net 2D and 3D, U-Net++, Seg-Net, and V-Net, were optimized and trained on radiologist- annotated masks derived from MRI images. Separate models were trained for liver segmentation, multi-label anatomical labeling into 8 Couinaud segments, vasculature segmentation, and direct mapping of MRI magnitude volumes to PDFF without additional acquisitions. Results obtained in the study demonstrate the effectiveness of the disclosed liver health assessment tool, with all CNN models achieving Dice similarity scores exceeding 0.94 (0.96 for 3D U-Nets), indicating strong agreement with ground truth annotations (80-20 split, 5-fold cross-validation) for segmentation. For Couinaud classification and magnitude to PDFF mapping, average Dice scores were 0.85 and 0.84, respectively.

[0034] The example embodiments offer a significant advancement in liver disease diagnosis. Some example embodiments provide a user-friendly platform for accurate segmentation, analysis, and quantification of the liver including in NASH and NAFLD. Among other features and benefits, the disclosed embodiments can provide automated liver and vasculature segmentation and visualization, along with quantification of 3D volumetric liver shape changes and features like volume and regional curvatures for disease progression monitoring.PCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOOAdditionally, some disclosed embodiments include statistical shape means for both NASH and NAFLD populations, enabling clinicians to compare new patients in terms of liver volume, 3D surface geometric characteristics, regional fat fraction distribution, and vasculature against those with NAFLD and NASH.

[0035] FIG. 3 shows a flow diagram of an example method 300 for quantitatively assessing a health of a liver according to an embodiment of the disclosed technology. At step 310, the method 300 includes providing a platform comprising multiple tools configured to enable processing of a set of data related to the liver. At step 320, the method 300 includes processing the set of data using at least one of the multiple tools to determine one or both of a value or a characteristic associated with the liver. At step 330, the method 300 includes enabling assessment of the health of the liver based on the one or both of the value or the characteristic. In some implementations, the set of data comprises: (i) measured data of the liver including one or more images of the liver, and (ii) one or both of historical health information of the liver and omic data associated with a biological sample of the liver. In some implementations, the multiple tools include: artificial intelligence (Al) tools configured to analyze the one or more images to extract features of the liver from the one or more images, additional Al tools configured to analyze historical records associated with the liver to obtain the historical health information of the liver, and genomic tools configured to determine, based on the omic data, genomic features related to the liver.

[0036] FIG. 3 shows a flow diagram of an example method 400 for quantitatively assessing a health of a liver according to an embodiment of the disclosed technology. At step 410, the method 400 includes obtaining a set of data related to the liver. At step 420, the method 400 includes processing the set of data by implementing at least one of multiple processing tools. At step 430, the method 400 includes determining one or both of a value or a characteristic associated with the liver based on results of processing the set of data. At step 440, the method 400 includes enabling assessment of the health of the liver based on the one or both of the value or the characteristic. In some implementations, the set of data comprises: (i) measured data of the liver including one or more images of the liver, and (ii) one or both of historical health information of the liver and omic data associated with a biological sample of the liver. In some implementations, the historical health information is obtained using an artificial intelligence (Al) tool configured to analyze historical records associated with the liver. In some implementations,PCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO the multiple processing tools include: artificial intelligence (Al) tools configured to analyze the one or more images to extract features of the liver from the one or more images, and genomic tools configured to determine, based on the omic data, genomic features related to the liver.

[0037] Embodiments of the disclosed technology support inter alia the following technical solutions.

[0038] 1. A method for quantitatively assessing a health of a liver, comprising: providing a platform comprising multiple tools configured to enable processing of a set of data related to the liver, wherein the set of data comprises: (i) measured data of the liver including one or more images of the liver, and (ii) one or both of historical health information of the liver and omic data associated with a biological sample of the liver, wherein the multiple tools include: artificial intelligence (Al) tools configured to analyze the one or more images to extract features of the liver from the one or more images, additional Al tools configured to analyze historical records associated with the liver to obtain the historical health information of the liver, and genomic tools configured to determine, based on the omic data, genomic features related to the liver; processing the set of data using at least one of the multiple tools to determine one or both of a value or a characteristic associated with the liver; and enabling assessment of the health of the liver based on the one or both of the value or the characteristic.

[0039] 2. The method of solution 1 , wherein the one or more images include images obtained using different imaging modalities, wherein the different imaging modalities include a magnetic resonance (MR)-based imaging modality, a computerized tomography (CT) imaging modality, or an ultrasound imaging modality.

[0040] 3. The method of solution 1, wherein the Al tools are configured to analyze the one or more images by: identifying a region of interest in the one or more images, wherein at least a portion of the liver is visualized within the region of interest, determining a set of image segments within the one or more images, wherein the set of image segments correspond to the region of interest, and determining the value or the characteristic based on some or all of the image segments in the set of image segments.

[0041] 4. The method of solution 3, wherein the set of image segments corresponds to an anatomical component, a vasculature of the liver, or an abnormality of the liver.

[0042] 5. The method of solution 4, wherein the set of image segments are optimized according to an optimization procedure.PCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO

[0043] 6. The method of solution 1 , comprising using the platform to obtain a visualization of the liver, a structure of the liver, a proton density fat fraction (PDFF) of the liver, or a vasculature of the liver, wherein the visualization is two-dimensional or three-dimensional.

[0044] 7. The method of solution 1, wherein the value or the characteristic relates to a volume of the liver, a shape of the liver, a fat metric of the liver, or a vasculature of the liver.

[0045] 8. The method of solution 1, wherein the assessment is used to diagnose a disease of the liver, evaluate a risk of disease of the liver, evaluate a severity or grading of a disease of the liver, or monitor progression of a disease of the liver.

[0046] 9. The method of solution 1, wherein the set of data is stored in a database.

[0047] 10. The method of solution 9, wherein the database is accessible via the platform.

[0048] 11. The method of solution 10, wherein the additional Al tools include NaturalLanguage Processing models (NLP) configured to extract data elements from the historical records, wherein at least some of the historical records have a structured or an unstructured format.

[0049] 12. The method of solution 1, wherein the omic data includes information of the liver related to at least one of gene expression, proteomics, or metabolomics.

[0050] 13. A method for quantitatively assessing a health of a liver, comprising: obtaining a set of data related to the liver, wherein the set of data comprises: (i) measured data of the liver including one or more images of the liver, and (ii) one or both of historical health information of the liver and omic data associated with a biological sample of the liver, wherein the historical health information is obtained using an artificial intelligence (Al) tool configured to analyze historical records associated with the liver; processing the set of data by implementing at least one of multiple processing tools, wherein the multiple processing tools include: artificial intelligence (Al) tools configured to analyze the one or more images to extract features of the liver from the one or more images, and genomic tools configured to determine, based on the omic data, genomic features related to the liver; determining one or both of a value or a characteristic associated with the liver based on results of processing the set of data; and enabling assessment of the health of the liver based on the one or both of the value or the characteristic.

[0051] 14. The method of solution 13, wherein the one or more images include images obtained using different imaging modalities, wherein the different imaging modalities include aPCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO magnetic resonance (MR)-based imaging modality, a computerized tomography (CT) imaging modality, or an ultrasound imaging modality.

[0052] 15. The method of solution 13, wherein the Al tools are configured to analyze the one or more images by: identifying a region of interest in the one or more images, wherein at least a portion of the liver is visualized within the region of interest, determining a set of image segments within the one or more images, wherein the set of image segments correspond to the region of interest, and determining the value or the characteristic based on some or all of the image segments in the set of image segments.

[0053] 16. The method of solution 15, wherein the set of image segments corresponds to an anatomical component, a vasculature of the liver, or an abnormality of the liver.

[0054] 17. The method of solution 16, wherein the set of image segments are optimized according to an optimization procedure.

[0055] 18. The method of solution 13, comprising obtaining a visualization of the liver, a structure of the liver, a proton density fat fraction (PDFF) of the liver, or a vasculature of the liver, wherein the visualization is two-dimensional or three-dimensional.

[0056] 19. The method of solution 13, wherein the value or the characteristic relates to a volume of the liver, a shape of the liver, a fat metric of the liver, or a vasculature of the liver.

[0057] 20. The method of solution 13, wherein the assessment is used to diagnose a disease of the liver, evaluate a risk of disease of the liver, evaluate a severity or grading of a disease of the liver, or monitor progression of a disease of the liver.

[0058] 21. The method of solution 1, wherein the omic data includes information of the liver related to at least one of gene expression, proteomics, or metabolomics.

[0059] 22. A computer program product comprising instructions, which, when the computer program product is executed by a computer, cause the computer to implement a method for quantitatively assessing health of a liver as recited in any one of solutions 1-21.

[0060] 23. A data processing apparatus configured to implement a method for quantitatively assessing health of a liver as recited in any one of solutions 1-21.

[0061] 24. A computer-implemented method for assessing liver disease, comprising: extracting, from a set of images, features that describe a liver of a subject; determining, from the images and one or more biological samples, data related to thePCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO liver of the subject; processing the data using a processing model configured to determine, from the set of images, one or more anatomical components of the liver of the subject; and making an assessment of liver disease in the subject based on results of the processing.

[0062] 25. The computer-implemented method of solution 1, further comprising: obtaining medical reports from a population of subjects; and creating a dataset based on information included in the medical reports, wherein making the assessment of liver disease comprises analyzing the dataset to identify liver disease biomarkers in the population of subjects.

[0063] 26. The computer-implemented method of solution 2, wherein the analyzing is performed using a natural language processing model.

[0064] 27. The computer- implemented method of solution 1, wherein the extracting is performed using at least one of a machine learning or artificial intelligence algorithm.

[0065] 28. The computer-implemented method of solution 1, wherein at least some of the images in the set are obtained using different imaging modalities.

[0066] 29. The computer- implemented method of solution 1, wherein set of images include one or more of a proton density fat fraction (PDFF) image, a magnetic resonance elastography (MRE) image, a computed tomography (CT) image, and an ultrasound image.

[0067] 30. The computer-implemented method of solution 1, wherein the set of images are visualized on a graphical user interface.

[0068] 31. The computer- implemented solution of claim 1, wherein the assessment comprises making a diagnosis of metabolic dysfunction-associated steatotic liver disease (MASLD), metabolic dysfunction-associated steatohepatitis (MASH), or Hepatocellular carcinoma (HCC).

[0069] 32. A data processing device configured to carry out any of the methods of solutions24-31.

[0070] 33. A computer program product comprising instructions, which, when the program is executed by a computer, cause the computer to carry out any of the methods of solutions 24-31.

[0071] Implementations of the subject matter and the functional operations described in this patent document can be implemented in various systems, digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Implementations of the subject matter described in this specification can be implemented as one or more computerPCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO program products, i.e., one or more modules of computer program instractions encoded on a tangible and non-transitory computer readable medium for execution by, or to control the operation of, data processing apparatus. The computer readable medium can be a machine- readable storage device, a machine-readable storage substrate, a memory device, a composition of matter effecting a machine-readable propagated signal, or a combination of one or more of them. The term “data processing unit” or “data processing apparatus” encompasses all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. The apparatus can include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them.

[0072] A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

[0073] The processes and logic flows described in this specification can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).

[0074] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from aPCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO read only memory or a random access memory or both. The essential elements of a computer are a processor for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks. However, a computer need not have such devices. Computer readable media suitable for storing computer program instructions and data include all forms of nonvolatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0075] Only a few implementations and examples are described and other implementations, enhancements and variations can be made based on what is described and illustrated in this patent document.

Claims

1. PCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOOWhat is claimed is:

1. A method for quantitatively assessing a health of a liver, comprising: providing a platform comprising multiple tools configured to enable processing of a set of data related to the liver, wherein the set of data comprises: (i) measured data of the liver including one or more images of the liver, and (ii) one or both of historical health information of the liver and omic data associated with a biological sample of the liver, wherein the multiple tools include: artificial intelligence (Al) tools configured to analyze the one or more images to extract features of the liver from the one or more images, additional Al tools configured to analyze historical records associated with the liver to obtain the historical health information of the liver, and genomic tools configured to determine, based on the omic data, genomic features related to the liver; processing the set of data using at least one of the multiple tools to determine one or both of a value or a characteristic associated with the liver; and enabling assessment of the health of the liver based on the one or both of the value or the characteristic.

2. The method of claim 1, wherein the one or more images include images obtained using different imaging modalities, wherein the different imaging modalities include a magnetic resonance (MR)-based imaging modality, a computerized tomography (CT) imaging modality, or an ultrasound imaging modality.

3. The method of claim 1, wherein the Al tools are configured to analyze the one or more images by:PCT Patent Application Attorney Docket No.: 009062.8554. WOOO identifying a region of interest in the one or more images, wherein at least a portion of the liver is visualized within the region of interest, determining a set of image segments within the one or more images, wherein the set of image segments correspond to the region of interest, and determining the value or the characteristic based on some or all of the image segments in the set of image segments.

4. The method of claim 3, wherein the set of image segments corresponds to an anatomical component, a vasculature of the liver, or an abnormality of the liver.

5. The method of claim 4, wherein the set of image segments are optimized according to an optimization procedure.

6. The method of claim 1, comprising using the platform to obtain a visualization of the liver, a structure of the liver, a proton density fat fraction (PDFF) of the liver, or a vasculature of the liver, wherein the visualization is two-dimensional or three- dimensional.

7. The method of claim 1, wherein the value or the characteristic relates to a volume of the liver, a shape of the liver, a fat metric of the liver, or a vasculature of the liver.

8. The method of claim 1 , wherein the assessment is used to diagnose a disease of the liver, evaluate a risk of disease of the liver, evaluate a severity or grading of a disease of the liver, or monitor progression of a disease of the liver.

9. The method of claim 1, wherein the set of data is stored in a database.

10. The method of claim 9, wherein the database is accessible via the platform.PCT Patent Application Attorney Docket No.: 009062.8554. WOOO11 . The method of claim 10, wherein the additional AT tools include Natural Language Processing models (NLP) configured to extract data elements from the historical records, wherein at least some of the historical records have a structured or an unstructured format.

12. The method of claim 1, wherein the omic data includes information of the liver related to at least one of gene expression, proteomics, or metabolomics.

13. A method for quantitatively assessing a health of a liver, comprising: obtaining a set of data related to the liver, wherein the set of data comprises: (i) measured data of the liver including one or more images of the liver, and (ii) one or both of historical health information of the liver and omic data associated with a biological sample of the liver, wherein the historical health information is obtained using an artificial intelligence (Al) tool configured to analyze historical records associated with the liver; processing the set of data by implementing at least one of multiple processing tools, wherein the multiple processing tools include: artificial intelligence (Al) tools configured to analyze the one or more images to extract features of the liver from the one or more images, and genomic tools configured to determine, based on the omic data, genomic features related to the liver; determining one or both of a value or a characteristic associated with the liver based on results of processing the set of data; and enabling assessment of the health of the liver based on the one or both of the value or the characteristic.

14. The method of claim 13, wherein the one or more images include images obtained using different imaging modalities, wherein the different imaging modalities include aPCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO magnetic resonance (MR)-based imaging modality, a computerized tomography (CT) imaging modality, or an ultrasound imaging modality.

15. The method of claim 13, wherein the Al tools are configured to analyze the one or more images by: identifying a region of interest in the one or more images, wherein at least a portion of the liver is visualized within the region of interest, determining a set of image segments within the one or more images, wherein the set of image segments correspond to the region of interest, and determining the value or the characteristic based on some or all of the image segments in the set of image segments.

16. The method of claim 15, wherein the set of image segments corresponds to an anatomical component, a vasculature of the liver, or an abnormality of the liver.

17. The method of claim 16, wherein the set of image segments are optimized according to an optimization procedure.

18. The method of claim 13, comprising obtaining a visualization of the liver, a structure of the liver, a proton density fat fraction (PDFF) of the liver, or a vasculature of the liver, wherein the visualization is two-dimensional or three-dimensional.

19. The method of claim 13, wherein the value or the characteristic relates to a volume of the liver, a shape of the liver, a fat metric of the liver, or a vasculature of the liver.

20. The method of claim 13, wherein the assessment is used to diagnose a disease of the liver, evaluate a risk of disease of the liver, evaluate a severity or grading of a disease of the liver, or monitor progression of a disease of the liver.PCT Patent ApplicationAttorney Docket No.: 009062.8554. WOOO21. The method of claim 1 , wherein the omic data includes information of the liver related to at least one of gene expression, proteomics, or metabolomics.

22. A computer program product comprising instructions, which, when the computer program product is executed by a computer, cause the computer to implement a method for quantitatively assessing health of a liver as recited in any one of claims 1-21.

23. A data processing apparatus configured to implement a method for quantitatively assessing health of a liver as recited in any one of claims 1-21.

Images