Schematic representation of health status of tissue of interest based on medical image data

Abstract

A computer-implemented method includes obtaining a first mask of primary tissue of interest segmented from image data of a subject; obtaining, from the image data of the subject, a second set of masks of other tissues indicative of a health status of the primary tissue of interest; obtaining, from the image data of the subject, a third set of masks of elements that are disease signs of the primary tissue of interest; and generating a schematic representation of the health status of the primary tissue of interest of the subject using the image data, the first mask, the second set of masks, and the third set of masks. In one example, a health status of the primary tissue of interest is being evaluated, and the schematic representation provides a summary of health-related information from the image data regarding the health status of the primary tissue of interest.

Description

Schematic representation of the health status of tissues of interest based on medical image data Technical Field

[0001] The following content relates generally to medical imaging, and more specifically to schematic representations of the health status of tissues of interest based on medical image data. Background Technology

[0002] Clinicians (such as radiologists) "read" (i.e., interpret) images for purposes such as diagnosis, monitoring, and screening. For example, clinicians observe images from examinations of patients and record findings (i.e., relevant observations), including descriptions of abnormal and / or normal features of tissues, organs, bones, etc. For diagnosis, these findings help clinicians identify diseases, injuries, abnormalities, etc. For monitoring, these findings help clinicians understand the progression of diseases, injuries, abnormalities, etc. For screening, these findings help clinicians identify conditions that may lead to certain diseases, injuries, abnormalities, etc.

[0003] Literature indicates that early detection of diseases, injuries, and abnormalities can improve treatment outcomes, including, for some diseases, patient survival rates. Existing visualization methods include generating and displaying renderings (e.g., mesh rendering, volume rendering, etc.) and using general atlases to visualize the tissue being evaluated. Unfortunately, such methods cannot adequately characterize the health status of the tissue being evaluated and / or other tissues when detecting diseases, injuries, abnormalities, and / or conditions that may lead to these conditions. Given the foregoing, there remains an unresolved need for improved methods. Summary of the Invention

[0004] The aspects described herein address the aforementioned and other problems. This invention provides a more detailed description of concepts in specific embodiments. It should not be used to identify the essential features of the claimed subject matter, nor should it be used to limit the scope of the claimed subject matter.

[0005] In one aspect, a computer-implemented method includes: obtaining a first mask of a primary tissue of interest segmented from image data of a subject. In one instance, the health status of the primary tissue of interest is being assessed. The computer-implemented method further includes: obtaining a second set of masks from the image data of the subject, representing other tissues indicative of the health status of the primary tissue of interest. The computer-implemented method further includes: obtaining a third set of masks from the image data of the subject, representing elements of disease signs in the primary tissue of interest. The computer-implemented method further includes: generating a schematic representation of the health status of the primary tissue of interest in the subject using the image data, the first mask, the second set of masks, and the third set of masks. In one instance, the schematic representation provides a summary of health-related information from the image data regarding the health status of the primary tissue of interest.

[0006] In another aspect, a system includes a display device, a memory, and at least one processor. The memory is configured to store computer-readable instructions for generating a schematic representation of the health status of a primary tissue of interest in the subject based on image data of the subject. The at least one processor is configured to execute the computer-readable instructions. The computer-readable instructions cause the at least one processor to obtain a first mask segmented from the image data of the primary tissue of interest; obtain a second set of masks from the image data of the subject indicating the health status of the primary tissue of interest; obtain a third set of masks from the image data of the subject as elements of disease signs in the primary tissue of interest; and generate the schematic representation using the image data, the first mask, the second set of masks, and the third set of masks. The schematic representation provides a summary of health-related information from the image data regarding the health status of the primary tissue of interest.

[0007] On the other hand, a computer-readable medium is encoded with computer-executable instructions. When executed by a processor, these computer-executable instructions cause the processor to: obtain a first mask of a primary tissue of interest segmented from image data of a subject, wherein the health status of the primary tissue of interest is being evaluated; obtain a second set of masks from the image data of the subject of other tissues indicating the health status of the primary tissue of interest; obtain a third set of masks from the image data of the subject of elements serving as signs of disease in the primary tissue of interest; and generate, using the image data, the first mask, the second set of masks, and the third set of masks, a schematic representation of the health status of the primary tissue of interest in the subject. This schematic representation provides a summary of health-related information from the image data regarding the health status of the primary tissue of interest.

[0008] Other aspects of this application will be recognized by those skilled in the art upon reading and understanding the accompanying specification. Attached Figure Description

[0009] This application is illustrated by way of example and is not limited to the figures in the accompanying drawings, in which the same reference numerals indicate similar elements.

[0010] Figure 1 illustrates a non-limiting example of a system including a schematic representation module according to one aspect of the embodiments described herein.

[0011] Figure 2 illustrates a non-limiting example of a schematic representation module according to the embodiments described herein.

[0012] Figure 3 illustrates a non-limiting example of an image data selector representing a schematic representation module according to the embodiments described herein.

[0013] Figure 4 illustrates a non-limiting example of the filtering criteria for an image data selector according to the embodiments described herein.

[0014] Figure 5 illustrates another non-limiting example of the filtering criteria for an image data selector according to the embodiments described herein.

[0015] Figure 6 illustrates a variation of the image data selector according to the implementation scheme described herein.

[0016] Figure 7 illustrates a non-limiting example of a segmentation mask generator representing a schematic representation module according to the embodiments described herein.

[0017] Figure 8 illustrates a non-limiting example of a trained segmentation mask generator according to the implementation scheme of this paper.

[0018] Figure 9 illustrates a non-limiting example of a feature determiner for a schematic representation module according to the embodiments described herein.

[0019] Figure 10 illustrates a non-limiting example of a schematic representation generator for a schematic representation module according to the embodiments described herein.

[0020] Figure 11 illustrates a non-limiting example of a schematic representation of an embodiment according to the present invention.

[0021] Figure 12 illustrates another non-limiting example of a schematic representation of an embodiment according to the present invention.

[0022] Figure 13 illustrates a non-limiting example of an imaging system configured for CT imaging according to an embodiment of the present invention.

[0023] Figure 14 illustrates a non-limiting example of a flowchart for generating a schematic representation according to one aspect of this paper, which provides a visual summary of the health status of an organization of interest.

[0024] Figure 15 illustrates a non-limiting example of a flowchart for generating a schematic representation according to one aspect of this paper, which provides a visual summary of the health status of a particular subject's liver. Detailed Implementation

[0025] Embodiments of this disclosure will now be described by way of example, with reference to the accompanying drawings, in which instructions of systems, methods, and / or computer-readable media generate a schematic representation of the health status of a primary tissue of interest in a subject. The schematic representation can be generated using CT, MR, SPECT, PET, and / or other image data of the subject. In one example, the method includes: generating and / or obtaining a mask of elements of the primary tissue of interest, other tissues indicating the health status of the primary tissue of interest, and disease signs of the primary tissue of interest. In some examples, the method further includes: determining and / or obtaining a classified measure indicating the health status of the primary tissue of interest; and including the classified measure in the schematic representation. In some examples, the method further includes: generating a rendering using image data, which can be displayed together with the schematic representation.

[0026] For trained clinicians (such as radiologists), a few seconds of examination of the schematic representation may be sufficient to determine whether further analysis is needed. This schematic representation can also be included in clinical reports, for example, to be shared with other radiologists or to summarize examinations, thereby facilitating communication and collaboration. The schematic representation can consider primary and secondary signs of disease in the primary tissue of interest and search for indications of disease in other organs and / or other regions. In one instance, this method can be used to aid screening. This includes processing image data acquired for reasons unrelated to the imaging of the primary tissue of interest, potentially triggering further analysis and early disease detection. This method can also be used to aid diagnosis. This method can also be used to aid monitoring. Other applications are also envisioned in this paper.

[0027] Referring first to Figure 1, a system 102 is illustrated, comprising a set of medical imaging modalities 104, a data storage library 106, and a computing system 108. This set of medical imaging modalities 104, data storage library 106, and computing system 108 communicates with a network 110. Such communication can be conducted via wired and / or wireless technologies. In one example, the network 110 is configured to transmit medical data, including image data and non-image data. In one example, the network 110 is configured to transmit image data using file formats (such as Digital Imaging and Communications in Medicine (DICOM)) and / or other formats, and to transmit non-image data using protocols (such as Layer 7 Health Information Exchange Protocol (HL7)) and / or other protocols. The set of medical imaging modalities 104, data storage library 106, and computing system 108 can communicate with each other and / or with other devices via the network 110.

[0028] In the illustrated example, the group of medical imaging modalities 104 includes a first imaging system 1041, ..., and an Nth imaging system 104. N Where N is an integer equal to or greater than 1. Examples of imaging systems in this group of medical imaging modalities 104 include one or more computed tomography (CT) imaging systems, one or more magnetic resonance (MR) imaging systems, one or more X-ray imaging systems, one or more positron emission tomography (PET) imaging systems, one or more single-photon emission computed tomography (SPECT) imaging systems, etc. This group of medical imaging modalities 104 may include imaging systems connected to a single entity such as a hospital, imaging center, etc., or imaging systems connected to multiple different entities.

[0029] As described in more detail below, the imaging system is configured to generate volumetric image data. In some instances, at least one imaging system of the group of medical imaging modalities 104 is configured to push image data to, for example, a data store 106 and / or a computing system 108 and / or retrieve the image data from the data store 106 and / or the computing system via network 110. In some instances, at least one imaging system of the group of medical imaging modalities 104 is configured to receive image data from, for example, a data store 106 and / or a computing system 108 via network 110. In some instances, at least one imaging system of the group of medical imaging modalities 104 is configured to allow, for example, access by the data store 106 and / or the computing system 108 via network 110 to image data stored therein.

[0030] Data repository 106 includes one or more of the following: a Radiology Information System (RIS), a server (such as a Picture Archiving and Communication System (PACS) server), a Hospital Information System (HIS), an Electronic Medical Record (EMR), and a database. Data repository 106 is configured to store image data and / or non-image data, such as image data generated by at least one imaging system and / or another imaging system in the group of medical imaging modalities 104, and / or image data processed by the computing system 108. The DICOM field of the image data includes information such as a unique identifier for the subject, an identifier of the imaging modality used to acquire the image data, an identifier of the anatomical structure being evaluated, an identifier of the series included in the examination, and an identifier of whether contrast materials were used for acquisition.

[0031] In some instances, at least one device of the data storage 106 is configured to push image data and / or non-image data to or pull image data and / or non-image data from the group of medical imaging modalities 104 and / or computing systems 108 via network 110. In some instances, at least one device of the data storage 106 is configured to receive image data and / or non-image data from, for example, the group of medical imaging modalities 104 and / or computing systems 108 via network 110. In some instances, at least one device of the data storage 106 is configured to allow access, for example, to image data and / or non-image data stored therein via network 110 through the group of medical imaging modalities 104 and / or computing systems 108.

[0032] The computing system 108 includes computers, workstations (e.g., a PACS workstation equipped with an image viewer), distributed processing services, cloud processing resources, etc. The computing system 108 includes at least one processor 112, such as a microprocessor (…). The computing system 108 includes a central processing unit (CPU), a graphics processing unit (GPU), etc. The computing system 108 further includes a computer-readable storage medium 114, which includes non-transitory media and excludes transient media (signals, carrier waves, etc.). At least one processor 112 is configured to execute software residing on, encoded, or embedded in the computer-readable storage medium 114. In the illustrated example, such software includes at least an illustrative representation module 116.

[0033] As described in more detail below, the schematic representation module 116 is configured to generate a segmentation mask from image data; determine and classify metrics based on the image data and the mask; and generate a schematic representation of the tissue of interest that summarizes the health status of the tissue of interest without requiring volume rendering, atlases, etc., although volume rendering, atlases, etc., may be included with the schematic representation. Similarly, in one instance, the schematic representation provides an overview of the health status of the primary tissue of interest in the subject. In one instance, the schematic representation assists the interpreter in interpreting the image data. For example, in one instance, the method at least assists in the early detection of diseases, injuries, abnormalities, etc., and improves treatment outcomes, thereby providing capabilities lacking in methods that omit the schematic representation module 116.

[0034] The computing system 108 further includes input / output (I / O) 118. Input devices 120 include a keyboard, mouse, touchscreen, microphone, etc. Input devices 120 are electrically connected to the computing system 108 via I / O 118 and / or otherwise. Output devices 122 include human-readable devices such as display monitors. Output devices 122 are electrically connected to the computing system 108 via I / O 118 and / or otherwise.

[0035] In some instances, computing system 108 is configured to push image data and / or non-image data to and / or pull image data and / or non-image data from the set of medical imaging modalities 104 and / or data storage 106 via network 110. In some instances, computing system 108 is configured to receive medical data and / or non-image data from the set of medical imaging modalities 104 and / or data storage 106 via network 110. In some instances, computing system 108 is configured to allow access to medical data and / or non-image data stored therein, for example, via network 110 through the set of medical imaging modalities 104 and / or data storage 106.

[0036] Turning to Figure 2, a non-limiting example of a schematic representation module 116 is illustrated. In this example, the schematic representation module 116 includes an image data selector 202, a segmentation mask generator 204, a feature determiner 206, and a schematic representation generator 208. In some instances, at least one of the medical data selector 202, the segmentation mask generator 204, and / or the feature determiner 206 is performed using different processing resources (i.e., not by the computing system 108). In such instances, the schematic representation module 116 may or may not include at least one of the image data selector 202, the segmentation mask generator 204, and / or the feature determiner 206.

[0037] Image data selector 202 obtains a set of image data from one or more sources in data storage 106 for processing by segmentation mask generator 204. In one example, this data is used in imaging systems 1041, ..., MR imaging systems 104 that form image modality 104. N After scanning the subject and generating image data, this image data is stored in one or more sources of data repository 106 for imaging examination. In one instance, the image data is stored automatically in the source. In another instance, the image data is stored semi-automatically, for example, based on user input. Image data selector 202 is configured to obtain the set of image data from one or more sources of data repository 106 based on user-defined filtering criteria, machine learning filtering criteria, etc.

[0038] In one instance, when an imaging examination is stored in data store 106, the medical data selector 202 is notified. For example, if data store 106 is a RIS (Representational Information System), the RIS can automatically add the imaging examination to the work list for the schematic representation module 116, and the image data selector 202 learns of the imaging examination through this work list. In some instances, the action of storing image data in data store 106 invokes the medical image data selector 202 to access the imaging examination. In another instance, the image data selector 202 accesses the imaging examination in data store 106 when the processing resources and / or other processing resources of computing system 108 are available. In yet another instance, the image data selector 202 accesses the imaging examination in data store 106 based on a pre-determined schedule. In yet another instance, the image data selector 202 accesses the imaging examination in data store 106 on demand based on user input.

[0039] Segmentation mask generator 204 is configured to process the set of image data obtained by image data selector 202 using a set of algorithms to generate a set of masks. Examples of such masks include one or more segmentation masks of primary tissue of interest, one or more sub-segmentation masks of one or more segmentation masks of primary tissue of interest, other tissues related to the health status of primary tissue of interest, elements indicating disease signs of primary tissue of interest, etc. Feature determiner 206 is configured to process the set of masks and determine and classify health-related metrics of primary tissue of interest based on measurements (such as size, shape, etc.) and at least the known extent of healthy tissue. Schematic representation generator 208 is configured to process the masks (and the classified metrics) and generate a schematic representation of primary tissue of interest (and other tissues, elements, and measurements) based on a set of rules, which summarizes the health status of primary tissue of interest.

[0040] The schematic representation module 116 outputs a schematic representation that can be displayed on a display monitor via output device 122, incorporated into a radiological report for examination, and stored in computing system 108 and / or data storage 106, etc. In one instance, the schematic representation is generated using a markup language-based image format, such as an Extensible Markup Language (XML)-based image format. An example of such a suitable XML-based image format is Scalable Vector Graphics (SVG). Using such an XML-based vector image format allows the schematic representation to be presented without loss of quality, whether on a display monitor, in a report, etc. Although the creation and display of the schematic representation does not require volume rendering, atlases, etc., optionally, volume rendering, atlases, etc., may be included with the schematic representation.

[0041] Figure 3 illustrates a non-limiting example of an image data selector 202. The image data selector 202 includes an image data filter 302 and filtering criteria 304. Filtering criteria 304 include information such as the imaging modality of interest (e.g., CT, MR, X-ray, PET, SPECT, etc.), the primary tissue of interest (e.g., liver, heart, lung, kidney, spleen, gallbladder, etc.), and tissues related to the health status of the primary tissue of interest (e.g., for liver, spleen, kidney, pancreas, etc.). The image data filter 302 filters the data stored in the data repository 106 based on the filtering criteria 304 to obtain a set of image data for processing. The image data selector 202 outputs this set of image datasets.

[0042] Figure 4 illustrates a non-limiting example of filter criterion 304. In this example, filter criterion 304 includes M modes, modes 4021, ..., and mode 402. M (Referred to as mode 402 in this paper), where M is an integer equal to or greater than 1. Each of the M modes includes multiple primary organizations of interest. For example, mode 4021 includes L organizations of interest, including primary organizations 4041, ..., and primary organization 404. L (collectively referred to herein as primary organization 404), where L is an integer equal to or greater than 1. Each of the multiple primary organizations identifies other organizations related to the health status of that primary organization. For example, primary organization 4041 includes other organizations 406.

[0043] In one instance, image data selector 202 will first filter data store 106 for checks corresponding to modality 4021. In one instance, this filtering includes searching for the DICOM and / or other fields of the files being checked in data store 106. Within this set of checks corresponding to modality 4021, image data selector 202 will filter data store 106 for checks corresponding to primary tissue 4041. Within this set of checks corresponding to primary tissue 4041, image data selector 202 will filter data store 106 for checks that include other tissues 406.

[0044] The identified examinations will be grouped together, but distinguished, for example, by the subject using a unique identifier (UID) and / or other information. By way of a non-limiting example, in the case where modality 4021 is a CT scan, primary tissue 4041 is the liver, and other tissues 406 include the spleen, kidneys, and pancreas, image data selector 202 looks for CT scans of the liver that also include the spleen, kidneys, and pancreas, and groups these CT scans together, but distinguishes them based on the subject. For example, in one instance, image data selector 202 identifies an abdominal CT scan that includes the liver, spleen, pancreas, and kidneys. Image data selector 202, for modality 4021, for primary tissue 404... L Repeat the above steps. This process is performed via mode 402. M Continuing. The final set of image data is segmented based on modality, primary tissue, and subject. Therefore, image data can be processed based on a combination of modality, primary tissue, and subject to generate a schematic representation of the subject's primary tissue.

[0045] Figure 5 illustrates another non-limiting example of filter criterion 304. In this variation, filter criterion 304 further includes series identifiers, including series 5021, ..., and series 502. K (Referred to herein as Series 502), where K is an integer equal to or greater than 1. In one instance, Series 502 provides another level of filtering. Continuing with the example discussed in conjunction with Figure 4, in one instance, Series 5021, ..., 502 K This can indicate a series of images acquired during contrast-enhanced scanning, such as images around a specific state (e.g., a specific contrast phase of a blood vessel, such as a non-enhanced phase, arterial phase, portal venous phase, delayed phase, etc.). In another example, series 502 can indicate a series acquired during different functional states (e.g., cardiac phase, respiratory cycle, etc.). Other levels of filtering are envisioned in this paper. For example, for MR image data, filtering could include different sequences such as T1, T2, diffusion-weighted (DW), fluid attenuation inversion recovery (FLAIR), time-of-flight (TOF), etc.

[0046] Figure 6 illustrates a variation of the image data selector 202 discussed in conjunction with Figure 3. In this variation, certain filtering criteria (such as modalities of interest and primary tissues) are provided to the image data selector 202. For example, a user of computing system 108 may input such information via input device 118. The image data selector 202 searches for filtering criteria 304 against the input modalities of interest and primary tissues, and filters the checks in data store 106 based on entries in filtering criteria 304 that include the input modalities of interest and primary tissues. In yet another instance, the user may input modalities of interest, primary tissues, other tissues, series, and / or other information. In such instances, the image data selector 202 may not utilize filtering criteria 304. Alternatively, the image data selector 202 may determine whether a term not provided in the input exists in filtering criteria 304, and display a notification indicating the term and / or a pop-up window allowing the user to accept or reject the addition of the term by clicking the mouse, etc.

[0047] Next, in Figure 7, a non-limiting example of the segmentation mask generator 204 is illustrated. In the illustrated example, the segmentation mask generator 204 includes a tissue segmenter 702, a tissue segmentation segmenter 704, and related other tissue segmenters 706. The segmentation mask generator 204 processes the inspection from the image data selector 202, and each of the tissue segmenter 702, the tissue segmentation segmenter 704, and the related other tissue segmenters 706 outputs a corresponding segmentation mask. In one instance, the tissue segmenter 702 segments the primary tissue and other tissues related to the health status of the primary tissue and creates a mask for each, the tissue segmentation segmenter 704 segments the segments of the primary tissue into subsegments, and the related other tissue segmenters 706 segments elements that are signs of disease in the primary tissue.

[0048] Tissue segmenter 702, tissue segment segmenter 704, and other related tissue segmenters 706 may utilize known and / or other segmentation methods. For example, in one instance, at least one of tissue segmenter 702, tissue segment segmenter 704, and other related tissue segmenters 706 employs an artificial intelligence (AI)-based method, such as a neural network (NN), for example, a convolutional neural network (CNN), such as U-Net. By way of non-limiting example, tissue segmenter 702, tissue segment segmenter 704, and other related tissue segmenters 706 may employ different U-Net models trained to segment various parts of an image. An example U-Net model 802 is shown in Figure 8. U-Net model 802 includes an encoder 804, a decoder 806, and multi-channel output to produce multiple segments 808 with at least one inference.

[0049] Generally, the specific model utilized by the segmentation mask generator 204 will depend on the modality and the primary organization of interest. Examples of suitable models include, but are not limited to, seed region watershed algorithms, graph cut methods, graph-based segmentation, random forests, support vector machines (SVMs), fully convolutional networks, visual transformers, etc. Other suitable methods include edge detection, such as search, zero-crossing and / or other edge detection techniques, thresholding to convert grayscale images to binary images, etc.

[0050] Next, in Figure 9, a non-limiting example of feature determiner 206 is illustrated. Feature determiner 206 receives a segmentation mask generated and output by image data selector 202 as input. Feature determiner 206 includes metric determiner 902 and classifier 904. Metric determiner 902 determines measurements, such as size, shape, etc., of different parts of primary tissue, other tissues, etc., based on image data and / or the mask. Metric determiner 902 further defines a metric based on the measurement results. For example, a metric may include determining a value based on the ratio of the measurement result of a part of the primary tissue (e.g., one or more subsegments) to the measurement result of the primary tissue. Classifier 904 compares the value of the metric with a value or range of values ​​corresponding to healthy (and / or unhealthy) tissue and classifies the metric according to the value or range. Feature determiner 206 outputs the metric with classification.

[0051] Next, at Figure 10, a non-limiting example of a schematic representation generator 208 is illustrated. The schematic representation generator 208 receives a segmentation mask and a classified metric as input. The schematic representation generator 208 includes a mask processor 1002 and a rule base 1004. The mask processor 1002 generates the schematic representation based on rules in the rule base 1004, which determines which data from the image data and / or the mask should be included in the schematic representation. In one instance, the summary includes graphical representations of the primary tissue of interest and related other tissues generated from the image data. The location and size of the primary tissue of interest and related other tissues reflect the location and size of the primary tissue of interest in a specific slice of the image / image and / or the cumulative location and size of related other tissues derived from a set of slices / images in a window surrounding the specific slice / image. In some instances, the schematic representation further includes two-dimensional (e.g., length, width, diameter, etc.) and / or three-dimensional (e.g., volume, etc.) measurements of the tissue. In some instances, the schematic representation further includes the resulting metric and the classified metric.

[0052] An exemplary use case scenario is described below. In this use case scenario, the imaging modality is CT or MR, the primary tissue of interest is the liver, other tissues include at least the spleen and kidneys, and the series includes acquisition times that prioritize the portal venous phase. Generally, liver disease causes more than 2,000,000 deaths annually, including deaths from cirrhosis, viral hepatitis, and liver cancer. Early stages of liver disease are often asymptomatic, leading to delays in clinical treatment. Early detection of the disease tends to improve patient survival rates.

[0053] Fibrosis, characterized by scar tissue formation, leads to progressive thickening and sclerosis of the liver tissue. This can have a variety of consequences, such as portal hypertension (splenomegaly, portal vein dilation, and the presence of ascites), changes in liver morphology (segment 4 atrophy, left hepatomegaly, presence of nodules on the liver surface, and right hepatic notch), or parenchymal heterogeneity. The method described in this paper uses image data to generate schematic representations that facilitate the assessment of liver health, for example, in the case of advanced chronic liver disease (ACLD).

[0054] The image data selector 202 (Figures 2 to 6) of the segmentation mask generator accesses at least one storage source of the data repository 106 (or the constituent image modality 104, computer-readable storage medium 112, and / or other storage devices) and identifies a contrast-enhanced image examination of the liver, which includes the spleen and kidneys and covers the portal venous phase. The tissue segmenter 702 of the segmentation mask generator 204 (Figures 2 and 7) processes the identified image data and segments the liver, spleen, and kidneys from the identified image examination, and generates a mask indicating them.

[0055] The segmentation mask generator 204 (Figures 2 and 7) segmentes the liver using a tissue segmenter 704 and generates its mask. In this example, the tissue segmenter 704 is configured to segment the liver based on the Couinaud segmentation method. Therefore, the tissue segmenter 704 segments the liver into eight functionally independent segments, each with independent vascular inflow, outflow, and bile drainage, and each segment has branches of the portal vein, hepatic artery, and bile duct at its center. Related additional tissue segmenters 706 of the segmentation mask generator 204 (Figures 2 and 7) process the identified image data and segment elements that serve as signs of liver disease, generating masks indicating these elements. Examples of such tissues include the right hepatic notch, portal vein, gallbladder, liver surface nodules, falciform ligament, collateral vessels, ascites, periportal portal canal space, etc.

[0056] The feature determiner 206 (Figures 2 and 9) of the schematic representation module 116 processes the mask and derives and classifies measures indicative of the liver's health status. Examples of such measures include liver volume, left hepatic hypertrophy, atrophy of segment 4, hypertrophy of segment 1, nodules on the liver surface, widening of the periportal space, thickening of ligaments, splenomegaly, widening of the portal vein, presence of ascites, thickening of the gallbladder wall, and hepatic heterogeneity. For example, the left hepatic hypertrophy measure can be derived by the ratio of Couinaud's segments 1 and 2 to the total liver volume. The feature determiner 206 classifies the left hepatic hypertrophy measure by comparing the value of the ratio to one or more known ranges to classify the value as "within" or "outside" the normal range. In some instances, the abnormal range is further subdivided into quantifiable ranges, such as "low," "mild," "severe," etc., or by a continuum.

[0057] The schematic representation generator 208 (Figures 2 and 10) of the schematic representation module 116 processes image data, masks, and measures, and generates a schematic representation based on the information in the image data, masks, and measures. This schematic representation summarizes the health status of primary tissues. Users can customize this schematic representation to effectively report information, thereby improving visualization. Examples of a set of rules from the rule base 1004 (Figure 10) include:

[0058] The shape of the liver is determined from slices of image data in which the portal vein enters the liver.

[0059] Determine the shape of the body at the slice location;

[0060] The shape of the spleen is determined from slices of image data in which the spleen is at its maximum size (e.g., based on the maximum diameter of the spleen).

[0061] Along the z-plane, each of the segments in the right hepatic notch, ligaments, portal vein, collateral vessels, and periportal space is accumulated from image data, and...

[0062] Along the z-plane, accumulate each of the ascites, gallbladder, and liver surface nodules around the predetermined slice boundaries.

[0063] The schematic representation generator 208 combines the identified and accumulated information to generate a schematic representation, and optionally generates legends and measures with their classifications. An example of such a schematic representation is illustrated in Figure 11. The schematic representation of Figure 11 can be visually presented in a graphical user interface (GUI) using a display monitor and / or otherwise incorporated into radiology reports, etc.

[0064] In Figure 11, the schematic representation includes the liver 1102, spleen 1104, gallbladder 1106, hilar space 1108, portal vein 1110, right hepatic notch 1112, ligament 1114, surface nodules 1116, 1118, 1120, 1122, ascites 1124, and body outline 1126. This schematic representation further includes the y-axis (depth) dimension 1128 and x-axis (width) dimension 1130 of the body outline 1126, the volume 1132 of the liver 1102, the longest dimension 1134 of the spleen 1104, and the diameter 1136 of the portal vein 1110. Other and / or different information may be incorporated into other schematic representations.

[0065] This illustrative representation further includes a set of 1138 derived measures and their corresponding classifications. In this example, the derived measures are categorized under liver morphology measurements, signs of portal hypertension, and other signs. The liver morphology measurement group includes liver volume, left hepatic hypertrophy, atrophy of segment 4, hypertrophy of segment 1, nodules on the liver surface, widening of the periportal space, and thickening of ligaments. The signs of portal hypertension group includes splenomegaly, widening of the portal vein, and presence of ascites. Other signs group includes gallbladder wall thickening and liver heterogeneity. In other examples, a different set of derived measures may be included in the pattern.

[0066] In this example, liver volume was classified as low, left hepatic hypertrophy as absent, atrophy of segment 4 as severe, hypertrophy of segment 1 as mild, nodules on liver surface as severe, widening of periportal space as mild, thickening of ligaments as absent, splenomegaly as absent, widening of portal vein as absent, presence of ascites as severe, thickening of gallbladder wall as absent, and liver heterogeneity as absent.

[0067] In this example, grayscale encoding is used for classification. The lightest gray shade corresponds to the "none" category, a darker gray shade corresponds to the "low" category, a slightly darker gray shade corresponds to the "mild" category, and the darkest gray shade corresponds to the "severe" category. This paper envisions other encoding schemes. For example, in another instance, different categories could be represented by one or more of different font styles, colors, sizes, effects, patterns, etc.

[0068] Figure 12 schematically illustrates a variation of the schematic representation discussed in conjunction with Figure 11. The schematic representation of Figure 12 further includes at least one rendering, comprising a tissue rendering 1202, a symptom rendering 1204, and / or a segmented liver rendering 1206. Tissue rendering 1202 shows segmented tissue including the liver, spleen, gallbladder, etc. Symptom rendering 1204 shows segmented elements as disease symptoms of primary tissue. Segmented liver rendering 1206 shows a segmented liver. In this example, segmented liver rendering 1206 shows Couinaud segments.

[0069] This schematic representation summarizes the health status of the subject's liver. For a trained radiologist, reviewing the schematic representation for just a few seconds may be sufficient to determine whether further liver analysis is needed. This schematic representation can also be included in clinical reports for sharing with other radiologists or for summarizing examinations, thereby facilitating communication and collaboration. The schematic representation considers primary and secondary signs of liver disease in primary tissues of interest and searches for indications of liver disease in other organs and / or other regions. This method can be used for screening and can process image data acquired for reasons unrelated to the liver (e.g., abdominal scans), potentially triggering further analysis and early disease detection.

[0070] As discussed herein, the described methods can process image data from the same and / or different modalities simultaneously or individually, and examples of image data include one or more of CT, MR, PET, SPECT, and / or other image data. In the use case scenario presented in conjunction with Figures 11 and 12, the modality of interest is CT. Figure 13 schematically illustrates a non-limiting example of an imaging system 1302 configured for CT imaging.

[0071] Imaging system 1302 includes a gantry 1304. In some instances, gantry 1304 is configured to be tilted. Imaging system 1302 further includes a rotating frame 1306. The rotating frame 1306 is rotatably supported in gantry 1304, for example via bearings (e.g., slip rings), and is configured to rotate about an inspection area 1308 about a rotation axis or z-axis 1310, which extends through a rotation center / center of inspection area 1308 (i.e., isocenter point). A gantry controller (not visible) is configured to control the rotation of the rotating frame 1306 and, if configured to be tilted, to control the tilt of gantry 1304.

[0072] X-ray source assembly 1312 is supported by and rotates in conjunction with a rotating frame 1306. X-ray source assembly 1312 includes an X-ray source 1314, such as an X-ray tube. X-ray source 1314 is configured to emit X-ray radiation with energy within the X-ray diagnostic range (e.g., 20 keV to 150 keV). X-ray source assembly 1312 may further include or be coupled to a filter 1316 and / or a collimator 1318, the filter characterizing the X-ray radiation dose distribution, and the collimator shaping the X-ray radiation to form a generally fan-shaped, wedge-shaped, cone-shaped, or similar beam traversing the examination area 1308. An X-ray controller (not visible) is configured to control components of X-ray assembly 1312, such as the X-ray radiation emission of X-ray source 1314, collimator 1318, etc.

[0073] X-ray radiation sensitive detector array 1320 comprises a one-dimensional (1-D) or two-dimensional (2-D) array of rows of X-ray radiation sensitive detector elements 1322, and is supported by a rotating frame 1306 along an arc spanning an inspection area 1308 opposite to the X-ray source 1314. Each X-ray radiation sensitive detector element in the X-ray radiation sensitive detector elements 1322 is electrically connected to a data acquisition system 1324 (DAS). The X-ray radiation sensitive detector elements 1322 include indirect conversion detectors such as scintillator / photodiode detectors and / or direct conversion detectors such as cadmium telluride (CdTe), cadmium zinc telluride (CZT), etc. A DAS controller (invisible) controls the X-ray radiation sensitive detector array 1320.

[0074] The subject / object support 1330 includes a table 1332 movably coupled to a frame / base 1334. In one example, the table 1332 is slidably coupled to the frame / base 1334 via bearings or the like, and a drive system (not visible) including a controller, motor, lead screw, and nut (or other drive system) allows the table 1332 to translate along the frame / base 1334 into and out of the inspection area 1308. The table 1332 is configured to support an object or subject in the inspection area 1308 for loading, scanning, and / or unloading the subject or object. A table controller (not visible) controls the drive system.

[0075] For axial scanning, the stage 1332 is positioned at a static location for each integration cycle and moves between integration cycles. For helical scanning, the rotating frame 1306 rotates in conjunction with the stage 1332, which moves along the Z-axis 1310, and the active X-ray detector elements 1322 of the X-ray radiation-sensitive detector array 1320 detect X-ray radiation and generate corresponding signals in each continuous arc segment (integration cycle) of rotation. For each arc segment, the data acquisition system (DAS) 1324 processes each signal and generates projection data.

[0076] Reconstructor 1336 reconstructs the projection data and generates volumetric 3D (3-D) image data for helical scanning and / or separate axial 2D (2-D) images for axial stepping and imaging scanning (which can be combined to generate volumetric image data). The volumetric image data and / or its 2D slices and / or individual axial images can be visually presented, captured, etc. Examples of suitable reconstruction algorithms include Filtered Back Projection (FBP), Advanced Statistical Iterative Reconstruction (ASIR), Conjugate Gradient (CG), Maximum Likelihood Expectation Maximization (MLEM), Model-Based Iterative Reconstruction (MBIR), and / or other reconstruction algorithms.

[0077] In a non-spectral configuration, the X-ray source 1314 comprises a single broadband X-ray tube emitting polychromatic radiation (e.g., 40 keV to 120 keV) at 1320 kVp. In another example, the imaging system 1302 is configured for spectral imaging. With such a configuration, the X-ray source 1314 can be configured to switch between at least two different kVp values, including multiple X-ray tubes, and / or the detector array 1320 can include multiple layers, each configured to detect different energies, where the projection data can be decomposed into photoelectric effect and Compton scattering components, and the reconstructor 1336 can reconstruct projection data for different energy bands.

[0078] The computing system serves as the operator console 1338 of system 1302. The computing system 1338 may include a computer, workstation, etc. The computing system 1338 further includes at least one processor 1340 (such as...). The computing system 1338 includes a computer-readable storage medium 1342 (“memory”), which includes non-transitory media and excludes transient media (signals, carrier waves, etc.). The memory 1342 includes application software 1344 that allows users to set up and initiate scans, view image data, and transmit image data via network 110. The computing system 1338 further includes I / O 1346, input devices 1348, and output devices 1350.

[0079] Figure 14 illustrates a non-limiting example of a flowchart for generating a schematic representation according to one aspect of this document, which provides an overview of the health status of an organization of interest. It should be understood that the order of actions in this method is not restrictive. Therefore, other orders are contemplated herein. Furthermore, one or more actions may be omitted, and / or one or more additional actions may be included.

[0080] At 1402, image data selector 202 accesses data store 106 and selects one or more sets of image data stored in data store 106 for processing by segmentation mask generator 204, as described herein and / or otherwise. At 1404, segmentation mask generator 204 processes the one or more sets of image data, each set of image data having a corresponding algorithm; and outputs a segmentation mask, as described herein and / or otherwise. At 1406, feature determiner 206 processes the mask generated by segmentation mask generator 204, derives a metric, and classifies it, as described herein and / or otherwise.

[0081] At 1408, the schematic representation generator 208 processes the mask and the resulting metrics, and generates a schematic representation that summarizes information from the image data, mask, and metrics, as described herein and / or otherwise. In one instance, the summary includes graphical representations of the primary tissue of interest and other relevant tissues generated from the image data. In some instances, two-dimensional and / or three-dimensional measurements of the tissue are also included in the schematic representation. In some instances, the resulting metrics and classified metrics are also included in the schematic representation. In some instances, rendering of the tissue is also included in the schematic representation.

[0082] At 1410, the schematic representation module 116 outputs a schematic representation, as described herein and / or otherwise. An example of a schematic representation generated from CT image data of the liver is illustrated with reference to Figure 11. Another example of a schematic representation generated from CT image data of the liver is illustrated with reference to Figure 12. This representation can be incorporated into reports, printed, archived, transmitted to another device, etc.

[0083] Figure 15 illustrates a non-limiting example of a flowchart for generating a schematic representation according to one aspect of this document, which provides an overview of the liver health status of a particular subject. It should be understood that the order of actions in this method is not limiting. Therefore, other orders are contemplated herein. Furthermore, one or more actions may be omitted, and / or one or more additional actions may be included.

[0084] At 1502, image data selector 202 accesses data repository 106 and selects one or more sets of image data, including the liver, from data repository 106 for processing by segmentation mask generator 204, as described herein and / or otherwise. For example, in one instance, image data selector 202 selects each set of image data based at least on a specific medical imaging modality, with the liver as the primary organ and other relevant organs including the spleen, kidney, pancreas, etc. In another instance, image data selector 202 further filters the selection to image data enhanced with contrast materials.

[0085] At 1504, the segmentation mask generator 204 processes the set or more sets of image data, each set having a corresponding algorithm; and outputs a segmentation mask, as described herein and / or otherwise. Similarly, the processing of the set or more sets of image data can be performed serially and / or in parallel. In cases where a set of image data comprises subgroups of image data from different examinations of the subject, the segmentation mask generator 204 processes the subject's subgroups of image data independently. For each set of image data (and / or subgroup of image data) processed, the segmentation mask generator 204 generates and outputs multiple masks, such as organ segmentation masks, sub-organ segmentation masks, and related other tissue masks.

[0086] For example, segmentation mask generator 204 employs an algorithm configured to segment the liver in CT image data and generate a liver mask. Segmentation mask generator 204 employs an algorithm configured to segment the liver into subsegments and generate masks for those subsegments. Non-restrictive segmentation methods include the Couinaud segment, which segments the liver into eight subsegments. Segmentation mask generator 204 further employs an algorithm configured to segment elements that are signs of liver disease (such as the right hepatic notch, portal vein, gallbladder, liver surface nodules, falciform ligament, collateral vessels, ascites, and / or perihular portal canal space) and / or other tissues and generate their masks.

[0087] At 1506, feature determiner 206 processes the mask generated by image data processor 202 and derives and classifies metrics, as described herein and / or otherwise. For example, feature determiner 206 determines measurements of different parts of the liver, such as size, shape, etc., and derives metrics based on ratios, comparisons, etc. of the measurements. By way of a non-limiting example, where the liver is segmented based on Couinaud segments (which comprise eight segments), feature determiner 206 may define a feature referred to as left hepatic hypertrophy and calculate the value of this feature by the ratio of the first and second segments of the Couinaud segment to the total liver volume. The value of the left hepatic hypertrophy feature may be classified based on information from an information pool corresponding to healthy livers, and in some instances, further classified based on information from an information pool corresponding to unhealthy livers.

[0088] At 1508, the schematic representation generator 208 processes the mask and the resulting measurements, and generates a schematic representation summarizing the liver's health status from the information in the mask and measurements, as described herein and / or otherwise. This summary includes a graphical representation of the liver and related other tissues generated from the image data. The location and size of the liver and spleen, kidneys, etc., reflect the actual location and size of the liver in a specific slice / image of interest, and the cumulative location and size of related other tissues derived from a set of slices / images within a window surrounding that specific slice / image. In one instance, one or more sub-patterns within a sub-pattern of the liver and spleen, kidneys, etc., will include one or more measurements.

[0089] In another instance, generator 208 schematically represents further processing of the resulting and categorized metrics, and schematically represents further summarizing information from the resulting and categorized metrics, as described herein and / or otherwise. For example, in one instance, the summary includes a list of each metric and maps each metric to a corresponding health state. By way of non-limiting example, an exemplary table includes a two-by-two table having a first column listing the identifiers of each resulting metric and a second column listing the derived health states, wherein each row includes the resulting metric in the first column (e.g., row 1, column 1) and the corresponding health state in the second column (e.g., row 1, column 2). The table may be further partitioned to group the resulting metrics across categories of interest.

[0090] In some instances, the schematic representation generator 208 further processes the set of image data and / or masks and generates at least one rendering, as described herein and / or otherwise. For example, in one instance, the schematic representation generator 208 processes such information and generates a rendering of the liver. In this instance, the schematic representation generator 208 may label different parts of the liver via text and / or graphic markers. Additionally or alternatively, the schematic representation generator 208 processes such information and generates renderings of other related tissues. Similarly, the schematic representation generator 208 may label different parts of other organs such as the spleen, kidneys, pancreas, etc., via text and / or graphic markers. Additionally or alternatively, the schematic representation generator 208 processes such information and generates renderings of elements characterizing liver disease (including the right hepatic notch, portal vein, gallbladder, liver surface nodules, falciform ligament, collateral vessels, ascites, and / or perihular portal canal space) and / or other tissues, and generates a mask of tissues reflecting the health status of the liver.

[0091] At 1510, the schematic representation module 116 outputs a schematic representation of the liver, as described herein and / or otherwise. An example of a schematic representation generated from CT imaging data of the liver is illustrated with reference to Figure 11. Another example of a schematic representation generated from CT imaging data of the liver is illustrated with reference to Figure 12. This representation can be incorporated into reports, printed, archived, transmitted to another device, etc.

[0092] The above method can be implemented by computer-readable instructions encoded or embedded on a computer-readable storage medium, which, when executed by a computer processor, cause the processor to perform the described action or function. Additionally or alternatively, at least one of the computer-readable instructions may be executed by a signal, a carrier wave, or other transient medium that is not a computer-readable storage medium.

[0093] As used herein, elements or steps listed in the singular and beginning with the word "a" or "an" should be understood to not exclude multiple said elements or steps unless such exclusion is explicitly stated. Furthermore, references to "an embodiment" of the invention are not intended to be construed as excluding the existence of additional embodiments that also include the referenced features. Moreover, unless explicitly stated to the contrary, embodiments that "comprise," "include," or "have" one or more elements having a particular attribute may include additional elements that do not have that attribute. The terms "comprise" and "in" are used as concise linguistic equivalents to the corresponding terms "comprising" and "wherein". Furthermore, the terms "first," "second," and "third," etc., are used merely as notations and are not intended to impose numerical requirements or a particular order of position on their objects.

[0094] Various implementations and / or components (e.g., modules or components and controllers therein) may also be implemented as part of one or more computers or processors. The computer or processor may include computing devices, input devices, display units, and interfaces, such as for accessing the Internet. The computer or processor may include a microprocessor. The microprocessor may be connected to a communication bus. The computer or processor may also include memory. Memory may include random access memory (RAM) and read-only memory (ROM). The computer or processor may further include a storage device, which may be a hard disk drive or a removable storage drive, such as a floppy disk drive, optical disk drive, etc. The storage device may also be other similar means for loading computer programs or other instructions into the computer or processor.

[0095] As used herein, the terms "computer" or "module" can include any processor-based or microprocessor-based system, including systems using microcontrollers, reduced instruction set computers (RISCs), application-specific integrated circuits (ASICs), logic circuits, and any other circuitry or processors capable of performing the functions described herein. The examples above are merely illustrative and are therefore not intended to limit the definition and / or meaning of the term "computer" in any way. A computer or processor executes a set of instructions stored in one or more storage elements to process input data. Storage elements may also store data or other information as desired or required. Storage elements may take the form of an information source within the processor or a physical memory element.

[0096] An instruction set may include various commands that instruct a computer or processor to perform specific operations (such as methods and processes according to various embodiments of the present invention) as a processing machine. The instruction set may be in the form of a software program. Software may take various forms, such as system software or application software. Furthermore, software may take the form of a collection of separate programs or modules, a program module within a larger program, or a portion of a program module. Software may also include modular programming in the form of object-oriented programming. The processor's processing of input data may be in response to operator commands, the results of previous processing, or a request from another processor.

[0097] As used herein, the terms “software” and “firmware” are interchangeable and include any computer program stored in memory for execution by a computer, including RAM memory, ROM memory, EPROM memory, EEPROM memory, and non-volatile RAM (NVRAM) memory. The memory types described above are merely exemplary and therefore do not limit the types of memory that can be used to store computer programs.

[0098] It should be understood that the above description is intended to be illustrative and not restrictive. For example, the above embodiments (and / or aspects thereof) may be used in combination with each other. Furthermore, many modifications may be made to adapt particular situations or materials to the teachings of various embodiments of the invention without departing from the scope of the invention. While the dimensions and types of materials described herein are intended to define parameters of various embodiments of the invention, these embodiments are by no means restrictive but exemplary. Many other embodiments will be apparent to those skilled in the art upon review of the above description.

[0099] This written description uses examples to disclose various embodiments of the invention, including the best mode, and also enables those skilled in the art to practice various embodiments of the invention, including making and using any device or system and performing any included methods. The patent scope of the various embodiments of the invention is defined by the claims and may include other examples that would occur to those skilled in the art. Such other examples are intended to fall within the scope of the claims if they have structural elements that are not indistinguishable from the literal language of the claims, or if they include equivalent structural elements that differ only slightly from the literal language of the claims.

[0100] The embodiments shown in the accompanying drawings and described above are merely exemplary embodiments and are not intended to limit the scope of the appended claims, including any equivalents included within the scope of the claims. Various modifications are possible and will be apparent to those skilled in the art. Any combination of the non-mutually exclusive features described herein is intended to be within the scope of this disclosure. That is, features of the embodiments may be combined with any suitable aspect described above, and optional features of any aspect may be combined with any other suitable aspect. Similarly, features listed in dependent claims may be combined with non-mutually exclusive features of other dependent claims, particularly where the dependent claims are subordinate to the same independent claim. In some jurisdictions that claim a single claim dependency, such dependencies may have been used in practice, but this should not be construed as meaning that the features in the dependent claims are mutually exclusive.

Claims

1. A computer-implemented method, the computer-implemented method comprising: A first mask of primary tissue of interest segmented from image data of a subject is obtained, wherein the health status of the primary tissue of interest is being evaluated; A second set of masks of other tissues indicating the health status of the primary tissue of interest is obtained from the image data of the subject; A third set of masks is obtained from the image data of the subject as elements representing disease signs in the primary tissue of interest; And using the image data, the first mask, the second set of masks, and the third set of masks, a schematic representation of the health status of the primary tissue of interest of the subject is generated, wherein the schematic representation provides a summary of health-related information from the image data regarding the health status of the primary tissue of interest.

2. The computer-implemented method according to claim 1, further comprising: Determine at least one measurement result of at least one organization in at least one of the first mask, the second set of masks, and the third set of masks; And include the at least one measurement result of the at least one organization in the illustrative representation.

3. The computer-implemented method according to claim 1, further comprising: Obtain the sub-segmentation mask of the first mask; A metric is derived based on at least one of the sub-segmentation mask, the first mask, the second set of masks, and the third set of masks; each of the derived metrics is classified as indicating healthy or unhealthy tissue; and the derived metrics and corresponding classifications are included together with the illustrative representation.

4. The computer-implemented method according to claim 3, wherein the computer-implemented method further comprises: Subclassify each resulting metric classified as unhealthy tissue across two or more subcategories or a series of consecutive subcategories.

5. The computer-implemented method according to claim 1, wherein the computer-implemented method further comprises: The schematic representation is generated based on a set of rules that identify a set of image slices in the image data for each organization in the schematic representation.

6. The computer-implemented method according to claim 5, wherein the set of rules includes: The primary tissue of interest from a predetermined image slice of the image data is incorporated into the schematic representation.

7. The computer-implemented method according to claim 6, wherein the set of rules includes: At least one of the other tissues from the image slices of the image data is incorporated into the illustrative representation, the image data including the maximum size of the at least one tissue.

8. The computer-implemented method according to claim 6, wherein the set of rules includes: The accumulation of at least one element of the elements in the image data is incorporated into the schematic representation.

9. The computer-implemented method according to claim 6, wherein the set of rules includes: The accumulation of at least one element from a predetermined set of image slices related to the image slice is incorporated into the illustrative representation.

10. The computer-implemented method of claim 6, wherein the set of rules comprises: The outline of the subject from the image slice is incorporated into the schematic representation.

11. The computer-implemented method according to claim 9, wherein the computer-implemented method further comprises: Rendering of at least one of the following: the primary organization of interest and other organizations; The element, and the sub-parts of the primary tissue of interest from the sub-segment; The rendering is included together with the schematic representation.

12. The computer-implemented method according to claim 1, further comprising: The illustrative representation is included together with the examinee's medical report.

13. A system comprising: Display devices; A memory configured to store computer-readable instructions for generating a schematic representation of the health status of the primary tissue of interest of the subject based on image data of the subject; and at least one processor configured to execute the computer-readable instructions, which cause the at least one processor to perform the method according to any one of claims 1 to 12.

14. A computer-readable medium encoded with computer-readable instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 12.

Images