Search

EP-4738248-A1 - SCHEMATIC REPRESENTATION OF A HEALTH STATE OF TISSUE OF INTEREST BASED ON MEDICAL IMAGE DATA

EP4738248A1EP 4738248 A1EP4738248 A1EP 4738248A1EP-4738248-A1

Abstract

A computer-implemented method includes obtaining a first mask of primary tissue of interest segmented from image data of a subject, obtaining a second set of masks of other tissue indicative of the health state of the primary tissue of interest from the image data of the subject, obtaining a third set of masks of elements that are signs of disease of the primary tissue of interest from the image data of the subject, and generating a schematic representation of the health state of the primary tissue of interest of the subject with the image data, the first mask, the second set of masks and the third set of masks. In one instance, a health state of the primary tissue of interest is under evaluation and the schematic representation provides a summary of health related information about the health state of the primary tissue of interest from the image data.

Inventors

  • MORARD, Vincent
  • LONDOÑO, Jorge Eduardo Hernandez
  • BOURGHES, Sofiène

Assignees

  • GE Precision Healthcare LLC

Dates

Publication Date
20260506
Application Date
20251006

Claims (15)

  1. A computer-implemented method, comprising: obtaining a first mask of primary tissue of interest segmented from image data of a subject, wherein a health state of the primary tissue of interest is under evaluation; obtaining a second set of masks of other tissue indicative of the health state of the primary tissue of interest from the image data of the subject; obtaining a third set of masks of elements that are signs of disease of the primary tissue of interest from the image data of the subject; and generating a schematic representation of the health state of the primary tissue of interest of the subject with the image data, the first mask, the second set of masks and the third set of masks, wherein the schematic representation provides a summary of health related information about the health state of the primary tissue of interest from the image data.
  2. The computer-implemented method of claim 1, further comprising: determining at least one measurement for at least one tissue in at least one of the first mask, the second set of masks and the third set of masks; and including the at least one measurement for the at least one tissue in the schematic representation.
  3. The computer-implemented method of claim 1, further comprising: obtaining a sub-segmentation mask of the first mask; deriving metrics based on at least one of the sub-segmentation mask, the first mask, the second set of masks and the third set of masks; classifying each of the derived metrics as indicating healthy or not healthy tissue; and including the derived metrics and corresponding classifications with the schematic representation.
  4. The computer-implemented method of claim 3, further comprising: sub-classifying each derived metric classified as not healthy tissue across two or more or a continuum of sub-classifications.
  5. The computer-implemented method of claim 1, further comprising: generating the schematic representation based on a set of rules that identifies a set of images slices in the image data for each tissue in the schematic representation.
  6. The computer-implemented method of claim 5, where the set of rules includes: incorporating the primary tissue of interest from a predetermined image slice of the image data into the schematic representation.
  7. The computer-implemented method of claim 6, where the set of rules includes: incorporating at least one tissue of the other tissue from an image slice of the image data that includes a largest dimension of the at least one tissue into the schematic representation.
  8. The computer-implemented method of claim 6, where the set of rules includes: incorporating an accumulation of at least one element of the elements through the image data into the schematic representation.
  9. The computer-implemented method of claim 6, where the set of rules includes: incorporating an accumulation of at least one element of the elements from a predetermined set of image slices about the image slice into the schematic representation.
  10. The computer-implemented method of claim 6, where the set of rules includes: incorporating a contour of the subject from the image slice into the schematic representation.
  11. The computer-implemented method of claim 9, further comprising: obtaining a rendering of at least one of: the primary tissue of interest with the other tissue; the elements, and sub-portions of the primary tissue of interest from the sub-segmentation; including the rendering with the schematic representation.
  12. The computer-implemented method of claim 1, further comprising: including the schematic representation with a medical report for the subject.
  13. A system (102), comprising: a display device (122); a memory (114) configured to store computer-readable instructions for generating a schematic representation of a health state of a primary tissue of interest of a subject based on image data of the subject; at least one processor (112) configured to execute the computer-readable instructions, which causes the at least one processor to: obtain a first mask of the primary tissue of interest segmented from the image data; obtain a second set of masks of other tissue indicative of the health state of the primary tissue of interest from the image data of the subject; obtain a third set of masks of elements that are signs of disease of the primary tissue of interest from the image data of the subject; and generate the schematic representation with the image data, the first mask, the second set of masks and the third set of masks, wherein the schematic representation provides a summary of health related information about the health state of the primary tissue of interest from the image data.
  14. The system of claim 13, wherein the at least one processor is further configured to: incorporate the primary tissue of interest from an image slice of the image data corresponding to a predetermined functional state of the primary tissue of interest into the schematic representation; incorporate at least one tissue of the other tissue from an image slice of the image data that includes a largest dimension of the at least one tissue into the schematic representation; incorporate an accumulation of at least one element of the elements through the image data into the schematic representation; incorporate an accumulation of at least one element of the elements from a predetermined set of image slices about the image slice into the schematic representation; and incorporate a contour of the subject from the image slice into the schematic representation.
  15. The system of claim 14, wherein the at least one processor is further configured to: determine at least one measurement for at least one tissue in at least one of the first mask, the second set of masks and the third set of masks; include the at least one measurement with the schematic representation; obtain a sub-segmentation mask of the first mask; derive metrics based on at least one of the sub-segmentation mask, the first mask, the second set of masks and the third set of masks; classify each of the derived metrics as indicating healthy or not healthy tissue; include the derived metrics and corresponding classifications with the schematic representation; obtain a rendering of at least one of: the primary tissue of interest with the other tissue; the elements, and sub-portions of the primary tissue of interest from the sub-segmentation; and include the rendering with the schematic representation.

Description

FIELD The following generally relates to medical imaging, and more particularly to a schematic representation of a health state of tissue of interest that is based on medical image data. BACKGROUND Clinicians such as radiologists "read" (i.e., interpret) images, e.g., for diagnosis, monitoring, screening, etc. For example, a clinician observes images in a study for a subject and documents findings (i.e., relevant observations), which include a description of abnormalities and/or normal notable features with respect to tissue, organs, bones, etc. For diagnosis, the findings assist the clinician with identifying diseases, injuries, abnormalities, etc. For monitoring, the findings may assist the clinician with understanding the progression of diseases, injuries, abnormalities, etc. For screening, the findings may assist the clinician with identifying conditions that are likely to lead to certain diseases, injuries, abnormalities, etc. The literature indicates that early detection of diseases, injuries, abnormalities, etc. improves treatment outcomes, including, with respect to certain diseases, the survival rate of patients. Existing visualization approaches have included generating and displaying renderings (e.g., mesh, volume, etc.) and using generic atlases or the like to visualize tissue under evaluation. Unfortunately, such approaches have poorly characterized a health state of the tissue under evaluation and/or other tissue in connection detection of diseases, injuries, abnormalities, etc. and/or conditions likely to lead thereto. In view of the foregoing, there is an unresolve need for an improved approach. SUMMARY Aspects described herein address the above-referenced problems and others. This summary introduces concepts that are described in more detail in the detailed description. It should not be used to identify essential features of the claimed subject matter, nor to limit the scope of the claimed subject matter. In one aspect, a computer-implement method includes obtaining a first mask of primary tissue of interest segmented from image data of a subject. In one instance, a health state of the primary tissue of interest is under evaluation. The computer-implement method further includes obtaining a second set of masks of other tissue indicative of the health state of the primary tissue of interest from the image data of the subject. The computer-implement method further includes obtaining a third set of masks of elements that are signs of disease of the primary tissue of interest from the image data of the subject. The computer-implement method further includes generating a schematic representation of the health state of the primary tissue of interest of the subject with 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 about the health state of the primary tissue of interest from the image data. 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 a health state of a primary tissue of interest of a 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 of the primary tissue of interest segmented from the image data, obtain a second set of masks of other tissue indicative of the health state of the primary tissue of interest from the image data of the subject, obtain a third set of masks of elements that are signs of disease of the primary tissue of interest from the image data of the subject, and generate the schematic representation with 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 about the health state of the primary tissue of interest from the image data. In another aspect, a computer readable medium is encoded with computer executable instructions. The computer executable instructions, when executed by a processor, cause the processor to obtain a first mask of primary tissue of interest segmented from image data of a subject, wherein a health state of the primary tissue of interest is under evaluation, obtain a second set of masks of other tissue indicative of the health state of the primary tissue of interest from the image data of the subject, obtain a third set of masks of elements that are signs of disease of the primary tissue of interest from the image data of the subject, and generate a schematic representation of the health state of the primary tissue of interest of the subject with 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 i