Method and apparatus for providing information associated with immune phenotypes for pathology slide image
Inventors
Yoo, Donggeun • OCK, Chanyoung • Paeng, Kyunghyun
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12688581-B2
Publication Date
2026-07-21
Expiration Date
Abstract
The present disclosure relates to a method, performed by at least one computing device, for providing information associated with immune phenotype for a pathology slide image. The method may include obtaining information associated with immune phenotype for one or more regions of interest (ROIs) in a pathology slide image, generating, based on the information associated with the immune phenotype for one or more ROIs, an image indicative of the information associated with the immune phenotype, and outputting the image indicative of the information associated with immune phenotype.
Core Innovation
The invention provides a computing device and a method for predicting and visualizing immune phenotypes using a digital image corresponding to an H&E-stained pathology slide. The digital image is divided into a plurality of patches generated by dividing the digital image into equal-sized patches, and the device acquires the digital image and detects one or more target items including immune cells, a cancer area, and a cancer stroma area within the plurality of patches.
The detection is performed using a deep learning model executed by the processor, where the deep learning model is trained based on a reference pathology slide image and label information for one or more reference target items. The device determines immune phenotypes of first patches by using immune-cell density information, where immune phenotypes are determined based on a density of immune cells in the cancer area and a density of immune cells in the cancer stroma area for each patch, and excludes second patches that do not satisfy a predetermined condition associated with at least one of a number of the immune cells, an area of the cancer area, or an area of the cancer stroma area.
Based on immune phenotype information, the device generates a prediction result indicating whether a patient associated with the digital image responds to an immune checkpoint inhibitor. Immune phenotype scores are calculated from information associated with the immune phenotypes of the first patches, and the prediction result is based on the immune phenotype scores.
The device also overlays a distinct visual representation for each of the first patches on the digital image, where the distinct visual representation is indicative of the immune phenotype of the corresponding patch and comprises at least one of color, brightness, saturation, or a mark corresponding to the immune phenotype.
Claims Coverage
The independent claims are clm-00001 and clm-00006. Across these independent claims, the coverage centers on four inventive features: deep-learning detection of immune cells and cancer/tissue regions within equal-sized patches, density-based determination of immune phenotypes for selected patches, immune-phenotype-score-based prediction of immune checkpoint inhibitor response, and distinct per-patch visual representation overlaid on the digital image and output to a user.
Deep learning detection of target items in equal-sized patches
Detecting, using a deep learning model executed by the processor, one or more target items including immune cells, a cancer area, and a cancer stroma area within a plurality of patches, wherein the plurality of patches are generated by dividing the digital image into equal-sized patches, and the deep learning model is trained based on a reference pathology slide image and label information for one or more reference target items.
Density-based immune phenotype determination with predetermined patch selection
Determining, based on a density of immune cells in the cancer area and a density of immune cells in the cancer stroma area for each patch of the plurality of patches, immune phenotypes of first patches from among the plurality of patches that satisfy a predetermined condition associated with at least one of a number of the immune cells, an area of the cancer area, or an area of the cancer stroma area, and excluding one or more second patches from among the plurality of patches that do not satisfy the predetermined condition.
Immune phenotype score-based prediction of immune checkpoint inhibitor response
Generating a prediction result indicating whether a patient associated with the digital image responds to an immune checkpoint inhibitor, based on immune phenotype scores calculated from information associated with the immune phenotypes of the first patches from among the plurality of patches.
Distinct per-patch visual representation for immune phenotype overlay and output
Overlaying a distinct visual representation for each of the first patches on the digital image, the distinct visual representation being indicative of the immune phenotype of the corresponding patch and comprising at least one of color, brightness, saturation, or a mark corresponding to the immune phenotype; and outputting, to a user, the digital image with the overlaid information and the prediction result.
The independent claims cover a computing device and method that combine deep-learning target detection on H&E-stained pathology slide images, density-based immune phenotype classification for selected patches, immune-phenotype-score-based prediction of immune checkpoint inhibitor response, and distinct per-patch immune-phenotype visualization overlaid onto the digital image for user output.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?