Invention Grant
- Patent Title: Few-shot learning based image recognition of whole slide image at tissue level
-
Application No.: US16129621Application Date: 2018-09-12
-
Publication No.: US10769788B2Publication Date: 2020-09-08
- Inventor: Bing Song , Mustafa Jaber
- Applicant: NantOmics, LLC
- Applicant Address: US CA Culver City
- Assignee: NantOmics, LLC
- Current Assignee: NantOmics, LLC
- Current Assignee Address: US CA Culver City
- Agency: Mauriel Kapouytian Woods LLP
- Agent Liang Huang; Andrew Noble
- Main IPC: G06T7/00
- IPC: G06T7/00 ; G06T7/73 ; G16H10/60 ; G16H80/00 ; G16H10/40 ; G06T7/40 ; G06K9/00 ; G16H30/40 ; G06K9/62 ; G06K9/46 ; G16H50/20 ; G16H40/67

Abstract:
A computer implemented method of generating at least one shape of a region of interest in a digital image is provided. The method includes obtaining, by an image processing engine, access to a digital tissue image of a biological sample; tiling, by the image processing engine, the digital tissue image into a collection of image patches; obtaining, by the image processing engine, a plurality of features from each patch in the collection of image patches, the plurality of features defining a patch feature vector in a multidimensional feature space including the plurality of features as dimensions; determining, by the image processing engine, a user selection of a user selected subset of patches in the collection of image patches; classifying, by applying a trained classifier to patch vectors of other patches in the collection of patches, the other patches as belonging or not belonging to a same class of interest as the user selected subset of patches; and identifying one or more regions of interest based at least in part on the results of the classifying.
Public/Granted literature
- US20190080453A1 FEW-SHOT LEARNING BASED IMAGE RECOGNITION OF WHOLE SLIDE IMAGE AT TISSUE LEVEL Public/Granted day:2019-03-14
Information query