Patents

US 12770378 B2: Medical imaging analysis using self-supervised learning

Granted
2026-10-20
Filed
2023-04-20 application 18304330
Type
Utility · 16 claims
Elsewhere
Google Patents ↗ · USPTO patent document ↗ · USPTO Patent Center record ↗

Abstract

A method includes obtaining a first training data set including unannotated multi-dimensional medical images and executing a self-supervised masked image modeling (MIM) training process to pre-train an image encoder on the first training data set. The method also includes obtaining a second training data set that includes annotated multi-dimensional medical images. Here, each annotated multi-dimensional medical image includes a plurality of image voxels each paired with a corresponding ground-truth label indicating a class the corresponding image voxel belongs to. The method also includes executing a supervised training process to train an image analysis model on the second training data set to teach the image analysis model to learn how to predict the corresponding ground-truth labels for the plurality of image voxels of each annotated multi-dimensional medical image. The image analysis model incorporates the pre-trained image encoder.

Source: PTBLXML, file of 2026-10-20 (ipgb20261020.xml).

Assignees

AssigneeTypePlaceAlso on furp.orgSource
Bristol-Myers Squibb Company 1,812 patentsUS company or organizationPrinceton, NJBRISTOL MYERS SQUIBB CO SEC filer FUZZY low confidence: same name (legal endings aside), one of each nationallyPTBLXML, file of 2026-10-20

Inventors

InventorPlacePatentsPerson pageSource
Zekai ChenGaithersburg, MDPTBLXML, file of 2026-10-20
Kevin Alex BrownDrexel Hill, PAPTBLXML, file of 2026-10-20

CPC categories

SubclassCategoryFirst groupSource
G06VImage or video recognition or understandingG06V10/7753PTBLXML, file of 2026-10-20
G06NComputing arrangements based on specific computational modelsG06N3/0455PTBLXML, file of 2026-10-20
G06TImage data processing or generation, in generalG06T7/0012PTBLXML, file of 2026-10-20
G16HHealthcare informatics, i.e. information and communication technology [ict] specially adapted for the handling or processing of medical or healthcare dataG16H30/20PTBLXML, file of 2026-10-20

Cooperative Patent Classification, as currently assigned (one row per subclass).

Assignments and security interests

No recorded assignments or security interests on file for this patent.

USPTO bulk data: PatentsView granted patents, disambiguated (PVGPATDIS) for patents, assignees, inventors, places and CPC categories; the USPTO Patent Assignment Dataset (ECORSEXC) for assignments and security interests. Patents filed in the last 20 years. No claims or full text. Links to other records are by name (and state): EXACT means the identical full name and state; FUZZY means a looser name match, with the confidence shown.