Method, device, and computer program product for self-supervised learning of pixel-wise anatomical embeddings in medical images
US11620359B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 22, 2021 |
| Grant date | Apr 4, 2023 |
| Priority date | — |
| Expiry date | Dec 22, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V2201/03
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present disclosure provides a method, a device, and a computer program product using a self-supervised anatomical embedding (SAM) method. The method includes randomly selecting a plurality of images; for each image of the plurality of images, performing random data augmentation to obtain a patch pair, generating global and local embedding tensors for each patch of the patch pair, and selecting positive pixel pairs from the patch pair and obtaining positive embedding pairs; for each positive pixel pair, computing global and local similarity maps, finding global hard negative embeddings, selecting global random negative embeddings, pooling the global hard negative embeddings and the global random negative embeddings to obtain final global negative embeddings, and finding local hard negative embeddings using the global and local similarity maps, and randomly sampling final local negative embeddings from the local hard negative embeddings; and minimizing a final info noise contrastive estimation (InfoNCE) loss.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.