Multiple landmark detection in medical images based on hierarchical feature learning and end-to-end training
US10210613B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 10, 2017 |
| Grant date | Feb 19, 2019 |
| Priority date | — |
| Expiry date | Jul 28, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30004
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present embodiments relate to detecting multiple landmarks in medical images. By way of introduction, the present embodiments described below include apparatuses and methods for detecting landmarks using hierarchical feature learning with end-to-end training. Multiple neural networks are provided with convolutional layers for extracting features from medical images and with a convolutional layer for learning spatial relationships between the extracted features. Each neural network is trained to detect different landmarks using a different resolution of the medical images, and the convolutional layers of each neural network are trained together with end-to-end training to learn appearance and spatial configuration simultaneously. The trained neural networks detect multiple landmarks in a test image iteratively by detecting landmarks at different resolutions, using landmarks detected a lesser resolutions to detect additional landmarks at higher resolutions.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.