System for segmentation of anatomical structures in cardiac CTA using fully convolutional neural networks
US10896508B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 26, 2018 |
| Grant date | Jan 19, 2021 |
| Priority date | — |
| Expiry date | Dec 5, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V2201/03
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method comprises (a) collecting (i) a set of chest computed tomography angiography (CTA) images scanned in the axial view and (ii) a manual segmentation of the images, for each one of multiple organs; (b) preprocessing the images such that they share the same field of view (FOV); (c) using both the images and their manual segmentation to train a supervised deep learning segmentation network, wherein loss is determined from a multi-dice score that is the summation of the dice scores for all the multiple organs, each dice score being computed as the similarity between the manual segmentation and the output of the network for one of the organs; (d) testing a given (input) pre-processed image on the trained network, thereby obtaining segmented output of the given image; and (e) smoothing the segmented output of the given image.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.