Developing a training set for a deep learning system configured to determine a centerline in a three dimensional image
US10861178B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 2, 2018 |
| Grant date | Dec 8, 2020 |
| Priority date | — |
| Expiry date | Jan 14, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30172
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods for generating a training example to train artificial intelligence software to automatically determine a centerline of an elongated structure of three dimensional images. One system includes an electronic processor configured to receive a plurality of reference points for a subset of a plurality of slices of a first three dimensional image. Each of the plurality of reference points marks a centerline of the elongated structure within one of the subset of the plurality of slices. The electronic processor is configured to determine an order of the plurality of reference points and fit a spline curve to the plurality of reference points based on the order of the reference points to create the training example. The electronic processor is further configured use the training example to train the artificial intelligence software to automatically determine a centerline of an elongated structure in a second three dimensional medical image.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.