Patent · US Active

Method and a system for creating a medical image database by means of a convolutional neural network

US11915464B2 · kind B2 · utility

0Cited by
2References
12Claims
0Family size

Assignee

Inventor

Key dates

Filing dateNov 23, 2017
Grant dateFeb 27, 2024
Priority date
Expiry dateMar 30, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V2201/031
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Embodiments of the disclosure are directed to methods and systems for creating a medical image database, wherein data which comprise partial images of two-dimensional or higher-dimensional initial images of parts of the human body are created, a projection for obtaining feature vectors is created from the partial images, wherein, in order to prepare the execution of the projection, a neural network based on specified learning partial images is created, wherein the data records are used within the scope of a metric learning method to learn the projection and creation of the feature vectors from learning partial images. This is achieved for example by specifying learning partial images that are slightly shifted, rotated, skewed or stretched relative to one another and were created starting from the same initial image as similar.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.