Patent · US Active

Multi-task learning based regions-of-interest enhancement in PET image reconstruction

US12367622B2 · kind B2 · utility

0Cited by
1References
4Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 22, 2022
Grant dateJul 22, 2025
Priority date
Expiry dateDec 12, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2211/441
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Disclosed is a method for region-of-interest enhanced PET image reconstruction based on multi-task learning, which comprises the following steps: firstly, acquiring a backprojection image of the PET original data, and designing a main task of establishing a mapping between the backprojection image and a reconstructed PET image by using a three-dimensional deep convolution neural network. A new auxiliary task 1 is designed to predict a computerized tomography (CT) image with the same anatomical structures as the PET image reconstructed from the backprojection image, so as to reduce the noise in the reconstructed PET image by using the local smoothing information of the high-resolution CT image.

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