Patent · US Active

Deep learning-assisted image reconstruction for tomographic imaging

US11403792B2 · kind B2 · utility

1Cited by
18References
25Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 18, 2018
Grant dateAug 2, 2022
Priority date
Expiry dateApr 7, 2039

Classification

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

Abstract

Systems and methods for reconstructing an image of a subject or object based on a plurality of measured signals representing the subject or object obtained by an imaging device are disclosed. The systems and methods reconstruct the image of the subject or object by performing an iterative reconstruction method to produce a plurality of intermediate images and the image of the subject, and transforming at least one selected intermediate image from the plurality of intermediate images using a quasi-projection operator. The quasi-projection operator includes a deep-learning model configured to map the at least one selected intermediate image to at least one regularized intermediate image. In addition, systems and methods for training the deep-learning model using a training data set that includes a plurality of training images and a plurality of corresponding training object images is disclosed.

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