Title: Few-view computed tomography reconstruction using deep neural network inference

Abstract

A system for generating 2D slices of a 3D image of a target volume is provided. The system receives a target sinogram collected during a computed tomography scan of the target volume. The system inputs the target sinogram to a convolutional neural network (CNN) to generate predicted 2D slices of the 3D image. The CNN is trained using training 2D slices of training 3D images. The system initializes 2D slices to the predicted 2D slices. The system reconstructs 2D slices of the 3D image from the target sinogram and the initialized 2D slices.

Inventors:

Kim, Hyojin; Anirudh, Rushil; Champley, Kyle

Issue Date:

2023-10-10

Research Org.:

Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Sponsoring Org.:

USDOE

OSTI Identifier:

2293704

Patent Number(s):

11783518

Application Number:

17/038,565

Assignee:

Lawrence Livermore National Security, LLC (Livermore, CA)

Patent Classifications (CPCs):

A - HUMAN NECESSITIES A61 - MEDICAL OR VETERINARY SCIENCE A61B - DIAGNOSIS

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS

Show more

A - HUMAN NECESSITIES A61 - MEDICAL OR VETERINARY SCIENCE A61B - DIAGNOSIS

A61B6/032 - {Transmission computed tomography [CT]}

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS

G06N3/08 - Learning methods
G06N3/088 - {Non-supervised learning, e.g. competitive learning}

G - PHYSICS G06 - COMPUTING G06T - IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

G06T11/006 - {Inverse problem, transformation from projection-space into object-space, e.g. transform methods, back-projection, algebraic methods}
G06T2211/436 - Limited angle
G06T9/002 - {using neural networks}

Show less

DOE Contract Number:  

AC52-07NA27344

Resource Type:

Patent

Resource Relation:

Patent File Date: 09/30/2020

Country of Publication:

United States

Language:

English