Title:
ADAPTIVE MACHINE LEARNING-BASED LESION IDENTIFICATION
Document Type and Number:
WIPO Patent Application WO/2024/081727
Kind Code:
A3
Abstract:
An adaptable deep learning method is provided that delivers sound hepatic lesion identification in NETs, while significantly reducing human effort for data annotation and improving model generalizability for PET image quantification. A region-guided GAN (RGGAN) model conducts image-to-image translation between list-mode simulated PET images and real-world clinical data, while preserving semantic content of interest, e.g., lesions. The RG-GAN model is integrated with a lesion detection model into an end-to-end, unified framework for joint-task learning, such that the two models can benefit from each other. The RG-GAN translates the list-mode simulated data into real world-style images, which appear to be drawn from the real clinical PET image dataset, and feeds the translated images into the lesion detection model for training. In order to deal with the limited diversity of list mode-simulated PET image data, a specific data augmentation module is incorporated into the unified framework to improve model training.
Inventors:
CHIN BENNETT (US)
SILOSKY MICHAEL STEPHEN (US)
XING FUYONG (US)
YANG XINYI (US)
SILOSKY MICHAEL STEPHEN (US)
XING FUYONG (US)
YANG XINYI (US)
Application Number:
PCT/US2023/076590
Publication Date:
May 23, 2024
Filing Date:
October 11, 2023
Export Citation:
Assignee:
UNIV COLORADO REGENTS (US)
International Classes:
G06T7/00; G06V10/82
Attorney, Agent or Firm:
BELL, Ethan W. et al. (US)
Download PDF: