公开(公告)号：US20220188978A1

公开(公告)日：2022-06-16

申请号：US17340117

申请日：2021-06-07

Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY

Inventor： Zhanli HU ,  Hairong ZHENG ,  Na ZHANG ,  Xin LIU ,  Dong LIANG ,  Yongfeng YANG ,  Hanyu SUN

IPC: G06T5/00 ,  A61B6/03 ,  G06N3/04 ,  G06N3/08

Abstract: The present application relates to a method and system for generating multi-task learning-type generative adversarial network for low-dose PET reconstruction, and relates to the field of deep learning. The method includes connecting layers of the encoder with layers of the decoder by skip connection to provide a U-Net type picture generator; generating a group of generative adversarial networks by matching a plurality of picture generators with a plurality of discriminators in one-to-one manner; obtaining a first multi-task learning-type generative adversarial network; designing a joint loss function 1 for improving image quality; and training the first multi-task learning-type generative adversarial network according to the joint loss function 1 in combination with an optimizer to provide a second multi-task learning-type generative adversarial network.