Multi-rater Prism:Learning self-calibrated medical image segmentation from multiple raters

扫码查看

原文链接

NETL
NSTL
万方数据

外文摘要：In medical image segmentation,it is often necessary to collect opinions from multiple experts to make the final decision.This clinical routine helps to mitigate individual bias.However,when data is annotated by multiple experts,standard deep learning models are often not applicable.In this paper,we propose a novel neural network framework called Multi-rater Prism(MrPrism)to learn medical image segmenta-tion from multiple labels.Inspired by iterative half-quadratic optimization,MrPrism combines the task of assigning multi-rater confidences and calibrated segmentation in a recurrent manner.During this pro-cess,MrPrism learns inter-observer variability while taking into account the image's semantic properties and finally converges to a self-calibrated segmentation result reflecting inter-observer agreement.Specifically,we propose Converging Prism(ConP)and Diverging Prism(DivP)to iteratively process the two tasks.ConP learns calibrated segmentation based on multi-rater confidence maps estimated by DivP,and DivP generates multi-rater confidence maps based on segmentation masks estimated by ConP.Experimental results show that the two tasks can mutually improve each other through this recur-rent process.The final converged segmentation result of MrPrism outperforms state-of-the-art(SOTA)methods for a wide range of medical image segmentation tasks.The code is available at https://github.-com/WuJunde/MrPrism.

外文关键词：

Medical image segmentationMultiple ratersSelf-calibrationHalf-quadratic algorithm

作者：

Junde Wu、Huihui Fang、Jiayuan Zhu、Yu Zhang、Xiang Li、Yuanpei Liu、Huiying Liu、Yueming Jin、Weimin Huang、Qi Liu、Cen Chen、Yanfei Liu、Lixin Duan、Yanwu Xu、Li Xiao、Weihua Yang、Yue Liu

展开 >

作者单位：

School of Future Technology,South China University of Technology,Guangzhou 511442,China

Pazhou Lab,Guangzhou 510320,China

The University of Oxford,Oxford OX14AL,UK

Cardiovascular Disease Center,Xiyuan Hospital of China Academy of Chinese Medical Sciences,Beijing 100091,China

State Key Laboratory of Pulsed Power Laser Technology,College of Electronic Engineering,National University of Defense Technology,Hefei 230037,China

Shenzhen Institute for Advanced Study,University of Electronic Science and Technology of China,Shenzhen 518110,China

The University of Hong Kong,Hong Kong 999077,China

Institute for Infocomm Research,A*STAR,Singapore 138632,Singapore

National University of Singapore,Singapore 119276,Singapore

Sichuan Provincial People's Hospital,University of Electronic Science and Technology of China,Chengdu 611731,China

Shenzhen Eye Hospital, Jinan University, Shenzhen 518040, China

展开 >

基金：

Excellent Young Science and Technology Talent Cultivation Special Project of China Academy of Chinese Medical SciencesNational Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaBeijing Natural Science FoundationShenzhen Fundamental Research ProgramGuangdong Provincial Key Laboratory of Human Digital Twin

项目编号：

CI2023D00682121003820220762190023JCYJ202208181032070152022B1212010004

出版年：

2024

DOI：

10.1016/j.scib.2024.06.037

科学通报(英文版)

中国科学院

科学通报(英文版)

CSTPCD

ISSN：1001-6538

年,卷(期)：2024.69(18)