Semi-supervised medical image segmentation via uncertainty rectified pyramid consistency

被引:151
作者
Luo, Xiangde [1 ,2 ]
Wang, Guotai [1 ,2 ]
Liao, Wenjun [3 ]
Chen, Jieneng [4 ]
Song, Tao [5 ]
Chen, Yinan [5 ,6 ]
Zhang, Shichuan [7 ]
Metaxas, Dimitris N. [8 ]
Zhang, Shaoting [1 ,2 ]
机构
[1] Univ Elect Sci & Technol China, Sch Mech & Elect Engn, Chengdu, Peoples R China
[2] Shanghai AI Lab, Shanghai, Peoples R China
[3] Southern Med Univ, Nanfang Hosp, Dept Radiat Oncol, Guangzhou, Peoples R China
[4] Tongji Univ, Coll Elect & Informat Engn, Shanghai, Peoples R China
[5] SenseTime Res, Shanghai, Peoples R China
[6] Sichuan Univ West China Hosp, West China Biomed Big Data Ctr, Chengdu, Peoples R China
[7] Univ Elect Sci & Technol China, Sichuan Canc Hosp & Inst, Dept Radiat Oncol, Chengdu, Peoples R China
[8] Rutgers State Univ, Dept Comp Sci, Piscataway, NJ 08854 USA
关键词
Semi-supervised learning; Uncertainty rectifying; Pyramid consistency; Image segmentation; NETWORKS;
D O I
10.1016/j.media.2022.102517
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Despite that Convolutional Neural Networks (CNNs) have achieved promising performance in many medical image segmentation tasks, they rely on a large set of labeled images for training, which is expensive and time-consuming to acquire. Semi-supervised learning has shown the potential to alleviate this challenge by learning from a large set of unlabeled images and limited labeled samples. In this work, we present a simple yet efficient consistency regularization approach for semi-supervised medical image segmentation, called Uncertainty Rectified Pyramid Consistency (URPC). Inspired by the pyramid feature network, we chose a pyramid-prediction network that obtains a set of segmentation predictions at different scales. For semi-supervised learning, URPC learns from unlabeled data by minimizing the discrepancy between each of the pyramid predictions and their average. We further present multi-scale uncertainty rectification to boost the pyramid consistency regularization, where the rectification seeks to temper the consistency loss at outlier pixels that may have substantially different predictions than the average, potentially due to upsampling errors or lack of enough labeled data. Experiments on two public datasets and an in-house clinical dataset showed that: 1) URPC can achieve large performance improvement by utilizing unlabeled data and 2) Compared with five existing semi-supervised methods, URPC achieved better or comparable results with a simpler pipeline. Furthermore, we build a semi-supervised medical image segmentation codebase to boost research on this topic: https://github.com/HiLab- git/SSL4MIS. (C) 2022 Published by Elsevier B.V.
引用
收藏
页数:13
相关论文
共 64 条
[1]  
Berthelot D, 2019, ADV NEUR IN, V32
[2]   Uncertainty Aware Temporal-Ensembling Model for Semi-Supervised ABUS Mass Segmentation [J].
Cao, Xuyang ;
Chen, Houjin ;
Li, Yanfeng ;
Peng, Yahui ;
Wang, Shu ;
Cheng, Lin .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2021, 40 (01) :431-443
[3]  
Carion Nicolas, 2020, Computer Vision - ECCV 2020. 16th European Conference. Proceedings. Lecture Notes in Computer Science (LNCS 12346), P213, DOI 10.1007/978-3-030-58452-8_13
[4]  
Chaitanya K., 2020, NeurIPS, V33
[5]  
Chapelle O., 2009, IEEE Trans. Neural Netw., V20, P542
[6]   Multi-task Attention-Based Semi-supervised Learning for Medical Image Segmentation [J].
Chen, Shuai ;
Bortsova, Gerda ;
Juarez, Antonio Garcia-Uceda ;
van Tulder, Gijs ;
de Bruijne, Marleen .
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT III, 2019, 11766 :457-465
[7]   Cancer incidence and mortality in China, 2014 [J].
Chen, Wanqing ;
Sun, Kexin ;
Zheng, Rongshou ;
Zeng, Hongmei ;
Zhang, Siwei ;
Xia, Changfa ;
Yang, Zhixun ;
Li, He ;
Zou, Xiaonong ;
He, Jie .
CHINESE JOURNAL OF CANCER RESEARCH, 2018, 30 (01) :1-12
[8]   DEEP ELASTICA FOR IMAGE SEGMENTATION [J].
Chen, Xu ;
Luo, Xiangde ;
Wang, Guotai ;
Zheng, Yalin .
2021 IEEE 18TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2021, :706-710
[9]   Learning Active Contour Models for Medical Image Segmentation [J].
Chen, Xu ;
Williams, Bryan M. ;
Vallabhaneni, Srinivasa R. ;
Czanner, Gabriela ;
Williams, Rachel ;
Zheng, Yalin .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :11624-11632
[10]  
Cicek Ozgun, 2016, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016. 19th International Conference. Proceedings: LNCS 9901, P424, DOI 10.1007/978-3-319-46723-8_49