PMID- 35604969
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20221031
LR  - 20221031
IS  - 1558-254X (Electronic)
IS  - 0278-0062 (Linking)
VI  - 41
IP  - 11
DP  - 2022 Nov
TI  - Anti-Interference From Noisy Labels: Mean-Teacher-Assisted Confident Learning for 
      Medical Image Segmentation.
PG  - 3062-3073
LID - 10.1109/TMI.2022.3176915 [doi]
AB  - Manually segmenting medical images is expertise-demanding, time-consuming and 
      laborious. Acquiring massive high-quality labeled data from experts is often 
      infeasible. Unfortunately, without sufficient high-quality pixel-level labels, 
      the usual data-driven learning-based segmentation methods often struggle with 
      deficient training. As a result, we are often forced to collect additional 
      labeled data from multiple sources with varying label qualities. However, 
      directly introducing additional data with low-quality noisy labels may mislead 
      the network training and undesirably offset the efficacy provided by those 
      high-quality labels. To address this issue, we propose a Mean-Teacher-assisted 
      Confident Learning (MTCL) framework constructed by a teacher-student architecture 
      and a label self-denoising process to robustly learn segmentation from a small 
      set of high-quality labeled data and plentiful low-quality noisy labeled data. 
      Particularly, such a synergistic framework is capable of simultaneously and 
      robustly exploiting (i) the additional dark knowledge inside the images of 
      low-quality labeled set via perturbation-based unsupervised consistency, and (ii) 
      the productive information of their low-quality noisy labels via explicit label 
      refinement. Comprehensive experiments on left atrium segmentation with simulated 
      noisy labels and hepatic and retinal vessel segmentation with real-world noisy 
      labels demonstrate the superior segmentation performance of our approach as well 
      as its effectiveness on label denoising.
FAU - Xu, Zhe
AU  - Xu Z
FAU - Lu, Donghuan
AU  - Lu D
FAU - Luo, Jie
AU  - Luo J
FAU - Wang, Yixin
AU  - Wang Y
FAU - Yan, Jiangpeng
AU  - Yan J
FAU - Ma, Kai
AU  - Ma K
FAU - Zheng, Yefeng
AU  - Zheng Y
FAU - Tong, Raymond Kai-Yu
AU  - Tong RK
LA  - eng
PT  - Journal Article
DEP - 20221027
PL  - United States
TA  - IEEE Trans Med Imaging
JT  - IEEE transactions on medical imaging
JID - 8310780
SB  - IM
EDAT- 2022/05/24 06:00
MHDA- 2022/05/24 06:01
CRDT- 2022/05/23 13:54
PHST- 2022/05/24 06:00 [pubmed]
PHST- 2022/05/24 06:01 [medline]
PHST- 2022/05/23 13:54 [entrez]
AID - 10.1109/TMI.2022.3176915 [doi]
PST - ppublish
SO  - IEEE Trans Med Imaging. 2022 Nov;41(11):3062-3073. doi: 10.1109/TMI.2022.3176915. 
      Epub 2022 Oct 27.