EUVIMEDEUVIMED entdecken
Crossref

Reliable Mutual Distillation for Medical Image Segmentation Under Imperfect Annotations

Chaowei Fang, Qian Wang, Lechao Cheng, Zhifan Gao, Chengwei Pan, Zhen Cao, Zhaohui Zheng, Dingwen Zhang

IEEE Transactions on Medical Imaging · 2023-06 · 42 (6) · 1720-1734

DOI: 10.1109/tmi.2023.3237183 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2023-06. Verfasst von Chaowei Fang und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Distillation, Neural Networks, Computer. Die Arbeit wurde bisher 88-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key-Area Research and Development Program of Shaanxi Province, Key-Area Research and Development Program of Guangdong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Convolutional neural networks (CNNs) have made enormous progress in medical image segmentation. The learning of CNNs is dependent on a large amount of training data with fine annotations. The workload of data labeling can be significantly relieved via collecting imperfect annotations which only match the underlying ground truths coarsely. However, label noises which are systematically introduced by the annotation protocols, severely hinders the learning of CNN-based segmentation models. Hence, we devise a novel collaborative learning framework in which two segmentation models cooperate to combat label noises in coarse annotations. First, the complementary knowledge of two models is explored by making one model clean training data for the other model. Secondly, to further alleviate the negative impact of label noises and make sufficient usage of the training data, the specific reliable knowledge of each model is distilled into the other model with augmentation-based consistency constraints. A reliability-aware sample selection strategy is incorporated for guaranteeing the quality of the distilled knowledge. Moreover, we employ joint data and model augmentations to expand the usage of reliable knowledge. Extensive experiments on two benchmarks showcase the superiority of our proposed method against existing methods under annotations with different noise levels. For example, our approach can improve existing methods by nearly 3% DSC on the lung lesion segmentation dataset LIDC-IDRI under annotations with 80% noise ratio. Code is available at: https://github.com/Amber-Believe/ReliableMutualDistillation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DistillationNeural Networks, ComputerReproducibility of ResultsImage Processing, Computer-Assisted

Förderung

  • National Natural Science Foundation of China
  • Key-Area Research and Development Program of Shaanxi Province
  • Key-Area Research and Development Program of Guangdong Province
  • Exploratory Research Project of Zhejiang Laboratory
  • Zhejiang Provincial Natural Science Foundation of China

Zitieren

APA

Fang, C., Wang, Q., Cheng, L., Gao, Z., Pan, C., Cao, Z., Zheng, Z., & Zhang, D. (2023). Reliable Mutual Distillation for Medical Image Segmentation Under Imperfect Annotations. IEEE Transactions on Medical Imaging, 42(6), 1720-1734. https://doi.org/10.1109/tmi.2023.3237183

Vancouver

Fang C, Wang Q, Cheng L, Gao Z, Pan C, Cao Z, et al. Reliable Mutual Distillation for Medical Image Segmentation Under Imperfect Annotations. IEEE Transactions on Medical Imaging. 2023;42(6):1720-1734. doi:10.1109/tmi.2023.3237183

BibTeX
@article{Fang2023,
  author = {Fang, Chaowei and Wang, Qian and Cheng, Lechao and Gao, Zhifan and Pan, Chengwei and Cao, Zhen and Zheng, Zhaohui and Zhang, Dingwen},
  title = {Reliable Mutual Distillation for Medical Image Segmentation Under Imperfect Annotations},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2023},
  volume = {42},
  number = {6},
  pages = {1720--1734},
  doi = {10.1109/tmi.2023.3237183}
}
Kostenlos starten →