EUVIMEDEUVIMED entdecken
Übersichtsarbeit

A survey of label-noise deep learning for medical image analysis

Jialin Shi, Kailai Zhang, Chenyi Guo, Youquan Yang, Yali Xu, Ji Wu

Medical Image Analysis · 2024-07 · 95 · 103166

DOI: 10.1016/j.media.2024.103166 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Medical Image Analysis, 2024-07. Verfasst von Jialin Shi und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China. Electronic address: shijl@ustb.edu.cn. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 88-mal zitiert (Crossref) und nennt 111 Literaturangaben. Gefördert von: Key Research and Development Program of Ningxia, Chinese Academy of Meteorological Sciences, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Several factors are associated with the success of deep learning. One of the most important reasons is the availability of large-scale datasets with clean annotations. However, obtaining datasets with accurate labels in the medical imaging domain is challenging. The reliability and consistency of medical labeling are some of these issues, and low-quality annotations with label noise usually exist. Because noisy labels reduce the generalization performance of deep neural networks, learning with noisy labels is becoming an essential task in medical image analysis. Literature on this topic has expanded in terms of volume and scope. However, no recent surveys have collected and organized this knowledge, impeding the ability of researchers and practitioners to utilize it. In this work, we presented an up-to-date survey of label-noise learning for medical image domain. We reviewed extensive literature, illustrated some typical methods, and showed unified taxonomies in terms of methodological differences. Subsequently, we conducted the methodological comparison and demonstrated the corresponding advantages and disadvantages. Finally, we discussed new research directions based on the characteristics of medical images. Our survey aims to provide researchers and practitioners with a solid understanding of existing medical label-noise learning, such as the main algorithms developed over the past few years, which could help them investigate new methods to combat with the negative effects of label noise.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHumansImage Processing, Computer-AssistedAlgorithmsDiagnostic ImagingReproducibility of Results

Stichwörter der Autor:innen

Deep learningMedical imagesNoise-tolerant learningNoisy labels

Autor:innen und Institutionen

  • School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China. Electronic address: shijl@ustb.edu.cn.
  • Department of Networks, China Mobile Communications Group Co., Ltd., Beijing, China.
  • Department of Electronic Engineering, Tsinghua University, Beijing, China.
  • ByteDance, Beijing, China.
  • Department of Breast Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.

Förderung

  • Key Research and Development Program of Ningxia
  • Chinese Academy of Meteorological Sciences
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Shi, J., Zhang, K., Guo, C., Yang, Y., Xu, Y., & Wu, J. (2024). A survey of label-noise deep learning for medical image analysis. Medical Image Analysis, 95, 103166. https://doi.org/10.1016/j.media.2024.103166

Vancouver

Shi J, Zhang K, Guo C, Yang Y, Xu Y, Wu J. A survey of label-noise deep learning for medical image analysis. Medical Image Analysis. 2024;95:103166. doi:10.1016/j.media.2024.103166

BibTeX
@article{Shi2024,
  author = {Shi, Jialin and Zhang, Kailai and Guo, Chenyi and Yang, Youquan and Xu, Yali and Wu, Ji},
  title = {A survey of label-noise deep learning for medical image analysis},
  journal = {Medical Image Analysis},
  year = {2024},
  volume = {95},
  pages = {103166},
  doi = {10.1016/j.media.2024.103166}
}
Kostenlos starten →