CARE: Class Attention to Regions of Lesion for Classification on Imbalanced Data

Jiaxin Zhuang, Jiabin Cai, Ruixuan Wang, Jianguo Zhang, Weishi Zheng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

To date, it is still an open and challenging problem for intelligent diagnosis systems to effectively learn from imbalanced data, especially with large samples of common diseases and much smaller samples of rare ones. Inspired by the process of human learning, this paper proposes a novel and effective way to embed attention into the machine learning process, particularly for learning characteristics of rare diseases. This approach does not change architectures of the original CNN classifiers and therefore can directly plug and play for any existing CNN architecture. Comprehensive experiments on a skin lesion dataset and a pneumonia chest X-ray dataset showed that paying attention to lesion regions of rare diseases during learning not only improved the classification performance on rare diseases, but also on the mean class accuracy.
Original languageEnglish
Title of host publicationProceedings of The 2nd International Conference on Medical Imaging with Deep Learning
EditorsM. Jorge Cardoso, Aasa Feragen, Ben Glocker, Ender Konukoglu, Ipek Oguz, Gozde Unal, Tom Vercauteren
Pages588-597
Number of pages10
Volume102
Publication statusPublished - 2019

Keywords

  • Attention
  • Imbalanced Data
  • Small Samples
  • Skin Lesion
  • Pneumonia Chest X-ray

Fingerprint Dive into the research topics of 'CARE: Class Attention to Regions of Lesion for Classification on Imbalanced Data'. Together they form a unique fingerprint.

Cite this