Skip to main navigation Skip to search Skip to main content

Pseudo Bias-Balanced Learning for Debiased Chest X-Ray Classification

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

Abstract

Deep learning models were frequently reported to learn from shortcuts like dataset biases. As deep learning is playing an increasingly important role in the modern healthcare system, it is of great need to combat shortcut learning in medical data as well as develop unbiased and trustworthy models. In this paper, we study the problem of developing debiased chest X-ray diagnosis models from the biased training data without knowing exactly the bias labels. We start with the observations that the imbalance of bias distribution is one of the key reasons causing shortcut learning, and the dataset biases are preferred by the model if they were easier to be learned than the intended features. Based on these observations, we proposed a novel algorithm, pseudo bias-balanced learning, which first captures and predicts per-sample bias labels via generalized cross entropy loss and then trains a debiased model using pseudo bias labels and bias-balanced softmax function. We constructed several chest X-ray datasets with various dataset bias situations and demonstrated with extensive experiments that our proposed method achieved consistent improvements over other state-of-the-art approaches (Code available at https://github.com/LLYXC/PBBL.).

Original languageEnglish
Title of host publicationMedical Image Computing and Computer Assisted Intervention – MICCAI 2022 - 25th International Conference Singapore, September 18–22, 2022 Proceedings, Part VIII
EditorsLinwei Wang, Qi Dou, P. Thomas Fletcher, Stefanie Speidel, Shuo Li
Place of PublicationCham Switzerland
PublisherSpringer
Pages621-631
Number of pages11
ISBN (Electronic)9783031164521
ISBN (Print)9783031164514
DOIs
Publication statusPublished - 2022
Externally publishedYes
EventMedical Image Computing and Computer-Assisted Intervention 2022 - Singapore, Singapore
Duration: 18 Sept 2022 → 22 Sept 2022
Conference number: 25th
https://link.springer.com/book/10.1007/978-3-031-16434-7 (Proceedings - Part 2)
https://conferences.miccai.org/2022/en/ (Website)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume13438
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceMedical Image Computing and Computer-Assisted Intervention 2022
Abbreviated titleMICCAI 2022
Country/TerritorySingapore
CitySingapore
Period18/09/22 → 22/09/22
Internet address

Keywords

  • Chest X-ray
  • Debias
  • Shortcut learning

Cite this