Self-Supervised Pretext Tasks in Model Robustness & Generalizability: A Revisit from Medical Imaging Perspective

Fernando Navarro, Christopher Watanabe, Suprosanna Shit, Anjany Sekuboyina, Jan C. Peeken, Stephanie E. Combs, Bjoern H. Menze

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Self-supervised pretext tasks have been introduced as an effective strategy when learning target tasks on small annotated data sets. However, while current research focuses on exploring novel pretext tasks for meaningful and reusable representation learning for the target task, the study of its robustness and generalizability has remained relatively under-explored. Specifically, it is crucial in medical imaging to proactively investigate performance under different perturbations for reliable deployment of clinical applications. In this work, we revisit medical imaging networks pre-trained with self-supervised learnings and categorically evaluate robustness and generalizability compared to vanilla supervised learning. Our experiments on pneumonia detection in X-rays and multi-organ segmentation in CT yield conclusive results exposing the hidden benefits of self-supervision pre-training for learning robust feature representations.

Original languageEnglish
Title of host publication44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5074-5079
Number of pages6
ISBN (Electronic)9781728127828
DOIs
StatePublished - 2022
Externally publishedYes
Event44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022 - Glasgow, United Kingdom
Duration: 11 Jul 202215 Jul 2022

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Volume2022-July
ISSN (Print)1557-170X

Conference

Conference44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
Country/TerritoryUnited Kingdom
CityGlasgow
Period11/07/2215/07/22

Keywords

  • generalizability
  • multi-organ segmentation
  • pneumonia classification
  • robustness
  • self-supervision

Fingerprint

Dive into the research topics of 'Self-Supervised Pretext Tasks in Model Robustness & Generalizability: A Revisit from Medical Imaging Perspective'. Together they form a unique fingerprint.

Cite this