Reference-Guided Pseudo-Label Generation for Medical Semantic Segmentation

Authors

  • Constantin Marc Seibold Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Germany
  • Simon Reiß Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Germany
  • Jens Kleesiek Institute for Artificial Intelligence in Medicine, University Medicine Essen, Germany
  • Rainer Stiefelhagen Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Germany

DOI:

https://doi.org/10.1609/aaai.v36i2.20114

Keywords:

Computer Vision (CV)

Abstract

Producing densely annotated data is a difficult and tedious task for medical imaging applications. To address this problem, we propose a novel approach to generate supervision for semi-supervised semantic segmentation. We argue that visually similar regions between labeled and unlabeled images likely contain the same semantics and therefore should share their label. Following this thought, we use a small number of labeled images as reference material and match pixels in an unlabeled image to the semantic of the best fitting pixel in a reference set. This way, we avoid pitfalls such as confirmation bias, common in purely prediction-based pseudo-labeling. Since our method does not require any architectural changes or accompanying networks, one can easily insert it into existing frameworks. We achieve the same performance as a standard fully supervised model on X-ray anatomy segmentation, albeit using 95% fewer labeled images. Aside from an in-depth analysis of different aspects of our proposed method, we further demonstrate the effectiveness of our reference-guided learning paradigm by comparing our approach against existing methods for retinal fluid segmentation with competitive performance as we improve upon recent work by up to 15% mean IoU.

Downloads

Published

2022-06-28

How to Cite

Seibold, C. M., Reiß, S., Kleesiek, J., & Stiefelhagen, R. (2022). Reference-Guided Pseudo-Label Generation for Medical Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(2), 2171-2179. https://doi.org/10.1609/aaai.v36i2.20114

Issue

Section

AAAI Technical Track on Computer Vision II