English

Bayesian uncertainty-weighted loss for improved generalisability on polyp segmentation task

Computer Vision and Pattern Recognition 2024-06-17 v2 Artificial Intelligence

Abstract

While several previous studies have devised methods for segmentation of polyps, most of these methods are not rigorously assessed on multi-center datasets. Variability due to appearance of polyps from one center to another, difference in endoscopic instrument grades, and acquisition quality result in methods with good performance on in-distribution test data, and poor performance on out-of-distribution or underrepresented samples. Unfair models have serious implications and pose a critical challenge to clinical applications. We adapt an implicit bias mitigation method which leverages Bayesian predictive uncertainties during training to encourage the model to focus on underrepresented sample regions. We demonstrate the potential of this approach to improve generalisability without sacrificing state-of-the-art performance on a challenging multi-center polyp segmentation dataset (PolypGen) with different centers and image modalities.

Keywords

Cite

@article{arxiv.2309.06807,
  title  = {Bayesian uncertainty-weighted loss for improved generalisability on polyp segmentation task},
  author = {Rebecca S. Stone and Pedro E. Chavarrias-Solano and Andrew J. Bulpitt and David C. Hogg and Sharib Ali},
  journal= {arXiv preprint arXiv:2309.06807},
  year   = {2024}
}

Comments

To be presented at the Fairness of AI in Medical Imaging (FAIMI) MICCAI 2023 Workshop and published in volumes of the Springer Lecture Notes Computer Science (LNCS) series

R2 v1 2026-06-28T12:20:06.980Z