Out-of-distribution data supervision towards biomedical semantic segmentation

TL;DR

This paper introduces Med-OoD, a data-centric framework that leverages Out-of-Distribution data supervision to improve biomedical semantic segmentation, preventing misclassification and enhancing performance without additional data or complex modifications.

Contribution

Med-OoD is a novel framework that integrates OoD data supervision into biomedical segmentation without external data, feature regularization, or extra annotations, and can be seamlessly added to existing networks.

Findings

Med-OoD reduces pixel misclassification in medical image segmentation.

The method achieves significant performance improvements on the Lizard dataset.

Training solely with OoD data yields a 76.1% mIoU in segmentation tasks.

Abstract

Biomedical segmentation networks easily suffer from the unexpected misclassification between foreground and background objects when learning on limited and imperfect medical datasets. Inspired by the strong power of Out-of-Distribution (OoD) data on other visual tasks, we propose a data-centric framework, Med-OoD to address this issue by introducing OoD data supervision into fully-supervised biomedical segmentation with none of the following needs: (i) external data sources, (ii) feature regularization objectives, (iii) additional annotations. Our method can be seamlessly integrated into segmentation networks without any modification on the architectures. Extensive experiments show that Med-OoD largely prevents various segmentation networks from the pixel misclassification on medical images and achieves considerable performance improvements on Lizard dataset. We also present an emerging learning paradigm of training a medical segmentation network completely using OoD data devoid of foreground class labels, surprisingly turning out 76.1% mIoU as test result. We hope this learning paradigm will attract people to rethink the roles of OoD data. Code is made available at https://github.com/StudioYG/Med-OoD.