Medical image segmentation models are typically supervised by expert annotations at the pixel-level, which can be expensive to acquire. In this work, we propose a method that combines the high quality of pixel-level expert annotations with the scale of coarse DNN-generated saliency maps for training multi-label semantic segmentation models. We demonstrate the application of our semi-supervised method, which we call CheXseg, on multi-label chest X-ray interpretation. We find that CheXseg improves upon the performance (mIoU) of fully-supervised methods that use only pixel-level expert annotations by 9.7% and weakly-supervised methods that use only DNN-generated saliency maps by 73.1%. Our best method is able to match radiologist agreement on three out of ten pathologies and reduces the overall performance gap by 57.2% as compared to weakly-supervised methods.
@article{arxiv.2102.10484,
title = {CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray Segmentation},
author = {Soham Gadgil and Mark Endo and Emily Wen and Andrew Y. Ng and Pranav Rajpurkar},
journal= {arXiv preprint arXiv:2102.10484},
year = {2021}
}
Comments
Accepted to Medical Imaging with Deep Learning (MIDL) Conference 2021