L9 - CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray Segmentation
Soham Uday Gadgil, Mark Endo, Emily Wen, Andrew Y. Ng, Pranav Rajpurkar
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.
Friday 9th July
L4-9 (short): Detection and Diagnosis 2 - 16:45 - 17:30 (UTC+2)