CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray Segmentation

02/21/2021
by   Soham Gadgil, et al.
4

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 13.4 and weakly-supervised methods that use only DNN-generated saliency maps by 91.2 distillation and find that though it is outperformed by CheXseg, it exceeds the performance (mIoU) of the best fully-supervised method by 4.83 method is able to match radiologist agreement on three out of ten pathologies and reduces the overall performance gap by 71.6 weakly-supervised methods.

READ FULL TEXT
research
04/08/2019

Weakly Supervised Semantic Segmentation of Satellite Images

When one wants to train a neural network to perform semantic segmentatio...
research
07/01/2020

Weakly-Supervised Segmentation for Disease Localization in Chest X-Ray Images

Deep Convolutional Neural Networks have proven effective in solving the ...
research
11/05/2019

Weakly Supervised Fine Tuning Approach for Brain Tumor Segmentation Problem

Segmentation of tumors in brain MRI images is a challenging task, where ...
research
09/14/2018

Keypoint Based Weakly Supervised Human Parsing

Fully convolutional networks (FCN) have achieved great success in human ...
research
07/02/2020

Weakly Supervised Segmentation with Multi-scale Adversarial Attention Gates

Large, fine-grained image segmentation datasets, annotated at pixel-leve...
research
07/20/2023

Exploring Effective Priors and Efficient Models for Weakly-Supervised Change Detection

Weakly-supervised change detection (WSCD) aims to detect pixel-level cha...
research
02/27/2019

FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference

The main obstacle to weakly supervised semantic image segmentation is th...

Please sign up or login with your details

Forgot password? Click here to reset