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

07/01/2020
by   Ostap Viniavskyi, et al.
0

Deep Convolutional Neural Networks have proven effective in solving the task of semantic segmentation. However, their efficiency heavily relies on the pixel-level annotations that are expensive to get and often require domain expertise, especially in medical imaging. Weakly supervised semantic segmentation helps to overcome these issues and also provides explainable deep learning models. In this paper, we propose a novel approach to the semantic segmentation of medical chest X-ray images with only image-level class labels as supervision. We improve the disease localization accuracy by combining three approaches as consecutive steps. First, we generate pseudo segmentation labels of abnormal regions in the training images through a supervised classification model enhanced with a regularization procedure. The obtained activation maps are then post-processed and propagated into a second classification model-Inter-pixel Relation Network, which improves the boundaries between different object classes. Finally, the resulting pseudo-labels are used to train a proposed fully supervised segmentation model. We analyze the robustness of the presented method and test its performance on two distinct datasets: PASCAL VOC 2012 and SIIM-ACR Pneumothorax. We achieve significant results in the segmentation on both datasets using only image-level annotations. We show that this approach is applicable to chest X-rays for detecting an anomalous volume of air in the pleural space between the lung and the chest wall. Our code has been made publicly available.

READ FULL TEXT

page 7

page 8

research
06/13/2020

NoPeopleAllowed: The Three-Step Approach to Weakly Supervised Semantic Segmentation

We propose a novel approach to weakly supervised semantic segmentation, ...
research
10/22/2020

High resolution weakly supervised localization architectures for medical images

In medical imaging, Class-Activation Map (CAM) serves as the main explai...
research
02/01/2018

Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach

Analysis of histopathology slides is a critical step for many diagnoses,...
research
10/06/2021

Improving Pneumonia Localization via Cross-Attention on Medical Images and Reports

Localization and characterization of diseases like pneumonia are primary...
research
09/30/2020

Self-Guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs

The lack of fine-grained annotations hinders the deployment of automated...
research
02/21/2021

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

Medical image segmentation models are typically supervised by expert ann...
research
01/07/2023

Weakly Supervised Joint Whole-Slide Segmentation and Classification in Prostate Cancer

The segmentation and automatic identification of histological regions of...

Please sign up or login with your details

Forgot password? Click here to reset