Weakly Supervised Thoracic Disease Localization via Disease Masks

TL;DR

This paper introduces a weakly supervised disease localization method for chest X-rays that uses disease masks and spatial attention to improve accuracy without needing detailed annotations.

Contribution

It proposes a novel spatial attention approach with disease masks and an alignment module to enhance localization accuracy in weakly supervised thoracic disease detection.

Findings

Outperforms state-of-the-art localization methods on NIH-Chest dataset

Effectively handles variations in X-ray images such as size, rotation, and noise

Achieves superior disease localization accuracy

Abstract

To enable a deep learning-based system to be used in the medical domain as a computer-aided diagnosis system, it is essential to not only classify diseases but also present the locations of the diseases. However, collecting instance-level annotations for various thoracic diseases is expensive. Therefore, weakly supervised localization methods have been proposed that use only image-level annotation. While the previous methods presented the disease location as the most discriminative part for classification, this causes a deep network to localize wrong areas for indistinguishable X-ray images. To solve this issue, we propose a spatial attention method using disease masks that describe the areas where diseases mainly occur. We then apply the spatial attention to find the precise disease area by highlighting the highest probability of disease occurrence. Meanwhile, the various sizes, rotations and noise in chest X-ray images make generating the disease masks challenging. To reduce the variation among images, we employ an alignment module to transform an input X-ray image into a generalized image. Through extensive experiments on the NIH-Chest X-ray dataset with eight kinds of diseases, we show that the proposed method results in superior localization performances compared to state-of-the-art methods.