Contralaterally Enhanced Networks for Thoracic Disease Detection

TL;DR

This paper introduces a contralateral context enhancement module for chest X-ray disease detection, leveraging bilateral symmetry to improve feature representation and detection accuracy in both fully and weakly supervised frameworks.

Contribution

The paper proposes a novel deep module that exploits contralateral chest information to enhance disease detection, achieving state-of-the-art results on multiple datasets.

Findings

Achieves 33.17 AP50 on a private dataset with 31,000 images.

Outperforms existing methods in weakly-supervised disease localization.

Effectively integrates into various detection frameworks.

Abstract

Identifying and locating diseases in chest X-rays are very challenging, due to the low visual contrast between normal and abnormal regions, and distortions caused by other overlapping tissues. An interesting phenomenon is that there exist many similar structures in the left and right parts of the chest, such as ribs, lung fields and bronchial tubes. This kind of similarities can be used to identify diseases in chest X-rays, according to the experience of broad-certificated radiologists. Aimed at improving the performance of existing detection methods, we propose a deep end-to-end module to exploit the contralateral context information for enhancing feature representations of disease proposals. First of all, under the guidance of the spine line, the spatial transformer network is employed to extract local contralateral patches, which can provide valuable context information for disease proposals. Then, we build up a specific module, based on both additive and subtractive operations, to fuse the features of the disease proposal and the contralateral patch. Our method can be integrated into both fully and weakly supervised disease detection frameworks. It achieves 33.17 AP50 on a carefully annotated private chest X-ray dataset which contains 31,000 images. Experiments on the NIH chest X-ray dataset indicate that our method achieves state-of-the-art performance in weakly-supervised disease localization.