A Weakly Supervised Adaptive DenseNet for Classifying Thoracic Diseases and Identifying Abnormalities

TL;DR

This paper introduces a weakly supervised deep learning model using an adaptive DenseNet architecture for accurate classification and localization of thoracic diseases in chest X-rays, trained solely on image-level labels.

Contribution

The proposed model effectively combines a customized pooling structure with an adaptive DenseNet, enabling disease classification and abnormality localization without region-level annotations.

Findings

Significant improvement over previous models on ChestX-ray14 dataset

Achieved accurate disease classification and localization

Supports potential clinical decision-making

Abstract

We present a weakly supervised deep learning model for classifying thoracic diseases and identifying abnormalities in chest radiography. In this work, instead of learning from medical imaging data with region-level annotations, our model was merely trained on imaging data with image-level labels to classify diseases, and is able to identify abnormal image regions simultaneously. Our model consists of a customized pooling structure and an adaptive DenseNet front-end, which can effectively recognize possible disease features for classification and localization tasks. Our method has been validated on the publicly available ChestX-ray14 dataset. Experimental results have demonstrated that our classification and localization prediction performance achieved significant improvement over the previous models on the ChestX-ray14 dataset. In summary, our network can produce accurate disease classification and localization, which can potentially support clinical decisions.