A Weakly Supervised Adaptive DenseNet for Classifying Thoracic Diseases and Identifying Abnormalities
This work addresses the challenge of reducing annotation costs for medical imaging analysis, though it is incremental as it builds on existing weakly supervised methods.
The authors tackled the problem of classifying thoracic diseases and identifying abnormalities in chest radiographs using only image-level labels, achieving significant improvement over previous models on the ChestX-ray14 dataset.
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.