Multi-label Thoracic Disease Image Classification with Cross-Attention Networks
This work addresses the problem of automated disease classification in radiology for clinical support, but it is incremental as it builds on existing attention-based methods.
The paper tackles automated multi-label thoracic disease classification from chest x-ray images, proposing Cross-Attention Networks and a new loss function to address class imbalance and easy-dominated samples, achieving state-of-the-art results.
Automated disease classification of radiology images has been emerging as a promising technique to support clinical diagnosis and treatment planning. Unlike generic image classification tasks, a real-world radiology image classification task is significantly more challenging as it is far more expensive to collect the training data where the labeled data is in nature multi-label; and more seriously samples from easy classes often dominate; training data is highly class-imbalanced problem exists in practice as well. To overcome these challenges, in this paper, we propose a novel scheme of Cross-Attention Networks (CAN) for automated thoracic disease classification from chest x-ray images, which can effectively excavate more meaningful representation from data to boost the performance through cross-attention by only image-level annotations. We also design a new loss function that beyond cross-entropy loss to help cross-attention process and is able to overcome the imbalance between classes and easy-dominated samples within each class. The proposed method achieves state-of-the-art results.