Weakly Supervised Anomaly Detection for Chest X-Ray Image
This work addresses a practical challenge in medical imaging for clinicians by enabling more accurate disease detection with limited labeled data, though it is incremental as it builds on existing weakly supervised methods.
The paper tackles the problem of weakly supervised anomaly detection in chest X-ray images by proposing WSCXR, a framework that uses few-shot anomaly images with image-level labels to refine features and augment data, achieving improved detection performance on two datasets.
Chest X-Ray (CXR) examination is a common method for assessing thoracic diseases in clinical applications. While recent advances in deep learning have enhanced the significance of visual analysis for CXR anomaly detection, current methods often miss key cues in anomaly images crucial for identifying disease regions, as they predominantly rely on unsupervised training with normal images. This letter focuses on a more practical setup in which few-shot anomaly images with only image-level labels are available during training. For this purpose, we propose WSCXR, a weakly supervised anomaly detection framework for CXR. WSCXR firstly constructs sets of normal and anomaly image features respectively. It then refines the anomaly image features by eliminating normal region features through anomaly feature mining, thus fully leveraging the scarce yet crucial features of diseased areas. Additionally, WSCXR employs a linear mixing strategy to augment the anomaly features, facilitating the training of anomaly detector with few-shot anomaly images. Experiments on two CXR datasets demonstrate the effectiveness of our approach.