Weakly Supervised Anomaly Detection for Chest X-Ray Image

TL;DR

This paper introduces WSCXR, a weakly supervised framework for detecting anomalies in chest X-ray images using few-shot learning and feature refinement, improving disease region identification with limited labeled data.

Contribution

The paper presents a novel weakly supervised anomaly detection method that refines features and employs data augmentation to effectively utilize scarce anomaly labels in CXR images.

Findings

WSCXR outperforms existing methods on two CXR datasets.

The approach effectively identifies disease regions with limited anomaly labels.

Feature refinement and augmentation significantly improve detection accuracy.

Abstract

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.