Spatial-aware Attention Generative Adversarial Network for Semi-supervised Anomaly Detection in Medical Image

TL;DR

This paper introduces SAGAN, a novel semi-supervised GAN that uses spatial-aware attention and position encoding to improve anomaly detection in medical images by focusing on abnormal regions.

Contribution

The paper proposes a new spatial-aware attention GAN that effectively utilizes unlabeled data and relaxes cyclic consistency for improved medical anomaly detection.

Findings

SAGAN outperforms state-of-the-art methods on three datasets.

Utilizes position encoding and attention for precise abnormal region focus.

Generates high-quality images guiding anomaly detection.

Abstract

Medical anomaly detection is a critical research area aimed at recognizing abnormal images to aid in diagnosis.Most existing methods adopt synthetic anomalies and image restoration on normal samples to detect anomaly. The unlabeled data consisting of both normal and abnormal data is not well explored. We introduce a novel Spatial-aware Attention Generative Adversarial Network (SAGAN) for one-class semi-supervised generation of health images.Our core insight is the utilization of position encoding and attention to accurately focus on restoring abnormal regions and preserving normal regions. To fully utilize the unlabelled data, SAGAN relaxes the cyclic consistency requirement of the existing unpaired image-to-image conversion methods, and generates high-quality health images corresponding to unlabeled data, guided by the reconstruction of normal images and restoration of pseudo-anomaly images.Subsequently, the discrepancy between the generated healthy image and the original image is utilized as an anomaly score.Extensive experiments on three medical datasets demonstrate that the proposed SAGAN outperforms the state-of-the-art methods.