ADFA: Attention-augmented Differentiable top-k Feature Adaptation for Unsupervised Medical Anomaly Detection

TL;DR

This paper introduces ADFA, an unsupervised medical anomaly detection method that leverages attention-augmented feature descriptors and differentiable top-k adaptation to improve detection accuracy on challenging datasets.

Contribution

The paper presents a novel unsupervised approach combining attention mechanisms and differentiable top-k feature adaptation for medical image anomaly detection.

Findings

ADFA outperforms state-of-the-art methods on multiple datasets.

The method effectively detects anomalies with limited annotated data.

Attention-augmented features improve detection accuracy.

Abstract

The scarcity of annotated data, particularly for rare diseases, limits the variability of training data and the range of detectable lesions, presenting a significant challenge for supervised anomaly detection in medical imaging. To solve this problem, we propose a novel unsupervised method for medical image anomaly detection: Attention-Augmented Differentiable top-k Feature Adaptation (ADFA). The method utilizes Wide-ResNet50-2 (WR50) network pre-trained on ImageNet to extract initial feature representations. To reduce the channel dimensionality while preserving relevant channel information, we employ an attention-augmented patch descriptor on the extracted features. We then apply differentiable top-k feature adaptation to train the patch descriptor, mapping the extracted feature representations to a new vector space, enabling effective detection of anomalies. Experiments show that ADFA outperforms state-of-the-art (SOTA) methods on multiple challenging medical image datasets, confirming its effectiveness in medical anomaly detection.