SD-MAD: Sign-Driven Few-shot Multi-Anomaly Detection in Medical Images

TL;DR

SD-MAD is a novel framework for few-shot medical image anomaly detection that leverages radiological signs and large-language models to identify multiple anomaly categories effectively.

Contribution

The paper introduces SD-MAD, a two-stage sign-driven framework that aligns radiological signs with anomalies and employs automatic sign selection, addressing multi-anomaly detection in few-shot medical imaging.

Findings

Effective multi-anomaly detection demonstrated in experiments

Outperforms existing few-shot medical AD methods

Robustness to limited data scenarios

Abstract

Medical anomaly detection (AD) is crucial for early clinical intervention, yet it faces challenges due to limited access to high-quality medical imaging data, caused by privacy concerns and data silos. Few-shot learning has emerged as a promising approach to alleviate these limitations by leveraging the large-scale prior knowledge embedded in vision-language models (VLMs). Recent advancements in few-shot medical AD have treated normal and abnormal cases as a one-class classification problem, often overlooking the distinction among multiple anomaly categories. Thus, in this paper, we propose a framework tailored for few-shot medical anomaly detection in the scenario where the identification of multiple anomaly categories is required. To capture the detailed radiological signs of medical anomaly categories, our framework incorporates diverse textual descriptions for each category generated by a Large-Language model, under the assumption that different anomalies in medical images may share common radiological signs in each category. Specifically, we introduce SD-MAD, a two-stage Sign-Driven few-shot Multi-Anomaly Detection framework: (i) Radiological signs are aligned with anomaly categories by amplifying inter-anomaly discrepancy; (ii) Aligned signs are selected further to mitigate the effect of the under-fitting and uncertain-sample issue caused by limited medical data, employing an automatic sign selection strategy at inference. Moreover, we propose three protocols to comprehensively quantify the performance of multi-anomaly detection. Extensive experiments illustrate the effectiveness of our method.