MadCLIP: Few-shot Medical Anomaly Detection with CLIP

TL;DR

MadCLIP introduces a novel few-shot medical anomaly detection method that leverages pre-trained CLIP with dual-branch design, learnable prompts, and SigLIP loss, achieving superior results without synthetic data or memory banks.

Contribution

It adapts CLIP for medical anomaly detection with a dual-branch architecture, learnable prompts, and SigLIP loss, marking the first application of SigLIP in medical imaging.

Findings

Superior performance over existing methods in AC and AS

Effective cross-dataset generalization

No reliance on synthetic data or memory banks

Abstract

An innovative few-shot anomaly detection approach is presented, leveraging the pre-trained CLIP model for medical data, and adapting it for both image-level anomaly classification (AC) and pixel-level anomaly segmentation (AS). A dual-branch design is proposed to separately capture normal and abnormal features through learnable adapters in the CLIP vision encoder. To improve semantic alignment, learnable text prompts are employed to link visual features. Furthermore, SigLIP loss is applied to effectively handle the many-to-one relationship between images and unpaired text prompts, showcasing its adaptation in the medical field for the first time. Our approach is validated on multiple modalities, demonstrating superior performance over existing methods for AC and AS, in both same-dataset and cross-dataset evaluations. Unlike prior work, it does not rely on synthetic data or memory banks, and an ablation study confirms the contribution of each component. The code is available at https://github.com/mahshid1998/MadCLIP.