Multi-Scale Feature and Prompt Learning for Few-Shot Medical Image Anomaly Detection

Few-shot anomaly detection in medical imaging remains challenging due to the scarcity of labeled abnormal samples and the need for robust feature representations. We propose AnomaMed, a novel multi-scale feature and prompt learning framework that extends Contrastive Language-Image Pretraining (CLIP) for medical anomaly detection. We introduce Prompt Feature Fusion Modules, which integrate multi-scale image and prompt feature fusion at different layers of a pretrained CLIP model, enabling hierarchical feature refinement for improved anomaly localization. Additionally, we incorporate self-attention-based prompt learning, dynamically refining textual representations to enhance text-image alignment in few-shot settings. To further improve generalization, we introduce the Artificial Anomaly Blending Module (AABM), which synthetically generates diverse medical anomalies, enabling the model to learn a broader range of pathological patterns. We evaluate AnomaMed on three benchmark medical imaging datasets, demonstrating state-of-the-art performance over existing vision-language models for few-shot anomaly detection. Results confirm that AnomaMed significantly improves anomaly detection and localization, validating the effectiveness of multi-scale feature fusion, self-attentive prompt learning, and synthetic anomaly augmentation.