Towards Continual Visual Anomaly Detection in the Medical Domain

TL;DR

This paper introduces a continual learning approach for visual anomaly detection in medical imaging, demonstrating that the adapted PatchCore model effectively maintains performance over time with minimal forgetting.

Contribution

It is the first to apply continual learning to visual anomaly detection in the medical domain, adapting the PatchCore model for evolving data scenarios.

Findings

PatchCoreCL achieves performance comparable to task-specific models.

Forgetting is less than 1%, indicating effective knowledge retention.

Demonstrates feasibility of continual learning in medical anomaly detection.

Abstract

Visual Anomaly Detection (VAD) seeks to identify abnormal images and precisely localize the corresponding anomalous regions, relying solely on normal data during training. This approach has proven essential in domains such as manufacturing and, more recently, in the medical field, where accurate and explainable detection is critical. Despite its importance, the impact of evolving input data distributions over time has received limited attention, even though such changes can significantly degrade model performance. In particular, given the dynamic and evolving nature of medical imaging data, Continual Learning (CL) provides a natural and effective framework to incrementally adapt models while preserving previously acquired knowledge. This study explores for the first time the application of VAD models in a CL scenario for the medical field. In this work, we utilize a CL version of the well-established PatchCore model, called PatchCoreCL, and evaluate its performance using BMAD, a real-world medical imaging dataset with both image-level and pixel-level annotations. Our results demonstrate that PatchCoreCL is an effective solution, achieving performance comparable to the task-specific models, with a forgetting value less than a 1%, highlighting the feasibility and potential of CL for adaptive VAD in medical imaging.