Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection Through Automatic Diffusion Models

Abstract

The introduction of diffusion models in anomaly detection has paved the way for more effective and accurate pseudo-healthy synthesis. However , the current limitations in controlling noise granularity hinder the ability of diffusion models to generalize across diverse anomaly types and compromise the restoration of healthy tissues. To overcome these challenges, we propose AutoDDPM, a novel approach that enhances the robustness of diffusion models. AutoDDPM utilizes diffusion models to generate initial likelihood maps of potential anomalies and seamlessly integrates healthy tissues in the de-noising process. By re-sampling from the joint noised distribution, AutoDDPM achieves harmonization and in-painting effects. Our study demonstrates the efficacy of AutoDDPM in replacing anomalous regions while preserving healthy tissues, considerably surpassing diffusion models’ limitations. It also contributes valuable insights and analysis on the limitations of current diffusion models, promoting robust and interpretable anomaly detection in medical imaging — an essential aspect of building autonomous clinical decision systems with higher interpretability. Code: https://github.com/ci-ber/autoDDPM