Timezone: »

 
Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Models
Cosmin Bercea · Michael Neumayr · Daniel Rueckert · Julia Schnabel

@
in 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH) »
Event URL: https://openreview.net/forum?id=kTpafpXrqa »

The introduction of diffusion models in anomaly detection has paved the way for more effective and accurate image reconstruction in pathologies. 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 them with the original image. Through joint noised distribution re-sampling, 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.

Keywords: anomaly detection; diffusion probabilistic models; robustness;

Author Information

Cosmin Bercea (Technische Universität München)
Michael Neumayr (Department of Informatics, Technische Universität München)
Daniel Rueckert (Imperial College London)
Julia Schnabel (King's College London)

More from the Same Authors