DISYRE: Diffusion-Inspired SYnthetic REstoration for Unsupervised Anomaly Detection
This work addresses unsupervised anomaly detection for medical imaging, offering a novel method that improves detection accuracy in brain MRI tasks.
The paper tackles the problem of learning a score function relevant for unsupervised anomaly detection in medical images by proposing DISYRE, which replaces Gaussian noise corruption in diffusion models with synthetic anomaly corruption, achieving state-of-the-art performance on two out of three Brain MRI benchmarks.
Unsupervised Anomaly Detection (UAD) techniques aim to identify and localize anomalies without relying on annotations, only leveraging a model trained on a dataset known to be free of anomalies. Diffusion models learn to modify inputs $x$ to increase the probability of it belonging to a desired distribution, i.e., they model the score function $\nabla_x \log p(x)$. Such a score function is potentially relevant for UAD, since $\nabla_x \log p(x)$ is itself a pixel-wise anomaly score. However, diffusion models are trained to invert a corruption process based on Gaussian noise and the learned score function is unlikely to generalize to medical anomalies. This work addresses the problem of how to learn a score function relevant for UAD and proposes DISYRE: Diffusion-Inspired SYnthetic REstoration. We retain the diffusion-like pipeline but replace the Gaussian noise corruption with a gradual, synthetic anomaly corruption so the learned score function generalizes to medical, naturally occurring anomalies. We evaluate DISYRE on three common Brain MRI UAD benchmarks and substantially outperform other methods in two out of the three tasks.