MIM-OOD: Generative Masked Image Modelling for Out-of-Distribution Detection in Medical Images
This addresses faster and more accurate anomaly detection in medical imaging, though it is incremental as it builds on existing token-based methods.
The paper tackled the problem of slow inference and error accumulation in unsupervised out-of-distribution detection for medical images by replacing auto-regressive models with task-specific transformers, resulting in a DICE score improvement from 0.301 to 0.458 and a 25x speedup.
Unsupervised Out-of-Distribution (OOD) detection consists in identifying anomalous regions in images leveraging only models trained on images of healthy anatomy. An established approach is to tokenize images and model the distribution of tokens with Auto-Regressive (AR) models. AR models are used to 1) identify anomalous tokens and 2) in-paint anomalous representations with in-distribution tokens. However, AR models are slow at inference time and prone to error accumulation issues which negatively affect OOD detection performance. Our novel method, MIM-OOD, overcomes both speed and error accumulation issues by replacing the AR model with two task-specific networks: 1) a transformer optimized to identify anomalous tokens and 2) a transformer optimized to in-paint anomalous tokens using masked image modelling (MIM). Our experiments with brain MRI anomalies show that MIM-OOD substantially outperforms AR models (DICE 0.458 vs 0.301) while achieving a nearly 25x speedup (9.5s vs 244s).