MAEDiff: Masked Autoencoder-enhanced Diffusion Models for Unsupervised Anomaly Detection in Brain Images
This work addresses the problem of reducing costly pixel-level annotations in medical imaging for clinicians, but it is incremental as it builds on existing generative model approaches.
The paper tackled the challenge of unsupervised anomaly detection in brain images by proposing MAEDiff, a masked autoencoder-enhanced diffusion model, which improved reconstruction quality and global information utilization, achieving state-of-the-art results on datasets for tumors and multiple sclerosis lesions.
Unsupervised anomaly detection has gained significant attention in the field of medical imaging due to its capability of relieving the costly pixel-level annotation. To achieve this, modern approaches usually utilize generative models to produce healthy references of the diseased images and then identify the abnormalities by comparing the healthy references and the original diseased images. Recently, diffusion models have exhibited promising potential for unsupervised anomaly detection in medical images for their good mode coverage and high sample quality. However, the intrinsic characteristics of the medical images, e.g. the low contrast, and the intricate anatomical structure of the human body make the reconstruction challenging. Besides, the global information of medical images often remain underutilized. To address these two issues, we propose a novel Masked Autoencoder-enhanced Diffusion Model (MAEDiff) for unsupervised anomaly detection in brain images. The MAEDiff involves a hierarchical patch partition. It generates healthy images by overlapping upper-level patches and implements a mechanism based on the masked autoencoders operating on the sub-level patches to enhance the condition on the unnoised regions. Extensive experiments on data of tumors and multiple sclerosis lesions demonstrate the effectiveness of our method.