Training-Free Zero-Shot Anomaly Detection in 3D Brain MRI with 2D Foundation Models
This addresses the problem of detecting anomalies in 3D medical images without supervision for medical imaging applications, though it is incremental as it adapts existing 2D methods to 3D.
The paper tackles the challenge of extending zero-shot anomaly detection to 3D brain MRI without task-specific training, by developing a training-free framework that aggregates 2D foundation model features into volumetric tokens. The result shows this approach effectively enables 3D anomaly detection using existing 2D models.
Zero-shot anomaly detection (ZSAD) has gained increasing attention in medical imaging as a way to identify abnormalities without task-specific supervision, but most advances remain limited to 2D datasets. Extending ZSAD to 3D medical images has proven challenging, with existing methods relying on slice-wise features and vision-language models, which fail to capture volumetric structure. In this paper, we introduce a fully training-free framework for ZSAD in 3D brain MRI that constructs localized volumetric tokens by aggregating multi-axis slices processed by 2D foundation models. These 3D patch tokens restore cubic spatial context and integrate directly with distance-based, batch-level anomaly detection pipelines. The framework provides compact 3D representations that are practical to compute on standard GPUs and require no fine-tuning, prompts, or supervision. Our results show that training-free, batch-based ZSAD can be effectively extended from 2D encoders to full 3D MRI volumes, offering a simple and robust approach for volumetric anomaly detection.