Brief

Researchers have developed CS3F, a novel framework for training-free zero-shot anomaly detection in 3D medical images. This approach utilizes existing 2D foundation models by decomposing 3D volumes into slices and encoding them with a 2D vision transformer. Anomaly scores are then derived from the similarity of these encoded features across different subjects, identifying tokens that deviate significantly from the norm. The method has been evaluated on brain MRI scans for conditions like metastases, glioma, and stroke, and further validated on lung CT scans to assess its generalizability. AI

Researchers have introduced AnyMC3D, a novel framework for 3D medical image classification that adapts 2D foundation models. This approach addresses common pitfalls like data-regime bias and suboptimal adaptation by using lightweight plugins on a single frozen backbone, allowing for efficient scaling to new tasks with minimal parameters. The framework supports multi-view inputs, auxiliary supervision, and heatmap generation, and has demonstrated state-of-the-art performance across a benchmark of 12 diverse tasks, including a first-place finish in the VLM3D challenge. AI