RAPS-3D: Efficient interactive segmentation for 3D radiological imaging
This addresses the need for efficient interactive segmentation in 3D medical imaging for clinicians, though it is incremental as it builds on existing models like SegVol.
The paper tackles the problem of adapting 2D promptable segmentation models like SAM to 3D radiological imaging, which typically requires complex and slow methods such as autoregressive or sliding-window inference, by presenting a simplified 3D method that reduces inference time and eliminates prompt management complexities while achieving state-of-the-art performance.
Promptable segmentation, introduced by the Segment Anything Model (SAM), is a promising approach for medical imaging, as it enables clinicians to guide and refine model predictions interactively. However, SAM's architecture is designed for 2D images and does not extend naturally to 3D volumetric data such as CT or MRI scans. Adapting 2D models to 3D typically involves autoregressive strategies, where predictions are propagated slice by slice, resulting in increased inference complexity. Processing large 3D volumes also requires significant computational resources, often leading existing 3D methods to also adopt complex strategies like sliding-window inference to manage memory usage, at the cost of longer inference times and greater implementation complexity. In this paper, we present a simplified 3D promptable segmentation method, inspired by SegVol, designed to reduce inference time and eliminate prompt management complexities associated with sliding windows while achieving state-of-the-art performance.