OHIF -SAM2: Accelerating Radiology Workflows with Meta Segment Anything Model 2

Abstract

The release of Segment Anything Models (SAM1 and SAM2) by Meta has significantly impacted various domains, including medical imaging. However, existing applications of SAM for medical images primarily rely on standalone tools that require local installation and configuration, limiting accessibility and ease of use. In this work, we present a web-based extension of SAM2 integrated into the Open Health Imaging Foundation (OHIF) viewer. Our tool supports all SAM2 prompt types, including points and bounding boxes, and additionally enables text-based prompting through integration with the Grounding DINO. This web-based integration eliminates installation requirements, providing a more user-friendly interface. The implementation is open-source and available at https://github.com/CCI-Bonn/OHIF-SAM2.

Ähnliche Arbeiten