MedSAM2: Segment Anything in 3D Medical Images and Videos
Jun Ma, Zongxin Yang, Sumin Kim, Bihui Chen, Mohammed Baharoon, Adibvafa Fallahpour, Reza Asakereh, Hongwei Lyu, Bo Wang
2025-04-07
Summary
This paper talks about MedSAM2, a smart AI tool that helps doctors automatically outline organs and problems in 3D medical scans and videos, like highlighting tumors in a CT scan with just one click.
What's the problem?
Current AI tools for medical scans mostly work on flat images and need lots of manual work for 3D scans, making it slow and expensive for hospitals to analyze complex cases.
What's the solution?
MedSAM2 learns from a huge collection of 3D medical data and lets doctors mark one example area, then automatically finds similar areas in all other scans and videos, reducing manual work by 85%.
Why it matters?
This helps doctors diagnose diseases faster and more accurately, making medical care better and cheaper while handling complex 3D scans like CTs and MRIs easily.
Abstract
Medical image and video segmentation is a critical task for precision medicine, which has witnessed considerable progress in developing task or modality-specific and generalist models for 2D images. However, there have been limited studies on building general-purpose models for 3D images and videos with comprehensive user studies. Here, we present MedSAM2, a promptable segmentation foundation model for 3D image and video segmentation. The model is developed by fine-tuning the Segment Anything Model 2 on a large medical dataset with over 455,000 3D image-mask pairs and 76,000 frames, outperforming previous models across a wide range of organs, lesions, and imaging modalities. Furthermore, we implement a human-in-the-loop pipeline to facilitate the creation of large-scale datasets resulting in, to the best of our knowledge, the most extensive user study to date, involving the annotation of 5,000 CT lesions, 3,984 liver MRI lesions, and 251,550 echocardiogram video frames, demonstrating that MedSAM2 can reduce manual costs by more than 85%. MedSAM2 is also integrated into widely used platforms with user-friendly interfaces for local and cloud deployment, making it a practical tool for supporting efficient, scalable, and high-quality segmentation in both research and healthcare environments.