wanglab

Jun Ma 1,2 , Zongxin Yang 3 , Sumin Kim 2,4,5 , Bihui Chen 2,4,5 , Mohammed Baharoon 2,3,5 , Adibvafa Fallahpour 2,4,5 , Reza Asakereh 4,7 , Hongwei Lyu 4 , Bo Wang † 1,2,4,5,6 Equal contribution     † Corresponding author 1 AI Collaborative Centre, University Health Network, Toronto, Canada 2 Vector Institute for Artificial Intelligence, Toronto, Canada 3 Department of Biomedical Informatics, Harvard Medical School, Harvard University, Boston, USA 4 Peter Munk Cardiac Centre, University Health Network, Toronto, Canada 5 Department of Computer Science, University of Toronto, Toronto, Canada 6 Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, Canada 7 Roche Canada and Genentech - A promptable foundation model for 3D medical image and video segmentation - Trained on 455,000+ 3D image-mask pairs and 76,000+ annotated video frames - Versatile segmentation capability across diverse organs and pathologies - Extensive user studies in large-scale lesion and video datasets demonstrate that MedSAM2 substantially facilitates annotation workflows Model Overview MedSAM2 is a promptable segmentation segmentation model tailored for medical imaging applications. Built upon the foundation of the Segment Anything Model (SAM) 2.1, MedSAM2 has been specifically adapted and fine-tuned for various 3D medical images and videos. - MedSAM22411.pt: Base model trained in November 2024 - MedSAM2USHeart.pt: Fine-tuned model specialized for heart ultrasound video segmentation - MedSAM2MRILiverLesion.pt: Fine-tuned model for liver lesion segmentation in MRI scans - MedSAM2CTLesion.pt: Fine-tuned model for general lesion segmentation in CT scans - MedSAM2latest.pt (recommended): Latest version trained on the combination of public datasets and newly annotated medical imaging data Option 1: Download individual models You can download the models directly from the Hugging Face repository: Alternatively, you can manually download the models from the Hugging Face repository page. The model weights can only be used for research and education purposes.