SAMM (Segment Any Medical Model): A 3D Slicer Integration to SAM

The Segment Anything Model (SAM) is a new image segmentation tool trained with the largest available segmentation dataset. The model has demonstrated that, with efficient prompting, it can create high-quality, generalized masks for image segmentation. However, the performance of the model on medical images requires further validation. To assist with the development, assessment, and application of SAM on medical images, we introduce Segment Any Medical Model (SAMM), an extension of SAM on 3D Slicer - an open-source image processing and visualization software extensively used by the medical imaging community. This open-source extension to 3D Slicer and its demonstrations are posted on GitHub (https://github.com/bingogome/samm). SAMM achieves 0.6-second latency of a complete cycle and can infer image masks in nearly real-time.

[1]  Benjamin Killeen,et al.  Synthetic data accelerates the development of generalizable learning-based algorithms for X-ray image analysis , 2023, Nature Machine Intelligence.

[2]  Mohammad Zalbagi Darestani,et al.  MONAI: An open-source framework for deep learning in healthcare , 2022, ArXiv.

[3]  S. Gelly,et al.  An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale , 2020, ICLR.

[4]  J. Dolz,et al.  Multi-Scale Self-Guided Attention for Medical Image Segmentation , 2019, IEEE Journal of Biomedical and Health Informatics.

[5]  Ahmad Almogren,et al.  A deep learning based medical image segmentation technique in Internet-of-Medical-Things domain , 2020, Future Gener. Comput. Syst..

[6]  Jaime Fern'andez del R'io,et al.  Array programming with NumPy , 2020, Nature.

[7]  Pieter Hintjens,et al.  ZeroMQ: Messaging for Many Applications , 2013 .

[8]  Ron Kikinis,et al.  3D Slicer , 2012, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).