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

The advent of large language models (LLM) has led to significant progress in image analysis with potential for future advancements. SAM [Kirillov et al., 2023] is a revolutionary foundation model for image segmentation and has already shown the capability of handling diverse segmentation tasks. SAM especially prevails in zero-shot domain generalization cases compared with the existing elaborate, fine-tuned models trained on specific domains. An important prospect for the application of SAM would be its adaptation to the complex task of segmenting medical images with significant inter-subject variations and a low signal-to-noise ratio. The segmentation task allows separation of different structures in medical images, which are then used to detect the region of interest or reconstruct multi-dimensional anatomical models [Sinha and Dolz, 2021]. The existing AI-based segmentation methods, however, do not fully bridge the domain gap among different imaging modalities, such as computed tomography (CT), magnetic resonance imaging (MRI), or ultrasound (US) [Wang et al., 2020]. The domain gap refers to the difference in the data format across various image modalities, as each modality offers a distinct advantage in visualizing anatomical structures and related pathologies (e.g., tumor, bone fracture). This difference introduces specific challenges for training AI systems to perform common analysis without the need for a comprehensive dataset that includes all relevant domains from various image modalities.