{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Zhao Y"],"funding":["NIGMS NIH HHS"],"pagination":["124-134"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12923679"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["15008"],"pubmed_abstract":["Cryogenic Electron Tomography (CryoET) is a useful imaging technology in structural biology that is hindered by its need for manual annotations, especially in particle picking. Recent works have endeavored to remedy this issue with few-shot learning or contrastive learning techniques. However, supervised training is still inevitable for them. We instead choose to leverage the power of existing 2D foundation models and present a novel, training-free framework, CryoSAM. In addition to prompt-based single-particle instance segmentation, our approach can automatically search for similar features, facilitating full tomogram semantic segmentation with only one prompt. CryoSAM is composed of two major parts: 1) a prompt-based 3D segmentation system that uses prompts to complete single-particle in"],"journal":["Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention"],"pubmed_title":["CryoSAM: Training-free CryoET Tomogram Segmentation with Foundation Models."],"pmcid":["PMC12923679"],"funding_grant_id":["R01 GM134020","P41 GM103712"],"pubmed_authors":["Mu M","Li X","Li Z","Xu M","Wang T","Bian H","Uddin MR","Zhao Y"],"additional_accession":[]},"is_claimable":false,"name":"CryoSAM: Training-free CryoET Tomogram Segmentation with Foundation Models.","description":"Cryogenic Electron Tomography (CryoET) is a useful imaging technology in structural biology that is hindered by its need for manual annotations, especially in particle picking. Recent works have endeavored to remedy this issue with few-shot learning or contrastive learning techniques. However, supervised training is still inevitable for them. We instead choose to leverage the power of existing 2D foundation models and present a novel, training-free framework, CryoSAM. In addition to prompt-based single-particle instance segmentation, our approach can automatically search for similar features, facilitating full tomogram semantic segmentation with only one prompt. CryoSAM is composed of two major parts: 1) a prompt-based 3D segmentation system that uses prompts to complete single-particle in","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Oct","modification":"2026-07-09T12:26:54.629Z","creation":"2026-07-09T11:17:41.474Z"},"accession":"S-EPMC12923679","cross_references":{"pubmed":["41726573"],"doi":["10.1007/978-3-031-72111-3_12"]}}