{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T17:56:25Z","timestamp":1792000585881,"version":"4.4.0"},"reference-count":37,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR AI"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Medical image segmentation is crucial for diagnosis and treatment planning in radiology, but it traditionally requires extensive manual effort and specialized training data. With its novel video tracking capabilities, the Segment Anything Model 2 (SAM 2) presents a potential solution for automated 3D medical image segmentation without the need for domain-specific training. However, its effectiveness in medical applications, particularly in abdominal computed tomography (CT) imaging remains unexplored.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The aim of this study was to evaluate the zero-shot performance of SAM 2 in 3D segmentation of abdominal organs in CT scans and to investigate the effects of prompt settings on segmentation results.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this retrospective study, we used a subset of the TotalSegmentator CT dataset from eight institutions to assess SAM 2\u2019s ability to segment eight abdominal organs. Segmentation was initiated from three different z-coordinate levels (caudal, mid, and cranial levels) of each organ. Performance was measured using the dice similarity coefficient (DSC). We also analyzed the impact of \u201cnegative prompts,\u201d which explicitly exclude certain regions from the segmentation process, on accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 123 patients (mean age 60.7, SD 15.5 years; 63 men, 60 women) were evaluated. As a zero-shot approach, larger organs with clear boundaries demonstrated high segmentation performance, with mean DSCs as follows: liver, 0.821 (SD 0.192); right kidney, 0.862 (SD 0.212); left kidney, 0.870 (SD 0.154); and spleen, 0.891 (SD 0.131). Smaller organs showed lower performance: gallbladder, 0.531 (SD 0.291); pancreas, 0.361 (SD 0.197); and adrenal glands\u2014right, 0.203 (SD 0.222) and left, 0.308 (SD 0.234). The initial slice for segmentation and the use of negative prompts significantly influenced the results. By removing negative prompts from the input, the DSCs significantly decreased for six organs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>SAM 2 demonstrated promising zero-shot performance in segmenting certain abdominal organs in CT scans, particularly larger organs. Performance was significantly influenced by input negative prompts and initial slice selection, highlighting the importance of optimizing these factors.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/72109","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T16:31:18Z","timestamp":1745944278000},"page":"e72109-e72109","source":"Crossref","is-referenced-by-count":11,"title":["Using Segment Anything Model 2 for Zero-Shot 3D Segmentation of Abdominal Organs in Computed Tomography Scans to Adapt Video Tracking Capabilities for 3D Medical Imaging: Algorithm Development and Validation"],"prefix":"10.2196","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7688-3075","authenticated-orcid":false,"given":"Yosuke","family":"Yamagishi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7496-1651","authenticated-orcid":false,"given":"Shouhei","family":"Hanaoka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4222-4569","authenticated-orcid":false,"given":"Tomohiro","family":"Kikuchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9498-7501","authenticated-orcid":false,"given":"Takahiro","family":"Nakao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6962-6704","authenticated-orcid":false,"given":"Yuta","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6471-9936","authenticated-orcid":false,"given":"Yukihiro","family":"Nomura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6365-6531","authenticated-orcid":false,"given":"Soichiro","family":"Miki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1924-5468","authenticated-orcid":false,"given":"Takeharu","family":"Yoshikawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1180-2629","authenticated-orcid":false,"given":"Osamu","family":"Abe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,4,29]]},"reference":[{"issue":"5","key":"R1","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1016\/j.media.2012.02.005","article-title":"Machine learning and radiology","volume":"16","author":"Wang","journal-title":"Med Image Anal"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2019.02.038","article-title":"The present and future of deep learning in radiology","volume":"114","author":"Saba","journal-title":"Eur J Radiol"},{"key":"R3","doi-asserted-by":"crossref","unstructured":"Kirillov A Mintun E Ravi N et al. Segment anything. arXiv. Preprint posted online onApr5, 2023. [doi: 10.1109\/ICCV51070.2023.00371]","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"R4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918","article-title":"Segment anything model for medical image analysis: An experimental study","volume":"89","author":"Mazurowski","journal-title":"Med Image Anal"},{"key":"R5","unstructured":"Roy S Wald T Koehler G et al. SAM.MD: Zero-shot medical image segmentation capabilities of the segment anything model. arXiv. Preprint posted online on2023. [doi: 10.48550\/arXiv.2304.05396]"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","journal-title":"Nat Commun"},{"key":"R7","unstructured":"Ravi N Gabeur V Hu YT et al. SAM 2: Segment Anything in images and videos. arXiv. Preprint posted online onOct28, 2024. URL: http:\/\/arxiv.org\/abs\/2408.00714 [Accessed 02-08-2024]"},{"key":"R8","unstructured":"Allan M Kondo S Bodenstedt S et al. 2018 robotic scene segmentation challenge. arXiv. Preprint posted online onAug3, 2020. [doi: 10.48550\/arXiv.2001.11190]"},{"key":"R9","unstructured":"Zhu J Qi Y Wu J . Medical SAM 2: Segment medical images as video via segment anything model 2. arXiv. Preprint posted online onDec4, 2024. URL: http:\/\/arxiv.org\/abs\/2408.00874 [Accessed 07-08-2024]"},{"issue":"4","key":"R10","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1007\/s00261-003-0139-2","article-title":"Normal organ volume assessment from abdominal CT","volume":"29","author":"Geraghty","journal-title":"Abdom Imaging"},{"issue":"6","key":"R11","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1097\/PPO.0000000000000290","article-title":"Diagnosis and detection of pancreatic cancer","volume":"23","author":"Chu","journal-title":"Cancer J"},{"issue":"10308","key":"R12","doi-asserted-by":"publisher","first-page":"1359","DOI":"10.1016\/S0140-6736(21)01374-X","article-title":"Liver cirrhosis","volume":"398","author":"Gin\u00e8s","journal-title":"Lancet"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","first-page":"17088","DOI":"10.1038\/nrdp.2017.88","article-title":"Chronic kidney disease","volume":"3","author":"Romagnani","journal-title":"Nat Rev Dis Primers"},{"issue":"2","key":"R14","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240427","article-title":"Automated CT measurement of total kidney volume for predicting renal function decline after 177Lu prostate-specific membrane antigen-I&T radioligand therapy","volume":"314","author":"Steinhelfer","journal-title":"Radiology"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.2196\/50638","article-title":"Prompt engineering as an important emerging skill for medical professionals: tutorial","volume":"25","author":"Mesk\u00f3","journal-title":"J Med Internet Res"},{"issue":"2","key":"R16","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020200029","article-title":"Checklist for artificial intelligence in medical imaging (claim): a guide for authors and reviewers","volume":"2","author":"Mongan","journal-title":"Radiol Artif Intell"},{"issue":"4","key":"R17","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.240300","article-title":"Checklist for artificial intelligence in medical imaging (CLAIM): 2024 update","volume":"6","author":"Tejani","journal-title":"Radiol Artif Intell"},{"issue":"5","key":"R18","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024","article-title":"TotalSegmentator: robust segmentation of 104 anatomic structures in ct images","volume":"5","author":"Wasserthal","journal-title":"Radiol Artif Intell"},{"key":"R19","unstructured":"Facebookresearch\/sam2. GitHub. 2025. URL: https:\/\/github.com\/facebookresearch\/sam2 [Accessed 04-02-2025]"},{"issue":"3","key":"R20","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the amount of ecologic association between species","volume":"26","author":"Dice","journal-title":"Ecology"},{"issue":"3","key":"R21","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.tjem.2018.08.001","article-title":"User\u2019s guide to correlation coefficients","volume":"18","author":"Akoglu","journal-title":"Turk J Emerg Med"},{"issue":"12","key":"R22","first-page":"614","volume":"44","author":"Chan","journal-title":"Singapore Med J"},{"key":"R23","unstructured":"Ma J Kim S Li F et al. Segment anything in medical images and videos: benchmark and deployment. arXiv. Preprint posted online onAug6, 2024. [doi: 10.48550\/arXiv.2408.03322]"},{"key":"R24","unstructured":"Dong H Gu H Chen Y Yang J Chen Y Mazurowski MA . Segment anything model 2: an application to 2D and 3D medical images. arXiv. Preprint posted online onAug22, 2024. [doi: 10.48550\/arXiv.2408.00756]"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108238","article-title":"Segment anything model for medical image segmentation: current applications and future directions","volume":"171","author":"Zhang","journal-title":"Comput Biol Med"},{"issue":"2","key":"R26","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","journal-title":"Nat Methods"},{"key":"R27","doi-asserted-by":"crossref","unstructured":"Ronneberge O Fischer P Brox T . U-net: convolutional networks for biomedical image segmentation. In: Navab N Hornegger J Wells WM Frangi AF , editors. Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015. Springer International Publishing; 2015:234-241. [doi: 10.1007\/978-3-319-24574-4_28]","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Chen X Cheng G Cai Y Wen D Li H . Semantic segmentation with modified deep residual networks. In: Tan T Li X Chen X Zhou J Yang J Cheng H , editors. Pattern Recognit DAGM. Springer; 2016:42-54. [doi: 10.1007\/978-981-10-3005-5_4]","DOI":"10.1007\/978-981-10-3005-5_4"},{"key":"R29","unstructured":"Swin. UNETR: swin transformers for semantic segmentation of brain tumors in MRI images. SpringerLink. 2022. URL: https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-08999-2_22 [Accessed 08-08-2024]"},{"key":"R30","unstructured":"Li W Yuille A Zhou Z . How well do supervised 3D models transfer to medical imaging tasks. Presented at: The Twelfth International Conference on Learning Representations; May 7-11, 2024; Vienna, Austria. URL: https:\/\/openreview.net\/forum?id=AhizIPytk4"},{"issue":"10","key":"R31","doi-asserted-by":"publisher","first-page":"6695","DOI":"10.1109\/TPAMI.2021.3100536","article-title":"AbdomenCT-1K: Is abdominal organ segmentation a solved problem?","volume":"44","author":"Ma","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103285","article-title":"AbdomenAtlas: a large-scale, detailed-annotated, & multi-center dataset for efficient transfer learning and open algorithmic benchmarking","volume":"97","author":"Li","journal-title":"Med Image Anal"},{"key":"R33","unstructured":"Qu C Zhang T Qiao H et al. AbdomenAtlas-8K: annotating 8,000 ct volumes for multi-organ segmentation in three weeks. Presented at: The 37th International Conference on Neural Information Processing Systems; Dec 10-16, 2023; New Orleans, USA. 2023."},{"issue":"4","key":"R34","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020190138","article-title":"A vertebral segmentation dataset with fracture grading","volume":"2","author":"L\u00f6ffler","journal-title":"Radiol Artif Intell"},{"key":"R35","unstructured":"D\u2019Antonoli TA Berger LK Indrakanti AK et al. TotalSegmentator MRI: sequence-independent segmentation of 59 anatomical structures in MR images. arXiv. Preprint posted online onFeb26, 2025. [doi: 10.48550\/arXiv.2405.19492]"},{"issue":"5","key":"R36","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.220275","article-title":"Duke liver dataset: a publicly available liver MRI dataset with liver segmentation masks and series labels","volume":"5","author":"Macdonald","journal-title":"Radiol Artif Intell"},{"key":"R37","unstructured":"Dataset with segmentations of 117 important anatomical structures in 1228 CT images. Zenodo. 2023. URL: https:\/\/zenodo.org\/records\/10047292 [Accessed 04-02-2025]"}],"container-title":["JMIR AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ai.jmir.org\/2025\/1\/e72109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:02:14Z","timestamp":1782842534000},"score":1,"resource":{"primary":{"URL":"https:\/\/ai.jmir.org\/2025\/1\/e72109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,29]]},"references-count":37,"URL":"https:\/\/doi.org\/10.2196\/72109","relation":{},"ISSN":["2817-1705"],"issn-type":[{"value":"2817-1705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,29]]},"article-number":"v4i5e72109"}}