{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:52:16Z","timestamp":1786981936197,"version":"build-2736575974"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004721","name":"The University of Tokyo","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004721","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Jpn J Radiol"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This study aimed to compare three publicly available deep learning models (TotalSegmentator, TotalVibeSegmentator, and PanSegNet) for automated pancreatic segmentation on magnetic resonance images and to evaluate their performance against human annotations in terms of segmentation accuracy, volumetric measurement, and intrapancreatic fat fraction (IPFF) assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>Twenty upper abdominal T1-weighted magnetic resonance series acquired using the two-point Dixon method were randomly selected. Three radiologists manually segmented the pancreas, and a ground-truth mask was constructed through a majority vote per voxel. Pancreatic segmentation was also performed using the three artificial intelligence models. Performance was evaluated using the Dice similarity coefficient (DSC), 95th-percentile Hausdorff distance, average symmetric surface distance, positive predictive value, sensitivity, Bland\u2013Altman plots, and concordance correlation coefficient (CCC) for pancreatic volume and IPFF.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      PanSegNet achieved the highest DSC (mean\u2009\u00b1\u2009standard deviation, 0.883\u2009\u00b1\u20090.095) and showed no statistically significant difference from the human interobserver DSC (0.896\u2009\u00b1\u20090.068;\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.24). In contrast, TotalVibeSegmentator (0.731\u2009\u00b1\u20090.105) and TotalSegmentator (0.707\u2009\u00b1\u20090.142) had significantly lower DSC values compared with the human interobserver average (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001). For pancreatic volume and IPFF, PanSegNet demonstrated the best agreement with the ground truth (CCC values of 0.958 and 0.993, respectively), followed by TotalSegmentator (0.834 and 0.980) and TotalVibeSegmentator (0.720 and 0.672).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>PanSegNet demonstrated the highest segmentation accuracy and the best agreement with human measurements for both pancreatic volume and IPFF on T1-weighted Dixon images. This model appears to be the most suitable for large-scale studies requiring automated pancreatic segmentation and intrapancreatic fat evaluation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11604-025-01814-5","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:49:20Z","timestamp":1750218560000},"page":"1663-1669","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Comparison of publicly available artificial intelligence models for pancreatic segmentation on T1-weighted Dixon images"],"prefix":"10.1007","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8622-2433","authenticated-orcid":false,"given":"Yuki","family":"Sonoda","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shota","family":"Fujisawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mariko","family":"Kurokawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wataru","family":"Gonoi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shouhei","family":"Hanaoka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takeharu","family":"Yoshikawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osamu","family":"Abe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"1814_CR1","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.14309\/ajg.0000000000002792","volume":"119","author":"X Dong","year":"2024","unstructured":"Dong X, Zhu Q, Yuan C, Wang Y, Ma X, Shi X, et al. Associations of intrapancreatic fat deposition with incident diseases of the exocrine and endocrine pancreas: a UK biobank prospective cohort study. Am J Gastroenterol. 2024;119:1158\u201366.","journal-title":"Am J Gastroenterol"},{"key":"1814_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2023.101391","volume":"5","author":"H Yamazaki","year":"2024","unstructured":"Yamazaki H, Streicher SA, Wu L, Fukuhara S, Wagner R, Heni M, et al. Evidence for a causal link between intra-pancreatic fat deposition and pancreatic cancer: a prospective cohort and Mendelian randomization study. Cell Rep Med. 2024;5: 101391.","journal-title":"Cell Rep Med"},{"key":"1814_CR3","doi-asserted-by":"publisher","first-page":"2991","DOI":"10.3390\/biomedicines10112991","volume":"10","author":"JZ Yang","year":"2022","unstructured":"Yang JZ, Zhao J, Nemati R, Yin X, He KH, Plank L, et al. An adapted deep convolutional neural network for automatic measurement of pancreatic fat and pancreatic volume in clinical multi-protocol magnetic resonance images: a retrospective study with multi-ethnic external validation. Biomedicines. 2022;10:2991.","journal-title":"Biomedicines"},{"key":"1814_CR4","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1002\/jmri.28275","volume":"57","author":"D Lin","year":"2023","unstructured":"Lin D, Wang Z, Li H, Zhang H, Deng L, Ren H, et al. Automated measurement of pancreatic fat deposition on dixon MRI using nnU-net. Magn Reson Imaging. 2023;57:296\u2013307.","journal-title":"Magn Reson Imaging"},{"key":"1814_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.107989","volume":"170","author":"G Zhang","year":"2024","unstructured":"Zhang G, Zhan Q, Gao Q, Mao K, Yang P, Gao Y, et al. Automated pancreatic segmentation and fat fraction evaluation based on a self-supervised transfer learning network. Comput Biol Med. 2024;170: 107989.","journal-title":"Comput Biol Med"},{"key":"1814_CR6","doi-asserted-by":"publisher","first-page":"4222","DOI":"10.3390\/cancers13164222","volume":"13","author":"Y Kobashi","year":"2021","unstructured":"Kobashi Y, Uchiyama M, Matsui J. The, \u201cK-Sign\u201d\u2014a novel CT finding suggestive before the appearance of pancreatic cancer. Cancers. 2021;13:4222.","journal-title":"Cancers"},{"key":"1814_CR7","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1016\/S2468-1253(23)00064-X","volume":"8","author":"MS Petrov","year":"2023","unstructured":"Petrov MS. Fatty change of the pancreas: the Pandora\u2019s box of pancreatology. Lancet Gastroenterol Hepatol. 2023;8:671\u201382.","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"1814_CR8","doi-asserted-by":"publisher","first-page":"e241613","DOI":"10.1148\/radiol.241613","volume":"314","author":"TA D\u2019Antonoli","year":"2025","unstructured":"D\u2019Antonoli TA, Berger LK, Indrakanti AK, Vishwanathan N, Wei\u00df J, Jung M, et al. TotalSegmentator MRI: Robust sequence-independent segmentation of multiple anatomic structures in MRI. Radiology. 2025;314:e241613.","journal-title":"Radiology"},{"key":"1814_CR9","unstructured":"Graf R, Platzek P-S, Riedel EO, Ramsch\u00fctz C, Starck S, M\u00f6ller HK, et al. TotalVibeSegmentator: full body MRI segmentation for the NAKO and UK Biobank [Internet]. arXiv; 2024 [cited 2025 Jan 28]. http:\/\/arxiv.org\/abs\/2406.00125."},{"key":"1814_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103382","volume":"99","author":"Z Zhang","year":"2025","unstructured":"Zhang Z, Keles E, Durak G, Taktak Y, Susladkar O, Gorade V, et al. Large-scale multi-center CT and MRI segmentation of pancreas with deep learning. Med Image Anal. 2025;99: 103382.","journal-title":"Med Image Anal"},{"key":"1814_CR11","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1148\/radiology.153.1.6089263","volume":"153","author":"WT Dixon","year":"1984","unstructured":"Dixon WT. Simple proton spectroscopic imaging. Radiology. 1984;153:189\u201394.","journal-title":"Radiology"},{"key":"1814_CR12","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","volume":"26","author":"LR Dice","year":"1945","unstructured":"Dice LR. Measures of the amount of ecologic association between species. Ecology. 1945;26:297\u2013302.","journal-title":"Ecology"},{"key":"1814_CR13","doi-asserted-by":"publisher","first-page":"255","DOI":"10.2307\/2532051","volume":"45","author":"LI Lin","year":"1989","unstructured":"Lin LI. A concordance correlation coefficient to evaluate reproducibility. Biometrics. 1989;45:255\u201368.","journal-title":"Biometrics"},{"key":"1814_CR14","unstructured":"McBride GB. A proposal for strength-of-agreement criteria for Lin\u2019s concordance correlation coefficient. _NIWA client report. 2005;45:307\u201310."},{"key":"1814_CR15","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1002\/jmri.21492","volume":"28","author":"J Ma","year":"2008","unstructured":"Ma J. Dixon techniques for water and fat imaging. Magn Reson Imaging. 2008;28:543\u201358.","journal-title":"Magn Reson Imaging"},{"key":"1814_CR16","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1038\/ajg.2014.1","volume":"109","author":"VW-S Wong","year":"2014","unstructured":"Wong VW-S, Wong GL-H, Yeung DK-W, Abrigo JM, Kong AP-S, Chan RS-M, et al. Fatty pancreas, insulin resistance, and \u03b2-cell function: a population study using fat-water magnetic resonance imaging. Am J Gastroenterol. 2014;109:589\u201397.","journal-title":"Am J Gastroenterol"},{"key":"1814_CR17","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230246","volume":"5","author":"M Huisman","year":"2023","unstructured":"Huisman M, Hannink G. The AI generalization gap: one size does not fit all. Radiol Artif Intell. 2023;5: e230246.","journal-title":"Radiol Artif Intell"}],"container-title":["Japanese Journal of Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11604-025-01814-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11604-025-01814-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11604-025-01814-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T11:53:14Z","timestamp":1759146794000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11604-025-01814-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,18]]},"references-count":17,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["1814"],"URL":"https:\/\/doi.org\/10.1007\/s11604-025-01814-5","relation":{},"ISSN":["1867-1071","1867-108X"],"issn-type":[{"value":"1867-1071","type":"print"},{"value":"1867-108X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,18]]},"assertion":[{"value":"11 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Y.S., S.F., M.K., W.G., S.H., T.Y., O.A.: no relevant relationships. The Department of Computational Radiology and Preventive Medicine is sponsored by HIMEDIC Inc. and Siemens Japan KK.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The study protocol was approved by the ethics committee of the University of Tokyo Hospital (Approval No. 2561). This retrospective study was conducted in accordance with the principles of the Declaration of Helsinki.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"The need for informed consent was waived because of the retrospective nature of the study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}