{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:59:55Z","timestamp":1782176395755,"version":"3.54.5"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T00:00:00Z","timestamp":1746576000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T00:00:00Z","timestamp":1746576000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Background<\/jats:title>\n            <jats:p>Cardiovascular diseases are the number one cause of death globally, making cardiac magnetic resonance image segmentation a popular research topic. Existing schemas relying on manual user interaction or semi-automatic segmentation are infeasible when dealing thousands of cardiac MRI studies. Thus, we proposed a full automatic and robust algorithm for large-scale cardiac MRI segmentation by combining the advantages of deep learning localization and 3D-ASM restriction.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Material and methods<\/jats:title>\n            <jats:p>The proposed method comprises several key techniques: 1) a hybrid network integrating CNNs and Transformer as a encoder with the EFG (Edge feature guidance) module (named as CTr-HNs) to localize the target regions of the cardiac on MRI images, 2) initial shape acquisition by alignment of coarse segmentation contours to the initial surface model of 3D-ASM, 3) refinement of the initial shape to cover all slices of MRI in the short axis by complex transformation. The datasets used are from the UK BioBank and the CAP (Cardiac Atlas Project). In cardiac coarse segmentation experiments on MR images, Dice coefficients (Dice), mean contour distances (MCD), and mean Hausdorff distances (HD95) are used to evaluate segmentation performance. In SPASM experiments, Point-to-surface (P2S) distances, Dice score are compared between automatic results and ground truth.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>The CTr-HNs from our proposed method achieves Dice coefficients (Dice), mean contour distances (MCD), and mean Hausdorff distances (HD95) of 0.95, 0.10 and 1.54 for the LV segmentation respectively, 0.88, 0.13 and 1.94 for the LV myocardium segmentation, and 0.91, 0.24 and 3.25 for the RV segmentation. The overall P2S errors from our proposed schema is 1.45\u00a0mm. For endocardium and epicardium, the Dice scores are 0.87 and 0.91 respectively.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions<\/jats:title>\n            <jats:p>Our experimental results show that the proposed schema can automatically analyze large-scale quantification from population cardiac images with robustness and accuracy.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1186\/s12880-025-01683-4","type":"journal-article","created":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T10:45:35Z","timestamp":1746614735000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Hybrid method for automatic initialization and segmentation of ventricular on large-scale cardiovascular magnetic resonance images"],"prefix":"10.1186","volume":"25","author":[{"given":"Ning","family":"Pan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cailu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junfeng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaifei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,7]]},"reference":[{"issue":"8","key":"1683_CR1","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1093\/eurheartj\/ehab892","volume":"43","author":"A Timmis","year":"2022","unstructured":"Timmis A, Vardas P, Townsend N, Torbica A, Katus H, De Smedt D, Gale CP, Maggioni AP, Petersen SE, Huculeci R. European society of cardiology: cardiovascular disease statistics 2021. Eur Heart J. 2022;43(8):716\u201399.","journal-title":"Eur Heart J"},{"issue":"6","key":"1683_CR2","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1016\/j.acra.2012.02.011","volume":"19","author":"H Liu","year":"2012","unstructured":"Liu H, Hu H, Xu X, Song E. Automatic left ventricle segmentation in cardiac MRI using topological stable-state thresholding and region restricted dynamic programming. Acad Radiol. 2012;19(6):723\u201331.","journal-title":"Acad Radiol"},{"key":"1683_CR3","first-page":"2","volume":"49","author":"Y Lu","year":"2009","unstructured":"Lu Y, Radau P, Connelly K, Dick A, Wright G. Automatic image-driven segmentation of left ventricle in cardiac cine MRI. The MIDAS J. 2009;49:2.","journal-title":"The MIDAS Journal"},{"key":"1683_CR4","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.neucom.2019.02.008","volume":"347","author":"H Hu","year":"2019","unstructured":"Hu H, Pan N, Wang J, Yin T, Ye R. Automatic segmentation of left ventricle from cardiac MRI via deep learning and region constrained dynamic programming. Neurocomputing. 2019;347:139\u201348.","journal-title":"Neurocomputing"},{"issue":"4","key":"1683_CR5","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1016\/j.mri.2012.10.004","volume":"31","author":"H Hu","year":"2013","unstructured":"Hu H, Liu H, Gao Z, Huang L. Hybrid segmentation of left ventricle in cardiac MRI using gaussian-mixture model and region restricted dynamic programming. Magn Reson Imaging. 2013;31(4):575\u201384.","journal-title":"Magn Reson Imaging"},{"key":"1683_CR6","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.neucom.2019.10.102","volume":"396","author":"H Hu","year":"2020","unstructured":"Hu H, Pan N, Yin T, Liu H, Du B. Hybrid method for automatic construction of 3D-ASM image intensity models for left ventricle. Neurocomputing. 2020;396:65\u201375.","journal-title":"Neurocomputing"},{"key":"1683_CR7","doi-asserted-by":"publisher","first-page":"116303","DOI":"10.1016\/j.image.2021.116303","volume":"96","author":"H Huaifei","year":"2021","unstructured":"Huaifei H, Pan N, Haihua L, Liman L, Tailang Y, Zhigang T, Frangi AF. Automatic segmentation of left and right ventricles in cardiac MRI using 3D-ASM and deep learning. Signal Process Image Commun. 2021;96:116303.","journal-title":"Signal Process Image Commun"},{"key":"1683_CR8","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.mri.2021.10.005","volume":"86","author":"X Shi","year":"2022","unstructured":"Shi X, Li C. Anatomical knowledge based level set segmentation of cardiac ventricles from MRI. Magn Reson Imaging. 2022;86:135\u201348.","journal-title":"Magn Reson Imaging"},{"key":"1683_CR9","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.mri.2018.04.011","volume":"51","author":"M-B Khamechian","year":"2018","unstructured":"Khamechian M-B, Saadatmand-Tarzjan M. FoCA: a new framework of coupled geometric active contours for segmentation of 3D cardiac magnetic resonance images. Magn Reson Imaging. 2018;51:51\u201360.","journal-title":"Magn Reson Imaging"},{"key":"1683_CR10","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.neucom.2016.08.125","volume":"259","author":"Y Zhang","year":"2017","unstructured":"Zhang Y, Wei H. Atlas construction of cardiac fiber architecture using a multimodal registration approach. Neurocomputing. 2017;259:219\u201325.","journal-title":"Neurocomputing"},{"key":"1683_CR11","doi-asserted-by":"crossref","unstructured":"Ankenbrand MJ, Shainberg L, Hock M, Lohr D, Schreiber LM. Sensitivity analysis for interpretation of machine learning based segmentation models in cardiac MRI. BMC Med. Imaging. 2021;21(1).","DOI":"10.1186\/s12880-021-00551-1"},{"key":"1683_CR12","doi-asserted-by":"crossref","unstructured":"Diller GP, Vahle J, Radke R, Vidal MLB, Fischer AJ, Bauer UMM, Sarikouch S, Berger F, Beerbaum P, Baumgartner H, et al. Utility of deep learning networks for the generation of artificial cardiac magnetic resonance images in congenital heart disease. BMC Med. Imaging. 2020;20(1).","DOI":"10.1186\/s12880-020-00511-1"},{"key":"1683_CR13","doi-asserted-by":"crossref","unstructured":"Wu J, Gan Z, Guo W, Yang X, Lin A. A fully convolutional network feature descriptor: application to left ventricle motion estimation based on graph matching in short-axis MRI. Neurocomputing. 2019.","DOI":"10.1016\/j.neucom.2018.10.101"},{"issue":"9","key":"1683_CR14","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1109\/TMI.2002.804442","volume":"21","author":"AF Frangl","year":"2002","unstructured":"Frangl AF, Rueckert D, Duncan JS. Three-dimensional cardiovascular image analysis. IEEE Trans Med Imaging. 2002;21(9):1005\u201310.","journal-title":"IEEE Trans Med Imaging"},{"issue":"2","key":"1683_CR15","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/j.media.2010.12.004","volume":"15","author":"C Petitjean","year":"2011","unstructured":"Petitjean C, Dacher JN. A review of segmentation methods in short axis cardiac MR images. Med Image Anal. 2011;15(2):169\u201384.","journal-title":"Med Image Anal"},{"issue":"2","key":"1683_CR16","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s10334-015-0521-4","volume":"29","author":"P Peng","year":"2016","unstructured":"Peng P, Lekadir K, Gooya A, Shao L, Petersen SE, Frangi AF. A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging. Magn Reson Mater Phys Biol Med. 2016;29(2):155\u201395.","journal-title":"Magn Reson Mater Phys Biol Med"},{"key":"1683_CR17","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.mri.2021.10.029","volume":"85","author":"H El-Rewaidy","year":"2022","unstructured":"El-Rewaidy H, Fahmy AS, Khalifa AM, Ibrahim E-SH. Multiple two-dimensional active shape model framework for right ventricular segmentation. Magn Reson Imaging. 2022;85:177\u201385.","journal-title":"Magn Reson Imaging"},{"issue":"11","key":"1683_CR18","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1109\/TMI.2008.2004819","volume":"27","author":"TG Catalina","year":"2008","unstructured":"Catalina TG, Constantine B, Santiago A, Federico S, Gloria M, Frangi AF. Automatic construction of 3D-ASM intensity models by simulating image acquisition: application to myocardial gated SPECT studies. IEEE Trans Med Imaging. 2008;27(11):1655\u201367.","journal-title":"IEEE Trans Med Imaging"},{"key":"1683_CR19","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.media.2017.10.001","volume":"43","author":"X Alba","year":"2018","unstructured":"Alba X, Lekadir K, Pereanez M, Medranogracia P, Young AA, Frangi AF. Automatic initialization and quality control of large-scale cardiac MRI segmentations. Med Image Anal. 2018;43:129\u201341.","journal-title":"Med Image Anal"},{"issue":"3","key":"1683_CR20","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.1109\/TETCI.2024.3377676","volume":"8","author":"MY Ansari","year":"2024","unstructured":"Ansari MY, Mangalote IAC, Meher PK, Aboumarzouk O, Al-Ansari A, Halabi O, Dakua SP. Advancements in deep learning for b-mode ultrasound segmentation: a comprehensive review. IEEE Trans Emerging Top Comput Intell. 2024;8(3):2126\u201349.","journal-title":"IEEE Trans Emerging Top Comput Intell"},{"key":"1683_CR21","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.mri.2021.01.005","volume":"78","author":"J Kar","year":"2021","unstructured":"Kar J, Cohen MV, McQuiston SP, Malozzi CM. A deep-learning semantic segmentation approach to fully automated MRI-based left-ventricular deformation analysis in cardiotoxicity. Magn Reson Imaging. 2021;78:127\u201339.","journal-title":"Magn Reson Imaging"},{"key":"1683_CR22","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.mri.2019.08.021","volume":"66","author":"Z Wang","year":"2020","unstructured":"Wang Z, Xie L, Qi J. Dynamic pixel-wise weighting-based fully convolutional neural networks for left ventricle segmentation in short-axis MRI. Magn Reson Imaging. 2020;66:131\u201340.","journal-title":"Magn Reson Imaging"},{"key":"1683_CR23","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.mri.2019.08.004","volume":"66","author":"A Lin","year":"2020","unstructured":"Lin A, Wu J, Yang X. A data augmentation approach to train fully convolutional networks for left ventricle segmentation. Magn Reson Imaging. 2020;66:152\u201364.","journal-title":"Magn Reson Imaging"},{"issue":"28","key":"1683_CR24","first-page":"139","volume":"347","author":"H Huaifei","year":"2019","unstructured":"Huaifei H, Pan N, Wang J, Yin T, Ye R. Automatic segmentation of left ventricle from cardiac MRI via deep learning and region constrained dynamic programming. Neurocomputing. 2019;347(28):139\u201348.","journal-title":"Neurocomputing"},{"key":"1683_CR25","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.media.2016.01.005","volume":"30","author":"MR Avendi","year":"2016","unstructured":"Avendi MR, Kheradvar A, Jafarkhani H. A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI\u2606. Med Image Anal. 2016;30:108\u201319.","journal-title":"Med Image Anal"},{"issue":"1","key":"1683_CR26","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/s13721-023-00412-7","volume":"12","author":"Y Regaya","year":"2023","unstructured":"Regaya Y, Amira A, Dakua SP. Development of a cerebral aneurysm segmentation method to prevent sentinel hemorrhage. Network Model Anal Health Inf Bioinf. 2023;12(1):18.","journal-title":"Network Model Anal Health Inf Bioinf"},{"issue":"2","key":"1683_CR27","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1016\/j.media.2005.12.001","volume":"10","author":"VHH Assen","year":"2006","unstructured":"Assen VHH, Danilouchkine MM, Frangi AA, Ord\u00e1s SS, Westenberg JJ, Reiber JJ, Lelieveldt BB. SPASM: a 3D-ASM for segmentation of sparse and arbitrarily oriented cardiac MRI data. Med Image Anal. 2006;10(2):286\u2013303.","journal-title":"Med Image Anal"},{"issue":"3","key":"1683_CR28","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1109\/TPAMI.2010.94","volume":"33","author":"H Radu","year":"2011","unstructured":"Radu H, Florence F, Manuel Y, Guillaume D, Jian Z. Rigid and articulated point registration with expectation conditional maximization. IEEE Trans Pattern Anal Mach Intell. 2011;33(3):587\u2013602.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1683_CR29","unstructured":"Jieneng Chen YL, Qihang Y, Luo X, Adeli E, Wang Y, Lu L, Yuille AL, Zhou Y. TransUNet: transformers make strong encoders for medical image segmentation. arXiv 2021, 2102.04306."},{"key":"1683_CR30","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/978-3-031-31778-1_9","volume-title":"Left Atrial and Scar Quantification and Segmentation: 2023\/\/","author":"S Zhou","year":"2023","unstructured":"Zhou S, Wang K-N, Zhou G-Q. Edge-enhanced feature guided joint segmentation of left atrial and scars in LGE MRI images: left atrial and scar quantification and segmentation: 2023\/\/. Cham: Springer Nature Switzerland; 2023. p. 93\u2013105"},{"issue":"12","key":"1683_CR31","doi-asserted-by":"publisher","first-page":"2262","DOI":"10.1109\/TPAMI.2010.46","volume":"32","author":"A Myronenko","year":"2010","unstructured":"Myronenko A, Song X. Point set registration: coherent point drift. IEEE Trans Pattern Anal Mach Intell. 2010;32(12):2262\u201375.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1683_CR32","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.cviu.2017.02.005","volume":"157","author":"Y Chen","year":"2017","unstructured":"Chen Y, Chan AB, Lin Z, Suzuki K, Wang G. Efficient tree-structured SfM by RANSAC generalized Procrustes analysis. Comput Vision Image Understanding. 2017;157:179\u201389.","journal-title":"Comput Vision Image Understanding"},{"key":"1683_CR33","doi-asserted-by":"publisher","first-page":"107679","DOI":"10.1016\/j.cmpb.2023.107679","volume":"240","author":"H Hu","year":"2023","unstructured":"Hu H, Pan N, Frangi AF. Fully automatic initialization and segmentation of left and right ventricles for large-scale cardiac MRI using a deeply supervised network and 3D-ASM. Comput Methods Programs Biomed. 2023;240:107679.","journal-title":"Comput Methods Programs Biomed"},{"issue":"16","key":"1683_CR34","doi-asserted-by":"publisher","first-page":"2288","DOI":"10.1093\/bioinformatics\/btr360","volume":"27","author":"CG Fonseca","year":"2011","unstructured":"Fonseca CG, Backhaus M, Bluemke DA, Britten RD, Chung JD, Cowan BR, Dinov ID, Finn JP, Hunter PJ, Kadish AH. The cardiac atlas project\u2014an imaging database for computational modeling and statistical atlases of the heart. Bioinformatics. 2011;27(16):2288\u201395.","journal-title":"Bioinformatics"},{"issue":"10","key":"1683_CR35","doi-asserted-by":"publisher","first-page":"e110243","DOI":"10.1371\/journal.pone.0110243","volume":"9","author":"X Zhang","year":"2014","unstructured":"Zhang X, Cowan BR, Bluemke DA, Finn JP, Fonseca CG, Kadish AH, Lee DC, Lima JA, Suinesiaputra A, Young AA. Atlas-based quantification of cardiac remodeling due to myocardial infarction. PloS One. 2014;9(10):e110243.","journal-title":"PloS One"},{"key":"1683_CR36","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s12968-018-0471-x","volume":"20","author":"W Bai","year":"2018","unstructured":"Bai W, Sinclair M, Tarroni G, Oktay O, Rajchl M, Vaillant G, Lee AM, Aung N, Lukaschuk E, Sanghvi MM, et al. Automated cardiovascular magnetic resonance image analysis with fully convolutional networks. J Cardiovasc Magn Reson 2018;20:65.","journal-title":"J Cardiovasc Magn Reson"},{"issue":"1","key":"1683_CR37","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/S0002-9149(02)02381-0","volume":"90","author":"F Grothues","year":"2002","unstructured":"Grothues F, Smith GC, Moon JCC, Bellenger NG, Collins P, Klein HU, Pennell DJ. Comparison of interstudy reproducibility of cardiovascular magnetic resonance with two-dimensional echocardiography in normal subjects and in patients with heart failure or left ventricular hypertrophy. Am J Cardiol. 2002;90(1):29\u201334.","journal-title":"Am J Cardiol"}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-025-01683-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-025-01683-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-025-01683-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T10:45:41Z","timestamp":1746614741000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedimaging.biomedcentral.com\/articles\/10.1186\/s12880-025-01683-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,7]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1683"],"URL":"https:\/\/doi.org\/10.1186\/s12880-025-01683-4","relation":{},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,7]]},"assertion":[{"value":"3 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 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":"This research has been conducted using the UK Biobank Resource under Applications 11350 and the Cardiac Atlas Project (CAP), which can be web-accessible ().","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Clinical trial number"}},{"value":"The authors declare no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"155"}}