{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T21:59:34Z","timestamp":1774648774034,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,7,8]],"date-time":"2023-07-08T00:00:00Z","timestamp":1688774400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,8]],"date-time":"2023-07-08T00:00:00Z","timestamp":1688774400000},"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><jats:sec>\n                <jats:title>Purpose<\/jats:title>\n                <jats:p>Segmentation of liver vessels from CT images is indispensable prior to surgical planning and aroused a broad range of interest in the medical image analysis community. Due to the complex structure and low-contrast background, automatic liver vessel segmentation remains particularly challenging. Most of the related researches adopt FCN, U-net, and V-net variants as a backbone. However, these methods mainly focus on capturing multi-scale local features which may produce misclassified voxels due to the convolutional operator\u2019s limited locality reception field.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>We propose a robust end-to-end vessel segmentation network called Inductive BIased Multi-Head Attention Vessel Net(IBIMHAV-Net) by expanding swin transformer to 3D and employing an effective combination of convolution and self-attention. In practice, we introduce voxel-wise embedding rather than patch-wise embedding to locate precise liver vessel voxels and adopt multi-scale convolutional operators to gain local spatial information. <\/jats:p>\n                <jats:p>On the other hand, we propose the inductive biased multi-head self-attention which learns inductively biased relative positional embedding from initialized absolute position embedding. Based on this, we can gain more reliable queries and key matrices.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>We conducted experiments on the 3DIRCADb dataset. The average dice and sensitivity of the four tested cases were 74.8<jats:inline-formula><jats:alternatives><jats:tex-math>$$\\%$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                    <mml:mo>%<\/mml:mo>\n                  <\/mml:math><\/jats:alternatives><\/jats:inline-formula> and 77.5<jats:inline-formula><jats:alternatives><jats:tex-math>$$\\%$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                    <mml:mo>%<\/mml:mo>\n                  <\/mml:math><\/jats:alternatives><\/jats:inline-formula>, which exceed the results of existing deep learning methods and improved graph cuts method. The Branches Detected(BD)\/Tree-length Detected(TD) indexes also proved the global\/local feature capture ability better than other methods.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>The proposed model IBIMHAV-Net provides an automatic, accurate 3D liver vessel segmentation with an interleaved architecture that better utilizes both global and local spatial features in CT volumes. It can be further extended for other clinical data.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12880-023-01045-y","type":"journal-article","created":{"date-parts":[[2023,7,8]],"date-time":"2023-07-08T08:01:42Z","timestamp":1688803302000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention"],"prefix":"10.1186","volume":"23","author":[{"given":"Mian","family":"Wu","sequence":"first","affiliation":[]},{"given":"Yinling","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Xiangyun","family":"Liao","sequence":"additional","affiliation":[]},{"given":"Qiong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,8]]},"reference":[{"key":"1045_CR1","unstructured":"Cao H, Wang Y, Chen J, Jiang D, Zhang X, Tian Q, et\u00a0al. Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation. arXiv preprint arXiv:2105.05537. 2021."},{"issue":"10","key":"1045_CR2","doi-asserted-by":"publisher","first-page":"2172","DOI":"10.1109\/TMI.2015.2425535","volume":"34","author":"S Cetin","year":"2015","unstructured":"Cetin S, Unal G. A higher-order tensor vessel tractography for segmentation of vascular structures. IEEE Trans Med Imaging. 2015;34(10):2172\u201385.","journal-title":"IEEE Trans Med Imaging."},{"issue":"2","key":"1045_CR3","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1109\/TMI.2012.2227118","volume":"32","author":"S Cetin","year":"2012","unstructured":"Cetin S, Demir A, Yezzi A, Degertekin M, Unal G. Vessel tractography using an intensity based tensor model with branch detection. IEEE Trans Med Imaging. 2012;32(2):348\u201363.","journal-title":"IEEE Trans Med Imaging."},{"key":"1045_CR4","unstructured":"Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, et\u00a0al. Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306. 2021."},{"issue":"8","key":"1045_CR5","first-page":"2144","volume":"58","author":"Y Chi","year":"2010","unstructured":"Chi Y, Liu J, Venkatesh SK, Huang S, Zhou J, Tian Q, et al. Segmentation of liver vasculature from contrast enhanced CT images using context-based voting. IEEE Trans Biomed Eng. 2010;58(8):2144\u201353.","journal-title":"IEEE Trans Biomed Eng."},{"key":"1045_CR6","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek \u00d6, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: International conference on medical image computing and computer-assisted intervention. Springer; 2016. p. 424\u2013432.","DOI":"10.1007\/978-3-319-46723-8_49"},{"issue":"6","key":"1045_CR7","doi-asserted-by":"publisher","first-page":"2027","DOI":"10.3390\/s21062027","volume":"21","author":"M Ciecholewski","year":"2021","unstructured":"Ciecholewski M, Kassja\u0144ski M. Computational Methods for Liver Vessel Segmentation in Medical Imaging: A Review. Sensors. 2021;21(6):2027.","journal-title":"Sensors."},{"key":"1045_CR8","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et\u00a0al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929. 2020."},{"issue":"2","key":"1045_CR9","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.media.2009.12.003","volume":"14","author":"O Friman","year":"2010","unstructured":"Friman O, Hindennach M, K\u00fchnel C, Peitgen HO. Multiple hypothesis template tracking of small 3D vessel structures. Med Image Anal. 2010;14(2):160\u201371.","journal-title":"Med Image Anal."},{"key":"1045_CR10","doi-asserted-by":"crossref","unstructured":"Fu H, Xu Y, Lin S, Wong DWK, Liu J. Deepvessel: Retinal vessel segmentation via deep learning and conditional random field. In: International conference on medical image computing and computer-assisted intervention. Springer; 2016. p. 132\u2013139.","DOI":"10.1007\/978-3-319-46723-8_16"},{"key":"1045_CR11","doi-asserted-by":"crossref","unstructured":"Hatamizadeh A, Yang D, Roth H, Xu D. Unetr: Transformers for 3d medical image segmentation. arXiv preprint arXiv:2103.10504. 2021.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"1045_CR12","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.compbiomed.2018.08.018","volume":"101","author":"Q Huang","year":"2018","unstructured":"Huang Q, Sun J, Ding H, Wang X, Wang G. Robust liver vessel extraction using 3D U-Net with variant dice loss function. Comput Biol Med. 2018;101:153\u201362.","journal-title":"Comput Biol Med."},{"key":"1045_CR13","doi-asserted-by":"crossref","unstructured":"Isensee F, Petersen J, Klein A, Zimmerer D, Jaeger PF, Kohl S, et\u00a0al. nnU-net: Self-adapting framework for u-net-based medical image segmentation. arXiv preprint arXiv:1809.10486. 2018.","DOI":"10.1007\/978-3-658-25326-4_7"},{"key":"1045_CR14","doi-asserted-by":"crossref","unstructured":"Karimi D, Vasylechko S, Gholipour A. Convolution-Free Medical Image Segmentation using Transformers. arXiv preprint arXiv:2102.13645. 2021.","DOI":"10.1007\/978-3-030-87193-2_8"},{"key":"1045_CR15","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.compmedimag.2019.05.002","volume":"75","author":"T Kitrungrotsakul","year":"2019","unstructured":"Kitrungrotsakul T, Han XH, Iwamoto Y, Lin L, Foruzan AH, Xiong W, et al. VesselNet: A deep convolutional neural network with multi pathways for robust hepatic vessel segmentation. Comput Med Imaging Graph. 2019;75:74\u201383.","journal-title":"Comput Med Imaging Graph."},{"key":"1045_CR16","doi-asserted-by":"crossref","unstructured":"Lamy J, Merveille O, Kerautret B, Passat N, Vacavant A. Vesselness filters: A survey with benchmarks applied to liver imaging. In: 2020 25th International Conference on Pattern Recognition (ICPR). IEEE; 2021. p. 3528\u20133535.","DOI":"10.1109\/ICPR48806.2021.9412362"},{"key":"1045_CR17","doi-asserted-by":"crossref","unstructured":"Lee TC, Kashyap RL, Chu CN. Building skeleton models via 3-D medial surface axis thinning algorithms. CVGIP: Graph Model Image Process. 1994;56(6):462\u2013478.","DOI":"10.1006\/cgip.1994.1042"},{"issue":"1","key":"1045_CR18","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/TMI.2015.2457891","volume":"35","author":"Q Li","year":"2015","unstructured":"Li Q, Feng B, Xie L, Liang P, Zhang H, Wang T. A cross-modality learning approach for vessel segmentation in retinal images. IEEE Trans Med Imaging. 2015;35(1):109\u201318.","journal-title":"IEEE Trans Med Imaging."},{"key":"1045_CR19","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et\u00a0al. Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030. 2021.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1045_CR20","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. p. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"10","key":"1045_CR21","doi-asserted-by":"publisher","first-page":"3905","DOI":"10.1088\/0031-9155\/60\/10\/3905","volume":"60","author":"HM Luu","year":"2015","unstructured":"Luu HM, Klink C, Moelker A, Niessen W, Van Walsum T. Quantitative evaluation of noise reduction and vesselness filters for liver vessel segmentation on abdominal CTA images. Phys Med Biol. 2015;60(10):3905.","journal-title":"Phys Med Biol."},{"key":"1045_CR22","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi SA. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV).\u00a02016. p. 565\u2013571. Ieee.","DOI":"10.1109\/3DV.2016.79"},{"key":"1045_CR23","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.cmpb.2018.02.001","volume":"158","author":"S Moccia","year":"2018","unstructured":"Moccia S, De Momi E, El Hadji S, Mattos LS. Blood vessel segmentation algorithms\u2014review of methods, datasets and evaluation metrics. Comput Methods Prog Biomed. 2018;158:71\u201391.","journal-title":"Comput Methods Prog Biomed."},{"key":"1045_CR24","doi-asserted-by":"crossref","unstructured":"Pamulapati V, Wood BJ, Linguraru MG, Intra-hepatic vessel segmentation and classification in multi-phase CT using optimized graph cuts. In: 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. IEEE; 2011. p. 1982\u20135.","DOI":"10.1109\/ISBI.2011.5872799"},{"issue":"6","key":"1045_CR25","doi-asserted-by":"publisher","first-page":"1603","DOI":"10.1109\/TMI.2021.3062280","volume":"40","author":"Y Qin","year":"2021","unstructured":"Qin Y, Zheng H, Gu Y, Huang X, Yang J, Wang L, et al. Learning tubule-sensitive CNNs for pulmonary airway and artery-vein segmentation in CT. IEEE Trans Med Imaging. 2021;40(6):1603\u201317.","journal-title":"IEEE Trans Med Imaging."},{"key":"1045_CR26","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. Springer; 2015. p. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1045_CR27","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.compbiomed.2017.12.019","volume":"93","author":"N Sangsefidi","year":"2018","unstructured":"Sangsefidi N, Foruzan AH, Dolati A. Balancing the data term of graph-cuts algorithm to improve segmentation of hepatic vascular structures. Comput Biol Med. 2018;93:117\u201326.","journal-title":"Comput Biol Med."},{"issue":"1","key":"1045_CR28","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s11548-009-0380-4","volume":"5","author":"A Sboarina","year":"2010","unstructured":"Sboarina A, Foroni RI, Minicozzi A, Antiga L, Lupidi F, Longhi M, et al. Software for hepatic vessel classification: feasibility study for virtual surgery. Int J CARS. 2010;5(1):39\u201348.","journal-title":"Int J CARS."},{"issue":"2","key":"1045_CR29","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/s11548-011-0624-y","volume":"7","author":"C Schumann","year":"2012","unstructured":"Schumann C, Bieberstein J, Braunewell S, Niethammer M, Peitgen HO. Visualization support for the planning of hepatic needle placement. Int J CARS. 2012;7(2):191\u20137.","journal-title":"Int J CARS."},{"key":"1045_CR30","doi-asserted-by":"crossref","unstructured":"Touvron H, Cord M, Sablayrolles A, Synnaeve G, J\u00e9gou H. Going deeper with image transformers. arXiv preprint arXiv:2103.17239. 2021.","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"1045_CR31","doi-asserted-by":"crossref","unstructured":"Xu M, Wang Y, Chi Y, Hua X, Training liver vessel segmentation deep neural networks on noisy labels from contrast CT imaging. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). IEEE; 2020. p. 1552\u20135.","DOI":"10.1109\/ISBI45749.2020.9098509"},{"key":"1045_CR32","doi-asserted-by":"crossref","unstructured":"Yan Q, Wang B, Zhang W, Luo C, Xu W, Xu Z, et\u00a0al. An attention-guided deep neural network with multi-scale feature fusion for liver vessel segmentation. IEEE J Biomed Health Inf. 2020.","DOI":"10.1109\/JBHI.2020.3042069"},{"key":"1045_CR33","doi-asserted-by":"crossref","unstructured":"Yu W, Fang B, Liu Y, Gao M, Zheng S, Wang Y. Liver vessels segmentation based on 3d residual U-NET. In: 2019 IEEE International Conference on Image Processing (ICIP). IEEE; 2019. p. 250\u2013254.","DOI":"10.1109\/ICIP.2019.8802951"},{"key":"1045_CR34","doi-asserted-by":"crossref","unstructured":"Zhang Y, Liu H, Hu Q. Transfuse: Fusing transformers and cnns for medical image segmentation. arXiv preprint arXiv:2102.08005. 2021.","DOI":"10.1007\/978-3-030-87193-2_2"}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-023-01045-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-023-01045-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-023-01045-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,8]],"date-time":"2023-07-08T08:04:15Z","timestamp":1688803455000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedimaging.biomedcentral.com\/articles\/10.1186\/s12880-023-01045-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,8]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["1045"],"URL":"https:\/\/doi.org\/10.1186\/s12880-023-01045-y","relation":{},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,8]]},"assertion":[{"value":"27 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2023","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 study is based on IRCADb France committee on ethics approval and consent for the dataset. The 3D-IRCADb-01 is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.","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":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"91"}}