{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T01:30:42Z","timestamp":1772155842649,"version":"3.50.1"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T00:00:00Z","timestamp":1653004800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T00:00:00Z","timestamp":1653004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100016964","name":"Werner Siemens-Stiftung","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100016964","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>\n                           <jats:bold>Purpose:<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>Automated distinct bone segmentation has many applications in planning and navigation tasks. 3D U-Nets have previously been used to segment distinct bones in the upper body, but their performance is not yet optimal. Their most substantial source of error lies not in confusing one bone for another, but in confusing background with bone-tissue.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>\n                           <jats:bold>Methods:<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>In this work, we propose binary-prediction-enhanced multi-class (BEM) inference, which takes into account an additional binary background\/bone-tissue prediction, to improve the multi-class distinct bone segmentation. We evaluate the method using different ways of obtaining the binary prediction, contrasting a two-stage approach to four networks with two segmentation heads. We perform our experiments on two datasets: An in-house dataset comprising 16 upper-body CT scans with voxelwise labelling into 126 distinct classes, and a public dataset containing 50 synthetic CT scans, with 41 different classes.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>\n                           <jats:bold>Results:<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>The most successful network with two segmentation heads achieves a class-median Dice coefficient of 0.85 on cross-validation with the upper-body CT dataset. These results outperform both our previously published 3D U-Net baseline with standard inference, and previously reported results from other groups. On the synthetic dataset, we also obtain improved results when using BEM-inference.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>\n                           <jats:bold>Conclusion:<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>Using a binary bone-tissue\/background prediction as guidance during inference improves distinct bone segmentation from upper-body CT scans and from the synthetic dataset. The results are robust to multiple ways of obtaining the bone-tissue segmentation and hold for the two-stage approach as well as for networks with two segmentation heads.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s11548-022-02650-y","type":"journal-article","created":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T21:05:48Z","timestamp":1653080748000},"page":"2113-2120","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Improved distinct bone segmentation from upper-body CT using binary-prediction-enhanced multi-class inference."],"prefix":"10.1007","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0226-9519","authenticated-orcid":false,"given":"Eva","family":"Schnider","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antal","family":"Huck","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mireille","family":"Toranelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Rauter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Magdalena","family":"M\u00fcller-Gerbl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philippe C.","family":"Cattin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,20]]},"reference":[{"issue":"17","key":"2650_CR1","doi-asserted-by":"publisher","first-page":"175020","DOI":"10.1088\/1361-6560\/ab2c95","volume":"64","author":"B Qiu","year":"2019","unstructured":"Qiu B, Guo J, Kraeima J, Glas HH, Borra RJ, Witjes MJ, van Ooijen PM (2019) Automatic segmentation of the mandible from computed tomography scans for 3d virtual surgical planning using the convolutional neural network. Phys Med Biol 64(17):175020","journal-title":"Phys Med Biol"},{"issue":"7","key":"2650_CR2","doi-asserted-by":"publisher","first-page":"2812","DOI":"10.1088\/1361-6560\/aa6055","volume":"62","author":"Y Fu","year":"2017","unstructured":"Fu Y, Liu S, Li HH, Yang D (2017) Automatic and hierarchical segmentation of the human skeleton in CT images. Phys Med Biol 62(7):2812\u20132833","journal-title":"Phys Med Biol"},{"key":"2650_CR3","first-page":"1","volume-title":"International workshop on computational methods and clinical applications in musculoskeletal imaging","author":"N Kamiya","year":"2018","unstructured":"Kamiya N, Kume M, Zheng G, Zhou X, Kato H, Chen H, Muramatsu C, Hara T, Miyoshi T, Matsuo M, Fujita H (2018) Automated recognition of erector spinae muscles and their skeletal attachment region via deep learning in torso ct images. International workshop on computational methods and clinical applications in musculoskeletal imaging. Springer, Cham, pp 1\u201310"},{"key":"2650_CR4","doi-asserted-by":"crossref","unstructured":"\u017belechowski M, Karnam M, Faludi B, Gerig N, Rauter G, Cattin PC (2021) Patient positioning by visualising surgical robot rotational workspace in augmented reality. Comput Methods Biomech Biomed Eng Imaging Vis, 1\u20137","DOI":"10.1080\/21681163.2021.2002192"},{"key":"2650_CR5","doi-asserted-by":"publisher","first-page":"103767","DOI":"10.1016\/j.compbiomed.2020.103767","volume":"121","author":"S Noguchi","year":"2020","unstructured":"Noguchi S, Nishio M, Yakami M, Nakagomi K, Togashi K (2020) Bone segmentation on whole-body ct using convolutional neural network with novel data augmentation techniques. Comput Biol Medicine 121:103767","journal-title":"Comput Biol Medicine"},{"issue":"1","key":"2650_CR6","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s11548-018-1883-7","volume":"14","author":"A Klein","year":"2019","unstructured":"Klein A, Warszawski J, Hillenga\u00df J, Maier-Hein KH (2019) Automatic bone segmentation in whole-body ct images. Int J Comput Assist Radiol Surg 14(1):21\u201329","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"1","key":"2650_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-01296-1","volume":"11","author":"P Cheng","year":"2021","unstructured":"Cheng P, Yang Y, Yu H, He Y (2021) Automatic vertebrae localization and segmentation in ct with a two-stage dense-u-net. Sci Rep 11(1):1\u201313","journal-title":"Sci Rep"},{"key":"2650_CR8","unstructured":"Boutillon A, Borotikar B, Burdin V, Conze P-H (2020) Multi-structure bone segmentation in pediatric mr images with combined regularization from shape priors and adversarial network. arXiv preprint arXiv:2009.07092"},{"key":"2650_CR9","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention, pp 234\u2013241. Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2650_CR10","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek \u00d6, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3d u-net: learning dense volumetric segmentation from sparse annotation. In: International conference on medical image computing and computer-assisted intervention, pp 424\u2013432 . Springer","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"2650_CR11","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.ejrad.2019.01.028","volume":"113","author":"S Lindgren Belal","year":"2019","unstructured":"Lindgren Belal S, Sadik M, Kaboteh R, Enqvist O, Ul\u00e9n J, Poulsen MH, Simonsen J, H\u00f8ilund-Carlsen PF, Edenbrandt L, Tr\u00e4g\u00e5rdh E (2019) Deep learning for segmentation of 49 selected bones in CT scans: first step in automated PET\/CT-based 3D quantification of skeletal metastases. Eur J Radiol 113:89\u201395","journal-title":"Eur J Radiol"},{"key":"2650_CR12","doi-asserted-by":"crossref","unstructured":"Schnider E, Horv\u00e1th A, Rauter G, Zam A, M\u00fcller-Gerbl M, Cattin PC (2020) 3d segmentation networks for excessive numbers of classes: distinct bone segmentation in upper bodies. In: International workshop on machine learning in medical imaging, pp 40\u201349 . Springer","DOI":"10.1007\/978-3-030-59861-7_5"},{"key":"2650_CR13","doi-asserted-by":"crossref","unstructured":"Cheng B, Collins MD, Zhu Y, Liu T, Huang TS, Adam H, Chen L-C (2020) Panoptic-deeplab: a simple, strong, and fast baseline for bottom-up panoptic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12475\u201312485","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"2650_CR14","unstructured":"Schnider E, Huck A, Rauter G, Zam A, M\u00fcller-Gerbl M, Cattin PC Ensemble uncertainty as a criterion for dataset expansion in distinct bone segmentation from upper-body ct images. In: Under submission"},{"issue":"2","key":"2650_CR15","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee F, Jaeger PF, Kohl SA, Petersen J, Maier-Hein KH (2021) nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18(2):203\u2013211","journal-title":"Nat Methods"},{"key":"2650_CR16","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi S-A (2016) V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 fourth international conference on 3D vision (3DV), pp 565\u2013571. IEEE","DOI":"10.1109\/3DV.2016.79"},{"key":"2650_CR17","doi-asserted-by":"publisher","first-page":"138","DOI":"10.14326\/abe.10.138","volume":"10","author":"Y Suzuki","year":"2021","unstructured":"Suzuki Y, Hori M, Kido S, Otake Y, Ono M, Tomiyama N, Sato Y (2021) Comparative study of vessel detection methods for contrast enhanced computed tomography: effects of convolutional neural network architecture and patch size. Adv Biomed Eng 10:138\u2013149","journal-title":"Adv Biomed Eng"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-022-02650-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-022-02650-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-022-02650-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T12:35:34Z","timestamp":1664282134000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-022-02650-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,20]]},"references-count":17,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["2650"],"URL":"https:\/\/doi.org\/10.1007\/s11548-022-02650-y","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,20]]},"assertion":[{"value":"11 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"None of the authors have competing interests to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Informed consent was obtained from all individual body donours included in the study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Body donours signed informed consent regarding publications using their data.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"This research study was conducted retrospectively from CT data routinely obtained from body donours. No ethical approval is required.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}