{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:05:50Z","timestamp":1773119150623,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T00:00:00Z","timestamp":1676073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T00:00:00Z","timestamp":1676073600000},"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>Background<\/jats:title>\n                <jats:p>Contouring of anatomical regions is a crucial step in the medical workflow and is both time-consuming and prone to intra- and inter-observer variability. This study compares different strategies for automatic segmentation of the prostate in T2-weighted MRIs.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>This study included 100 patients diagnosed with prostate adenocarcinoma who had undergone multi-parametric MRI and prostatectomy. From the T2-weighted MR images, ground truth segmentation masks were established by consensus from two expert radiologists. The prostate was then automatically contoured with six different methods: (1) a multi-atlas algorithm, (2) a proprietary algorithm in the Syngo.Via medical imaging software, and four deep learning models: (3) a V-net trained from scratch, (4) a pre-trained 2D U-net, (5) a GAN extension of the 2D U-net, and (6) a segmentation-adapted EfficientDet architecture. The resulting segmentations were compared and scored against the ground truth masks with one 70\/30 and one 50\/50 train\/test data split. We also analyzed the association between segmentation performance and clinical variables.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>The best performing method was the adapted EfficientDet (model 6), achieving a mean Dice coefficient of 0.914, a mean absolute volume difference of 5.9%, a mean surface distance (MSD) of 1.93 pixels, and a mean 95th percentile Hausdorff distance of 3.77 pixels. The deep learning models were less prone to serious errors (0.854 minimum Dice and 4.02 maximum MSD), and no significant relationship was found between segmentation performance and clinical variables.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Deep learning-based segmentation techniques can consistently achieve Dice coefficients of 0.9 or above with as few as 50 training patients, regardless of architectural archetype. The atlas-based and Syngo.via methods found in commercial clinical software performed significantly worse (0.855<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>0.887 Dice).<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12880-023-00974-y","type":"journal-article","created":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T08:03:58Z","timestamp":1676102638000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Comparison of automated segmentation techniques for magnetic resonance images of the prostate"],"prefix":"10.1186","volume":"23","author":[{"given":"Lars Johannes","family":"Isaksson","sequence":"first","affiliation":[]},{"given":"Matteo","family":"Pepa","sequence":"additional","affiliation":[]},{"given":"Paul","family":"Summers","sequence":"additional","affiliation":[]},{"given":"Mattia","family":"Zaffaroni","sequence":"additional","affiliation":[]},{"given":"Maria Giulia","family":"Vincini","sequence":"additional","affiliation":[]},{"given":"Giulia","family":"Corrao","sequence":"additional","affiliation":[]},{"given":"Giovanni Carlo","family":"Mazzola","sequence":"additional","affiliation":[]},{"given":"Marco","family":"Rotondi","sequence":"additional","affiliation":[]},{"given":"Giuliana","family":"Lo Presti","sequence":"additional","affiliation":[]},{"given":"Sara","family":"Raimondi","sequence":"additional","affiliation":[]},{"given":"Sara","family":"Gandini","sequence":"additional","affiliation":[]},{"given":"Stefania","family":"Volpe","sequence":"additional","affiliation":[]},{"given":"Zaharudin","family":"Haron","sequence":"additional","affiliation":[]},{"given":"Sarah","family":"Alessi","sequence":"additional","affiliation":[]},{"given":"Paola","family":"Pricolo","sequence":"additional","affiliation":[]},{"given":"Francesco Alessandro","family":"Mistretta","sequence":"additional","affiliation":[]},{"given":"Stefano","family":"Luzzago","sequence":"additional","affiliation":[]},{"given":"Federica","family":"Cattani","sequence":"additional","affiliation":[]},{"given":"Gennaro","family":"Musi","sequence":"additional","affiliation":[]},{"given":"Ottavio De","family":"Cobelli","sequence":"additional","affiliation":[]},{"given":"Marta","family":"Cremonesi","sequence":"additional","affiliation":[]},{"given":"Roberto","family":"Orecchia","sequence":"additional","affiliation":[]},{"given":"Giulia","family":"Marvaso","sequence":"additional","affiliation":[]},{"given":"Giuseppe","family":"Petralia","sequence":"additional","affiliation":[]},{"given":"Barbara Alicja","family":"Jereczek-Fossa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,11]]},"reference":[{"key":"974_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2019.108716","volume":"121","author":"AS Becker","year":"2019","unstructured":"Becker AS, Chaitanya K, Schawkat K, Muehlematter UJ, H\u00f6tker AM, Konukoglu E, Donati OF. Variability of manual segmentation of the prostate in axial t2-weighted mri: a multi-reader study. Eur J Radiol. 2019;121: 108716.","journal-title":"Eur J Radiol"},{"issue":"11","key":"974_CR2","doi-asserted-by":"publisher","DOI":"10.1118\/1.4899182","volume":"41","author":"M Shahedi","year":"2014","unstructured":"Shahedi M, Cool DW, Romagnoli C, Bauman GS, Bastian-Jordan M, Gibson E, Rodrigues G, Ahmad B, Lock M, Fenster A, et al. Spatially varying accuracy and reproducibility of prostate segmentation in magnetic resonance images using manual and semiautomated methods. Med Phys. 2014;41(11): 113503.","journal-title":"Med Phys"},{"issue":"4","key":"974_CR3","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1016\/j.ijrobp.2006.11.027","volume":"67","author":"WL Smith","year":"2007","unstructured":"Smith WL, Lewis C, Bauman G, Rodrigues G, D\u2019Souza D, Ash R, Ho D, Venkatesan V, Downey D, Fenster A. Prostate volume contouring: a 3d analysis of segmentation using 3dtrus, ct, and mr. Int J Radiat Oncol Biol Phys. 2007;67(4):1238\u201347.","journal-title":"Int J Radiat Oncol Biol Phys"},{"issue":"3","key":"974_CR4","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1111\/1754-9485.12462","volume":"60","author":"SK Vinod","year":"2016","unstructured":"Vinod SK, Min M, Jameson MG, Holloway LC. A review of interventions to reduce inter-observer variability in volume delineation in radiation oncology. J Med Imaging Radiat Oncol. 2016;60(3):393\u2013406.","journal-title":"J Med Imaging Radiat Oncol"},{"key":"974_CR5","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, 2015; pp. 234\u2013241. Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"974_CR6","unstructured":"Jin J, Dundar A, Culurciello E. Flattened convolutional neural networks for feedforward acceleration 2014. arXiv preprint arXiv:1412.5474"},{"key":"974_CR7","unstructured":"Li H, Xiong P, An J, Wang L. Pyramid attention network for semantic segmentation 2018. arXiv preprint arXiv:1805.10180"},{"key":"974_CR8","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016; pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"974_CR9","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/42.836373","volume":"19","author":"LG Ny\u00fal","year":"2000","unstructured":"Ny\u00fal LG, Udupa JK, Zhang X. New variants of a method of mri scale standardization. IEEE Trans Med Imaging. 2000;19(2):143\u201350.","journal-title":"IEEE Trans Med Imaging"},{"key":"974_CR10","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.ejmp.2020.02.007","volume":"71","author":"LJ Isaksson","year":"2020","unstructured":"Isaksson LJ, Raimondi S, Botta F, Pepa M, Gugliandolo SG, De Angelis SP, Marvaso G, Petralia G, De Cobelli O, Gandini S, et al. Effects of mri image normalization techniques in prostate cancer radiomics. Physica Med. 2020;71:7\u201313.","journal-title":"Physica Med"},{"key":"974_CR11","unstructured":"Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, 2019; pp. 6105\u20136114. PMLR"},{"key":"974_CR12","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV. Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020; pp. 10781\u201310790.","DOI":"10.1109\/CVPR42600.2020.01079"},{"issue":"7193","key":"974_CR13","doi-asserted-by":"publisher","first-page":"1288","DOI":"10.1136\/bmj.318.7193.1288a","volume":"318","author":"TV Perneger","year":"1999","unstructured":"Perneger TV. Adjusting for multiple testing in studies is less important than other concerns. BMJ. 1999;318(7193):1288.","journal-title":"BMJ"},{"issue":"24","key":"974_CR14","doi-asserted-by":"publisher","first-page":"11944","DOI":"10.1073\/pnas.90.24.11944","volume":"90","author":"MI Miller","year":"1993","unstructured":"Miller MI, Christensen GE, Amit Y, Grenander U. Mathematical textbook of deformable neuroanatomies. Proc Natl Acad Sci. 1993;90(24):11944\u20138.","journal-title":"Proc Natl Acad Sci"},{"issue":"3","key":"974_CR15","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1002\/hbm.460030304","volume":"3","author":"DL Collins","year":"1995","unstructured":"Collins DL, Holmes CJ, Peters TM, Evans AC. Automatic 3-d model-based neuroanatomical segmentation. Hum Brain Mapp. 1995;3(3):190\u2013208.","journal-title":"Hum Brain Mapp"},{"issue":"10","key":"974_CR16","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1109\/42.811271","volume":"18","author":"BM Dawant","year":"1999","unstructured":"Dawant BM, Hartmann SL, Thirion J-P, Maes F, Vandermeulen D, Demaerel P. Automatic 3-d segmentation of internal structures of the head in mr images using a combination of similarity and free-form transformations. i. methodology and validation on normal subjects. IEEE Trans Med Imaging. 1999;18(10):909\u201316.","journal-title":"IEEE Trans Med Imaging"},{"key":"974_CR17","unstructured":"Healtineers S. syngo.via. https:\/\/www.siemens-healthineers.com\/medical-imaging-it\/advanced-visualization-solutions\/syngovia"},{"key":"974_CR18","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi S-A. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), 2016; pp. 565\u2013571. IEEE","DOI":"10.1109\/3DV.2016.79"},{"key":"974_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, 2015; pp. 1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"974_CR20","unstructured":"Yakubovskiy P. Segmentation Models. GitHub 2019."},{"key":"974_CR21","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017; pp. 1125\u20131134.","DOI":"10.1109\/CVPR.2017.632"},{"key":"974_CR22","unstructured":"Zhang H, Cisse M, Dauphin YN, Lopez-Paz D. mixup: beyond empirical risk minimization 2017. arXiv preprint arXiv:1710.09412"},{"issue":"1","key":"974_CR23","doi-asserted-by":"publisher","first-page":"29","DOI":"10.2478\/jaiscr-2022-0003","volume":"12","author":"LJ Isaksson","year":"2022","unstructured":"Isaksson LJ, Summers P, Raimondi S, Gandini S, Bhalerao A, Marvaso G, Petralia G, Pepa M, Jereczek-Fossa BA. Mixup (sample pairing) can improve the performance of deep segmentation networks. J Artif Intell Soft Comput Res. 2022;12(1):29\u201339.","journal-title":"J Artif Intell Soft Comput Res"},{"key":"974_CR24","unstructured":"Jolicoeur-Martineau A. The relativistic discriminator: a key element missing from standard gan 2018. arXiv preprint arXiv:1807.00734"},{"issue":"2","key":"974_CR25","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/j.media.2013.12.002","volume":"18","author":"G Litjens","year":"2014","unstructured":"Litjens G, Toth R, van de Ven W, Hoeks C, Kerkstra S, van Ginneken B, Vincent G, Guillard G, Birbeck N, Zhang J, et al. Evaluation of prostate segmentation algorithms for mri: the promise12 challenge. Med Image Anal. 2014;18(2):359\u201373.","journal-title":"Med Image Anal"},{"key":"974_CR26","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.radonc.2019.10.019","volume":"144","author":"J Wong","year":"2020","unstructured":"Wong J, Fong A, McVicar N, Smith S, Giambattista J, Wells D, Kolbeck C, Giambattista J, Gondara L, Alexander A. Comparing deep learning-based auto-segmentation of organs at risk and clinical target volumes to expert inter-observer variability in radiotherapy planning. Radiother Oncol. 2020;144:152\u20138.","journal-title":"Radiother Oncol"},{"key":"974_CR27","doi-asserted-by":"crossref","unstructured":"Khan Z, Yahya N, Alsaih K, Al-Hiyali MI, Meriaudeau F. Recent automatic segmentation algorithms of mri prostate regions: a review. IEEE Access 2021","DOI":"10.1109\/ACCESS.2021.3090825"},{"key":"974_CR28","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J. Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017; pp. 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"key":"974_CR29","doi-asserted-by":"crossref","unstructured":"Chaurasia A, Culurciello E. Linknet: Exploiting encoder representations for efficient semantic segmentation. In: 2017 IEEE Visual Communications and Image Processing (VCIP), 2017; pp. 1\u20134. IEEE","DOI":"10.1109\/VCIP.2017.8305148"},{"key":"974_CR30","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016; pp. 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"issue":"1","key":"974_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13244-022-01276-7","volume":"13","author":"LJ Isaksson","year":"2022","unstructured":"Isaksson LJ, Summers P, Bhalerao A, Gandini S, Raimondi S, Pepa M, Zaffaroni M, Corrao G, Mazzola GC, Rotondi M, et al. Quality assurance for automatically generated contours with additional deep learning. Insights Imaging. 2022;13(1):1\u201310.","journal-title":"Insights Imaging"},{"key":"974_CR32","doi-asserted-by":"crossref","unstructured":"Bokhovkin A, Burnaev E. Boundary loss for remote sensing imagery semantic segmentation. In: International Symposium on Neural Networks, 2019; pp. 388\u2013401. Springer","DOI":"10.1007\/978-3-030-22808-8_38"},{"key":"974_CR33","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P. Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, 2017; pp. 2980\u20138.","DOI":"10.1109\/ICCV.2017.324"},{"issue":"4","key":"974_CR34","doi-asserted-by":"publisher","first-page":"1707","DOI":"10.1002\/mp.13416","volume":"46","author":"B Wang","year":"2019","unstructured":"Wang B, Lei Y, Tian S, Wang T, Liu Y, Patel P, Jani AB, Mao H, Curran WJ, Liu T, et al. Deeply supervised 3d fully convolutional networks with group dilated convolution for automatic mri prostate segmentation. Med Phys. 2019;46(4):1707\u201318.","journal-title":"Med Phys"},{"key":"974_CR35","doi-asserted-by":"crossref","unstructured":"Deng Z, Hu X, Zhu L, Xu X, Qin J, Han G, Heng P-A. R3net: Recurrent residual refinement network for saliency detection. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018; pp. 684\u201390. AAAI Press","DOI":"10.24963\/ijcai.2018\/95"},{"key":"974_CR36","unstructured":"Micikevicius P, Narang S, Alben J, Diamos G, Elsen E, Garcia D, Ginsburg B, Houston M, Kuchaiev O, Venkatesh G, et al. Mixed precision training 2017. arXiv preprint arXiv:1710.03740"},{"issue":"1","key":"974_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-69920-0","volume":"10","author":"F Renard","year":"2020","unstructured":"Renard F, Guedria S, Palma ND, Vuillerme N. Variability and reproducibility in deep learning for medical image segmentation. Sci Rep. 2020;10(1):1\u201316.","journal-title":"Sci Rep"},{"key":"974_CR38","doi-asserted-by":"crossref","unstructured":"Narang S, Chung HW, Tay Y, Fedus W, Fevry T, Matena M, Malkan K, Fiedel N, Shazeer N, Lan Z, et al. Do transformer modifications transfer across implementations and applications? 2021. arXiv preprint arXiv:2102.11972","DOI":"10.18653\/v1\/2021.emnlp-main.465"},{"key":"974_CR39","unstructured":"Wightman R. Tensorflow Litterbox. GitHub 2016."}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-023-00974-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-023-00974-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-023-00974-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T13:10:24Z","timestamp":1676293824000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedimaging.biomedcentral.com\/articles\/10.1186\/s12880-023-00974-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,11]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["974"],"URL":"https:\/\/doi.org\/10.1186\/s12880-023-00974-y","relation":{},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,11]]},"assertion":[{"value":"6 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 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":"The study was performed with the approval of the Ethics Committee of IRCCS Istituto Europeo di Oncologia and Centro Cardiologico Monzino (via Ripamonti 435, 20,141 Milano, Italy), CE notification n. UID 2438. Informed consent was obtained from all subjects for use of their data for research and educational purposes. All methods were performed in accordance with the relevant guidelines and regulations under the Declaration of Helsinki (as revised in 2013).","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 that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"32"}}