{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:39:58Z","timestamp":1760150398977,"version":"build-2065373602"},"reference-count":56,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T00:00:00Z","timestamp":1700006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>MR-Linac is a recent device combining a linear accelerator with an MRI scanner. The improved soft tissue contrast of MR images is used for optimum delineation of tumors or organs at risk (OARs) and precise treatment delivery. Automatic segmentation of OARs can contribute to alleviating the time-consuming process for radiation oncologists and improving the accuracy of radiation delivery by providing faster, more consistent, and more accurate delineation of target structures and organs at risk. It can also help reduce inter-observer variability and improve the consistency of contouring while reducing the time required for treatment planning. In this work, state-of-the-art deep learning techniques were evaluated based on 2D and 2.5D training strategies to develop a comprehensive tool for the accurate segmentation of pelvic OARs dedicated to 0.35 T MR-Linac. In total, 103 cases with 0.35 T MR images of the pelvic region were investigated. Experts considered and contoured the bladder, rectum, and femoral heads as OARs and the prostate as the target volume. For the training of the neural network, 85 patients were randomly selected, and 18 were used for testing. Multiple U-Net-based architectures were considered, and the best model was compared using both 2D and 2.5D training strategies. The evaluation of the models was performed based on two metrics: the Dice similarity coefficient (DSC) and the Hausdorff distance (HD). In the 2D training strategy, Residual Attention U-Net (ResAttU-Net) had the highest scores among the other deep neural networks. Due to the additional contextual information, the configured 2.5D ResAttU-Net performed better. The overall DSC were 0.88 \u00b1 0.09 and 0.86 \u00b1 0.10, and the overall HD was 1.78 \u00b1 3.02 mm and 5.90 \u00b1 7.58 mm for 2.5D and 2D ResAttU-Net, respectively. The 2.5D ResAttU-Net provides accurate segmentation of OARs without affecting the computational cost. The developed end-to-end pipeline will be merged with the treatment planning system for in-time automatic segmentation.<\/jats:p>","DOI":"10.3390\/a16110521","type":"journal-article","created":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T10:57:46Z","timestamp":1700045866000},"page":"521","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Multiorgan Segmentation in Pelvic Region with Convolutional Neural Networks on 0.35 T MR-Linac Images"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2342-7934","authenticated-orcid":false,"given":"Emmanouil","family":"Koutoulakis","sequence":"first","affiliation":[{"name":"Department of Medical Physics, Centre Georges-Francois Leclerc, 21000 Dijon, France"},{"name":"Computation Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece"}]},{"given":"Louis","family":"Marage","sequence":"additional","affiliation":[{"name":"Department of Medical Physics, Centre Georges-Francois Leclerc, 21000 Dijon, France"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4395-6588","authenticated-orcid":false,"given":"Emmanouil","family":"Markodimitrakis","sequence":"additional","affiliation":[{"name":"Computation Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece"},{"name":"ICMUB Laboratory, UMR 6302 CNRS, University of Burgundy, 21000 Dijon, France"}]},{"given":"Leone","family":"Aubignac","sequence":"additional","affiliation":[{"name":"Department of Medical Physics, Centre Georges-Francois Leclerc, 21000 Dijon, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2319-9780","authenticated-orcid":false,"given":"Catherine","family":"Jenny","sequence":"additional","affiliation":[{"name":"Department of Oncologic Radiotherapy, Groupe Hospitalier Piti\u00e9-Salpetriere, Assistance Publique-Hopitaux de Paris, 75013 Paris, France"}]},{"given":"Igor","family":"Bessieres","sequence":"additional","affiliation":[{"name":"Department of Medical Physics, Centre Georges-Francois Leclerc, 21000 Dijon, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7970-366X","authenticated-orcid":false,"given":"Alain","family":"Lalande","sequence":"additional","affiliation":[{"name":"ICMUB Laboratory, UMR 6302 CNRS, University of Burgundy, 21000 Dijon, France"},{"name":"Medical Imaging Department, University Hospital of Dijon, 21000 Dijon, France"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.radonc.2006.05.012","article-title":"Guidelines for primary radiotherapy of patients with prostate cancer","volume":"79","author":"Boehmer","year":"2006","journal-title":"Radiother. Oncol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1515\/raon-2016-0023","article-title":"Uncertainties in target volume delineation in radiotherapy\u2014Are they relevant and what can we do about them?","volume":"50","author":"Segedin","year":"2016","journal-title":"Radiol. Oncol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.phro.2019.03.004","article-title":"Target definition in radiotherapy of prostate cancer using magnetic resonance imaging only workflow","volume":"9","author":"Gunnlaugsson","year":"2019","journal-title":"Phys. Imaging Radiat. Oncol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.semradonc.2014.02.013","article-title":"Magnetic Resonance\u2013Guided Adaptive Radiotherapy: A Solution to the Future","volume":"24","author":"Kupelian","year":"2014","journal-title":"Semin. Radiat. Oncol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"20160667","DOI":"10.1259\/bjr.20160667","article-title":"The future of image-guided radiotherapy will be MR guided","volume":"90","author":"Pollard","year":"2017","journal-title":"Br. J. Radiol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.phro.2020.09.009","article-title":"Clinical experience and workflow challenges with magnetic resonance-only radiation therapy simulation and planning for prostate cancer","volume":"16","author":"Tyagi","year":"2020","journal-title":"Phys. Imaging Radiat. Oncol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"826","DOI":"10.3389\/fonc.2019.00826","article-title":"A multi-center prospective study for implementation of an MRI-only prostate treatment planning work-flow","volume":"9","author":"Greer","year":"2019","journal-title":"Front. Oncol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/j.rcl.2017.10.012","article-title":"Role of Prostate MR Imaging in Radiation Oncology","volume":"56","author":"Paulson","year":"2018","journal-title":"Radiol. Clin. N. Am."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1585","DOI":"10.21037\/qims-21-697","article-title":"A narrative review of MRI acquisition for MR-guided-radiotherapy in prostate cancer","volume":"12","author":"Yuan","year":"2022","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1001\/jamaoncol.2022.6558","article-title":"Magnetic Resonance Imaging\u2013Guided vs Computed Tomography\u2013Guided Stereotactic Body Radiotherapy for Prostate Cancer","volume":"9","author":"Kishan","year":"2023","journal-title":"JAMA Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e692","DOI":"10.1016\/j.ijrobp.2023.06.2168","article-title":"Treatment Delivery Gating of MRI-Guided Stereotactic Radiotherapy for Prostate Cancer: An Exploratory Analysis of a Phase III Randomized Trial of CT-Vs. MR-Guided Radiotherapy (MIRAGE)","volume":"117","author":"Ma","year":"2023","journal-title":"Int. J. Radiat. Oncol."},{"key":"ref_12","first-page":"98","article-title":"Technical design and concept of a 0.35 T MR-Linac","volume":"18","year":"2019","journal-title":"Clin. Transl. Radiat. Oncol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.semradonc.2019.02.001","article-title":"Advances in Auto-Segmentation","volume":"29","author":"Cardenas","year":"2019","journal-title":"Semin. Radiat. Oncol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kalantar, R., Lin, G., Winfield, J.M., Messiou, C., Lalondrelle, S., Blackledge, M.D., and Koh, D.-M. (2021). Automatic Segmentation of Pelvic Cancers Using Deep Learning: State-of-the-Art Approaches and Challenges. Diagnostics, 11.","DOI":"10.20944\/preprints202108.0258.v1"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1007\/s10916-020-01641-3","article-title":"Deep Learning in Radiation Oncology Treatment Planning for Prostate Cancer: A Systematic Review","volume":"44","author":"Almeida","year":"2020","journal-title":"J. Med. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.ejmp.2021.05.003","article-title":"A review of deep learning based methods for medical image multi-organ segmentation","volume":"85","author":"Fu","year":"2021","journal-title":"Phys. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"97878","DOI":"10.1109\/ACCESS.2021.3090825","article-title":"Recent Automatic Segmentation Algorithms of MRI Prostate Regions: A Review","volume":"9","author":"Khan","year":"2021","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.radonc.2014.09.014","article-title":"Recommendations on how to establish evidence from auto-segmentation software in radiotherapy","volume":"112","author":"Valentini","year":"2014","journal-title":"Radiother. Oncol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.ejmp.2021.05.010","article-title":"Artificial Intelligence in magnetic Resonance guided Radiotherapy: Medical and physical considerations on state of art and future perspectives","volume":"85","author":"Cusumano","year":"2021","journal-title":"Phys. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e158","DOI":"10.1016\/j.cmpb.2011.07.015","article-title":"A review of atlas-based segmentation for magnetic resonance brain images","volume":"104","author":"Cabezas","year":"2011","journal-title":"Comput. Methods Progr. Biomed."},{"key":"ref_21","first-page":"535","article-title":"Multi-atlas Segmentation without Registration: A Supervoxel-Based Approach","volume":"16","author":"Wang","year":"2013","journal-title":"Med. Image Comput. Comput.-Assist. Interv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.neuroimage.2006.05.061","article-title":"Automatic anatomical brain MRI segmentation combining label propagation and decision fusion","volume":"33","author":"Heckemann","year":"2006","journal-title":"NeuroImage"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1471","DOI":"10.1088\/0031-9155\/59\/6\/1471","article-title":"Segmentation of pelvic structures for planning CT using a geometrical shape model tuned by a multi-scale edge detector","volume":"59","author":"Romero","year":"2014","journal-title":"Phys. Med. Biol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/j.media.2015.06.012","article-title":"Multi-atlas segmentation of biomedical images: A survey","volume":"24","author":"Iglesias","year":"2015","journal-title":"Med. Image Anal."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","article-title":"Fully convolutional networks for semantic segmentation","volume":"39","author":"Shelhamer","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_26","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation, Springer. Available online: https:\/\/arxiv.org\/abs\/1505.04597v1."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., and Liang, J. (2018). UNet++: A Nested U-Net Architecture for Medical Image Seg-mentation. arXiv.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2682","DOI":"10.1049\/iet-ipr.2019.1527","article-title":"DenseUNet: Densely connected UNet for electron microscopy image segmentation","volume":"14","author":"Cao","year":"2020","journal-title":"IET Image Process."},{"key":"ref_29","unstructured":"Chen, X., Yao, L., and Zhang, Y. (2020). Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19 Chest CT Images. arXiv."},{"key":"ref_30","unstructured":"Oktay, O., Schlemper, J., Le Folgoc, L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention U-Net: Learning Where to Look for the Pancreas. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ben-Cohen, A., Diamant, I., Klang, E., Amitai, M., and Greenspan, H. (2016). Fully Convolutional Network for Liver Segmentation and Lesions Detection, Springer.","DOI":"10.1007\/978-3-319-46976-8_9"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Minnema, J., Wolff, J., Koivisto, J., Lucka, F., Batenburg, K.J., Forouzanfar, T., and van Eijnatten, M. (2021). Comparison of convolutional neural network training strategies for cone-beam CT image segmentation. Comput. Methods Progr. Biomed., 207.","DOI":"10.1016\/j.cmpb.2021.106192"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Maji, D., Sigedar, P., and Singh, M. (2021). Attention Res-UNet with Guided Decoder for semantic segmentation of brain tumors. Biomed. Signal Process. Control, 71.","DOI":"10.1016\/j.bspc.2021.103077"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"14315","DOI":"10.1038\/s41598-020-71080-0","article-title":"Automatic prostate and prostate zones segmentation of magnetic resonance images using DenseNet-like U-net","volume":"10","author":"Aldoj","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2016). Densely Connected Convolutional Networks. arXiv.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.phro.2019.11.006","article-title":"Deep learning-based auto-segmentation of targets and organs-at-risk for magnetic resonance imaging only planning of prostate radiotherapy","volume":"12","author":"Elguindi","year":"2019","journal-title":"Phys. Imaging Radiat. Oncol."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation, Springer.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Alkadi, R., El-Baz, A., Taher, F., and Werghi, N. (2018, January 8\u201314). A 2.5D Deep Learning-Based Approach for Prostate Cancer Detection on T2-Weighted Magnetic Resonance Imaging. Proceedings of the 2018 European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-11018-5_66"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"7930","DOI":"10.1002\/mp.15285","article-title":"Integrating multiple MRI sequences for pelvic organs segmentation via the attention mechanism","volume":"48","author":"Huang","year":"2021","journal-title":"Med. Phys."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Marage, L., Walker, P.-M., Boudet, J., Fau, P., Debuire, P., Clausse, E., Petitfils, A., Aubignac, L., Rapacchi, S., and Bessieres, I. (2022). Characterisation of a split gradient coil design induced systemic imaging artefact on 0.35 T MR-linac systems. Phys. Med. Biol., 68.","DOI":"10.1088\/1361-6560\/aca876"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal Loss for Dense Object Detection","volume":"42","author":"Lin","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","article-title":"A systematic study of the class imbalance problem in convolutional neural networks","volume":"106","author":"Buda","year":"2018","journal-title":"Neural Netw."},{"key":"ref_44","unstructured":"Kingma, D.P., and Ba, J.L. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015-Conference Track Proceedings, San Diego, CA, USA."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.zemedi.2018.11.002","article-title":"An overview of deep learning in medical imaging focusing on MRI","volume":"29","author":"Lundervold","year":"2018","journal-title":"Z. Med. Phys."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Schenk, A., Prause, G., and Peitgen, H.O. (2000). Efficient Semiautomatic Segmentation of 3D Objects in Medical Images, Springer.","DOI":"10.1007\/978-3-540-40899-4_19"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1111\/1754-9485.13286","article-title":"Deep learning for segmentation in radiation therapy planning: A review","volume":"65","author":"Samarasinghe","year":"2021","journal-title":"J. Med. Imaging Radiat. Oncol."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"5543","DOI":"10.1002\/mp.14303","article-title":"Improving the slice interaction of 2.5D CNN for automatic pancreas segmentation","volume":"47","author":"Zheng","year":"2020","journal-title":"Med. Phys."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.neucom.2022.01.044","article-title":"A 2.5D semantic segmentation of the pancreas using attention guided dual context embedded U-Net","volume":"480","author":"Li","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Hu, K., Liu, C., Yu, X., Zhang, J., He, Y., and Zhu, H. (2018, January 20\u201322). A 2.5D Cancer Segmentation for MRI Images Based on U-Net. Proceedings of the 2018 5th International Conference on Information Science and Control Engineering (ICISCE), ICISCE 2018, Zhengzhou, China.","DOI":"10.1109\/ICISCE.2018.00011"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"e2","DOI":"10.2196\/ijmr.2172","article-title":"The Effectiveness of an Interactive 3-Dimensional Computer Graphics Model for Medical Education","volume":"1","author":"Battulga","year":"2012","journal-title":"Interact. J. Med. Res."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1086","DOI":"10.1002\/pd.5549","article-title":"Quantitative diagnostic advantages of three-dimensional ultrasound volume imaging for fetal posterior fossa anomalies: Preliminary establishment of a prediction model","volume":"39","author":"Sun","year":"2019","journal-title":"Prenat. Diagn."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"e170","DOI":"10.1016\/j.oooo.2017.01.012","article-title":"Three-dimensional volumetric analysis of ghost cell odontogenic carcinoma using 3-D reconstruction software: A case report","volume":"123","author":"Gomes","year":"2017","journal-title":"Oral Surg. Oral Med. Oral Pathol. Oral Radiol."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.compmedimag.2019.02.001","article-title":"3D convolutional neural networks for tumor segmentation using long-range 2D context","volume":"73","author":"Mlynarski","year":"2019","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"S136","DOI":"10.1016\/S1166-7087(20)30752-1","article-title":"French ccAFU guidelines\u2014Update 2020\u20132022: Prostate cancer","volume":"30","author":"Rozet","year":"2020","journal-title":"Progr\u00e8s en Urologie"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Singh, S.P., Wang, L., Gupta, S., Goli, H., Padmanabhan, P., and Guly\u00e1s, B. (2020). 3D Deep Learning on Medical Images: A Review. Sensors, 20.","DOI":"10.3390\/s20185097"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/11\/521\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:23:19Z","timestamp":1760131399000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/11\/521"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,15]]},"references-count":56,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["a16110521"],"URL":"https:\/\/doi.org\/10.3390\/a16110521","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2023,11,15]]}}}