{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T16:56:55Z","timestamp":1776013015022,"version":"3.50.1"},"reference-count":30,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Bone segmentation in magnetic resonance imaging (MRI) is crucial for clinical and research applications, including diagnosis, surgical planning, and treatment monitoring. However, it remains challenging due to anatomical variability and complex bone morphology. Manual segmentation is time-consuming and operator-dependent, fostering interest in automated methods. This study proposes an automated segmentation method based on a 3D U-Net convolutional neural network to segment the femur, tibia, and patella from low-field MRI scans. Low-field MRI offers advantages in cost, patient comfort, and accessibility but presents challenges related to lower signal quality. Our method achieved a Dice Similarity Coefficient (DSC) of 0.9838, Intersection over Union (IoU) of 0.9682, and Average Hausdorff Distance (AHD) of 0.0223, with an inference time of approximately 3.96 s per volume on a GPU. Although post-processing had minimal impact on metrics, it significantly enhanced the visual smoothness of bone surfaces, which is crucial for clinical use. The final segmentations enabled the creation of clean, 3D-printable bone models, beneficial for preoperative planning. These results demonstrate that the model achieves accurate segmentation with a high degree of overlap compared to manually segmented reference data. This accuracy results from meticulous fine-tuning of the network, along with the application of advanced data augmentation and post-processing techniques.<\/jats:p>","DOI":"10.3390\/bdcc9060146","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T03:52:08Z","timestamp":1748404328000},"page":"146","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Bone Segmentation in Low-Field Knee MRI Using a Three-Dimensional Convolutional Neural Network"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5532-9188","authenticated-orcid":false,"given":"Ciro","family":"Listone","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Information Technologies, University of Naples Federico II, 80125 Naples, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2640-157X","authenticated-orcid":false,"given":"Diego","family":"Romano","sequence":"additional","affiliation":[{"name":"Institute for High Performance Computing and Networking, National Research Council, 80131 Naples, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9953-1319","authenticated-orcid":false,"given":"Marco","family":"Lapegna","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Applications, University of Naples Federico II, 80125 Naples, Italy"}]}],"member":"1968","published-online":{"date-parts":[[2025,5,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.compmedimag.2019.06.002","article-title":"Fully automatic knee osteoarthritis severity grading using deep neural networks with a novel ordinal loss","volume":"75","author":"Chen","year":"2019","journal-title":"Comput. Med Imaging Graph."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1016\/j.rcl.2017.04.012","article-title":"Imaging in osteoarthritis","volume":"55","author":"Hayashi","year":"2017","journal-title":"Radiol. Clin."},{"key":"ref_3","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":"2019","journal-title":"Z. F\u00fcr Med. Phys."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1148\/radiol.2018171820","article-title":"Current applications and future impact of machine learning in radiology","volume":"288","author":"Choy","year":"2018","journal-title":"Radiology"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Cabitza, F., Locoro, A., and Banfi, G. (2018). Machine learning in orthopedics: A literature review. Front. Bioeng. Biotechnol., 6.","DOI":"10.3389\/fbioe.2018.00075"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1038\/s41584-018-0130-5","article-title":"Machine-learning-based patient-specific prediction models for knee osteoarthritis","volume":"15","author":"Jamshidi","year":"2019","journal-title":"Nat. Rev. Rheumatol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1016\/j.joca.2019.04.005","article-title":"Machine-learning for osteoarthritis research","volume":"27","author":"Kluzek","year":"2019","journal-title":"Osteoarthr. Cartil."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.compeleceng.2019.04.011","article-title":"Identification of plant leaf diseases using a nine-layer deep convolutional neural network","volume":"76","author":"Geetharamani","year":"2019","journal-title":"Comput. Electr. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2379","DOI":"10.1002\/mrm.26841","article-title":"Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging","volume":"79","author":"Liu","year":"2018","journal-title":"Magn. Reson. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.media.2018.11.009","article-title":"Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: Data from the Osteoarthritis Initiative","volume":"52","author":"Ambellan","year":"2019","journal-title":"Med. Image Anal."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Lim, J., Kim, J., and Cheon, S. (2019). A deep neural network-based method for early detection of osteoarthritis using statistical data. Int. J. Environ. Res. Public Health, 16.","DOI":"10.3390\/ijerph16071281"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Tiulpin, A., and Saarakkala, S. (2020). Automatic grading of individual knee osteoarthritis features in plain radiographs using deep convolutional neural networks. Diagnostics, 10.","DOI":"10.3390\/diagnostics10110932"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"101854","DOI":"10.1016\/j.softx.2024.101854","article-title":"KneeBones3Dify: Open-source software for segmentation and 3D reconstruction of knee bones from MRI data","volume":"27","author":"Maddalena","year":"2024","journal-title":"SoftwareX"},{"key":"ref_15","unstructured":"Listone, C. (2025, April 23). clist1\/Bone-Segmentation-in-Low-Field-Knee-MRI-Using-a-3D-Convolutional-Neural-Network: 3D U-Net for Low Field Knee MRI. Available online: https:\/\/zenodo.org\/records\/15372998."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_17","unstructured":"Wu, W. (2025, April 23). Patchify, 2017. Available online: https:\/\/pypi.org\/project\/patchify\/."},{"key":"ref_18","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany. proceedings, part III 18."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Avesta, A., Hossain, S., Lin, M., Aboian, M., Krumholz, H.M., and Aneja, S. (2023). Comparing 3D, 2.5D, and 2D Approaches to Brain Image Auto-Segmentation. Bioengineering, 10.","DOI":"10.3390\/bioengineering10020181"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shivdeo, A., Lokwani, R., Kulkarni, V., Kharat, A., and Pant, A. (2021). Comparative Evaluation of 3D and 2D Deep Learning Techniques for Semantic Segmentation in CT Scans. arXiv.","DOI":"10.1109\/icABCD51485.2021.9519338"},{"key":"ref_21","unstructured":"Bach, F., and Blei, D. (2015, January 7\u20139). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning, Lille, France. Proceedings of Machine Learning Research."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., and Wells, W. (2016, January 17\u201321). 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2016, Athens, Greece.","DOI":"10.1007\/978-3-319-46726-9"},{"key":"ref_23","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Yaqub, M., Feng, J., Zia, M.S., Arshid, K., Jia, K., Rehman, Z.U., and Mehmood, A. (2020). State-of-the-art CNN optimizer for brain tumor segmentation in magnetic resonance images. Brain Sci., 10.","DOI":"10.3390\/brainsci10070427"},{"key":"ref_25","unstructured":"Belyaev, A. (2025, April 23). Mesh Smoothing and Enhancing. Curvature Estimation. Available online: https:\/\/maths.dur.ac.uk\/users\/norbert.peyerimhoff\/epsrc2013\/06gm_surf3.pdf."},{"key":"ref_26","unstructured":"Chollet, F. (2025, April 23). Keras. Available online: https:\/\/keras.io."},{"key":"ref_27","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2016). Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv."},{"key":"ref_28","unstructured":"Loizides, F., and Schmidt, B. (2016). Jupyter Notebooks\u2014A publishing format for reproducible computational workflows. Positioning and Power in Academic Publishing: Players, Agents and Agendas, IOS Press."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Jungo, A., Scheidegger, O., Reyes, M., and Balsiger, F. (2021). pymia: A Python package for data handling and evaluation in deep learning-based medical image analysis. Comput. Methods Programs Biomed., 198.","DOI":"10.1016\/j.cmpb.2020.105796"},{"key":"ref_30","unstructured":"Soscia, E., Romano, D., Maddalena, L., Gregoretti, F., De Lucia, G., and Antonelli, L. (2025, April 23). KneeBones3Dify-Annotated-Dataset v1.0.0. Available online: https:\/\/zenodo.org\/records\/10534328."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/6\/146\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:41:52Z","timestamp":1760031712000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/6\/146"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,28]]},"references-count":30,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["bdcc9060146"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9060146","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,28]]}}}