{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T18:29:06Z","timestamp":1791829746532,"version":"4.3.4"},"reference-count":34,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Health & Welfare, Republic of Korea","award":["HF21C0026"],"award-info":[{"award-number":["HF21C0026"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate identification of anatomical landmarks on three-dimensional (3D) pelvic surface scans is essential for musculoskeletal assessment, yet manual procedures remain limited by operator dependence and soft tissue variability. This study presents a fully automated deep learning pipeline for localizing anatomical landmarks on the posterior pelvic region from raw 3D point cloud data. The pipeline integrates three modules: PelvicROINet for extracting the region of interest, PelvicAlignNet for rotation correction to standardize posture, and PelvicLandmarkNet for localizing six anatomical landmarks including the bilateral posterior superior iliac spines, bilateral iliac crests, L1, and L4. The models were trained independently with task-specific annotations and combined sequentially during inference. Under a subject-level split evaluation setting, the fully integrated system achieved a median error of 11.25 mm, demonstrating consistent localization performance across unseen subjects. Compared with manual landmark marking, the automated measurements showed improved within-visit repeatability, with reduced variability and higher intraclass correlation coefficients. The entire inference process required approximately three seconds per scan, supporting near real-time clinical applicability. These results indicate that the proposed modular framework enhances numerical consistency and robustness in surface-based pelvic landmark assessment and provides a scalable foundation for AI-assisted musculoskeletal evaluation and longitudinal monitoring.<\/jats:p>","DOI":"10.3390\/s26061760","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T17:04:24Z","timestamp":1773162264000},"page":"1760","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Fully Automated Deep Learning Pipeline for Anatomical Landmark Localization on Three-Dimensional Pelvic Surface Scans"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3924-8225","authenticated-orcid":false,"given":"Woosu","family":"Choi","sequence":"first","affiliation":[{"name":"Korea Institute of Oriental Medicine, 1672 Yuseong-daero, Yuseong-gu, Daejeon 34054, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7639-5884","authenticated-orcid":false,"given":"Jun-Su","family":"Jang","sequence":"additional","affiliation":[{"name":"Korea Institute of Oriental Medicine, 1672 Yuseong-daero, Yuseong-gu, Daejeon 34054, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"D\u2019Amico, M., Kinel, E., D\u2019Amico, G., and Roncoletta, P. (2021). A Self-Contained 3D Biomechanical Analysis Lab for Complete Automatic Spine and Full Skeleton Assessment of Posture, Gait and Run. Sensors, 21.","DOI":"10.3390\/s21113930"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Balasubramanian, M., and Sheykhmaleki, P. (2025). Emerging Roles of 3D Body Scanning in Human-Centric Applications. Technologies, 13.","DOI":"10.3390\/technologies13040126"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Cruz-Medel, I., Rodrigues-de Souza, D.P., and Alburquerque-Send\u00edn, F. (2024). Comprehensive Analysis of Pelvic Asymmetries in Low Back Pain, Scoliosis, Post-Traumatic Pelvic Dysfunctions and Obstetric Changes: A Narrative Review Focused on Clinical Relevance. Symmetry, 16.","DOI":"10.3390\/sym16101304"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bibrowicz, K., Szurmik, T., Ogrodzka-Ciechanowicz, K., Hudakova, Z., G\u0105sienica-Walczak, B., and Kurzeja, P. (2023). Asymmetry of the pelvis in Polish young adults. Front. Psychol., 14.","DOI":"10.3389\/fpsyg.2023.1148239"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Rayward, L., Pearcy, M., Izatt, M., Green, D., Labrom, R., Askin, G., and Little, J.P. (2023). Predicting spinal column profile from surface topography via 3D non-contact surface scanning. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0282634"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1186\/s13018-021-02843-2","article-title":"Evaluation of 3D vertebral and pelvic position by surface topography in asymptomatic females: Presentation of normative reference data","volume":"16","author":"Wolf","year":"2021","journal-title":"J. Orthop. Surg. Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1007\/s00701-024-06411-5","article-title":"A new 3D full-body scanner analyzing the sagittal and coronal balance of the adult spine: A preliminary prospective observational study","volume":"167","author":"Kang","year":"2025","journal-title":"Acta Neurochir."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.jmpt.2007.12.009","article-title":"Upright Static Pelvic Posture as Rotations and Translations in 3-Dimensional From Three 2-Dimensional Digital Images: Validation of a Computerized Analysis","volume":"31","author":"Harrison","year":"2008","journal-title":"J. Manip. Physiol. Ther."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1016\/j.cmpb.2013.10.014","article-title":"A Kinect-based system for cognitive rehabilitation exercises monitoring","volume":"113","year":"2014","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.cegh.2018.05.006","article-title":"3D scanning applications in medical field: A literature-based review","volume":"7","author":"Haleem","year":"2019","journal-title":"Clin. Epidemiol. Glob. Health"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zurawski, A.L., Friebe, D., Zaleska, S., Wojtas, K., Gawlik, M., and Wilczy\u0144ski, J. (2025). Assessing Trunk Cross-Section Geometry and Spinal Postures with Noninvasive 3D Surface Topography: A Study of 108 Healthy Young Adults. Sensors, 25.","DOI":"10.3390\/s25216626"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s44267-024-00046-x","article-title":"A review of point cloud segmentation for understanding 3D indoor scenes","volume":"2","author":"Sun","year":"2024","journal-title":"Vis. Intell."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Xu, T., An, D., Jia, Y., and Yue, Y. (2021). A Review: Point Cloud-Based 3D Human Joints Estimation. Sensors, 21.","DOI":"10.3390\/s21051684"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"101140","DOI":"10.1016\/j.gmod.2022.101140","article-title":"Point cloud denoising review: From classical to deep learning-based approaches","volume":"121","author":"Zhou","year":"2022","journal-title":"Graph. Models"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.image.2017.05.009","article-title":"A review of algorithms for filtering the 3D point cloud","volume":"57","author":"Han","year":"2017","journal-title":"Signal Process. Image Commun."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1109\/34.121791","article-title":"A Method for registration of 3-D shapes","volume":"14","author":"Besl","year":"1992","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_17","first-page":"3450","article-title":"Fast and Robust Iterative Closest Point","volume":"44","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","first-page":"36","article-title":"The reliability of palpating the posterior superior iliac spine: A systematic review","volume":"60","author":"Cooperstein","year":"2016","journal-title":"J. Can. Chiropr. Assoc."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1093\/ejo\/cjac077","article-title":"Accuracy and reliability of automated three-dimensional facial landmarking in medical and biological studies. A systematic review","volume":"45","author":"Alkalaly","year":"2023","journal-title":"Eur. J. Orthod."},{"key":"ref_20","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. arXiv."},{"key":"ref_21","unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017). PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Fu, C.W., and Jia, J. (2019, January 15\u201320). PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00571"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1145\/3326362","article-title":"Dynamic Graph CNN for Learning on Point Clouds","volume":"38","author":"Wang","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"ref_24","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., and Chen, B. (2018). PointCNN: Convolution On X-Transformed Points. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.jbiomech.2017.01.013","article-title":"Soft Tissue Displacement over Pelvic Anatomical Landmarks during 3-D Hip Movements","volume":"62","author":"Camomilla","year":"2017","journal-title":"J. Biomech."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Abreu de Souza, M., Alka Cordeiro, D.C., Oliveira, J.d., Oliveira, M.F.A.d., and Bonafini, B.L. (2023). 3D Multi-Modality Medical Imaging: Combining Anatomical and Infrared Thermal Images for 3D Reconstruction. Sensors, 23.","DOI":"10.3390\/s23031610"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, T., Liang, Z., and Wang, B. (2025). A Survey of Medical Point Cloud Shape Learning: Registration, Reconstruction and Variation. arXiv.","DOI":"10.1109\/BIBM66473.2025.11357130"},{"key":"ref_28","unstructured":"Yan, X. (2025, November 04). Pointnet\/Pointnet++ Pytorch, 2019. Available online: https:\/\/github.com\/yanx27\/Pointnet_Pointnet2_pytorch."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.math.2011.08.008","article-title":"Manual palpation of lumbo-pelvic landmarks: A validity study","volume":"17","author":"Kilby","year":"2012","journal-title":"Man. Ther."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hvidk\u00e6r, I.S., Harsted, S., Hadizadeh, M., O\u2019Neill, S., Kawchuk, G.N., and Nim, C. (2024). Static palpation ain\u2019t easy: Evaluating palpation precision using a topographical map of the lumbar spine as a reference. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0304571"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1007\/BF02513282","article-title":"Pelvis and lower limb anatomical landmark calibration precision and its propagation to bone geometry and joint angles","volume":"37","author":"Cappozzo","year":"1999","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Fagertun, J., Harder, S., Rosengren, A., Moeller, C., Werge, T., Paulsen, R.R., and Hansen, T.F. (2014). 3D facial landmarks: Inter-operator variability of manual annotation. BMC Med. Imaging, 14.","DOI":"10.1186\/1471-2342-14-35"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Lavaill, M., Martelli, S., Kerr, G.K., and Pivonka, P. (2022). Statistical Quantification of the Effects of Marker Misplacement and Soft-Tissue Artifact on Shoulder Kinematics and Kinetics. Life, 12.","DOI":"10.3390\/life12060819"},{"key":"ref_34","first-page":"123713","article-title":"Application of Soft Tissue Artifact Compensation Using Displacement Dependency between Anatomical Landmarks and Skin Markers","volume":"2012","author":"Ryu","year":"2012","journal-title":"Anat. Res. Int."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/6\/1760\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T17:06:19Z","timestamp":1773162379000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/6\/1760"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":34,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["s26061760"],"URL":"https:\/\/doi.org\/10.3390\/s26061760","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]}}}