{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T15:03:00Z","timestamp":1790348580710,"version":"4.1.0"},"posted":{"date-parts":[[2024,5,7]]},"group-title":"Radiology and Imaging","reference-count":80,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T00:00:00Z","timestamp":1715040000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2024,10,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Analyzing anatomic shapes of tissues and organs is pivotal for accurate disease diagnostics and clinical decision-making. One prominent disease that depends on anatomic shape analysis is osteoarthritis, which affects 30 million Americans. To advance osteoarthritis diagnostics and prognostics, we introduce\n                  <jats:italic>ShapeMed-Knee<\/jats:italic>\n                  , a 3D shape dataset with 9,376 high-resolution, medicalimaging-based 3D shapes of both femur bone and cartilage. Besides data, ShapeMed-Knee includes two benchmarks for assessing reconstruction accuracy and five clinical prediction tasks that assess the utility of learned shape representations. Leveraging ShapeMed-Knee, we develop and evaluate a novel hybrid explicit-implicit neural shape model which achieves up to 40% better reconstruction accuracy than a statistical shape model and two implicit neural shape models. Our hybrid models achieve state-of-the-art performance for preserving cartilage biomarkers (root mean squared error \u2264 0.05 vs. \u2264 0.07, 0.10, and 0.14). Our models are also the first to successfully predict localized structural features of osteoarthritis, outperforming shape models and convolutional neural networks applied to raw magnetic resonance images and segmentations (e.g., osteophyte size and localization 63% accuracy vs. 49-61%). The ShapeMed-Knee dataset provides medical evaluations to reconstruct multiple anatomic surfaces and embed meaningful disease-specific information. ShapeMed-Knee reduces barriers to applying 3D modeling in medicine, and our benchmarks highlight that advancements in 3D modeling can enhance the diagnosis and risk stratification for complex diseases. The dataset, code, and benchmarks are freely accessible.\n                <\/jats:p>","DOI":"10.1101\/2024.05.06.24306965","type":"posted-content","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T09:21:17Z","timestamp":1715160077000},"source":"Crossref","is-referenced-by-count":6,"title":["ShapeMed-Knee: A Dataset and Neural Shape Model Benchmark for Modeling 3D Femurs"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6717-8979","authenticated-orcid":false,"given":"Anthony A.","family":"Gatti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Louis","family":"Blankemeier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dave","family":"Van Veen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Hargreaves","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott L.","family":"Delp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Garry E.","family":"Gold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feliks","family":"Kogan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akshay S.","family":"Chaudhari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2024102504051239000_2024.05.06.24306965v2.1","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1002\/acr.22721","article-title":"\u201cAlternative Methods for Defining Osteoarthritis and the Impact on Estimating Prevalence in a US Population-Based Survey: OA Prevalence in a Population-Based Survey","volume":"68","year":"2016","journal-title":"Arthritis Care & Research"},{"key":"2024102504051239000_2024.05.06.24306965v2.2","doi-asserted-by":"publisher","DOI":"10.1002\/art.24984"},{"key":"2024102504051239000_2024.05.06.24306965v2.3","doi-asserted-by":"crossref","first-page":"100069","DOI":"10.1016\/j.ocarto.2020.100069","article-title":"\u201cMachine learning in knee osteoarthritis: A review","volume":"2","year":"2020","journal-title":"Osteoarthritis and Cartilage Open"},{"key":"2024102504051239000_2024.05.06.24306965v2.4","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.joca.2022.10.001","article-title":"\u201cThe KNee OsteoArthritis Prediction (KNOAP2020) challenge: An image analysis challenge to predict incident symptomatic radiographic knee osteoarthritis from MRI and X-ray images","volume":"31","year":"2023","journal-title":"Osteoarthritis and Cartilage"},{"key":"2024102504051239000_2024.05.06.24306965v2.5","unstructured":"S. Mohammadi et al., \u201cArtificial intelligence in osteoarthritis detection: A systematic review and meta-analysis,\u201d Osteoarthritis and Cartilage, p. S1063458423009482, Oct. 2023."},{"key":"2024102504051239000_2024.05.06.24306965v2.6","first-page":"e200078","article-title":"\u201cThe International Workshop on Osteoarthritis Imaging Knee MRI Segmentation Challenge: A Multi-Institute Evaluation and Analysis Framework on a Standardized Dataset","volume":"3","year":"2021","journal-title":"Radiology: Artificial Intelligence"},{"key":"2024102504051239000_2024.05.06.24306965v2.7","doi-asserted-by":"crossref","first-page":"135323","DOI":"10.1109\/ACCESS.2023.3338379","article-title":"\u201c3D Efficient Multi-Task Neural Network for Knee Osteoarthritis Diagnosis Using MRI Scans: Data From the Osteoarthritis Initiative","volume":"11","year":"2023","journal-title":"IEEE Access"},{"key":"2024102504051239000_2024.05.06.24306965v2.8","doi-asserted-by":"crossref","first-page":"1164655","DOI":"10.3389\/fbioe.2023.1164655","article-title":"\u201cTransfer learning-assisted 3D deep learning models for knee osteoarthritis detection: Data from the osteoarthritis initiative","volume":"11","year":"2023","journal-title":"Frontiers in Bioengineering and Biotechnology"},{"issue":"6","key":"2024102504051239000_2024.05.06.24306965v2.9","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1186\/ar3488","article-title":"\u201cWhy radiography should no longer be considered a surrogate outcome measure for longitudinal assessment of cartilage in knee osteoarthritis","volume":"13","year":"2011","journal-title":"Arthritis Research & Therapy"},{"key":"2024102504051239000_2024.05.06.24306965v2.10","doi-asserted-by":"publisher","DOI":"10.1136\/ard.16.4.494"},{"key":"2024102504051239000_2024.05.06.24306965v2.11","unstructured":"M. Schaufelberger et al., \u201cA statistical shape model for radiation-free assessment and classification of craniosynostosis,\u201d Mar. 2022. arXiv:2201.03288 [cs, eess]."},{"key":"2024102504051239000_2024.05.06.24306965v2.12","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1002\/jor.24214","article-title":"\u201cStatistical shape modeling of femur shape variability in female patients with hip dysplasia","volume":"37","year":"2019","journal-title":"Journal of Orthopaedic Research"},{"key":"2024102504051239000_2024.05.06.24306965v2.13","doi-asserted-by":"crossref","first-page":"116803","DOI":"10.1016\/j.bone.2023.116803","article-title":"\u201cSex disparities in tibia-fibula geometry and density are associated with elevated bone strain in females: A cross-validation study","volume":"173","year":"2023","journal-title":"Bone"},{"key":"2024102504051239000_2024.05.06.24306965v2.14","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.medengphy.2019.02.009","article-title":"\u201cThe effect of articular geometry features identified using statistical shape modelling on knee biomechanics","volume":"66","year":"2019","journal-title":"Medical Engineering & Physics"},{"key":"2024102504051239000_2024.05.06.24306965v2.15","doi-asserted-by":"crossref","first-page":"100178","DOI":"10.1016\/j.ostima.2024.100178","article-title":"\u201c3-dimensional bone shape and knee osteoarthritis: What have we learned?","volume":"4","year":"2024","journal-title":"Osteoarthritis Imaging"},{"key":"2024102504051239000_2024.05.06.24306965v2.16","doi-asserted-by":"crossref","first-page":"1695","DOI":"10.1016\/j.joca.2015.05.027","article-title":"\u201cThree-dimensional MRI-based statistical shape model and application to a cohort of knees with acute ACL injury","volume":"23","year":"2015","journal-title":"Osteoarthritis and Cartilage"},{"key":"2024102504051239000_2024.05.06.24306965v2.17","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2020-217160"},{"key":"2024102504051239000_2024.05.06.24306965v2.18","first-page":"99","article-title":"\u201cNeRF: representing scenes as neural radiance fields for view synthesis","volume":"65","year":"2021","journal-title":"Commun. ACM"},{"key":"2024102504051239000_2024.05.06.24306965v2.19","unstructured":"A. X. Chang et al., \u201cShapeNet: An Information-Rich 3D Model Repository,\u201d Dec. 2015. arXiv:1512.03012 [cs]."},{"key":"2024102504051239000_2024.05.06.24306965v2.20","unstructured":"J. Li et al., \u201cMedShapeNet \u2013 A Large-Scale Dataset of 3D Medical Shapes for Computer Vision,\u201d Dec. 2023. arXiv:2308.16139 [cs]."},{"key":"2024102504051239000_2024.05.06.24306965v2.21","doi-asserted-by":"crossref","unstructured":"J. J. Park , P. Florence , J. Straub , R. Newcombe and S. Lovegrove , \u201cDeepSDF: Learning Continuous Signed Distance Functions for Shape Representation,\u201d in 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (Long Beach, CA, USA), pp. 165\u2013 174, IEEE, June 2019.","DOI":"10.1109\/CVPR.2019.00025"},{"key":"2024102504051239000_2024.05.06.24306965v2.22","doi-asserted-by":"crossref","unstructured":"Z. Chen and H. Zhang , \u201cLearning Implicit Fields for Generative Shape Modeling,\u201d Sept. 2019. arXiv:1812.02822 [cs].","DOI":"10.1109\/CVPR.2019.00609"},{"key":"2024102504051239000_2024.05.06.24306965v2.23","doi-asserted-by":"crossref","unstructured":"L. Mescheder , M. Oechsle , M. Niemeyer , S. Nowozin and A. Geiger , \u201cOccupancy Networks: Learning 3D Reconstruction in Function Space,\u201d tech. rep., Apr. 2019. arXiv:1812.03828 [cs] type: article.","DOI":"10.1109\/CVPR.2019.00459"},{"key":"2024102504051239000_2024.05.06.24306965v2.24","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/978-3-030-58598-3_4","volume-title":"Computer Vision \u2013 ECCV 2020","volume":"12353","author":"Series Title: Lecture Notes in Computer Science","year":"2020"},{"key":"2024102504051239000_2024.05.06.24306965v2.25","doi-asserted-by":"crossref","unstructured":"I. Mehta , M. Gharbi , C. Barnes , E. Shechtman , R. Ramamoorthi and M. Chandraker , \u201cModulated Periodic Activations for Generalizable Local Functional Representations,\u201d in 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), (Montreal, QC, Canada), pp. 14194\u201314203, IEEE, Oct. 2021.","DOI":"10.1109\/ICCV48922.2021.01395"},{"key":"2024102504051239000_2024.05.06.24306965v2.26","first-page":"7462","volume-title":"in Advances in Neural Information Processing Systems","volume":"33","year":"2020"},{"key":"2024102504051239000_2024.05.06.24306965v2.27","unstructured":"H. Li , X. Yang , H. Zhai , Y. Liu , H. Bao and G. Zhang , \u201cVox-Surf: Voxel-Based Implicit Surface Representation,\u201d IEEE Transactions on Visualization and Computer Graphics, pp. 1\u201312, 2022."},{"key":"2024102504051239000_2024.05.06.24306965v2.28","doi-asserted-by":"crossref","unstructured":"S. Peng , M. Niemeyer , L. Mescheder , M. Pollefeys and A. Geiger , \u201cConvolutional Occupancy Networks,\u201d in Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part III, (Berlin, Heidelberg), pp. 523\u2013540, Springer-Verlag, Aug. 2020.","DOI":"10.1007\/978-3-030-58580-8_31"},{"key":"2024102504051239000_2024.05.06.24306965v2.29","doi-asserted-by":"crossref","unstructured":"E. R. Chan et al., \u201cEfficient Geometry-aware 3D Generative Adversarial Networks,\u201d in 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (New Orleans, LA, USA), pp. 16102\u2013 16112, IEEE, June 2022.","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"2024102504051239000_2024.05.06.24306965v2.30","doi-asserted-by":"crossref","unstructured":"G. Chou , Y. Bahat and F. Heide , \u201cDiffusion-SDF: Conditional Generative Modeling of Signed Distance Functions,\u201d in 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), (Paris, France), pp. 2262\u20132272, IEEE, Oct. 2023.","DOI":"10.1109\/ICCV51070.2023.00215"},{"key":"2024102504051239000_2024.05.06.24306965v2.31","unstructured":"D. Van Veen et al., \u201cScale-Agnostic Super-Resolution in MRI using Feature-Based Coordinate Networks,\u201d Oct. 2022. arXiv:2210.08676 [cs]."},{"key":"2024102504051239000_2024.05.06.24306965v2.32","unstructured":"G. Vincent , C. Wolstenholme , I. Scott and M. Bowes , \u201cFully Automatic Segmentation of the Knee Joint using Active Appearance Models,\u201d in Medical Image Analysis for the Clinic: A Grand Challenge, (Beijing), p. 7, 2010."},{"key":"2024102504051239000_2024.05.06.24306965v2.33","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.11.009"},{"key":"2024102504051239000_2024.05.06.24306965v2.34","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/978-3-030-78191-0_14","volume-title":"Information Processing in Medical Imaging","volume":"12729","author":"Series Title: Lecture Notes in Computer Science","year":"2021"},{"key":"2024102504051239000_2024.05.06.24306965v2.35","doi-asserted-by":"publisher","DOI":"10.1002\/art.37987"},{"key":"2024102504051239000_2024.05.06.24306965v2.36","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1123\/jab.2021-0162","article-title":"\u201cInfluence of Articular Geometry and Tibial Tu-bercle Location on Patellofemoral Kinematics and Contact Mechanics","volume":"38","year":"2022","journal-title":"Journal of Applied Biomechanics"},{"key":"2024102504051239000_2024.05.06.24306965v2.37","doi-asserted-by":"crossref","unstructured":"M. Styner et al., \u201cFramework for the Statistical Shape Analysis of Brain Structures using SPHARM-PDM,\u201d The Insight Journal, July 2006.","DOI":"10.54294\/owxzil"},{"key":"2024102504051239000_2024.05.06.24306965v2.38","doi-asserted-by":"crossref","first-page":"e1008851","DOI":"10.1371\/journal.pcbi.1008851","article-title":"\u201cLinking statistical shape models and simulated function in the healthy adult human heart","volume":"17","year":"2021","journal-title":"PLOS Computational Biology"},{"key":"2024102504051239000_2024.05.06.24306965v2.39","doi-asserted-by":"crossref","unstructured":"A. A. Gatti , P. J. Keir , M. D. Noseworthy and M. R. Maly , \u201cInvestigating acute changes in osteoarthritic cartilage by integrating biomechanics and statistical shape models of bone: data from the osteoarthritis initiative,\u201d Magn Reson Mater Phy, Mar. 2022.","DOI":"10.1007\/s10334-022-01004-8"},{"key":"2024102504051239000_2024.05.06.24306965v2.40","doi-asserted-by":"crossref","first-page":"2143","DOI":"10.1109\/TPAMI.2012.276","article-title":"\u201cFOCUSR: Feature Oriented Correspondence Using Spectral Regularization\u2013A Method for Precise Surface Matching","volume":"35","year":"2013","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2024102504051239000_2024.05.06.24306965v2.41","doi-asserted-by":"crossref","first-page":"103099","DOI":"10.1016\/j.media.2024.103099","article-title":"\u201cLearning continuous shape priors from sparse data with neural implicit functions","volume":"94","year":"2024","journal-title":"Medical Image Analysis"},{"key":"2024102504051239000_2024.05.06.24306965v2.42","unstructured":"P. M. Jensen , U. Wickramasinghe , A. B. Dahl , P. Fua and V. A. Dahl , \u201cDeep Active Latent Surfaces for Medical Geometries,\u201d June 2022. arXiv:2206.10241 [cs]."},{"key":"2024102504051239000_2024.05.06.24306965v2.43","doi-asserted-by":"crossref","unstructured":"D. L\u00fcdke , T. Amiranashvili , F. Ambellan , I. Ezhov , B. Menze and S. Zachow , \u201cLandmark-free Statistical Shape Modeling via Neural Flow Deformations,\u201d Sept. 2022. arXiv:2209.06861 [cs].","DOI":"10.1007\/978-3-031-16434-7_44"},{"key":"2024102504051239000_2024.05.06.24306965v2.44","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2006.02.025"},{"key":"2024102504051239000_2024.05.06.24306965v2.45","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1007\/s10334-021-00934-z","article-title":"\u201cAutomatic knee cartilage and bone segmentation using multi-stage convolutional neural networks: data from the osteoarthritis initiative","volume":"34","year":"2021","journal-title":"Magnetic Resonance Materials in Physics, Biology and Medicine"},{"key":"2024102504051239000_2024.05.06.24306965v2.46","doi-asserted-by":"crossref","unstructured":"W. Wirth et al., \u201cAccuracy and longitudinal reproducibility of quantitative femorotibial cartilage measures derived from automated U-Net-based segmentation of two different MRI contrasts: data from the osteoarthritis initiative healthy reference cohort,\u201d Magn Reson Mater Phy, Oct. 2020.","DOI":"10.1007\/s10334-020-00889-7"},{"key":"2024102504051239000_2024.05.06.24306965v2.47","doi-asserted-by":"crossref","unstructured":"M. C. M. Khan , J. O\u2019Donovan , J. M. Charlton , J.-S. Roy , M. A. Hunt and J.-F. Esculier , \u201cThe Influence of Running on Lower Limb Cartilage: A Systematic Review and Meta-analysis,\u201d Sports Medicine, Sept. 2021.","DOI":"10.1007\/s40279-021-01533-7"},{"key":"2024102504051239000_2024.05.06.24306965v2.48","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2014.06.023"},{"key":"2024102504051239000_2024.05.06.24306965v2.49","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2019-216453"},{"key":"2024102504051239000_2024.05.06.24306965v2.50","unstructured":"A. A. Gatti , \u201cPython musculoskeletal toolkit,\u201d 2021. https:\/\/www.github.com\/gattia\/pymskt."},{"key":"2024102504051239000_2024.05.06.24306965v2.51","doi-asserted-by":"crossref","first-page":"986","DOI":"10.1186\/s13018-023-04482-1","article-title":"\u201cInvestigating the reliability and validity of subacromial space measurements using ultrasound and MRI","volume":"18","year":"2023","journal-title":"Journal of Orthopaedic Surgery and Research"},{"key":"2024102504051239000_2024.05.06.24306965v2.52","doi-asserted-by":"crossref","unstructured":"F. Eckstein and W. Wirth , \u201cQuantitative Cartilage Imaging in Knee Osteoarthritis,\u201d Arthritis, vol. 2011, pp. 1\u201319, 2011.","DOI":"10.1155\/2011\/475684"},{"key":"2024102504051239000_2024.05.06.24306965v2.53","unstructured":"A. Kaszynski , \u201cPython approximated centroidal voronoi diagrams,\u201d 2015. https:\/\/github.com\/pyvista\/pyacvd."},{"key":"2024102504051239000_2024.05.06.24306965v2.54","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1111\/j.1467-8659.2004.00769.x","article-title":"\u201cApproximated Centroidal Voronoi Diagrams for Uniform Polygonal Mesh Coarsening","volume":"23","year":"2004","journal-title":"Computer Graphics Forum"},{"key":"2024102504051239000_2024.05.06.24306965v2.55","doi-asserted-by":"crossref","first-page":"S78","DOI":"10.1016\/j.joca.2023.01.020","article-title":"\u201cPredicting Chronic Knee Pain Using An Automated Mri-Based Bone And Cartilage Statistical Shape Model: Data From The Osteoarthritis Initiative","volume":"31","year":"2023","journal-title":"Osteoarthritis and Cartilage"},{"key":"2024102504051239000_2024.05.06.24306965v2.56","unstructured":"A. A. Gatti , \u201cPython musculoskeletal toolkit,\u201d 2020. https:\/\/www.github.com\/gattia\/pyfocusr."},{"key":"2024102504051239000_2024.05.06.24306965v2.57","doi-asserted-by":"crossref","first-page":"1450","DOI":"10.21105\/joss.01450","article-title":"\u201cPyVista: 3D plotting and mesh analysis through a streamlined interface for the Visualization Toolkit (VTK)","volume":"4","year":"2019","journal-title":"Journal of Open Source Software"},{"key":"2024102504051239000_2024.05.06.24306965v2.58","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2011.05.004"},{"key":"2024102504051239000_2024.05.06.24306965v2.59","doi-asserted-by":"crossref","first-page":"10915","DOI":"10.1038\/s41598-021-90292-6","article-title":"\u201cDeep learning for large scale MRI-based morphological phenotyping of osteoarthritis","volume":"11","year":"2021","journal-title":"Scientific Reports"},{"key":"2024102504051239000_2024.05.06.24306965v2.60","doi-asserted-by":"crossref","first-page":"6922","DOI":"10.1038\/s41598-023-33934-1","article-title":"\u201cPrediction of total knee replacement using deep learning analysis of knee MRI","volume":"13","year":"2023","journal-title":"Scientific Reports"},{"key":"2024102504051239000_2024.05.06.24306965v2.61","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1148\/radiol.2020192091","article-title":"\u201cPrediction of Total Knee Replacement and Diagnosis of Osteoarthritis by Using Deep Learning on Knee Radiographs: Data from the Osteoarthritis Initiative","volume":"296","year":"2020","journal-title":"Radiology"},{"key":"2024102504051239000_2024.05.06.24306965v2.62","doi-asserted-by":"crossref","first-page":"1727","DOI":"10.1038\/s41598-018-20132-7","article-title":"\u201cAutomatic Knee Osteoarthritis Diagnosis from Plain Radiographs: A Deep Learning-Based Approach","volume":"8","year":"2018","journal-title":"Scientific Reports"},{"key":"2024102504051239000_2024.05.06.24306965v2.63","doi-asserted-by":"crossref","first-page":"104334","DOI":"10.1016\/j.compbiomed.2021.104334","article-title":"\u201cDeep learning-based algorithm for assessment of knee osteoarthritis severity in radiographs matches performance of radiologists","volume":"133","year":"2021","journal-title":"Computers in Biology and Medicine"},{"key":"2024102504051239000_2024.05.06.24306965v2.64","doi-asserted-by":"crossref","first-page":"110249","DOI":"10.1016\/j.ejrad.2022.110249","article-title":"\u201cExternal validation of an artificial intelligence tool for radiographic knee osteoarthritis severity classification","volume":"150","year":"2022","journal-title":"European Journal of Radiology"},{"key":"2024102504051239000_2024.05.06.24306965v2.65","unstructured":"I. Loshchilov and F. Hutter , \u201cDecoupled Weight Decay Regularization,\u201d Jan. 2019. arXiv:1711.05101 [cs, math]."},{"issue":"4","key":"2024102504051239000_2024.05.06.24306965v2.66","first-page":"7","volume":"21","year":"1987","journal-title":"\u201cMarching Cubes: A High Resolution 3D Surface Construction Algorithm,\u201d"},{"key":"2024102504051239000_2024.05.06.24306965v2.67","doi-asserted-by":"crossref","unstructured":"H. Fu , C. Li , X. Liu , J. Gao , A. Celikyilmaz and L. Carin , \u201cCyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing,\u201d arXiv:1903.10145 [cs, stat], June 2019. arXiv: 1903.10145.","DOI":"10.18653\/v1\/N19-1021"},{"key":"2024102504051239000_2024.05.06.24306965v2.68","unstructured":"M. J. Cardoso et al., \u201cMONAI: An open-source framework for deep learning in healthcare,\u201d Nov. 2022. arXiv:2211.02701 [cs]."},{"key":"2024102504051239000_2024.05.06.24306965v2.69","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1007\/s10044-023-01181-9","article-title":"\u201cDeep Neural Networks for Rank-Consistent Ordinal Regression Based On Conditional Probabilities","volume":"26","year":"2023","journal-title":"Pattern Analysis and Applications"},{"key":"2024102504051239000_2024.05.06.24306965v2.70","doi-asserted-by":"publisher","DOI":"10.1007\/s00167-014-3205-0"},{"key":"2024102504051239000_2024.05.06.24306965v2.71","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2015.05.003"},{"key":"2024102504051239000_2024.05.06.24306965v2.72","first-page":"e190065","article-title":"\u201cAutomated Classification of Radiographic Knee Osteoarthritis Severity Using Deep Neural Networks","volume":"2","year":"2020","journal-title":"Radiology: Artificial Intelligence"},{"key":"2024102504051239000_2024.05.06.24306965v2.73","doi-asserted-by":"crossref","first-page":"5196","DOI":"10.3390\/app11115196","article-title":"\u201cKnee Osteoarthritis Classification Using 3D CNN and MRI","volume":"11","year":"2021","journal-title":"Applied Sciences"},{"key":"2024102504051239000_2024.05.06.24306965v2.74","doi-asserted-by":"crossref","first-page":"1242","DOI":"10.1016\/j.joca.2023.05.006","article-title":"\u201cComparison of evaluation metrics of deep learning for imbalanced imaging data in osteoarthritis studies","volume":"31","year":"2023","journal-title":"Osteoarthritis and Cartilage"},{"key":"2024102504051239000_2024.05.06.24306965v2.75","doi-asserted-by":"crossref","first-page":"3155","DOI":"10.1038\/s41598-022-07092-9","article-title":"\u201cAutomatic estimation of knee effusion from limited MRI data","volume":"12","year":"2022","journal-title":"Scientific Reports"},{"key":"2024102504051239000_2024.05.06.24306965v2.76","doi-asserted-by":"crossref","first-page":"752","DOI":"10.5435\/JAAOS-D-18-00267","article-title":"\u201cThe Significance of Osteoarthritis-associated Bone Marrow Lesions in the Knee","volume":"27","year":"2019","journal-title":"Journal of the American Academy of Orthopaedic Surgeons"},{"key":"2024102504051239000_2024.05.06.24306965v2.77","doi-asserted-by":"crossref","unstructured":"A. A. Tolpadi , J. J. Lee , V. Pedoia and S. Majumdar , \u201cDeep Learning Predicts Total Knee Replacement from Magnetic Resonance Images,\u201d Scientific Reports, vol. 10, Dec. 2020.","DOI":"10.1038\/s41598-020-63395-9"},{"key":"2024102504051239000_2024.05.06.24306965v2.78","doi-asserted-by":"publisher","DOI":"10.1007\/s00167-010-1072-x"},{"key":"2024102504051239000_2024.05.06.24306965v2.79","first-page":"75","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2009","volume":"5761","author":"Series Title: Lecture Notes in Computer Science","year":"2009"},{"key":"2024102504051239000_2024.05.06.24306965v2.80","doi-asserted-by":"crossref","unstructured":"R. Rombach , A. Blattmann , D. Lorenz , P. Esser and B. Ommer , \u201cHigh-Resolution Image Synthesis with Latent Diffusion Models,\u201d Apr. 2022. arXiv:2112.10752 [cs].","DOI":"10.1109\/CVPR52688.2022.01042"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2024.05.06.24306965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:00:10Z","timestamp":1768507210000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2024.05.06.24306965"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,7]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1101\/2024.05.06.24306965","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1109\/TMI.2024.3485613","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2024,5,7]]},"subtype":"preprint"}}