Visualizing Preosteoarthritis: Updates on UTE-Based Compositional MRI and Deep Learning Algorithms
Dong Sun MD
Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Search for more papers by this authorCorresponding Author
Gang Wu MD
Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Address reprint requests to: X.L., No. 1095, Jiefang Road, Wuhan 430030, China. E-mail: [email protected]
Search for more papers by this authorWei Zhang MD
Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Search for more papers by this authorNadeer M. Gharaibeh MD
Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Search for more papers by this authorCorresponding Author
Xiaoming Li MD, PhD
Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Address reprint requests to: X.L., No. 1095, Jiefang Road, Wuhan 430030, China. E-mail: [email protected]
Search for more papers by this authorDong Sun MD
Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Search for more papers by this authorCorresponding Author
Gang Wu MD
Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Address reprint requests to: X.L., No. 1095, Jiefang Road, Wuhan 430030, China. E-mail: [email protected]
Search for more papers by this authorWei Zhang MD
Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Search for more papers by this authorNadeer M. Gharaibeh MD
Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Search for more papers by this authorCorresponding Author
Xiaoming Li MD, PhD
Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Address reprint requests to: X.L., No. 1095, Jiefang Road, Wuhan 430030, China. E-mail: [email protected]
Search for more papers by this authorGang Wu and Xiaoming Li contributed equally and share the corresponding authorship.
Abstract
Osteoarthritis (OA) is heterogeneous and involves structural changes in the whole joint, such as cartilage, meniscus/labrum, ligaments, and tendons, mainly with short T2 relaxation times. Detecting OA before the onset of irreversible changes is crucial for early proactive management and limit growing disease burden. The more recent advanced quantitative imaging techniques and deep learning (DL) algorithms in musculoskeletal imaging have shown great potential for visualizing “pre-OA.” In this review, we first focus on ultrashort echo time-based magnetic resonance imaging (MRI) techniques for direct visualization as well as quantitative morphological and compositional assessment of both short- and long-T2 musculoskeletal tissues, and second explore how DL revolutionize the way of MRI analysis (eg, automatic tissue segmentation and extraction of quantitative image biomarkers) and the classification, prediction, and management of OA.
Plain Language Summary
Detecting osteoarthritis (OA) before the onset of irreversible changes is crucial for early proactive management. OA is heterogeneous and involves structural changes in the whole joint, such as cartilage, meniscus/labrum, ligaments, and tendons, mainly with short T2 relaxation times. Ultrashort echo time-based magnetic resonance imaging (MRI), in particular, enables direct visualization and quantitative compositional assessment of short-T2 tissues. Deep learning is revolutionizing the way of MRI analysis (eg, automatic tissue segmentation and extraction of quantitative image biomarkers) and the detection, classification, and prediction of disease. They together have made further advances toward identification of imaging biomarkers/features for pre-OA.
Level of Evidence
5
Technical Efficacy
Stage 2
References
- 1Perruccio AV, Young JJ, Wilfong JM, Denise Power J, Canizares M, Badley EM. Osteoarthritis year in review 2023: Epidemiology & therapy. Osteoarthr Cartil 2024; 32(2): 159-165.
- 2Primorac D, Molnar V, Rod E, et al. Knee osteoarthritis: A review of pathogenesis and state-of-the-art non-operative therapeutic considerations. Genes (Basel) 2020; 11(8): 854.
- 3Guermazi A, Roemer FW, Haugen IK, Crema MD, Hayashi D. MRI-based semiquantitative scoring of joint pathology in osteoarthritis. Nat Rev Rheumatol 2013; 9(4): 236-251.
- 4Zibetti MVW, Menon RG, de Moura HL, Zhang X, Kijowski R, Regatte RR. Updates on compositional MRI mapping of the cartilage: Emerging techniques and applications. J Magn Reson Imaging 2023; 58(1): 44-60.
- 5Chalian M, Li X, Guermazi A, et al. The QIBA profile for MRI-based compositional imaging of knee cartilage. Radiology 2021; 301(2): 423-432.
- 6Ma Y, Jang H, Jerban S, et al. Making the invisible visible-ultrashort echo time magnetic resonance imaging: Technical developments and applications. Appl Phys Rev 2022; 9(4):041303.
- 7Chu CR, Williams AA, Erhart-Hledik JC, Titchenal MR, Qian Y, Andriacchi TP. Visualizing pre-osteoarthritis: Integrating MRI UTE-T2* with mechanics and biology to combat osteoarthritis—The 2019 Elizabeth Winston Lanier Kappa Delta Award. J Orthop Res 2021; 39(8): 1585-1595.
- 8Chang EY, Du J, Chung CB. UTE imaging in the musculoskeletal system. J Magn Reson Imaging 2015; 41(4): 870-883.
- 9Caliva F, Namiri NK, Dubreuil M, Pedoia V, Ozhinsky E, Majumdar S. Studying osteoarthritis with artificial intelligence applied to magnetic resonance imaging. Nat Rev Rheumatol 2022; 18(2): 112-121.
- 10Mazurowski MA, Buda M, Saha A, Bashir MR. Deep learning in radiology: An overview of the concepts and a survey of the state of the art with focus on MRI. J Magn Reson Imaging 2019; 49(4): 939-954.
- 11Ebrahimkhani S, Jaward MH, Cicuttini FM, Dharmaratne A, Wang Y, de Herrera AGS. A review on segmentation of knee articular cartilage: From conventional methods towards deep learning. Artif Intell Med 2020; 106:101851.
- 12Xue YP, Jang H, Byra M, et al. Automated cartilage segmentation and quantification using 3D ultrashort echo time (UTE) cones MR imaging with deep convolutional neural networks. Eur Radiol 2021; 31(10): 7653-7663.
- 13Desai AD, Caliva F, Iriondo C, et al. The international workshop on osteoarthritis imaging knee MRI segmentation challenge: A multi-institute evaluation and analysis framework on a standardized dataset. Radiol Artif Intell 2021; 3(3):e200078.
- 14Bergin CJ, Pauly JM, Macovski A. Lung parenchyma: Projection reconstruction MR imaging. Radiology 1991; 179(3): 777-781.
- 15Afsahi AM, Sedaghat S, Moazamian D, et al. Articular cartilage assessment using ultrashort echo time MRI: A review. Front Endocrinol (Lausanne) 2022; 13:892961.
- 16Cui L, McWalter EJ, Moran G, Venugopal N. Design and development of a novel flexible ultra-short echo time (FUSE) sequence. Magn Reson Med 2023; 90(5): 1905-1918.
- 17Newbould RD, Miller SR, Toms LD, et al. T2* measurement of the knee articular cartilage in osteoarthritis at 3T. J Magn Reson Imaging 2012; 35(6): 1422-1429.
- 18Li G, Yin J, Gao J, et al. Subchondral bone in osteoarthritis: Insight into risk factors and microstructural changes. Arthritis Res Ther 2013; 15(6): 223.
- 19Du J, Takahashi AM, Bae WC, Chung CB, Bydder GM. Dual inversion recovery, ultrashort echo time (DIR UTE) imaging: Creating high contrast for short-T2 species. Magn Reson Med 2010; 63(2): 447-455.
- 20Bae WC, Dwek JR, Znamirowski R, et al. Ultrashort echo time MR imaging of osteochondral junction of the knee at 3 T: Identification of anatomic structures contributing to signal intensity. Radiology 2010; 254(3): 837-845.
- 21Wang H, Li Z, Li Q, et al. Comparing the effect of mechanical loading on deep and superficial cartilage using quantitative UTE MRI. J Magn Reson Imaging 2024; 59(6): 2048-2057.
- 22Foreman SC, Ashmeik W, Baal JD, et al. Patients with type 2 diabetes exhibit a more mineralized deep cartilage layer compared with nondiabetic controls: A pilot study. Cartilage 2021; 13(1_suppl): 428S-436S.
- 23Wong TT, Quarterman P, Lynch TS, Rasiej MJ, Jaramillo D, Jambawalikar SR. Feasibility of ultrashort echo time (UTE) T2* cartilage mapping in the hip: A pilot study. Acta Radiol 2021; 63(6): 760-766.
- 24Mohtadi NG, Chan DS. Return to sport-specific performance after primary anterior cruciate ligament reconstruction: A systematic review. Am J Sports Med 2018; 46(13): 3307-3316.
- 25Warth RJ, Zandiyeh P, Rao M, et al. Quantitative assessment of in vivo human anterior cruciate ligament autograft remodeling: A 3-dimensional UTE-T2* imaging study. Am J Sports Med 2020; 48(12): 2939-2947.
- 26DePhillipo NN, Cinque ME, Godin JA, Moatshe G, Chahla J, LaPrade RF. Posterior tibial translation measurements on magnetic resonance imaging improve diagnostic sensitivity for chronic posterior cruciate ligament injuries and graft tears. Am J Sports Med 2018; 46(2): 341-347.
- 27Wilms LM, Radke KL, Latz D, et al. UTE-T2* versus conventional T2* mapping to assess posterior cruciate ligament ultrastructure and integrity-an in-situ study. Quant Imaging Med Surg 2022; 12(8): 4190-4201.
- 28Drew BT, Smith TO, Littlewood C, Sturrock B. Do structural changes (eg, collagen/matrix) explain the response to therapeutic exercises in tendinopathy: A systematic review. Br J Sports Med 2014; 48(12): 966-972.
- 29Breda SJ, de Vos RJ, Poot DHJ, Krestin GP, Hernandez-Tamames JA, Oei EHG. Association between T(2)(*) relaxation times derived from ultrashort Echo time MRI and symptoms during exercise therapy for patellar tendinopathy: A large prospective study. J Magn Reson Imaging 2021; 54(5): 1596-1605.
- 30Shao H, Pauli C, Li S, et al. Magic angle effect plays a major role in both T1rho and T2 relaxation in articular cartilage. Osteoarthr Cartil 2017; 25(12): 2022-2030.
- 31Wu Z, Zaylor W, Sommer S, et al. Assessment of ultrashort echo time (UTE) T(2)* mapping at 3T for the whole knee: Repeatability, the effects of fat suppression, and knee position. Quant Imaging Med Surg 2023; 13(12): 7893-7909.
- 32Yang Z, Xie C, Ou S, Zhao M, Lin Z. Cutoff points of T1 rho/T2 mapping relaxation times distinguishing early-stage and advanced osteoarthritis. Arch Med Sci 2022; 18(4): 1004-1015.
- 33Nebelung S, Sondern B, Jahr H, et al. Non-invasive T1ρ mapping of the human cartilage response to loading and unloading. Osteoarthr Cartil 2018; 26(2): 236-244.
- 34Wu M, Ma YJ, Kasibhatla A, et al. Convincing evidence for magic angle less-sensitive quantitative T(1rho) imaging of articular cartilage using the 3D ultrashort echo time cones adiabatic T(1rho) (3D UTE cones-AdiabT(1rho)) sequence. Magn Reson Med 2020; 84(5): 2551-2560.
- 35Ma Y, Carl M, Tang Q, et al. Whole knee joint mapping using a phase modulated UTE adiabatic T1ρ (PM-UTE-AdiabT) sequence. Magn Reson Med 2024; 91(3): 896-910.
- 36Wu M, Ma YJ, Liu M, et al. Quantitative assessment of articular cartilage degeneration using 3D ultrashort echo time cones adiabatic T(1rho) (3D UTE-cones-AdiabT(1rho)) imaging. Eur Radiol 2022; 32(9): 6178-6186.
- 37Namiranian B, Jerban S, Ma Y, et al. Assessment of mechanical properties of articular cartilage with quantitative three-dimensional ultrashort echo time (UTE) cones magnetic resonance imaging. J Biomech 2020; 113:110085.
- 38Jerban S, Afsahi AM, Ma Y, et al. Correlations between elastic modulus and ultrashort echo time (UTE) adiabatic T1rho relaxation time (UTE-Adiab-T1rho) in Achilles tendons and entheses. J Biomech 2023; 160:111825.
- 39Wei Z, Lombardi AF, Lee RR, et al. Comprehensive assessment of in vivo lumbar spine intervertebral discs using a 3D adiabatic T(1ρ) prepared ultrashort echo time (UTE-Adiab-T(1ρ)) pulse sequence. Quant Imaging Med Surg 2022; 12(1): 269-280.
- 40Henkelman RM, Stanisz GJ, Graham SJ. Magnetization transfer in MRI: A review. NMR Biomed 2001; 14(2): 57-64.
- 41Feuerriegel GC, Marth AA, Goller SS, Hilbe M, Sommer S, Sutter R. Quantifying tendon degeneration using magic angle insensitive ultra-short Echo time magnetization transfer: A phantom study in bovine tendons. Invest Radiol 2024; 59(10): 691-698.
- 42Guo T, Song Y, Tong J, et al. Collagen degradation assessment with an in vitro rotator cuff tendinopathy model using multiparametric ultrashort-TE magnetization transfer (UTE-MT) imaging. Magn Reson Med 2024; 92(4): 1658-1669.
- 43Yarnykh VL. Fast macromolecular proton fraction mapping from a single off-resonance magnetization transfer measurement. Magn Reson Med 2012; 68(1): 166-178.
- 44Ma YJ, Chang EY, Carl M, Du J. Quantitative magnetization transfer ultrashort echo time imaging using a time-efficient 3D multispoke cones sequence. Magn Reson Med 2018; 79(2): 692-700.
- 45Xue YP, Ma YJ, Wu M, et al. Quantitative 3D ultrashort echo time magnetization transfer imaging for evaluation of knee cartilage degeneration in vivo. J Magn Reson Imaging 2021; 54(4): 1294-1302.
- 46Zhang X, Ma YJ, Wei Z, et al. Macromolecular fraction (MMF) from 3D ultrashort echo time cones magnetization transfer (3D UTE-cones-MT) imaging predicts meniscal degeneration and knee osteoarthritis. Osteoarthr Cartil 2021; 29(8): 1173-1180.
- 47Zhu D, Wu W, Yu W, et al. Ultrashort echo time magnetization transfer imaging of knee cartilage and meniscus after long-distance running. Eur Radiol 2023; 33(7): 4842-4854.
- 48Fang Y, Zhu D, Wu W, Yu W, Li S, Ma YJ. Assessment of Achilles tendon changes after Long-distance running using ultrashort Echo time magnetization transfer MR imaging. J Magn Reson Imaging 2022; 56(3): 814-823.
- 49Moazamian D, Athertya JS, Dwek S, et al. Achilles tendon and enthesis assessment using ultrashort echo time magnetic resonance imaging (UTE-MRI) T1 and magnetization transfer (MT) modeling in psoriatic arthritis. NMR Biomed 2024; 37(1):e5040.
- 50Li Y, Liang X, Liu J, Ma Y. Assessment of osteoporosis at the lumbar spine using ultrashort Echo time magnetization transfer (UTE-MT) MRI. J Magn Reson Imaging 2024; 59(4): 1285-1298.
- 51Vinogradov E, Sherry AD, Lenkinski RE. CEST: From basic principles to applications, challenges and opportunities. J Magn Reson 2013; 229: 155-172.
- 52Longo DL, Sun PZ, Consolino L, Michelotti FC, Uggeri F, Aime S. A general MRI-CEST ratiometric approach for pH imaging: Demonstration of in vivo pH mapping with iobitridol. J Am Chem Soc 2014; 136(41): 14333-14336.
- 53Chen LQ, Howison CM, Jeffery JJ, Robey IF, Kuo PH, Pagel MD. Evaluations of extracellular pH within in vivo tumors using acidoCEST MRI. Magn Reson Med 2014; 72(5): 1408-1417.
- 54Lombardi AF, Wong JH, High R, et al. AcidoCEST MRI evaluates the bone microenvironment in multiple myeloma. Mol Imaging Biol 2021; 23(6): 865-873.
- 55Abdelhamid RE, Sluka KA. ASICs mediate pain and inflammation in musculoskeletal diseases. Physiology (Bethesda) 2015; 30(6): 449-459.
- 56Ma YJ, High RA, Tang Q, et al. AcidoCEST-UTE MRI for the assessment of extracellular pH of joint tissues at 3 T. Invest Radiol 2019; 54(9): 565-571.
- 57High RA, Ji Y, Ma YJ, et al. In vivo assessment of extracellular pH of joint tissues using acidoCEST-UTE MRI. Quant Imaging Med Surg 2019; 9(10): 1664-1673.
- 58Lombardi AF, Ma Y, Jang H, et al. AcidoCEST-UTE MRI reveals an acidic microenvironment in knee osteoarthritis. Int J Mol Sci 2022; 23(8): 4466.
- 59Su X, Wang Y, Chen J, Liang Z, Wan L, Tang G. A feasibility study of in vivo quantitative ultra-short echo time-MRI for detecting early cartilage degeneration. Insights Imaging 2024; 15(1): 162.
- 60Shao H, Yang J, Ma Y, et al. Evaluation of cartilage degeneration using multiparametric quantitative ultrashort echo time-based MRI: An ex vivo study. Quant Imaging Med Surg 2022; 12(3): 1738-1749.
- 61Wan L, Cheng X, Searleman AC, et al. Evaluation of enzymatic proteoglycan loss and collagen degradation in human articular cartilage using ultrashort echo time-based biomarkers: A feasibility study. NMR Biomed 2022; 35(5):e4664.
- 62Kaggie JD, Markides H, Graves MJ, et al. Ultra short Echo time MRI of iron-labelled mesenchymal stem cells in an ovine osteochondral defect model. Sci Rep 2020; 10(1): 8451.
- 63Bydder M, Carl M, Bydder GM, Du J. MRI chemical shift artifact produced by center-out radial sampling of k-space: A potential pitfall in clinical diagnosis. Quant Imaging Med Surg 2021; 11(8): 3677-3683.
- 64Kronthaler S, Rahmer J, Börnert P, et al. Trajectory correction based on the gradient impulse response function improves high-resolution UTE imaging of the musculoskeletal system. Magn Reson Med 2021; 85(4): 2001-2015.
- 65Gurney PT, Hargreaves BA, Nishimura DG. Design and analysis of a practical 3D cones trajectory. Magn Reson Med 2006; 55(3): 575-582.
- 66Athertya JS, Ma Y, Masoud Afsahi A, et al. Accelerated quantitative 3D UTE-cones imaging using compressed sensing. Sensors (Basel) 2022; 22(19): 7459.
- 67Shen D, Wu G, Suk HI. Deep learning in medical image analysis. Annu Rev Biomed Eng 2017; 19: 221-248.
- 68Jia H, Zhang J, Ma K, Qiao X, Ren L, Shi X. Application of convolutional neural networks in medical images: A bibliometric analysis. Quant Imaging Med Surg 2024; 14(5): 3501-3518.
- 69Van Eetvelde H, Mendonca LD, Ley C, Seil R, Tischer T. Machine learning methods in sport injury prediction and prevention: A systematic review. J Exp Orthop 2021; 8(1): 27.
- 70Long H, Liu Q, Yin H, et al. Prevalence trends of site-specific osteoarthritis from 1990 to 2019: Findings from the global burden of disease study 2019. Arthritis Rheumatol 2022; 74(7): 1172-1183.
- 71Zhao H, Ou L, Zhang Z, Zhang L, Liu K, Kuang J. The value of deep learning-based X-ray techniques in detecting and classifying K-L grades of knee osteoarthritis: A systematic review and meta-analysis. Eur Radiol 2025; 35(1): 327-340.
- 72Martel-Pelletier J, Paiement P, Pelletier JP. Magnetic resonance imaging assessments for knee segmentation and their use in combination with machine/deep learning as predictors of early osteoarthritis diagnosis and prognosis. Ther Adv Musculoskelet Dis 2023; 15:1759720x231165560.
- 73Ratna HVK, Jeyaraman M, Jeyaraman N, et al. Machine learning and deep neural network-based learning in osteoarthritis knee. World J Methodol 2023; 13(5): 419-425.
- 74Norman B, Pedoia V, Majumdar S. Use of 2D U-net convolutional neural networks for automated cartilage and meniscus segmentation of knee MR imaging data to determine relaxometry and morphometry. Radiology 2018; 288(1): 177-185.
- 75Ambellan F, Tack A, Ehlke M, Zachow S. Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: Data from the Osteoarthritis Initiative. Med Image Anal 2019; 52: 109-118.
- 76Liu F. SUSAN: Segment unannotated image structure using adversarial network. Magn Reson Med 2019; 81(5): 3330-3345.
- 77Stammberger T, Eckstein F, Michaelis M, Englmeier KH, Reiser M. Interobserver reproducibility of quantitative cartilage measurements: Comparison of B-spline snakes and manual segmentation. Magn Reson Imaging 1999; 17(7): 1033-1042.
- 78Renard F, Guedria S, Palma N, Vuillerme N. Variability and reproducibility in deep learning for medical image segmentation. Sci Rep 2020; 10(1): 13724.
- 79Chadoulos C, Tsaopoulos D, Symeonidis A, Moustakidis S, Theocharis J. Dense multi-scale graph convolutional network for knee joint cartilage segmentation. Bioengineering (Basel) 2024; 11(3): 278.
- 80Brui E, Efimtcev AY, Fokin VA, et al. Deep learning-based fully automatic segmentation of wrist cartilage in MR images. NMR Biomed 2020; 33(8):e4320.
- 81Schmidt AM, Desai AD, Watkins LE, et al. Generalizability of deep learning segmentation algorithms for automated assessment of cartilage morphology and MRI relaxometry. J Magn Reson Imaging 2023; 57(4): 1029-1039.
- 82Yang M, Colak C, Chundru KK, et al. Automated knee cartilage segmentation for heterogeneous clinical MRI using generative adversarial networks with transfer learning. Quant Imaging Med Surg 2022; 12(5): 2620-2633.
- 83Si L, Xuan K, Zhong J, et al. Knee cartilage thickness differs alongside ages: A 3-T magnetic resonance research upon 2,481 subjects via deep learning. Front Med (Lausanne) 2020; 7:600049.
- 84Luo P, Lu L, Xu R, Jiang L, Li G. Gaining insight into updated MR imaging for quantitative assessment of cartilage injury in knee osteoarthritis. Curr Rheumatol Rep 2024; 26(9): 311-320.
- 85Thomas KA, Krzeminski D, Kidzinski L, et al. Open source software for automatic subregional assessment of knee cartilage degradation using quantitative T2 relaxometry and deep learning. Cartilage 2021; 13(1_suppl): 747S-756S.
- 86Zhang Q, Geng J, Zhang M, et al. Cartilage morphometry and magnetic susceptibility measurement for knee osteoarthritis with automatic cartilage segmentation. Quant Imaging Med Surg 2023; 13(6): 3508-3521.
- 87Tang X, Guo D, Liu A, et al. Fully automatic knee joint segmentation and quantitative analysis for osteoarthritis from magnetic resonance (MR) images using a deep learning model. Med Sci Monit 2022; 28:e936733.
- 88Byra M, Wu M, Zhang X, et al. Knee menisci segmentation and relaxometry of 3D ultrashort echo time cones MR imaging using attention U-net with transfer learning. Magn Reson Med 2020; 83(3): 1109-1122.
- 89Jiang K, Xie Y, Zhang X, et al. Fully and weakly supervised deep learning for meniscal injury classification, and location based on MRI. J Imaging Inform Med 2024.
- 90Deng Y, You L, Wang Y, Zhou X. A coarse-to-fine framework for automated knee bone and cartilage segmentation data from the Osteoarthritis Initiative. J Digit Imaging 2021; 34(4): 833-840.
- 91Awan MJ, Rahim MSM, Salim N, Rehman A, Garcia-Zapirain B. Automated knee MR images segmentation of anterior cruciate ligament tears. Sensors (Basel) 2022; 22(4): 1552.
- 92Kemnitz J, Baumgartner CF, Eckstein F, et al. Clinical evaluation of fully automated thigh muscle and adipose tissue segmentation using a U-net deep learning architecture in context of osteoarthritic knee pain. MAGMA 2020; 33(4): 483-493.
- 93Roach KE, Bird AL, Pedoia V, Majumdar S, Souza RB. Automated evaluation of hip abductor muscle quality and size in hip osteoarthritis: Localized muscle regions are strongly associated with overall muscle quality. Magn Reson Imaging 2024; 111: 237-245.
- 94Cheng R, Alexandridi NA, Smith RM, et al. Fully automated patellofemoral MRI segmentation using holistically nested networks: Implications for evaluating patellofemoral osteoarthritis, pain, injury, pathology, and adolescent development. Magn Reson Med 2020; 83(1): 139-153.
- 95Ponnusamy R, Zhang M, Wang Y, et al. Automatic segmentation of bone marrow lesions on MRI using a deep learning method. Bioengineering (Basel) 2024; 11(4): 374.
- 96Peng Y, Zheng H, Liang P, et al. KCB-net: A 3D knee cartilage and bone segmentation network via sparse annotation. Med Image Anal 2022; 82:102574.
- 97Latif MHA, Faye I. Automated tibiofemoral joint segmentation based on deeply supervised 2D-3D ensemble U-net: Data from the Osteoarthritis Initiative. Artif Intell Med 2021; 122:102213.
- 98Zhong J, Yao Y, Cahill DG, et al. Unsupervised domain adaptation for automated knee osteoarthritis phenotype classification. Quant Imaging Med Surg 2023; 13(11): 7444-7458.
- 99Tibrewala R, Ozhinsky E, Shah R, et al. Computer-aided detection AI reduces interreader variability in grading hip abnormalities with MRI. J Magn Reson Imaging 2020; 52(4): 1163-1172.
- 100Chang GH, Felson DT, Qiu S, Guermazi A, Capellini TD, Kolachalama VB. Assessment of knee pain from MR imaging using a convolutional Siamese network. Eur Radiol 2020; 30(6): 3538-3548.
- 101Joseph GB, McCulloch CE, Nevitt MC, Link TM, Sohn JH. Machine learning to predict incident radiographic knee osteoarthritis over 8 years using combined MR imaging features, demographics, and clinical factors: Data from the Osteoarthritis Initiative. Osteoarthr Cartil 2022; 30(2): 270-279.
- 102Schiratti JB, Dubois R, Herent P, et al. A deep learning method for predicting knee osteoarthritis radiographic progression from MRI. Arthritis Res Ther 2021; 23(1): 262.
- 103Hu J, Zheng C, Yu Q, et al. DeepKOA: A deep-learning model for predicting progression in knee osteoarthritis using multimodal magnetic resonance images from the osteoarthritis initiative. Quant Imaging Med Surg 2023; 13(8): 4852-4866.
- 104Hu J, Peng J, Zhou Z, et al. Associating knee osteoarthritis progression with temporal-regional graph convolutional network analysis on MR images. J Magn Reson Imaging 2024; 61: 378-391.
- 105Jin P, Lu L, Tang Y, Karniadakis GE. Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness. Neural Netw 2020; 130: 85-99.
- 106Stead WW. Clinical implications and challenges of artificial intelligence and deep learning. JAMA 2018; 320(11): 1107-1108.
- 107Rodriguez-Vila B, Gonzalez-Hospital V, Puertas E, Beunza JJ, Pierce DM. Democratization of deep learning for segmenting cartilage from MRIs of human knees: Application to data from the osteoarthritis initiative. J Orthop Res 2023; 41(8): 1754-1766.
- 108Si L, Zhong J, Huo J, et al. Deep learning in knee imaging: A systematic review utilizing a checklist for artificial intelligence in medical imaging (CLAIM). Eur Radiol 2022; 32(2): 1353-1361.
- 109Howard J, Gugger SJI. fastai: A layered API for deep learning. Information 2020; 11:108.