MRI影像组学在膝骨关节炎中的应用
Application of MRI-Based Radiomics in Knee Osteoarthritis
DOI: 10.12677/acm.2026.1662309, PDF,    科研立项经费支持
作者: 王鸿轩, 姬 明, 李荣荣, 高春愿, 袁 慧, 陈海洋*：联勤保障部队临潼康复疗养中心医学影像科，陕西 西安
关键词: 膝关节；骨关节炎；磁共振；影像组学；早期诊断；Knee Joint； Osteoarthritis； Magnetic Resonance Imaging； Radiomics； Early Diagnosis
摘要: 膝关节骨关节炎(Knee Osteoathritis, KOA)是临床常见的慢性退行性关节疾病，传统影像学检查对早期病变敏感性不足，易造成诊断延迟。MRI影像组学可高通量提取医学影像定量特征，结合机器学习算法构建评估模型，客观量化关节组织微观异质性，在KOA早期诊断、病情进展预测、疗效评估及风险分层中展现出重要的应用价值。本文围绕MRI影像组学的基础理论、技术流程、在KOA诊疗中的应用现状、现存挑战及发展前景进行综述，为该技术的临床转化与规范化应用提供参考。
Abstract: Knee osteoarthritis (KOA) is a prevalent chronic degenerative joint disorder in clinical practice. Conventional imaging modalities show inadequate sensitivity for detecting subtle early lesions, which frequently leads to delayed diagnosis and intervention. Magnetic resonance imaging (MRI)-based radiomics enables high-throughput extraction of quantitative features from medical images and allows the construction of predictive models using machine learning algorithms, thereby objectively quantifying the microscopic heterogeneity of articular tissues. This technique has demonstrated significant clinical value in early diagnosis, disease progression prediction, treatment efficacy evaluation, and risk stratification of KOA. The present article systematically reviews the fundamental principles, technical workflows, current application status, existing challenges, and future prospects of MRI-based radiomics in the management of KOA, with the aim of providing theoretical references for the clinical translation and standardized implementation of this technology.
文章引用：王鸿轩, 姬明, 李荣荣, 高春愿, 袁慧, 陈海洋. MRI影像组学在膝骨关节炎中的应用[J]. 临床医学进展, 2026, 16(6): 1043-1048. https://doi.org/10.12677/acm.2026.1662309

参考文献

[1] 王明兴, 田向东, 王枳翌, 等. 1990年至2021年膝关节骨关节炎全球疾病负担分析及至2035年的预测[J]. 国际骨科学杂志, 2026, 47(1): 64-72.
[2] Yoshioka, N.K., Young, G.M., Khajuria, D.K., Karuppagounder, V., Pinamont, W.J., Fanburg-Smith, J.C., et al. (2022) Structural Changes in the Collagen Network of Joint Tissues in Late Stages of Murine OA. Scientific Reports, 12, Article No. 9159. [Google Scholar] [CrossRef] [PubMed]
[3] Onuora, S. (2015) Cartilage Matrix Stiffness Regulates Chondrocyte Metabolism and OA Pathogenesis. Nature Reviews Rheumatology, 11, Article No. 504. [Google Scholar] [CrossRef] [PubMed]
[4] Case, R., Thomas, E., Clarke, E. and Peat, G. (2015) Prodromal Symptoms in Knee Osteoarthritis: A Nested Case-Control Study Using Data from the Osteoarthritis Initiative. Osteoarthritis and Cartilage, 23, 1083-1089. [Google Scholar] [CrossRef] [PubMed]
[5] Gelber, A.C. (2024) Knee Osteoarthritis. Annals of Internal Medicine, 177, ITC129-ITC144. [Google Scholar] [CrossRef] [PubMed]
[6] Lv, W., Peng, J., Hu, J., Lu, Y., Zhou, Z., Xu, H., et al. (2025) LMSST-GCN: Longitudinal MRI Sub-Structural Texture Guided Graph Convolution Network for Improved Progression Prediction of Knee Osteoarthritis. Computer Methods and Programs in Biomedicine, 261, Article ID: 108600. [Google Scholar] [CrossRef] [PubMed]
[7] Xue, Z., Wang, L., Sun, Q., Xu, J., Liu, Y., Ai, S., et al. (2022) Radiomics Analysis Using MR Imaging of Subchondral Bone for Identification of Knee Osteoarthritis. Journal of Orthopaedic Surgery and Research, 17, Article No. 414. [Google Scholar] [CrossRef] [PubMed]
[8] Li, W., Feng, J., Zhu, D., Xiao, Z., Liu, J., Fang, Y., et al. (2023) Nomogram Model Based on Radiomics Signatures and Age to Assist in the Diagnosis of Knee Osteoarthritis. Experimental Gerontology, 171, Article ID: 112031. [Google Scholar] [CrossRef] [PubMed]
[9] Chen, T., Chen, J., Liu, H., Liu, Z., Yu, B., Wang, Y., et al. (2025) Integration of Longitudinal Load-Bearing Tissue MRI Radiomics and Neural Network to Predict Knee Osteoarthritis Incidence. Journal of Orthopaedic Translation, 51, 187-197. [Google Scholar] [CrossRef] [PubMed]
[10] Cui, T., Liu, R., Jing, Y., Fu, J. and Chen, J. (2023) Development of Machine Learning Models Aiming at Knee Osteoarthritis Diagnosing: An MRI Radiomics Analysis. Journal of Orthopaedic Surgery and Research, 18, Article No. 375. [Google Scholar] [CrossRef] [PubMed]
[11] Wang, K., Liu, W.V., Yang, R., Li, L., Lu, X., Lei, H., et al. (2025) Super-Resolution Synthetic MRI Using Deep Learning Reconstruction for Accurate Diagnosis of Knee Osteoarthritis. Insights into Imaging, 16, Article No. 44. [Google Scholar] [CrossRef] [PubMed]
[12] Cheng, K.Y., Moazamian, D., Ma, Y., Jang, H., Jerban, S., Du, J., et al. (2023) Clinical Application of Ultrashort Echo Time (UTE) and Zero Echo Time (ZTE) Magnetic Resonance (MR) Imaging in the Evaluation of Osteoarthritis. Skeletal Radiology, 52, 2149-2157. [Google Scholar] [CrossRef] [PubMed]
[13] Hu, J., Peng, J., Zhou, Z., Zhao, T., Zhong, L., Yu, K., et al. (2024) Associating Knee Osteoarthritis Progression with Temporal-Regional Graph Convolutional Network Analysis on MR Images. Journal of Magnetic Resonance Imaging, 61, 378-391. [Google Scholar] [CrossRef] [PubMed]
[14] Wang, T., Liu, H., Zhao, W., Cao, P., Li, J., Chen, T., et al. (2025) Predicting Knee Osteoarthritis Progression Using Neural Network with Longitudinal MRI Radiomics, and Biochemical Biomarkers: A Modeling Study. PLOS Medicine, 22, e1004665. [Google Scholar] [CrossRef] [PubMed]
[15] Meena, R., Dwivedi, M., Haq, R.U. and Malik, R. (2025) Assessing the Clinical Utility of MRI in Knee Osteoarthritis: Bridging the Gap between Radiographic Findings and Patient Symptoms. Indian Journal of Orthopaedics, 59, 1462-1468. [Google Scholar] [CrossRef] 
[16] Murphy, L.A. and Scanzello, C.R. (2025) Cellular and Molecular Mechanisms Underlying Subchondral Bone Remodeling and Associated Pain in Osteoarthritis. Connective Tissue Research, 66, 435-441. [Google Scholar] [CrossRef] [PubMed]
[17] Pishgar, F., Ashraf-ganjouei, A., Dolatshahi, M., Guermazi, A., Zikria, B., Cao, X., et al. (2022) Conventional MRI-Derived Subchondral Trabecular Biomarkers and Their Association with Knee Cartilage Volume Loss as Early as 1 Year: A Longitudinal Analysis from Osteoarthritis Initiative. Skeletal Radiology, 51, 1959-1966. [Google Scholar] [CrossRef] [PubMed]
[18] Cao, G., Gao, S. and Xiong, B. (2023) Application of Quantitative T1, T2 and T2* Mapping Magnetic Resonance Imaging in Cartilage Degeneration of the Shoulder Joint. Scientific Reports, 13, Article No. 4558. [Google Scholar] [CrossRef] [PubMed]
[19] Collins, J.E., Mesenbrink, P., Jin, R., Dam, E.B., Deveza, L.A., Eckstein, F., et al. (2025) Magnetic Resonance Imaging Biomarkers of Knee Osteoarthritis Progression. ACR Open Rheumatology, 7, e70085. [Google Scholar] [CrossRef] 
[20] Li, S., Cao, P., Li, J., Chen, T., Luo, P., Ruan, G., et al. (2024) Integrating Radiomics and Neural Networks for Knee Osteoarthritis Incidence Prediction. Arthritis & Rheumatology, 76, 1377-1386. [Google Scholar] [CrossRef] [PubMed]
[21] Wei, Y., Qian, H., Zhang, X., Wang, J., Yan, H., Xiao, N., et al. (2025) Progress in Multi-Omics Studies of Osteoarthritis. Biomarker Research, 13, Article No. 26. [Google Scholar] [CrossRef] [PubMed]
[22] Fu, J., Mu, L., Dong, D., Li, M., Miao, Z., Huai, X., et al. (2025) An MRI-Based Radiomics Framework for Early Identification and Progression Stratification in Knee Osteoarthritis: Data from the Osteoarthritis Initiative. BMC Musculoskeletal Disorders, 26, Article No. 1018. [Google Scholar] [CrossRef] 
[23] Attur, M., Krasnokutsky, S., Zhou, H., Samuels, J., Chang, G., Bencardino, J., et al. (2020) The Combination of an Inflammatory Peripheral Blood Gene Expression and Imaging Biomarkers Enhance Prediction of Radiographic Progression in Knee Osteoarthritis. Arthritis Research & Therapy, 22, Article No. 208. [Google Scholar] [CrossRef] [PubMed]
[24] Lin, T., Peng, S., Lu, S., Fu, S., Zeng, D., Li, J., et al. (2023) Prediction of Knee Pain Improvement over Two Years for Knee Osteoarthritis Using a Dynamic Nomogram Based on MRI-Derived Radiomics: A Proof-of-Concept Study. Osteoarthritis and Cartilage, 31, 267-278. [Google Scholar] [CrossRef] [PubMed]
[25] He, Y., Wei, J., Sun, Y., Bao, W., Huang, D., Fan, Y., et al. (2025) A Multimodal Deep Learning Radiomics Model for Predicting Degenerative Meniscus Tear after Arthroscopy. PLOS One, 20, e0328299. [Google Scholar] [CrossRef] [PubMed]
[26] Desai, A.D., Caliva, F., Iriondo, C., Mortazi, A., Jambawalikar, S., Bagci, U., et al. (2021) The International Workshop on Osteoarthritis Imaging Knee MRI Segmentation Challenge: A Multi-Institute Evaluation and Analysis Framework on a Standardized Dataset. Radiology: Artificial Intelligence, 3, e200078. [Google Scholar] [CrossRef] [PubMed]
[27] Felfeliyan, B., Hareendranathan, A., Kuntze, G., Jaremko, J. and Ronsky, J. (2021) MRI Knee Domain Translation for Unsupervised Segmentation by CycleGAN (Data from Osteoarthritis Initiative (OAI)). 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Mexico, 1-5 November 2021, 4052-4055. [Google Scholar] [CrossRef] [PubMed]
[28] Salamah, A.A.S., Láinez Ramos-Bossini, A.J., Khan, K.S. and Ruiz Santiago, F. (2024) Diagnostic Accuracy of Magnetic Resonance Imaging (MRI) for Symptomatic Knee Osteoarthritis: A Scoping Review. Quantitative Imaging in Medicine and Surgery, 14, 8001-8011. [Google Scholar] [CrossRef] [PubMed]
[29] Humayun, A., Rehman, M. and Zainulabideen, M. (2026) Artificial Intelligence in Knee Osteoarthritis Imaging and Total Knee Arthroplasty: Advances, Challenges, and Segmentation Methods—A Review. The Knee, 60, Article ID: 104327. [Google Scholar] [CrossRef] 
[30] Martel-Pelletier, J., Paiement, P. and Pelletier, J. (2023) Magnetic Resonance Imaging Assessments for Knee Segmentation and Their Use in Combination with Machine/Deep Learning as Predictors of Early Osteoarthritis Diagnosis and Prognosis. Therapeutic Advances in Musculoskeletal Disease, 15, 1-39. [Google Scholar] [CrossRef] [PubMed]

为你推荐