Performance of artificial intelligence in automated measurement of patellofemoral joint parameters: a systematic review.

IF 2.8 3区医学 Q1 ORTHOPEDICS

Journal of Orthopaedic Surgery and Research Pub Date : 2025-09-26 DOI:10.1186/s13018-025-06247-4

Hongwei Zhan, Zandong Zhao, Qiuzhen Liang, Jiang Zheng, Liang Zhang

{"title":"Performance of artificial intelligence in automated measurement of patellofemoral joint parameters: a systematic review.","authors":"Hongwei Zhan, Zandong Zhao, Qiuzhen Liang, Jiang Zheng, Liang Zhang","doi":"10.1186/s13018-025-06247-4","DOIUrl":null,"url":null,"abstract":"Background: The evaluation of patellofemoral joint parameters is essential for diagnosing patellar dislocation, yet manual measurements exhibit poor reproducibility and demonstrate significant variability dependent on clinician expertise. This systematic review aimed to evaluate the performance of artificial intelligence (AI) models in automatically measuring patellofemoral joint parameters.Methods: A comprehensive literature search of PubMed, Web of Science, Cochrane Library, and Embase databases was conducted from database inception through June 15, 2025. Two investigators independently performed study screening and data extraction, with methodological quality assessment based on the modified MINORS checklist. This systematic review is registered with PROSPERO. A narrative review was conducted to summarize the findings of the included studies.Results: A total of 19 studies comprising 10,490 patients met the inclusion and exclusion criteria, with a mean age of 51.3 years and a mean female proportion of 56.8%. Among these, six studies developed AI models based on radiographic series, nine on CT imaging, and four on MRI. The results demonstrated excellent reliability, with intraclass correlation coefficients (ICCs) ranging from 0.900 to 0.940 for femoral anteversion angle, 0.910-0.920 for trochlear groove depth and 0.930-0.950 for tibial tuberosity-trochlear groove distance. Additionally, good reliability was observed for patellar height (ICCs: 0.880-0.985), sulcus angle (ICCs: 0.878-0.980), and patellar tilt angle (ICCs: 0.790-0.990). Notably, the AI system successfully detected trochlear dysplasia, achieving 88% accuracy, 79% sensitivity, 96% specificity, and an AUC of 0.88.Conclusion: AI-based measurement of patellofemoral joint parameters demonstrates methodological robustness and operational efficiency, showing strong agreement with expert manual measurements. To further establish clinical utility, multicenter prospective studies incorporating rigorous external validation protocols are needed. Such validation would strengthen the model's generalizability and facilitate its integration into clinical decision support systems.Systematic review registration: This systematic review was registered in PROSPERO (CRD420251075068).","PeriodicalId":16629,"journal":{"name":"Journal of Orthopaedic Surgery and Research","volume":"20 1","pages":"847"},"PeriodicalIF":2.8000,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12465275/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Orthopaedic Surgery and Research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s13018-025-06247-4","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ORTHOPEDICS","Score":null,"Total":0}

引用次数: 0

Abstract

Background: The evaluation of patellofemoral joint parameters is essential for diagnosing patellar dislocation, yet manual measurements exhibit poor reproducibility and demonstrate significant variability dependent on clinician expertise. This systematic review aimed to evaluate the performance of artificial intelligence (AI) models in automatically measuring patellofemoral joint parameters.

Methods: A comprehensive literature search of PubMed, Web of Science, Cochrane Library, and Embase databases was conducted from database inception through June 15, 2025. Two investigators independently performed study screening and data extraction, with methodological quality assessment based on the modified MINORS checklist. This systematic review is registered with PROSPERO. A narrative review was conducted to summarize the findings of the included studies.

Results: A total of 19 studies comprising 10,490 patients met the inclusion and exclusion criteria, with a mean age of 51.3 years and a mean female proportion of 56.8%. Among these, six studies developed AI models based on radiographic series, nine on CT imaging, and four on MRI. The results demonstrated excellent reliability, with intraclass correlation coefficients (ICCs) ranging from 0.900 to 0.940 for femoral anteversion angle, 0.910-0.920 for trochlear groove depth and 0.930-0.950 for tibial tuberosity-trochlear groove distance. Additionally, good reliability was observed for patellar height (ICCs: 0.880-0.985), sulcus angle (ICCs: 0.878-0.980), and patellar tilt angle (ICCs: 0.790-0.990). Notably, the AI system successfully detected trochlear dysplasia, achieving 88% accuracy, 79% sensitivity, 96% specificity, and an AUC of 0.88.

Conclusion: AI-based measurement of patellofemoral joint parameters demonstrates methodological robustness and operational efficiency, showing strong agreement with expert manual measurements. To further establish clinical utility, multicenter prospective studies incorporating rigorous external validation protocols are needed. Such validation would strengthen the model's generalizability and facilitate its integration into clinical decision support systems.

Systematic review registration: This systematic review was registered in PROSPERO (CRD420251075068).

查看原文本刊更多论文

人工智能在髌股关节参数自动测量中的应用：系统综述。

背景：髌股关节参数的评估对于诊断髌骨脱位至关重要，但人工测量的可重复性较差，并表现出依赖于临床医生专业知识的显著差异。本系统综述旨在评估人工智能（AI）模型在自动测量髌骨股骨关节参数方面的性能。方法：对PubMed、Web of Science、Cochrane Library和Embase数据库从建库到2025年6月15日进行综合文献检索。两名研究者独立进行研究筛选和数据提取，并根据修改后的未成年人检查表进行方法学质量评估。本系统综述已在普洛斯彼罗注册。进行叙述性回顾，以总结纳入研究的结果。结果：共有19项研究10490例患者符合纳入和排除标准，平均年龄51.3岁，平均女性比例56.8%。其中，6项研究开发了基于放射影像序列的人工智能模型，9项研究开发了基于CT成像的人工智能模型，4项研究开发了基于MRI的人工智能模型。结果具有良好的可靠性，股骨前倾角的类内相关系数（ICCs）为0.900 ~ 0.940，滑车沟深度为0.910 ~ 0.920，胫骨结节-滑车沟距离为0.930 ~ 0.950。此外，髌骨高度（ICCs: 0.880-0.985）、沟角（ICCs: 0.878-0.980）和髌骨倾斜角（ICCs: 0.790-0.990）的可靠性良好。值得注意的是，人工智能系统成功检测出滑车发育不良，准确率达到88%，灵敏度为79%，特异性为96%，AUC为0.88。结论：基于人工智能的髌股关节参数测量具有方法稳健性和操作效率，与专家手动测量结果高度一致。为了进一步建立临床应用，需要采用严格的外部验证方案的多中心前瞻性研究。这样的验证将加强模型的普遍性，并促进其整合到临床决策支持系统。系统评价注册：该系统评价在PROSPERO注册（CRD420251075068）。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Orthopaedic Surgery and Research ORTHOPEDICS-

CiteScore

4.10

自引率

7.70%

发文量

494

审稿时长

>12 weeks

期刊介绍： Journal of Orthopaedic Surgery and Research is an open access journal that encompasses all aspects of clinical and basic research studies related to musculoskeletal issues. Orthopaedic research is conducted at clinical and basic science levels. With the advancement of new technologies and the increasing expectation and demand from doctors and patients, we are witnessing an enormous growth in clinical orthopaedic research, particularly in the fields of traumatology, spinal surgery, joint replacement, sports medicine, musculoskeletal tumour management, hand microsurgery, foot and ankle surgery, paediatric orthopaedic, and orthopaedic rehabilitation. The involvement of basic science ranges from molecular, cellular, structural and functional perspectives to tissue engineering, gait analysis, automation and robotic surgery. Implant and biomaterial designs are new disciplines that complement clinical applications. JOSR encourages the publication of multidisciplinary research with collaboration amongst clinicians and scientists from different disciplines, which will be the trend in the coming decades.