PMID- 38297322 OWN - NLM STAT- MEDLINE DCOM- 20240202 LR - 20240203 IS - 1749-799X (Electronic) IS - 1749-799X (Linking) VI - 19 IP - 1 DP - 2024 Jan 31 TI - Application of machine learning-based multi-sequence MRI radiomics in diagnosing anterior cruciate ligament tears. PG - 99 LID - 10.1186/s13018-024-04602-5 [doi] LID - 99 AB - OBJECTIVE: To compare the diagnostic power among various machine learning algorithms utilizing multi-sequence magnetic resonance imaging (MRI) radiomics in detecting anterior cruciate ligament (ACL) tears. Additionally, this research aimed to create and validate the optimal diagnostic model. METHODS: In this retrospective analysis, 526 patients were included, comprising 178 individuals with ACL tears and 348 with a normal ACL. Radiomics features were derived from multi-sequence MRI scans, encompassing T1-weighted imaging and proton density (PD)-weighted imaging. The process of selecting the most reliable radiomics features involved using interclass correlation coefficient (ICC) testing, t tests, and the least absolute shrinkage and selection operator (LASSO) technique. After the feature selection process, five machine learning classifiers were created. These classifiers comprised logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), light gradient boosting machine (LightGBM), and multilayer perceptron (MLP). A thorough performance evaluation was carried out, utilizing diverse metrics like the area under the receiver operating characteristic curve (ROC), specificity, accuracy, sensitivity positive predictive value, and negative predictive value. The classifier exhibiting the best performance was chosen. Subsequently, three models were developed: the PD model, the T1 model, and the combined model, all based on the optimal classifier. The diagnostic performance of these models was assessed by employing AUC values, calibration curves, and decision curve analysis. RESULTS: Out of 2032 features, 48 features were selected. The SVM-based multi-sequence radiomics outperformed all others, achieving AUC values of 0.973 and 0.927, sensitivities of 0.933 and 0.857, and specificities of 0.930 and 0.829, in the training and validation cohorts, respectively. CONCLUSION: The multi-sequence MRI radiomics model, which is based on machine learning, exhibits exceptional performance in diagnosing ACL tears. It provides valuable insights crucial for the diagnosis and treatment of knee joint injuries, serving as an accurate and objective supplementary diagnostic tool for clinical practitioners. CI - (c) 2024. The Author(s). FAU - Cheng, Qi AU - Cheng Q AD - Department of Orthopedic Surgery, The First Affiliated Hospital of Wannan Medical College, Yijishan Hospital, Wuhu, 241001, Anhui, People's Republic of China. FAU - Lin, Haoran AU - Lin H AD - Department of Orthopedic Surgery, The First Affiliated Hospital of Wannan Medical College, Yijishan Hospital, Wuhu, 241001, Anhui, People's Republic of China. FAU - Zhao, Jie AU - Zhao J AD - Department of Orthopedic Surgery, The First Affiliated Hospital of Wannan Medical College, Yijishan Hospital, Wuhu, 241001, Anhui, People's Republic of China. FAU - Lu, Xiao AU - Lu X AD - Department of Orthopedic Surgery, The First Affiliated Hospital of Wannan Medical College, Yijishan Hospital, Wuhu, 241001, Anhui, People's Republic of China. FAU - Wang, Qiang AU - Wang Q AD - Department of Orthopedic Surgery, The First Affiliated Hospital of Wannan Medical College, Yijishan Hospital, Wuhu, 241001, Anhui, People's Republic of China. yjsgjwq@163.com. LA - eng GR - 2022AH040170/Major Project of Scientific Research Project of Provincial Education Department of Anhui Province/ PT - Journal Article DEP - 20240131 PL - England TA - J Orthop Surg Res JT - Journal of orthopaedic surgery and research JID - 101265112 SB - IM MH - Humans MH - Radiomics MH - *Anterior Cruciate Ligament Injuries/diagnostic imaging MH - Retrospective Studies MH - Magnetic Resonance Imaging MH - *Knee Injuries MH - Machine Learning PMC - PMC10829177 OTO - NOTNLM OT - Anterior cruciate ligament tear OT - Machine learning OT - Magnetic resonance imaging OT - Radiomics COIS- The authors declare that they have no conflict of interest. EDAT- 2024/02/01 00:42 MHDA- 2024/02/02 06:43 PMCR- 2024/01/31 CRDT- 2024/01/31 23:45 PHST- 2023/10/29 00:00 [received] PHST- 2024/01/28 00:00 [accepted] PHST- 2024/02/02 06:43 [medline] PHST- 2024/02/01 00:42 [pubmed] PHST- 2024/01/31 23:45 [entrez] PHST- 2024/01/31 00:00 [pmc-release] AID - 10.1186/s13018-024-04602-5 [pii] AID - 4602 [pii] AID - 10.1186/s13018-024-04602-5 [doi] PST - epublish SO - J Orthop Surg Res. 2024 Jan 31;19(1):99. doi: 10.1186/s13018-024-04602-5.