Diagnosis of triangular fibrocartilage complex injury:based on MRI radiomics
GAO Yue
CHENG Lin
LI Yifan
MA Changdong
HOU Zenghao
WANG Shanshan
Abstract：Objective To explore the clinical application of MRI radiomics in the diagnosis of triangular fibrocartilage complex(TFCC)injuries.Methods This retrospective study enrolled 96(injury/non-injury:62/34)patients who received arthroscopy in Binzhou Medical University Hospital from January 2019 to October 2024.Regions of Interest were delineated on multi-sequence MRI,followed by radiomic feature extraction.The dataset was randomly split into training and test sets at a ratio of 7:3.The best radiomics features were selected by LASSO algorithm,and C-support vector classification(CSVC),Nu-support vector classification(NuSVC),random forest(RF),logistic regression(LR),adaptive boosting(AdaBoost),eXtreme gradient boosting(XGBoost)were used to establish the omics model respectively.The radiomics model was constructed using the optimal algorithm selected by AUC evaluation,while the same algorithm was employed to build the clinical model based on clinical data.Subsequently,both models were combined to develop a Nomogram prediction model.The diagnostic performance was assessed using ROC curve and decision curve analysis,followed by quantitative comparison of core indicators.Results The AUC values for the training and test sets of radiomics models constructed using six algorithms(CSVC,NuSVC,LR,RF,AdaBoost,and XGBoost)were as follows:0.7568 and 0.8355;0.8570 and 0.8421;0.8052 and 0.8092;0.8848 and 0.8026;0.8202 and 0.8224;and 0.7926 and 0.7796,respectively.The clinical model achieved AUCs of 0.6890(training)and 0.7417(testing),compared to 0.9738 and 0.9250 respectively for the Nomogram model.The difference between Nomogram model and clinical model was statistically significant(P<0.05).The AUC of the Nomogram was higher than that of the radiomics model,but the difference was not statistically significant in the test set(P>0.05).Conclusion The radiomics model based on RF algorithm is superior to other algorithms in TFCC damage diagnosis.Compared with the clinical model and the omics model,the Nomogram model showed a more superior diagnostic efficiency in the diagnosis of TFCC injury.
Keywords：MRIradiomicstriangular fibrocartilage complexdiagnosis
Publication Date：2025-07-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 821-826 )