Abstract

Background: Experienced surgeons most commonly utilize Magnetic Resonance Imaging (MRI) to diagnose rotator cuff tear (RCT) and predict the possibility of post-operative re-tear. Radiomics adjuvant therapy is widely used to improve the response prediction of clinical tasks. We validated a classifier to distinguish the status of rotator cuff tear and predict post-operative re-tear by utilizing MRI markers. Methods: We selected 101 patients with no abnormality in rotator cuff and 101 patients undergoing arthroscopic rotator cuff repair diagnosed as RCT by MRI. Radiomics features of RCT were identified from the pre-operative shoulder MRI. A radiomics model for diagnosis of RCT was constructed, based on the 3D volume of interest (VOI) of supraspinatus from 202 patients. Additionally, a model for prediction prognosis was made, based on VOI of humerus, supraspinatus, infraspinatus and other clinical parameters. Findings: The model for diagnosing the status of RCT produced an AUC of 0.989 (95%CI: 0.954-0.999) in the training cohort and 0.979 (95% CI: 0.906-0.999) for the validation cohort. Four highest mRMR-ranked features were selected to construct the RCT model. The MRI signature markers, based on features extracted from the humerus, supraspinatus, and infraspinatus yielded average AUC of 0.662±0.054,0.673±0.089,0.879±0.041 for training sets and 0.600±0.064, 0.673±0.089, 0.739±0.069 for validation sets. The model based on multiple regions of interests produced an AUC of 0.923±0.017 for the training dataset and 0.790±0.082 for the validation dataset. The nomogram combining integrated features and clinical factors yielded an AUC of 0.961±0.020 for the training dataset and 0.808±0.081 for the validation dataset, which displayed the best performance among all models. Interpretation: Our study validated two models for the diagnosis of rotator cuff tear and prediction of post-operative re-tear respectively. The RCT model had a favorable performance in diagnosis, while the combined nomogram based on radiomics score and clinical factors yielded a decent prediction accuracy of re-tear. Both models are anticipated to provide valuable information for clinical decision-making in the future. Funding Statement: This work was supported by the National Natural Science Foundation (81874019). Declaration of Interests: All authors declare that they have no conflicts of interest. Ethics Approval Statement: This retrospective study was approved by the Institutional Review Board of the Second Affiliated Hospital, Zhejiang University School of Medicine (Zhejiang, China). The signed informed consent forms were waived. This study was conducted according to the Declaration of Helsinki.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.