13Aug 2023
Prediction of Retear After Arthroscopic Rotator Cuff Repair Based on Intraoperative Arthroscopic Images Using Deep Learning

Prediction of Retear After Arthroscopic Rotator Cuff Repair Based on Intraoperative Arthroscopic Images Using Deep Learning

This study assessed the potential of using deep learning algorithms to predict retear after arthroscopic rotator cuff repair (ARCR) by analyzing intraoperative images. Images from 580 patients were collected, and three deep learning models (VGG16, DenseNet, Xception) were employed for prediction. The models showed promising results, with DenseNet achieving the highest accuracy (91%) and area under the curve (AUC) of 0.92. Specificity and sensitivity were also notable, indicating the potential for accurate retear prediction. In conclusion, applying deep learning to intraoperative arthroscopic images holds promise for accurately forecasting retear occurrences and enhancing the prognosis assessment of ARCR.

  • #orthopaedics

Like

Save

Share