TY - JOUR AU - Chen, AU - Yang Kun-Hui AU - Yang, Chih-Yu AU - Wang, hsinyi AU - Ma, xiaoli AU - Lee, Oscar Kuang-Sheng PY - 2022 DA - 2022/7/26 TI -基于磁共振图像的人工智能辅助前交叉韧带撕裂诊断:算法开发和验证研究乔- J AI SP - e37508六世- 1 - 1 KW -人工智能KW -卷积神经网络KW -磁共振成像KW - MRI KW -深度学习KW -前交叉韧带KW -运动医学KW -机器学习KW -韧带KW -运动KW -诊断KW -眼泪千瓦损害KW -成像千瓦发展KW -验证KW -算法AB -背景:前交叉韧带(ACL)损伤在运动中很常见，是严重的膝关节损伤，需要及时诊断。磁共振成像(MRI)是检测前交叉韧带撕裂的一种强大的、非侵入性的工具，需要经过训练才能准确读取。对于前交叉韧带撕裂的诊断，具有不同阅读MR图像经验的临床医生需要不同的信息。人工智能图像处理在前交叉韧带撕裂的诊断中具有广阔的应用前景。目的:本研究寻求使用AI(1)从完整的MR图像中诊断ACL撕裂，(2)从完整的MR图像中识别ACL撕裂诊断，(3)从所选的MR图像中区分完整ACL和撕裂ACL的MR图像。方法:回顾性收集800例ACL撕裂(n=1205)和ACL完整(n=1018)患者的矢状面MR图像，以及200例20-40岁患者的全膝关节MR图像(100例ACL撕裂和100例ACL完整)。一种使用卷积神经网络的人工智能方法被用于为目标建立模型。使用200个独立病例(100个撕裂ACL和100个完整ACL)的MR图像作为模型的测试集。 The MR images of 40 randomly selected cases from the test set were used to compare the reading accuracy of ACL tears between the trained model and clinicians with different levels of experience. Results: The first model differentiated between torn-ACL, intact-ACL, and other images from complete MR images with an accuracy of 0.9946, and the sensitivity, specificity, precision, and F1-score were 0.9344, 0.9743, 0.8659, and 0.8980, respectively. The final accuracy for ACL-tear diagnosis was 0.96. The model showed a significantly higher reading accuracy than less experienced clinicians. The second model identified torn-ACL images from complete MR images with a diagnosis of ACL tear with an accuracy of 0.9943, and the sensitivity, specificity, precision, and F1-score were 0.9154, 0.9660, 0.8167, and 0.8632, respectively. The third model differentiated torn- and intact-ACL images with an accuracy of 0.9691, and the sensitivity, specificity, precision, and F1-score were 0.9827, 0.9519, 0.9632, and 0.9728, respectively. Conclusions: This study demonstrates the feasibility of using an AI approach to provide information to clinicians who need different information from MRI to diagnose ACL tears. UR - https://ai.www.mybigtv.com/2022/1/e37508 UR - https://doi.org/10.2196/37508 DO - 10.2196/37508 ID - info:doi/10.2196/37508 ER -