Wu Kuan-Ting, Chen Po-Cheng, Chou Wen-Yi, Chang Ching-Di, James Lien Jenn-Jier
Department of Orthopedic Surgery, Kaohsiung Chang Gung Memorial Hospital, Graduate Institute of Clinical Medical Science, Chang Gung University College of Medicine, Kaohsiung, Taiwan; Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan; Department of Sports, Health and Leisure and Graduate Institute of Sports, Health and Leisure, Cheng Shiu University, Kaohsiung, Taiwan; Kaohsiung Municipal Fong Shan Hospital - Under the Management of Chang Gung Medical Foundation, Kaohsiung, Taiwan.
Kaohsiung Municipal Fong Shan Hospital - Under the Management of Chang Gung Medical Foundation, Kaohsiung, Taiwan; Department of Physical Medicine and Rehabilitation, Kaohsiung Chang Gung Memorial Hospital, Graduate Institute of Clinical Medical Science, Chang Gung University College of Medicine, Kaohsiung, Taiwan; Kaohsiung Municipal Ta-Tung Hospital, Kaohsiung, Taiwan.
Arthroscopy. 2024 Dec 25. doi: 10.1016/j.arthro.2024.12.024.
To improve the accuracy of 1-stage object detection by modifying the YOLOv7 with the convolutional block attention module (CBAM), known as YOLOv7-CBAM, which can automatically identify torn or intact rotator cuff tendon to assist physicians in diagnosing rotator cuff lesions through ultrasound.
Between 2020 and 2021, patients who experienced shoulder pain for over 3 months and had both ultrasound and magnetic resonance imaging examinations were categorized into torn and intact groups. To ensure balanced training, we included the same number of patients in both groups. Transfer learning was conducted using a pretrained model of YOLOv7 and an improved model with CBAM. The mean average precision, sensitivity, and F1-score were calculated to evaluate the models. A gradient-weighted class activation mapping method was employed to visualize important regions using a heatmap. A simulation data set was recruited to evaluate the diagnostic performance of clinical physicians using our artificial intelligence-assisted model.
A total of 280 patients were included in this study, with 80% of 840 ultrasound images randomly allocated for model training. The accuracy for the test set was 0.96 for YOLOv7 and 0.98 for YOLOv7-CBAM, and the precision and sensitivity were 0.94 and 0.98 for YOLOv7 and 0.98 and 0.98 for YOLOv7-CBAM. F1-score and mean average precision were higher for YOLOv7-CBAM (0.980 and 0.993) than YOLOv7 (0.961 and 0.965). Furthermore, the gradient-weighted class activation mapping method elucidated that the deep learning model primarily emphasized a hypoechoic anechoic defect within the tendon. Following adopting an artificial intelligence-assisted model (YOLOv7-CBAM model), diagnostic accuracy improved from 80.86% to 88.86% (P = .01), and interobserver reliability improved from 0.49 to 0.71 among physicians.
The YOLOv7-CBAM model shows high accuracy in detecting torn or intact rotator cuff tendon from ultrasound images. Integrating this model into the diagnostic process can assist physicians in improving diagnostic accuracy and interobserver reliability across different physicians.
The attentional deep learning model aids physicians in improving the accuracy and consistency of ultrasound diagnosis of torn or intact rotator cuff tendons.
通过使用卷积块注意力模块（CBAM）对YOLOv7进行改进，即YOLOv7-CBAM，以提高单阶段目标检测的准确性，该模型能够自动识别撕裂或完整的肩袖肌腱，通过超声辅助医生诊断肩袖损伤。
在2020年至2021年期间，将肩部疼痛超过3个月且同时接受超声和磁共振成像检查的患者分为撕裂组和完整组。为确保训练平衡，两组纳入相同数量的患者。使用YOLOv7的预训练模型和带有CBAM的改进模型进行迁移学习。计算平均精度、灵敏度和F1分数以评估模型。采用梯度加权类激活映射方法，使用热图可视化重要区域。招募模拟数据集以评估临床医生使用我们的人工智能辅助模型的诊断性能。
本研究共纳入280例患者，840张超声图像中的80%被随机分配用于模型训练。YOLOv7对测试集的准确率为0.96，YOLOv7-CBAM为0.98；YOLOv7的精确率和灵敏度分别为0.94和0.98，YOLOv7-CBAM为0.98和0.98。YOLOv7-CBAM的F1分数和平均精度（分别为0.980和0.993）高于YOLOv7（分别为0.961和0.965）。此外，梯度加权类激活映射方法表明深度学习模型主要强调肌腱内的低回声无回声缺陷。采用人工智能辅助模型（YOLOv7-CBAM模型）后，医生的诊断准确率从80.86%提高到88.86%（P = 0.01），观察者间可靠性从0.49提高到0.71。
YOLOv7-CBAM模型在从超声图像中检测撕裂或完整的肩袖肌腱方面显示出高准确率。将该模型整合到诊断过程中可帮助医生提高不同医生之间的诊断准确率和观察者间可靠性。
注意力深度学习模型有助于医生提高超声诊断撕裂或完整肩袖肌腱的准确性和一致性。
