METHODS: For intelligent diagnosis of pterygium, the attention mechanisms-SENet, ECANet, CBAM, and Self-Attention-were fused with the lightweight MobileNetV2 model structure to construct a tri-classification model. The study used 1220 images of three types of anterior ocular segments of the pterygium provided by the Eye Hospital of Nanjing Medical University. Conventional classification models-VGG16, ResNet50, MobileNetV2, and EfficientNetB7-were trained on the same dataset for comparison. To evaluate model performance in terms of accuracy, Kappa value, test time, sensitivity, specificity, the area under curve (AUC), and visual heat map, 470 test images of the anterior segment of the pterygium were used.
RESULTS: The accuracy of the MobileNetV2+Self-Attention model with 281 MB in model size was 92.77%, and the Kappa value of the model was 88.92%. The testing time using the model was 9ms/image in the server and 138ms/image in the local computer. The sensitivity, specificity, and AUC for the diagnosis of pterygium using normal anterior segment images were 99.47%, 100%, and 100%, respectively; using anterior segment images in the observation period were 88.30%, 95.32%, and 96.70%, respectively; and using the anterior segment images in the surgery period were 88.18%, 94.44%, and 97.30%, respectively.
CONCLUSIONS: The developed model is lightweight and can be used not only for detection but also for assessing the severity of pterygium.
方法:对于翼状胬肉的智能诊断,注意机制——SENET,ECANet,CBAM,和自我注意力与轻量级MobileNetV2模型结构融合,构建了三分类模型。该研究使用了南京医科大学眼科医院提供的三种类型的翼状胬肉眼前段的1220张图像。常规分类模型-VGG16、ResNet50、MobileNetV2和EfficientNetB7-在相同的数据集上进行了训练以进行比较。为了评估模型性能的准确性,Kappa值,测试时间,灵敏度,特异性,曲线下面积(AUC),和视觉热图,使用了470张翼状胬肉前段的测试图像。
结果:模型大小为281MB的MobileNetV2自我注意力模型的准确性为92.77%,模型的Kappa值为88.92%。使用该模型的测试时间在服务器中为9ms/映像,在本地计算机中为138ms/映像。敏感性,特异性,使用正常眼前节图像诊断翼状胬肉的AUC为99.47%,100%,100%,用眼前节图像观察期间分别为88.30%,95.32%,96.70%,术中使用眼前节图像的比例分别为88.18%,94.44%,和97.30%,分别。
结论:开发的模型是轻量级的,不仅可用于检测,而且可用于评估翼状胬肉的严重程度。