Hung Kuo-Hsuan, Lin Chihung, Roan Jinsheng, Kuo Chang-Fu, Hsiao Ching-Hsi, Tan Hsin-Yuan, Chen Hung-Chi, Ma David Hui-Kang, Yeh Lung-Kun, Lee Oscar Kuang-Sheng
Department of Ophthalmology, Chang-Gung Memorial Hospital, Linkou, No. 5, Fu-Hsing St., Kuei Shan Hsiang, Taoyuan 83301, Taiwan.
College of Medicine, Chang-Gung University, No. 259 Wen-Hwa 1st Road, Kuei Shan Hsiang, Taoyuan 33302, Taiwan.
Diagnostics (Basel). 2022 Apr 2;12(4):888. doi: 10.3390/diagnostics12040888.
The aim of this study was to evaluate the efficacy of a deep learning system in pterygium grading and recurrence prediction.
This was a single center, retrospective study. Slit-lamp photographs, from patients with or without pterygium, were collected to develop an algorithm. Demographic data, including age, gender, laterality, grading, and pterygium area, recurrence, and surgical methods were recorded. Complex ocular surface diseases and pseudopterygium were excluded. Performance of the algorithm was evaluated by sensitivity, specificity, F1 score, accuracy, and area under the receiver operating characteristic curve. Confusion matrices and heatmaps were created to help explain the results.
A total of 237 eyes were enrolled, of which 176 eyes had pterygium and 61 were non-pterygium eyes. The training set and testing set were comprised of 189 and 48 photographs, respectively. In pterygium grading, sensitivity, specificity, F1 score, and accuracy were 80% to 91.67%, 91.67% to 100%, 81.82% to 94.34%, and 86.67% to 91.67%, respectively. In the prediction model, our results showed sensitivity, specificity, positive predictive value, and negative predictive values were 66.67%, 81.82%, 33.33%, and 94.74%, respectively.
Deep learning systems can be useful in pterygium grading based on slit lamp photographs. When clinical parameters involved in the prediction of pterygium recurrence were included, the algorithm showed higher specificity and negative predictive value in prediction.
本研究旨在评估深度学习系统在翼状胬肉分级及复发预测中的效能。
这是一项单中心回顾性研究。收集有或无翼状胬肉患者的裂隙灯照片以开发算法。记录人口统计学数据，包括年龄、性别、患侧、分级、翼状胬肉面积、复发情况及手术方法。排除复杂眼表疾病和假性胬肉。通过敏感性、特异性、F1评分、准确性及受试者操作特征曲线下面积评估算法性能。创建混淆矩阵和热图以辅助解释结果。
共纳入237只眼，其中176只眼患有翼状胬肉，61只为无翼状胬肉的眼。训练集和测试集分别由189张和48张照片组成。在翼状胬肉分级中，敏感性、特异性、F1评分及准确性分别为80%至91.67%、91.67%至100%、81.82%至94.34%及86.67%至91.67%。在预测模型中，我们的结果显示敏感性、特异性、阳性预测值及阴性预测值分别为66.67%、81.82%、33.33%及94.74%。
基于裂隙灯照片的深度学习系统在翼状胬肉分级中可能有用。当纳入翼状胬肉复发预测所涉及的临床参数时，该算法在预测中显示出更高的特异性和阴性预测值。
