Fully automated grading system for the evaluation of punctate epithelial erosions using deep neural networks.
Fully automated grading system for the evaluation of punctate epithelial erosions using deep neural networks.
复制标题
使用深度神经网络评估点状上皮糜烂的全自动分级系统
DOI：
10.1136/bjophthalmol-2021-319755
复制
发表时间：
2023-04
影响因子：
4.1
通讯作者：
Hong, Jing
中科院分区：
文献类型：
--
作者：
Qu, Jing-Hao;Qin, Xiao-Ran;Li, Chen-Di;Peng, Rong-Mei;Xiao, Ge-Ge;Cheng, Jian;Gu, Shao-Feng;Wang, Hai-Kun;Hong, Jing
目的本研究的目标是开发一种全自动分级系统，用于使用深度神经网络评估点状上皮糜烂（PEE）。方法利用角膜荧光素染色图像，建立全自动角膜定位系统，对角膜进行定位和染色程度分级。全自动流水线由以下三个步骤组成：角膜分割模型提取角膜区域;基于提取的角膜的五个子区域从染色图像中裁剪五个图像块;染色分级模型预测每个图像块的分数从0到3，并且获得整个角膜的自动分级分数从0到15。最后，将三位眼科医生注释的临床分级分数与自动分级分数进行比较。结果对于角膜分割，该分割模型的交并比为0.937。对于点状染色分级，分级模型的分类准确度为76.5%，受试者工作特征曲线下面积为0.940（95% CI 0.932 - 0.949）。对于全自动流水线，临床评分和自动评分之间的Pearson相关系数为0.908（p<0.01）。Bland-Altman分析显示，临床和自动分级评分之间的95%一致性限度在-4.125至3.720之间（一致性相关系数=0.904）。在流水线期间处理单个染色图像所需的平均时间为0.58 s。结论建立了一个全自动的PEE评分系统。分级结果可作为临床试验和住院医师培训程序中的眼科医生参考。
Purpose The goal was to develop a fully automated grading system for the evaluation of punctate epithelial erosions (PEEs) using deep neural networks. Methods A fully automated system was developed to detect corneal position and grade staining severity given a corneal fluorescein staining image. The fully automated pipeline consists of the following three steps: a corneal segmentation model extracts corneal area; five image patches are cropped from the staining image based on the five subregions of extracted cornea; a staining grading model predicts a score for each image patch from 0 to 3, and automated grading score for the whole cornea is obtained from 0 to 15. Finally, the clinical grading scores annotated by three ophthalmologists were compared with automated grading scores. Results For corneal segmentation, the segmentation model achieved an intersection over union of 0.937. For punctate staining grading, the grading model achieved a classification accuracy of 76.5% and an area under the receiver operating characteristic curve of 0.940 (95% CI 0.932 to 0.949). For the fully automated pipeline, Pearson’s correlation coefficient between the clinical and automated grading scores was 0.908 (p<0.01). Bland-Altman analysis revealed 95% limits of agreement between the clinical and automated grading scores of between −4.125 and 3.720 (concordance correlation coefficient=0.904). The average time required for processing a single stained image during pipeline was 0.58 s. Conclusion A fully automated grading system was developed to evaluate PEEs. The grading results may serve as a reference for ophthalmologists in clinical trials and residency training procedures.
登录
查看更多内容
影响因子：
4.2
作者：
Peterson, Rachael C.;Wolffsohn, James S.;Fowler, Colin W.
通讯作者：
Fowler, Colin W.
影响因子：
19.5
作者：
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者：
Fei-Fei, Li
影响因子：
4.4
作者：
Rodriguez, John D.;Lane, Keith J.;Abelson, Mark B.
通讯作者：
Abelson, Mark B.
数字图像对球结膜丽丝胺绿染色半自动定量的开发和评估
影响因子：
8.1
作者：
Bunya, Vatinee Y.;Chen, Min;Maguire, Maureen G.
通讯作者：
Maguire, Maureen G.
影响因子：
4.3
作者：
Su, Tai-Yuan;Ting, Peng-Jen;Chen, Duan-Yu
通讯作者：
Chen, Duan-Yu