Early Diagnosis and Quantitative Analysis of Stages in Retinopathy of Prematurity Based on Deep Convolutional Neural Networks.
Early Diagnosis and Quantitative Analysis of Stages in Retinopathy of Prematurity Based on Deep Convolutional Neural Networks.
复制标题
DOI：
10.1167/tvst.11.5.17
复制
发表时间：
2022-05-02
影响因子：
3
通讯作者：
Liu, Jia
中科院分区：
文献类型：
--
作者：
Li, Peng;Liu, Jia
关键词：
早产儿视网膜病变（ROP）是儿童失明的主要原因。对 ROP 早期阶段的准确及时诊断使眼科医生能够推荐适当的治疗方案，同时失明仍然是可以预防的。本研究的目的是开发一种基于自动深度卷积神经网络的系统，该系统通过特征参数提供 I 至 III 期 ROP 的诊断。我们开发了三个数据集，其中包含 18,827 个早产儿的视网膜图像。这些视网膜图像是从中国嘉兴市妇幼保健院眼科获得的。分割图像后，我们计算感兴趣区域（ROI）。我们根据训练数据集中分割的 ROI 图像来训练我们的系统，在测试数据集上测试分类器的性能，并在比较数据集上评估系统提取的分界线或脊线的宽度，以及 ROI 内血管增殖的比率。经过训练的网络对 I 期 ROP 的诊断灵敏度为 90.21%，特异性为 97.67%，对 II 期 ROP 的诊断灵敏度为 92.75%，特异性为 98.74%，对 III 期 ROP 的诊断灵敏度为 91.84%，特异性为 99.29%。当系统诊断正常图像时，敏感性和特异性分别达到95.93%和96.41%。正常、I 期、II 期和 III 期的分界线或脊的宽度（以像素为单位）分别为 15.22 ± 1.06、26.35 ± 1.36 和 30.75 ± 1.55。 ROI内血管增殖的比率为1.40±0.29、1.54±0.26和1.81±0.33。各组之间的所有参数均存在统计学差异。当医生将提取的特征的定量参数与临床诊断相结合时，κ 评分显着提高。我们的系统实现了 I 至 III 期 ROP 的高精度诊断。它使用提取的特征的定量分析来帮助医生提供分类决策。该系统的高性能表明其在 ROP 早期辅助诊断中具有潜在的应用前景。
Retinopathy of prematurity (ROP) is a leading cause of childhood blindness. An accurate and timely diagnosis of the early stages of ROP allows ophthalmologists to recommend appropriate treatment while blindness is still preventable. The purpose of this study was to develop an automatic deep convolutional neural network–based system that provided a diagnosis of stage I to III ROP with feature parameters. We developed three data sets containing 18,827 retinal images of preterm infants. These retinal images were obtained from the ophthalmology department of Jiaxing Maternal and Child Health Hospital in China. After segmenting images, we calculated the region of interest (ROI). We trained our system based on segmented ROI images from the training data set, tested the performance of the classifier on the test data set, and evaluated the widths of the demarcation lines or ridges extracted by the system, as well as the ratios of vascular proliferation within the ROI on a comparison data set. The trained network achieved a sensitivity of 90.21% with 97.67% specificity for the diagnosis of stage I ROP, 92.75% sensitivity with 98.74% specificity for stage II ROP, and 91.84% sensitivity with 99.29% sensitivity for stage III ROP. When the system diagnosed normal images, the sensitivity and specificity reached 95.93% and 96.41%, respectively. The widths (in pixels) of the demarcation lines or ridges for normal, stage I, stage II, and stage III were 15.22 ± 1.06, 26.35 ± 1.36, and 30.75 ± 1.55. The ratios of the vascular proliferation within the ROI were 1.40 ± 0.29, 1.54 ± 0.26, and 1.81 ± 0.33. All parameters were statistically different among the groups. When physicians integrated quantitative parameters of the extracted features with their clinic diagnosis, the κ score was significantly improved. Our system achieved a high accuracy of diagnosis for stage I to III ROP. It used the quantitative analysis of the extracted features to assist physicians in providing classification decisions. The high performance of the system suggests potential applications in ancillary diagnosis of the early stages of ROP.
登录
查看更多内容
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：
3.8
作者：
Han, Xiao
通讯作者：
Han, Xiao
影响因子：
7.3
作者：
Awrangjeb, Mohammad;Lu, Guojun
通讯作者：
Lu, Guojun
影响因子：
3.4
作者：
Mao, Jianbo;Luo, Yuhao;Shen, Lijun
通讯作者：
Shen, Lijun
影响因子：
8
作者：
Gilbert, C;Fielder, A;Zin, A
通讯作者：
Zin, A