Automated diagnosis and quantitative analysis of plus disease in retinopathy of prematurity based on deep convolutional neural networks
Automated diagnosis and quantitative analysis of plus disease in retinopathy of prematurity based on deep convolutional neural networks
复制标题
DOI：
10.1111/aos.14264
复制
发表时间：
2019-09-27
影响因子：
3.4
通讯作者：
Shen, Lijun
中科院分区：
文献类型：
--
作者：
Mao, Jianbo;Luo, Yuhao;Shen, Lijun
背景本研究的目的是开发一个针对PLUS疾病的自动化诊断和定量分析系统。该系统不仅提供诊断决策，还对疾病的典型病理特征进行量化分析，帮助医生做出最佳判断并传达决策。方法深度学习网络提供视网膜血管和视盘(OD)的分割。在血管分割的基础上，对PLUS病变进行分类，自动计算血管的曲度、宽度、分维和血管密度。结果训练好的网络对PLUS病的诊断灵敏度为95.1%，特异度为97.8%。对于Preplus或Preplus更差的检测，敏感性和特异性分别为92.4%和97.4%。二次加权系数k为0.9244。正常组、预加正组和加正组的弯曲度分别为3.61+/-0.08、5.95+/-1.57和10.67+/-0.50(10(4)cm(-3))。血管宽度分别为63.46+/-0.39、67.21+/-0.70和68.89+/-0.75亩，分维分别为1.18+/-0.01、1.22+/-0.01和1.26+/-0.02。血管密度分别为1.39±0.03、1.60±-0.01和1.64±0.09(%)。所有的数值在不同的组间有统计学上的差异。雷尼比珠单抗治疗Plus病后，定量分析显示病理特征有明显变化。结论本系统对早产儿视网膜病变的诊断准确率较高。它提供了疾病进展的动态特征的定量分析。这个自动化系统可以通过提供疾病典型病理特征的辅助定量评估的分类决策来帮助医生。
Background The purpose of this study was to develop an automated diagnosis and quantitative analysis system for plus disease. The system provides a diagnostic decision but also performs quantitative analysis of the typical pathological features of the disease, which helps the physicians to make the best judgement and communicate the decisions. Methods The deep learning network provided segmentation of the retinal vessels and the optic disc (OD). Based on the vessel segmentation, plus disease was classified and tortuosity, width, fractal dimension and vessel density were evaluated automatically. Results The trained network achieved a sensitivity of 95.1% with 97.8% specificity for the diagnosis of plus disease. For detection of preplus or worse, the sensitivity and specificity were 92.4% and 97.4%. The quadratic weighted k was 0.9244. The tortuosities for the normal, preplus and plus groups were 3.61 +/- 0.08, 5.95 +/- 1.57 and 10.67 +/- 0.50 (10(4) cm(-3)). The widths of the blood vessels were 63.46 +/- 0.39, 67.21 +/- 0.70 and 68.89 +/- 0.75 mu m. The fractal dimensions were 1.18 +/- 0.01, 1.22 +/- 0.01 and 1.26 +/- 0.02. The vessel densities were 1.39 +/- 0.03, 1.60 +/- 0.01 and 1.64 +/- 0.09 (%). All values were statistically different among the groups. After treatment for plus disease with ranibizumab injection, quantitative analysis showed significant changes in the pathological features. Conclusions Our system achieved high accuracy of diagnosis of plus disease in retinopathy of prematurity. It provided a quantitative analysis of the dynamic features of the disease progression. This automated system can assist physicians by providing a classification decision with auxiliary quantitative evaluation of the typical pathological features of the disease.