Deng Xinyi, Chen Kun, Chen Yijing, Xiang Ziyi, Zhang Shian, Shen Lijun, Sun Mingzhai, Cai Lingzhi
Center for Rehabilitation Medicine, Department of Ophthalmology, Zhejiang Provincial People's Hospital (Affiliated People's Hospital, Hangzhou Medical College), Hangzhou, China.
Department of Precision Machinery and Instrumentation, University of Science and Technology of China, Hefei, China.
Front Pediatr. 2023 Aug 24;11:1252875. doi: 10.3389/fped.2023.1252875. eCollection 2023.
The purpose of this study was to investigate the quantitative retinal vascular morphological characteristics of Retinopathy of Prematurity (ROP) and Familial Exudative Vitreoretinopathy (FEVR) in the newborn by the application of a deep learning network with artificial intelligence.
Standard 130-degree fundus photographs centered on the optic disc were taken in the newborns. The deep learning network provided segmentation of the retinal vessels and the optic disc (OD). Based on the vessel segmentation, the vascular morphological characteristics, including avascular area, vessel angle, vessel density, fractal dimension (FD), and tortuosity, were automatically evaluated.
201 eyes of FEVR, 289 eyes of ROP, and 195 eyes of healthy individuals were included in this study. The deep learning system of blood vessel segmentation had a sensitivity of 72% and a specificity of 99%. The vessel angle in the FEVR group was significantly smaller than that in the normal group and ROP group (37.43 ± 5.43 vs. 39.40 ± 5.61, 39.50 ± 5.58, = 0.001, < 0.001 respectively). The normal group had the lowest vessel density, the ROP group was in between, and the FEVR group had the highest (2.64 ± 0.85, 2.97 ± 0.92, 3.37 ± 0.88 respectively). The FD was smaller in controls than in the FEVR and ROP groups (0.984 ± 0.039, 1.018 ± 0.039 and 1.016 ± 0.044 respectively, < 0.001). The ROP group had the most tortuous vessels, while the FEVR group had the stiffest vessels, the controls were in the middle (11.61 ± 3.17, 8.37 ± 2.33 and 7.72 ± 1.57 respectively, < 0.001).
The deep learning technology used in this study has good performance in the quantitative analysis of vascular morphological characteristics in fundus photography. Vascular morphology was different in the newborns of FEVR and ROP compared to healthy individuals, which showed great clinical value for the differential diagnosis of ROP and FEVR.
本研究旨在通过应用具有人工智能的深度学习网络，调查新生儿视网膜病变（ROP）和家族性渗出性玻璃体视网膜病变（FEVR）的定量视网膜血管形态特征。
对新生儿拍摄以视盘为中心的标准130度眼底照片。深度学习网络提供视网膜血管和视盘（OD）的分割。基于血管分割，自动评估包括无血管区、血管角度、血管密度、分形维数（FD）和迂曲度在内的血管形态特征。
本研究纳入了201只FEVR眼、289只ROP眼和195只健康个体的眼睛。血管分割的深度学习系统灵敏度为72%，特异性为99%。FEVR组的血管角度明显小于正常组和ROP组（分别为37.43±5.43 vs. 39.40±5.61、39.50±5.58，P = 0.001、P < 0.001）。正常组的血管密度最低，ROP组居中，FEVR组最高（分别为2.64±0.85、2.97±0.92、3.37±0.88）。对照组的FD小于FEVR组和ROP组（分别为0.984±0.039、1.018±0.039和1.016±0.044，P < 0.001）。ROP组的血管最迂曲，而FEVR组的血管最僵硬，对照组居中（分别为11.61±3.17、8.37±2.33和7.72±1.57，P < 0.001）。
本研究中使用的深度学习技术在眼底摄影血管形态特征的定量分析中具有良好性能。与健康个体相比，FEVR和ROP新生儿的血管形态不同，这对ROP和FEVR的鉴别诊断具有重要临床价值。
Zotero 插件
