基于深度学习的双模态眼底照相机视网膜分支静脉阻塞的血氧饱和度及血管形态学研究  

The oxygen saturation and vascular morphology of branch retinal vein occlusion by a dual-model fundus camera bsscd on deep learning

作　　者：邓昕熠 刘辉 毛剑波 孙明斋 张正熙 陶继伟 佘相均 陈亦棋 沈丽君 Deng Xinyi;Liu Hui;Mao Jianbo;Sun Mingzhai;Zhang Zhengxi;Tao Jiwei;She Xiangjun;Chen Yiqi;Shen Lijun(Eye Hospital and School of Ophthalmology and Optometry,Wenzhou Medical University,Wenzhou 325027,China;Department of Precision Machinery and Precision Instrumentation,University of Science and Technology of China,Hefei 230022,China;Department of Ophthalmology,Zhejiang Provincial People's Hospital,Hangzhou 310000,China)

机构地区：[1]温州医科大学附属眼视光医院,温州325027 [2]中国科学技术大学工程科学学院精密器械与精密仪器系,合肥230022 [3]浙江省人民医院眼科,杭州310000

出　　处：《中华眼底病杂志》2022年第2期108-113,共6页Chinese Journal of Ocular Fundus Diseases

摘　　要：目的基于深度学习的双模态眼底照相机研究视网膜分支静脉阻塞(BRVO)患眼视网膜血氧饱和度及血管形态变化。方法前瞻性研究。2020年5~10月于温州医科大学附属眼视光学院检查确诊的BRVO患者31例31只眼(BRVO组)和性别年龄匹配的健康志愿者20名20只眼(对照组)纳入研究。BRVO组31例31只眼中,既往接受1次玻璃体腔注射抗血管内皮生长因子药物治疗20例20只眼,未接受任何治疗11例11只眼;并据此分为治疗组、未治疗组。应用双模态眼底照相机采集视网膜图像;利用深度学习方法在黄斑感兴趣区域(MROI)分割动静脉;使用光密度比计算对照组受检眼、BRVO组患者受累侧和非受累侧视网膜血氧饱和度(SO_(2)),并计算MROI内动静脉直径、曲率、分形维数及密度。组间定量资料比较采用单因素方差分析。结果BRVO组患眼、对侧眼及对照组受检眼MROI内动脉SO_(2)(SO_(2)-A)比较,差异有统计学意义(F=4.925,P<0.001);静脉SO_(2)(SO_(2)-V)比较,差异无统计学意义(F=0.607,P=0.178)。未治疗组患者受累侧、非受累侧MROI内SO_(2)-A较对照组升高,差异有统计学意义(F=4.925,P=0.012);SO_(2)-V比较,差异无统计学意义(F=0.607,P=0.550)。治疗组受累侧、非受累侧和对照组受检眼MROI内SO_(2)-A、SO_(2)-V比较,差异均无统计学意义(F=0.159、1.701,P=0.854、0.197)。治疗组、未治疗组受累侧和对照组受检眼MROI内SO_(2)-A、SO_(2)-V比较,差异无统计学意义(F=2.553、0.265,P=0.088、0.546)。未治疗组、治疗组患眼和对照组受检眼动脉直径、动脉曲率、动脉分形维数、静脉分形维数、动脉密度、静脉密度比较,差异均有统计学意义(F=3.527、3.322、7.251、26.128、4.782、5.612,P=0.047、0.044、0.002、<0.001、0.013、0.006);静脉直径、静脉曲率比较,差异无统计学意义(F=2.132、1.199,P=0.143、0.321)。结论BRVO患者SO_(2)-A较健康眼升高,抗血管内皮生长因子药物治疗后降低;SO_(2)Objective To study a deep learning-based dual-modality fundus camera which was used to study retinal blood oxygen saturation and vascular morphology changes in eyes with branch retinal vein occlusion(BRVO).Methods A prospective study.From May to October 2020,31 patients(31 eyes)of BRVO(BRVO group)and 20 healthy volunteers(20 eyes)with matched gender and age(control group)were included in the study.Among 31 patients(31 eyes)in BRVO group,20 patients(20 eyes)received one intravitreal injection of anti-vascular endothelial growth factor drugs before,and 11 patients(11 eyes)did not receive any treatment.They were divided into treatment group and untreated group accordingly.Retinal images were collected with a dual-modality fundus camera;arterial and vein segments were segmented in the macular region of interest(MROI)using deep learning;the optical density ratio was used to calculate retinal blood oxygen saturation(SO_(2))on the affected and non-involved sides of the eyes in the control group and patients in the BRVO group,and calculated the diameter,curvature,fractal dimension and density of arteriovenous in MROI.Quantitative data were compared between groups using one-way analysis of variance.Results There was a statistically significant difference in arterial SO_(2)(SO_(2)-A)in the MROI between the affected eyes,the fellow eyes in the BRVO group and the control group(F=4.925,P<0.001),but there was no difference in the venous SO(SO_(2)-V)(F=0.607,P=0.178).Compared with the control group,the SO_(2)-A in the MROI of the affected side and the non-involved side of the untreated group was increased,and the difference was statistically significant(F=4.925,P=0.012);there was no significant difference in SO_(2)-V(F=0.607,P=O.550).There was no significant difference in SO_(2)-A and SO_(2)-V in the MROI between the affected side,the non-involved side in the treatment group and the control group(F=0.159,1.701;P=0.854,0.197).There was no significant difference in SO_(2)-A and SO_(2)-V in MROI between the affected side of the tr

关 键 词：视网膜静脉闭塞 血氧饱和度 血管形态学 深度学习 双模态眼底相机 

分 类 号：R774.1[医药卫生—眼科]