基于深度学习技术的豹纹状眼底自动量化及分级初步研究

Preliminary study on automatic quantification and grading of leopard spots fundus based on deep learning technology

目的利用深度学习技术实现对不同区域豹纹状眼底(FT)的自动分割、量化及分级,分析新型量化指标与FT等级和全身及眼部各参数的相关性。方法横断面研究。数据来源于“北京眼病研究”(一项以人群为基础的纵向研究),于2001年整群抽取北京市海淀区5个社区及大兴区3个农村社区的40岁及以上人群进行调查,并于2011年对该人群进行随访。本研究纳入2011年接受第2个5年随访的50岁以上人群,仅纳入右眼数据。将以右眼黄斑为中心的彩色眼底图像输入豹纹分割模型及黄斑检测网络,以黄斑中心凹为原点,内圈直径为1 mm,中圈直径为3 mm,外圈直径为6 mm,实现眼底的精细分割,从而得出各区域FT密度(FTD)及FT等级。进一步对各区域FTD及不同FT等级间各眼部及全身参数进行差异性分析。按照等效球镜度数(SE)将受试眼分为近视眼(SE<-0.25 D)、正视眼(-0.25 D≤SE≤0.25 D)及远视眼(SE>0.25 D)3种屈光类型。根据眼轴长度,将受试眼分为眼轴长度<24 mm、24~26 mm及>26 mm 3种眼轴类型,对不同类型的FTD进行分析。采用单因素方差分析、Kruskal-Wallis检验、Bonferroni检验及Spearman相关分析等统计学分析方法。结果研究共纳入3369名受试者(3369只眼),年龄为(63.9±10.6)岁;其中女性1886名(56.0%)男性1483名(64.0%)。所有受试眼整体FTD为0.060(0.016,0.163);内圈FTD为0.000(0.000,0.025);中圈FTD为0.030(0.000,0.130);外圈FTD为0.055(0.009,0.171)。单因素分析结果表明,各区域FTD与眼轴长度(整体:r=0.38,P<0.001;内圈:r=0.31,P<0.001;中圈:r=0.36,P<0.001;外圈:r=0.39,P<0.001)、黄斑中心凹下脉络膜厚度(SFCT)(整体:r=-0.69,P<0.001;内圈:r=-0.57,P<0.001;中圈:r=-0.68,P<0.001;外圈:r=-0.72,P<0.001)、年龄(整体:r=0.34,P<0.001;内圈:r=0.30,P<0.001;中圈:r=0.31,P<0.001;外圈:r=0.35,P<0.001)、性别(整体:r=-0.11,P<0.001;内圈:r=-0.04,P<0.001;中圈:r=-0.07,P<0.001;外圈:r=-0.11,P<0.001)、SE(整体:r=-0.20;P<0.001;内圈:r=-0.19,P<0.001;中圈:r=-0.20,P<0.001;外圈:r=-0.20,P<0.001)、裸眼视力(整体:r=-0.18,P<0.001;内圈:r=-0.26,P<0.001;中圈:r=-0.24,P<0.001;外圈:r=-0.22,P<0.001)、体质量指数(整体:r=-0.11,P<0.001;内圈:r=-0.13,P<0.001;中圈:r=-0.14,P<0.001;外圈:r=-0.13,P<0.001)均有相关性。进一步多因素分析结果显示,不同区域FTD与眼轴长度(整体:β=0.020,P<0.001;内圈:β=-0.022,P<0.001;中圈:β=0.027,P<0.001;外圈:β=0.022,P<0.001)、SFCT(整体:β=-0.001,P<0.001;内圈:β=-0.001,P<0.001;中圈:β=-0.001,P<0.001;外圈:β=-0.001,P<0.001)及年龄(整体:β=0.002,P<0.001;内圈:β=0.001,P<0.001;中圈:β=0.002,P<0.001;外圈:β=0.002,P<0.001)均有相关性。不同屈光类型受试眼的整体(H=56.76,P<0.001)、内圈(H=72.22,P<0.001)、中圈(H=75.83,P<0.001)及外圈(H=70.34,P<0.001)FTD分布均有统计学差异。不同眼轴长度受试眼的整体(H=373.15,P<0.001)、内圈(H=367.67,P<0.001)、中圈(H=389.14,P<0.001)及外圈(H=386.89,P<0.001)FTD分布均有统计学差异。进一步比较各级别FT受试受试者全身及眼部参数差异,在所有参数中,眼轴长度(F=142.85,P<0.001)与SFCT(F=530.46,P<0.001)差异有统计学意义。结论利用深度学习技术可实现眼底不同区域FT的自动分割及量化,并可实现FT的初步分级。不同区域FTD与眼轴长度、SFCT及年龄显著相关,年龄较大、患有近视眼及眼轴较长的人群眼底各区域FTD更重,豹纹等级更高。

Objective To achieve automatic segmentation,quantification,and grading of different regions of leopard spots fundus(FT)using deep learning technology.The analysis includes exploring the correlation between novel quantitative indicators,leopard spot fundus grades,and various systemic and ocular parameters.Methods This was a cross-sectional study.The data were sourced from the Beijing Eye Study,a population-based longitudinal study.In 2001,a group of individuals aged 40 and above were surveyed in five urban communities in Haidian District and three rural communities in Daxing District of Beijing.A follow-up was conducted in 2011.This study included individuals aged 50 and above who participated in the second 5-year follow-up in 2011,considering only the data from the right eye.Color fundus images centered on the macula of the right eye were input into the leopard spot segmentation model and macular detection network.Using the macular center as the origin,with inner circle diameters of 1 mm,3 mm,and outer circle diameter of 6 mm,fine segmentation of the fundus was achieved.This allowed the calculation of the leopard spot density(FTD)and leopard spot grade for each region.Further analyses of the differences in ocular and systemic parameters among different regions′FTD and leopard spot grades were conducted.The participants were categorized into three refractive types based on equivalent spherical power(SE):myopia(SE<-0.25 D),emmetropia(-0.25 D≤SE≤0.25 D),and hyperopia(SE>0.25 D).Based on axial length,the participants were divided into groups with axial length<24 mm,24-26 mm,and>26 mm for the analysis of different types of FTD.Statistical analyses were performed using one-way analysis of variance,Kruskal-Wallis test,Bonferroni test,and Spearman correlation analysis.Results The study included 3369 participants(3369 eyes)with an average age of(63.9±10.6)years;among them,1886 were female(56.0%)and 1,483 were male(64.0%).The overall FTD for all eyes was 0.060(0.016,0.163);inner circle FTD was 0.000(0.000,0.025);middle circle FTD was 0.030(0.000,0.130);outer circle FTD was 0.055(0.009,0.171).The results of the univariate analysis indicated that FTD in various regions was correlated with axial length(overall:r=0.38,P<0.001;inner circle:r=0.31,P<0.001;middle circle:r=0.36,P<0.001;outer circle:r=0.39,P<0.001),subfoveal choroidal thickness(SFCT)(overall:r=-0.69,P<0.001;inner circle:r=-0.57,P<0.001;middle circle:r=-0.68,P<0.001;outer circle:r=-0.72,P<0.001),age(overall:r=0.34,P<0.001;inner circle:r=0.30,P<0.001;middle circle:r=0.31,P<0.001;outer circle:r=0.35,P<0.001),gender(overall:r=-0.11,P<0.001;inner circle:r=-0.04,P<0.001;middle circle:r=-0.07,P<0.001;outer circle:r=-0.11,P<0.001),SE(overall:r=-0.20;P<0.001;inner circle:r=-0.19,P<0.001;middle circle:r=-0.20,P<0.001;outer circle:r=-0.20,P<0.001),uncorrected visual acuity(overall:r=-0.18,P<0.001;inner circle:r=-0.26,P<0.001;middle circle:r=-0.24,P<0.001;outer circle:r=-0.22,P<0.001),and body mass index(BMI)(overall:r=-0.11,P<0.001;inner circle:r=-0.13,P<0.001;middle circle:r=-0.14,P<0.001;outer circle:r=-0.13,P<0.001).Further multivariate analysis results indicated that different region FTD was correlated with axial length(overall:β=0.020,P<0.001;inner circle:β=-0.022,P<0.001;middle circle:β=0.027,P<0.001;outer circle:β=0.022,P<0.001),SFCT(overall:β=-0.001,P<0.001;inner circle:β=-0.001,P<0.001;middle circle:β=-0.001,P<0.001;outer circle:β=-0.001,P<0.001),and age(overall:β=0.002,P<0.001;inner circle:β=0.001,P<0.001;middle circle:β=0.002,P<0.001;outer circle:β=0.002,P<0.001).The distribution of overall(H=56.76,P<0.001),inner circle(H=72.22,P<0.001),middle circle(H=75.83,P<0.001),and outer circle(H=70.34,P<0.001)FTD differed significantly among different refractive types.The distribution of overall(H=373.15,P<0.001),inner circle(H=367.67,P<0.001),middle circle(H=389.14,P<0.001),and outer circle(H=386.89,P<0.001)FTD differed significantly among different axial length groups.Furthermore,comparing various levels of FTD with systemic and ocular parameters,significant differences were found in axial length(F=142.85,P<0.001)and SFCT(F=530.46,P<0.001).Conclusions The use of deep learning technology enables automatic segmentation and quantification of different regions of theFT,as well as preliminary grading.Different region FTD is significantly correlated with axial length,SFCT,and age.Individuals with older age,myopia,and longer axial length tend to have higher FTD and more advanced FT grades.