Prediction of causative genes in inherited retinal disorder from fundus photography and autofluorescence imaging using deep learning techniques.
Prediction of causative genes in inherited retinal disorder from fundus photography and autofluorescence imaging using deep learning techniques.
复制标题
利用深度学习技术从眼底照相和自发荧光成像预测遗传性视网膜疾病的致病基因
DOI：
10.1136/bjophthalmol-2020-318544
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Japan Eye Genetics Study (JEGC) Group
中科院分区：
文献类型：
--
作者：
Fujinami-Yokokawa Y;Ninomiya H;Liu X;Yang L;Pontikos N;Yoshitake K;Iwata T;Sato Y;Hashimoto T;Tsunoda K;Miyata H;Fujinami K;Japan Eye Genetics Study (JEGC) Group
研究数据驱动的深度学习方法在遗传性视网膜疾病（IRD）患者中的实用性，并基于眼底摄影和眼底自发荧光（FAF）成像预测致病基因。回顾了来自729个遗传学证实的IRD家族的1302例受试者的临床和遗传学数据，这些家族在日本眼科遗传学协会注册。根据其致病基因的高患病率，选择了三类遗传诊断：Stargardt病（ABCA 4）、视网膜色素变性（EYS）和隐匿性黄斑营养不良（RP 1 L1）。使用宏算法以标准化方式裁剪眼底照片和FAF图像。使用随机、四重交叉验证方法选择用于训练/测试的图像。建立了遗传诊断与机器诊断（ABCA 4、EYS、RP 1 L1和正常）一致性学习精度（目标：>80%）的应用程序接口。共检查了来自156名日本受试者的417张图像，其中包括115名由三种流行致病基因引起的基因确认患者和41名正常受试者。眼底照片和FAF图像的平均总体测试准确度分别为88.2%和81.3%。眼底照片和FAF图像的平均总体敏感性/特异性值分别为88.3%/97.4%和81.8%/95.5%。强调了深度神经网络在从眼底照片和FAF预测致病IRD基因中的新应用，其预测准确率高达80%以上。这些成就将通过促进早期诊断，特别是非专家的早期诊断、获得护理、减少转诊费用以及防止不必要的临床和基因检测，广泛提高医疗质量。
To investigate the utility of a data-driven deep learning approach in patients with inherited retinal disorder (IRD) and to predict the causative genes based on fundus photography and fundus autofluorescence (FAF) imaging. Clinical and genetic data from 1302 subjects from 729 genetically confirmed families with IRD registered with the Japan Eye Genetics Consortium were reviewed. Three categories of genetic diagnosis were selected, based on the high prevalence of their causative genes: Stargardt disease (ABCA4), retinitis pigmentosa (EYS) and occult macular dystrophy (RP1L1). Fundus photographs and FAF images were cropped in a standardised manner with a macro algorithm. Images for training/testing were selected using a randomised, fourfold cross-validation method. The application program interface was established to reach the learning accuracy of concordance (target: >80%) between the genetic diagnosis and the machine diagnosis (ABCA4, EYS, RP1L1 and normal). A total of 417 images from 156 Japanese subjects were examined, including 115 genetically confirmed patients caused by the three prevalent causative genes and 41 normal subjects. The mean overall test accuracy for fundus photographs and FAF images was 88.2% and 81.3%, respectively. The mean overall sensitivity/specificity values for fundus photographs and FAF images were 88.3%/97.4% and 81.8%/95.5%, respectively. A novel application of deep neural networks in the prediction of the causative IRD genes from fundus photographs and FAF, with a high prediction accuracy of over 80%, was highlighted. These achievements will extensively promote the quality of medical care by facilitating early diagnosis, especially by non-specialists, access to care, reducing the cost of referrals, and preventing unnecessary clinical and genetic testing.
登录
查看更多内容
影响因子：
--
作者：
Roberts, Chris B.;Hiratsuka, Yoshimune;Taylor, Hugh R.
通讯作者：
Taylor, Hugh R.
影响因子：
4.4
作者：
Abramoff, Michael David;Lou, Yiyue;Niemeijer, Meindert
通讯作者：
Niemeijer, Meindert
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S
影响因子：
3
作者：
Hardcastle AJ;Sieving PA;Sahel JA;Jacobson SG;Cideciyan AV;Flannery JG;Beltran WA;Aguirre GD
通讯作者：
Aguirre GD
影响因子：
3.9
作者：
Miere A;Le Meur T;Bitton K;Pallone C;Semoun O;Capuano V;Colantuono D;Taibouni K;Chenoune Y;Astroz P;Berlemont S;Petit E;Souied E
通讯作者：
Souied E