Christian Doppler Laboratory for Ophthalmic Image Analysis, Vienna Reading Center, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria.
Genentech, Inc., South San Francisco, California, United States.
Invest Ophthalmol Vis Sci. 2018 Jul 2;59(8):3199-3208. doi: 10.1167/iovs.18-24106.
While millions of individuals show early age-related macular degeneration (AMD) signs, yet have excellent vision, the risk of progression to advanced AMD with legal blindness is highly variable. We suggest means of artificial intelligence to individually predict AMD progression.
In eyes with intermediate AMD, progression to the neovascular type with choroidal neovascularization (CNV) or the dry type with geographic atrophy (GA) was diagnosed based on standardized monthly optical coherence tomography (OCT) images by independent graders. We obtained automated volumetric segmentation of outer neurosensory layers and retinal pigment epithelium, drusen, and hyperreflective foci by spectral domain-OCT image analysis. Using imaging, demographic, and genetic input features, we developed and validated a machine learning-based predictive model assessing the risk of conversion to advanced AMD.
Of a total of 495 eyes, 159 eyes (32%) had converted to advanced AMD within 2 years, 114 eyes progressed to CNV, and 45 to GA. Our predictive model differentiated converting versus nonconverting eyes with a performance of 0.68 and 0.80 for CNV and GA, respectively. The most critical quantitative features for progression were outer retinal thickness, hyperreflective foci, and drusen area. The features for conversion showed pathognomonic patterns that were distinctly different for the neovascular and the atrophic pathways. Predictive hallmarks for CNV were mostly drusen-centric, while GA markers were associated with neurosensory retina and age.
Artificial intelligence with automated analysis of imaging biomarkers allows personalized prediction of AMD progression. Moreover, pathways of progression may be specific in respect to the neovascular/atrophic type.
虽然数以百万计的个体表现出与年龄相关的黄斑变性（AMD）的早期迹象，但仍具有良好的视力，但进展为具有法律意义的失明的晚期 AMD 的风险高度可变。我们建议使用人工智能来单独预测 AMD 的进展。
在具有中间 AMD 的眼中，根据独立分级员的每月标准化光学相干断层扫描（OCT）图像，诊断出向新生血管型（伴有脉络膜新生血管（CNV））或干性型（伴有地理萎缩（GA））的进展。我们通过光谱域-OCT 图像分析获得外神经感觉层和视网膜色素上皮、玻璃膜疣和高反射焦点的自动容积分割。使用成像、人口统计学和遗传输入特征，我们开发并验证了一种基于机器学习的预测模型，评估向晚期 AMD 转化的风险。
在总共 495 只眼中，159 只眼（32%）在 2 年内转化为晚期 AMD，114 只眼进展为 CNV，45 只眼进展为 GA。我们的预测模型区分了转化眼和非转化眼，CNV 和 GA 的性能分别为 0.68 和 0.80。进展的最关键的定量特征是外视网膜厚度、高反射焦点和玻璃膜疣面积。用于转化的特征表现出独特的模式，与新生血管和萎缩途径明显不同。CNV 的预测标志主要是玻璃膜疣中心，而 GA 标志物与神经感觉视网膜和年龄有关。
使用自动分析成像生物标志物的人工智能允许对 AMD 的进展进行个性化预测。此外，进展途径可能在新生血管/萎缩类型方面具有特异性。
