Department of Ophthalmology, University of Bonn, Bonn, Germany; GRADE Reading Center, Bonn, Germany; Department of Biomedical Data Science, Stanford University, Stanford, California, USA.
Department of Ophthalmology, University of Bonn, Bonn, Germany.
Am J Ophthalmol. 2020 Sep;217:162-173. doi: 10.1016/j.ajo.2020.04.003. Epub 2020 Apr 11.
To investigate the association between retinal microstructure and cone and rod function in geographic atrophy (GA) secondary to age-related macular degeneration (AMD) by using artificial intelligence (AI) algorithms.
Prospective, observational case series.
A total of 41 eyes of 41 patients (75.8 ± 8.4 years old; 22 females) from a tertiary referral hospital were included. Mesopic, dark-adapted (DA) cyan and red sensitivities were assessed by using fundus-controlled perimetry ("microperimetry"); and retinal microstructure was assessed by using spectral-domain optical-coherence-tomography (SD-OCT), fundus autofluorescence (FAF), and near-infrared-reflectance (IR) imaging. Layer thicknesses and intensities and FAF and IR intensities were extracted for each test point. The cross-validated mean absolute error (MAE) was evaluated for random forest-based predictions of retinal sensitivity with and without patient-specific training data and percentage of increased mean-squared error (%IncMSE) as measurement of feature importance.
Retinal sensitivity was predicted with a MAE of 4.64 dB for mesopic, 4.89 dB for DA cyan, and 4.40 dB for DA red testing in the absence of patient-specific data. Partial addition of patient-specific sensitivity data to the training sets decreased the MAE to 2.89 dB, 2.86 dB, and 2.77 dB. For all 3 types of testing, the outer nuclear layer thickness constituted the most important predictive feature (35.0, 42.22, and 53.74 %IncMSE). Spatially resolved mapping of "inferred sensitivity" revealed regions with differential degrees of mesopic and DA cyan sensitivity loss outside of the GA lesions.
"Inferred sensitivity" accurately reflected retinal function in patients with GA. Mapping of "inferred sensitivity" could facilitate monitoring of disease progression and serve as "quasi functional" surrogate outcome in clinical trials, especially in consideration of retinal regions beyond areas of GA.
利用人工智能 (AI) 算法研究与年龄相关性黄斑变性 (AMD) 相关的地图状萎缩 (GA) 患者的视网膜微观结构与视锥细胞和视杆细胞功能之间的关系。
前瞻性、观察性病例系列研究。
共纳入 41 名患者（75.8±8.4 岁；22 名女性）的 41 只眼，均来自一家三级转诊医院。通过眼底控制的微视野计评估明适应、暗适应（DA）蓝和红敏感度（“微视野计”）；并通过频域光相干断层扫描（SD-OCT）、眼底自发荧光（FAF）和近红外反射（IR）成像评估视网膜微观结构。提取每个测试点的层厚和强度以及 FAF 和 IR 强度。使用随机森林预测视网膜敏感度，并评估交叉验证的平均绝对误差（MAE），同时评估有无患者特异性训练数据和特征重要性测量的均方误差增加百分比（%IncMSE）。
在没有患者特异性数据的情况下，明适应、暗适应蓝和暗适应红测试的 MAE 分别为 4.64dB、4.89dB 和 4.40dB，可预测视网膜敏感度。将患者特异性敏感度数据部分添加到训练集中，MAE 分别降至 2.89dB、2.86dB 和 2.77dB。对于所有 3 种测试，外核层厚度是最重要的预测特征（35.0%、42.22%和 53.74%IncMSE）。“推断敏感度”的空间分辨图显示，GA 病变之外的区域存在明适应和暗适应蓝敏感度损失的不同程度。
“推断敏感度”准确反映了 GA 患者的视网膜功能。“推断敏感度”的映射可以促进疾病进展的监测，并作为临床试验中的“准功能”替代终点，尤其是考虑到 GA 区域以外的视网膜区域。
