Department of Ophthalmology, University Hospital Bonn, Bonn, NRW, Germany.
University of Bonn, Bonn, Nordrhein-Westfalen, Germany.
BMJ Open Ophthalmol. 2024 Apr 29;9(1):e001628. doi: 10.1136/bmjophth-2023-001628.
Retinal imaging, including fundus autofluorescence (FAF), strongly depends on the clearness of the optical media. Lens status is crucial since the ageing lens has both light-blocking and autofluorescence (AF) properties that distort image analysis. Here, we report both lens opacification and AF metrics and the effect on automated image quality assessment.
227 subjects (range: 19-89 years old) received quantitative AF of the lens (LQAF), Scheimpflug, anterior chamber optical coherence tomography as well as blue/green FAF (BAF/GAF), and infrared (IR) imaging. LQAF values, the Pentacam Nucleus Staging score and the relative lens reflectivity were extracted to estimate lens opacification. Mean opinion scores of FAF and IR image quality were compiled by medical readers. A regression model for predicting image quality was developed using a convolutional neural network (CNN). Correlation analysis was conducted to assess the association of lens scores, with retinal image quality derived from human or CNN annotations.
Retinal image quality was generally high across all imaging modalities (IR (8.25±1.99) >GAF >BAF (6.6±3.13)). CNN image quality prediction was excellent (average mean absolute error (MAE) 0.9). Predictions were comparable to human grading. Overall, LQAF showed the highest correlation with image quality grading criteria for all imaging modalities (eg, Pearson correlation±CI -0.35 (-0.50 to 0.18) for BAF/LQAF). BAF image quality was most vulnerable to an increase in lenticular metrics, while IR (-0.19 (-0.38 to 0.01)) demonstrated the highest resilience.
The use of CNN-based retinal image quality assessment achieved excellent results. The study highlights the vulnerability of BAF to lenticular remodelling. These results can aid in the development of cut-off values for clinical studies, ensuring reliable data collection for the monitoring of retinal diseases.
视网膜成像，包括眼底自发荧光（FAF），强烈依赖于光学介质的清晰度。晶状体状态至关重要，因为老化的晶状体既有遮光性又有自发荧光（AF）特性，会扭曲图像分析。在这里，我们报告晶状体混浊和 AF 指标及其对自动图像质量评估的影响。
227 名受试者（年龄范围：19-89 岁）接受了晶状体定量自发荧光（LQAF）、Scheimpflug、前房光学相干断层扫描以及蓝/绿 FAF（BAF/GAF）和红外（IR）成像。提取 LQAF 值、Pentacam 核分期评分和相对晶状体反射率来估计晶状体混浊。由医学读者汇编 FAF 和 IR 图像质量的平均意见评分。使用卷积神经网络（CNN）开发了用于预测图像质量的回归模型。进行了相关分析，以评估晶状体评分与来自人类或 CNN 注释的视网膜图像质量之间的关联。
所有成像方式的视网膜图像质量总体较高（IR（8.25±1.99）>GAF>BAF（6.6±3.13））。CNN 图像质量预测非常出色（平均平均绝对误差（MAE）为 0.9）。预测与人类分级相当。总体而言，对于所有成像方式，LQAF 与图像质量分级标准的相关性最高（例如，BAF/LQAF 的 Pearson 相关系数±CI 为-0.35（-0.50 至 0.18））。BAF 图像质量对晶状体指标的增加最敏感，而 IR（-0.19（-0.38 至 0.01））则显示出最高的弹性。
基于 CNN 的视网膜图像质量评估取得了出色的结果。该研究强调了 BAF 对晶状体重塑的脆弱性。这些结果可以帮助为临床研究制定截止值，确保为监测视网膜疾病可靠地收集数据。
