Salvi Anish, Cluceru Julia, Gao Simon S, Rabe Christina, Schiffman Courtney, Yang Qi, Lee Aaron Y, Keane Pearse A, Sadda Srinivas R, Holz Frank G, Ferrara Daniela, Anegondi Neha
Genentech, Inc., South San Francisco, California.
Department of Ophthalmology, University of Washington, Seattle, Washington.
Ophthalmol Sci. 2024 Oct 23;5(2):100635. doi: 10.1016/j.xops.2024.100635. eCollection 2025 Mar-Apr.
The region of growth (ROG) of geographic atrophy (GA) throughout the macular area has an impact on visual outcomes. Here, we developed multiple deep learning models to predict the 1-year ROG of GA lesions using fundus autofluorescence (FAF) images.
In this retrospective analysis, 3 types of models were developed using FAF images collected 6 months after baseline to predict the GA lesion area (segmented lesion mask) at 1.5 years, FAF images collected at baseline and 6 months to predict the GA lesion at 1.5 years, and FAF images collected 6 months after baseline to predict the GA lesion at 1 and 1.5 years. The 1-year ROG from the 6-month visit was derived by taking the difference between the GA lesion area (segmented lesion mask) at the 1.5-year and 6-month visits.
Patients enrolled in the following lampalizumab clinical trials and prospective observational studies: NCT02247479, NCT02247531, NCT02479386, and NCT02399072.
Datasets of study eyes from 597 patients were split into model training (310), validation (78), and test sets (209), stratified by baseline or initial lesion area, lesion growth rate, foveal involvement, and focality. Deep learning experiments were performed using the 2-dimensional U-Net; whole-lesion and multiclass models were developed.
The performance of the models was evaluated by calculating the Dice score, coefficient of determination (R), and the squared Pearson correlation coefficient (r) between the true and derived GA lesion 1-year ROG.
The model using baseline and 6-month FAF images to predict GA lesion enlargement at 1.5 years had the best performance for the derived 1-year ROG. Mean Dice scores were 0.73, 0.68, and 0.70 in the training, validation, and test sets, respectively. The R (0.77, 0.53, and 0.79) and r (0.83, 0.61, and 0.79) showed similar trends across the 3 sets.
These findings show the potential of using baseline and/or 6-month visit FAF images to predict 1-year GA ROG using a deep learning approach. This work could potentially help support decision-making in clinical trials and more informed treatment decisions in clinical practice.
Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
整个黄斑区地理性萎缩（GA）的生长区域（ROG）对视觉结果有影响。在此，我们开发了多个深度学习模型，以使用眼底自发荧光（FAF）图像预测GA病变的1年ROG。
在这项回顾性分析中，使用基线后6个月收集的FAF图像开发了3种类型的模型，以预测1.5年时的GA病变面积（分割病变掩码）；使用基线和6个月时收集的FAF图像预测1.5年时的GA病变；使用基线后6个月收集的FAF图像预测1年和1.5年时的GA病变。6个月随访时的1年ROG通过计算1.5年和6个月随访时GA病变面积（分割病变掩码）之间的差异得出。
纳入以下lampalizumab临床试验和前瞻性观察性研究的患者：NCT02247479、NCT02247531、NCT02479386和NCT02399072。
将来自597例患者的研究眼数据集分为模型训练集（310例）、验证集（78例）和测试集（209例），按基线或初始病变面积、病变生长率、黄斑中心凹受累情况和病灶性进行分层。使用二维U-Net进行深度学习实验；开发了全病变和多类模型。
通过计算真实和推导的GA病变1年ROG之间的Dice分数、决定系数（R）和皮尔逊相关系数平方（r）来评估模型的性能。
使用基线和6个月FAF图像预测1.5年时GA病变扩大的模型在推导的1年ROG方面表现最佳。训练集、验证集和测试集的平均Dice分数分别为0.73、0.68和0.70。R（0.77、0.53和0.79）和r（0.83、0.61和0.79）在这3个数据集上呈现相似趋势。
这些发现表明，使用深度学习方法，利用基线和/或6个月随访时的FAF图像预测1年GA ROG具有潜力。这项工作可能有助于支持临床试验中的决策制定以及临床实践中更明智的治疗决策。
在本文末尾的脚注和披露中可能会发现专有或商业披露信息。
