Neri Giovanni, Rebecchi Chiara, Oakley Jonathan D, Olivieri Chiara, Ricardi Federico, Marolo Paola, Russakoff Daniel B, Reibaldi Michele, Borrelli Enrico
Department of Surgical Sciences, University of Turin, Turin, Italy.
Department of Ophthalmology, "City of Health and Science" Hospital, Turin, Italy.
Invest Ophthalmol Vis Sci. 2025 Jul 1;66(9):55. doi: 10.1167/iovs.66.9.55.
To develop a deep learning algorithm capable of accurately classifying macular neovascularization (MNV) subtypes in patients with treatment-naïve exudative neovascular age-related macular degeneration (AMD) using structural optical coherence tomography (OCT) images.
In this retrospective cohort study, a total of 193 eyes with treatment-naïve neovascular AMD were included. Each case was classified into MNV subtypes (type 1, 2, or 3) based on structural OCT features. Convolutional neural network (CNN)-based deep learning models were trained using cross-validation to classify MNV subtypes. Preprocessing included homogenization of image data to optimize use of layer information for classification. Performance metrics included sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC), with and without homogenization.
Homogenized OCT data improved classification performance compared to non-homogenized data for all models. The highest reported sensitivity and specificity for type 1 MNV was 96.7% and 84.9%; for type 2, 100.0% and 85.5%; and, for type 3, 84.9% and 87.9%, respectively. The AUCs for type 1, 2, and 3 MNV were 0.95, 0.97, and 0.91, respectively. Occlusion sensitivity analysis revealed critical regions for classification, highlighting distinct anatomical differences among MNV subtypes.
The proposed deep learning model demonstrated high accuracy in classifying MNV subtypes on structural OCT, with improved performance following homogenization. This tool could assist clinicians in accurately and efficiently diagnosing MNV subtypes, potentially influencing treatment decisions and patient outcomes in neovascular AMD.
开发一种深度学习算法，能够使用结构光学相干断层扫描（OCT）图像，对初治渗出性新生血管性年龄相关性黄斑变性（AMD）患者的黄斑新生血管（MNV）亚型进行准确分类。
在这项回顾性队列研究中，共纳入193只初治新生血管性AMD眼。根据结构OCT特征，将每个病例分为MNV亚型（1型、2型或3型）。基于卷积神经网络（CNN）的深度学习模型通过交叉验证进行训练，以对MNV亚型进行分类。预处理包括图像数据的均匀化，以优化分类中层信息的使用。性能指标包括敏感性、特异性和受试者操作特征（ROC）曲线下面积（AUC），分别在有和没有均匀化的情况下进行评估。
与未均匀化的数据相比，所有模型的均匀化OCT数据均提高了分类性能。报道的1型MNV的最高敏感性和特异性分别为96.7%和84.9%；2型分别为100.0%和85.5%；3型分别为84.9%和87.9%。1型、2型和3型MNV的AUC分别为0.95、0.97和0.91。遮挡敏感性分析揭示了分类的关键区域，突出了MNV亚型之间明显的解剖差异。
所提出的深度学习模型在基于结构OCT对MNV亚型进行分类方面表现出高准确性，均匀化后性能有所提高。该工具可协助临床医生准确、高效地诊断MNV亚型，可能影响新生血管性AMD的治疗决策和患者预后。
