Department of Ophthalmology, Eye Center of the Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China.
Department of Ophthalmology, The First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China.
Front Public Health. 2022 Sep 21;10:1005700. doi: 10.3389/fpubh.2022.1005700. eCollection 2022.
To apply deep learning (DL) techniques to develop an automatic intelligent classification system identifying the specific types of myopic maculopathy (MM) based on macular optical coherence tomography (OCT) images using transfer learning (TL).
In this retrospective study, a total of 3,945 macular OCT images from 2,866 myopic patients were recruited from the ophthalmic outpatients of three hospitals. After culling out 545 images with poor quality, a dataset containing 3,400 macular OCT images was manually classified according to the ATN system, containing four types of MM with high OCT diagnostic values. Two DL classification algorithms were trained to identify the targeted lesion categories: Algorithm A was trained from scratch, and algorithm B using the TL approach initiated from the classification algorithm developed in our previous study. After comparing the training process, the algorithm with better performance was tested and validated. The performance of the classification algorithm in the test and validation sets was evaluated using metrics including sensitivity, specificity, accuracy, quadratic-weighted kappa score, and the area under the receiver operating characteristic curve (AUC). Moreover, the human-machine comparison was conducted. To better evaluate the algorithm and clarify the optimization direction, the dimensionality reduction analysis and heat map analysis were also used to visually analyze the algorithm.
Algorithm B showed better performance in the training process. In the test set, the algorithm B achieved relatively robust performance with macro AUC, accuracy, and quadratic-weighted kappa of 0.986, 96.04% (95% CI: 0.951, 0.969), and 0.940 (95% CI: 0.909-0.971), respectively. In the external validation set, the performance of algorithm B was slightly inferior to that in the test set. In human-machine comparison test, the algorithm indicators were inferior to the retinal specialists but were the same as the ordinary ophthalmologists. In addition, dimensionality reduction visualization and heatmap visualization analysis showed excellent performance of the algorithm.
Our macular OCT image classification algorithm developed using the TL approach exhibited excellent performance. The automatic diagnosis system for macular OCT images of MM based on DL showed potential application prospects.
应用深度学习（DL）技术，通过迁移学习（TL），开发一种基于黄斑光学相干断层扫描（OCT）图像的自动智能分类系统，以识别特定类型的近视性黄斑病变（MM）。
在这项回顾性研究中，从三所医院的眼科门诊共招募了 2866 名近视患者的 3945 张黄斑 OCT 图像。剔除 545 张质量较差的图像后，使用 ATN 系统手动对包含 3400 张黄斑 OCT 图像的数据集进行分类，该系统包含四种具有高 OCT 诊断价值的 MM 类型。使用两种 DL 分类算法来识别目标病变类别：算法 A 从头开始训练，算法 B 使用从我们之前研究中开发的分类算法开始的 TL 方法进行训练。比较训练过程后，测试和验证了性能更好的算法。使用包括敏感性、特异性、准确性、二次加权 kappa 评分和接收器操作特征曲线（AUC）下面积在内的指标评估分类算法在测试集和验证集的性能。此外，还进行了人机比较。为了更好地评估算法并阐明优化方向，还使用降维分析和热图分析进行了直观的算法分析。
算法 B 在训练过程中表现出更好的性能。在测试集中，算法 B 表现出相对稳健的性能，其宏观 AUC、准确性和二次加权 kappa 分别为 0.986、96.04%（95%CI：0.951，0.969）和 0.940（95%CI：0.909-0.971）。在外部验证集中，算法 B 的性能略逊于测试集。在人机比较测试中，算法指标逊于视网膜专家，但与普通眼科医生相同。此外，降维可视化和热图可视化分析显示算法性能优异。
我们使用 TL 方法开发的黄斑 OCT 图像分类算法具有出色的性能。基于 DL 的 MM 黄斑 OCT 图像自动诊断系统具有潜在的应用前景。
