Purpose: 

To develop and validate an artificial intelligence framework for identifying multiple retinal lesions at image level and performing an explainable macular disease diagnosis at eye level in optical coherence tomography images.

Methods: 

A total of 26,815 optical coherence tomography images were collected from 865 eyes, and 9 retinal lesions and 3 macular diseases were labeled by ophthalmologists, including diabetic macular edema and dry/wet age-related macular degeneration. We applied deep learning to classify retinal lesions at image level and random forests to achieve an explainable disease diagnosis at eye level. The performance of the integrated two-stage framework was evaluated and compared with human experts.

Results: 

On testing data set of 2,480 optical coherence tomography images from 80 eyes, the deep learning model achieved an average area under curve of 0.978 (95% confidence interval, 0.971–0.983) for lesion classification. In addition, random forests performed accurate disease diagnosis with a 0% error rate, which achieved the same accuracy as one of the human experts and was better than the other three experts. It also revealed that the detection of specific lesions in the center of macular region had more contribution to macular disease diagnosis.

Conclusion: 

The integrated method achieved high accuracy and interpretability in retinal lesion classification and macular disease diagnosis in optical coherence tomography images and could have the potential to facilitate the clinical diagnosis.

中文翻译：

---

基于光学相干断层扫描图像的黄斑病诊断可解释人工智能框架的开发和验证

目的： 

开发和验证用于在图像级别识别多个视网膜病变并在光学相干断层扫描图像中在眼睛级别执行可解释的黄斑疾病诊断的人工智能框架。

方法： 

865只眼共采集26815张光学相干断层扫描图像，眼科医生标注了9种视网膜病变和3种黄斑疾病，包括糖尿病性黄斑水肿和干/湿性年龄相关性黄斑变性。我们应用深度学习在图像级别和随机森林对视网膜病变进行分类，以在眼睛级别实现可解释的疾病诊断。对集成的两阶段框架的性能进行了评估，并与人类专家进行了比较。

结果： 

在测试来自 80 只眼睛的 2,480 张光学相干断层扫描图像的数据集上，深度学习模型实现了病变分类的平均曲线下面积 0.978（95% 置信区间，0.971-0.983）。此外，随机森林以 0% 的错误率进行准确的疾病诊断，达到了与一位人类专家相同的准确率，并且优于其他三位专家。还揭示了黄斑区域中心特定病变的检测对黄斑疾病的诊断有更大的贡献。

结论： 

该集成方法在光学相干断层扫描图像中的视网膜病变分类和黄斑疾病诊断方面实现了高精度和可解释性，并具有促进临床诊断的潜力。