Dos Santos Valentin Aranha, Schmetterer Leopold, Stegmann Hannes, Pfister Martin, Messner Alina, Schmidinger Gerald, Garhofer Gerhard, Werkmeister René M
Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Austria.
Christian Doppler Laboratory for Ocular and Dermal Effects of Thiomers, Medical University of Vienna, Austria.
Biomed Opt Express. 2019 Jan 17;10(2):622-641. doi: 10.1364/BOE.10.000622. eCollection 2019 Feb 1.
Deep learning has dramatically improved object recognition, speech recognition, medical image analysis and many other fields. Optical coherence tomography (OCT) has become a standard of care imaging modality for ophthalmology. We asked whether deep learning could be used to segment cornea OCT images. Using a custom-built ultrahigh-resolution OCT system, we scanned 72 healthy eyes and 70 keratoconic eyes. In total, 20,160 images were labeled and used for the training in a supervised learning approach. A custom neural network architecture called CorneaNet was designed and trained. Our results show that CorneaNet is able to segment both healthy and keratoconus images with high accuracy (validation accuracy: 99.56%). Thickness maps of the three main corneal layers (epithelium, Bowman's layer and stroma) were generated both in healthy subjects and subjects suffering from keratoconus. CorneaNet is more than 50 times faster than our previous algorithm. Our results show that deep learning algorithms can be used for OCT image segmentation and could be applied in various clinical settings. In particular, CorneaNet could be used for early detection of keratoconus and more generally to study other diseases altering corneal morphology.
深度学习极大地改善了目标识别、语音识别、医学图像分析及许多其他领域。光学相干断层扫描（OCT）已成为眼科护理的标准成像方式。我们探讨了深度学习是否可用于分割角膜OCT图像。使用定制的超高分辨率OCT系统，我们扫描了72只健康眼睛和70只圆锥角膜眼睛。总共20160张图像被标记并用于监督学习方法的训练。设计并训练了一种名为CorneaNet的定制神经网络架构。我们的结果表明，CorneaNet能够高精度地分割健康和圆锥角膜图像（验证准确率：99.56%）。在健康受试者和圆锥角膜患者中均生成了角膜三个主要层（上皮层、Bowman层和基质层）的厚度图。CorneaNet比我们之前的算法快50多倍。我们的结果表明，深度学习算法可用于OCT图像分割，并可应用于各种临床环境。特别是，CorneaNet可用于圆锥角膜的早期检测，更广泛地用于研究其他改变角膜形态的疾病。
