Department of Computer & Software Engineering, National University of Sciences and Technology (NUST), Islamabad, 44000, Pakistan.
Department of Electrical Engineering, Bahria University, Islamabad, 44000, Pakistan.
J Med Syst. 2018 Oct 4;42(11):223. doi: 10.1007/s10916-018-1078-3.
Maculopathy is the group of diseases that affects central vision of a person and they are often associated with diabetes. Many researchers reported automated diagnosis of maculopathy from optical coherence tomography (OCT) images. However, to the best of our knowledge there is no literature that presents a complete 3D suite for the extraction as well as diagnosis of macula. Therefore, this paper presents a multilayered convolutional neural networks (CNN) structure tensor Delaunay triangulation and morphing based fully autonomous system that extracts up to nine retinal and choroidal layers along with the macular fluids. Furthermore, the proposed system utilizes the extracted retinal information for the automated diagnosis of maculopathy as well as for the robust reconstruction of 3D macula of retina. The proposed system has been validated on 41,921 retinal OCT scans acquired from different OCT machines and it significantly outperformed existing state of the art solutions by achieving the mean accuracy of 95.27% for extracting retinal and choroidal layers, mean dice coefficient of 0.90 for extracting fluid pathology and the overall accuracy of 96.07% for maculopathy diagnosis. To the best of our knowledge, the proposed framework is first of its kind that provides a fully automated and complete 3D integrated solution for the extraction of candidate macula along with its fully automated diagnosis against different macular syndromes.
黄斑病变是一组影响人中央视力的疾病，它们通常与糖尿病有关。许多研究人员报道了使用光学相干断层扫描 (OCT) 图像自动诊断黄斑病变。然而，据我们所知，目前还没有文献提出一种完整的 3D 套件来提取和诊断黄斑。因此，本文提出了一种基于多层卷积神经网络 (CNN) 结构张量 Delaunay 三角剖分和变形的全自动系统，该系统可以提取多达 9 层视网膜和脉络膜以及黄斑积液。此外，该系统利用提取的视网膜信息进行黄斑病变的自动诊断以及视网膜 3D 黄斑的稳健重建。该系统在从不同 OCT 机器获取的 41921 个视网膜 OCT 扫描上进行了验证，其在提取视网膜和脉络膜层方面的平均准确率达到 95.27%，在提取液病理方面的平均骰子系数达到 0.90，在黄斑病变诊断方面的总体准确率达到 96.07%，显著优于现有最先进的解决方案。据我们所知，该框架是首例提供全自动和完整的 3D 集成解决方案，用于提取候选黄斑以及针对不同黄斑综合征进行全自动诊断的框架。
