Deep structure tensor graph search framework for automated extraction and characterization of retinal layers and fluid pathology in retinal SD-OCT scans
Deep structure tensor graph search framework for automated extraction and characterization of retinal layers and fluid pathology in retinal SD-OCT scans
复制标题
DOI：
10.1016/j.compbiomed.2018.12.015
复制
发表时间：
2019-02-01
影响因子：
7.7
通讯作者：
Yasin, Ubaidullah
中科院分区：
文献类型：
--
作者：
Hassan, Taimur;Akram, Muhammad Usman;Yasin, Ubaidullah
黄斑病变是一组影响黄斑的视网膜疾病，如果不及时治疗，会导致严重的视力障碍。过去已经提出了许多自动检测黄斑疾病的计算机辅助诊断方法。然而，据我们所知，没有文献提供用于分析健康和患病黄斑病理的端到端解决方案。本文提出了一种独立于供应商的深度卷积神经网络和基于结构张量图搜索的分割框架（CNN-STGS），用于视网膜层和流体病理学的提取和表征，沿着3-D视网膜轮廓。CNN-STGS的工作原理是首先从光学相干断层扫描（OCT）中提取九层。然后，提取的层与深度CNN模型相结合，用于自动分割囊肿和浆液性病变，然后进行自主的3-D视网膜轮廓分析。CNN-STGS已在公开可用的杜克数据集（包含来自439名受试者的累积42，281次扫描）和武装部队眼科研究所数据集（包含51名受试者的4260次OCT扫描）上进行了验证，这些数据集通过不同的OCT机器获取。CNN-STGS框架的性能通过标记的注释进行了验证，并且在各种指标上都明显优于现有的解决方案。所提出的CNN-STGS框架实现了用于分割视网膜液体的平均Dice系数为0.906，沿着用于表征来自患病视网膜OCT扫描的囊肿和浆液的准确度为98.75%。
Maculopathy is a group of retinal disorders that affect macula and cause severe visual impairment if not treated in time. Many computer-aided diagnostic methods have been proposed over the past that automatically detect macular diseases. However, to our best knowledge, no literature is available that provides an end-to-end solution for analyzing healthy and diseased macular pathology. This paper proposes a vendor-independent deep convolutional neural network and structure tensor graph search-based segmentation framework (CNN-STGS) for the extraction and characterization of retinal layers and fluid pathology, along with 3-D retinal profiling. CNN-STGS works by first extracting nine layers from an optical coherence tomography (OCT) scan. Afterward, the extracted layers, combined with a deep CNN model, are used to automatically segment cyst and serous pathology, followed by the autonomous 3-D retinal profiling. CNN-STGS has been validated on publicly available Duke datasets (containing a cumulative of 42,281 scans from 439 subjects) and Armed Forces Institute of Ophthalmology dataset (containing 4260 OCT scans of 51 subjects), which are acquired through different OCT machinery. The performance of the CNN-STGS framework is validated through the marked annotations, and it significantly outperforms the existing solutions in various metrics. The proposed CNN-STGS framework achieved a mean Dice coefficient of 0.906 for segmenting retinal fluids, along with an accuracy of 98.75% for characterizing cyst and serous fluid from diseased retinal OCT scans.