Faculty of Computers and Information, Mansoura University, Mansoura, 35516, Egypt.
Bioengineering Department, University of Louisville, Louisville, KY40292, USA.
Med Phys. 2018 Oct;45(10):4582-4599. doi: 10.1002/mp.13142. Epub 2018 Sep 19.
This paper introduces a new computer-aided diagnosis (CAD) system for detecting early-stage diabetic retinopathy (DR) using optical coherence tomography angiography (OCTA) images.
The proposed DR-CAD system is based on the analysis of new local features that describe both the appearance and retinal structure in OCTA images. It starts with a new segmentation approach that has the ability to extract the blood vessels from superficial and deep retinal OCTA maps. The high capability of our segmentation approach stems from using a joint Markov-Gibbs random field stochastic model integrating a 3D spatial statistical model with a first-order appearance model of the blood vessels. Following the segmentation step, three new local features are estimated from the segmented vessels and the foveal avascular zone (FAZ): (a) vessels density, (b) blood vessel calibre, and (c) width of the FAZ. To distinguish mild DR patients from normal cases, the estimated three features are used to train and test a support vector machine (SVM) classifier with the radial basis function (RBF) kernel.
On a cohort of 105 subjects, the presented DR-CAD system demonstrated an overall accuracy (ACC) of 94.3%, a sensitivity of 97.9%, a specificity of 87.0%, the area under the curve (AUC) of 92.4%, and a Dice similarity coefficient (DSC) of 95.8%. This in turn demonstrates the promise of the proposed CAD system as a supplemental tool for early detection of DR.
We developed a new DR-CAD system that is capable of diagnosing DR in its early stage. The proposed system is based on extracting three different features from the segmented OCTA images, which reflect the changes in the retinal vasculature network.
本文介绍了一种新的计算机辅助诊断（CAD）系统，用于使用光相干断层扫描血管造影（OCTA）图像检测早期糖尿病视网膜病变（DR）。
所提出的 DR-CAD 系统基于分析新的局部特征，这些特征既描述了 OCTA 图像中的外观，又描述了视网膜结构。它首先采用一种新的分割方法，该方法具有从浅层和深层视网膜 OCTA 图谱中提取血管的能力。我们的分割方法的高能力源于使用联合马尔可夫-吉布斯随机场随机模型，该模型将 3D 空间统计模型与血管的一阶外观模型相结合。在分割步骤之后，从分割后的血管和中央无血管区（FAZ）中估计三个新的局部特征：（a）血管密度，（b）血管口径和（c）FAZ 的宽度。为了将轻度 DR 患者与正常病例区分开来，使用所估计的三个特征通过具有径向基函数（RBF）核的支持向量机（SVM）分类器进行训练和测试。
在 105 名受试者的队列中，所提出的 DR-CAD 系统表现出 94.3%的总体准确性（ACC）、97.9%的敏感性、87.0%的特异性、92.4%的曲线下面积（AUC）和 95.8%的骰子相似系数（DSC）。这反过来证明了所提出的 CAD 系统作为早期发现 DR 的辅助工具的潜力。
我们开发了一种新的 DR-CAD 系统，能够在早期诊断 DR。所提出的系统基于从分割的 OCTA 图像中提取三个不同的特征，这些特征反映了视网膜血管网络的变化。
