ElTanboly Ahmed, Ismail Marwa, Shalaby Ahmed, Switala Andy, El-Baz Ayman, Schaal Shlomit, Gimel'farb Georgy, El-Azab Magdi
Department of Mathematical Engineering, Mansoura University, Mansoura, 35516, Egypt.
Department of Bioengineering, University of Louisville, Louisville, KY, 40292, USA.
Med Phys. 2017 Mar;44(3):914-923. doi: 10.1002/mp.12071.
Detection (diagnosis) of diabetic retinopathy (DR) in optical coherence tomography (OCT) images for patients with type 2 diabetes, but almost clinically normal retina appearances.
The proposed computer-aided diagnostic (CAD) system detects the DR in three steps: (a) localizing and segmenting 12 distinct retinal layers on the OCT image; (b) deriving features of the segmented layers, and (c) learning most discriminative features and classifying each subject as normal or diabetic. To localise and segment the retinal layers, signals (intensities) of the OCT image are described with a joint Markov-Gibbs random field (MGRF) model of intensities and shape descriptors. Each segmented layer is characterized with cumulative probability distribution functions (CDF) of its locally extracted features, such as reflectivity, curvature, and thickness. A multistage deep fusion classification network (DFCN) with a stack of non-negativity-constrained autoencoders (NCAE) is trained to select the most discriminative retinal layers' features and use their CDFs for detecting the DR. A training atlas was built using the OCT scans for 12 normal subjects and their maps of layers hand-drawn by retina experts.
Preliminary experiments on 52 clinical OCT scans (26 normal and 26 with early-stage DR, balanced between 40-79 yr old males and females; 40 training and 12 test subjects) gave the DR detection accuracy, sensitivity, and specificity of 92%; 83%, and 100%, respectively. The 100% accuracy, sensitivity, and specificity have been obtained in the leave-one-out cross-validation test for all the 52 subjects.
Both the quantitative and visual assessments confirmed the high accuracy of the proposed computer-assisted diagnostic system for early DR detection using the OCT retinal images.
在光学相干断层扫描（OCT）图像中检测（诊断）2型糖尿病患者的糖尿病视网膜病变（DR），但其视网膜外观在临床上几乎正常。
所提出的计算机辅助诊断（CAD）系统分三步检测DR：（a）在OCT图像上定位并分割12个不同的视网膜层；（b）提取分割层的特征，以及（c）学习最具判别力的特征并将每个受试者分类为正常或糖尿病患者。为了定位和分割视网膜层，使用强度和形状描述符的联合马尔可夫 - 吉布斯随机场（MGRF）模型来描述OCT图像的信号（强度）。每个分割层通过其局部提取特征的累积概率分布函数（CDF）来表征，例如反射率、曲率和厚度。训练一个具有非负约束自动编码器（NCAE）堆栈的多级深度融合分类网络（DFCN），以选择最具判别力的视网膜层特征，并使用它们的CDF来检测DR。使用12名正常受试者的OCT扫描及其由视网膜专家手绘的层图构建了一个训练图谱。
对52次临床OCT扫描（26例正常和26例早期DR，年龄在40 - 79岁的男性和女性之间平衡；40名训练受试者和12名测试受试者）进行的初步实验得出DR检测准确率、灵敏度和特异性分别为92%、83%和100%。在对所有52名受试者的留一法交叉验证测试中获得了100%的准确率、灵敏度和特异性。
定量和视觉评估均证实了所提出的计算机辅助诊断系统使用OCT视网膜图像早期检测DR的高准确性。
