Yao Hsin-Yu, Tseng Kuang-Wen, Nguyen Hong-Thai, Kuo Chie-Tong, Wang Hsiang-Chen
Department of Ophthalmology, Kaohsiung Armed Forced General Hospital, Kaohsiung City 80284, Taiwan.
Department of Medicine, Mackay Medical College, 46, Sec. 3, Zhongzheng Rd., Sanzhi Dist., New Taipei 25245, Taiwan.
J Clin Med. 2020 May 26;9(6):1613. doi: 10.3390/jcm9061613.
A methodology that applies hyperspectral imaging (HSI) on ophthalmoscope images to identify diabetic retinopathy (DR) stage is demonstrated. First, an algorithm for HSI image analysis is applied to the average reflectance spectra of simulated arteries and veins in ophthalmoscope images. Second, the average simulated spectra are categorized by using a principal component analysis (PCA) score plot. Third, Beer-Lambert law is applied to calculate vessel oxygen saturation in the ophthalmoscope images, and oxygenation maps are obtained. The average reflectance spectra and PCA results indicate that average reflectance changes with the deterioration of DR. The G-channel gradually decreases because of vascular disease, whereas the R-channel gradually increases with oxygen saturation in the vessels. As DR deteriorates, the oxygen utilization of retinal tissues gradually decreases, and thus oxygen saturation in the veins gradually increases. The sensitivity of diagnosis is based on the severity of retinopathy due to diabetes. Normal, background DR (BDR), pre-proliferative DR (PPDR), and proliferative DR (PDR) are arranged in order of 90.00%, 81.13%, 87.75%, and 93.75%, respectively; the accuracy is 90%, 86%, 86%, 90%, respectively. The F1-scores are 90% (Normal), 83.49% (BDR), 86.86% (PPDR), and 91.83% (PDR), and the accuracy rates are 95%, 91.5%, 93.5%, and 96%, respectively.
展示了一种将高光谱成像（HSI）应用于检眼镜图像以识别糖尿病视网膜病变（DR）阶段的方法。首先，将一种HSI图像分析算法应用于检眼镜图像中模拟动脉和静脉的平均反射光谱。其次，使用主成分分析（PCA）得分图对平均模拟光谱进行分类。第三，应用比尔-朗伯定律计算检眼镜图像中的血管氧饱和度，并获得氧合图。平均反射光谱和PCA结果表明，平均反射率随DR的恶化而变化。由于血管疾病，G通道逐渐降低，而R通道随血管中的氧饱和度逐渐增加。随着DR的恶化，视网膜组织的氧利用率逐渐降低，因此静脉中的氧饱和度逐渐增加。诊断的敏感性基于糖尿病引起的视网膜病变的严重程度。正常、背景性DR（BDR）、增殖前期DR（PPDR）和增殖性DR（PDR）的排列顺序分别为90.00%、81.13%、87.75%和93.75%；准确率分别为90%、86%、86%、90%。F1分数分别为90%（正常）、83.49%（BDR）、86.86%（PPDR）和91.83%（PDR），准确率分别为95%、91.5%、93.5%和96%。
