The aim of this study is to detect whether the quantitative textural features of optical coherencetomography angiography (OCTA) images can be used to detect the eyes in the early stage ofdiabetic retinopathy (DR) from...The aim of this study is to detect whether the quantitative textural features of optical coherencetomography angiography (OCTA) images can be used to detect the eyes in the early stage ofdiabetic retinopathy (DR) from eyes with diabetes and no DR (NDR). Textural features includingfractal dimension, contrast, correlation, entropy, energy, and homogeneity were calculatedfrom the OCTA images. The Student's t-test was performed to identify the textural featuresthat can be able to detect DR in the early stage. The area under the receiver operating characteristic(AUROC) curves, sensitivity, and specicity were calculated between the study groups.Our results indicated that the fractal dimension in ICP and SVP and the correlation in SVCshowed the statistical signicance between mild NPDR patients and NDR patients. The ROCanalysis results showed that the AUROC of the fractal dimension in ICP was 0.736 with 0.773sensitivity and 0.700 specicity. The cuto® point in ICP was 2.616. The OCTA-based fractaldimension was able to discriminate diabetic eyes with early retinopathy from healthy and NDRwith higher sensitivity and specicity. The OCTA-based correlation showed the power to differentiatethe mild NPDR eyes from the normal healthy and diabetic eyes. These results suggestthat texture-based features of OCTA have the potential to assist in the assessment of therapeuticinterventions to prevent early DR in diabetic subjects.展开更多
基金the Zhejiang Provincial Natural Science Foundation(LY20H180009)the Qianjiang Talent Plan(QJD1803009)+2 种基金the Ningbo Science and Technology Service Industry Demonstration Project(2020F031)the Ningbo Natural Science Foundation(2018A610362)the Ministry of Science and Higher Education of the Russian Federation as part of the program for increasing the competitiveness of Samara University among the world's leading research and educational centers for 2013–2020.
文摘The aim of this study is to detect whether the quantitative textural features of optical coherencetomography angiography (OCTA) images can be used to detect the eyes in the early stage ofdiabetic retinopathy (DR) from eyes with diabetes and no DR (NDR). Textural features includingfractal dimension, contrast, correlation, entropy, energy, and homogeneity were calculatedfrom the OCTA images. The Student's t-test was performed to identify the textural featuresthat can be able to detect DR in the early stage. The area under the receiver operating characteristic(AUROC) curves, sensitivity, and specicity were calculated between the study groups.Our results indicated that the fractal dimension in ICP and SVP and the correlation in SVCshowed the statistical signicance between mild NPDR patients and NDR patients. The ROCanalysis results showed that the AUROC of the fractal dimension in ICP was 0.736 with 0.773sensitivity and 0.700 specicity. The cuto® point in ICP was 2.616. The OCTA-based fractaldimension was able to discriminate diabetic eyes with early retinopathy from healthy and NDRwith higher sensitivity and specicity. The OCTA-based correlation showed the power to differentiatethe mild NPDR eyes from the normal healthy and diabetic eyes. These results suggestthat texture-based features of OCTA have the potential to assist in the assessment of therapeuticinterventions to prevent early DR in diabetic subjects.
