TY - JOUR
T1 - Early diabetic retinopathy diagnosis based on local retinal blood vessel analysis in optical coherence tomography angiography (OCTA) images
AU - Eladawi, Nabila
AU - Elmogy, Mohammed
AU - Khalifa, Fahmi
AU - Ghazal, Mohammed
AU - Ghazi, Nicola
AU - Aboelfetouh, Ahmed
AU - Riad, Alaa
AU - Sandhu, Harpal
AU - Schaal, Shlomit
AU - El-Baz, Ayman
N1 - Publisher Copyright:
© 2018 American Association of Physicists in Medicine
PY - 2018/10
Y1 - 2018/10
N2 - Purpose: This paper introduces a new computer-aided diagnosis (CAD) system for detecting early-stage diabetic retinopathy (DR) using optical coherence tomography angiography (OCTA) images. Methods: 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. Results: 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. Conclusion: 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.
AB - Purpose: This paper introduces a new computer-aided diagnosis (CAD) system for detecting early-stage diabetic retinopathy (DR) using optical coherence tomography angiography (OCTA) images. Methods: 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. Results: 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. Conclusion: 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.
KW - early diabetic retinopathy (DR) diagnosis
KW - local retinal blood vessels analysis
KW - optical coherence tomography angiography (OCTA)
KW - support vector machine (SVM), foveal avascular zone (FAZ)
UR - http://www.scopus.com/inward/record.url?scp=85053552746&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85053552746&partnerID=8YFLogxK
U2 - 10.1002/mp.13142
DO - 10.1002/mp.13142
M3 - Article
C2 - 30144102
AN - SCOPUS:85053552746
SN - 0094-2405
VL - 45
SP - 4582
EP - 4599
JO - Medical Physics
JF - Medical Physics
IS - 10
ER -