A Multi-Branch Convolutional Neural Network for Screening and Staging of Diabetic Retinopathy Based on Wide-Field Optical Coherence Tomography Angiography - 07/12/22
Abstract |
Background |
Diabetic retinopathy (DR) is one of the major causes of blindness in adults suffering from diabetes. With the development of wide-field optical coherence tomography angiography (WF-OCTA), it is to become a gold standard for diagnosing DR. The demand for automated DR diagnosis system based on OCTA images have been fostered due to large diabetic population and pervasiveness of retinopathy cases.
Materials and methods |
In this study, 288 diabetic patients and 97 healthy people were imaged by the swept-source optical coherence tomography (SS-OCT) with 12 mm × 12 mm single scan centered on the fovea. A multi-branch convolutional neural network (CNN) was proposed to classify WF-OCTA images into four grades: no DR, mild non-proliferative diabetic retinopathy (NPDR), moderate to severe NPDR, and proliferative diabetic retinopathy (PDR).
Results |
The proposed model achieved a classification accuracy of 96.11%, sensitivity of 98.08% and specificity of 89.43% in detecting DR. The accuracy of the model for DR staging is 90.56%, which is higher than that of other mainstream convolution neural network models.
Conclusion |
This technology enables early diagnosis and objective tracking of disease progression, which may be useful for optimal treatment to reduce vision loss.
Le texte complet de cet article est disponible en PDF.Graphical abstract |
Highlights |
• | Use wide-field optical coherence tomography angiography images instead of fundus photography. |
• | Propose a multi-branch convolutional neural network. |
• | Our model can automatically diagnose diabetic retinopathy. |
Keywords : Diabetic retinopathy (DR), Convolutional neural network (CNN), Optical coherence tomography angiography (OCTA)
Plan
Vol 43 - N° 6
P. 614-620 - décembre 2022 Retour au numéroBienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?