A novel approach for detecting diabetic retinopathy using two-stream CNNs model

Pham Thi Viet Huong (Vietnam National University)
Le Duc Thinh (Hanoi University of Science and Technology)
Tran Thi Oanh (Vietnam National University)
Tran Xuan Bach (Hanoi University of Science and Technology)
Hoang Quang Huy (Hanoi University of Science and Technology)
Tran Anh Vu (Hanoi University of Science and Technology)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 41, No 1: January 2026

Major causes of visual impairment, particularly diabetic retinopathy (DR) and aged-related macular degeneration (AMD), has posed significant challenges for clinical diagnosis and treatment. Early detection and prompt intervention can help prevent severe consequences for patients. The study presents a novel approach for detecting eye diseases using a two-stream convolutional neural network (CNN) model. The first stream processes preprocessed fundus images, while the second stream analyzes high-pass filtered fundus images in the spatial frequency domain. To assess the model’s performance, we use the APTOS 2019 dataset, which was originally compiled for the Asia Pacific Tele-Ophthalmology Society 2019 Blindness Detection competition and is publicly available on Kaggle. Our method shows promise as an early screening tool for DR detection with an accuracy of 0.986.