Research on hybrid algorithms for diagnosing eye diseases

Iskandarova , Sayyora, Iskandarova , Feruza, Eraliyev , Seitjan

Innovations in Science and Technologies · 2026-yil

Annotatsiya

To develop and rigorously evaluate a novel hybrid deep learning framework for simultaneous diagnosis of four critical ocular conditions, more precisely: cataract, diabetic retinopathy, glaucoma, and normal fundus - using a relatively small but balanced dataset of fundus images. The study addresses the challenge of achieving high diagnostic accuracy with limited data through architectural innovation and optimized training protocols. We propose a parallel hybrid convolutional neural network that integrates EfficientNetB3 (for global contextual feature extraction) and DenseNet121 (for local detailed feature extraction). The model processes dual-resolution inputs (300×300 and 224×224 pixels) simultaneously. A novel two-phase training strategy was implemented: Phase 1 (10 epochs) with frozen ImageNet-pre-trained backbones to train only the newly added classification heads, followed by Phase 2 (15 epochs) with selective fine-tuning of upper layers. The model incorporated label smoothing (ε=0.05), L2 regularization, and dropout to combat overfitting. The dataset comprised 3,200 curated fundus images (800 per class), split into training (2,560), validation (320), and test (320) sets. The hybrid model achieved a peak validation accuracy of 92.19% and a test accuracy of 91.87%, significantly outperforming standalone EfficientNetB3 and DenseNet121 models (p<0.001, McNemar's test). Diabetic retinopathy was detected with nearperfect precision (98.75%), while cataract, glaucoma, and normal classes showed robust and balanced performance. The proposed parallel hybrid architecture, combined with a disciplined twophase training regimen, successfully overcomes the limitations of small medical datasets. It effectively leverages complementary feature hierarchies from two state-of-the-art networks, establishing a new benchmark for multi-class ocular disease diagnosis. This work demonstrates that architectural synergy and meticulous training design can yield clinically relevant accuracy without requiring prohibitively large datasets.

Maqola ma’lumotlari
MualliflarIskandarova , Sayyora, Iskandarova , Feruza, Eraliyev , Seitjan
JurnalInnovations in Science and Technologies
NashriyotТошкент давлат иқтисодиёт университети
ISSN3030-3451
Nashr sanasi2026-02-16
Jild3
Son2
Betlar67-79
TilIngliz
Ilmiy sohaIqtisodiyot
Indeksga qo‘shilgan2026-08-26

Maqolaning asl sahifasi

Kalit so‘zlar

Ocular Disease Diagnosis, Deep Learning, Hybrid Neural Networks, EfficientNet, DenseNet, Fundus Imaging, Multi-class Classification, Small Dataset Learning

Ilmiy soha

Iqtisodiyot

Iqtibos keltirish

APAIskandarova , Sayyora, Iskandarova , Feruza, & Eraliyev , Seitjan (2026). RESEARCH ON HYBRID ALGORITHMS FOR DIAGNOSING EYE DISEASES. Innovations in Science and Technologies, 3(2), 67-79. https://innoist.uz/index.php/ist/article/view/1458
GOST (OAK)Iskandarova , Sayyora, Iskandarova , Feruza, Eraliyev , Seitjan RESEARCH ON HYBRID ALGORITHMS FOR DIAGNOSING EYE DISEASES // Innovations in Science and Technologies. – 2026. – T. 3, № 2. – P. 67-79.
MLAIskandarova , Sayyora, Iskandarova , Feruza, and Eraliyev , Seitjan. “RESEARCH ON HYBRID ALGORITHMS FOR DIAGNOSING EYE DISEASES.” Innovations in Science and Technologies, 3(2), 67-79, 2026. https://innoist.uz/index.php/ist/article/view/1458
ChicagoIskandarova , Sayyora, Iskandarova , Feruza, and Eraliyev , Seitjan. “RESEARCH ON HYBRID ALGORITHMS FOR DIAGNOSING EYE DISEASES.” Innovations in Science and Technologies, 3(2), 67-79 (2026). https://innoist.uz/index.php/ist/article/view/1458
HarvardIskandarova , Sayyora, Iskandarova , Feruza, and Eraliyev , Seitjan (2026) ‘RESEARCH ON HYBRID ALGORITHMS FOR DIAGNOSING EYE DISEASES’, Innovations in Science and Technologies, 3(2), 67-79. https://innoist.uz/index.php/ist/article/view/1458
BibTeX
@article{iskandarovasayyora2026,
  title = {RESEARCH ON HYBRID ALGORITHMS FOR DIAGNOSING EYE DISEASES},
  author = {Iskandarova , Sayyora and Iskandarova , Feruza and Eraliyev , Seitjan},
  journal = {Innovations in Science and Technologies},
  year = {2026},
  volume = {3},
  number = {2},
  pages = {67-79},
  url = {https://innoist.uz/index.php/ist/article/view/1458}
}

Boshqa maqola uchun iqtibos tayyorlash

Innovations in Science and Technologies jurnalidan boshqa maqolalar

Innovations in Science and Technologies — barcha maqolalar · 2026-yil arxivi

Iskandarova , Sayyora — boshqa maqolalari

Iqtisodiyot sohasidagi boshqa maqolalar

Iqtisodiyot sohasidagi OAK jurnallari