Lightweight Convolutional Neural Network Based on Modified LeNet for Retinal Pathology Classification in High-Resolution Fundus Imaging
DOI:
https://doi.org/10.47065/bulletincsr.v6i2.796Keywords:
CNN; LeNet; Fundus Image; Classification; Retinal PathologyAbstract
Eye disease are visual impairments that can lead to blindness if not detected early. Fundus imaging is one of the most effective methods for identifying abnormalities in the eye. With the advancement of deep neural network technologies, particularly Convolutional Neural Network (CNN), the classification of fundus image can now be performed efficiently. LeNet is a well-known CNN architecture commonly used in image classification tasks, however it has limitation when processing images with complex visual features with high resolution, such as fundus images. This study proposes a modification to the LeNet architecture to enhance it’s a ability to extract important features from images with high resolution. The modification involves adding convolutional layers and adjusting image resolution to optimize the models performance in detecting eye disease in fundus images. The dataset used consists of 4,217 fundus images, classified into four categories: normal, cataract, glaucoma, and diabetic retinopathy. Experimental result show that the original LeNet-5 achieved an accuracy 0f 76%, while the modified LeNet architecture improved the accuracy to 86%. The main contibution of this research lies in the development of a modified and lighweight LeNet architecture, which is capable of handling high-resolution fundus images while maintainig computational efficiency and producing better classification performance compared to the original LeNet.
Downloads
References
A. Tashkandi, “Eye Care: Predicting Eye Diseases Using Deep Learning Based on Retinal Images,” Computation, vol. 13, no. 4, p. 91, Apr. 2025, doi: 10.3390/computation13040091.
O. Bernabe, E. Acevedo, A. Acevedo, R. Carreno, and S. Gomez, “Classification of Eye Diseases in Fundus Images,” IEEE Access, vol. 9, pp. 101267–101276, 2021, doi: 10.1109/ACCESS.2021.3094649.
E. H. Rachmawanto et al., “Eye disease classification using deep learning convolutional neural networks,” J. Soft Comput. Explor., vol. 5, no. 4, pp. 332–341, Dec. 2024, doi: 10.52465/joscex.v5i4.493.
R. Amin, A. Ahmed, S. Shabih Ul Hasan, and H. Akbar, “Multiple Eye Disease Detection Using Deep Learning,” Found. Univ. J. Eng. Appl. Sci. Bri StylecolorblackHEC Recognized Categ. ISSN 2706-7351i, vol. 3, no. 2, pp. 14–26, Jan. 2023, doi: 10.33897/fujeas.v3i2.689.
G. Sharma, V. Anand, and S. Gupta, “Cracking Light on Cataract Detection by Implementing VGG16 Transfer Learning-Based Model on Fundus Images,” in 2023 International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE), Chennai, India: IEEE, Nov. 2023, pp. 1–6. doi: 10.1109/rmkmate59243.2023.10368860.
A. Shoukat, S. Akbar, S. A. Hassan, S. Iqbal, A. Mehmood, and Q. M. Ilyas, “Automatic Diagnosis of Glaucoma from Retinal Images Using Deep Learning Approach,” Diagnostics, vol. 13, no. 10, p. 1738, May 2023, doi: 10.3390/diagnostics13101738.
B. Menaouer, Z. Dermane, N. El Houda Kebir, and N. Matta, “Diabetic Retinopathy Classification Using Hybrid Deep Learning Approach,” SN Comput. Sci., vol. 3, no. 5, p. 357, Jul. 2022, doi: 10.1007/s42979-022-01240-8.
K. V. Naveen, B. N. Anoop, K. S. Siju, M. K. Kar, and V. Venugopal, “EffNet-SVM: A Hybrid Model for Diabetic Retinopathy Classification Using Retinal Fundus Images,” IEEE Access, pp. 1–1, 2025, doi: 10.1109/ACCESS.2025.3566073.
“Vision impairment and blindness.” Accessed: Jul. 24, 2025. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/blindness-and-visual-impairment
S. Benbakreti, S. Benbakreti, and U. Ozkaya, “The classification of eye diseases from fundus images based on CNN and pretrained models,” Acta Polytech., vol. 64, no. 1, pp. 1–11, Mar. 2024, doi: 10.14311/AP.2024.64.0001.
R. Sarki, K. Ahmed, H. Wang, Y. Zhang, and K. Wang, “Convolutional Neural Network for Multi-class Classification of Diabetic Eye Disease,” ICST Trans. Scalable Inf. Syst., p. 172436, 2021, doi: 10.4108/eai.16-12-2021.172436.
O. Ouda, E. AbdelMaksoud, A. A. Abd El-Aziz, and M. Elmogy, “Multiple Ocular Disease Diagnosis Using Fundus Images Based on Multi-Label Deep Learning Classification,” Electronics, vol. 11, no. 13, p. 1966, Jun. 2022, doi: 10.3390/electronics11131966.
R. Mohan, S. Kadry, S. Yassine, and V. Rajinikanth, “Healthy/Glaucoma Fundus Retinal Image Classification using Butterfly Algorithm Optimized ResNet-Features,” Procedia Comput. Sci., vol. 258, pp. 1804–1812, 2025, doi: 10.1016/j.procs.2025.04.432.
T. Hu, B. Yang, W. Zhang, Y. Zhang, and H. Li, “A degradation-aware enhancement network with fused features for fundus images,” Expert Syst. Appl., vol. 266, p. 125954, Mar. 2025, doi: 10.1016/j.eswa.2024.125954.
C. Guo, M. Yu, and J. Li, “Prediction of Different Eye Diseases Based on Fundus Photography via Deep Transfer Learning,” J. Clin. Med., vol. 10, no. 23, p. 5481, Nov. 2021, doi: 10.3390/jcm10235481.
J. Wang, L. Yang, Z. Huo, W. He, and J. Luo, “Multi-Label Classification of Fundus Images With EfficientNet,” IEEE Access, vol. 8, pp. 212499–212508, 2020, doi: 10.1109/access.2020.3040275.
A. Shamsan, E. M. Senan, and H. S. A. Shatnawi, “Automatic Classification of Colour Fundus Images for Prediction Eye Disease Types Based on Hybrid Features,” Diagnostics, vol. 13, no. 10, p. 1706, May 2023, doi: 10.3390/diagnostics13101706.
L. Hakim, “Regularizer based on Euler characteristic for retinal blood vessel segmentation,” Pattern Recognit. Lett., vol. 149, 2021, doi: doi:10.1016/j.patrec.2021.05.023.
N. Al-Kahtani, J. Varela-Aldás, A. Aljarbouh, M. K. Ishak, and S. M. Mostafa, “Discrete migratory bird optimizer with deep transfer learning aided multi-retinal disease detection on fundus imaging,” Results Eng., vol. 26, p. 104574, Jun. 2025, doi: 10.1016/j.rineng.2025.104574.
C. Jatmoko, H. Lestiawan, F. Agustina, and L. Erawan, “Comparative Study of Classification of Eye Disease Types Using DenseNet and EfficientNetB3,” Kinet. Game Technol. Inf. Syst. Comput. Netw. Comput. Electron. Control, Jul. 2024, doi: 10.22219/kinetik.v9i3.1931.
F. T. A. Sayyidul Laily, “Feature Extraction and Classification of Retinal Images Using Sobel Segmentation and Linear SVC,” Int. J. Artif. Intell. Med. Issues, vol. 2, no. 2, pp. 136–149, Nov. 2024, doi: 10.56705/ijaimi.v2i2.153.
Md. R. Islam and A. Matin, “Detection of COVID 19 from CT Image by The Novel LeNet-5 CNN Architecture,” in 2020 23rd International Conference on Computer and Information Technology (ICCIT), DHAKA, Bangladesh: IEEE, Dec. 2020, pp. 1–5. doi: 10.1109/ICCIT51783.2020.9392723.
X. Chen and R. Hu, “Intelligent English multiple-choice question scoring method based on LeNet-5 and strengthened convolutional module,” Syst. Soft Comput., vol. 7, p. 200314, Dec. 2025, doi: 10.1016/j.sasc.2025.200314.
S. Balasubramaniam, Y. Velmurugan, D. Jaganathan, and S. Dhanasekaran, “A Modified LeNet CNN for Breast Cancer Diagnosis in Ultrasound Images,” Diagnostics, vol. 13, no. 17, p. 2746, Aug. 2023, doi: 10.3390/diagnostics13172746.
“penyakit_mata.” Accessed: Jul. 25, 2025. [Online]. Available: https://www.kaggle.com/datasets/annisawlya/penyakit-mata
A. Nawaz, T. Ali, G. Mustafa, M. Babar, and B. Qureshi, “Multi-Class Retinal Diseases Detection Using Deep CNN With Minimal Memory Consumption,” IEEE Access, vol. 11, pp. 56170–56180, 2023, doi: 10.1109/ACCESS.2023.3281859.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Lightweight Convolutional Neural Network Based on Modified LeNet for Retinal Pathology Classification in High-Resolution Fundus Imaging
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2026 Cahyatul Mu’awanah, Lukman Hakim
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
