Accuracy Analysis of the Capsule Network Method in Cataract Fundus Image Classification

Salshabila Putri; Arnawan Hasibuan; Rizki Suwanda

doi:10.30871/jaic.v10i4.13557

Authors

Salshabila Putri Universitas Malikussaleh
Arnawan Hasibuan Universitas Malikussaleh
Rizki Suwanda Universitas Malikussaleh

DOI:

https://doi.org/10.30871/jaic.v10i4.13557

Keywords:

Capsule Network (CapsNet), Cataract, Deep Learning, Fundus Image, Image Classification

Abstract

Cataract is one of the leading causes of blindness worldwide and requires early detection to prevent vision deterioration. Advances in artificial intelligence, particularly deep learning, have enabled the development of automated systems for medical image classification. However, conventional Convolutional Neural Networks (CNNs) tend to lose important spatial information due to pooling operations, which may affect classification performance. This study aims to analyze the accuracy of the Capsule Network (CapsNet) method for cataract classification using fundus images. The proposed method employs image preprocessing techniques, including resizing, data augmentation, and normalization, before training the CapsNet model. The model was developed using Python and the PyTorch framework. Performance evaluation was conducted using a Confusion Matrix and several metrics, namely Accuracy, Precision, Recall, Specificity, F1-score, and Area Under the Curve (AUC). Experimental results showed that the model achieved a training accuracy of 86.29% and a best validation accuracy of 81.34%. Furthermore, testing on 1,813 fundus images resulted in an accuracy of 89.85%, precision of 94.56%, recall of 84.53%, specificity of 95.15%, F1-score of 89.26%, AUC-ROC of 95.27%, and Average Precision (AP) of 94.71%. These findings indicate that CapsNet is capable of effectively classifying cataract fundus images. Although the obtained performance is consistent with the theoretical capability of CapsNet to preserve spatial relationships among image features, this capability was not directly evaluated in the present study.

Downloads

Download data is not yet available.

References

[1] World Health Organization, “Cataract,” World Health Organization. Accessed: Oct. 21, 2025. [Online]. Available: https://www.who.int/health-topics/cataract

[2] J. Dreyer, “Cataract Statistics Worldwide For 2025,” Contact Lenses Plus. Accessed: Oct. 21, 2025. [Online]. Available: https://www.contactlensesplus.com/education/cataract-stats

[3] L. Lin et al., “Global, regional, and national burden of cataract: A comprehensive analysis and projections from 1990 to 2021,” PLoS One, vol. 20, no. 6 June, pp. 1–17, 2025, doi: 10.1371/journal.pone.0326263.

[4] V. P. R. W. Amd. Kep, “Katarak: Penyakit Mata yang Sering Tidak Disadari Hingga Terlambat.” Accessed: Nov. 17, 2025. [Online]. Available: https://keslan.kemkes.go.id/view_artikel/3721/katarak-penyakit-mata-yang-sering-tidak-disadari-hingga-terlambat

[5] I. Santoso, A. M. Manurung, and E. R. Subhiyakto, “Comparison of ResNet-50, EfficientNet-B1, and VGG-16 Algorithms for Cataract Eye Image Classification,” Journal of Applied Informatics and Computing, vol. 9, no. 2, pp. 284–294, 2025, doi: 10.30871/jaic.v9i2.8968.

[6] M. A. S. Yudono, F. F. Ridha, D. Mardiyana, F. Al-Ghozi, and A. Maulana, “Klasifikasi Katarak Berdasarkan Optic Disc Citra Fundus Smartphone: Perbandingan Ekstraksi Ciri Tekstur Dan Metode Neural Network,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 12, no. 1, pp. 203–212, 2025, doi: 10.25126/jtiik.2025129254.

[7] A. Elsawy et al., “A deep network DeepOpacityNet for detection of cataracts from color fundus photographs,” Communications Medicine, vol. 3, no. 1, pp. 1–11, 2023, doi: 10.1038/s43856-023-00410-w.

[8] I. D. Mienye, T. G. Swart, G. Obaido, M. Jordan, and P. Ilono, “Deep Convolutional Neural Networks in Medical Image Analysis: A Review,” Information (Switzerland), vol. 16, no. 3, pp. 1–28, 2025, doi: 10.3390/info16030195.

[9] R. Nirthika, S. Manivannan, A. Ramanan, and R. Wang, “Pooling in convolutional neural networks for medical image analysis: a survey and an empirical study,” Neural Comput. Appl., vol. 34, no. 7, pp. 5321–5347, 2022, doi: 10.1007/s00521-022-06953-8.

[10] L. Cai, J. Gao, and D. Zhao, “A review of the application of deep learning in medical image classification and segmentation,” Ann. Transl. Med., vol. 8, no. 11, pp. 713–713, 2020, doi: 10.21037/atm.2020.02.44.

[11] S. Sabour, N. Frosst, and G. E. Hinton, “Dynamic routing between capsules,” Adv. Neural Inf. Process. Syst., vol. 2017-Decem, no. Nips, pp. 3857–3867, 2017.

[12] T. Tsuji et al., “Classification of optical coherence tomography images using a capsule network,” BMC Ophthalmol., vol. 20, no. 1, pp. 1–9, 2020, doi: 10.1186/s12886-020-01382-4.

[13] Govindharaj I, Karthick G, and Micheal G, “International Journal of Intelligent Systems And Applications In Engineering Accurate Segmentation and Classification of Glaucoma Disease Utilising Grey Wolf Based U-Net++ with Capsule Network,” Original Research Paper International Journal of Intelligent Systems and Applications in Engineering IJISAE, vol. 2024, no. 18s, pp. 445–455, 2024, [Online]. Available: www.ijisae.org

[14] G. Manohar and R. O’Reilly, “InceptionCaps: A Performant Glaucoma Classification Model for Data-Scarce Environment,” 2023 31st Irish Conference on Artificial Intelligence and Cognitive Science, AICS 2023, 2023, doi: 10.1109/AICS60730.2023.10470926.

[15] M. U. Haq, M. A. J. Sethi, and A. U. Rehman, “Capsule Network with Its Limitation, Modification, and Applications—A Survey,” Sep. 01, 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/make5030047.