KLASIFIKASI RETINOPATI DIABETIK PADA CITRA RETINA MENGGUNAKAN RESNET50 DENGAN PERBANDINGAN VGG16 DAN MOBILENETV2

Dwi Ari Suryaningrum, Annisa Rasyid, Arya Wiratama

Abstract


Retinopati diabetik merupakan salah satu komplikasi mikrovaskular diabetes melitus yang dapat menyebabkan gangguan penglihatan hingga kebutaan permanen apabila tidak dideteksi sejak dini. Perkembangan deep learning, khususnya Convolutional Neural Network (CNN), telah membuka peluang dalam pengembangan sistem skrining otomatis berbasis citra retina. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi retinopati diabetik menggunakan arsitektur ResNet50 dan membandingkan performanya dengan VGG16 serta MobileNetV2. Dataset yang digunakan meliputi EyePACS, APTOS 2019 Blindness Detection, dan Messidor dengan lima kelas tingkat keparahan retinopati diabetik. Tahapan penelitian mencakup pra-pemrosesan citra, augmentasi data, penerapan transfer learning, pelatihan model, serta evaluasi menggunakan accuracy, precision, recall, F1-score, confusion matrix, dan ROC-AUC. Hasil eksperimen menunjukkan bahwa ResNet50 memberikan performa terbaik dengan accuracy sebesar 95,00%, precision 94,10%, recall 93,20%, F1-score 93,65%, dan nilai AUC sebesar 0,979. Analisis statistik menggunakan paired t-test menunjukkan bahwa peningkatan performa ResNet50 signifikan dibandingkan model pembanding (p < 0,05). Selain itu, analisis confusion matrix menunjukkan bahwa ResNet50 mampu mengurangi kesalahan klasifikasi pada kelas retinopati diabetik tingkat berat. Hasil penelitian menunjukkan bahwa ResNet50 memiliki kemampuan generalisasi yang baik dan berpotensi diterapkan sebagai sistem pendukung skrining retinopati diabetik berbasis kecerdasan buatan.

Keywords


Retinopati Diabetik; Citra Retina; Convolutional Neural Network; ResNet50; Transfer Learning

Full Text:

PDF

References


A. Gargeya and T. Leng, “Automated identification of diabetic retinopathy using deep learning,” Ophthalmology, vol. 124, no. 7, pp. 962–969, 2017.

R. Gulshan et al., “Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs,” JAMA, vol. 316, no. 22, pp. 2402–2410, 2016.

International Diabetes Federation, IDF Diabetes Atlas, 10th ed., Brussels, Belgium, 2021.

S. Sengupta et al., “Evaluation of machine learning systems for diabetic retinopathy screening,” IEEE Access, vol. 7, pp. 93200–93212, 2019.

S. M. Anwar et al., “Medical image analysis using convolutional neural networks: A review,” Journal of Medical Systems, vol. 42, no. 11, pp. 1–13, 2018.

J. Chen and M. Wu, “Recent advances in deep learning for medical image analysis,” Pattern Recognition, vol. 122, pp. 108–120, 2022.

H. Pratt et al., “Convolutional neural networks for diabetic retinopathy,” Image and Vision Computing, vol. 58, pp. 221–228, 2017.

I. Kandel and M. Castelli, “Transfer learning with convolutional neural networks for diabetic retinopathy classification,” Applied Sciences, vol. 10, no. 6, pp. 2020–2032, 2020.

K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” International Conference on Learning Representations, 2015.

K. He et al., “Deep residual learning for image recognition,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778, 2016.

A. G. Howard et al., “MobileNets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, 2017.

M. Feng et al., “Enhanced ResNet50 for diabetic retinopathy classification using attention mechanisms,” IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 4, pp. 1261–1272, 2023.

P. Rajalakshmi et al., “MobileNetV2 for diabetic retinopathy screening on mobile devices,” IEEE Transactions on Medical Imaging, vol. 41, no. 3, pp. 789–799, 2022.

A. K. Raj et al., “Cross-dataset generalization in diabetic retinopathy classification,” Computers in Biology and Medicine, vol. 149, pp. 105931, 2022.

T. Zhang et al., “Domain adaptation techniques for retinal image classification,” Pattern Recognition Letters, vol. 158, pp. 52–60, 2022.

M. J. Harvey and P. C. Fox, “Explainable AI techniques for retinal disease detection,” Frontiers in Medicine, vol. 9, pp. 903210, 2022.

Y. Liu et al., “Deep learning-based diabetic retinopathy classification using retinal fundus images,” Computers in Biology and Medicine, vol. 145, pp. 105451, 2022.

N. Islam, M. Hasan, and S. Hossain, “Performance analysis of transfer learning models for diabetic retinopathy detection,” IEEE Access, vol. 10, pp. 88421–88435, 2022.

S. Karthik et al., “Retinal image classification using hybrid deep learning framework for diabetic retinopathy detection,” Biomedical Signal Processing and Control, vol. 84, pp. 104812, 2023.




DOI: https://doi.org/10.29100/jipi.v11i2.10580

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika)
ISSN 2540-8984
Published by
Prodi Pendidikan Teknologi Informasi
Universitas Bhinneka PGRI

Website :https://jurnal.stkippgritulungagung.ac.id/index.php/jipi/index
Email: jipistkippti@gmail.com

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.