DETEKSI RETINOPATI DIABETIK ON-DEVICE MENGGUNAKAN MODEL MOBILENETV2 PADA APLIKASI MOBILE BERBASIS FLUTTER

Ali Mustopa; Agung Sasongko; Ade Hendini

doi:10.23960/jitet.v14i1.8641

Authors

Ali Mustopa Universitas Bina Sarana Informatika
Agung Sasongko Universitas Bina Sarana Informatika
Ade Hendini Universitas Bina Sarana Informatika

DOI:

https://doi.org/10.23960/jitet.v14i1.8641

Abstract Views: 0 File Views: 0

Keywords:

Retinopati Diabetik, MobileNetV2, Deep Learning, TensorFlow Lite, Aplikasi Mobile

Abstract

Retinopati Diabetik (RD) adalah penyebab utama kebutaan yang dapat dicegah, namun skrining manual seringkali sulit diakses dan mahal. Penelitian ini bertujuan membangun aplikasi mobile yang efisien untuk deteksi RD menggunakan Deep Learning. Model CNN berbasis MobileNetV2 dilatih dengan teknik transfer learning pada dataset APTOS 2019 yang dikelompokkan menjadi 2 kelas (RD dan Non-RD). Model terbaik dikonversi ke format TensorFlow Lite (TFLite) dengan optimasi kuantisasi untuk implementasi on-device pada aplikasi Flutter. Hasil penelitian menunjukkan model mencapai akurasi 97.3% pada data uji. Konversi TFLite berhasil mereduksi ukuran file sebesar 74% (menjadi 11.8 MB) dengan latensi inferensi rata-rata ~150 ms. Penelitian ini membuktikan kelayakan implementasi MobileNetV2 pada aplikasi mobile untuk skrining RD yang cepat, akurat, hemat biaya, dan menjaga privasi secara offline. Solusi ini berpotensi besar meningkatkan deteksi dini di fasilitas layanan kesehatan dengan sumber daya terbatas

Downloads

Download data is not yet available.

References

I. D. Federation, IDF Diabetes Atlas. Brussels, Belgium: International Diabetes Federation, 2021. [Online]. Available: https://diabetesatlas.org

Z. L. Teo, Y. C. Tham, M. Yu, M. L. Chee, T. H. Rim, and N. Cheung, “Global prevalence of diabetic retinopathy and projection of burden through 2045: Systematic review and meta-analysis,” Ophthalmology, vol. 128, no. 11, pp. 1580–1591, 2021, doi: 10.1016/j.ophtha.2021.04.040.

B. A. Umam, “Identifikasi Penyakit Daun Tembakau Berbasis Pengolahan Citra dengan Metode Convolutional Neural Network ( CNN ) Dan Metode Transfer Learning,” 2024.

V. 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, doi: 10.1001/jama.2016.17216.

D. S. W. Ting et al., “Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes,” JAMA, vol. 318, no. 22, pp. 2211–2223, 2017, doi: 10.1001/jama.2017.18152.

A. G. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” 2017, [Online]. Available: http://arxiv.org/abs/1704.04861

M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510–4520. doi: 10.1109/CVPR.2018.00474.

M. H. Aly, M. S. El-Bialy, and A. A. M. Khalaf, “A mobile application for diabetic retinopathy screening based on deep learning,” J. King Saud Univ. - Comput. Inf. Sci., vol. 32, no. 7, pp. 804–811, 2020, doi: 10.1016/j.jksuci.2019.05.008.

A. Kaphle, M. Karkee, D. Maru, and A. Shrestha, “A lightweight CNN model for diabetic retinopathy classification on a mobile application,” Heal. Inf. Sci. Syst., vol. 9, no. 1, p. 10, 2021, doi: 10.1007/s13755-021-00143-5.

I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016. [Online]. Available: https://www.deeplearningbook.org/

G. A. Pratama, E. Y. Puspaningrum, and H. Maulana, “Convolutional Neural Network dan Faster Region Convolutional Neural Network untuk Klasifikasi Kualitas Biji Kopi Arabika,” J. Inform. dan Tek. Elektro Terap., vol. 12, no. 3, 2024, doi: 10.23960/jitet.v12i3.4887.

J. Ruiz, M. Mahmud, S. Jahan, and M. Islam, “On the feasibility of mobile phones for medical imaging analysis,” Mob. Networks Appl., vol. 26, pp. 1234–1245, 2021, doi: 10.1007/s11036-020-01732-3.

N. Priaulx, “Digital health and the rural-urban divide,” J. Bioeth. Inq., vol. 17, no. 3, pp. 453–460, 2020, doi: 10.1007/s11673-020-10002-2.

Z. Abed, R. D. Al-Dabbagh, and S. Naji, “Cloud-based deep learning system for automatic detection of diabetic retinopathy,” in IEEE International Conference on Cloud Computing in Emerging Markets (CCEM), 2020. doi: 10.1109/CCEM51005.2020.00020.

S. Qummar et al., “A deep learning ensemble approach for diabetic retinopathy detection,” IEEE Access, vol. 7, pp. 150530–150539, 2019, doi: 10.1109/ACCESS.2019.2947484.

S. R. Islam, D. Kwak, M. H. Kabir, M. Hossain, and K. S. Kwak, “The internet of things for health care: a comprehensive survey,” IEEE Access, vol. 3, pp. 678–708, 2015, doi: 10.1109/ACCESS.2015.2437951.

P. K. Darabi, “Diagnosis of Diabetic Retinopathy,” 2019, Kaggle. [Online]. Available: https://www.kaggle.com/datasets/pkdarabi/diagnosis-of-diabetic-retinopathy

A. Mustopa, A. Sasongko, H. M. Nawawi, S. K. Wildah, and S. Agustiani, “Chicken Disease Detection Based on Fases Image Using EfficientNetV2L Model,” SISTEMASI, vol. 12, no. 3, p. 715, 2023, doi: 10.32520/stmsi.v12i3.2807.

H. C. et al. Shin, “Deep convolutional neural networks for computer-aided detection: Cnn architectures, dataset characteristics and transfer learning,” IEEE Trans. Med. Imaging, vol. 35, no. 5, pp. 1285–1298, 2016, doi: 10.1109/TMI.2016.2528162.

D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv Prepr. arXiv1412.6980, 2014, [Online]. Available: https://arxiv.org/abs/1412.6980

R. et al. David, “TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems,” arXiv Prepr. arXiv2104.10491, 2021.

M. D’Amico and T. King, Flutter for Beginners: An introductory guide to building cross-platform mobile applications. Birmingham, UK: Packt Publishing, 2023.