Deteksi Dini Diabetes Melitus melalui Analisis Citra Lidah Berbasis Deep Learning

Aulia Novira; Era Madona; Hazimah Widyagustin

doi:10.30630/eji.17.1.594

Aulia Novira PNP
Era Madona
Hazimah Widyagustin

DOI: https://doi.org/10.30630/eji.17.1.594

Keywords: Diabetes Melitus, Non-Invasif, Citra Lidah, Deep Learning, Convulusional Neural Network (CNN)

Abstract

Diabetes melitus merupakan penyakit metabolik kronis yang prevalensinya terus meningkat secara global. Deteksi dini menjadi kunci untuk mencegah komplikasi jangka panjang, namun metode diagnostik konvensional umumnya bersifat invasif dan membutuhkan fasilitas laboratorium. Penelitian ini mengusulkan pendekatan non-invasif untuk mendeteksi diabetes berdasarkan citra lidah menggunakan metode Convolutional Neural Network (CNN). Citra lidah diperoleh dari pasien diabetes dan non-diabetes, kemudian diproses melalui tahapan preprocessing seperti normalisasi ukuran, augmentasi data, dan segmentasi area lidah. Model CNN dirancang untuk mengekstraksi fitur visual utama seperti warna, tekstur, dan bentuk dari citra yang telah diproses. Hasil pelatihan menunjukkan bahwa model mampu mencapai akurasi 97% . Evaluasi dilakukan pula terhadap citra uji, di mana model secara konsisten dapat mengklasifikasikan lidah pasien dengan benar ke dalam kelas diabetes maupun non-diabetes. Temuan ini menunjukkan bahwa pendekatan berbasis deep learning memiliki potensi besar dalam pengembangan sistem deteksi dini diabetes yang cepat, efisien, dan non-invasif, terutama untuk diterapkan pada perangkat mobile atau layanan kesehatan berbasis teknologi.

Downloads

Download data is not yet available.

References

[1] T. Babu, P. M. Ebin, and R. R. Nair, “Deep Learning-Driven Non-Invasive Diabetes Diagnosis Using Tongue Images,” in 2024 International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS), IEEE, Dec. 2024, pp. 1703–1708. doi: 10.1109/ICICNIS64247.2024.10823196.
[2] V. Bhatnagar and P. P. Bansod, “Convolution Neural Network Based Multi-Label Disease Detection Using Smartphone Captured Tongue Images,” Applied Sciences, vol. 14, no. 10, p. 4208, May 2024, doi: 10.3390/app14104208.
[3] T. Jiang et al., “Deep Learning Multi-label Tongue Image Analysis and Its Application in a Population Undergoing Routine Medical Checkup,” Evidence-Based Complementary and Alternative Medicine, vol. 2022, pp. 1–12, Sep. 2022, doi: 10.1155/2022/3384209.
[4] A. Hidayat, “The burden of the complications of diabetes mellitus,” Universa Medicina, vol. 35, no. 2, p. 65, Aug. 2016, doi: 10.18051/UnivMed.2016.v35.65-67.
[5] K. M. Hisar, “A Global Public Health Issue: Diabetes Mellitus,” in Current Perspective on Diabetes Mellitus in Clinical Sciences, Istanbul: Nobel Tip Kitabevleri, 2023, pp. 1–8. doi: 10.69860/nobel.9786053359111.1.
[6] Md. J. Hossain, Md. Al‐Mamun, and Md. R. Islam, “Diabetes mellitus, the fastest growing global public health concern: Early detection should be focused,” Health Sci Rep, vol. 7, no. 3, Mar. 2024, doi: 10.1002/hsr2.2004.
[7] S. Lerman Ginzburg, “Diabetes,” Open Encyclopedia of Anthropology, Oct. 2023, doi: 10.29164/23diabetes.
[8] S. Mahajan, P. K. Sarangi, A. K. Sahoo, and M. Rohra, “Diabetes Mellitus Prediction using Supervised Machine Learning Techniques,” in 2023 International Conference on Advancement in Computation & Computer Technologies (InCACCT), IEEE, May 2023, pp. 587–592. doi: 10.1109/InCACCT57535.2023.10141734.
[9] Z. Tian, D. Wang, X. Sun, C. Cui, and H. Wang, “Predicting the diabetic foot in the population of type 2 diabetes mellitus from tongue images and clinical information using multi-modal deep learning,” Front Physiol, vol. 15, Dec. 2024, doi: 10.3389/fphys.2024.1473659.
[10] T. Babu, P. M. Ebin, and R. R. Nair, “Deep Learning-Driven Non-Invasive Diabetes Diagnosis Using Tongue Images,” in 2024 International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS), IEEE, Dec. 2024, pp. 1703–1708. doi: 10.1109/ICICNIS64247.2024.10823196.
[11] R. S. and J. S. Dr., “IMPROVEMENT IN TONGUE COLOR IMAGE ANALYSIS FOR DISEASE IDENTIFICATION USING DEEP LEARNING BASED DEPTHWISE SEPARABLE CONVOLUTION MODEL,” Indian Journal of Computer Science and Engineering, vol. 12, no. 1, pp. 21–34, Feb. 2021, doi: 10.21817/indjcse/2021/v12i1/211201082.
[12] I. M. Nooralli, S. B. Patil, and G. Kulkarni, “Predictive Analytics for Tongue Diseases: A Comparative Study of Deep Learning Models,” in 2024 International Conference on Innovation and Novelty in Engineering and Technology (INNOVA), IEEE, Dec. 2024, pp. 1–5. doi: 10.1109/INNOVA63080.2024.10847037.
[13] A. I. Khan et al., “Computational Approach for Detection of Diabetes from Ocular Scans,” Comput Intell Neurosci, vol. 2022, pp. 1–8, May 2022, doi: 10.1155/2022/5066147.
[14] V. Feyzi, A. Komeili, S. M. Kumeleh, H. Vahedi, N. Izadi, and A. S. Sahlabadi, “Examining the Concordance between ART and ERIN Methods in the Assessment of Musculoskeletal Disorders in Dental Students of Shahid Beheshti University of Medical Sciences,” Open Dent J, vol. 18, no. 1, May 2024, doi: 10.2174/0118742106302342240502094935.
[15] Towfiq Tomal, “Tongue__DIABETES,” https://www.kaggle.com/datasets/towfiqtomal/tongue-diabetes?select=output_valid.