Identification of Skin Diseases in Toddlers Using  Convolutional Neural Networks

Dian Maharani; Yuhandri; Jhon Very

doi:10.35134/komtekinfo.v12i3.665

Authors

Dian Maharani Universitas Putra Indonesia YPTK Padang
Yuhandri Universitas Putra Indonesia YPTK Padang
Jhon Very Universitas Putra Indonesia YPTK Padang

DOI:

https://doi.org/10.35134/komtekinfo.v12i3.665

Keywords:

CNN, U-Net, Image Segmentation, Toddler Skin Disease, Deep Learning

Abstract

The development of Artificial Intelligence (AI) technology, particularly in the field of computer vision, has made a significant contribution to medical image analysis. Skin disease in toddlers is a common health problem, especially in developing countries. Toddlers' skin is highly susceptible to various infections and dermatological conditions, ranging from bacterial and viral infections to allergies. Some skin diseases frequently found in toddlers include eczema, dermatitis, impetigo, and fungal infections. This study aims to develop a skin disease classification system in toddlers using the Convolutional Neural Network (CNN) method that can be implemented in applications. The Convolutional Neural Network (CNN) method and the U-Net architecture are used to identify skin diseases in toddlers, requiring a fast and accurate diagnosis, but limited medical personnel and examination time are challenges. A deep learning-based system is proposed to assist the automatic identification process. The research dataset consists of 100 toddler skin images obtained from Siti Rahmah Islamic Hospital, covering various types of common skin diseases. The preprocessing process includes cropping, resizing to 128x128 pixels, normalization, and data augmentation to increase the diversity of the dataset. The CNN architecture is used in the feature extraction stage through convolution and pooling layers, while the U-Net is applied in the segmentation stage to separate the wound area from healthy skin with high precision through the encoder-decoder mechanism and skip connection. The model is trained using the Adam optimization algorithm with the Binary Cross-Entropy loss function and the accuracy evaluation metric and Mean Intersection over Union (IoU). The results show that the system is able to segment the wound area with 95.7% accuracy on the test data, and produces fast and efficient detection. The application of the CNN and U-Net methods in this study proves its effectiveness in supporting the medical diagnosis process, especially in cases of toddler skin diseases, as well as can be a reference in contributing to improving the quality of health services, especially in the diagnosis of skin diseases in toddlers and the development of computer vision-based decision support systems in the health sector.

References

N. S. Irjanto, R. H. Kiswanto, I. S. Sabra, and F. Rahman, “Sistem Pengenalan Penyakit Kulit Berbasis Computer Vision Dengan Metode Convolutional Neural Network (CNN),” Techno.Com, vol. 23, no. 3, pp. 716–728, 2024, doi: 10.62411/tc.v23i3.11355.

L. Hakim, Z. Sari, and Handhajani, “Klasifikasi Citra Pigmen Kanker Kulit Menggunakan Convolutional Neural Network,” J. RESTI, vol. 5, no. 2, pp. 379–385, 2021, doi: 10.29207/resti.v5i2.3001.

T. Naraloka, L. I. Kesuma, A. Sukmawati, and M. Cristianti, “Arsitektur U-Net pada Segmentasi Citra Hati sebagai Deteksi Dini Kanker Liver,” Techno.Com, vol. 21, no. 4, pp. 753–764, 2022, doi: 10.33633/tc.v21i4.6669.

D. Gunawan and H. Setiawan, “Convolutional Neural Network dalam Citra Medis,” KONSTELASI Konvergensi Teknol. dan Sist. Inf., vol. 2, no. 2, pp. 376–390, 2022, doi: 10.24002/konstelasi.v2i2.5367.

R. Gustia, S. W. Yenny, and S. Octari, “Karakteristik penyakit kulit pada anak di poliklinik kulit dan kelamin RSUP. Dr. M. Djamil Padang periode 2016-2018,” J. Kedokt. Syiah Kuala, vol. 20, no. 3, 2020, doi: 10.24815/jks.v20i3.18277.

A. N. Mario et al., “Anatomical and Physiological Characteristics of Neonatal and Infant Skin: Effects on Immunity and Dermatitis Prevalence,” J. Biol. Trop., vol. 24, no. 1b, pp. 173–180, 2024, doi: 10.29303/jbt.v24i1b.7918.

M. D. A. Putra, A. D. Baihaqie, and A. Irawan, “Sistem Pakar Diagnosa Penyakit Kulit pada Manusia dengan Menerapkan Metode Forward Chaining,” J. Ris. dan Apl. Mhs. Inform., vol. 5, no. 2, pp. 325–332, 2024, doi: 10.30998/jrami.v5i2.9191.

D. Supiyan, “Pengembangan Sistem Pakar Untuk Diagnosa Penyakit Diabetes Melitus Menggunakan Metode Forward Chaining,” bit-Tech, vol. 7, no. 3, pp. 918–927, 2025, doi: 10.32877/bt.v7i3.2244.

Siti Masrichah, “Ancaman Dan Peluang Artificial Intelligence (AI),” Khatulistiwa J. Pendidik. dan Sos. Hum., vol. 3, no. 3, pp. 83–101, 2023, doi: 10.55606/khatulistiwa.v3i3.1860.

M. R. Febrianto, “Pemanfaatan Artificial Intelligence Untuk Mengidentifikasi Dan Mengatasi Masalah Kesehatan Kulit Wajah,” Pros. Semin. Nas. Sains dan Teknol. SainTek", vol. 2, no. 1, pp. 712–720, 2025.

G. F. Tarimakase, A. Gunaryati, and S. Ningsih, “Sistem Pakar Diagnosis Penyakit Kulit Balita Menggunakan Metode Certainty Factor dan Forward Chaining,” STRING (Satuan Tulisan Ris. dan Inov. Teknol., vol. 8, no. 1, p. 120, 2023, doi: 10.30998/string.v8i1.16469.

R. Rismanto, Y. Yunhasnawa, and M. JIFTI, “Pengembangan Sistem Pakar Untuk Diagnosa Penyakit Kulit Pada Manusia Menggunakan Metode Naive Bayes,” J. Ilm. Teknol. Inf. dan Robot., vol. 1, no. 1, pp. 18–24, 2019, doi: 10.33005/jifti.v1i1.8.

R. J. Putri, D. R. Saputri, M. Ifaya, H. Himaniarwati, M. P. Zulfikar, and A. Nonovan, “Pemberian Informasi Obat Yang Tepat Kepada Masyarakat di Desa Puasana, Kecamatan Moramo Utara, Kabupaten Konawe Selatan,” J. Mandala Pengabdi. Masy., vol. 3, no. 2, pp. 196–201, 2022, doi: 10.35311/jmpm.v3i2.96.

L. Irwanisyah et al., “Analisis Strategi Peningkatan Kepatuhan Pengobatan Pada Pasien Tuberkulosis Resisten Obat (Tbc-Ro) Di Indonesia,” J. Kesehat. Masy. Seroja, vol. 4, no. 1, pp. 21–38, 2024, [Online]. Available: https://doi.org/10.572349/husada.v1i1.363

F. N. Darmawan, E. P. Silmina, and T. Hardiani, “Sistem Klasifikasi Penyakit Kulit Menggunakan Metode Convolutional Neural Network (CNN) Berbasis Website,” Pros. Semin. Nas. Penelit. dan Pengabdi. Kpd. Masy., vol. 2, no. 2, pp. 871–881, 2024.

D. A. Wijaya, A. Triayudi, and A. Gunawan, “Penerapan Artificial Intelligence Untuk Klasifikasi Penyakit Kulit Dengan Metode Convolutional Neural Network Berbasis Web,” J. Comput. Syst. Informatics, vol. 4, no. 3, pp. 685–692, 2023, doi: 10.47065/josyc.v4i3.3519.

B. S. Nusantara and M. Akbar, “Klasifikasi Penyakit Tuberculosis Berdasarkan Citra Rontgen Thorax Menggunakan Multi-Scale Convolutional Neural Network,” sudo J. Tek. Inform., vol. 3, no. 1, pp. 1–8, 2024, doi: 10.56211/sudo.v3i1.483.

K. Anwar, R. Maruf, F. Susanto, and M. B. Ryando, “Analisis Performa Deteksi Penyakit Paru-Paru dengan Model Klasifikasi Gambar Menggunakan LSTM Deep Learning,” J. Ilm. Univ. Batanghari Jambi, vol. 25, no. 1, p. 972, 2025, doi: 10.33087/jiubj.v25i1.5697.

W. Widyawati, R. Sidik, E. Nuryani, and P. Haryo Winasis, “Rancang Bangun Sistem Deteksi Katarak Menggunakan Metode Convolutional Neural Network,” J. Innov. Futur. Technol., vol. 7, no. 1, pp. 155–165, 2025, doi: 10.47080/iftech.v7i1.3895.

M. A. Djohar et al., “Liver Segmentation Using Convolutional Neural Network Method with U-Net Architecture,” J. Informatics Telecommun. Eng., vol. 6, no. 1, pp. 221–234, 2022, doi: 10.31289/jite.v6i1.6751.