Early Detection of Dermatitis Through Comparison of Image Size Variations Using the You Only Look Once (YOLO) Framework

Septora Ivanda Gabrani Agda; Rudi Heriansyah; Zaid Romegar Mair

doi:10.59934/jaiea.v5i3.2450

Authors

Septora Ivanda Gabrani Agda Universitas Indo Global Mandiri
Rudi Heriansyah Universitas Indo Global Mandiri
Zaid Romegar Mair Universitas Indo Global Mandiri

DOI:

https://doi.org/10.59934/jaiea.v5i3.2450

Keywords:

Dermatitis; Deep Learning, Early Disease Detection; Image Size Variation; YOLO

Abstract

Dermatitis is an inflammatory skin disease characterized by symptoms such as redness and itching, requiring early identification to prevent the development of more serious conditions. The use of image processing technology and deep learning is important as a supporting solution in the process of rapid and accurate skin disease detection. This study aims to compare the performance of the You Only Look Once (YOLO) model on several image size variations, evaluate the model's ability to detect types of dermatitis based on precision, recall, and mean Average Precision (mAP) metrics, and determine the optimal number of epochs to improve model performance. The dataset used consisted of 440 images of patients' skin obtained from Dr. Rivai Abdullah General Hospital and augmented to 1,320 images. The data was divided into training, validation, and test data. The YOLOv11 model was trained to detect four types of dermatitis, namely contact dermatitis, atopic dermatitis, static dermatitis, and circumscribed neurodermatitis. The results showed that image size and epoch number affected model performance. The best configuration was obtained with an image size of 640 × 640 pixels and 150 epochs, resulting in a precision value of 0.693 and a recall value of 0.674. These results indicate that the YOLO model has the potential to be used as an effective early identification support system for dermatitis.

Downloads

Download data is not yet available.

References

S. S. Malik et al., “Adolopment Of Atopic Dermatitis Management Guidelines For Pakistan,” East. Mediterr. Heal. J., vol. 31, no. 9–10, pp. 552–559, 2025, doi: 10.26719/2025.31.10.552.

E. Heryanto, S. Sarwoko, F. Meliyanti, D. Prodi, K. Masyarakat, and S. Al-Ma’arif Baturaja, “Faktor Resiko Dermatitis Pada Anak,” J. Kesehat. Abdurahman Palembang, vol. 11, no. 1, pp. 10–16, 2022.

P. Asih, “Faktor- Faktor Yang Berhubungan Dengan Kejadian Gejala Dermatitis Kontak Iritan Pada Petani Nanas Pengguna Pestisida Di Desa Tangkit Baru Kecamatan Sungai Gelam Kabupaten Muaro Jambi Tahun 2023,” Universitas Jambi, 2024. [Online]. Available: https://repository.unja.ac.id/id/eprint/62378

S. M. Abuabara, K., Yu, A. M., Okhovat, J. P., Allen, I. E., & Langan, “The Prevalence Of Atopic Dermatitis Beyond Childhood: A Systematic Review And Meta‐Analysis Of Longitudinal Studies,” Allergy, vol. 73, pp. 696–704, 2018, doi: 10.1111/all.13320.

Z. R. Mair and M. A. Rahmanda, “Perbandingan Versi Terbaik YOLO Dalam Mendeteksi Jarak Spasi Antar Baris Tulisan Tangan,” J. Sains, Nalar, dan Apl. Teknol. Inf., vol. 4, no. 2, pp. 103–110, 2025, doi: 10.20885/snati.v4.i2.40414.

J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” 2018, [Online]. Available: http://arxiv.org/abs/1804.02767

Tanadi, Kartika, and Najaf, “Sistem Pendeteksi Penyakit Kanker Kulit Menggunakan Convolutional Neural Network Arsitektur YOLOv8 Berbasis Website,” Repeater Publ. Tek. Inform. dan Jar., vol. 2, no. 3, pp. 166–177, 2024, doi: 10.62951/repeater.v2i3.124.

P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, “A Review of Yolo Algorithm Developments,” Procedia Comput. Sci., vol. 199, pp. 1066–1073, 2021, doi: 10.1016/j.procs.2022.01.135.

M. Widyaningsih and A. Harjoko, “Identifikasi Gejala Penyakit Tanaman Jeruk Melalui Pengolahan Citra,” J. Sains Komput. dan Teknol. Inf., vol. 3, no. 2, pp. 104–113, 2021, doi: 10.33084/jsakti.v3i2.2294.

Supiyandi Supiyandi, Mona Donaon, and Muhammad Yusuf Azmi, “Analisis Sistem Aplkasi Pengolahan Citra Pada Pertanian Cerdas Untuk Pemantauan Tanaman,” SABER J. Tek. Inform. Sains dan Ilmu Komun., vol. 2, no. 3, pp. 221–228, 2024, doi: 10.59841/saber.v2i3.1443.

M. M. Sebatubun and C. Haryawan, “Implementasi Algoritma Convolutional Neural Network untuk Klasifikasi Jenis Keris,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 3, pp. 595–602, 2024, doi: 10.25126/jtiik.937260.

Nurohman, Rudi Heriansyah, Dwi Asa Verano, and Zaid Romegar Mair, “Deteksi Penyakit Diabetes Retinopathy Menggunakan Citra Digital Dengan Metode Convolutional Neural Network (Cnn),” Pros. Snast, no. November, pp. 311–320, 2024, doi: 10.34151/prosidingsnast.v1i1.5120.

Z. R. Mair et al., “An Enhanced Deep Learning Framework for Diabetic Retinopathy Classification Using Multiple Convolutional Neural Network Architectures,” Int. J. Adv. Comput. Sci. Appl., vol. 16, no. 11, pp. 769–776, 2025, doi: 10.14569/IJACSA.2025.0161176.

T. B. Sasongko, H. Haryoko, and A. Amrullah, “Analisis Efek Augmentasi Dataset dan Fine Tune pada Algoritma Pre-Trained Convolutional Neural Network (CNN),” J. Teknol. Inf. dan Ilmu Komput., vol. 10, no. 4, pp. 763–768, 2023, doi: 10.25126/jtiik.20241046583.

D. Nafis Alfarizi, R. Agung Pangestu, D. Aditya, M. Adi Setiawan, and P. Rosyani, “Penggunaan Metode YOLO Pada Deteksi Objek: Sebuah Tinjauan Literatur Sistematis,” J. Artif. Intel. dan Sist. Penunjang Keputusan, vol. 1, no. 1, pp. 54–63, 2023, [Online]. Available: https://jurnalmahasiswa.com/index.php/aidanspk

R. Supriyadi et al., “Pengembangan Aplikasi Estimasi Kalori Makanan Berbasis Citra Dengan Pendekatan Deteksi Objek Menggunakan Yolo,” J. Inform. dan Tek. Elektro Terap., vol. 14, no. 1, pp. 1393–1404, 2026, doi: 10.23960/jitet.v14i1.8545.

S. Nugroho, M. Kahfi, M. Alamsyah, A. Natanael, and P. Rosyani, “MENDETEKSI JENIS KENDARAAN di JALAN,” vol. 2, no. 2, pp. 127–131, 2024.

F. T. Hidayat and A. K. Whardana, “Deteksi Pelanggaran Sepeda Motor Menggunakan Algoritma Yolo Dan Mean Average Precision,” vol. VIII, no. September, pp. 71–79, 2024.