Klasifikasi Penyakit Kulit Menggunakan Model Deep Learning EfficientNet pada Citra Dermastokopi
Abstract
Penyakit kulit merupakan salah satu masalah
kesehatan yang umum terjadi dan dapat berkembang menjadi
kondisi serius seperti melanoma, salah satu jenis kanker kulit
yang berbahaya. Proses diagnosis manual sering kali memakan
waktu, bergantung pada keahlian subjektif, serta berpotensi
menghasilkan hasil yang tidak konsisten. Penelitian ini
bertujuan mengembangkan model klasifikasi penyakit kulit
berbasis Convolutional Neural Network (CNN) dengan
arsitektur EfficientNet pada citra dermatoskopi. Dataset yang
digunakan adalah HAM10000, yang berisi 10.015 citra
dermatoskopi dari tujuh kategori lesi kulit. Tahapan penelitian
meliputi preprocessing data, augmentasi untuk
menyeimbangkan kelas, serta pelatihan model dengan
pendekatan dua tahap, yaitu feature extraction dan fine-tuning.
Tiga varian model diuji, yaitu EfficientNetB0,
EfficientNetV2B0, dan EfficientNetV2B3. Hasil pengujian
menunjukkan bahwa EfficientNetV2B3 memberikan performa
terbaik dengan akurasi 90,53% dan F1-score 85,56%,
mengungguli dua model lainnya. Temuan ini menunjukkan
bahwa arsitektur EfficientNetV2B3 memiliki potensi besar
dalam mendukung sistem diagnosis berbasis citra dermatoskopi
secara lebih akurat dan efisien.
Kata kunci — CNN, EfficientNet, dermatoskopi,
HAM10000, klasifikasi penyakit kulit, akurasi
References
World Health Organization, “Ultraviolet radiation,”
WHO. Accessed: Dec 7, 2024. [Online]. Available:
https://www.who.int/news-room/factsheets/detail/ultraviolet-radiation
A. G. Pacheco and R. A. Krohling, "The impact of patient
clinical information on automated skin cancer detection,"
Computers in Biology and Medicine, vol. 116, p. 103545,
doi: 10.1016/j.compbiomed.2019.103545.
M. Tan, Q. V. Le, and Google Research, Brain Team,
“EfficientNetV2: Smaller models and faster training,”
Proceedings of the 38th International Conference on Machine
Learning, vol. 139, 2021, [Online]. Available:
https://arxiv.org/abs/2104.00298v3
P. Tschandl et al., "Human–computer collaboration for
skin cancer recognition," Nature Medicine, vol. 26, no. 8, pp.
–1234, 2020. doi: 10.1038/s41591-020-0942-0.
S. Polesie et al., "Attitudes towards artificial intelligence
within dermatology: An international online survey," British
Journal of Dermatology, vol. 183, no. 1, pp. 159–161, 2020.
doi: 10.1111/bjd.18985.
S. Rangaswamy et al., “Skin Disease Classification Using
Deep Learning,” The National Academy of Sciences, 2024.
doi: 10.1007/s40009-024-01523-z.
K. Ali, Z. A. Shaikh, A. A. Khan, and A. A. Laghari,
“Multiclass skin cancer classification using EfficientNets – a
first step towards preventing skin cancer,” Neuroscience
Informatics, vol. 2, no. 4, p. 100034, Dec. 2021, doi:
1016/j.neuri.2021.100034.
P. N. Srinivasu, J. G. SivaSai, M. F. Ijaz, A. K. Bhoi, W.
Kim, and J. J. Kang, "Classification of skin disease using
deep learning neural networks with MobileNet V2 and
LSTM," Sensors, vol. 21, no. 8, p. 2852, Apr. 2021. doi:
3390/s21082852.
J. J. Luke, K. T. Flaherty, A. Ribas, and G. V. Long,
"Targeted agents and immunotherapies: Optimizing
outcomes in melanoma," Nature Reviews Clinical Oncology,
vol. 17, no. 8, pp. 456–467, 2020. doi: 10.1038/s41571-020-
-9.
A. Sharma, S. Rani, and D. Gupta, "Artificial
Intelligence-Based Classification of Chest X-ray Images into
COVID-19 and Other Infectious Diseases," IEEE Access,
vol. 9, pp. 110143–110154, 2021. doi:
1109/ACCESS.2021.3103053.
R. S. Samir, “EfficientNet algorithm for classification of
different types of cancer,” arXiv (Cornell University), Jan.
, doi: 10.48550/arxiv.2304.08715.
T. J. Brinker, A. Hekler, J. S. Utikal, and C. Berking,
"Skin Cancer Diagnosis Using Convolutional Neural
Networks: Systematic Review," Frontiers in Medicine, vol.
, p. 193, 2020. doi: 10.3389/fmed.2020.00193.
Mader Scott K., "Skin Cancer MNIST: HAM10000,"
[Online].
Available: https://www.kaggle.com/datasets/kmader/skincancer-mnist-ham10000. [Accessed: Dec. 9, 2024].
S. KOM. , M. KOM. DR. MARIA SUSAN
ANGGREANY "Confusion Matrix," [Online]. Available:
https://socs.binus.ac.id/2020/11/01/confusion-matrix/.
[Accessed: Dec. 9, 2024].
