Kombinasi U-Net DenseNet untuk Klasifikasi Dermoskopi Kanker Kulit
Abstract
Kanker kulit merupakan jenis kanker yang paling umum ditemukan. Namun kanker kulit masih dapat merusak struktur organ hingga menyebabkan kematian. Resiko kanker kulit dapat dimitigasikan apabila dapat ditangani sejak awal. Oleh karena itu mendeteksi apabila seseorang terkena melanoma sangatlah penting. Salah satu metode yang umum digunakan ahli dermatologi untuk mendeteksi melanoma adalah dengan melakukan dermoskopi dan mengujinya dengan bantuan algoritma visi komputer. Pada penelitian ini dibangun sebuah model kombinasi segmentasi dengan klasifikasi menggunakan U-Net dan DenseNet. Model ini bekerja dengan pertama melakukan segmentasi terhadap input menggunakan U-Net yang kemudian hasil dari model tersebut akan digunakan untuk melakukan masking pada input untuk model klasifikasi. Pelatihan model dilakukan menggunakan dataset HAM10000 dan dilakukan secara bertahap. Pelatihan dimulai dari model U-Net, kemudian langsung digabungkan dengan model kombinasi untuk mengevaluasi performa dari model serta metode masking yang digunakan. Pada akhirnya diperoleh sebuah model kombinasi dengan nilai akurasi 76%, dengan presisi rata-rata berbobot 76%, recall rata-rata berbobot 76%, dan F1-Score rata-rata berbobot 75% beserta model segmentasi dengan mean IoU sebesar 87%, F1-Score rata-rata sebesar 92%, Sensitivitas 94%, dan specificity 97%.
Kata kunci: kanker kulit, densenet, unet, segmentasi, klasifikasi, masking
References
E. R. Parker, "The influence of climate change on skin cancer incidence – A review of the evidence," International Journal of Women's Dermatology, pp. 17-27, 2021.
R. Gordon, "Skin Cancer: An Overview of Epidemiology and Risk Factors," Seminars in Oncology Nursing, vol. 29, no. 3, pp. 160-169, 2013.
G. Liezel L, L. John T and A. Faisal Rehman, "Non-melanoma skin cancer," Clinical Medicine, vol. 16, no. 1, pp. 62-65, 2016.
H. Md. Kamrul, A. Md. Asif, Y. Choon Hwai and Y. Guang, "A survey, review, and future trends of skin lesion segmentation and classification," Computers in Biology and Medicine, vol. 155, p. 106624, 2023.
A. A. Adegun and S. Viriri, "FCN-Based DenseNet Framework for Automated Detection and Classification of Skin Lesions in Dermoscopy Images," IEEE Access, vol. 8, pp. 150377-150396, 2020.
M. Dildar, S. Akram, M. Irfan, H. U. Khan, M. Ramzan, A. R. Mahmood, S. A. Alsaiari, A. H. M. Saeed, M. O. Alraddadi and M. H. Mahnashi, "Skin Cancer Detection: A Review Using Deep Learning Techniques," International Journal of Environmental Research and Public Health, vol. 18, no. 10, 2021.
N. Zhang, Y.-X. Cai, Y.-Y. Wang, Y.-T. Tian, X.-L. Wang and B. Badami, "Skin cancer diagnosis based on optimized convolutional neural network," Artificial Intelligence in Medicine, vol. 102, p. 101756, 2020.
P. Tschandl, C. Rosendahl and H. Kittler, "The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions," Scientific Data, no. 1, 2018.
V. Anand, S. Gupta, D. Koundal and K. Singh, "Fusion of U-Net and CNN model for segmentation and classification of skin lesion from dermoscopy images," Expert Systems with Applications, vol. 213, p. 119230, 2023.
F. Perez, C. Vasconcelos, S. Avila and E. Valle, "Data Augmentation for Skin Lesion Analysis," Cham, 2018.
N. Siddique, S. Paheding, C. P. Elkin and V. Devabhaktuni, "U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications," IEEE Access, vol. 9, pp. 82031-82057, 2021.
W. Jiangtao, N. I. R. Ruhaiyem and F. Panpan, "A Comprehensive Review of U-Net and Its Variants: Advances and Applications in Medical Image Segmentation," IET Image Processing, vol. 19, p. e70019, 2025.
T. Li, W. Jiao, L.-N. Wang and G. Zhong, "Automatic DenseNet Sparsification," IEEE Access, vol. 8, pp. 62561-62571, 2020.
G. Huang, Z. Liu, L. Van Der Maaten and K. Q. Weinberger, "Densely Connected Convolutional Networks," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
A. Mahbod, P. Tschandl, G. Langs, R. Ecker and I. Ellinger, "The effects of skin lesion segmentation on the performance of dermatoscopic image classification," Computer Methods and Programs in Biomedicine, vol. 197, p. 105725, 2020.
D. Müller, I. Soto-Rey and F. Kramer, "Towards a guideline for evaluation metrics in medical image segmentation," BMC Research Notes, vol. 15, no. 1, p. 210, 2022.
H. Basak, R. Kundu and R. Sarkar, "MFSNet: A multi focus segmentation network for skin lesion segmentation," Pattern Recognition, vol. 128, p. 108673, 2022.
