Klasifikasi Kanker Kulit menggunakan Metode Convolutional Neural Network dengan Arsitektur VGG-16

REGITA AGUSTINA, RITA MAGDALENA, NOR KUMALASARI CAECAR PRATIWI

Sari


ABSTRAK

Kanker kulit merupakan penyakit yang ditimbulkan oleh perubahan karakteristik sel penyusun kulit dari normal menjadi ganas, yang menyebabkan sel tersebut membelah secara tidak terkendali dan merusak DNA. Deteksi dini dan diagnosis yang akurat diperlukan untuk membantu masyarakat mengindentifikasi apakah kanker kulit atau hanya kelainan kulit biasa. Pada studi ini, dirancang sebuah sistem yang dapat mengklasifikasi kanker kulit dengan memanfaatkan citra kulit pasien yang kemudian diolah menggunakan metode Convolutional Neural Network (CNN) arsitektur VGG-16. Dataset yang digunakan berupa citra jaringan kanker sebanyak 4000 gambar. Proses diawali dengan input citra, pre-processing, pelatihan model dan pengujian sistem. Hasil terbaik diperoleh pada pengujian tanpa pre-processing CLAHE dan Gaussian filter, dengan menggunakan hyperparameter optimizer SGD, learning rate 0,001, epoch 50 dan batch size 32. Akurasi yang diperoleh sebesar 99,70%, loss 0,0055, presisi 0,9975, recall 0,9975 dan f1-score 0,9950.

Kata kunci: Kanker kulit, CNN, VGG-16

 

ABSTRACT

Skin cancer is a disease caused by changes in the characteristics of skin cells from normal to malignant, which causes the cells to divide uncontrollably and damage DNA. Early detection and accurate diagnosis are necessary to help the public identify whether skin cancer or just a common skin disorder. In this study, a system was designed that can classify skin cancer by utilizing images of patients' skin which is then processed using the Convolutional Neural Network (CNN) method of VGG-16 architecture. Dataset used in the form of cancer tissue imagery as many as 4000 images. The process begins with image input, pre-processing, model training and system testing. The best results were obtained on testing without pre-processing CLAHE and Gaussian filters, using hyperparameters, SGD optimizer, learning rate 0.001, epoch 50 and batch size 32. Accuracy obtained by 99.70%, loss 0.0055, precision 0.9975, recall 0.9975 and f1-score 0.9950.

Keywords: Skin cancer, CNN, VGG-16


Kata Kunci


Kanker kulit; CNN; VGG-16

Teks Lengkap:

PDF

Referensi


Bera, S., & Shrivastava, V. K. (2020). Analysis of various optimizers on deep convolutional neural network model in the application of hyperspectral remote sensing image classification. International Journal of Remote Sensing, 41(7), 2664–2683. https://doi.org/10.1080/01431161.2019.1694725

Bruballa, R. G. (2018). Understanding Categorical Cross-Entropy Loss, Binary Cross-Entropy Loss, Softmax Loss, Logistic Loss, Focal Loss and all those confusing names. Retrieved from https://gombru.github.io/2018/05/23/cross_entropy_loss/

Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542 (7639), 115–118. https://doi.org/10.1038/nature21056

Fu’adah, Y. N., Pratiwi, N. C., Pramudito, M. A., & Ibrahim, N. (2020). Convolutional neural network (CNN) for automatic skin cancer classification system. IOP Conference Series: Materials Science and Engineering, 982(1), 0–10. https://doi.org/10.1088/1757-899X/982/1/012005

Hendaria, M. P., Asmarajaya, A., & Maliawan, S. (2013). Kanker kulit. Universitas Udayana.

Munthe, T. L. D. (2018). Klasifikasi citra kanker kulit berdasarkan tingkat keganasan kanker pada melanosit menggunakan deep convolutional neural network (DCNN). Repositori Institusi Universitas Sumatera Utara (RI-USU), 44–48.

Prabowo, D., & Pramunendar, R. (2019). Implementasi metode clahe menggunakan parameter distribusi untuk meningkatkan kualitas citra objek bawah air. Prosiding SNST Ke-10, (pp. 264–269).

Prasetyo, E. (2012). Data Mining: Konsep dan aplikasi menggunakan MATLAB (1st ed.). Yogyakarta Andi Offset.

Pratiwi, N. K. C., Fu’adah, Y. N., & Edwar. (2021). Early detection of deforestation through satellite land geospatial images based on CNN architecture. Jurnal Infotel, 13(2), 1–8.

Savera, T. R., Suryawan, W. H., & Setiawan, A. W. (2020). Deteksi dini kanker kulit menggunakan K-Nn dan early detection of skin cancer using K-Nn and convolutional. 7(2), 373–378. https://doi.org/10.25126/jtiik.202072602

Silpa, S. R., & V, C. (2013). A review on skin cancer. International Research Journal of Pharmacy, 4(8), 83–88. https://doi.org/10.7897/2230-8407.04814

Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, (pp. 1–14).

Tsaniyah, R. A. D., Aspitriani, & Fatmawati. (2015). Prevalensi dan Gambaran Histopatologi Nevus Pigmentosus di Bagian Patologi Anatomi Rumah Sakit Dr . Mohammad Hoesin Palembang Periode 1 Januari 2009-31 Desember 2013. Mks, 2, 110–114. https://media.neliti.com/media/publications/181832-ID-prevalensi-dan-gambaranhistopatologi-ne.pdf

Wang, M., Zheng, S., Li, X., & Qin, X. (2014). A new image denoising method based on the bilateral filter. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, (pp. 163–167). https://doi.org/10.1109/ICASSP.2008.4517763

Wilvestra, S., Lestari, S., & Asri, E. (2018). Studi retrospektif kanker kulit di poliklinik ilmu kesehatan kulit dan kelamin RS Dr. M. Djamil Padang periode tahun 2015-2017. Jurnal Kesehatan Andalas, 7, 47. https://doi.org/10.25077/jka.v7i0.873




DOI: https://doi.org/10.26760/elkomika.v10i2.446

Refbacks

  • Saat ini tidak ada refbacks.


_______________________________________________________________________________________________________________________

ISSN (print) : 2338-8323 | ISSN (electronic) : 2459-9638

Publisher:

Department of Electrical Engineering Institut Teknologi Nasional Bandung

Address: 20th Building  Institut Teknologi Nasional Bandung PHH. Mustofa Street No. 23 Bandung 40124

Contact: +627272215 (ext. 206)

Email: jte.itenas@itenas.ac.id________________________________________________________________________________________________________________________


Free counters!

Web Analytics Made Easy - StatCounter

Statistic Journal

Jurnal ini terlisensi oleh Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons License