Studi Awal Deteksi COVID-19 Menggunakan Citra CT Berbasis Deep Learning

Penulis

  • Windra Swastika Program Studi Teknik Informatika, Universitas Ma Chung

DOI:

https://doi.org/10.25126/jtiik.2020733399

Abstrak

Pada bulan Desember 2019, virus COVID-19 menyebar ke banyak negara, termasuk di Indonesia yang kemudian menjadi pandemi dan menimbulkan masalah serius karena masih belum adanya vaksin untuk mencegah penularan. Uji spesimen saluran nafas atas dan saluran nafas bawah saat ini merupakan salah satu metode yang efektif untuk mengetahui apakah seseorang terinfeksi COVID-19 atau tidak. Salah satu indikasi dari infeksi COVID-19 adalah sesak nafas atau pneumonia serta munculnya ground-glass opacity pada citra CT. Penelitian ini merupakan studi awal untuk melihat apakah citra CT dari organ thorax dapat digunakan sebagai alternatif untuk mendeteksi infeksi virus COVID-19. Deep learning digunakan untuk membuat sebuah model dengan citra CT sebagai masukan. Total 140 data citra CT yang terbagi menjadi 2 yaitu citra dari pasien terinfeksi dan citra dari subjek normal digunakan sebagai masukan pada deep learning. Proses pelatihan dilakukan menggunakan CNN dengan arsitektur VGG16 dan optimizer SGD dan Adam. Hasil yang didapatkan adalah akurasi sebesar 92,86% untuk mengklasifikasikan infeksi COVID-19 dan normal. Nilai spesifisitas dan sensitivitas sebesar 100% dan 85,71% untuk pelatihan dengan menggunakan optimizer SGD.

 

Abstract

In December 2019, the COVID-19 virus spread to many countries, including Indonesia which later became a pandemic and caused serious problems because there was still no vaccine to prevent transmission. Tests of upper and lower respiratory tract specimens are now an effective method of finding whether a person is infected with COVID-19 or not. One indication of COVID-19 infection is shortness of breath or pneumonia and the appearance of ground-glass opacity on CT images. This research is a preliminary study to see whether CT images of the thorax organs can be used as an alternative to detect COVID-19 virus. The deep learning is used to create a model with CT images as input. A total of 140 CT image data which are divided into 2 images from infected patients and images from normal subjects are used as input for deep learning. The training process is carried out using CNN with VGG16 architecture and SGD and Adam optimizers. The results obtained are 92.86% accuracy for classifying COVID-19 infections and normal. Specificity and sensitivity values were 100% and 85.71% for training using the SGD optimizer.


Downloads

Download data is not yet available.

Referensi

COHEN, J.P., MORRISON, P. AND DAO, L., 2020. COVID-19 image data collection. arXiv preprint arXiv:2003.11597.

Coronavirus Disease 2019 (COVID-19): A Perspective from China. Radiology, p.200490.

ISLAM, M.T., AOWAL, M.A., MINHAZ, A.T. AND ASHRAF, K., 2017. Abnormality detection and localization in chest x-rays using deep convolutional neural networks. arXiv preprint arXiv:1705.09850.

KINGMA, D.P. AND BA, J., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

KOMPAS, 2020. UPDATE: Tambah 17 Pasien, Total Ada 134 Kasus Positif Virus Korona. [online] Tersedia pada: KOMPAS.COM <https://gaya.tempo.co/read/877228/9-juta-orang-di-indonesia-mengalami-depresi/full&view=ok>. Diakses pada tanggal 17 Maret 2020

LI, Q., GUAN, X., WU, P., WANG, X., ZHOU, L., TONG, Y., REN, R., LEUNG, K.S., LAU, E.H., WONG, J.Y. AND XING, X., 2020. Early transmission dynamics in Wuhan, China, of novel coronavirus–infected pneumonia. New England Journal of Medicine.

MOONEY, PAUL, 2018. Chest X-Ray Images (Pneumonia). [online] Tersedia pada: https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia. Diakses pada tanggal 17 Maret 2020.

NG, M.Y., LEE, E.Y., YANG, J., YANG, F., LI, X., WANG, H., LUI, M.M.S., LO, C.S.Y., LEUNG, B., KHONG, P.L. AND HUI, C.K.M., 2020. Imaging profile of the COVID-19 infection: radiologic findings and literature review. Radiology: Cardiothoracic Imaging, 2(1), p.e200034.

RRI, 2020. Sepekan, RS Unair Telah Uji Tes Corona 500 Pasien. [online] Tersedia pada: http://rri.co.id/post/berita/802394/daerah/sepekan_rs_unair_telah_uji_tes_corona_500_pasien.html. Diakses pada tanggal 17 Maret 2020.

STEPHEN, O., SAIN, M., MADUH, U.J. AND JEONG, D.U., 2019. An efficient deep learning approach to pneumonia classification in healthcare. Journal of healthcare engineering, 2019

WANG, D., HU, B., HU, C., ZHU, F., LIU, X., ZHANG, J., WANG, B., XIANG, H., CHENG, Z., XIONG, Y. AND ZHAO, Y., 2020. Clinical characteristics of 138 hospitalized patients with 2019 novel coronavirus–infected pneumonia in Wuhan, China. Jama.

World Health Organization, 2020. Laboratory testing for coronavirus disease 2019 (COVID-19) in suspected human cases: interim guidance, 2 March 2020 (No. WHO/COVID-19/laboratory/2020.4). World Health Organization.

SIMONYAN, K. AND ZISSERMAN, A., 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

ZHOU, S., WANG, Y., ZHU, T. AND XIA, L., 2020. CT Features of Coronavirus Disease 2019 (COVID-19) Pneumonia in 62 Patients in Wuhan, China. American Journal of Roentgenology, pp.1-8.

ZU, Z.Y., JIANG, M.D., XU, P.P., CHEN, W., NI, Q.Q., LU, G.M. AND ZHANG, L.J., 2020. Coronavirus disease 2019 (COVID-19): A perspective from China. Radiology, p.200490.

Diterbitkan

22-05-2020

Terbitan

Bagian

Ilmu Komputer

Cara Mengutip

Studi Awal Deteksi COVID-19 Menggunakan Citra CT Berbasis Deep Learning. (2020). Jurnal Teknologi Informasi Dan Ilmu Komputer, 7(3), 629-634. https://doi.org/10.25126/jtiik.2020733399