Preprint / Version 1

Deteksi Covid-19 Pada Citra Sinar-x Dada menggunakan Pre-training Deep Autoencoder

Keywords:

unsupervised learning, COVID-19 X-ray, autoencoder, deep learning

Abstract

Pada awal tahun 2020, virus baru bernama COVID-19 diidentifikasi di kota Wuhan, China. Virus inimenyebarkebanyak negaradengan sangat cepat hingga pada waktu yang berdekatan WHO menetapkan virus tersebut sebagai pandemi. Virus ini menyerangsistempernafasan dandapat menyebabkan komplikasi terhadap penyakit lainnya seperti pneumonia, gagal ginjal, hingga dapat menyebabkan pengidap meninggal dunia. Deteksi virus COVID-19 ini umumnya menggunakan tes laboratorium dengan metode RT-PCR untuk mendapatkan hasil yang akurat. Sayangnya, tes ini membutuhkan waktu yang cukup lama yaitu sekitar 24 jam untuk mendapatkan hasil. Selain menggunakan tes RT-PCR, beberapa penelitian menunjukkan bahwa deteksi menggunakan citra sinar-X menunjukkan hasil yang cukup akurat dengan waktu prediksi yang lebih cepat. Citra sinar-X yang didominasi warna dalam jangkauan grayscale dapat dikatakan memiliki karakteristik yang berbeda jika dibandingkan dengan citra secara umumsehingga dalam penelitian inieksperimendilakukan terhadap pelatihan untuk kasus klasifikasi citra sinar-X dengan melatih model mulai dari awal (scratch). Namun seringkali model yang dilatih tanpa adanya pretraining menyebabkan model tidak dapat mencapai performa yang cukup baik. Salah satu bentuk metode pretrainingyang dapatdigunakanadalah penggunaan autoencoder sebagai model untuk rekonstruksi citra. Dalam penelitian ini pelatihan menggunakan pretraining autoencoder menghasilkan akurasi terbaik sebesar 81,78% dengantambahan metode CutMix, color manipulation, dan rotation sebagai augmentasi. Kami juga membuktikan bahwa penambahan pretraining autoencoder secara konsisten dapat meningkatkan akurasi hingga 2,58% pada model yang dilatih dariawal (scratch).

References

ABBAS, A., ABDELSAMEA, M. M., & GABER, M. M. (2021). Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network. Applied Intelligence, 854-864. doi:https://doi.org/10.1007/s10489-020-01829-7

DAI, W.-C., ZHANG, H.-W., YU, J., XU, H.-J., CHEN, H., LUO, S.-P., . . . LIN, F. (2020). CT Imaging and Differential Diagnosis of COVID-19. Canadian Association of Radiologists Journal, 71(2), 195-200. doi:https://doi.org/10.1177/0846537120913033

DEBRABATA, D., KUMAR, R., AISHIK, B., D. JUDE, H., DEEPAK, G., ASHISH, K., & OSCAR, C. (2020). Early diagnosis of COVID-19-affected patients based on X-ray and computed tomography images using deep learning algorithm. Springer-Verlag GmbH Germany, part of Springer Nature 2020, 9. doi:https://doi.org/10.1007/s00500-020-05275-y

HARRIS, E., MARCU, A., PAINTER, M., NIRANJAN, M., PRÜGEL-BENNET, A., & HARE, J. (2020). FMix: Enhancing Mixed Sample Data Augmentation. Vision, Learning, and Control Group. Retrieved from https://www.researchgate.net/publication/339551062_FMix_Enhancing_Mixed_Sample_Data_Augmentation

HE, K., ZHANG, X., REN, S., & SUN, J. (2015). Deep Residual Learning for Image Recognition. doi:https://doi.org/10.1109/CVPR.2016.90

HUANG, C., WANG, Y., LI, X., REN, L., ZHAO, J., HU, Y., & ZHANG, L. (2020). Clinical Features of Patients Infected with 2019 Novel Coronavirus in Wuhan, China. 395, 10. doi:https://doi.org/10.1016/S0140-6736(20)30183-5

KEMENTERIAN KESEHATAN REPUBLIK INDONESIA. (2020). Pedoman Pencegahan dan Pengendalian Coronavirus Disease (COVID19) (3rd ed.). Jakarta.

KHAN, A. I., SHAH, J. L., & BHAT, M. M. (2020). CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images. Elsevier, 9. doi:https://doi.org/10.1016/j.cmpb.2020.105581

KINGMA, D. P., & BA, J. (2015). Adam: A Method for Stochastic Optimization. 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 1-15. Retrieved from https://arxiv.org/abs/1412.6980

LI, D., FU, Z., & XU, J. (2020). Stacked-autoencoder-based model for COVID-19 diagnosis on CT images. Applied Intelligence. doi:https://doi.org/10.1007/s10489-020-02002-w

MINAEE, S., KAFIEH, R., SONKA, M., YAZDANI, S., & JAMALIPOUR, G. S. (2020). Deep-COVID: Predicting COVID-19 from chest X-ray images using deep transfer learning. Elsevier, 65, 9. doi:https://doi.org/10.1016/j.media.2020.101794

OZTURK, T., TALO, M., YILDIRIM, E. A., BALOGLU, U. B., YILDIRIM, O., & ACHARYA, U. R. (2020). Automated detection of COVID-19 cases using deep neural networks with X-ray images. Elsevier Public Health Emergency Collection. doi:https://doi.org/10.1016/j.compbiomed.2020.103792

PANWAR, H., GUPTA, P., SIDDIQUI, M. K., MENENDEZ, R. M., & SINGH, V. (2020). Application of deep learning for fast detection of COVID-19 in X-Rays using nCOVnet. Elsevier, 9. doi:https://doi.org/10.1016/j.chaos.2020.109944

RUGERY, P. (2020, September 8). Explanation of YOLO V4 a one stage detector. Retrieved from Becoming Human: Artificial Intelligence Magazine: https://becominghuman.ai/explaining-yolov4-a-one-stage-detector-cdac0826cbd7

SALAMEH, J., LEEFLANG, M., HOOFT, L., & ISLAM, N. (2020). Thoracic imaging tests for the diagnosis of COVID-19. In Thoracic imaging tests for the diagnosis of COVID-19 (p. 97). Cochrane Library. doi:https://doi.org//10.1002/14651858.CD013639.pub3

SANGDOO, Y., DONGYOON, H., JUNSUK, C., SEONG, J. O., YOUNGJOON, Y., & SANGHYUK, C. (2019). CutMix : Regularization Strategy to Train Strong Classi?ers with Localizable Features. 1-14. doi:https://doi.org/10.1109/iccv.2019.00612

SHVETS, A., IGLOVIKOV, V., RAKHLIN, A., & KALININ, A. A. (2018). Angiodysplasia Detection and Localization Using Deep Convolutional Neural Networks. 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), 612-617. doi:https://doi.org/10.1109/ICMLA.2018.00098

TARESH, M., ZHU, N., & ALI, T. A. (2020). Transfer learning to detect COVID-19 automatically from X-ray images, using convolutional neural networks. medRxiv - Radiology and Imaging. doi:10.1101/2020.08.25.20182170

TURKOGLU, M. (2021). COVIDetectioNet: COVID-19 diagnosis system based on X-ray images using features selected from pre-learned deep features ensemble. Artificial Intelligence Applications for COVID-19, Detection, Control, Prediction, and Diagnosis, 1213–1226. doi:https://doi.org/10.1007/s10489-020-01888-w

WORLD HEALTH ORGANIZATION. (2020). World Health Organization. Retrieved December 6, 2020, from https://www.who.int/emergencies/diseases/novel-coronavirus-2019/question-and-answers-hub/q-a-detail/coronavirus-disease-covid-19

YUDISTIRA, N., WIDODO, A. W., & RAHAYUDI, B. (2020). Deteksi COVID-19 Pada Citra Sinar-X Dada Menggunakan Deep Learning Yang Efisien. Jurnal Teknologi Informasi dan Ilmu Komputer, 1289-1296. doi:https://doi.org/10.25126/jtiik.2020763651

ZHANG, H., CISSE, M., DAUPHIN, Y. N., & LOPEZ-PAZ, D. (2018). mixup: BEYOND EMPIRICAL RISK MINIMIZATION. Arxiv. Retrieved from https://arxiv.org/abs/1710.09412

Downloads

Posted

2021-09-21

License

Copyright (c) 2021 Novanto Yudistira

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.