Identifikasi Penyakit COVID-19 dan Tuberkulosis Menggunakan Metode Convolutional Neural Network Arsitektur GoogLeNet Berdasarkan Citra Rontgen Thorax
DOI:
https://doi.org/10.26418/pf.v11i3.65228Abstract
Penelitian identifikasi penyakit COVID-19 dan tuberkulosis berdasarkan rontgen thorax dengan metode convolutional neural network (CNN) arsitektur GoogLeNet telah dilakukan untuk menganalisis dan meningkatkan nilai akurasi dari penelitian CNN GoogLeNet dalam mengidentifikasi penyakit COVID-19 dan tuberkulosis. Data penelitian diperoleh dari situs Kaggle yang terdiri dari 700 citra COVID-19, 700 citra normal, dan 700 citra tuberkulosis. Metode CNN GoogLeNet dalam mengidentifikasi citra dimulai dari tahapan augmentasi, pelatihan, dan pengujian. Tahap augmentasi diawali dengan mengecilkan dan memotong citra hingga berukuran 224×224 piksel, membuat citra dirotasi secara acak 5â° dan citra dibalik posisinya secara horizontal serta citra akan digeser secara acak sebesar 0,08 berdasarkan kemiringan 0,2â°. Tahapan pelatihan dan pengujian menggunakan hyperparameter yang terdiri atas batch size (16, 32, dan 64), epoch (10, 30, dan 50), cross entropy loss, optimizer (Adam), dan learning rate 0,0001. Hasil penelitian menunjukkan bahwa CNN GoogLeNet mengidentifikasi penyakit berdasarkan derajat keabuan yang dimiliki oleh citra melalui proses feature learning dan classification. Derajat keabuan pada citra berkisar antara 0-255 sedangkan yang dimiliki penyakit COVID-19 dominan pada >200-255, penyakit tuberkulosis dominan pada >100-255, dan kondisi paru-paru normal dominan pada >0-100. Hasil penelitian berdasarkan proses klasifikasi pengujian menghasilkan akurasi 97% (batch size 16 dan epoch 10), 98% (batch size 16 dan epoch 30), 97% (batch size 16 dan epoch 50), 96% (batch size 32 dan epoch 10), 98% (batch size 32 dan epoch 30), 96% (batch size 32 dan epoch 50), 96% (batch size 64 dan epoch 10), 96% (batch size 64 dan epoch 30), dan 97% (batch size 64 dan epoch 50).
Kata Kunci : Citra Rontgen, CNN, COVID-19, GoogLeNet, Tuberkulosis
References
A. Narin, C. Kaya, and Z. Pamuk, “Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks,†Pattern Anal. Appl., vol. 24, no. 3, pp. 1207–1220, 2021, doi: 10.1007/s10044-021-00984-y.
Y. Agussationo, I. Soesanti, and W. Najib, “Klasifikasi Citra X-Ray Diagnosis Tuberkulosis Berbasis Fitur Statistis,†J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 2, no. 3, pp. 736–745, 2018, doi: 10.29207/resti.v2i3.523.
S. Purba, J., S. Zasneda, S., and S. Saragih, R., “Teknik Pemeriksaan Thorax Proyeksi Pa ( Posterior- Anterior ) Dengan Kasus Tb ( Tuberculosis ) Militer Di Instalasi Radiologi Rumah Sakit Efarina Etaham Berastagi,†Morenal Unefa J. Radiol., vol. 7, no. 1, pp. 1–10, 2019.
L. Tobias, A. Ducournau, F. Rousseau, G. Mercier, and R. Fablet, “Convolutional Neural Networks for object recognition on mobile devices: A case study,†Proc. - Int. Conf. Pattern Recognit., no. December, 2016, doi: 10.1109/ICPR.2016.7900181.
M. S. Fattah, “Deteksi Penyakit Pneumonia dan COVID-19 Menggunakan Citra X-Ray dengan Metode Convolutional Neural Network (CNN) Model GoogleNet,†UIN Sunan Ampel Surabaya, 2021. [Online]. Available: http://digilib.uinsby.ac.id/id/eprint/49030%0Ahttp://digilib.uinsby.ac.id/49030/2/M. Syaifulloh Fattah_H72217031.pdf
S. Bahri, R. Wajhillah, and M. F. Adiwisastra, “Diagnosa Tuberculosis Paru Berbasis Citra X-ray Menggunakan Convolutional Neural Network,†IJCIT (Indonesian J. Comput. Inf. Technol., vol. 6, no. September, pp. 181–186, 2021.
B. P. Hartato, “Penerapan Convolutional Neural Network pada Citra Rontgen Paru-Paru untuk Deteksi SARS-CoV-2,†J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 5, no. 4, pp. 747–759, 2021, doi: 10.29207/resti.v5i4.3153.
M. Saiful, L. M. Samsu, and Fathurrahman, “Sistem Deteksi Infeksi COVID-19 Pada Hasil X-Ray Rontgen menggunakan Algoritma Convolutional Neural Network (CNN),†Infotek J. Inform. dan Teknol., vol. 4, no. 2, pp. 217–227, 2021, doi: 10.29408/jit.v4i2.3582.
N. Yudistira, A. W. Widodo, and B. Rahayudi, “Deteksi Covid-19 pada Citra Sinar-X Dada Menggunakan Deep Learning yang Efisien,†J. Teknol. Inf. dan Ilmu Komput., vol. 7, no. 6, p. 1289, 2020, doi: 10.25126/jtiik.2020763651.
Jahandad, S. M. Sam, K. Kamardin, N. N. Amir Sjarif, and N. Mohamed, “Offline signature verification using deep learning convolutional Neural network (CNN) architectures GoogLeNet inception-v1 and inception-v3,†Procedia Comput. Sci., vol. 161, pp. 475–483, 2019, doi: 10.1016/j.procs.2019.11.147.
C. Szegedy et al., “Going Deeper with Convolutions,†CVF IEEE Xplore, pp. 1–8, 2015.
Downloads
Published
Issue
Section
License
Copyright Notice using Creative Commons License for an Online Journal
The online journal Prisma Fisika operates under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0). This copyright notice serves to inform authors, readers, and users of the terms and conditions regarding the use and distribution of the journal's content. By submitting or accessing the content, you agree to the following:
1. Content License:
a. All articles, images, and supplementary materials published in Prisma Fisika are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
b. This license permits users to copy, distribute, and adapt the content for non-commercial purposes, provided appropriate credit is given to the original authors and the journal.
c. If you remix, transform, or build upon the content, you must distribute your contributions under the same license as the original.
2. Attribution:
a. When using or sharing content from Prisma Fisika, you must properly attribute the original authors and the journal.
b. Include the title of the article, the names of all authors, Prisma Fisika, the year of publication, the volume/issue number, and the specific page numbers.
c. Provide a hyperlink to the original article on Prisma Fisika's website, if applicable.
3. Non-Commercial Use:
a. The content published in Prisma Fisika may not be used for commercial purposes without obtaining explicit permission from the copyright holders.
b. Commercial use includes, but is not limited to, reproduction or distribution of the content for financial gain, selling or licensing the content, or using the content in products or services that are sold or monetized.
4. ShareAlike:
a. If you adapt or remix the content from Prisma Fisika, you must distribute your derivative work under the same Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
b. This provision ensures that any modifications, adaptations, or remixes of the content maintain the same open licensing framework.
5. Disclaimer:
a. The views expressed in articles published in Prisma Fisika are solely those of the authors and do not necessarily reflect the opinions or policies of the journal, its editorial board, or affiliated institutions.
b. Prisma Fisika and its editors are not liable for any errors, omissions, or damages arising from the use or interpretation of the published content.
Please note that this Copyright Notice does not supersede any additional permissions or restrictions that may be granted by individual authors or copyright holders for their specific content within Prisma Fisika. For any questions or requests regarding the use of the journal's content, please contact the editorial team at prismafisika@physics.untan.ac.id.
By accessing or contributing to Prisma Fisika, you agree to comply with the terms of this Creative Commons license. Violation of these terms may result in legal consequences as governed by applicable copyright laws.
Date: 24-05-2023
Prisma Fisika
Email: prismafisika@physics.untan.ac.id
