Browse > Article
http://dx.doi.org/10.7742/jksr.2020.14.6.773

Diagnostic Classification of Chest X-ray Pneumonia using Inception V3 Modeling  

Kim, Ji-Yul (Daewoo general hospital)
Ye, Soo-Young (Department of Radiology Catholic University of the Pusan)
Publication Information
Journal of the Korean Society of Radiology / v.14, no.6, 2020 , pp. 773-780 More about this Journal
Abstract
With the development of the 4th industrial, research is being conducted to prevent diseases and reduce damage in various fields of science and technology such as medicine, health, and bio. As a result, artificial intelligence technology has been introduced and researched for image analysis of radiological examinations. In this paper, we will directly apply a deep learning model for classification and detection of pneumonia using chest X-ray images, and evaluate whether the deep learning model of the Inception series is a useful model for detecting pneumonia. As the experimental material, a chest X-ray image data set provided and shared free of charge by Kaggle was used, and out of the total 3,470 chest X-ray image data, it was classified into 1,870 training data sets, 1,100 validation data sets, and 500 test data sets. I did. As a result of the experiment, the result of metric evaluation of the Inception V3 deep learning model was 94.80% for accuracy, 97.24% for precision, 94.00% for recall, and 95.59 for F1 score. In addition, the accuracy of the final epoch for Inception V3 deep learning modeling was 94.91% for learning modeling and 89.68% for verification modeling for pneumonia detection and classification of chest X-ray images. For the evaluation of the loss function value, the learning modeling was 1.127% and the validation modeling was 4.603%. As a result, it was evaluated that the Inception V3 deep learning model is a very excellent deep learning model in extracting and classifying features of chest image data, and its learning state is also very good. As a result of matrix accuracy evaluation for test modeling, the accuracy of 96% for normal chest X-ray image data and 97% for pneumonia chest X-ray image data was proven. The deep learning model of the Inception series is considered to be a useful deep learning model for classification of chest diseases, and it is expected that it can also play an auxiliary role of human resources, so it is considered that it will be a solution to the problem of insufficient medical personnel. In the future, this study is expected to be presented as basic data for similar studies in the case of similar studies on the diagnosis of pneumonia using deep learning.
Keywords
Pneumonia; Artificial Intelligence; Deep learning; Pneumonia Detection; Chest X-ray image;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 Becky McCall, "COVID-19 and artificial intelligence: protecting health-care workers and curbing the spread", Lancet Digital Health, Vol 2, No. s, pp. 166-167, 2020.http://dx.doi.org/10.1016/S2589-7500(20)30054-6   DOI
2 J. Y. Baek, "Recent artificial intelligence project trends, Institute for Information & communication Technology Planning & evaluation", Weekly Technology Trend, Vol. 1899, pp. 13-26, 2016.
3 E. Musalar, S. Ekinci, O. Unek, E. Ars, H. S. Eren, B. Gurses, C. Aktas, "Conventional vs invert-grayscale X-ray for diagnosis of pneumothorax in the emergency setting", The American Journal of Emergency Medicine, Vol. 35, No. 9, pp. 1217-1221, 2017. http://dx.doi.org/10.1016/j.ajem.2017.03.031   DOI
4 Pranav Rajpurkar, Jeremy Irvin, Kaylie Zhu, "CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning", arXiv:1711.05525, 2017.
5 J. U. Sin, "Social Efforts for Loss and Recovery in the Medical Industry Following Coronavirus Infection-19", Korea Institute for Health and Social Affairs, Vol. 40, No. 3, pp. 1-6, 2020.
6 Y. Heo, "Environmental Health Aspects on the Transmission of Coronavirus Infectious Disease-19", Journal of Environmental Health Science, Vol. 46, No. 1, pp. 1-2, 2020.
7 M. Y. Cha, "Diagnosis and prediction of coronavirus-19 with artificial intelligence", Corona-19 Science Report, Vol. 4, No. 1, pp. 52-55, 2020.
8 C. Y. Park, "AI Research Trends Looking Through 2018 ICML", KAKAO AI report, Vol. 14, No. 1, pp. 126-136, 2018.
9 S. Chen, H. Wang, "SAR Target Recognition Basedon Deep learning", Data Science and Advanced Analytics, Vol. 2, No. 1, pp. 541-547, 2014. http://dx.doi.org/10.1109/DSAA.2014.7058124   DOI
10 Y. M. Seo, J. K. Han, "Deep Learning Algorithm to Identify Cancer Pictures", The Korean Institute of Broadcast and Media Engineers, Vol. 23, No. 5, pp. 669-681, 2018. http://dx.doi.org/10.5909/JBE.2018.23.5.669   DOI
11 J. K. Lee, S. J. Kim, N. J. Kwak, D. W. Kim, J. H. Ahn, "A Deep Learning Model for Judging Presence or Absence of Lesions in the Chest X-ray Images", The Journal of the Korean Institute of Information and Communication Engineering, Vol. 24, No. 2, pp. 212-218, 2020.
12 K. D. Song, M. C. Kim, S. H. Do, "The Latest Trends in the Use of Deep Learning in Radiology Illustrated Through the Stages of Deep Learning Algorithm Development", Korean Journal of Radiology, Vol. 80, No. 2, pp. 202-212, 2019. http://dx.doi.org/10.3348/jksr.2019.80.2.202   DOI
13 J. E. Oh, S. W. Shin, G.G. Kim., "The role of computer-assisted diagnosis in 2D medical imaging", The Korean Institute of Electrical Engineers, Vol. 64, No. 7, pp. 16-25, 2015.   DOI
14 M. J. Warrens, "Cohen's kappa can always be increased and decreased by combining categories", Statistical Methodology, Vol. 7, No. 6, pp. 673-677, 2010.   DOI