The binary classification of CT images of pneumonia realized by machine learning

Shiyu Zhang

doi:10.1117/12.3003860

11 October 2023 The binary classification of CT images of pneumonia realized by machine learning

Shiyu Zhang

Proceedings Volume 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023); 1280053 (2023) https://doi.org/10.1117/12.3003860
Event: 6th International Conference on Computer Information Science and Application Technology (CISAT 2023), 2023, Hangzhou, China

Abstract

In the light of the COVID-19 outbreak in late 2019, numerous researchers have attempted to employ machine learning techniques to identify CT images of pneumonia patients. However, the approach may be marred by limitations such as low accuracy, deficient datasets and inadequate model utilization. This paper is committed to using machine learning to build multiple models and improve the accuracy. Infected and uninfected lung CT images are classified in the dataset containing more than 4,000 CT images, with the objective of aiding medical practitioners in diagnosing the disease. The method can be explained as firstly training with five basic machine learning models, among which the random forest model achieves a relatively high accuracy of 97.79%; secondly, using the multi-layer back propagation neural network and convolutional neural network to predict the training set respectively. Of the two models, the convolutional neural network demonstrates superior efficacy, achieving an accuracy rate of 94.27%. Finally, the transfer learning method is used to pretrain six different models, ultimately attaining a maximum accuracy rate of 90.73% on the Xception model.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Shiyu Zhang "The binary classification of CT images of pneumonia realized by machine learning", Proc. SPIE 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), 1280053 (11 October 2023); https://doi.org/10.1117/12.3003860

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Machine learning

Education and training

Computed tomography

Data modeling

Deep learning

Random forests

Convolutional neural networks

Show All Keywords

Keywords/Phrases

Search In:

Publication Years