Classification of chest x-ray picture for hyperbaric oxygen therapy based on convolutional neural network

Ting Wei Chiang; Yan Bo Chen; Chien-Teng Lin; Cheng-Yi Hsieh; Ying-Jui Huang; Wei-Chia Su; Fu-Li Hsiao

doi:10.1117/12.3036145

31 December 2024 Classification of chest x-ray picture for hyperbaric oxygen therapy based on convolutional neural network

Ting Wei Chiang, Yan Bo Chen, Chien-Teng Lin, Cheng-Yi Hsieh, Ying-Jui Huang, Wei-Chia Su, Fu-Li Hsiao

Author Affiliations +

Proceedings Volume 13487, Optics and Photonics International Congress 2024; 1348708 (2024) https://doi.org/10.1117/12.3036145
Event: Optics and Photonics International Congress, 2024, Yokohama, Japan

Abstract

In this study, we trained various pretrained convolutional neural networks to classify Chest X-Ray images. The training dataset consisted of 65 Chest X-Ray images obtained from clinical treatment and classified by expert radiologists. The objective was to differentiate between patients suitable for hyperbaric oxygen therapy and those who are not. The pretrained convolutional neural network architectures we employed included GoogLeNet, ResNet, and VGGNet. Optimal training demonstrated that all pretrained models achieved 100% accuracy on the validation dataset. Results from Grad Class activation mapping indicated that these pretrained models tended to focus on features present in clean lung images. Considering training time, model size, and feature extraction efficiency, GoogLeNet emerged as the most suitable choice for clinical application.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Ting Wei Chiang, Yan Bo Chen, Chien-Teng Lin, Cheng-Yi Hsieh, Ying-Jui Huang, Wei-Chia Su, and Fu-Li Hsiao "Classification of chest x-ray picture for hyperbaric oxygen therapy based on convolutional neural network", Proc. SPIE 13487, Optics and Photonics International Congress 2024, 1348708 (31 December 2024); https://doi.org/10.1117/12.3036145

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
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Education and training

Lung

Oxygen

Image classification

Chest imaging

Feature extraction

RGB color model

Show All Keywords

Keywords/Phrases

Search In:

Publication Years