Proceedings of the International Conference on Smart Health and Intelligent Technologies (ICSHit-2024)

Advanced Deep Learning Models for Pneumonia Detection

Authors
Apurv Verma1, Suman Kumar Swarnkar1, *, Karanbeer Singh1, Chetan Pandey1, Yatharth Sharma1
1Department Of Computer Science and Engineering, Shri Shankaracharya Institute of Professional Management and Technology, Raipur, Chhattisgarh, India
*Corresponding author. Email: sumanswarnkar17@gmail.com
Corresponding Author
Suman Kumar Swarnkar
Available Online 30 April 2025.
DOI
10.2991/978-94-6463-704-5_15How to use a DOI?
Keywords
Pneumonia; deep learning; VGG19; chest X-ray; diagnostic accuracy
Abstract

Pneumonia, a significant global cause of morbidity and mortality, especially among populations of youngsters and the elderly, poses a critical diagnostic challenge. Early and accurate detection of pneumonia can significantly reduce mortality rates and ensure timely treatment. While conventional methods such as chest X-ray interpretation by radiologists remain the standard, they are often subjective, resource-intensive, and prone to human error. To address these challenges, deep learning (DL) techniques have gained prominence for their ability to automate and enhance diagnostic accuracy. This study focuses on using a deep convolutional neural network, the VGG19 architecture, to identify pneumonia in chest X-ray pictures. VGG19, known for its simplicity and depth, excels at deriving complex features from pictures. A tagged dataset of chest X-rays was used to train the model, employing several preprocessing methods, including image normalization and augmentation to improve generalizability. With a reported precision of 81%, the VGG19 model showed a strong performance in identifying cases of pneumonia while preserving steady memory rates and accuracy. The model does well in identifying genuine positives and lowering false negatives, which are crucial for medical diagnosis, according to an analysis of the confusion matrix. This study underscores the potential of deep learning in developing reliable and scalable diagnostic tools for pneumonia, particularly in resource-constrained environments. Future work will aim to enhance interpretability using techniques like Grad-CAM, address data imbalances, and improve adaptability across diverse populations and imaging settings. Advancing automated pneumonia detection contributes to integrating AI into healthcare for more efficient and accurate diagnostics.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the International Conference on Smart Health and Intelligent Technologies (ICSHit-2024)
Series
Advances in Intelligent Systems Research
Publication Date
30 April 2025
ISBN
978-94-6463-704-5
ISSN
1951-6851
DOI
10.2991/978-94-6463-704-5_15How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - Apurv Verma
AU  - Suman Kumar Swarnkar
AU  - Karanbeer Singh
AU  - Chetan Pandey
AU  - Yatharth Sharma
PY  - 2025
DA  - 2025/04/30
TI  - Advanced Deep Learning Models for Pneumonia Detection
BT  - Proceedings of the International Conference on Smart Health and Intelligent Technologies (ICSHit-2024)
PB  - Atlantis Press
SP  - 190
EP  - 210
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-704-5_15
DO  - 10.2991/978-94-6463-704-5_15
ID  - Verma2025
ER  -