Multi Scale EfficientNetB0 Backed Convolutional Neural Network for Automated Pneumonia Detection from Chest Radiographs

DOI

10.2991/978-94-6239-693-7_23How to use a DOI?

Keywords

Deep Learning; Medical Imaging; Multi Scale Architecture; Radiography; Image Classification; Transfer learning

Abstract

Pneumonia is an infection caused by various pathogens, be they bacteria named Streptococcus pneumonia or viruses named Influenza and SARS-CoV-2. It is one of the leading causes of death in the elderly and young population. Traditionally, the diagnosis of pneumonia was done by an experienced physician, which can sometimes be misinterpreted. To tackle this issue, we present a novel multiscale convolutional neural network framework for analysis and detection of pneumonia from the radiographs of the chest of the individual. The model makes use of EfficientNetB0 as its backbone and then multi scale feature extraction is introduced which divides the learning into three parallel convolutional branches, whose output is then concatenated to perform downstream classification. The model is also validated alongside other traditional and state-of-the-art convolutional neural networks named DenseNet121, ResNet50, InceptionV3, VGG16, and base EfficientNetB0. The study was done on the publicly available dataset consisting of 5856 images. Results subsequently show that the proposed and upgraded model provides better accuracy and outperforms other traditional approaches.

Copyright

© 2026 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)

TY  - CONF
AU  - Shikhar Agrawal
AU  - Bina Kotiyal
PY  - 2026
DA  - 2026/06/16
TI  - Multi Scale EfficientNetB0 Backed Convolutional Neural Network for Automated Pneumonia Detection from Chest Radiographs
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 217
EP  - 229
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_23
DO  - 10.2991/978-94-6239-693-7_23
ID  - Agrawal2026
ER  -