SmartLungXNet: A Deep Learning Framework for Accurate Multiclass Detection of Lung Diseases from Chest X-Rays

A. Bhagyalakshmi, Ramakrishna Kosuri, R. Dharani, G. Nagarjunarao, Kanakala Prathibha Malini, Nandhitha G.

2025

Abstract

The precise identification of diseases in chest X-ray image of the lung is a crucial task in recent medical screening process. This paper proposes SmartLungXNet, a deep learning based diagnostic architecture capable of identifying various lung conditions with high accuracy, using a single architecture. Using a heterogeneous, globally representative dataset, the model integrates attention mechanisms and explainable AI to improve interpretability and clinical trust. The system is efficient for real-time inference and easily interfaces with the clinical workflow via an intuitive interface. Demonstration on clinical validation shows better performance in various lung diseases and proves it is an efficient and extendible methodology for automatic radiogram examination.

Paper Citation

in Harvard Style

Bhagyalakshmi A., Kosuri R., Dharani R., Nagarjunarao G., Malini K. and G. N. (2025). SmartLungXNet: A Deep Learning Framework for Accurate Multiclass Detection of Lung Diseases from Chest X-Rays. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 13-19. DOI: 10.5220/0013856800004919

in Bibtex Style

@conference{icrdicct`2525,
author={A. Bhagyalakshmi and Ramakrishna Kosuri and R. Dharani and G. Nagarjunarao and Kanakala Malini and Nandhitha G.},
title={SmartLungXNet: A Deep Learning Framework for Accurate Multiclass Detection of Lung Diseases from Chest X-Rays},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25},
year={2025},
pages={13-19},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013856800004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25
TI - SmartLungXNet: A Deep Learning Framework for Accurate Multiclass Detection of Lung Diseases from Chest X-Rays
SN - 978-989-758-777-1
AU - Bhagyalakshmi A.
AU - Kosuri R.
AU - Dharani R.
AU - Nagarjunarao G.
AU - Malini K.
AU - G. N.
PY - 2025
SP - 13
EP - 19
DO - 10.5220/0013856800004919
PB - SciTePress