Vol.:(0123456789)
Multimedia Tools and Applications
https://doi.org/10.1007/s11042-023-17767-8
1 3
Enhanced deep transfer learning with multi‑feature fusion
for lung disease detection
S. Vidyasri
1
· S. Saravanan
1
Received: 26 July 2023 / Revised: 22 September 2023 / Accepted: 28 November 2023
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023
Abstract
Early detection of lung disease is important for timely intervention and treatment, enhanc-
ing patient outcomes and decreasing healthcare cost. Chest X-rays are a widely employed
imaging modality to examine the structures within the chest, including the lungs and sur-
rounding tissues. Lung disease detection using chest X-rays is a critical application of
medical imaging and artifcial intelligence (AI) in healthcare. Recently, lung disease detec-
tion using deep learning (DL) becomes a signifcant research area, which has the potential
to improve early detection rate and decrease mortality rate. Therefore, this article intro-
duces a Multi-Feature Fusion Based Deep Transfer Learning with Enhanced Dung Beetle
Optimization Algorithm (MFFTL-EDBOA) for lung disease detection and classifcation.
The MFFTL-EDBOA technique aims to recognize the existence of lung diseases on CXR
images. At the primary stage, the MFFTL-EDBOA technique uses adaptive fltering (AF)
approach to remove the noise level. Besides, a multi-feature fusion-based feature extrac-
tion approach is developed based on three DL models namely DenseNet, EfcientNet, and
MobileNet. For accurate lung disease detection and classifcation purposes, the convolu-
tional fuzzy neural network (CFNN) approach is utilized. The hyperparameter tuning of
the CFNN model occurs using the EDBOA. To illustrate the enhanced lung disease detec-
tion results of the MFFTL-EDBOA technique, a sequence of experiments is carried out on
benchmark medical dataset from Kaggle repository. The experimental values highlighted
the greater result of the MFFTL-EDBOA system over other recent approaches with maxi-
mum accuracy of 98.99%.
Keywords Lung disease · Computer aided diagnosis · Multi-feature fusion · Deep transfer
learning · Chest X-ray images · Dung beetle optimizer
* S. Vidyasri
thirukamusaipriya1991@gmail.com
S. Saravanan
aucissaran@gmail.com
1
Department of Computer and Information Science, Faculty of Science, Annamalai University,
Annamalai Nagar, Chidambaram, Tamil Nadu, India