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