An Improved Deep Transfer Learning Approach For Specific Lung Disease Classification
DOI:
https://doi.org/10.69980/ajpr.v28i5.649Keywords:
Deep Learning, CNN, Transfer Learning, Lung Diseases, classificationAbstract
In every region of the world, the prevalence of lung illness is quite significant. Lung conditions such as pneumonia, tuberculosis, fibrosis, and chronic obstructive pulmonary disease are examples of conditions that are included in this category. A respiratory disease must be identified as soon as possible in order to be of the utmost importance. As a result of this, a great number of computational models that make use of deep learning (DL) and image processing have been established. Within the scope of this research, an innovative deep learning transfer learning (TL) method for the classification of a specific lung ailment is investigated in great detail. The availability of image datasets such as computed tomography (CT) and X-ray scans has made it possible for us to easily obtain important medical information. Combining TL with convolutional neural networks (CNN) is the approach that this method takes. In this study, the utilisation of Kaggle datasets that are accessible to the general public and contain chest X-ray images and CT scans of the lungs is investigated. The value of data augmentation strategies and preprocessing stages in improving the performance of models is investigated in depth in this article. The purpose of this study is to evaluate three enhanced CNN architectures by placing them through a series of tests. These designs are modified VGG-16, improved VGG-19, and improved MobileNetV2. Based on the findings, it appears that the improved VGG-19 model exhibits superior recall, precision, and accuracy when compared to alternative designs on both the training dataset and the testing dataset. This method's improved accuracy in diagnosing instances of pneumonia and tuberculosis is further highlighted by comparing it to earlier research that has demonstrated its usefulness in assessing medical images. This comparison highlights the fact that this method is improved. In general, this work introduces a complete method for classifying lung disorders and gives useful insights that can be utilised in the course of future research in the fields of deep learning and medical imaging.
References
1. Agarwala, S., Kumar, A., Dhara, A. K., Thakur, S. B., Sadhu, A., & Nandi, D. (2021). Special 417.
2. Al-Sheikh, M. H., Al Dandan, O., Al-Shamayleh, A. S., Jalab, H. A., & Ibrahim, R. W. (2023). Multi-class deep learning architecture for classifying lung diseases from chest X-Ray and CT images. Scientific Reports, 13(1), 19373.
3. Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., ... & Farhan, L. (2021). Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of big Data, 8, 1-74.
4. Arora, V., Ng, E. Y. K., Leekha, R. S., Darshan, M., & Singh, A. (2021). Transfer learning based approach for detecting COVID-19 ailment in lung CT scan. Computers in biology and medicine, 135, 104575.
5. Bailer, C., Habtegebrial, T., & Stricker, D. (2018). Fast feature extraction with CNNs with pooling layers. arXiv preprint arXiv:1805.03096.
6. Bharati, S., Podder, P., & Mondal, M. R. H. (2020). Hybrid deep learning for detecting lung diseases from X-ray images. Informatics in Medicine Unlocked, 20, 100391.
7. Convolutional Neural Network for Identification and Positioning of Interstitial Lung Disease Patterns in Computed Tomography Images. Pattern Recognition and Image Analysis, 31, 730-738.
8. Desai, M., & Shah, M. (2021). An anatomization on breast cancer detection and diagnosis employing multi-layer perceptron neural network (MLP) and Convolutional neural network (CNN). Clinical eHealth, 4, 1-11.
9. Goyal, M., Goyal, R., & Lall, B. (2019). Learning activation functions: A new paradigm for understanding neural networks. arXiv preprint arXiv:1906.09529.
10. Hashmi, M. F., Katiyar, S., Keskar, A. G., Bokde, N. D., & Geem, Z. W. (2020). Efficient pneumonia detection in chest xray images using deep transfer learning. Diagnostics, 10(6),
11. Huang, S., Lee, F., Miao, R., Si, Q., Lu, C., & Chen, Q. (2020). A deep convolutional neural network architecture for interstitial lung disease pattern classification. Medical & biological engineering & computing, 58, 725-737.
12. Lee, A. L. S., To, C. C. K., Lee, A. L. H., Li, J. J. X., & Chan, R. C. K. (2022). Model architecture and tile size selection for convolutional neural network training for non-small cell lung cancer detection on whole slide images. Informatics in Medicine Unlocked, 28, 100850.
13. Maleki, N., & Niaki, S. T. A. (2023). An intelligent algorithm for lung cancer diagnosis using extracted features from Computerized Tomography images. Healthcare Analytics, 3, 100150.
14. Manickam, A., Jiang, J., Zhou, Y., Sagar, A., Soundrapandiyan, R., & Samuel, R. D. J. (2021). Automated pneumonia detection on chest X-ray images: A deep learning approach with different optimizers and cer learning architectures. Measurement, 184, 109953.
15. Rao, G. E., Rajitha, B., Srinivasu, P. N., Ijaz, M. F., & Woźniak, M. (2024). Hybrid framework for respiratory lung diseases detection based on classical CNN and quantum classifiers from chest X-rays. Biomedical Signal Processing and Control, 88, 105567.
16. Singh, A. P., Singh, A., Kumar, A., Agarwal, H., Yadav, S., & Gupta, M. (2024). Development of an Artificial Neural Network-Based Image Retrieval System for Lung Disease Classification and Identification. Engineering Proceedings, 62(1), 2. Springer International Publishing.
17. Tekerek, A., & Al-Rawe, I. A. M. (2023). A Novel Approach for Prediction of Lung Disease Using Chest X-ray Images Based on DenseNet and MobileNet. Wireless Personal Communications, 1-15.
18. Tomassini, S., Falcionelli, N., Sernani, P., Burattini, L., & Dragoni, A. F. (2022). Lung nodule diagnosis and cancer histology classification from computed tomography data by convolutional neural networks: A survey. Computers in Biology and Medicine, 146, 105691.
19. Zak, M., & Krzyżak, A. (2020, June). Classification of lung diseases using deep learning models. In International Conference on Computational Science (pp. 621-634). Cham:
Downloads
Published
Issue
Section
License
Copyright (c) 2025 American Journal of Psychiatric Rehabilitation
This work is licensed under a Creative Commons Attribution 4.0 International License.
This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 International License permitting all use, distribution, and reproduction in any medium, provided the work is properly cited.
