A Comprehensive Review of Bio-inspired and Artificial Intelligence Algorithms for Various Lung Diseases Detection | IJCT Volume 13 – Issue 2 | IJCT-V13I2P56
A Comprehensive Review of Bio-inspired and Artificial Intelligence Algorithms for Various Lung Diseases Detection | IJCT Volume 13 – Issue 2 | IJCT-V13I2P56
In the world, millions of people are affected by lung disease. Some lung-related diseases include Pneumonia, tumors, Cancer, Asthma, Tuberculosis, and Pulmonary Emphysema. Various diagnostic techniques are employed to identify such diseases, including CXR, CT, MRI, PET scan, biopsy, and pulmonary function tests. It causes symptoms such as cough, fever, chest pain, breathing difficulties, weight loss, and fatigue. This research is mainly focused on Pneumonia, tumors, and Pulmonary Emphysema. Bacteria, Viruses, and Fungi mainly cause pneumonia. It is an inflammatory disease that primarily affects the lungs’ air sacs. A lung tumor is an abnormal cell growth in the lung. It may be benign (Non-cancerous) or Malignant (Cancerous). Chronic Obstructive Pulmonary Disease is a form of Pulmonary Emphysema. It damages the alveoli, resulting in reduced lung elasticity and reduced ability to exhale. These illnesses are identified through Bio-inspired and Artificial Intelligence algorithms. The limited set of Bio-inspired algorithms comprises Swarm Intelligence-Based, Evolutionary, and Swarm-Based Metaheuristics, as well as Population-Based Stochastic Optimization Algorithms. Some of the Artificial Intelligence Algorithms are Deep Learning (DL), Machine Learning (ML), Clustering Algorithm, and Image Enhancement Algorithm. Early diagnosis of these diseases helps people save lives.
This study shows that the application of Bio-inspired and Artificial Intelligence (AI) algorithms for the diagnosis of major lung diseases, including pneumonia, Lung Tumors, and Pulmonary Emphysema. From this study, the results indicate that Hybrid Bio-inspired Meta-heuristics and Genetic algorithms have enhanced diagnostic accuracy, sensitivity, and specificity compared with Machine Learning algorithms for classification. Therefore, integrating bio-inspired algorithms and AI methods provides an effective framework for early detection of lung disease, helping reduce mortality rates and supporting clinical decision-making.
References
[1]Vijh, S., Gaurav, P., & Pandey, H. M. (2023). Hybrid bio-inspired algorithm and convolutional neural network for automatic lung tumor detection. Neural Computing and Applications, 35(33), 23711-23724.
[2]Alkhonaini, M. A., Hassine, S. B. H., Obayya, M., Al-Wesabi, F. N., Hilal, A. M., Hamza, M. A., & Al Duhayyim, M. (2022). Detection of lung tumors using ASPP-Unet with the whale optimization algorithm. CMC- Computers Materials & Continua, 72(2), 3511-3527.
[3]Devi, R. M. (2026). Reformed histogram equalization with Tasmanian devil optimization and hybrid MDHNN-MLP for lung tumor detection. Evolving Systems, 17(1), 21.
[4]Rajput, G. K., Singh, A., Kumar, S., & Doda, D. K. (2023). Identification of pneumonia in chest X-ray images using bio-inspired optimization-based LSTM. IJISAE, 11, 468-475.
[5]Khosla, T., & Verma, O. P. (2024). Optimal threshold selection for segmentation of Chest X-Ray images using an opposition-based swarm-inspired algorithm for the diagnosis of pneumonia. Multimedia Tools and Applications, 83(9), 27089-27119.
[6]Sabaawi, A. M., & Koyuncu, H. (2024). A Novel Deep Learning Framework Enhanced by Hybrid Optimization Using Dung Beetle and Fick’s Law for Superior Pneumonia Detection. Electronics, 13(20), 4042.
[7]Isaac, A., Nehemiah, H. K., Isaac, A., & Kannan, A. (2020). Computer-Aided Diagnosis system for diagnosis of pulmonary emphysema using bio-inspired algorithms. Computers in Biology and Medicine, 124, 103940.
[8]Isaac, A., Nehemiah, H. K., Dunston, S. D., Christo, V. E., & Kannan, A. (2022). Feature selection using competitive coevolution of bio-inspired algorithms for the diagnosis of pulmonary emphysema. Biomedical Signal Processing and Control, 72, 103340.
Ananthajothi, K., Rajasekar, P., & Amanullah, M. (2023). Enhanced U-Net-based segmentation and heuristically improved deep neural network for pulmonary emphysema diagnosis. Sādhanā, 48(1), 33.
How to Cite This Paper
Abirami T, Dr. W. Rose Varuna (2026). A Comprehensive Review of Bio-inspired and Artificial Intelligence Algorithms for Various Lung Diseases Detection. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
