Citation :

Sivasakthi S, Radha V, "An Enhancing Lung Disease Detection with Scalable UNet-Mamba Segmentation," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 9, pp. 580-594, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I9P140

Abstract

Lung diseases are conditions that damage the lung tissues, airways or blood vessels of the lungs, causing breathing difficulties and decreased oxygen supply to the body. Computed Tomography (CT) plays a crucial role in lung disease prediction because it provides detailed cross-sectional images for detecting tumors at initial stages. However, CT scans have drawbacks such as radiation exposure, high cost, large data size, and the possibility of false positives. Recently, many Deep Learning (DL) techniques have been used to automatically analyze CT images for early and accurate detection of lung diseases, improving diagnostic efficiency. However, existing models may struggle to capture fine spatial details, leading to inaccurate boundary delineation and poor segmentation of small or low-contrast regions. Some models are also sensitive to imaging artifacts, which can reduce performance in real-world conditions. In this paper, a lung disease prediction model is developed using ResNet and Mamba Network (LRMNet) to solve the aforementioned issues for lung disease prediction. The first step is improving the model's ability to conduct pre-processing and enrich the data using a Deep Convolutional Generative Adversarial Network (DCGAN). Then, the Scalable Vision UNet-Mamba (SVU-M) model is developed to efficiently capture fine spatial details along with long-range contextual information. SVU-M leverages Scalable Vision State Space (SVSS) blocks to efficiently model the global dependencies while maintaining linear computational complexity. The integration of SVSS within a U-shaped framework enhances the boundary delineation and improves segmentation of small or low-contrast regions, which increases the efficiency against imaging artifacts for more reliable performance. The decoder feature maps of SVU-M are further processed using Global Average Pooling (GAP) to determine image-level feature representations for classification. Simultaneously, the input image is directly fed into ResNet-50 for capturing the whole image's semantic features. A Multi-Layer Perceptron (MLP) classifier is trained with the extracted features to forecast lung diseases. A total accuracy of 94.15% on the customized dataset and 93.29% on the SARS-CoV-2 CT dataset was achieved by the suggested model, according to the experimental results, exceeding the performance of other models.

Keywords

Computed Tomography, Deep Learning, Lung Disease, ResNet-50, U-Mamba.

References

[1] Wei Shi, Saverio Bellusci, and David Warburton, “Lung Development and Adult Lung Diseases,” Chest Journal, vol. 132, no. 2, pp. 651-656, 2007.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Stephanie M. Levine, and Darcy D. Marciniuk, “Global Impact of Respiratory Disease: What can we do, Together, to make a Difference?,” Chest Journal, vol. 161, no. 5, pp. 1153-1154, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Ying Zhai et al., “Global, Regional, and National Burden of Chronic Respiratory Diseases, 1990–2021 and Predictions to 2035: Analysis of Data from the Global Burden of Disease Study 2021,” Annals of Medicine, vol. 57, no. 1, pp. 1-25, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[4] William Cookson et al., “A Pandemic Lesson for Global Lung Diseases: Exacerbations are Preventable,” American Journal of Respiratory and Critical Care Medicine, vol. 205, no. 11, pp. 1271-1280, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Sunil Kumar et al., “A Methodical Exploration of Imaging Modalities from Dataset to Detection through Machine Learning Paradigms in Prominent Lung Disease Diagnosis: A Review,” BMC Medical Imaging, vol. 24, no. 1, pp. 1-42, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Shri Ramtej Kondamuri et al., “Chest CT Image based Lung Disease Classification–A Review,” Current Medical Imaging, vol. 20, no. 1, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Khamidov Obid Abdurakhmanovich et al., “Respiratory Computed Tomography,” Central Asian Journal of Medical and Natural Science, vol. 2, no. 2, pp. 1-8, 2021.
[Publisher Link]

[8] Abobaker Mohammed Qasem Farhan, Shangming Yang, and Mohammed Al-Nehari, “Automatic Classification of Lung Diseases from CT Images,” World Academy of Science, Engineering and Technology, International Journal of Health and Medical Engineering, vol. 17, no. 4, pp. 87-91, 2023.
[Publisher Link]

[9] Stefanus Tao Hwa Kieu et al., “A Survey of Deep Learning for Lung Disease Detection on Medical Images: State-of-the-Art, Taxonomy, Issues and Future Directions,” Journal of Imaging, vol. 6, no. 12, pp. 1-38, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[10] M. Jasmine Pemeena Priyadarsini et al., “Lung Diseases Detection using various Deep Learning Algorithms,” Journal of Healthcare Engineering, vol. 2023, no. 1, pp. 1-13, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Min Hong et al., “Multi-Class Classification of Lung Diseases using CNN Models,” Applied Sciences, vol. 11, no. 19, pp. 1-17, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Poonam Devi, Shrddha Sagar, and Harish Rohil, “Prediction of Lung Disease using Machine and Deep Learning Techniques: A Review,” International Journal of Health Sciences, vol. 6, no. S2, pp. 7583-7601, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Andreas Christe et al., “Computer-Aided Diagnosis of Pulmonary Fibrosis using Deep Learning and CT Images,” Investigative Radiology, vol. 54, no. 10, pp. 627-632, 2019. 
[CrossRef] [Google Scholar] [Publisher Link]

[14] Jooae Choe et al., “Content-based Image Retrieval by using Deep Learning for Interstitial Lung Disease Diagnosis with Chest CT,” Radiology, vol. 302, no. 1, pp. 187-197, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Hassaan Malik et al., “Deep Learning-based Classification of Chest Diseases using X-Rays, CT Scans, and Cough Sound Images,” Diagnostics, vol. 13, no. 17, pp. 1-33, 2023.
[CrossRef]  [Google Scholar] [Publisher Link]

[16] Shimpy Goyal, and Rajiv Singh, “Detection and Classification of Lung Diseases for Pneumonia and Covid-19 using Machine and Deep Learning Techniques,” Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 4, pp. 3239-3259, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Prajoy Podder et al., “Lddnet: A Deep Learning Framework for the Diagnosis of Infectious Lung Diseases,” Sensors, vol. 23, no. 1, pp. 1-26, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Mona Hmoud Al-Sheikh et al., “Multi-Class Deep Learning Architecture for Classifying Lung Diseases from Chest X-Ray and CT Images,” Scientific Reports, vol. 13, no. 1, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Nasr Y. Gharaibeh et al., “Automated Lung Cancer Diagnosis Applying Butterworth Filtering, Bi-Level Feature Extraction, and Sparse Convolutional Neural Network to LUNA 16 CT Images,” Journal of Imaging, vol. 10, no. 7, pp. 1-31, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Pshtiwan Qader Rashid, and lker Türker, “Lung Disease Detection using U-Net Feature Extractor Cascaded by Graph Convolutional Network,” Diagnostics, vol. 14, no. 12, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Surendra Reddy Vinta et al., “Segmentation and Classification of Interstitial Lung Diseases based on Hybrid Deep Learning Network Model,” IEEE Access, vol. 12, pp. 50444-50458, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Muhammad Irtaza et al., “Multi-Label Classification of Lung Diseases using Deep Learning,” IEEE Access, vol. 12, pp. 124062-124080, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Pardhasaradhi Mittapalli, and V. Thanikaiselvan, “FibroRegNet: A Regression Framework for the Pulmonary Fibrosis Prognosis Prediction using a Convolutional Spatial Transformer Network,” IEEE Access, vol. 12, pp. 131928-131941, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Hoan-Suk Choi, and Jinhong Yang, “High-Performance Lung Disease Identification and Explanation using a ReciproCAM-Enhanced Lightweight Convolutional Neural Network,” IEEE Access, vol. 13, pp. 84954-84965, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[25] C. Shyamala Kumari, and K. Seethalakshmi, “Efficient NetV2 for Lung Disease Diagnosis and Treatment by Harnessing the Synergy of Verifiable Convolutional Neural Network optimized with Nutcracker Optimizer Algorithm,” Biomedical Signal Processing and Control, vol. 113, pp. 1-13, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Aicha Akrout, Amira Echtioui, and Mohamed Ghorbel, “Explainable Fusion-based Transfer Learning for Lung Diseases Classification,” Network Modeling Analysis in Health Informatics and Bioinformatics, vol. 15, no. 1, pp. 1-31, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[27] John Jenkins, and Kaushik Roy, “Exploring Deep Convolutional Generative Adversarial Networks (DCGAN) in Biometric Systems: A Survey Study,” Discover Artificial Intelligence, vol. 4, no. 1, pp. 1-22, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Weerakkody Y, Silverstone L, and Walizai T, “Lung Atelectasis,” Radiopaedia, 2025.
[CrossRef] [Publisher Link]

[29] Mehrad Aria, COVID-19 Lung CT Scans Dataset, Kaggle. [Online]. Available: https://www.kaggle.com/datasets/mehradaria/covid19-lung-ct-scans

[30] Weerakkody Y, Elfeky M, and Bell D, “Viral Respiratory Tract Infection,” Radiopaedia, 2025.
[CrossRef] [Publisher Link]

[31] Udithamala Priyanthi Ratnayak, Samitha - Lung Infiltrates, Radiopaedia, 2026. [Online]. Available: https://radiopaedia.org/playlists/41156?lang=us

[32] PlamenEduardo, SARS-CoV-2 CT Scan Dataset, Kaggle, 2020. [Online]. Available: https://www.kaggle.com/datasets/plameneduardo/sarscov2-ctscan-dataset