Vinutha K.; CH. Bhavani; Karthi Govindharaju; A. V. Subbarao; Spandana Shivanadhuni; Tummala Ranga Babu

Automated Tuberculosis and Lung Cancer Co-detection using Dual-Path ConvNet–ViT Hybrid Framework Architecture

PDF (1096KB), PP.16-32

Views: 0 Downloads: 0

Author(s)

Vinutha K. ^1,* CH. Bhavani ² Karthi Govindharaju ³ A. V. Subbarao ⁴ Spandana Shivanadhuni ⁵ Tummala Ranga Babu ⁶

1. Department of Information Science and Engineering BMS Institute of Technology & Management, India

2. Department of CSE CVR College of Engineering, India

3. Artificial Intelligence and Data Science, Saveetha Engineering College, India

4. Department of ECE St.Mary's Group of Institutions Guntur for Women, India

5. Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, India

6. Department of Electronics & Communication Engineering R.V.R. & J.C.College of Engineering, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2026.05.02

Received: 25 Jan. 2026 / Revised: 18 Feb. 2026 / Accepted: 23 Mar. 2026 / Published: 8 Oct. 2026

Index Terms

Vision Transformer (ViT), Multi-Task Learning, Tuberculosis Detection, Lung Cancer Detection, Lesion Segmentation, Medical Image Classification, Deep Learning.

Abstract

Tuberculosis (TB) and lung cancer remain leading causes of mortality worldwide, emphasizing the need for reliable automated diagnostic systems. Existing deep learning approaches typically address segmentation and classification as independent tasks or rely on loosely coupled hybrid architectures, limiting joint optimization and interpretability. To address these limitations, this work proposes a Dual-Path ConvNet–Vision Transformer (ViT) hybrid framework for simultaneous pulmonary disease classification and lesion segmentation. Unlike fully shared multi-task models, the proposed design integrates convolutional feature extraction for classification with transformer-based global context modeling for segmentation, followed by feature-level fusion to enhance diagnostic consistency. The framework is evaluated on the IQ-OTH/NCCD dataset, achieving an accuracy of 0.950, recall of 0.951, precision of 0.947, specificity of 0.975, F1-score of 0.949, and AUC of 0.963. Results demonstrate that the proposed hybrid approach provides robust and interpretable performance for pulmonary disease co-analysis while maintaining architectural flexibility.

Cite This Paper

Vinutha K., CH. Bhavani, Karthi Govindharaju, A. V. Subbarao, Spandana Shivanadhuni, Tummala Ranga Babu, "Automated Tuberculosis and Lung Cancer Co-detection Using Dual-Path ConvNet–ViT Hybrid Framework Architecture", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.18, No.5, pp. 16-32, 2026. DOI:10.5815/ijigsp.2026.05.02

Reference

[1]A. Alqhatani, T. K. S. R. Babu, T. R. Mahesh, S. Bhatia Khan, O. Saidani, and M. T. Quasim, “Automated classification and explainable AI analysis of lung cancer stages using EfficientNet and gradient-weighted class activation mapping,” Frontiers in Medicine, vol. 12, 1625183, 2025. https://doi.org/10.3389/fmed.2025.1625183.
[2]J., P.Debnath, A. S. U. K ranta,A.,Hossain, A.Sakib, H.Rahman, R.Haque, M. R.Ahmed, A. W.Reza, S. M. M. R.Swapno, , & A. Appaji, “LMVT: A hybrid vision transformer with attention mechanisms for efficient and explainable lung cancer diagnosis”. Informatics in Medicine Unlocked, vol.57, pp.101669. 2025. https://doi.org/10.1016/j.imu.2025.101669
[3]W.Jian, A. U.Haq, , N.Afzal, S.,Khan, H.Alsolai, S. M.Alanazi, & A. T. Zamani, “Developing an innovative lung cancer detection model for accurate diagnosis in AI healthcare systems”. Scientific Reports, vol.15(1), pp.22945. 2025. https://doi.org/10.1038/s41598-025-03960-2
[4]J. N.Gandhi, K.Venkatesh Guru, Y.Varun, K.Vasanth, P.Vimal, & K.Madheswaran, “Hybrid Attention Vision Transformer for Enhanced Lung Cancer Detection”. In Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024). Atlantis Press. pp. 671–682.2025. https://doi.org/10.2991/978-94-6463-718-2_58
[5]G.Siddharth, A.Ambekar, & N.Jayakumar,. Enhanced CoAtNet-based hybrid deep learning architecture for automated tuberculosis detection in human chest X-rays. BMC Medical Imaging,vol. 25, no.1, pp.379. 2025https://doi.org/10.1186/s12880-025-01901-z
[6]K.Vanitha, T. R.Mahesh, V. V.Kumar, & S.Guluwadi, “Enhanced tuberculosis detection using Vision Transformers and explainable AI with a Grad-CAM approach on chest X-rays”. BMC Medical Imaging, vol.25, no.1, pp.96.2025. https://doi.org/10.1186/s12880-025-01630-3
[7]A. S.Akbari, A.Kumar, B. R.Reddy, K. K. Singh, & M.Takei, “Vision Transformer-based automated model for enhancing lung cancer classification”. 2024 IEEE International Conference on Imaging Systems and Techniques (IST), pp.1–6. 2024. https://api.semanticscholar.org/CorpusID:274374560
[8]M. Q. Shatnawi, Q. Abuein, and R. Al-Quraan, “Deep learning-based approach to diagnose lung cancer using CT-scan images,” Intelligence-Based Medicine, vol. 11, 100188, 2025. https://doi.org/10.1016/j.ibmed.2024.100188.
[9]G. Inbasakaran and J. Anitha Ruth, “Clinical-ready CNN framework for lung cancer classification: Systematic optimization for healthcare deployment with enhanced computational efficiency,” Intelligence-Based Medicine, vol. 12, 100292, 2025. https://doi.org/10.1016/j.ibmed.2025.100292.
[10]S. M. Elhassan, S. M. Darwish, and S. M. Elkaffas, “An enhanced lung cancer detection approach using dual-model deep learning technique,” CMES: Computer Modeling in Engineering & Sciences, vol. 142, no. 1, pp. 835–867, 2025. https://doi.org/10.32604/cmes.2024.058770.
[11]A. Kawama, R. W. Mwangi, and L. Nderu, “Enhanced lung cancer prediction via integrated multi-space feature adaptation, collaborative alignment, and disentanglement learning,” Engineering Reports, vol. 7, no. 1, e13069, 2024. https://doi.org/10.1002/eng2.13069.
[12]A. A., Abe, & M.Nyathi, “Lung cancer diagnosis from computed tomography images using deep learning algorithms with random pixel swap data augmentation: Algorithm development and validation study”. JMIR Bioinformatics and Biotechnology, vol.6, no.1,pp. e68848. 2025. https://doi.org/10.2196/68848
[13]S. Ghosh and A. Chatterjee, “Self-attention driven transfer learnt deep neural network for improved lung cancer detection from radiographic images,” Heliyon, vol. 11, no. 16, e44066, 2025. https://doi.org/10.1016/j.heliyon.2025.e44066.
[14]D. Hasan and A. M. Abdulazeez, “Lung Segmentation from Chest X-Ray Images Using Deeplabv3plus-Based CNN Model,” The Indonesian Journal of Computer Science, vol. 13, no. 1, 2024. doi: 10.33022/ijcs.v13i1.3700.
[15]C.-F. Chen, C.-H. Hsu, Y.-C. Jiang, W.-R. Lin, W.-C. Hong, I.-Y. Chen, M.-H. Lin, K.-A. Chu, C.-H. Lee, D. L. Lee, and P.-F. Chen, “A deep learning-based algorithm for pulmonary tuberculosis detection in chest radiography,” Scientific Reports, vol. 14, no. 1, p. 14917, 2024, doi: 10.1038/s41598-024-65703-z.
[16]F. Turk and M. Kılıçaslan, “Lung image segmentation with improved U-Net, V-Net and Seg-Net techniques,” PeerJ Computer Science, vol. 11, p. e2700, Feb. 2025, doi: 10.7717/peerj-cs.2700.
[17]V. Sharma, Nillmani, S. K. Gupta, and K. K. Shukla, “Deep learning models for tuberculosis detection and infected region visualization in chest X-ray images,” Intelligent Medicine, vol. 4, no. 2, pp. 104–113, 2024, doi: 10.1016/j.imed.2023.06.001.

International Journal of Image, Graphics and Signal Processing (IJIGSP)