Conference Paper2025Cited by 1

SensaNet: a lightweight DL model for tuberculosis detection in histopathological images

MD Ajmain Mahtab, Sanjida Tasnim, Manosh Sur Choudhury, Sefatul Wasi, Siam Tahsin Bhuiyan, Saadia Binte Alam, Rashedur Rahman

2025 22nd International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)

IEEE, pp. 1-6

  • Good Health and Well-being — Relevance: 97%
DOI: 10.1109/cce67728.2025.11271983URL

Abstract

Tuberculosis remains a global health problem, particularly in resource-limited settings in which early and accurate diagnosis is paramount. This research presents SensaNet, an efficient yet light-weight binary tuberculosis (TB) classification for histopathological image patches. SensaNet is evaluated against a well-curated set of 27,987 Kinyoun-stained image patches that were scanned from digitized slides of sputum smears, with wellbalanced bacilli-positive and negative distributions. SensaNet combines current architectural innovations such as Squeeze-and-Excitation (SE) blocks, Swish activation, and single-head self-attention to amplify feature representation in channel and spatial domains with lower memory cost. Experimental results confirm that SensaNet achieves an accuracy of 98.54%, precision of 98.19%, and recall of 98.95%, outperforming several baseline architectures on sensitivity with the compact size of 12.2 MB and only above 1 million parameters. Comparative analysis proves SensaNet's suitability for TB diagnosis, offering a good trade-off between diagnostic performance and computational expense. These results weigh in favor of the model's potential deployment for real-time point-of-care diagnostics, particularly for low-resource environments.

Keywords

  • tuberculosis detection
  • Swish activation
  • resource-limited settings
  • sputum smear microscopy
  • point-of-care testing
  • self-attention
  • Kinyoun staining
  • Binary classification
  • lightweight deep learning
  • squeeze-and-excitation

CCDS Authors

Md Ajmain Mahtab
Md Ajmain Mahtab

Md Ajmain Mahtab

  • Research Assistant, CCDS

Bachelors

Department of Computer Science and Engineering

BRAC University

Manosh Sur Choudhury
Manosh Sur Choudhury

Manosh Sur Choudhury

  • Research Assistant, CCDS

Masters

+1 more affiliation

Dhaka University

Siam Tahsin Bhuiyan
Siam Tahsin Bhuiyan

Siam Tahsin Bhuiyan

  • Intern, CCDS

Bachelors

Independent University, Bangladesh

Published at

Scientific Reports

Saadia Binte Alam, PhD
Saadia Binte Alam, PhD

Saadia Binte Alam, PhD

  • Director, MIRA & WiSE Wings

Associate Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Published at

HCII, Scientific Reports, Cognitive Computation, Neural Computing and Applications

Md. Rashedur Rahman, D. Eng.
Md. Rashedur Rahman, D. Eng.

Md. Rashedur Rahman, D. Eng.

  • Co-Director, MIRA & NEST Wings

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Published at

CHI, HCII, Scientific Reports, Cognitive Computation, Neural Computing and Applications

References

  1. 1.Stefan Elfwing, Eiji Uchibe, Kenji Doya. (2018). Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Networks, 107, 3–11[10.1016/j.neunet.2017.12.012]
  2. 2.Yan Xiong, Xiaojun Ba, Ao Hou, Kaiwen Zhang, Longsen Chen, Ting Li. (2018). Automatic detection of mycobacterium tuberculosis using artificial intelligence. Journal of Thoracic Disease, 10(3), 1936–1940[10.21037/jtd.2018.01.91]
  3. 3.Thomas E. Tavolara, M.K.K. Niazi, Adam C. Gower, Melanie Ginese, Gillian Beamer, Metin N. Gurcan. (2021). Deep learning predicts gene expression as an intermediate data modality to identify susceptibility patterns in Mycobacterium tuberculosis infected Diversity Outbred mice. EBioMedicine, 67, 103388[10.1016/j.ebiom.2021.103388]
  4. 4.Liron Pantanowitz, Uno Wu, Lindsey Seigh, Edmund LoPresti, Fang-Cheng Yeh, Payal Salgia, Pamela Michelow, Scott Hazelhurst, Wei-Yu Chen, Douglas Hartman, Chao-Yuan Yeh. (2020). Artificial Intelligence–Based Screening for Mycobacteria in Whole-Slide Images of Tissue Samples. American Journal of Clinical Pathology, 156(1), 117–128[10.1093/ajcp/aqaa215]
  5. 5.Hsiao-Chuan Huang, King-Lung Kuo, Mei-Hsin Lo, Hsiao-Yun Chou, Yusen E. Lin. (2022). Novel TB smear microscopy automation system in detecting acid-fast bacilli for tuberculosis – A multi-center double blind study. Tuberculosis, 135, 102212[10.1016/j.tube.2022.102212]
  6. 6.Garima Verma, Ajay Kumar, Sushil Dixit. (2023). Early detection of tuberculosis using hybrid feature descriptors and deep learning network. Polish Journal of Radiology, 88, 445–454[10.5114/pjr.2023.131732]
  7. 7.Gabriel Tamura, Gonzalo Llano, Andrés Aristizábal, Juan Valencia, Luz Sua, Liliana Fernandez. (2024). Machine-learning methods for detecting tuberculosis in Ziehl-Neelsen stained slides: A systematic literature review. Intelligent Systems with Applications, 22, 200365[10.1016/j.iswa.2024.200365]
  8. 8.Arief Budi Witarto, Bogdan Ceachi, Cristiana Popp, Sabina Zurac, Ioana Cristina Daha, Flora Eka Sari, Nirawan Putranto, Satria Pratama, Benyamin P. Octavianus, Luciana Nichita, Julian Gerald Dcruz, Cristian Mogodici, Mirela Cioplea, Liana Sticlaru, Mihai Busca, Oana Stefan, Irina Tudor, Carmen Dumitru, Alexandra Vilaia, Alexandra Bastian, Gheorghita Jugulete, Gyula Laszlo Fekete, Petronel Mustatea. (2024). AI-Based Analysis of Ziehl–Neelsen-Stained Sputum Smears for Mycobacterium tuberculosis as a Screening Method for Active Tuberculosis. Life, 14(11), 1418[10.3390/life14111418]
  9. 9.Shengyi Li, Yue Hu, Lexin Yang, Baohua Lv, Xue Kong, Guangliang Qiang. (2024). DSEception: a noval neural networks architecture for enhancing pneumonia and tuberculosis diagnosis. Frontiers in Bioengineering and Biotechnology, 12, 1454652[10.3389/fbioe.2024.1454652]
  10. 10.Kamran Riasat, Akhtar Jamil, Shaha Al-Otaibi, Sania Zeb, Saima Riasat, Shamsa Kanwal. (2025). Tuberculosis detection using few shot learning. Scientific Reports, 15(1), 13167[10.1038/s41598-025-97803-9]
  11. 11.Mohamed Ahmed Elashmawy, Irraivan Elamvazuthi, Lila Iznita Izhar, Sivajothi Paramasivam, Steven Su. (2023). Detection of Tuberculosis Based on Hybridized Pre-Processing Deep Learning Method. International Journal of Advanced Computer Science and Applications, 14(8)[10.14569/ijacsa.2023.0140808]
  12. 12.Terisara Micaraseth, Shanop Shuangshoti, Kantawatchr Chaiprabha, Natcha Wanpiyarat, Poonchavist Chantranuwatana, Gridsada Phanomchoeng. (2025). Comprehensive Framework for Tuberculosis Detection Using Deep Learning and Image Processing in Whole-Slide Images. IEEE Access, 13, 83694–83716[10.1109/access.2025.3568073]

Cited By

  1. 1.Sayeda Subha Ashrafi, Tushar Ahmed Shishir. (2026). Deep Learning-Based Automated Breast Cancer Detection from Histopathology Images: Benchmarking CNN and Transformer Architectures. , 1–6[10.1109/peccii70991.2026.11662018]
← All publications