Conference Paper2026

CheXNet-CBAM: Enhancing Large-scale Medical Pre-training with Attention for Lung Disease Diagnosis

Siam Tahsin Bhuiyan, Zayan Zaman, Rashedur Rahman, Manosh Sur Choudhury, Sefatul Wasi, Ashraful Islam, Saadia Binte Alam, Syoji Kobashi

2026 IEEE 56th International Symposium on Multiple-Valued Logic (ISMVL)

IEEE, pp. 105-110

  • Good Health and Well-being — Relevance: 95%
DOI: 10.1109/ismvl68998.2026.00027URL

Abstract

Lung diseases can lead to life-threatening conditions when not diagnosed accurately. Chest X-rays (CXRs) are a commonly used modality but overlapping radiological features make their assessment subjective. This study presents CheXNet-CBAM, a CNN model proposed for multi-class lung disease classification. It integrates the Convolutional Block Attention Module (CBAM) into CheXNet, a DenseNet121 variant pretrained on large numbers of Chest X-rays. This model was trained on a combined dataset covering five diagnostic classes. CheXNet-CBAM achieved accuracy, recall and AUROC of 96.21%, 94.67% and 0.9894 respectively. Grad-CAM visualizations show that the model’s attention focused on potentially relevant anatomical areas. Integrating attention into CNNs pre-trained on data specific to the relevant domain can hence improve accuracy in CXR-based diagnoses.

Keywords

  • CBAM
  • CheXNet
  • DenseNet121
  • lung disease classification
  • Grad-CAM
  • chest radiography
  • computer-aided diagnosis
  • multi-class classification
  • attention mechanism

CCDS Authors

Siam Tahsin Bhuiyan
Siam Tahsin Bhuiyan

Siam Tahsin Bhuiyan

  • Intern, CCDS

Bachelors

Independent University, Bangladesh

Published at

Scientific Reports

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

Manosh Sur Choudhury
Manosh Sur Choudhury

Manosh Sur Choudhury

  • Research Assistant, CCDS

Masters

+1 more affiliation

Dhaka University

Ashraful Islam, PhD
Ashraful Islam

Ashraful Islam, PhD

  • Center Director, CCDS
  • Director, HCI Wing

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh (IUB)

Published at

CHI, UIST, UbiComp, IJCNN, ICIP, HCII, ICDMW, BLP, IEEE Internet of Things Journal, JMIR, JMIR Human Factors, JMIR Formative Research, IEEE Access, Smart Agricultural Technology, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Human-Computer Interaction, AI for Social Good, AI for Public Health, AI for Impact

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

References

  1. 1.Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. (2016). Deep Residual Learning for Image Recognition. , 770–778[10.1109/cvpr.2016.90]
  2. 2.Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei. (2009). ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 248–255[10.1109/cvpr.2009.5206848]
  3. 3.Gao Huang, Zhuang Liu, Laurens Van Der Maaten, Kilian Q. Weinberger. (2017). Densely Connected Convolutional Networks. , 2261–2269[10.1109/cvpr.2017.243]
  4. 4.Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. , 4510–4520[10.1109/cvpr.2018.00474]
  5. 5.Sanghyun Woo, Jongchan Park, Joon-Young Lee, In So Kweon. (2018). CBAM: Convolutional Block Attention Module. Lecture notes in computer science, 3–19[10.1007/978-3-030-01234-2_1]
  6. 6.Rikiya Yamashita, Mizuho Nishio, Richard Kinh Gian Do, Kaori Togashi. (2018). Convolutional neural networks: an overview and application in radiology. Insights into Imaging, 9(4), 611–629[10.1007/s13244-018-0639-9]
  7. 7.Xiaosong Wang, Yifan Peng, Le Lu, Zhiyong Lu, Mohammadhadi Bagheri, Ronald M. Summers. (2017). ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases. , 3462–3471[10.1109/cvpr.2017.369]
  8. 8.Rose Grace Bender, Sarah Brooke Sirota, Lucien R Swetschinski, Regina-Mae Villanueva Dominguez, Amanda Novotney, Eve E Wool, Kevin S Ikuta, Avina Vongpradith, Emma Lynn Best Rogowski, Matthew Doxey, Christopher E Troeger, Samuel B Albertson, Jianing Ma, Jiawei He, Kelsey Lynn Maass, Eric A.F.Simões, Meriem Abdoun, Jeza Muhamad Abdul Aziz, Deldar Morad Abdulah, Samir Abu Rumeileh, Hasan Abualruz, Salahdein Aburuz, Abiola Victor Adepoju, Rishan Adha, Wirawan Adikusuma, Saryia Adra, Ali Afraz, Shahin Aghamiri, Antonella Agodi, Amir Mahmoud Ahmadzade, Haroon Ahmed, Ayman Ahmed, Karolina Akinosoglou, Tareq Mohammed Ali AL-Ahdal, Rasmieh Mustafa Al-amer, Mohammed Albashtawy, Mohammad T. AlBataineh, Hediyeh Alemi, Adel Ali Saeed Al-Gheethi, Abid Ali, Syed Shujait Shujait Ali, Jaber S Alqahtani, Mohammad AlQudah, Jaffar A. Al-Tawfiq, Yaser Mohammed Al-Worafi, Karem H Alzoubi, Reza Amani, Prince M Amegbor, Edward Kwabena Ameyaw, John H Amuasi, Abhishek Anil, Philip Emeka Anyanwu, Mosab Arafat, Damelash Areda, Reza Arefnezhad, Kendalem Asmare Atalell, Firayad Ayele, Ahmed Y Azzam, Hassan Babamohamadi, François-Xavier Babin, Yogesh Bahurupi, Stephen Baker, Biswajit Banik, Martina Barchitta, Hiba Jawdat Barqawi, Zarrin Basharat, Pritish Baskaran, Kavita Batra, Ravi Batra, Nebiyou Simegnew Bayileyegn, Apostolos Beloukas, James A Berkley, Kebede A Beyene, Ashish Bhargava, Priyadarshini Bhattacharjee, Julia A Bielicki, Mariah Malak Bilalaga, Veera R Bitra, Colin Stewart Brown, Katrin Burkart, Yasser Bustanji, Sinclair Carr, Yaacoub Chahine, Vijay Kumar Chattu, Fatemeh Chichagi, Hitesh Chopra, Isaac Sunday Chukwu, Eunice Chung, Sriharsha Dadana, Xiaochen Dai, Lalit Dandona, Rakhi Dandona, Isaac Darban, Nihar Ranjan Dash, Mohsen Dashti, Mohadese Dashtkoohi, Denise Myriam Dekker, Ivan Delgado-Enciso, Vinoth Gnana Chellaiyan Devanbu, Kuldeep Dhama. (2024). Global, regional, and national incidence and mortality burden of non-COVID-19 lower respiratory infections and aetiologies, 1990–2021: a systematic analysis from the Global Burden of Disease Study 2021. The Lancet Infectious Diseases, 24(9), 974–1002[10.1016/s1473-3099(24)00176-2]
  9. 9.Saeed Iqbal, Adnan N. Qureshi, Jianqiang Li, Tariq Mahmood. (2023). On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks. Archives of Computational Methods in Engineering, 30(5), 3173–3233[10.1007/s11831-023-09899-9]
  10. 10.FM Javed Mehedi Shamrat, Sami Azam, Asif Karim, Kawsar Ahmed, Francis M. Bui, Friso De Boer. (2023). High-precision multiclass classification of lung disease through customized MobileNetV2 from chest X-ray images. Computers in Biology and Medicine, 155, 106646[10.1016/j.compbiomed.2023.106646]
  11. 11.Sebastian Gündel, Sasa Grbic, Bogdan Georgescu, Siqi Liu, Andreas Maier, Dorin Comaniciu. (2019). Learning to Recognize Abnormalities in Chest X-Rays with Location-Aware Dense Networks. Lecture notes in computer science, 757–765[10.1007/978-3-030-13469-3_88]
  12. 12.Selin Ardali Duzgun, Gamze Durhan, Figen Basaran Demirkazik, Meltem Gulsun Akpinar, Orhan Macit Ariyurek. (2020). COVID-19 pneumonia: the great radiological mimicker. Insights into Imaging, 11(1), 118[10.1186/s13244-020-00933-z]
  13. 13.Marios Constantinou, Themis Exarchos, Aristidis G. Vrahatis, Panagiotis Vlamos. (2023). COVID-19 Classification on Chest X-ray Images Using Deep Learning Methods. International Journal of Environmental Research and Public Health, 20(3), 2035[10.3390/ijerph20032035]
  14. 14.Steven Schalekamp, Kicky van Leeuwen, Erdi Calli, Keelin Murphy, Matthieu Rutten, Bram Geurts, Liesbeth Peters-Bax, Bram van Ginneken, Mathias Prokop. (2024). Performance of AI to exclude normal chest radiographs to reduce radiologists’ workload. European Radiology, 34(11), 7255–7263[10.1007/s00330-024-10794-5]
  15. 15.Mark O. Wielpütz, Claus P. Heußel, Felix J. F. Herth, Hans-Ulrich Kauczor. (2014). Radiological Diagnosis in Lung Disease. Deutsches Ärzteblatt international, 111(11), 181–7[10.3238/arztebl.2014.0181]
  16. 16.Chin Poo Lee, Kian Ming Lim. (2022). COVID-19 Diagnosis on Chest Radiographs with Enhanced Deep Neural Networks. Diagnostics, 12(8), 1828[10.3390/diagnostics12081828]
  17. 17.Ikuma Kasuga, Hiromi Maezawa, Sanae Gamo, Yoshimi Yokoe, Yuri Yanagihara, Tomoko Sugiyama, Michiyo Tokura, Mayumi Okayama, Osamu Ohtsubo. (2022). Evaluation of chest radiography and low-dose computed tomography as valuable screening tools for thoracic diseases. Medicine, 101(29), e29261[10.1097/md.0000000000029261]
  18. 18.Nadya Novalina, Mia Rizkinia. (2023). Implementation of Xception and EfficientNetB3 for COVID-19 Detection on Chest X-Ray Image via Transfer Learning. International Journal of Electrical Computer and Biomedical Engineering, 1(2), 97–107[10.62146/ijecbe.v1i2.14]
← All publications