An Intelligent Deep Residual Network for Automated Lung Cancer Detection Using ResNet50

Zainab Muhammed; Belal Al-Khateeb

doi:10.59746/60dkc389

Authors

Zainab Muhammed Informatics Institute for Postgraduate Studies, Information Technology & Communication University, Baghdad,10074, Iraq
Belal Al-Khateeb Computer Science Department, College of Computer Science and Information Technology, University of Anbar, Ramadi, 10003, Iraq

DOI:

https://doi.org/10.59746/60dkc389

Keywords:

Automated Diagnosis, ResNet50, Medical Image Analysis, Lung Cancer, Residual Network

Abstract

Lung cancer accounts for one of the leading causes of cancer death in the world; patients' prognosis can be greatly improved when diagnosed and predicted accurately as early as possible. The proposed intelligent deep learning models will enable automatic identification and classification of lung cancer from histopathological images.

The architecture used was a deep residual network based on ResNet-50, trained on approximately 15,000 lung histopathology images in three classes: adenocarcinoma (ACA), squamous cell carcinoma (SCC), and normal tissue (N). Different testing protocols were performed to objectively evaluate the proposed model robustness and generalization capabilities, including prospective tests using images from a single dataset and external tests using images from other sources.

In the experimental results, the overall accuracy for classification using this proposed model was 99.96%, implying a strong classification ability. Additional evaluation with a confusion matrix and ROC curve confirmed the discriminative power of the model, and external testing demonstrated that the model generalized well when tested on unseen samples from different sources.

The findings indicate that the effective ResNet50-based deep learning technique may be employed as a pioneering tool for automatic lung cancer diagnosis, while also supporting pathologists in improving precision and efficiency.

References

[1] S. Anjum, I. Ahmed, M. Asif, et al., “Lung Cancer Classification in Histopathology Images Using Multiresolution Efficient Nets,” Comput. Intell. Neurosci., 2023, pp. 1–12, doi: 10.1155/2023/7282944.

[2] M. Chen, “A Comparative Study of Transfer Learning Based Models for Lung Cancer Histopathology Classification,” Highlights Sci. Eng. Technol., 2023, pp. 1–8, doi: 10.54097/hset.v39i.6488.

[3] M. M. R. Said, M. S. B. Islam, R. M. Al Saady, et al., “Innovative Deep Learning Architecture for the Classification of Lung and Colon Cancer From Histopathology Images,” Appl. Comput. Intell. Soft Comput., 2024, pp. 1–18, doi: 10.1155/2024/5562890.

[4] “Automated Classification of Lung Cancer Subtypes Cells Using Microscopic Images and Ensembled Deep Learning Architectures,” Sci. Rep., 2025, pp. 1–14, doi: 10.1038/s41598-025-29492-3.

[5] S. Zhong, G. Wang, X. Liao, and S. Zhang, “Segmentation and Classification of Lung Cancer Using Deep Learning Techniques,” Procedia Comput. Sci., vol. 235, pp. 3226–3235, 2024, doi: 10.1016/j.procs.2024.04.305.

[6] D. M. Nair, N. M. Shaji, M. B. M., et al., “Classification of Lung Cancer from Histopathology Images Using Deep Ensemble Classifier,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 14, no. I, pp. 1–7, 2026, doi: 10.22214/ijraset.2026.77154.

[7] F. Al Qahtani, et al., “Enhanced Diagnosis of Lung and Colon Cancer through a Deep Learning Ensemble Model,” Diagnostics, vol. 20, art. 2274, 2024, doi: 10.3390/diagnostics14202274.

[8] S. K. Jha, A. Prakash, and R. Singh, “Automated Lung Cancer Classification from Histopathology Images Using Ensemble Deep Learning Techniques,” Biomedical Signal Processing and Control, vol. 88, p. 105654, 2024, doi: 10.1016/j.bspc.2023.105654.

[9] X. Xu, F. Liu, S. Chen, et al., “Deep Learning-Based Classification of Lung Cancer Histopathological Images Using ResNet and DenseNet Architectures,” Computers in Biology and Medicine, vol. 166, p. 107512, 2024, doi: 10.1016/j.compbiomed.2023.107512.

[10] Z. Muhammed and B. Al Khateeb, “CNN-EWC: A Continuous Deep Learning Approach for Lung Cancer Classification,” J. Intell. Syst., vol. 34, no. 1, pp. 179–201, 2025, doi: 10.1515/jisys-2024-0541.

[11] H. Yang, L. Chen, Z. Cheng, et al., “Deep Learning-Based Six-Type Classifier for Lung Cancer and Mimics from Histopathological Whole Slide Images: A Retrospective Study,” BMC Med., vol. 19, art. 80, 2021, doi: 10.1186/s12916-021-01953-2.

[12] H. T. Nguyen, Q. H. Tran, and T. T. Le, “Multi-Class Classification of Lung Cancer Subtypes Using Transfer Learning on Histopathological Images,” Applied Sciences, vol. 14, no. 3, p. 1452, 2024, doi: 10.3390/app14031452.

[13] R. K. Mishra and S. Tripathi, “Attention-Based Deep Learning Model for Lung Cancer Classification Using Histopathology Images,” Expert Systems with Applications, vol. 235, p. 121237, 2024, doi: 10.1016/j.eswa.2023.121237.

[14] D. Roy, S. Banik, and A. Chatterjee, “Explainable Deep Learning Model for Lung Cancer Detection and Classification from Histopathological Images,” Diagnostics, vol. 14, no. 2, p. 214, 2024, doi: 10.3390/diagnostics14020214.

[15] W. Li, S. Yu, R. Yang, et al., “Machine Learning Model of ResNet50-Ensemble Voting for Malignant-Benign Small Pulmonary Nodule Classification on Computed Tomography Images,” Cancers (Basel), vol. 15, no. 22, art. 5417, 2023, doi: 10.3390/cancers15225417.

[16] “Lung Cancer Disease Prediction with CT Scan and Histopathological Images Feature Analysis Using Deep Learning Techniques,” Results Eng., vol. 15, art. 101111, 2023, doi: 10.1016/j.rineng.2023.101111.

[17] P. Rajpurkar, E. Park, J. Irvin, et al., “Deep Learning for Chest Cancer Diagnosis: A Comprehensive Review of Histopathology and Imaging Techniques,” IEEE Reviews in Biomedical Engineering, vol. 17, pp. 88–102, 2024, doi: 10.1109/RBME.2023.3321456.

[18] S. Anisha D. P. J., et al., “Deep Learning Algorithms for Classification of Lung Cancer Types from Histopathological Images,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 14, no. I, pp. 12–20, 2026, doi: 10.22214/ijraset. 2026. deep.

[19] M. F. Khatun, M. R. Ajmain, and Md. Assaduzzaman, “A Deep Learning Approach to Detect and Classification of Lung Cancer,” in Proc. ICONAT, 2023, pp. 1–6, doi: 10.1109/ICONAT57137.2023.10080801.

[20] B. K. Hatuwal and H. C. Thapa, “Lung Cancer Detection Using Convolutional Neural Network on Histopathological Images,” Int. J. Comput. Trends Technol., vol. 68, no. 10, pp. 21–24, Oct. 2020, doi: 10.14445/22312803/ijctt-v68i10p104.

[21] S. Mangal, A. Chaurasia, and A. Khajanchi, “Convolution Neural Networks for Diagnosing Colon and Lung Cancer Histopathological Images,” arXiv, Sep. 2020.

[22] J. Civit-Masot, A. Bañuls-Beaterio, M. Domínguez-Morales, M. Rivas-Pérez, L. Muñoz-Saavedra, and J. M. Rodríguez Corral, “Non-Small Cell Lung Cancer Diagnosis Aid with Histopathological Images Using Explainable Deep Learning Techniques,” Comput. Methods Programs Biomed., vol. 226, p. 107108, Nov. 2022, doi: 10.1016/j.cmpb.2022.107108.

[23] S. Wadekar and D. K. Singh, “A Modified Convolutional Neural Network Framework for Categorizing Lung Cell Histopathological Image Based on Residual Network,” Healthcare Analytics, vol. 4, p. 100224, Dec. 2023, doi: 10.1016/j.health.2023.100224.

[24] R. D. Mohalder, K. A. Hossain, J. P. Sarkar, L. Paul, M. Raihan, and K. H. Talukder, “Lung Cancer Detection from Histopathological Images Using Deep Learning,” in Machine Intelligence and Emerging Technologies, vol. 490, pp. 201–212, 2023, doi: 10.1007/978-3-031-34619-4_17.

[25] “Lung and Colon Cancer Histopathological Images,” Kaggle. [Online]. Available: https://www.kaggle.com/datasets/andrewmvd/lung-and-colon-cancer-histopathological-images