Article Sidebar

Download
PDF
Statistic
Read Counter : 0 Download : 0

Main Article Content

Abstract

Lung cancer remains one of the leading causes of cancer-related mortality worldwide, making accurate and timely detection essential for improving patient outcomes. Computed tomography (CT) is widely used for lung assessment; however, manual interpretation can be affected by inter-observer variability and subtle imaging characteristics. This study proposes an automated three-class lung CT classification framework that integrates deep transfer learning with quantitative lung-region features. EfficientNet-B7, initialized with ImageNet-pretrained weights, was employed to extract high-level deep representations from CT images. In parallel, lung Regions of Interest (ROIs) were automatically segmented, from which four quantitative descriptors were extracted: Skewness, Kurtosis, GLCM Contrast, and GLCM Homogeneity. The standardized lung-ROI features were subsequently concatenated with the EfficientNet-B7 deep feature representation using a feature-level fusion strategy and classified into Normal, Benign, and Malignant categories. Experimental evaluation on the held-out test set demonstrated an overall classification accuracy of 96.36%, correctly classifying 106 of 110 CT images. The proposed fusion framework achieved macro-averaged Precision, Recall, F1-score, and Specificity of 94.39%, 90.87%, 92.39%, and 97.53%, respectively. Furthermore, one-vs-rest ROC analysis yielded AUC values of 0.9849, 0.9634, and 1.0000 for the Normal, Benign, and Malignant classes, respectively, corresponding to a macro-average AUC of 0.9828. These results demonstrate the strong discriminative capability of the proposed deep and quantitative feature fusion framework for three-class lung CT image classification.

Keywords

Detection Lung cancer EfficientNet Features Image processing

Article Details

How to Cite
Al-Tamimi, M. S., Abdulateef, A. H., & Abdulateef, I. H. (2026). Deep transfer learning and radiomics synergy for enhanced lung cancer classification on CT scans. Future Technology, 5(4), 299–309. Retrieved from https://fupubco.com/futech/article/view/1165
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
Bookmark and Share

References

  1. Shong, L.Y.W. and Lam DC. "Emerging trends in global lung cancer burden." Semin Respir Crit Care Med Thieme Med Publ 2025. https://www.thieme-connect.com/products/ejournals/html/10.1055/a-2651-0612
  2. Al-Suhail NSJ and GA. "Lung cancer detection: The role of transfer learning in medical imaging." Int. Conf. Futur. Telecommun. Artif. Intell. (IC-FTAI), IEEE, pp. 1–6, 2024. https://doi.org/https://doi.org/10.1109/IC-FTAI62324.2024.10950018.
  3. Mienye, I.D., Swart, T.G., Obaido, G., Jordan, M. and Ilono P. "Deep convolutional neural networks in medical image analysis: A review." Information, vol. 16, 2025. https://doi.org/https://doi.org/10.3390/info16030195.
  4. Y. G. Chandavarkar, D. Rao, S. B. Pathan, K. Devaraja and SDP. "A multi-faceted approach to lung cancer classification using diverse machine learning algorithms using the IQ-OTH/NCCD dataset." Emerg. Technol. AI, Comput. Commun. Cybersecurity, CRC Press., pp. 53-58.
  5. Linguraru MG, Bakas S, Aboian M, Chang PD, Flanders AE, Kalpathy-Cramer J, Kitamura FC, Lungren MP, Mongan J, and Prevedello LM SR. "Clinical, cultural, computational, and regulatory considerations to deploy ai in radiology: perspectives of rsna and miccai experts." Radiology: Artificial Intelligence, vol. 4, no. 6, p. e240225, 2024. https://doi.org/10.1148/ryai.240225.
  6. W. Wulaningsih, C. Villamaria, A. Akram, J. Benemile, F. Croce and JW. "Deep learning models for predicting malignancy risk in CT-Detected pulmonary nodules: A systematic review and meta-analysis." Lung, vol. 202, pp. 625–636, 2024. https://doi.org/10.1007/s00408-024-00706-1.
  7. Huang S, Yang J, Shen N, Xu Q, and Zhao Q. "Artificial intelligence in lung cancer diagnosis and prognosis: Current application and future perspective." Seminar. Cancer Biol., vol. 89, pp. 30–37, 2023. https://doi.org/10.1016/j.semcancer.2023.01.006?utm_source=chatgpt.com
  8. M. Z. Khan, M. Jabeen, M. U. G. Khan, S. S. Alqahtani and SA. "Deep learning in medical imaging: challenges and opportunities. " Artificial Intelligence, vol. 57, p 10625, 2024. https://doi.org/10.1007/s10462-023-10625-5.
  9. Hosseini SH, Monsefi R, and Shadroo S. "Deep learning applications for lung cancer diagnosis: a systematic review." Multimed Tools Application, vol. 83, pp:14305–14335, 2024. https://doi.org/10.1007/s11042-023-16046-w?utm_source=chatgpt.com
  10. M. Tan and Q. V. Le. "EfficientNet: rethinking model scaling for convolutional neural networks." Proc. 36th Internation Conference. Mach. Learn., vol. 97, pp. 6105–6114, 2019.
  11. Raza, R., Zulfiqar, F., Khan, M.O., Arif, M., Alvi, A., Iftikhar, M.A. and Alam, T., "Lung-EffNet: Lung cancer classification using EfficientNet from CT-scan images." Engineering Applications of Artificial Intelligence, vol. 126, p. 106902, 2023. https://doi.org/10.1016/j.engappai.2023.106902?utm_source=chatgpt.com.
  12. Suresha R, Devika KM, and Prabhu A. "Support Vector Machine classifier based lung cancer recognition: a fusion approach." International Conference On Edge Computing and Applications (ICECAA) 2022 - Proc., 2022, pp. 1565–1572. https://doi.org/10.1109/ICECAA55415.2022.9936385.
  13. Qadir AM, Abdalla PA, and Abd DF. "A hybrid lung cancer model for diagnosis and stage classification from computed tomography images." Iraqi Journal for Electrical and Electronic Engineering, vol. 20, pp. 266-274, 2024. https://doi.org/10.37917/ijeee.20.2.23.
  14. Gulsoy T, and Kablan EB. "FocalNeXt: a ConvNeXt augmented FocalNet architecture for lung cancer classification from CT-Scan images." Expert System Application, vol. 1, no. 261, p. 125553, 2024. https://doi.org/10.2139/ssrn.4741248.
  15. Majumder S, Gautam N, Basu A, Sau A, Geem ZW, and Sarkar R. "MENet: a mitscherlich function based ensemble of CNN models to classify lung cancer using CT scans." PLoS One, vol. 19, no. 3, p. :e0298527, 2024. https://doi.org/10.1371/journal.pone.0298527.
  16. Al-Tamimi MSH, Jabbar SF, Taha AM, and Al-Jibory FK. "Enhancing lung cancer classification using CT images using processing techniques employing U-Net architecture." Journal of Internet Services and Information Security, vol. 15, no. 2, pp.:590–609, 2025.https://doi.org/10.58346/JISIS.2025.I2.041.
  17. AL-Huseiny HA and M. "The IQ-OTH/NCCD lung cancer dataset. mendeley data" no. 4, 2023. https://doi.org/https://doi.org/10.17632/bhmdr45bh2.4.
  18. Nazir, Nahida, Abid Sarwar and BSS. "Recent developments in denoising medical images using deep learning: An overview of models, techniques, and challenges." Micron, , vol.1, no. 180, p. 103615, 2024. https://doi.org/10.1016/j.micron.2024.103615.
  19. Buades, A., Coll, B. and Morel, J.M. "A non-local algorithm for image denoising." In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), vol. 2, pp. 60-65. https://doi.org/10.1109/CVPR.2005.38.
  20. D’hondt L, Franck C, Kellens PJ, Zanca F, Buytaert D, Van Hoyweghen A, Addouli HE, Carpentier K, Niekel M, and Spinhoven M BK. "Impact of deep learning image reconstruction on volumetric accuracy and image quality of pulmonary nodules with different morphologies in low-dose CT." Cancer Imaging, vol. 24. no. 1, 2024. https://doi.org/https://doi.org/10.1186/s12880-024-00703-w?utm_source=chatgpt.com.
  21. Golkarieh A, Kiashemshaki K, Boroujeni SR, and Isakan NA. "Advanced U-Net architectures with CNN backbones for automated lung cancer detection and segmentation in chest CT images." ArXiv Prepr ArXiv 09898, 2025. https://doi.org/10.21203/rs.3.rs-5232211/v1.
  22. E. D. Pisano, S. Zong, B. M. Hemminger, M. DeLuca, R. E. Johnston, K. Muller, M. P. Braeuning and SMP. "Contrast limited adaptive histogram equalization image processing to improve the detection of simulated spiculations in dense mammograms." Journal of Digit Imaging, vol. 11, no. 4, pp. 193–200, 1998. https://doi.org/10.1007/BF03178082.
  23. Papadopoulos, Athanasios, Dimitrios I. Fotiadis, and Lena Costaridou. "Improvement of microcalcification cluster detection in mammography utilizing image enhancement techniques." Computers in biology and medicine, vol. 38, no. 10, pp. 1045-1055, 2008. https://doi.org/10.1016/j.compbiomed.2008.07.006.
  24. R. C. Gonzalez and R. E. Woods. "Digital Image Processing." 4th ed. New York, NY, USA: Pearson: 2018. https://www.cl72.org/090imagePLib/books/Gonzales,Woods-Digital.Image.Processing.4th.Edition.pdf
  25. Hofmanninger, J., Prayer, F., Pan, J., Röhrich, S., Prosch, H. and Langs G. "Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem." European radiology experimental, vol. 4, no. 1, p. 50, 2020. https://doi.org/https://doi.org/10.1186/s41747-020-00173-2?utm_source=chatgpt.com.
  26. Zwanenburg, A., Vallières, M., Abdalah, M.A., Aerts, H.J., Andrearczyk, V., Apte, A., Ashrafinia, S., Bakas, S., Beukinga, R.J., Boellaard, R. and Bogowicz M. "The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping." Radiology, vol. 295, no. 2, pp. 328-338, 2020. https://doi.org/https://doi.org/10.1148/radiol.2020191145?utm_source=chatgpt.com.
  27. Sokolova, M. and Lapalme G. A "Systematic analysis of performance measures for classification tasks." Information Processing & Management, vol 45, no. 1, pp. 427-437, 2009. https://doi.org/https://doi.org/10.1016/j.ipm.2009.03.002?utm_source=chatgpt.com.