Lung Cancer Classification from CT Images Using Ensemble Transfer Learning of VGG16, ResNet50V2 and MobileNetV2
Source abstract
Abstract
Lung cancer remains one of the most common cancers worldwide, and how early it is caught shapes what treatment is possible and how long a patient lives. Computed tomography (CT) sits at the center of this process, and deep learning has become a standard tool for reading CT images, with strong results across medical image classification tasks. This paper proposes an ensemble approach that brings pre-trained VGG16, ResNet50V2, and MobileNetV2 together in a single framework, classifying lung CT images as benign, malignant, or normal. The dataset consists of 1946 CT images from 473 patients, collected at Atatürk University Hospital and labeled by a nuclear medicine physician. All three backbones were fully fine-tuned end-to-end, an approach that an ablation study confirmed outperformed both fully frozen and partially frozen configurations. Splits were made at the patient level throughout, so no patient appears in both training and validation. Five-fold cross-validation gave 89.42 ± 3.21% accuracy and a macro F1 of 0.865 ± 0.036; the same configuration, retrained on a separate patient-level split, reached 90.62% accuracy with a macro F1 of 0.874. The results indicate that ensemble transfer learning can serve as a supporting tool in lung cancer screening.
Source: crossref · Quality: baseline
Affiliations
Department of Computer Engineering, Faculty of Engineering, Ataturk University, 25240 Erzurum, Türkiye
Department of Nuclear Medicine, Ataturk University Research Hospital, Ataturk University, 25240 Erzurum, Türkiye
Funding
Ataturk University Scientific Research Projects Coordination Unit
References (33)
Show source-provided references
1. Patoloji görüntülerinin derin öğrenme yöntemleri ile sınıflandırılması
2. By artificial intelligence algorithms and machine learning models to diagnosis cancer10.1016/j.matpr.2021.07.088 ↗
3. The artificial intelligence and machine learning in lung cancer immunotherapy10.1186/s13045-023-01456-y ↗
4. Espinoza, J.L., and Dong, L.T. (2020). Artificial intelligence tools for refining lung cancer screening. J. Clin. Med., 9.10.3390/jcm9123860 ↗
5. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
6. Breast cancer images classification using a new transfer learning technique
7. Predicting lung cancer survival based on clinical data using machine learning: A review10.1016/j.compbiomed.2023.107338 ↗
8. Machine learning-based lungs cancer detection using reconstruction independent component analysis and sparse filter features10.1080/17455030.2021.1905912 ↗
9. Deep convolutional neural networks with genetic algorithm-based synthetic minority over-sampling technique for improved imbalanced data classification10.1016/j.asoc.2024.111491 ↗
10. Transformative breast Cancer diagnosis using CNNs with optimized ReduceLROnPlateau and Early stopping Enhancements10.1007/s44196-023-00397-1 ↗
11. Albalawi, E., Mahesh, T.R., Thakur, A., Kumar, V.V., Gupta, M., Khan, S.B., and Almusharraf, A. (2024). Integrated approach of federated learning with transfer learning for classification and diagnosis of brain tumor. BMC Med. Imaging, 24.10.1186/s12880-024-01261-0 ↗
12. Derin öğrenme metodu kullanarak BT görüntülerinden akciğer kanseri teşhisi10.21205/deufmd.2022247114 ↗
13. Early diagnosis of lung cancer using deep learning and uncertainty measures
14. Akciğer Kanseri Tespitinde Dönüşüm ve Evrişim Tabanlı Modeller ile Açıklanabilir Yapay Zeka Uygulaması
15. Deep learning ensemble 2D CNN approach towards the detection of lung cancer10.1038/s41598-023-29656-z ↗
16. Sybil: A validated deep learning model to predict future lung cancer risk from a single low-dose chest computed tomography10.1200/JCO.22.01345 ↗
17. A novel hybrid deep learning method for early detection of lung cancer using neural networks10.1016/j.health.2023.100195 ↗
18. Said, Y., Alsheikhy, A.A., Shawly, T., and Lahza, H. (2023). Medical images segmentation for lung cancer diagnosis based on deep learning architectures. Diagnostics, 13.10.3390/diagnostics13030546 ↗
19. DeepXplainer: An interpretable deep learning based approach for lung cancer detection using explainable artificial intelligence10.1016/j.cmpb.2023.107879 ↗
20. Interstitial lung abnormalities at CT in the Korean National Lung Cancer Screening Program: Prevalence and deep learning–based texture analysis10.1148/radiol.222828 ↗
21. Big data analytics on lung cancer diagnosis framework with deep learning10.1109/TCBB.2023.3281638 ↗
22. Mohamed, T.I., Oyelade, O.N., and Ezugwu, A.E. (2023). Automatic detection and classification of lung cancer CT scans based on deep learning and ebola optimization search algorithm. PLoS ONE, 18.10.1371/journal.pone.0285796 ↗
23. Lung cancer disease prediction with CT scan and histopathological images feature analysis using deep learning techniques10.1016/j.rineng.2023.101111 ↗
24. Kusuma, S., Krishnan, S.G., Samreen, K., Ramana, M.V., and Prasad, G.S. (2024, January 15–16). A hybrid deep learning approach for early detection and classification of lung cancer using the pelican optimization algorithm. Proceedings of the 2024 International Conference on Distributed Computing and Optimization Techniques (ICDCOT), Bengaluru, India.10.1109/ICDCOT61034.2024.10515355 ↗
25. Performance analysis of lung cancer detection and its classification using deep convolutional neural network with low dose Ct scan lung images over convolutional neural network with increase in classifier accuracy10.1063/5.0189463 ↗
26. Convolutional neural network based ResNet50 for finding accuracy in prediction of lung cancer using CT images and compared with CNN based inception V3
27. Safta, W., and Shaffie, A. (2024). Advancing pulmonary nodule diagnosis by integrating Engineered and Deep features extracted from CT scans. Algorithms, 17.10.3390/a17040161 ↗
28. Detection of lung cancer using novel attention gate residual U-Net model and KNN classifier from computer tomography images
29. Kumaran, S.Y., Jeya, J.J., Mahesh, T.R., Khan, S.B., Alzahrani, S., and Alojail, M. (2024). Explainable lung cancer classification with ensemble transfer learning of VGG16, Resnet50 and InceptionV3 using grad-cam. BMC Med. Imaging, 24.10.1186/s12880-024-01345-x ↗
30. Yang, X., Duan, A., Jiang, Z., Li, X., Wang, C., Wang, J., and Zhou, J. (2026). Segmentation and Classification of Lung Cancer Images Using Deep Learning. Appl. Sci., 16.10.3390/app16020628 ↗
31. Simonyan, K., and Zisserman, A. (2015, January 7–9). Very deep convolutional networks for large-scale image recognition. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA.
32. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 11–14). Identity mappings in deep residual networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_38 ↗
33. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 18–28). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗