Lung Cancer Prediction and Classification Using Transfer Learning Technique
Keywords:
Lung cancer prediction, Transfer learning technique, Computed Tomography (CT), VGG16 model, Convolutional Neural Networks (CNNs)Abstract
Cancer is a leading cause of human loss worldwide. Lung cancer has a relatively high death rate. Patients' lives can be saved by early lung cancer identification. Lung cancer can be detected in a variety of ways. One of the most effective techniques is Computed Tomography (CT). In the literature, numerous approaches utilizing deep learning and machine learning have been put forth. This study suggested a deep learning approach for lung cancer detection without professional consultation. In this paper VGG16 model with transfer learning is used. VGG16 gives best results for image processing method in all perspectives. This paper classifies the dataset into three classes likely: normal, Benign and malignant. Dataset is divided into training, testing and validation parts. The model is trained with 80% data, validates with 10% data and finally tested with 10% data. The kappa score and F1 score obtained by VGG16 for lung cancer is 98% and 96.43%. The VGG16 with transfer learning introduced in this paper enhance the accuracy of lung cancer detection and outperforms traditional image processing methods across multiple performance metrics.
References
Mayo Clinic, “Lung Cancer - Symptoms and Causes,” Mayo Clinic, Apr. 30, 2024. https://www.mayoclinic.org/diseases-conditions/lung-cancer/symptoms-causes/syc-20374620
T. Jin, H. Cui, S. Zeng and X. Wang, "Learning Deep Spatial Lung Features by 3D Convolutional Neural Network for Early Cancer Detection," 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Sydney, NSW, Australia, 2017, pp. 1-6, doi: https://doi.org/10.1109/DICTA.2017.8227454.
W. Shen et al., “Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification,” Pattern Recognition, vol. 61, pp. 663–673, Jan. 2017, doi: https://doi.org/10.1016/j.patcog.2016.05.029.
T. Wang,Y. Lei,S. Tian,T. Liu,“Lung tumor segmentation of PET/CT using dual pyramid mask R-CNN,” Medical Imaging 2022: Image Processing, pp. 107–107, Feb. 2021, doi: https://doi.org/10.1117/12.2580987.
S. Thanzeem Mohamed Sheriff, J. Venkat Kumar, S. Vigneshwaran, A. Jones, and J. Anand, “Lung Cancer Detection using VGG NET 16 Architecture,” Journal of Physics: Conference Series, vol. 2040, no. 1, p. 012001, Oct. 2021, doi: https://doi.org/10.1088/1742-6596/2040/1/012001.
Y. Lu, H. Liang, S. Shi, and X. Fu, “Lung Cancer Detection using a Dilated CNN with VGG16,” In Proceedings of the 2021 4th International Conference on Signal Processing and Machine Learning, pp. 45-51. Aug. 2021, doi: https://doi.org/10.1145/3483207.3483215.
V. Kapoor, A. Mittal, S. Garg, M. Diwakar, A. K. Mishra and P. Singh, "Lung Cancer Detection Using VGG16 and CNN," 2023 IEEE World Conference on Applied Intelligence and Computing (AIC), Sonbhadra, India, 2023, pp. 758-762, doi: https://doi.org/10.1109/AIC57670.2023.10263901.
N. Thapliyal, M. Manwal, V. Kukreja and R. Sharma, "Artificial Intelligence-Based ResNet50, Xception, and VGG16 Models for an Efficient Detection of Lung Cancer," 2024 5th International Conference for Emerging Technology (INCET), Belgaum, India, 2024, pp. 1-5, doi: https://doi.org/10.1109/INCET61516.2024.10593219.
A. Ter-Sarkisov, “Network of Steel: Neural Font Style Transfer from Heavy Metal to Corporate Logos,” arXiv (Cornell University), Jan. 2020, doi: https://doi.org/10.48550/arxiv.2001.03659.
Arya, Mithlesh, Arvind Singh Rajpoot, Dhruv Pathak, Bhagyansh Garg, Megha Gupta, and Abha Jain. "A Hybrid Approach for Lung Cancer Detection Using Relevant Feature and Neural Network Techniques." In 2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies (INSPECT), pp. 1-5. IEEE, 2024. Doi: https://doi.org/10.1109/INSPECT63485.2024.10896170
