CNN-Based Deep Learning Approach for Early Detection and Prediction of Lung Cancer from CT Images

A. Prasannakumari; Dr. G. Kannan

doi:10.29284/f9ktqp95

Authors

A. Prasannakumari Research Scholar, Department of Computer and Information Science, Annamalai University, Annamalai Nagar, Chidambaram, Tamil Nadu, India
Dr. G. Kannan Assistant Professor, Department of Computer Science, Government Arts and Science College, Manalmedu, (Deputed from Department of CIS, Annamalai University)

DOI:

https://doi.org/10.29284/f9ktqp95

Keywords:

Lung Cancer Prediction, Deep Learning, Convolutional Neural Network (CNN), Medical Image Analysis, CT Scan Images, Early Cancer Detection, Classification, Artificial Intelligence, Healthcare Analytics, Computer-Aided Diagnosis (CAD).

Abstract

Lung cancer is the third most common type of cancer worldwide and remains one of the leading causes of cancer-related deaths. Many lives are at risk due to delays and inaccuracies in the early diagnosis of this disease. Early detection is crucial because it significantly improves treatment outcomes and survival rates. The primary objective of this study is to develop an automated system for the early detection of lung cancer using deep learning techniques, thereby reducing mortality rates and improving patient care. Recent advancements in deep learning have greatly enhanced the field of medical image analysis, enabling efficient and accurate detection of abnormalities in medical scans. In this research, a Convolutional Neural Network (CNN)-based deep learning model is proposed for imaging-based lung cancer prediction. The model is trained and evaluated using lung CT scan images to classify cancerous and non-cancerous cases. Experimental results demonstrate that the proposed CNN model achieves Accuracy, Precision, Recall (Sensitivity), Specificity, F1-Score, and Area Under the Curve (AUC). These results indicate that the proposed approach can effectively support healthcare professionals in the early diagnosis of lung cancer, leading to timely treatment and improved patient survival rates.

References

[1]. Huang, T. et al. Distinguishing lung adenocarcinoma from lung squamous cell carcinoma by two hypomethylated and three hypermethylated genes: a meta-analysis. PLoS ONE 11, e0149088 (2016)

[2]. Davidson, M. R., Gazdar, A. F. & Clarke, B. E. Te pivotal role of pathology in the management of lung cancer. J. Torac. Dis. 5(Suppl 5), S463–S478 (2013).

[3]. Aisner, D. L. et al. Te impact of smoking and TP53 mutations in lung adenocarcinoma patients with targetable mutations-the lung cancer mutation consortium (LCMC2). Clin. Cancer Res. 24, 1038–1047 (2018).

[4]. Hosny, A. et al. Deep learning for lung cancer prognostication: a retrospective multi-cohort radiomics study. PLoS Med 15, e1002711 (2018).

[5]. Hua, K.-L., Hsu, C.-H., Hidayati, S. C., Cheng, W.-H. & Chen, Y.-J. Computer-aided classifcation of lung nodules on computed tomography images via deep learning technique. Oncol. Targets Ter. 8, 2015–2022 (2015).

[6]. Kim, L. et al. Clinicopathologic and molecular characteristics of lung adenocarcinoma arising in young patients. J. Kor. Med. Sci. 27, 1027–1036 (2012).

[7]. Rajesh, P., & Karthikeyan, M. (2017). A comparative study of data mining algorithms for decision tree approaches using weka tool. Advances in Natural and Applied Sciences, 11(9), 230-243.

[8]. Shrivastava, A., Rajput, N., Rajesh, P., & Swarnalatha, S. R. (2023). IoT-Based Label Distribution Learning Mechanism for Autism Spectrum Disorder for Healthcare Application. In Practical Artificial Intelligence for Internet of Medical Things (pp. 305-321). CRC Press.

[9]. Saito, S. et al. Current status of research and treatment for non-small cell lung cancer in neversmoking females. Cancer Biol. Ter. 18, 359–368 (2017).

[10]. Rajesh, P., Karthikeyan, M., Santhosh Kumar, B., & Mohamed Parvees, M. Y. (2019). Comparative study of decision tree approaches in data mining using chronic disease indicators (CDI) data. Journal of Computational and Theoretical Nanoscience, 16(4), 1472-1477.

[11]. Aerts, H. J. W. L. et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat. Commun. 5, 1. https://doi.org/10.1038/ncomms5006 (2014).

[12]. Zeiler, M. D. & Fergus, R. Visualizing and Understanding Convolutional Networks. In Computer Vision – ECCV 2014 818–833 (Springer, Berlin, 2014).

[13]. Rajesh, P., Karthikeyan, M., & Arulpavai, R. (2019). Data mining algorithm to predict the factors for agricultural development using stochastic model. International Journal of Recent Technology and Engineering, 8(3), 2713-271.

[14]. Hecht, S. S. Tobacco smoke carcinogens and lung cancer. J. Natl. Cancer Inst. 91, 1194–1210

[15]. Rajesh, P., & Karthikeyan, M. (2019). Data mining approaches to predict the factors that affect the agriculture growth using stochastic model. International Journal of Computer Sciences and Engineering, 7(4), 18-23.