Prediction of Lung Cancer Using Machine Learning

Abstract

With the highest cancer-related mortality, lung cancer is one of the most dangerous and difficult cancers to identify. Over time, machine learning techniques have been used in medical research, and many significant developments have been made in cancer research for decades. There have been a lot of machine learning algorithms that could significantly help in feature extraction and other radiological analysis. With the help of available datasets from research organizations, it is made possible easily. In this study, we built a system with the help of the YOLO algorithm that uses CNN to predict lung cancer from the fed datasets of cancerous and non-cancerous CT scans.

Introduction

Lung cancer is the leading cause of cancer deaths worldwide, with symptoms often appearing late, making early detection crucial for improving survival. Lung cancer arises from uncontrollable cell growth (metastasis) due to genetic mutations. Besides smoking, factors like pollution, harmful gases, and genetics contribute to risk.

Traditional diagnostic methods (tumor markers, biopsies, imaging like CT and MRI) have limitations, including invasiveness and difficulty detecting small nodules. Artificial intelligence (AI), especially machine learning (ML) and deep learning (DL) algorithms—such as SVM, decision trees, random forests, artificial neural networks (ANN), and convolutional neural networks (CNN)—have shown promise in improving early lung cancer detection and classification.

Studies demonstrate varied accuracy across different ML algorithms, with ANN and CNN often outperforming others. Radiomics combined with ML can predict tumor histology, and hybrid models improve lung nodule detection. Techniques like multi-stage classification, image enhancement, and segmentation further boost detection accuracy.

The proposed system uses CNN (DenseNet-121 and YOLOv8 models) on pre-processed lung CT scan datasets classified into benign, malignant, and normal categories. It achieves high accuracy (~95%) in identifying cancerous nodules, showing strong performance in distinguishing malignant from benign and normal cases. Validation indicates some overfitting but overall effective learning.

Future scope includes real-time object detection improvements, better precision, multi-object tracking, and domain-specific detection, aiming to advance automated, accurate lung cancer diagnosis and reduce human workload.

Conclusion

It\'s critical to diagnose lung cancer as soon as possible. This study compares the effectiveness of the most popular deep learning and machine learning algorithms for lung cancer prediction. A system that was designed to find ways to improve accuracy was assessed using performance metrics in order to analyze the results. As a result, the system has greater accuracy than the current ones.

References

[1] G. Sruthi, C. L. Ram, M. K. Sai, B. P. Singh, N. Majhotra and N. Sharma, \"Cancer Prediction using Machine Learning,\" 2022 2nd International Conference on Innovative Practices in Technology and Management (ICIPTM), Gautam Buddha Nagar, India, 2022, pp. 217-221, doi: 10.1109/ICIPTM54933.2022.9754059. [2] D. Manivannan., N. K. Manikandan and M. Kavitha, \"Discovering Lung Cancer Cell Using Machine Learning,\" 2022 International Conference on Data Science, Agents & Artificial Intelligence (ICDSAAI), Chennai, India, 2022, pp. 1-3, doi: 10.1109/ICDSAAI55433.2022.10028961. [3] Wu W, Parmar C, Grossmann P, Quackenbush J, Lambin P, Bussink J, Mak R, Aerts HJ. \"Exploratory Study to Identify Radiomics Classifiers for Lung Cancer Histology\". Front Oncol. 2016 Mar 30;6:71. doi: 10.3389/fonc.2016.00071. [4] Hazra, Animesh & Bera, Nanigopal & Mandal, Avijit. (2017). Predicting Lung Cancer Survivability using SVM and Logistic Regression Algorithms. International Journal of Computer Applications. 174. 19-24. 10.5120/ijca2017915325. [5] Akram, Sheeraz & Javed, Muhammad & Qamar, Usman & Khanum, Aasia & Hassan, Ali. (2014). \"ANN based Classification of Lungs Nodule using Hybrid Features from Computerized Tomographic Images\". Applied Mathematics & Information Sciences. 9. 183-195. 10.12785/amis/010124. [6] J. Alam, S. Alam and A. Hossan, \"Multi-Stage Lung Cancer Detection and Prediction Using Multi-class SVM Classifie,\" 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2), Rajshahi, Bangladesh, 2018, pp. 1-4, doi: 10.1109/IC4ME2.2018.8465593. [7] D. Rawat, Meenakshi, L. Pawar, G. Bathla, and R. Kant, \"Optimized Deep Learning Model for Lung Cancer Prediction Using Artificial Neural Networks Algorithm,\" 2022 3rd International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, pp. 889-894, doi: 10.1109/ICESC54411.2022.9885607. [8] R. P.R., R. A. S. Nair and V. G., \"A Comparative Study of Lung Cancer Detection using Machine Learning Algorithms,\" 2019 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT), Coimbatore, India, 2019, pp. 1-4, doi: 10.1109/ICECCT.2019.8869001. [9] Khan A, Tariq I, Khan H, Khan SU, He N, Zhiyang L, Raza F. \"Lung Cancer Nodules Detection via an Adaptive Boosting Algorithm Based on SNMV CNN\". J Oncol. 2022 Sep 26;2022:5682451. doi: 10.1155/2022/5682451. [10] Ausawalaithong, Worawate & Thirach, Arjaree & Marukatat, Sanparith & Wilaiprasitporn, Theerawit. (2018). Automatic Lung Cancer Prediction from Chest X-ray Images Using the Deep Learning Approach. 1-5. 10.1109/BMEiCON.2018.8609997. [11] V. Nisha Jenipher and S. Radhika, \"A Study on Early Prediction of Lung Cancer Using Machine Learning Techniques,\" 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS), Thoothukudi, India, 2020, pp. 911-916, doi: 10.1109/ICISS49785.2020.9316064. [12] J. Al-Tawalbeh, B. Alshargawi, H. Alquran, W. Al-Azzawi, W. A. Mustafa, and A. Alkhayyat, \"Classification of Lung Cancer by Using Machine Learning Algorithms\" 2022 5th International Conference on Engineering Technology and its Applications (IICETA), Al-Najaf, Iraq, pp. 528-531, doi: 10.1109/IICETA54559.2022.9888332. [13] J. Oentoro, R. Prahastya, R. Pratama, M. S. Kom and M. Fajar, \"Machine Learning Implementation in Lung Cancer Prediction - A Systematic Literature Review,\" 2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Bali, Indonesia, 2023, pp. 435-439, doi: 10.1109/ICAIIC57133.2023.10067128. [14] Huang S, Yang J, Shen N, Xu Q, Zhao Q. Artificial intelligence in lung cancer diagnosis and prognosis: Current application and future perspective. Semin Cancer Biol. 2023 Feb;89:30-37. doi: 10.1016/j.semcancer.2023.01.006. [15] J. Chen, \"Comparative Analysis of Machine Learning Models for Lung Cancer Prediction,\" 2023 IEEE International Conference on Image Processing and Computer Applications (ICIPCA), Changchun, China, 2023, pp. 242-246, doi: 10.1109/ICIPCA59209.2023.10257778.

Copyright

Copyright © 2025 Avinash S, Anu Kiruthiga R, Aditya Saran K P, Harish A, Dr. D Rasi. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.