AN EFFECTIVE WAY OF FINDING LUNG CANCER USING DEEP LEARNING TECHNIQUES

Abstract According to world health organization, Cancer is a leading cause of death worldwide, accounting for nearly 10 million deaths in 2020, or nearly one in six deaths. The most common cancers are breast, lung, colon and rectum and prostate cancers. Around one-third of deaths from cancer are due to tobacco use, high body mass index, alcohol consumption, low fruit and vegetable intake, and lack of physical activity. Cancer-causing infections, such as human papilloma virus (HPV) and hepatitis, are responsible for approximately 30% of cancer cases in low- and lower-middle-income countries. Many cancers can be cured if detected early and treated effectively. Computer programming used to improve cancer diagnosis, drug development, and precision medicine. AI involves programming a computer to act, reason, and learn. It’s great at finding patterns in large amounts of data, which is particularly helpful in scientific research. NCI, the Department of Energy, the Frederick National Laboratory for Cancer Research, and a transdisciplinary group of investigators are using AI to advance development of digital twins for people with cancer. Others use it to analyze imaging data and electronic health records to tailor patients’ radiation doses. AI is even being harnessed to quickly analyze population-based cancer data and estimate the probability of certain cancers. And these examples just scratch the surface—Artificial Intelligence has the potential to truly transform cancer care. Lung cancer can cause complications, such as: Shortness of breath. People with lung cancer can experience shortness of breath if cancer grows to block the major airways. Lung cancer can also cause fluid to accumulate around the lungs, making it harder for the affected lung to expand fully when you inhale. In this study, lung patient Computer Tomography (CT) scan images are utilised to identify and categorise lung nodules as well as to determine the nodules' malignancy degree in relation to parameters including radon gas exposure, air pollution, and chemical exposure. CNN is being used at work for this assignment. With the help of image processing and deep learning techniques, it is now much easier to diagnose lung cancer at an early stage. Computer tomography (CT) scan images are now utilised to identify and categorise lung nodules and determine their level of malignancy. In order to put this idea into practise, we have employed the CNN algorithm to identify lung cancer from CT-SCAN images, and we have a dataset of CT-SCAN images to train CNN