Paper Title
Lung Tumor Detection with Improved Accuracy Using Convolutional Neural Networks

Abstract
Cancer is one of the most prevalent and dead illnesses that claims a large number of lives every year. Lung cancer has the greatest death rate and is the most prevalent type of cancer overall. CT scans are used to diagnose lung cancer as it produces detailed images of tumors in the body and track their growth. The likelihood of survival will rise with early cancer detection. CT scans of the lungs were processed using Computer-Aided Diagnosis (CAD) to see if there was any indication of malignancy. The nature and location of the cancer will determine the course of treatment. The image processing methods are frequently employed in the medical field to detect lung cancers. The deep learning techniques are used to analyze important lung cancer diagnosis and reduce the workload of pathologists. The goal is to provide computers with the ability to perceive and process images in a manner similar to human vision and then produce the desired results. Deep learning techniques like Convolutional Neural Networks (CNN), improve the efficiency of cancer analysis. The efficient way to find lung cancer is to employ automated machine vision algorithms. The modified CNN in numerous computer vision tasks have demonstrated exceptional performance. Lung disease diagnosis can benefit greatly from the information that computed tomography (CT) can provide. The objective is to identify and categorize lung cancer from a provided input lung image. Keywords - Convolutional Neural Networks, Computed Tomography, Computer-Aided Diagnosis