Investigations on lung images for early cancer detection using machine learning techniques

Abstract

Lung cancer is one of the most commonly occurring diseases that newlineranked in the top of the present survey. The advancements in the medical field newlineenable non-invasive method of computerized diagnosis procedures and newlinedetection process. Deep learning methods are already in evaluation by newlinekeeping the deep analysis on improving segmentation accuracy and prediction newlineaccuracy etc. The classification of tumor type depends on the quality of newlinesegmentation work and feature mappings. The proposed research work is newlinefocused on developing a robust model that not only classify the type of newlinetumors with improved accuracy but also capable of detecting the early stages newlineof cancer by detecting the lung nodules, segmenting tumor area and classify newlinethe tumor size . The system also includes the estimation of area infected after newlinethe tumor is being segmented and estimates the survival rate with respect to newlinethe age and medical history of the patient. People with sustainable medical newlinerecords seems to be more survival strength comparing with the patients with newlinediabetics, high blood pressure, surgical background etc. The system act as a newlinecomplete support system for lung tumor related implications with recently newlinegrowing technologies. Lung cancer is the most dangerous and widespread newlinecancer in the globe according to evaluation of cancer cells in the lungs. In newlinecase of non-treating the cancer cells, leads to metastasis and enable the cancer newlinecell to travel from one place to other organs through lymph nodes.The aim of newlinethis research was to detect features for accurate images comparison as pixels newlinepercentage and mask-labelling. The objective of the research work considers newlinevarious scenarios on lung tumor detection, related symptoms are considered. newlineso the process of early detection of the disease. It plays a crucial role in newlinepreventing serious advanced stages and lowering its distribution percentage newline