Prediction Lung Cancer– In Machine Learning Perspective

Abstract

Recent years have shown an increasing mortality rate from lung cancer; therefore, it is essential to determine whether or not the tumor has
transformed into cancer. If an accurate prediction can be made at an early stage, not only will many lives be saved, but doctors will be able to begin treatment sooner. Checking the tumor's size, location, etc., with the help of computed tomography is crucial for ensuring the tumor's health. In this paper, we propose a framework for early cancer prediction that has the potential to save a large number of lives. Our primary research interests lie in the areas of computer science known as Digital Image Processing (DIP) and Machine Learning (ML). The preprocessing stage of digital image processing has gained a lot of notoriety in recent years. The next step involves putting the pre-processed image through a segmentation phase, passing the resulting image on to a feature extraction phase, and then using machine learning classification algorithms like SVM (Support Vector Machines), Random Forest, and ANN (Artificial Neural Network) to train the features extracted from the image. The prognosis for the tumor's malignancy or benign nature is based on the classification results obtained.