Predictive Analysis of Colorectal Cancer via CT scans Using Convolutional Neural Networks
DOI:
https://doi.org/10.15379/ijmst.v10i3.3365Keywords:
Deep Learning, Machine Learning, Neural Network, Convolutional Neural Network, Image Processing, Healthcare, Colorectal Cancer, Heterogeneous DataAbstract
In recent years, the area of Medicine and Healthcare has made significant advances with the assistance of computational technology. New diagnostic techniques including image processing were developed which can help healthcare/clinical experts in many ways. One of the domains is cancer prediction and treatment. Cancer is the world's second-largest cause of mortality, claiming the lives of one out of every six individuals. Colorectal cancer (CRC) is a common cancer worldwide. It ranks as the third most frequently detected cancer among men and the second among women, with more than 1.4 million new cancer cases every year. This article proposed an improvised CNN approach to analyze the CT scan images of colorectal cancer to predict and classify them into benign(non-cancerous) and malignant(cancerous). In further work the result with tumorous class with patient’s other parameters are integrated for assessing the risk level of cancer. This model results in 96.8% accuracy and minimal error rate. The main contribution of this work is to assist medical fraternity to automatically analyze the CT scan images for prediction and classification of colorectal cancer.