Breast Cancer Prediction using Relative Analysis of Machine Learning and Deep Learning Techniques
Manas Bhole, Pranav Sandip Chavan, Yash Bharambay, Anish Nair · Zenodo (CERN European Organization for Nuclear Research) · 2021
Breast cancer is one of the deadliest disease caused to the women in this world. Women are the ones who are more likely to be diagnosed with it. A major cause of increased mortality in women. A breast cancer diagnosis takes time, and because systems are limited, it is vital to design a system that can automatically diagnose breast cancer in its early stages. According to the statistics, 7 billion people and out of which 3.4 billion are women and that 1 out of every 22 women is diagnosed with breast cancer. Though this method cannot definitively detect cancer, it can assist clinicians in determining whether a biopsy is necessary by giving information on whether the patient has breast cancer. Confusion matrix and ROC analyses were used to evaluate the definite diagnosis for each patient. The dataset has been taken from the alcrase dataset, which contains approx 16000 datasets and 30 features that would be used in detecting the results from the algorithm applied. The main idea for the paper is to do a comparative research of the machine learning and deep learning methods and to show which is the best performing algorithm amongst all of them.