AN ENSEMBLE STRATEGY LEVERAGING HYBRID DATASETS FOR ROBUST BREAST CANCER DETECTION

Abstract

Breast cancer is especially dangerous for women because it kills and hurts a lot of people. Because of this, there is a need for an algorithm that can spot the first signs of breast cancer essential. One of the most common types of cancer in women is breast cancer. Its spread among people is a major worry all over the world. To save the patient's life, it is very important to find the disease and treat it right away. Last year, more than 2.3 million women were told they had breast cancer, and about 0.7 million of them died. Manually diagnosing the disease isn't very good, and most of the time, it's almost impossible to find severe cancer early, which means that the patients die. Machine learning is a key part of figuring out what early signs of breast cancer to look for.

The goal of this study will show how Machine Learning (ML) and Deep Learning (DL) methods can be used to find breast cancer early and accurately to save lives. In this work breast cancer will predicted by using a hybrid model to combine ML and DL techniques. Firstly, a DL method Scale-Invariant Feature Transform (SWIFT) is used to extract the meaning full information from the image’s dataset and then different machine learning models such as (KNN and random forest and etc.) are applied to classify the malignant and benign cases. The main focus of this work is to figure out whether a breast cancer is benign or malignant based on different specific characteristics taken from a group of images from normal and breast cancer patients. The results will compare on the basis of accuracy, precision, Recall and F1-Score of the models. This study used Principal Component Analysis to find the optimized features from the for improving the accuracy of the used models. This will be done by using multiple Machine Learning algorithms and choosing the classification model with the highest accuracy.