Breast Cancer Detection using image segmentation and Machine Learning approaches

The most prevalent cancer in women worldwide is breast cancer. A better outlook and lower mortality rates depend on early detection. Machine learning algorithms have recently demonstrated encouraging results in assisting breast cancer detection. This abstract seeks to give a summary of the research on machine learning algorithms for breast cancer detection. Various machine learning methods, such as artificial neural networks, support vector machines, and random forests, among others, have been used in a number of studies. Mammography image and patients data are used to train these algorithms, which can reliably predict the presence of breast cancer. The findings of these studies suggest that machine learning methods can support the highly accurate, sensitive, and specific detection of breast cancer. These algorithms can also recognise features and trends. Some algorithms might perform well on specific datasets but struggle to generalize to different populations or diverse patient demographics. This can limit their applicability in real-world scenarios. Image segmentation methods are employed to isolate the region of interest (ROI) containing potential abnormalities. To identify the key-points we compared two feature extraction algorithms SIFT (Scale-Invariant Feature Transform), ORB (Oriented FAST and Rotated BRIEF)