Deep learning with perspective modeling for early detection of malignancy in mammograms

Malignancy in human bodies are named behind the body part in which it invades exponentially like lungs cancer if malignancy is invading lungs. Growth of a cell is controlled by its centroid and it goes uncontrolled if it is behaving abnormally. Objective of this work is to deliver a classification system that can be used to classify breast images as a benign or malignant and if malignant then can further classify which type of malignancy that is non-invasive or invasive cancer. This model can also prescribe treatment for predicted malignant class with details like time taken, degree of seriousness, probability of curing by opted treatment because treatment of a breast cancer depends on type and stage of malignancy. To achieve higher or clinical usage accuracy by deploying advances of soft computing and image analysis like deep learning and deep neural networks to decrease breast cancer death as a concrete effort using mammograms by detecting breast cancer in an early stage.