Computer-Aided Breast Cancer Classification Framework for Predictive, Preventive, and Personalized Medicine

In 3P medicine, a physician applies a more holistic approach to breast cancer treatment that focuses on prevention, prediction, and personalized treatment. There are many approaches to meet these criteria that, in the end, result in the creation of customized treatment plans which meet the patient’s individual needs. In this chapter, we describe a neural network approach to computer-aided automatic cancer classification using cytological slides to numerically grade breast cancer malignancies. The proposition of such a system is an answer to fast, repeatable, and reliable cancer detection that can lead to faster diagnosis. Early detection and effective treatment can reduce mortality by up to 30%. To establish a precise and faster diagnosis, a biopsy examination is often required. Here, we describe a computer-aided breast cancer classification framework that allows the estimation of a malignancy grade. Grading breast cancer malignancies is an essential step in breast cancer diagnosis and helps determine their prognosis and course of treatment. In the case of breast cancer, the determination of cancer malignancy influences the patient’s type of treatment and therefore it not only has a prognostic, but also a predictive value. The proposed framework can determine these factors from microscopic images of fine needle aspirates with high accuracy. Moreover, the results of this study have shown that machine learning methods are very effective in breast cancer prevention by providing a range of tools for early detection and diagnosis.