Breast Cancer Diagnosis Using Computational Model: Recent Advancement

Abstract

Since breast cancer affects one in every four women, it is an utmost need to investigate novel diagnostic technologies and treatment techniques. This requires the development of diagnostic techniques to simplify the identification of cancer cells, which can facilitate cancer therapy. One of the most significant obstacles in chemotherapy is the absence of technologies that can measure its effectiveness while it is being administered. Additionally, due to its steadily expanding prevalence and mortality rate, cancer has surpassed AIDS as the world's second leading cause of death. Breast cancer accounts for a disproportionately high number of cancer-related deaths among women worldwide, making precise, sensitive imaging a necessity for this disease. Breast cancer can be successfully treated if it is diagnosed early. As an alternate strategy, the use of cutting-edge computational methodologies has been advocated for developing innovative breast cancer diagnostic imaging techniques. The following article provides an overview of the traditional diagnostic procedures that have historically been employed for the detection of breast carcinoma, as well as the current methods that are being utilized. Furthermore, a comprehensive overview of various mathematical frameworks is provided, including machine learning, deep learning, artificial neural networks, and robotics, highlighting their progress and potential applications in the field of breast cancer diagnostic imaging.