Deep learning approaches for detection, classification, and localization of breast cancer using microscopic images: A review and bibliometric analysis

The prevalence of breast cancer continues to be a major public health concern. Timely detection is vital for effective treatment and patient survival. In order to appropriately detect and effectively manage breast cancer, which affects people of both sexes and is characterized by its complexity and prevalence, new diagnostic approaches are required.

Microscopic images are crucial for identifying and characterizing breast lesions. Nevertheless, accurately classifying these abnormalities is difficult because of the inconsistencies in image clarity and the heterogeneous composition of breast tissue. This article intends to examine current breakthroughs in the area of breast cancer detection, classification, and localization utilizing deep learning approaches that are specifically designed for evaluating microscopic images. It highlights the importance of early detection in significantly influencing treatment outcomes, patient survival rates, and the critical role of deep learning methodologies in enhancing breast cancer diagnosis. These approaches include a variety of advanced algorithms specifically developed for extracting features, segmenting, and classifying breast lesions that are visible in microscopic images. The thorough examination of these images utilizing deep learning models enhances diagnostic precision and assists in differentiating between benign and malignant cancers.

This article aims to present a comprehensive integration of state-of-the-art studies, highlighting the significant influence of deep learning in utilizing microscopic images to achieve precise breast cancer diagnosis. It provides an in-depth look at how deep learning is being used to analyze microscopic images for the purpose of locating, diagnosing, and categorizing breast cancer.