Recent Papers

It is one of the most common types of cancer worldwide and can affect both women and men, though it is far more common in women. Breast cancer occurs when normal cells in the breast begin to grow uncontrollably, forming a tumor and can invade surrounding tissues or spread (metastasize) to other parts of the body. It is the leading cause of death for women globally, and in order to properly treat it and lower mortality rates, it must be identified early and diagnosed accurately. Using a variety of datasets and imaging modalities, including multipara metric Magnetic Resonance Imaging (mpMRI), ultrasound, and histopathology pictures, research have used artificial intelligence (AI) and deep learning approaches to help predict, diagnose, and classify breast cancer. A range of machine learning algorithms, including ensemble techniques like Ada Boost, Gradient Boosting, and Random Forest, as well as sophisticated models like Convolutional Neural Networks (CNN) and Vision Transformers (ViT), have been evaluated for their ability to distinguish between benign and malignant tumors. Techniques such as adaptive token sampling, semi-supervised learning, and optimized stacking ensemble learning (OSEL) have been used in recent research to maximize classification accuracy, with the findings showing notable gains in performance measures across several studies. These developments highlight the possibility of incorporating machine learning (ML) techniques to improve computer-aided diagnostic (CAD) systems; models have been shown to achieve classification accuracies of 91% to 99%, offering useful resources for medical practitioners managing breast cancer.

Copyright © 2024 Santaji Soujanya. This is an open access article distributed under the Creative Commons Attribution License.