Revolutionizing Breast Cancer Detection with Artificial Intelligence and Machine Learning Breakthroughs in Imaging and Diagnosis: Literature Review
Abstract
Cancer is a major global health challenge, with 19.3 million new cases and 10 million deaths in 2021. Breast cancer, with 2.3 million cases in 2022, is among the most common. Personalized treatment is vital for better outcomes but requires collaboration between clinicians and researchers. Traditional diagnostic methods, relying on manual histological examination, are slow and error-prone, worsened by a global shortage of pathologists, highlighting the need for more reliable diagnostic tools. The digitization of tissue slides has enabled artificial intelligence (AI) and machine learning (ML) integration into medical imaging, promising improved patient care. This study evaluates AI-based computational models for digital pathology, focusing on breast cancer diagnosis. These models aim to boost diagnostic accuracy and efficiency, overcoming limitations of conventional histopathological methods. We assessed various AI-based models for digital pathology, emphasizing their potential to enhance patient outcomes, treatment planning, and diagnostic accuracy in oncology, particularly for breast cancer. This paper reviews recent AI applications in oncology, highlighting their strengths and current challenges, and underscores their ability to improve the accuracy and efficiency of diagnostic processes.