Application of CAD Systems in Breast Cancer Diagnosis Using Machine Learning Techniques: An Overview of Systematic...

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Oncology

Background:

• Breast cancer remains a leading cause of mortality in women globally.
• Early detection and diagnosis are crucial for improving treatment outcomes.
• Computer-Aided Diagnosis (CAD) systems utilizing Artificial Intelligence (AI) are increasingly vital for radiologists in medical image analysis.

Purpose of the Study:

• To provide a comprehensive meta-review of CAD systems for breast cancer diagnosis and treatment.
• To synthesize evidence from 48 systematic reviews published between 2015 and January 2025.
• To offer a broad overview of imaging techniques, datasets, AI methods, and clinical tasks in breast cancer CAD.

Main Methods:

• A systematic meta-review following PRISMA guidelines.
• Inclusion of 48 systematic reviews published between 2015 and January 2025.
• Analysis focused on imaging modalities, datasets, AI methods, and clinical tasks.

Main Results:

• Mammography is the most common imaging modality; DDSM, MIAS, and INBreast are frequently used datasets.
• Detection and classification of breast lesions are the most studied clinical tasks.
• Deep learning approaches are increasingly prevalent in CAD systems.

Conclusions:

• Current CAD systems show promise but face limitations such as data scarcity, lack of transparency, and restricted clinical integration.
• This review aids medical professionals and researchers in understanding the current landscape of breast cancer CAD.
• Identified limitations provide direction for future research and development in AI for breast cancer care.