Machine learning techniques for breast cancer computer aided diagnosis using different image modalities: A systematic...

Area of Science:

• Medical Imaging
• Artificial Intelligence in Healthcare
• Oncology

Background:

• Increasing incidence of breast cancer necessitates advanced diagnostic tools.
• Physician expertise in breast cancer diagnosis can be augmented by computational methods.
• Computer-aided diagnosis/detection (CAD) systems offer potential for improved accuracy.

Purpose of the Study:

• To conduct a systematic review of the state-of-the-art in computer-aided diagnosis/detection (CAD) systems for breast cancer.
• To analyze current CAD systems based on image modalities and machine learning classifiers.
• To identify potential research directions for more objective and efficient CAD systems.

Main Methods:

• Systematic review methodology employed.
• Searches conducted across Springer Link, Science Direct, IEEE Xplore, and PubMed databases.
• Inclusion/exclusion criteria applied to 320 retrieved studies, with 154 selected for analysis.

Main Results:

• Analysis of current CAD systems categorized by image modalities and machine learning classifiers.
• Discussion of potential research avenues for enhancing CAD system objectivity and efficiency.
• Overview of the landscape of academic and scientific CAD research, excluding commercial interests.

Conclusions:

• The review highlights the current advancements and challenges in CAD systems for breast cancer.
• Further research is needed to develop more objective and efficient CAD systems.
• CAD systems show promise in assisting physicians with breast cancer diagnosis and detection.