Deep Learning Based Methods for Breast Cancer Diagnosis: A Systematic Review and Future Direction

Area of Science:

• Oncology
• Artificial Intelligence
• Medical Imaging

Background:

• Breast cancer remains a significant health concern for women globally, with ongoing research focused on improving early detection and treatment outcomes.
• Artificial intelligence (AI), specifically deep learning, is emerging as a powerful tool in medical diagnostics, offering enhanced capabilities for identifying complex patterns in biological data.
• Traditional machine learning methods often require extensive manual feature engineering, whereas deep learning models can automatically extract relevant features, streamlining the diagnostic process.

Purpose of the Study:

• To conduct a systematic literature review of deep learning-based methods for breast cancer detection.
• To analyze current trends, challenges, and future research directions in the application of deep learning to breast cancer diagnostics.
• To provide a comprehensive overview for researchers and practitioners in the field, focusing on genomics and histopathological imaging data.

Main Methods:

• A systematic literature review was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.
• Searched and gathered relevant studies, followed by eligibility screening and quality evaluation.
• Identified and analyzed 98 eligible articles focusing on deep learning techniques for breast cancer detection.

Main Results:

• Convolutional Neural Networks (CNNs) were identified as the most accurate and widely adopted deep learning model for breast cancer detection.
• Accuracy metrics are the predominant method for evaluating the performance of these deep learning models.
• The review also examined datasets commonly used and evaluation metrics employed in breast cancer detection studies.

Conclusions:

• Deep learning models, especially CNNs, offer significant advancements in the accuracy and efficiency of breast cancer detection.
• The findings underscore the potential of AI to improve early diagnosis and patient survival rates.
• Further research is needed to address existing challenges and explore new avenues in AI-driven breast cancer diagnostics.