A Comprehensive Review and Analysis of Advancements in Breast Cancer Detection and Classification
Baljit Kaur, Renu Popli · 2024
The comprehensive review analyzes Machine Learning (ML) in breast cancer detection, prediction, diagnosis, and treatment. The review study covers research from 2018–2024 on breast cancer prediction, detection, and diagnosis using machine learning tools/techniques. It compared different models, and performance metrics, which utilized datasets such as the Wisconsin breast cancer database and the online database for screening mammography. It encourages further research and innovation in breast cancer prediction to enhance ML-based disease forecasting. The review highlights research gaps and current techniques and suggests areas for future enhancement. This review explores machine learning algorithms to improve the effectiveness of breast cancer detection and classification. Recent research has highlighted using federated and deep learning to encourage cooperative data analysis while protecting patient privacy. Enhancing computing efficiency, researching advanced machine learning techniques like deep learning, and validating models on large amounts of data are among the main areas of key research gaps. Machine learning, deep learning, and federated learning techniques improve the accuracy and efficiency of breast cancer detection. These technologies improved results for breast cancer and personalized healthcare. Future research should focus on scalability, real-world validation, and integration of real-time systems to advance early detection and therapy planning for breast cancer.