A Comprehensive and Forward-Looking Approach to Diagnosing Breast Cancer: Methods Based on Deep Learning through PRISMA

Resumen

Background: Breast Cancer (BC) is the predominant form of cancer among women globally. We conducted a comprehensive investigation and meta-analysis to address the information gaps and enhance the Balance of life (BoL) for individuals with breast cancer. Consequently, researchers and clinicians will have a deeper understanding of the issue.

Methods: This research aims to look at the current computer and digital pathology methods used to find breast cancer, focusing on deep learning. The first step is to look at public sources that have information about breast cancer diagnoses. In addition, the study looks at the newest developments in using deep learning to find breast cancer.

Results: The study's results indicate that deep learning-based testing methods have pros and cons. This study thoroughly analyses the present condition of machine learning-based classifiers and image modalities in computer-aided design (CAD) systems. Research is advised to develop CAD systems that are both objective and efficient.

Conclusion: Deep learning-based methods for detecting breast cancer in computational pathology show promise but have advantages and disadvantages.