Current projects

The rationale for this systematic review is to address the interobserver variability and subjectivity in the Nottingham Grading System (NGS), which remains a significant challenge in breast cancer histopathology. Accurate grading is essential for prognosis and treatment decisions, yet differences in pathologists’ assessments—particularly in evaluating nuclear pleomorphism and mitotic count—can impact clinical outcomes. With the rise of Artificial Intelligence (AI) in digital pathology, AI-based grading tools offer a potential solution by improving diagnostic accuracy, reproducibility, and efficiency. This review aims to systematically evaluate the performance, reliability, and clinical applicability of AI-driven Nottingham grading compared to human pathologists. By synthesizing existing research, it will provide insights into the strengths, limitations, and feasibility of AI integration in pathology practice. The findings could contribute to the development of standardized AI- assisted grading protocols, ultimately enhancing diagnostic consistency and patient outcomes in breast cancer management.