A Quantitative Measurement Method for Nuclear-Pleomorphism Scoring in Breast Cancer

The study introduces a novel quantitative method, termed HM, for measuring nuclear pleomorphism in breast cancer, which is a critical factor in the Nottingham Histopathology Grading system. This method integrates size, shape, and appearance into a single model, providing a quantitative value between 0 and 1, with higher values indicating more pronounced pleomorphism. The HM model demonstrated high performance metrics, including an accuracy of 0.97 and an F1-score of 0.95, outperforming existing methods and showing potential as a new standard for assessing nuclear pleomorphism. The study used a dataset of 48 breast histopathology slides and validated the method with a fivefold cross-validation SVM classifier. Future work aims to expand the dataset and develop a deep learning model for automated nucleus segmentation.