Artificial Intelligence-Based Mitosis Scoring in Breast Cancer: Clinical Application
Asmaa Ibrahim, Mostafa Jahanifar, Noorul Wahab, Michael S. Toss, Shorouk Makhlouf, N Atallah, Ayat Lashen, Ayaka Katayama, Simon Graham, Mohsin Bilal, Abhir Bhalerao, Shan E Ahmed Raza, David Snead, Fayyaz Minhas, Nasir Rajpoot, Emad A. Rakha
Abstract
In recent years, artificial intelligence (AI) has demonstrated exceptional performance in mitosis identification and quantification. However, the implementation of AI in clinical practice needs to be evaluated against the existing methods. This study is aimed at assessing the optimal method of using AI-based mitotic figure scoring in breast cancer (BC). We utilized whole slide images (WSIs) from a large cohort of BC with extended follow-up comprising a discovery (n=1715) and a validation (n=859) set (Nottingham cohort). The TCGA-BRCA cohort (n=757) was used as an external test set. Employing automated mitosis detection, the mitotic count was assessed using three different methods, the mitotic count per tumor area (MCT; calculated by dividing the number of mitotic figures by the total tumor area), the mitotic index (MI; defined as the average number of mitotic figures per 1000 malignant cells), and the mitotic activity index (MAI; defined as the number of mitotic figures in 3mm2 area within the mitotic hotspot). These automated metrics were evaluated and compared based on their correlation with the well-established visual scoring method of the Nottingham grading system (NGS) as well as Ki67 score, clinicopathological parameters, and patient outcome. AI-based mitotic scores derived from the three methods (MCT, MI and MAI) were significantly correlated with the clinicopathological characteristics and patient’s survival (p<0.001). However, the mitotic counts and the derived cut-offs varied significantly between the 3 methods. Only MAI and MCT were positively correlated with the gold standard visual scoring method used in NGS (r=0.8 and r=0.7 respectively), as well as Ki67 score (r=0.69 and r=0.55 respectively) and MAI was the only independent predictor of survival (p<0.05) in multivariate Cox regression analysis. For clinical applications, the optimum method of scoring mitosis using AI needs to be considered. MAI can provide reliable and reproducible results and can accurately quantify mitotic figures in BC.