Background: Breast cancer (BC) is the most frequently diagnosed cancer worldwide and the second leading cause of cancer-related deaths. To advance predictive recurrence models we developed an AI-image analysis platform that utilizes whole slide images (WSI) to phenotype invasive BC (IBC) at the tissue-cell architectural level. The objective was to produce an AI-IBC phenotype that includes a novel methodology to grade BC along with additional features that reflect biological pathways. We sought to combine these extracted and complex image feature sets with standard clinical pathology data to develop readily accessible models that predict early-stage BC recurrence.