Radiopathomic Graph Deep Learning for Multiscale Spatial-Contextual Modeling of Intratumoral Heterogeneity to Predict Breast Cancer Response to Neoadjuvant Therapy

A radiopathomic graph deep learning system performed well for explainable prediction of pathologic complete response to neoadjuvant therapy in breast cancer through intratumoral heterogeneity spatial-contextual modeling at the tissue and cellular scales.