Response to NAC is a key predictor of recurrence risk and is commonly evaluated using the Residual Cancer Burden (RCB) score in TNBC patients. Patients experiencing a pathologic complete response (pCR), have RCB 0 disease and a lower recurrence risk compared to those with residual disease (RD) (RCB 1, 2 or 3).
While RCB quantifies residual disease (RD) based on tumor size, cellularity, and lymph node involvement, it does not capture the complexity of the tumor microenvironment (TME).
In this study, we employ a machine learning (ML)-based approach to analyze digitized H&E-stained slides and assess whether ML-derived pathology features can further improve prognostic information in patients with RD.
Conference
USCAP 2025
Partner
Dana Farber Cancer Institute
View Poster