Motivation: Currently, there are no standardized methods or imaging biomarkers available in clinical practice to accurately predict pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in patients with non-mass enhancement breast cancer. Goal(s): Utilize longitudinal dynamic contrast-enhanced (DCE) MRI radiological features alongside clinical and pathological data to predict pCR in breast cancer patients. Approach: We retrospectively collected longitudinal MRI and clinical data from 303 patients undergoing NAC and utilized machine learning approaches for pCR prediction. Results: Our results showed significant associations between multiple radiological and clinical characteristics and pCR. The XGBoost machine learning models effectively predicted pCR in breast cancer. Impact: We proposed a novel model based on longitudinal MRI data to predict pCR to NAC in breast cancer, including both mass and non-mass enhancement lesions, to inform personalized clinical treatment plans.
Tang et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: