Prediction of pathological complete response in breast cancer by histogram signatures from multi-phase contrast enhanced MRI

Motivation: Accurate prediction of pathological complete response (pCR) after neoadjuvant chemotherapy enables individualized treatment options to avoid unnecessary breast excision and improve patients’ life quality. Goal(s): To improve the prediction accuracy by simultaneously extracting temporal and spatial features of MRI signal during contrast enhancement. Approach: A histogram signature is designed by concatenating histograms at different enhancing phases into a 2D picture and classified by convolutional neural network into pCR or non-pCR. Results: The AUC, sensitivity, specificity of the histogram signature for pCR prediction is 0.833 in the test group (n=132). The model combining histogram signature with ER and HER2 increases AUC to 0.842. Impact: Histogram signatures from multi-phase MRI can be used as a new marker to measure tumor heterogeneity, estimate drug uptake, evaluate treatment response and predict prognosis for breast cancer or other cancers.