Multichannel deep learning using multiregional DCE-MRI to predict axillary pathological complete response after neoadjuvant chemotherapy in breast cancer

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Abstract Objectives To develop and compare multiregional 2D and 2.5D deep learning models based on DCE-MRI for noninvasive prediction of axillary lymph node (ALN) pathological complete response (pCR) after neoadjuvant chemotherapy (NAC). Methods This retrospective study enrolled 305 patients with invasive breast cancer and ipsilateral ALN metastasis, which were randomly assigned to a training set ( n = 214) and a validation set ( n = 91). The Mann–Whitney U test, Spearman correlation analysis, max-relevance and min-redundancy and least absolute shrinkage and selection operator were used to select the most significant features. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve analysis, and decision curve analysis. Results Among the 305 patients, ALN pCR accounted for 46.6% (142/305). ER status, tumor MP grade and HER2 status were selected as independent predictors for ALN pCR ( P < 0.05). Both the 2.5D tumor (2.5D T ) and the 2.5D tumor–ALN (2.5D T+ALN ) models had higher AUC than those of the 2D tumor (2D T ) and 2.5D tumor–ALN (2D T+ALN ) models in the validation set (AUC: 0.797 vs. 0.706, 0.834 vs. 0.815). When combining clinicopathological factors, the 2.5D tumor–ALN–clinicopathologic (2.5D T+ALN +clinic) model achieved the highest performance among all models (AUC = 0.861). A retrospective model-based simulation suggested that a strategy guided by model predictions could reduce the estimated rate of unnecessary ALND from 40.7% to 8.8% and increase the model-estimated overall benefit rate from 59.3% to 74.7%. Conclusion The 2.5D T+ALN +clinic model demonstrated promising performance for predicting ALN pCR after NAC and has the potential to assist individualized axillary management by helping reduce unnecessary ALND.