Radiomics of Multiparametric MRI for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer: A Multicenter Study

Abstract

Purpose: We evaluated the performance of the newly proposed radiomics of multiparametric MRI (RMM), developed and validated based on a multicenter dataset adopting a radiomic strategy, for pretreatment prediction of pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer. Experimental Design: A total of 586 potentially eligible patients were retrospectively enrolled from four hospitals (primary cohort and external validation cohort 1-3). Quantitative imaging features were extracted from T2-weighted imaging, diffusion-weighted imaging, and contrast-enhanced T1-weighted imaging before NAC for each patient. With features selected using a coarse to fine feature selection strategy, four radiomic signatures were constructed based on each of the three MRI sequences and their combination. RMM was developed based on the best radiomic signature incorporating with independent clinicopathologic risk factors. The performance of RMM was assessed with respect to its discrimination and clinical usefulness, and compared with that of clinical information-based prediction model. Results: Radiomic signature combining multiparametric MRI achieved an AUC of 0.79 (the highest among the four radiomic signatures). The signature further achieved good performances in hormone receptor-positive and HER2negative group and triple-negative group. RMM yielded an AUC of 0.86, which was significantly higher than that of clinical model in two of the three external validation cohorts. Conclusions: The study suggested a possibility that RMM provided a potential tool to develop a model for predicting pCR to NAC in breast cancer.

Prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer using a deep learning (DL) method

“…Several methods have been proposed by using radiomics or DL on pre‐NAC MRI data to predict pCR before the initiation of NAC. In several studies, the AUC ranged from 0.78 to 0.86 . Unfortunately, to date, no radiomics or DL models have been used in clinical practice to change the clinical decision‐making of neoadjuvant therapy.…”

“…Multiple studies have shown that dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI) has higher predictive power in predicting residual tumor size after NAC, compared with the conventional methods including clinical breast examination, mammography, and ultrasound . Recent developments in radiomics have shown potentials in the prediction of pathological results by radiological data . Deep learning makes it possible to automatically extract features from an image without the necessity of feature predefinition …”

“…In previous studies, only pre‐NAC MRI data were used and the area under receiver operating characteristic (ROC) curve (AUC) ranged from 0.78 to 0.86 . Actually, the structural and functional change in tumor microenvironment after NAC can reflect the therapeutic response effect of patients .…”

“…7,8 Recent developments in radiomics have shown potentials in the prediction of pathological results by radiological data. 9,10 Deep learning makes it possible to automatically extract features from an image without the necessity of feature predefinition. 11,12 In previous studies, only pre-NAC MRI data were used and the area under receiver operating characteristic (ROC) curve (AUC) ranged from 0.78 to 0.86.…”

“…11,12 In previous studies, only pre-NAC MRI data were used and the area under receiver operating characteristic (ROC) curve (AUC) ranged from 0.78 to 0.86. 9,10,12 Actually, the structural and functional change in tumor microenvironment after NAC can reflect the therapeutic response effect of patients. 13,14 Therefore, we suspected that more accurate prediction could be achieved after NAC when post-NAC MRI data were also available, but no relevant literature has been found.…”