AUTHOR=Zhang Shuhai , Wang Xiaolei , Yang Zhao , Zhu Yun , Zhao Nannan , Li Yang , He Jie , Sun Haitao , Xie Zongyu 

TITLE=Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning Study

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.905551

DOI=10.3389/fonc.2022.905551

ISSN=2234-943X

ABSTRACT=Purpose: To investigate radiomics features extracted from the optimal peritumoral region and intratumoral area on the early phase of DCE-MRI for predicting molecular subtypes of invasive ductal breast carcinoma (IDBC).
Methods: A total of 422 IDBC patients with immunohistochemical and fluorescence in situ hybridization results from two hospitals (Center 1: 327 cases, Center 2: 95 cases) who underwent preoperative DCE-MRI were retrospectively enrolled. After images preprocessing, radiomic features were extracted from intratumoral area and four peritumoral regions on DCE-MRI from two centers, and selected optimal peritumoral region. Based on the intratumoral, peritumoral radiomics features and clinical-radiological characteristics, five radiomics models were constructed through support vector machine (SVM) in multiple classification tasks related to molecular subtypes and visualized by nomogram. The performance of radiomics models was evaluated by ROC, confusion matrix, calibration curves and decision curve analysis.
Results: 6mm peritumoral size were defined optimal peritumoral region in classification tasks of hormone receptor (HR)-positive vs others, triple-negative breast cancer (TNBC) vs others, HR-positive vs human epidermal growth factor receptor 2 (HER2)-enriched vs TNBC, and 8mm was applied in HER2-enriched vs others. The combined clinical-radiological and radiomics models in three binary classification tasks (HR-positive vs others, HER2-enriched vs others, TNBC vs others) obtained optimal performance with the AUCs were 0.838, 0.848 and 0.930 in training cohort, respectively; 0.827, 0.813 and 0.879 in internal test cohort, respectively; 0.791, 0.707 and 0.852 in external test cohort, respectively.
Conclusion: Radiomics features in the intratumoral and peritumoral regions of IDBC on DCE-MRI had a potential to predict the HR-positive, HER2-enriched and TNBC molecular subtypes preoperatively.