AUTHOR=Yu Xiangling , Song Wenlong , Guo Dajing , Liu Huan , Zhang Haiping , He Xiaojing , Song Junjie , Zhou Jun , Liu Xinjie 

TITLE=Preoperative Prediction of Extramural Venous Invasion in Rectal Cancer: Comparison of the Diagnostic Efficacy of Radiomics Models and Quantitative Dynamic Contrast-Enhanced Magnetic Resonance Imaging

JOURNAL=Frontiers in Oncology

VOLUME=Volume 10 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2020.00459

DOI=10.3389/fonc.2020.00459

ISSN=2234-943X

ABSTRACT=Background: To compare the diagnostic performance of radiomics models with dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) perfusion parameters for the preoperative prediction of extramural venous invasion (EMVI) in rectal cancer patients, and to develop a preoperative nomogram for predicting EMVI status. 
Methods: In total, 106 rectal cancer patients were enrolled in our study. All patients underwent preoperative rectal high-resolution MRI and DCE-MRI. We built five models based on the perfusion parameters of DCE-MRI (quantitative model), the radiomics of T2-weighted (T2W) CUBE imaging (R1 model), DCE-MRI (R2 model), clinical features (clinical model), and clinical-radiomics features (R2-C model). The predictive efficacy of the radiomics signature was assessed and internally verified. The area under the receiver operating curve (AUC) was used to compare the diagnostic performance of different radiomics models and DCE-MRI quantitative parameters. The radiomics score and clinical-pathologic risk factors were constructed to an easy-to-use nomogram.
Results: The quantitative parameters of Ktrans and Ve values in EMVI-positive group were significantly higher than those in the EMVI-negative group (both P =0.02). Ktrans combine Ve showed a fair degree of accuracy (AUC: 0.680 in the training cohort; and an AUC of 0.715 in the validation cohort ) with Ktrans and Ve alone. The AUCs of R1 model and R2 model were 0.826, 0.715 and 0.872, 0.812 in the training and validation cohorts, respectively. And the R2-C model yielded an AUC of 0.904 in the training cohort and 0.812 in the validation cohort. The nomogram was presented based on the clinical-radiomics model. The calibration curves showed good agreement.
Conclusion: The radiomics nomogram that incorporates the radiomics score, histopathological grade and T stage, demonstrated better diagnostic accuracy than the DCE-MRI quantitative parameters, which may have significant clinical implications on preoperative individualized prediction of EMVI in the rectal cancer patients.