Objective To investigate the relationship between imaging features from whole-tumor evaluation with MRI as well as radiomics and SMAD4 expression in pancreatic ductal adenocarcinoma (PDAC) and to determine imaging biomarkers of SMAD4.

Methods A total of 60 patients with pathologically confirmed PDAC in Zhongshan Hospital, Fudan University from January 2012 to September 2017 were included. All the patients received abdominal contrast-enhanced MRI examination with the same equipment before surgery. Whole-tumor evaluation including subjective evaluation and radiomics analysis was performed. Sections of specimens were reviewed and SMAD4 expression was evaluated. Univariate analysis, as well as the radiomics were screened by maximum relevance minimum redundancy (mRMR) method, and multi-factor fusion modeling was contracted to find the imaging biomarkers that could predict SMAD4 expression.

Results The positive and negative expressions of SMAD4 were found in 11 (18.3%) and 49 (81.7%) patients, respectively. Only the gender had statistically significant difference between the two groups (P＝0.012). There was no significant difference in qualitative features and whole-tumor quantitative features. The proportion of males was significantly higher than that of females in the negative expression group (71.4% vs 28.6%). After single-factor screening of whole-tumor radiomic features basing on SMAD4 expression, 6 features entered into multi-factor fusion models. Portal phase_wavelet-HHL_NGTDM_Contrast+T₁WI_wavelet-HHL_GLDM_HighGrayLevelEmphasis were enrolled as the best subset model, with the BIC of 33.4, and the area under ROC curve was 0.92 (P < 0.001) for predicting the expression of SMAD4. The prediction sensitivity and specificity was 90.9% and 81.6%, with the intra-group prediction accuracy of 83.3%.

Conclusion Through whole-tumor MRI evaluation with radiomics analysis is expected to noninvasively obtain the imaging-biological markers of SMAD4 expression in PDAC, with good performance.