MRI-based radiomics approach for differentiation of hypovascular non-functional pancreatic neuroendocrine tumors and solid pseudopapillary neoplasms of the pancreas

Abstract

Background: This study aims to investigate the value of radiomics parameters derived from contrast enhanced (CE) MRI in differentiation of hypovascular non-functional pancreatic neuroendocrine tumors (hypo-NF-pNETs) and solid pseudopapillary neoplasms of the pancreas (SPNs).

Methods: Fifty-seven SPN patients and twenty-two hypo-NF-pNET patients were enrolled. Radiomics features were extracted from T1WI, arterial, portal and delayed phase of MR images. The enrolled patients were divided into training cohort and validation cohort with the 7:3 ratio. We built four radiomics signatures for the four phases respectively and ROC analysis were used to select the best phase to discriminate SPNs from hypo-NF-pNETs. The chosen radiomics signature and clinical independent risk factors were integrated to construct a clinic-radiomics nomogram.

Results: SPNs occurred in younger age groups than hypo-NF-pNETs (P < 0.0001) and showed a clear preponderance in females (P = 0.0185). Age was a significant independent factor for the differentiation of SPNs and hypo-NF-pNETs revealed by logistic regression analysis. With AUC values above 0.900 in both training and validation cohort (0.978 [95% CI, 0.942-1.000] in the training set, 0.907 [95% CI, 0.765-1.000] in the validation set), the radiomics signature of the arterial phase was picked to build a clinic-radiomics nomogram. The nomogram, composed by age and radiomics signature of the arterial phase, showed sufficient performance for discriminating SPNs and hypo-NF-pNETs with AUC values of 0.965 (95% CI, 0.923-1.000) and 0.920 (95% CI, 0.796-1.000) in the training and validation cohorts, respectively. Delong Test did not demonstrate statistical significance between the AUC of the clinic-radiomics nomogram and radiomics signature of arterial phase.

Conclusion: CE-MRI-based radiomics approach demonstrated great potential in the differentiation of hypo-NF-pNETs and SPNs.

Keywords: Magnetic resonance imaging; Pancreatic neuroendocrine tumors; Radiomics; Solid pseudopapillary neoplasms of the pancreas.

Fig. 1

Flowchart of the patients’ recruitment

Fig. 2

The selected radiomics features from LASSO regression and their associated coefficients. a Precontrast T1WI, b arterial phase, c portal phase, d delayed phase

Fig. 2

The selected radiomics features from LASSO regression and their associated coefficients. a Precontrast T1WI, b arterial phase, c portal phase, d delayed phase

Fig. 3

ROC curve of radiomics signatures extracted from CE-MRI for the training and validation cohort. AP, arterial phase; PP, portal phase; DP, delayed phase

Fig. 4

Quantitative nomogram for the discrimination of SPNs and hypo-NF-pNETs. The closer the risk is to 0.9, the more likely the tumor is to be SPN, and the closer the risk is to 0.1, the more likely it is to be hypo-NF-pNETs. Radscore was calculated by summing the selected features weighted by their coefficients. The final formula of radscore is: Radscore = -0.601 × wavelet_HLH_glszm_GrayLevelNonUniformityNormalized + 0.326 × log_sigma_5_0_mm_3D_gldm_DependenceNonUniformityNormalized + -1.391 × wavelet_HHH_glszm_SizeZoneNonUniformityNormalized + 1.138 × wavelet_HLL_glcm_ClusterShade + -1.778 × log_sigma_5_0_mm_3D_gldm_LargeDependenceLowGrayLevelEmphasis + 1.074 × wavelet_LHL_firstorder_Skewness + 0.199 × log_sigma_4_0_mm_3D_firstorder_90Percentile + 0.002 × wavelet_HHL_glszm_GrayLevelNonUniformityNormalized + 3.734 × wavelet_LLH_glszm_GrayLevelNonUniformityNormalized + 0.76 × wavelet_HLL_firstorder_Skewness + 0.259 × wavelet_HHH_glcm_Imc1 + 0.322 × log_sigma_5_0_mm_3D_glszm_LargeAreaLowGrayLevelEmphasis + 1.754 × log_sigma_3_0_mm_3D_firstorder_Maximum + -0.495*original_shape_Flatness + 2.127

Fig. 5

ROC curve of the established nomogram

Fig. 6

Calibration curves of the nomogram. a Training cohort, b validation cohort

Fig. 7

The decision curve analysis for the nomogram. The gray and black line represent the treat-all and treat-none scheme respectively