A novel radiomics signature based on T2-weighted imaging accurately predicts hepatic inflammation in individuals with biopsy-proven nonalcoholic fatty liver disease: a derivation and independent validation study

Abstract

Background: Currently, there are no effective methods for assessing hepatic inflammation without resorting to histological examination of liver tissue obtained by biopsy. T2-weighted images (T2WI) are routinely obtained from liver magnetic resonance imaging (MRI) scan sequences. We aimed to establish a radiomics signature based on T2WI (T2-RS) for assessment of hepatic inflammation in people with nonalcoholic fatty liver disease (NAFLD).

Methods: A total of 203 individuals with biopsy-confirmed NAFLD from two independent Chinese cohorts with liver MRI examination were enrolled in this study. The hepatic inflammatory activity score (IAS) was calculated by the unweighted sum of the histologic scores for lobular inflammation and ballooning. One thousand and thirty-two radiomics features were extracted from the localized region of interest (ROI) in the right liver lobe of T2WI and, subsequently, selected by minimum redundancy maximum relevance and least absolute shrinkage and selection operator (LASSO) methods. The T2-RS was calculated by adding the selected features weighted by their coefficients.

Results: Eighteen radiomics features from Laplacian of Gaussian, wavelet, and original images were selected for establishing T2-RS. The T2-RS value differed significantly between groups with increasing grades of hepatic inflammation (P<0.01). The T2-RS yielded an area under the receiver operating characteristic (ROC) curve (AUROC) of 0.80 [95% confidence interval (CI): 0.71-0.89] for predicting hepatic inflammation in the training cohort with excellent calibration. The AUROCs of T2-RS in the internal cohort and external validation cohorts were 0.77 (0.61-0.93) and 0.75 (0.63-0.84), respectively.

Conclusions: The T2-RS derived from radiomics analysis of T2WI shows promising utility for predicting hepatic inflammation in individuals with NAFLD.

Keywords: Nonalcoholic fatty liver disease (NAFLD); inflammation activity; magnetic resonance imaging (MRI); radiomics.

Figure 1

Radiomics feature selection using the LASSO method after mRMR. (A) Identification of the optimal penalization coefficient lambda (λ) in the LASSO via the minimum criterion. (B) LASSO coefficient profiles of the 20 radiomics features. The dotted vertical line was plotted at the minimum log(λ), and resulted in 18 non-zero coefficients. (C) Coefficients of the features selected by LASSO. Feature 1: original_glszm_LowGrayLevelZoneEmphasis; feature 2: original_glrlm_RunVarian-ce; feature 3: original_glcm_Imc1; feature 4: original_glszm_GrayLevelNon-Uniformity; feature 5: wavelet-LLL_glrlm_LongRunHighGrayLevelEmphasis; feature 6: original_glrlm_GrayLevelNonUniformity; feature 7: original_ngtdm_Str-ength; feature 8: original_glcm_ClusterShade; feature 9: log-sigma-3-0-mm-3D_glszm_LowGrayLevelZoneEmphasis; feature 10: wavelet-HHH_glszm_Gray-LevelNonUniformityNormalized; feature 11: wavelet-HHL_glszm_SizeZoneNon-Uniformity: feature 12: wavelet-HHH_glszm_SizeZoneNonUniformity; feature 13: wavelet-LLL_glszm_SizeZoneNonUniformity; feature 14: log-sigma-2-0-mm-3D_glszm_SizeZoneNonUniformity; feature 15: original_ngtdm_Busyness; feature 16: original_gldm_LowGrayLevelEmphasis; feature 17: original_glrlm_LongRun-HighGrayLevelEmphasis; feature 18: original_gldm_SmallDependenceLowGray-LevelEmphasis. LASSO, least absolute shrinkage and selection operator; mRMR, minimum redundancy maximum relevance.

Figure 2

Comparison of T2-RS between patients with MIA vs. SIA in the training cohort (A), internal validation cohort (B), and external validation cohort (C). In the boxplot, the central box represents the values from the lower to upper quartile (25 to 75 percentile). T2-RS, radiomics signature based on T2WI; MIA, mild hepatic inflammatory activity; SIA, severe inflammatory activity.

Figure 3

Performances of T2-RS in the training cohort (A), internal validation cohort (B) and external validation cohort (C) presented as ROC curves. T2-RS, radiomics signature based on T2WI; ROC, receiver operating characteristic.