Accuracy of MR elastography and anatomic MR imaging features in the diagnosis of severe hepatic fibrosis and cirrhosis

Abstract

Purpose: To compare the diagnostic accuracy of magnetic resonance imaging elastography (MRE) and anatomic MRI features in the diagnosis of severe hepatic fibrosis and cirrhosis.

Materials and methods: Three readers independently assessed presence of morphological changes associated with hepatic fibrosis in 72 patients with liver biopsy including: caudate to right lobe ratios, nodularity, portal venous hypertension (PVH) stigmata, posterior hepatic notch, expanded gallbladder fossa, and right hepatic vein caliber. Three readers measured shear stiffness values using quantitative shear stiffness maps (elastograms). Sensitivity, specificity, and diagnostic accuracy of stiffness values and each morphological feature were calculated. Interreader agreement was summarized using weighted kappa statistics. Intraclass correlation coefficient was used to assess interreader reproducibility of stiffness measurements. Binary logistic regression was used to assess interreader variability for dichotomized stiffness values and each morphological feature.

Results: Using 5.9 kPa as a cutoff for differentiating F3-F4 from F0-2 stages, overall sensitivity, specificity, and diagnostic accuracy for MRE were 85.4%, 88.4%, and 87%, respectively. Overall interreader agreement for stiffness values was substantial, with an insignificant difference (P = 0.74) in the frequency of differentiating F3-4 from F0-2 fibrosis. Only hepatic nodularity and PVH stigmata showed moderately high overall accuracy of 69.4% and 72.2%. Interreader agreement was substantial only for PVH stigmata, moderate for C/R m, deep notch, and expanded gallbladder fossa. Only posterior hepatic notch (P = 0.82) showed no significant difference in reader rating.

Conclusion: MRE is a noninvasive, accurate, and reproducible technique compared with conventional features of detecting severe hepatic fibrosis.

Figure 1

Axial contrast enhanced T1 fat suppressed gradient echo recalled image in a 55-year-old man with known cirrhosis, shows a sharp indentation (posterior hepatic notch sign) in the posterior margin of the right hepatic lobe (arrow).

Figure 2

Graph showing no significant difference in reader pattern of assigning stiffness values (p=0.74). Overall inter-reader agreement was substantial with k: 0.79 (CI 95% 0.72–0.86).

Figure 3

Figure 3 (a–g) Graphs show reader variability in rating distribution for each morphological feature. Positive and negative bars indicate percentage of the correct and incorrect assignment respectively, of the presence of a morphological feature compared with histology. Figure 3 (a) Rating distribution of caudate to right lobe ratio (using right portal vein) showing significant inter-reader difference, p<0.001. Figure 3 (b) Rating distribution of caudate to right lobe ratio (using main portal vein) showing significant inter-reader difference, p=0.033. Figure 3 (c) Rating distribution of liver nodularity showing significant inter-reader difference, p<0.001. Figure 3 (d) Rating distribution of posterior hepatic notch showing no significant inter-reader difference, p=0.822. Figure 3 (e) Rating distribution of expanded gallbladder fossa showing significant inter-reader difference, p=0.004. Figure 3 (f) Rating distribution of portal venous hypertension stigmata shows borderline significant inter-reader difference, p=0.056. Figure 3 (g) Rating distribution of right hepatic vein caliber showing significant inter-reader difference, p<0.001.

Figure 3

Figure 3 (a–g) Graphs show reader variability in rating distribution for each morphological feature. Positive and negative bars indicate percentage of the correct and incorrect assignment respectively, of the presence of a morphological feature compared with histology. Figure 3 (a) Rating distribution of caudate to right lobe ratio (using right portal vein) showing significant inter-reader difference, p<0.001. Figure 3 (b) Rating distribution of caudate to right lobe ratio (using main portal vein) showing significant inter-reader difference, p=0.033. Figure 3 (c) Rating distribution of liver nodularity showing significant inter-reader difference, p<0.001. Figure 3 (d) Rating distribution of posterior hepatic notch showing no significant inter-reader difference, p=0.822. Figure 3 (e) Rating distribution of expanded gallbladder fossa showing significant inter-reader difference, p=0.004. Figure 3 (f) Rating distribution of portal venous hypertension stigmata shows borderline significant inter-reader difference, p=0.056. Figure 3 (g) Rating distribution of right hepatic vein caliber showing significant inter-reader difference, p<0.001.

Figure 3

Figure 3 (a–g) Graphs show reader variability in rating distribution for each morphological feature. Positive and negative bars indicate percentage of the correct and incorrect assignment respectively, of the presence of a morphological feature compared with histology. Figure 3 (a) Rating distribution of caudate to right lobe ratio (using right portal vein) showing significant inter-reader difference, p<0.001. Figure 3 (b) Rating distribution of caudate to right lobe ratio (using main portal vein) showing significant inter-reader difference, p=0.033. Figure 3 (c) Rating distribution of liver nodularity showing significant inter-reader difference, p<0.001. Figure 3 (d) Rating distribution of posterior hepatic notch showing no significant inter-reader difference, p=0.822. Figure 3 (e) Rating distribution of expanded gallbladder fossa showing significant inter-reader difference, p=0.004. Figure 3 (f) Rating distribution of portal venous hypertension stigmata shows borderline significant inter-reader difference, p=0.056. Figure 3 (g) Rating distribution of right hepatic vein caliber showing significant inter-reader difference, p<0.001.

Figure 3

Figure 3 (a–g) Graphs show reader variability in rating distribution for each morphological feature. Positive and negative bars indicate percentage of the correct and incorrect assignment respectively, of the presence of a morphological feature compared with histology. Figure 3 (a) Rating distribution of caudate to right lobe ratio (using right portal vein) showing significant inter-reader difference, p<0.001. Figure 3 (b) Rating distribution of caudate to right lobe ratio (using main portal vein) showing significant inter-reader difference, p=0.033. Figure 3 (c) Rating distribution of liver nodularity showing significant inter-reader difference, p<0.001. Figure 3 (d) Rating distribution of posterior hepatic notch showing no significant inter-reader difference, p=0.822. Figure 3 (e) Rating distribution of expanded gallbladder fossa showing significant inter-reader difference, p=0.004. Figure 3 (f) Rating distribution of portal venous hypertension stigmata shows borderline significant inter-reader difference, p=0.056. Figure 3 (g) Rating distribution of right hepatic vein caliber showing significant inter-reader difference, p<0.001.

Figure 3

Figure 3 (a–g) Graphs show reader variability in rating distribution for each morphological feature. Positive and negative bars indicate percentage of the correct and incorrect assignment respectively, of the presence of a morphological feature compared with histology. Figure 3 (a) Rating distribution of caudate to right lobe ratio (using right portal vein) showing significant inter-reader difference, p<0.001. Figure 3 (b) Rating distribution of caudate to right lobe ratio (using main portal vein) showing significant inter-reader difference, p=0.033. Figure 3 (c) Rating distribution of liver nodularity showing significant inter-reader difference, p<0.001. Figure 3 (d) Rating distribution of posterior hepatic notch showing no significant inter-reader difference, p=0.822. Figure 3 (e) Rating distribution of expanded gallbladder fossa showing significant inter-reader difference, p=0.004. Figure 3 (f) Rating distribution of portal venous hypertension stigmata shows borderline significant inter-reader difference, p=0.056. Figure 3 (g) Rating distribution of right hepatic vein caliber showing significant inter-reader difference, p<0.001.

Figure 3

Figure 3 (a–g) Graphs show reader variability in rating distribution for each morphological feature. Positive and negative bars indicate percentage of the correct and incorrect assignment respectively, of the presence of a morphological feature compared with histology. Figure 3 (a) Rating distribution of caudate to right lobe ratio (using right portal vein) showing significant inter-reader difference, p<0.001. Figure 3 (b) Rating distribution of caudate to right lobe ratio (using main portal vein) showing significant inter-reader difference, p=0.033. Figure 3 (c) Rating distribution of liver nodularity showing significant inter-reader difference, p<0.001. Figure 3 (d) Rating distribution of posterior hepatic notch showing no significant inter-reader difference, p=0.822. Figure 3 (e) Rating distribution of expanded gallbladder fossa showing significant inter-reader difference, p=0.004. Figure 3 (f) Rating distribution of portal venous hypertension stigmata shows borderline significant inter-reader difference, p=0.056. Figure 3 (g) Rating distribution of right hepatic vein caliber showing significant inter-reader difference, p<0.001.

Figure 3

Figure 3 (a–g) Graphs show reader variability in rating distribution for each morphological feature. Positive and negative bars indicate percentage of the correct and incorrect assignment respectively, of the presence of a morphological feature compared with histology. Figure 3 (a) Rating distribution of caudate to right lobe ratio (using right portal vein) showing significant inter-reader difference, p<0.001. Figure 3 (b) Rating distribution of caudate to right lobe ratio (using main portal vein) showing significant inter-reader difference, p=0.033. Figure 3 (c) Rating distribution of liver nodularity showing significant inter-reader difference, p<0.001. Figure 3 (d) Rating distribution of posterior hepatic notch showing no significant inter-reader difference, p=0.822. Figure 3 (e) Rating distribution of expanded gallbladder fossa showing significant inter-reader difference, p=0.004. Figure 3 (f) Rating distribution of portal venous hypertension stigmata shows borderline significant inter-reader difference, p=0.056. Figure 3 (g) Rating distribution of right hepatic vein caliber showing significant inter-reader difference, p<0.001.

Figure 4

Figure 4 (a) Axial contrast-enhanced fat-suppressed T1 gradient echo in a 48-year-old female with known history of non-alcoholic steatohepatitis (NASH) showing normal hepatic morphology. Figure 4 (b) Elastogram shows significantly elevated pressures with mean 6.4 kPa. Biopsy showed stage 3 fibrosis.

Figure 4

Figure 4 (a) Axial contrast-enhanced fat-suppressed T1 gradient echo in a 48-year-old female with known history of non-alcoholic steatohepatitis (NASH) showing normal hepatic morphology. Figure 4 (b) Elastogram shows significantly elevated pressures with mean 6.4 kPa. Biopsy showed stage 3 fibrosis.

Figure 5

Figure 5 (a) Axial contrast-enhanced fat-suppressed T1 gradient echo image in a 29-year-old male with chronic hepatitis C, shows normal hepatic morphology without definitive findings of cirrhosis. Figure 5 (b) Elastogram shows elevated pressures with mean 7.6 kPa from severe fibrosis.

Figure 5

Figure 5 (a) Axial contrast-enhanced fat-suppressed T1 gradient echo image in a 29-year-old male with chronic hepatitis C, shows normal hepatic morphology without definitive findings of cirrhosis. Figure 5 (b) Elastogram shows elevated pressures with mean 7.6 kPa from severe fibrosis.