Imaging modalities for the diagnosis of hepatic fibrosis and cirrhosis

Artificial Intelligence-Based Feature Analysis of Ultrasound Images of Liver Fibrosis

Liver fibrosis is a common liver disease that seriously endangers human health. Liver biopsy is the gold standard for diagnosing liver fibrosis, but its clinical use is limited due to its invasive nature. Ultrasound image examination is a widely used liver fibrosis examination method. Clinicians can diagnose the severity of liver fibrosis according to their own experience by observing the roughness of the texture of the ultrasound image, and this method is highly subjective. Under the premise that artificial intelligence technology is widely used in medical image analysis, this paper uses convolutional neural network analysis to extract the characteristics of ultrasound images of liver fibrosis and then classify the degree of liver fibrosis. Using neural network for image classification can avoid the subjectivity of manual classification and improve the accuracy of judging the degree of liver fibrosis, so as to complete the prevention and treatment of liver fibrosis. Therefore, the following work is done in this paper: (1) the research background, research significance, research status at home and abroad, and the impact of the development of medical imaging on the diagnosis of liver fibrosis are introduced; (2) the related technologies of deep learning and deep convolutional network are introduced, and the indicators of liver fibrosis degree assessment are constructed by using ultrasonic image extraction features; (3) using the collected liver fibrosis dataset to conduct model evaluation experiments, four classic CNN models are selected to compare and analyze the recognition rate. The experiments show that the GoogLeNet model has the best classification and recognition effect.

Liver fibrosis staging by computed tomography: Prospective randomized multicentric evaluation of image analyses

AIM

Liver fibrosis staging is essential. We prospectively evaluated the liver fibrosis staging performance of computed tomography (CT).

METHODS

70 hepato-gastroenterology clinicians were randomized into three stratified groups with different image analyses of radiological semiology, i.e., on raw images (group 1) and on expert-annotated (group 2) and computerized-morphometry-enriched (group 3) images. Radiological fibrosis staging based on seven simple descriptors into four stages equivalent to Metavir stages (F0/1, F2, F3, F4=cirrhosis) was determined at baseline and after image analyses in 10 patients with chronic liver diseases (two per F) concordant for four independent fibrosis stagings including Metavir. 23,800 CT images were analysed, providing 1400 fibrosis stagings.

RESULTS

Fibrosis staging: overall (3 groups) accuracy (correct classification rate) was, baseline: 43%, post-analysis: 60% (p < 0.001) without significant progression in group 1 (6%, p = 0.207) contrary to groups 2 (34%, p < 0.001) and 3 (13%, p = 0.007). Cirrhosis diagnosis: overall accuracy was, baseline: 84%, post-analysis: 89% (p < 0.001) without significant progression in group 1 (0%, p = 1) contrary to groups 2 (8%, p = 0.009) and 3 (7%, p = 0.015). Baseline AUROCs were good (≥0.83) for marked fibrosis (F≥3 or cirrhosis) in all groups. Post-analysis AUROCs became excellent (≥0.89) in group 2 for all diagnostic targets (≥0.98 for F≥3 and cirrhosis) and in group 3 for cirrhosis. In post-analysis group 2, discrimination between all F was excellent (especially, F1 from F0) with an Obuchowski index at 0.87. Negative and positive predictive values for marked fibrosis were 98% and 95%, respectively.

CONCLUSION

Simple CT descriptors accurately discriminate all Metavir liver fibrosis stages.

Comparison of liver stiffness measurement with MRE and liver and spleen volumetry for prediction of disease severity and hepatic decompensation in patients with primary sclerosing cholangitis

PURPOSE

To compare liver stiffness measurement (LSM) with magnetic resonance elastography (MRE) and liver and spleen volumetry for prediction of disease severity and hepatic decompensation in primary sclerosing cholangitis (PSC).

METHODS

This retrospective study was approved by the institutional review board. Magnetic resonance imaging (MRI) and MRE studies were reviewed, and mean LSM of entire liver, right lobe and left lobe, total liver, right lobe, left lobe, caudate lobe, and spleen volumes were calculated. Qualitative evaluation of lobar atrophy or hypertrophy and presence of macronodular regeneration (MNR) was recorded. Statistical analysis was performed to evaluate correlations between LSM, volumetry measurements, and Mayo risk score. Univariate and multivariate analyses were performed to predict hepatic decompensation.

RESULTS

A total of 266 patients with PSC were included in the study. Lobar stiffness measures were higher in the presence of relative lobe atrophy. Mean LSM was higher in the presence of MNR. Significant correlations were observed between mean LSM and volumetry measurements with a fair correlation between LSM and spleen volume (r_s = 0.526, p < 0.0001). Among the measurements, the best correlation was observed between mean LSM and Mayo risk score (r_s = 0.646, p < 0.0001). In the multivariate analyses, mean LSM and Mayo risk score were significantly associated with liver decompensation (hazard ratio, 1.18; 95%CI 1.02-1.36 and hazard ratio, 1.65; 95%CI 1.08-2.53, respectively).

CONCLUSION

LSM with MRE performs significantly better than liver and spleen volumes for prediction of both disease severity and hepatic decompensation.

Liver fibrosis: stretched exponential model outperforms mono-exponential and bi-exponential models of diffusion-weighted MRI

OBJECTIVES

To compare the ability of diffusion-weighted imaging (DWI) parameters acquired from three different models for the diagnosis of hepatic fibrosis (HF).

METHODS

Ninety-five patients underwent DWI using nine b values at 3 T magnetic resonance. The hepatic apparent diffusion coefficient (ADC) from a mono-exponential model, the true diffusion coefficient (D _t ), pseudo-diffusion coefficient (D _p ) and perfusion fraction (f) from a biexponential model, and the distributed diffusion coefficient (DDC) and intravoxel heterogeneity index (α) from a stretched exponential model were compared with the pathological HF stage. For the stretched exponential model, parameters were also obtained using a dataset of six b values (DDC^#, α^#). The diagnostic performances of the parameters for HF staging were evaluated with Obuchowski measures and receiver operating characteristics (ROC) analysis. The measurement variability of DWI parameters was evaluated using the coefficient of variation (CoV).

RESULTS

Diagnostic accuracy for HF staging was highest for DDC^# (Obuchowski measures, 0.770 ± 0.03), and it was significantly higher than that of ADC (0.597 ± 0.05, p < 0.001), D _t (0.575 ± 0.05, p < 0.001) and f (0.669 ± 0.04, p = 0.035). The parameters from stretched exponential DWI and D _p showed higher areas under the ROC curve (AUCs) for determining significant fibrosis (≥F2) and cirrhosis (F = 4) than other parameters. However, D _p showed significantly higher measurement variability (CoV, 74.6%) than DDC^# (16.1%, p < 0.001) and α^# (15.1%, p < 0.001).

CONCLUSIONS

Stretched exponential DWI is a promising method for HF staging with good diagnostic performance and fewer b-value acquisitions, allowing shorter acquisition time.

KEY POINTS

• Stretched exponential DWI provides a precise and accurate model for HF staging. • Stretched exponential DWI parameters are more reliable than D _p from bi-exponential DWI model • Acquisition of six b values is sufficient to obtain accurate DDC and α.

Liver elastography: what it is, how it is done, and how it is interpreted

Liver elastography is a noninvasive method for diagnosing fibrosis that has been developed over the last decade in response to the limitations of liver biopsies, blood markers, and traditional imaging modalities. There are different methods of measuring tissue stiffness through ultrasound; thus far, shear wave elastography has proven superior for diagnosing clinically significant liver fibrosis, where early detection modifies the approach to treatment and improves prognosis. This article aims to provide a brief review of the different methods for performing elastography with ultrasound, focusing especially on shear wave elastography and on technical aspects for carrying out the procedure and key points for interpreting the findings.

Multiparametric or practical quantitative liver MRI: towards millisecond, fat fraction, kilopascal and function era

New advances in liver magnetic resonance imaging (MRI) may enable diagnosis of unseen pathologies by conventional techniques. Normal T1 (550-620 ms for 1.5 T and 700-850 ms for 3 T), T2, T2* (>20 ms), T1rho (40-50 ms) mapping, proton density fat fraction (PDFF) (≤5%) and stiffness (2-3kPa) values can enable differentiation of a normal liver from chronic liver and diffuse diseases. Gd-EOB-DTPA can enable assessment of liver function by using postcontrast hepatobiliary phase or T1 reduction rate (normally above 60%). T1 mapping can be important for the assessment of fibrosis, amyloidosis and copper overload. T1rho mapping is promising for the assessment of liver collagen deposition. PDFF can allow objective treatment assessment in NAFLD and NASH patients. T2 and T2* are used for iron overload determination. MR fingerprinting may enable single slice acquisition and easy implementation of multiparametric MRI and follow-up of patients. Areas covered: T1, T2, T2*, PDFF and stiffness, diffusion weighted imaging, intravoxel incoherent motion imaging (ADC, D, D* and f values) and function analysis are reviewed. Expert commentary: Multiparametric MRI can enable biopsyless diagnosis and more objective staging of diffuse liver disease, cirrhosis and predisposing diseases. A comprehensive approach is needed to understand and overcome the effects of iron, fat, fibrosis, edema, inflammation and copper on MR relaxometry values in diffuse liver disease.

Value of MR elastography for the preoperative estimation of liver regeneration capacity in patients with hepatocellular carcinoma

PURPOSE

To demonstrate the negative relationship between liver stiffness (LS) values measured at preoperative magnetic resonance elastography (MRE) and the regeneration capacity of the remnant liver after major hepatectomy, in patients with hepatocellular carcinoma (HCC).

MATERIALS AND METHODS

Thirty-eight patients with HCC (mean age, 57.1) who had undergone liver computed tomography (CT) and 1.5T MRE prior to right hepatectomy were included in this retrospective study. CT volumetric analysis of total functional liver (calculated by subtracting tumor volume from total liver volume), future liver remnant (FLR), and postoperative liver remnant (LR) were performed using a semiautomatic analysis program. The regeneration index was expressed as [(V_LR -V_FLR )/V_FLR ] × 100, where V_LR is the volume of the liver remnant and V_FLR is the volume of the FLR. The relationship between degree of LS measured at MRE and the regeneration index was assessed using the Spearman correlation test.

RESULTS

Average LS value at MRE increased along with hepatic fibrosis (HF) stage (r = 0.604, P < 0.001). At MRE, a cutoff value greater than 2.46 kPa yielded 90.0% sensitivity and 100% specificity in identifying HF stage 2 or greater (area under the curve [AUC], 0.95). Mean V_FLR and V_LR were 477.1 ± 147.5 mL and 911.9 ± 188.8 mL, respectively. The regeneration index of the liver remnant was 102.1 ± 58.2%. LS values at MRE and calculated regeneration index after right hepatectomy showed moderate negative correlation (r = -0.361, P = 0.026).

CONCLUSION

LS values measured at MRE may serve as a postoperative predictor of liver regeneration in patients with liver cirrhosis and HCC.

LEVEL OF EVIDENCE

4 Technical Efficacy: Stage 2 J. MAGN. RESON. IMAGING 2017;45:1627-1636.

Comparison of the effect of region-of-interest methods using gadoxetic acid-enhanced MR imaging with diffusion-weighted imaging on staging hepatic fibrosis

OBJECTIVE

To evaluate the utility of T1 mapping on gadoxetic acid-enhanced MRI and DWI for staging liver fibrosis and assess the influence of ROI positioning on interobserver variability, T1 relaxation time and ADC value.

METHODS

This retrospective study was approved by the institutional review board and included 150 patients (mean age 58 years old; 91 men and 59 women). Liver fibrosis stages (S) were histopathologically determined. T1 relaxation time and ADC value of liver were measured by three distinct ROI protocols (the whole left lobe liver, the whole right lobe liver and the individual ROIs). T1 relaxation time measurements were compared with ADC values according to S scores. Interobserver variability for the T1 relaxation times and ADC values by the three distinct ROI protocols was analyzed by calculating the ICC.

RESULTS

T1 relaxation time measurements by the three distinct ROI protocols on severe fibrosis stage were significantly higher than the relative values on mild fibrosis stage. The mean ADC values on severe fibrosis stage showed no significantly different when measured by means of the whole right lobe liver (p = 0.057) and the individual ROIs (p = 0.10), compared with the relative values on mild fibrosis stage. AUCs of T1 relaxation time and ADC value by the means of the three distinct ROI protocols were 0.614, 0.676, 0.677 and 0.656, 0.585, 0.575 for identification of severe fibrosis stage. The interobserver reproducibility was excellent for measuring the right lobe liver T1 relaxation time and the individual ROIs T1 relaxation time (ICC 0.814, 0.883, respectively).

CONCLUSIONS

T1 relaxation time measurements by means of the three distinct ROI protocols on gadoxetic acid-enhanced MR imaging were a potential biomarker in staging of hepatic fibrosis, which were more accuracy than DWI-ADC measurements. The more reproducible results were obtained when measuring T1 relaxation time of the whole right lobe liver and the individual ROIs.

Contrast-enhanced ultrasonography for the evaluation of liver fibrosis after biliary obstruction

AIM: To investigate perfusion change in contrast-enhanced ultrasonography (CEUS) to evaluate liver fibrosis based on biliary obstruction using an animal model.

METHODS: New Zealand white rabbits (3-4 kg) underwent bile duct ligation to form a biliary obstruction model. We performed liver CEUS and laboratory tests on the day before the operation (day 0) and every 7 postoperative days until the rabbits were sacrificed. After CEUS, signal intensity of liver parenchyma with a time-intensity curve was analyzed. Perfusion parameters were automatically calculated from region-of-interests, including peak signal intensity, mean transit time, area under the curve and time to peak. Histological grades of liver fibrosis were assessed according to the Metavir score system immediately after sacrifice. Generalized estimating equations were used to analyze the association between liver fibrosis grades and perfusion parameters for statistical analysis. The perfusion parameters were measured on the last day and the difference between day 0 and the last day were evaluated.

RESULTS: From the nine rabbits, histological grades of liver fibrosis were grade 1 in one rabbit, grade 2 and 3 in three rabbits each, and grade 4 in two rabbits. Among the four CEUS parameters, only the peak signal intensity measured on the last day demonstrated a significant association with liver fibrosis grades (OR = 1.392, 95%CI: 1.114-1.741, P = 0.004). The difference in peak signal intensity between day 0 and the last day also demonstrated an association with liver fibrosis (OR = 1.191, 95%CI: 0.999-1.419, P = 0.051). The other parameters tested, including mean transit time, area under the curve, and time to peak, showed no significant correlation with liver fibrosis grades.

CONCLUSION: This animal study demonstrates that CEUS can be used to evaluate liver fibrosis from biliary obstruction using peak signal intensity as a parameter.