Invasive and Non-invasive Diagnosis of Portal Hypertension in Cirrhosis

TMM: A comprehensive CAD system for hepatic fibrosis 5-grade METAVIR staging based on liver MRI

BACKGROUND

Precise staging of hepatic fibrosis with MRI is necessary as it can assist precision medicine. Computer aided diagnosis (CAD) system with distinguishing radiomics features and radiologists domain knowledge is expected to obtain 5-grade meta-analysis of histological data in viral hepatitis (METAVIR) staging.

PURPOSE

This study aims to obtain the precise staging of hepatic fibrosis based on MRI as it predicts the risk of future liver-related morbidity and the need for treatment, monitoring and surveillance. Based on METAVIR score, fibrosis can be divided into five stages. Most previous researches focus on binary classification, such as cirrhosis versus non-cirrhosis, early versus advanced fibrosis, and substantial fibrosis or not. In this paper, a comprehensive CAD system TMM is proposed to precisely class hepatic fibrosis into five stages for precision medicine instead of the common binary classification.

METHODS

We propose a novel hepatic fibrosis staging CAD system TMM which includes three modules, Two-level Image Statistical Radiomics Feature (TISRF), Monotonic Error Correcting Output Codes (MECOC) and Monotone Multiclassification with Deep Forest (MMDF). TISRF extracts radiomics features for distinguishing different hepatic fibrosis stages. MECOC is proposed to encode monotonic multiclass by making full use of the progressive severity of hepatic fibrosis and increase the fault tolerance and error correction ability. MMDF combines multiple Deep Forest network to ensure the final five-class classification, which can achieve more precise classification than the common binary classification. The performance of the proposed hepatic fibrosis CAD system is tested on the hepatic data collected from our rabbits models of fibrosis.

RESULTS

A total of 140 regions of interest (ROI) are selected from MRI T1W of liver fibrosis models in 35 rabbits with F0(n = 16), F1(n = 28), F2(n = 29), F3(n = 44) and F4(n = 23). The performance is evaluated by five-fold cross-validation. TMM can achieve the highest total accuracy of 72.14% for five fibrosis stages compared with other popular classifications. To make a comprehensive comparison, a binary classification experiment have been carried out.

CONCLUSIONS

T1WI can obtain precise staging of hepatic fibrosis with the help of comprehensive CAD including radiomics features extraction inspired by radiologists, monotonic multiclass according to the severity of hepatic fibrosis, and deep learning classification.

The Presence of Ascites Affects the Predictive Value of HVPG on Early Rebleeding in Patients with Cirrhosis

Background and Aims

Gastroesophageal variceal bleeding is a serious complication of portal hypertension in cirrhotic patients and could be predicted by hepatic venous pressure gradient (HVPG). However, whether the presence of ascites affects the prognostic value of HVPG for patients with acute variceal bleeding is still unknown. This retrospective study is aimed at investigating the influence of ascites on predictive performance of HVPG for early rebleeding in cirrhotic patients with acute variceal bleeding.

Methods

In this retrospective study, a total of 148 patients with cirrhosis hospitalized for acute variceal bleeding who underwent HVPG measurement and endoscopic variceal ligation (EVL) for the prevention of rebleeding were included. The receiver operating characteristic curve (ROC) and logistical regression method were employed to analyze the predictive performance of HVPG for early rebleeding. The locally weighted scatterplot smoothing approach was adopted to assess the monotonicity between bleeding risk and HVPG.

Results

A significantly higher HVPG level was observed in patients with early rebleeding compared to patients without rebleeding in the nonascites cohort. When using HVPG to predict early rebleeding, there was a lower area under curve in the ascites cohort compared to the nonascites cohort. HVPG was recognized as a risk factor for early rebleeding by a logistic regression model only in the nonascites cohort. An overall monotonicity in the trend of change in HVPG and risk for early rebleeding was observed in the nonascites cohort solely.

Conclusion

The predictive value of HVPG for early rebleeding in patients with cirrhosis that developed acute variceal bleeding is hindered by the presence of ascites.