Non-invasive predictive model for hepatic venous pressure gradient based on a 3-dimensional computed tomography volume rendering technology

The impact of hepatic and splenic volumetric assessment in imaging for chronic liver disease: a narrative review

Chronic liver disease is responsible for significant morbidity and mortality worldwide. Abdominal computed tomography (CT) and magnetic resonance imaging (MRI) can fully visualise the liver and adjacent structures in the upper abdomen providing a reproducible assessment of the liver and biliary system and can detect features of portal hypertension. Subjective interpretation of CT and MRI in the assessment of liver parenchyma for early and advanced stages of fibrosis (pre-cirrhosis), as well as severity of portal hypertension, is limited. Quantitative and reproducible measurements of hepatic and splenic volumes have been shown to correlate with fibrosis staging, clinical outcomes, and mortality. In this review, we will explore the role of volumetric measurements in relation to diagnosis, assessment of severity and prediction of outcomes in chronic liver disease patients. We conclude that volumetric analysis of the liver and spleen can provide important information in such patients, has the potential to stratify patients' stage of hepatic fibrosis and disease severity, and can provide critical prognostic information. CRITICAL RELEVANCE STATEMENT: This review highlights the role of volumetric measurements of the liver and spleen using CT and MRI in relation to diagnosis, assessment of severity, and prediction of outcomes in chronic liver disease patients. KEY POINTS: Volumetry of the liver and spleen using CT and MRI correlates with hepatic fibrosis stages and cirrhosis. Volumetric measurements correlate with chronic liver disease outcomes. Fully automated methods for volumetry are required for implementation into routine clinical practice.

Implementing Better Standard Instruments for Detecting Cirrhosis in Hepatitis C Patients

An increasing number of hepatitis C diagnoses in the younger population could partly be due to the rising opioid epidemic and intravenous drug use. Using hepatic venous portal gradient (HVPG) and liver stiffness tests, this study investigates better early diagnostic markers in identifying cirrhosis-related complications compared to percutaneous liver biopsy in hepatitis C patients. Scholarly journal articles were surveyed using PubMed and MeSH terms. Articles published more than 15 years ago were excluded. Various databases from the New England Journal of Medicine and the Centers for Disease Control and Prevention were also referenced to support the hypothesis. There is substantial affirmation from cohort and clinical studies that transient elastography and HVPG can indicate advancing chronic inflammatory and fibrotic stages of cirrhosis in comparison to liver biopsy. Additionally, they are helpful in predicting overall mortality from complications such as esophageal varices. The use of liver stiffness measurements and HVPG appears to be equivalent and/or superior to liver biopsy in assessing advancing cirrhosis. As hepatitis C cases continue to rise, it is crucial to search for alternative methods to better suit the needs of the patients and to improve their overall prognosis and potential treatments. Liver biopsy as the gold standard for cirrhosis assessment is questionable when less invasive instrumental tools are available in practice that have been shown to predict progressing fibrosis.

Towards optimal deep fusion of imaging and clinical data via a model-based description of fusion quality

BACKGROUND

Due to intrinsic differences in data formatting, data structure, and underlying semantic information, the integration of imaging data with clinical data can be non-trivial. Optimal integration requires robust data fusion, that is, the process of integrating multiple data sources to produce more useful information than captured by individual data sources. Here, we introduce the concept of fusion quality for deep learning problems involving imaging and clinical data. We first provide a general theoretical framework and numerical validation of our technique. To demonstrate real-world applicability, we then apply our technique to optimize the fusion of CT imaging and hepatic blood markers to estimate portal venous hypertension, which is linked to prognosis in patients with cirrhosis of the liver.

PURPOSE

To develop a measurement method of optimal data fusion quality deep learning problems utilizing both imaging data and clinical data.

METHODS

Our approach is based on modeling the fully connected layer (FCL) of a convolutional neural network (CNN) as a potential function, whose distribution takes the form of the classical Gibbs measure. The features of the FCL are then modeled as random variables governed by state functions, which are interpreted as the different data sources to be fused. The probability density of each source, relative to the probability density of the FCL, represents a quantitative measure of source-bias. To minimize this source-bias and optimize CNN performance, we implement a vector-growing encoding scheme called positional encoding, where low-dimensional clinical data are transcribed into a rich feature space that complements high-dimensional imaging features. We first provide a numerical validation of our approach based on simulated Gaussian processes. We then applied our approach to patient data, where we optimized the fusion of CT images with blood markers to predict portal venous hypertension in patients with cirrhosis of the liver. This patient study was based on a modified ResNet-152 model that incorporates both images and blood markers as input. These two data sources were processed in parallel, fused into a single FCL, and optimized based on our fusion quality framework.

RESULTS

Numerical validation of our approach confirmed that the probability density function of a fused feature space converges to a source-specific probability density function when source data are improperly fused. Our numerical results demonstrate that this phenomenon can be quantified as a measure of fusion quality. On patient data, the fused model consisting of both imaging data and positionally encoded blood markers at the theoretically optimal fusion quality metric achieved an AUC of 0.74 and an accuracy of 0.71. This model was statistically better than the imaging-only model (AUC = 0.60; accuracy = 0.62), the blood marker-only model (AUC = 0.58; accuracy = 0.60), and a variety of purposely sub-optimized fusion models (AUC = 0.61-0.70; accuracy = 0.58-0.69).

CONCLUSIONS

We introduced the concept of data fusion quality for multi-source deep learning problems involving both imaging and clinical data. We provided a theoretical framework, numerical validation, and real-world application in abdominal radiology. Our data suggests that CT imaging and hepatic blood markers provide complementary diagnostic information when appropriately fused.

Network Meta-Analysis: Noninvasive Imaging Modalities for Identifying Clinically Significant Portal Hypertension

BACKGROUND

Although measurement of the hepatic venous pressure gradient (HVPG) is the current reference standard for obtaining portal venous pressures, several noninvasive imaging-based modalities have been proposed as alternatives.

AIMS

We performed a systematic review and meta-analysis to compare the diagnostic accuracy of noninvasive imaging approaches for identifying clinically significant portal hypertension (CSPH).

METHODS

Two independent reviewers conducted a literature search of PubMed, SCOPUS, and the Cochrane Library from inception until January 5, 2021. The following imaging modalities were compared to HVPG: computed tomography (CT), magnetic resonance imaging (MRI), magnetic resonance elastography, ultrasound, transient elastography (TE), shear wave elastography (SWE), acoustic radiation force impulse (ARFI) imaging, contrast-enhanced ultrasound (CEUS), and subharmonic-aided pressure estimation (SHAPE). Sensitivity, specificity, diagnostic odds ratio (DOR), and area under the curve (AUC) for summary receiver operating characteristic were calculated using both frequentist random effects and Bayesian network meta-analytic approaches.

RESULTS

We analyzed 45 studies of 5678 patients. A broad overlapping confidence interval (CI) of DOR was observed among different imaging modalities: ARFI (30.5; 95% CI 12.7-73.3), CEUS and SHAPE (21.1; 95% CI 6.4-69.8), TE of liver stiffness (21.1; 95% CI 13.3-33.5), CT and MRI (13.7; 95% CI 7.40-25.4), SWE of liver stiffness (10.5; 95% CI 5.2-21.1), and ultrasound (9.5; 95% CI 4.9-18.4). The AUC of all imaging methods exceeded 0.8, indicating very good performance. At a cutoff of 80% specificity, TE, CEUS, and SHAPE exceeded 80% sensitivity.

CONCLUSION

Overall, noninvasive imaging modalities perform well for identifying CSPH. Clinicians should consider these noninvasive and cost-efficient tests when diagnosing CSPH.

Artificial intelligence in the diagnosis of cirrhosis and portal hypertension

Clinically significant portal hypertension is associated with an increased risk of developing gastroesophageal varices and hepatic decompensation. Hepatic venous pressure gradient measurement and esophagogastroduodenoscopy are the gold-standard methods for assessing clinically significant portal hypertension and gastroesophageal varices, respectively. However, invasiveness, cost, and feasibility limit their widespread use, especially if repeated and serial evaluations are required to assess the efficacy of pharmacotherapy. Artificial intelligence describes a range of techniques that allow machines to perform tasks typically thought to require human reasoning and problem-solving skills. Artificial intelligence has made great strides in the field of medicine, and is also involved in portal hypertension diagnosis. Artificial intelligence tools will potentially transform our practice by leveraging massive amounts of data to personalize care to the right patient, in the right amount, at the right time. This review focuses on the recent advances in artificial intelligence for the noninvasive diagnosis of portal hypertension and gastroesophageal varices and monitoring of risk assessment of its complications in clinical practice.

Diagnostic accuracy of non-invasive methods detecting clinically significant portal hypertension in liver cirrhosis: a systematic review and meta-analysis

INTRODUCTION

We attempted to investigate non-invasive techniques and their diagnostic performances for evaluating clinically significant portal hypertension.

EVIDENCE ACQUISITION

The systematic search was performed on PubMed, Embase, Scopus, and Web of Science TM core index databases before 13 December 2018 restricted to English language and human studies.

EVIDENCE SYNTHESIS

Thirty-two studies were included, with total populations of 3,987. The overall pooled analysis was performed by bivariate random effect model, which revealed significantly higher sensitivity and specificity of 77.1% (95% confidence interval, 76.8-78.5%) and 80.1% (95% confidence interval, 78.2-81.9%), respectively; positive likelihood ratio (3.67), negative likelihood ratio (0.26); and diagnostic odd ratio (16.24). Additionally, the area under curve exhibited significant diagnostic accuracy of 0.871. However, notable heterogeneity existed in between studies (I2=87.1%), therefore, further subgroup analysis was performed. It demonstrated ultrasonography, elastography, biomarker, and computed tomography scan had a significant overall summary sensitivity (specificity) of 89.6% (78.9%), 81.7% (83.2%), 72.2% (76.8%), and 77.2% (81.2%), respectively. Moreover, the areas under curve values were significantly higher in elastography (0.906), followed by computed tomography scan (0.847), biomarker (0.825), and ultrasonography (0.803).

CONCLUSIONS

In future, non-invasive techniques could be the future choice of investigations for screening and diagnosis of clinically significant portal hypertension in cirrhosis. However, standardization of diagnostic indices and their cut-off values in each non-invasive method needs to be addressed.