Noninvasive Diagnosis Of Portal Hypertension Research Articles

Deep Neural Network Regression to Assist Non-Invasive Diagnosis of Portal Hypertension.

Portal hypertension is a complex medical condition characterized by elevated blood pressure in the portal venous system. The conventional diagnosis of such disease often involves invasive procedures such as liver biopsy, endoscopy, or imaging techniques with contrast agents, which can be uncomfortable for patients and carry inherent risks. This study presents a deep neural network method in support of the non-invasive diagnosis of portal hypertension in patients with chronic liver diseases. The proposed method utilizes readily available clinical data, thus eliminating the need for invasive procedures. A dataset composed of standard laboratory parameters is used to train and validate the deep neural network regressor. The experimental results exhibit reasonable performance in distinguishing patients with portal hypertension from healthy individuals. Such performances may be improved by using larger datasets of high quality. These findings suggest that deep neural networks can serve as useful auxiliary diagnostic tools, aiding healthcare professionals in making timely and accurate decisions for patients suspected of having portal hypertension.

Quantitative computed tomography‐based approaches for noninvasive diagnosis of portal hypertension in patients with cirrhosis

AbstractNoninvasive diagnosis of portal hypertension in patients with cirrhosis can be achieved using different methods, including laboratory tests and imaging. The Baveno VII consensus suggested that liver stiffness measurements and platelet counts were sufficient for assessing the presence of clinically significant portal hypertension. However, computed tomography (CT) is frequently performed in patients with cirrhosis, and numerous studies have established the possibility of an opportunistic noninvasive diagnosis of portal hypertension using CT. These studies have utilized radiomics, volumetric changes in the liver and spleen, quantitative assessment of liver surface nodularity, and more advanced techniques based on computational fluid dynamics. This review summarizes the main original studies related to the quantitative CT‐based noninvasive diagnosis of portal hypertension.

Research progress of cirrhotic portal hypertension in diagnostic imaging methods

Hepatic venous pressure gradient measurement via jugular vein catheterization is still currently the gold standard for evaluating portal hypertension. However, how to accurately and reproducibly assess whether there is portal hypertension has always been a concern in patients with liver cirrhosis. In recent years, imaging methods have made significant progress in the non-invasive diagnosis of portal hypertension. This paper reviews the current different diagnostic value of imaging methods and related research progress in an attempt to evaluate patients with cirrhotic portal hypertension.

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.

Noninvasive diagnosis of portal hypertension using gadoxetate DCE-MRI of the liver and spleen.

To assess the performance of gadoxetate dynamic contrast-enhanced (DCE) MRI of the liver and spleen for noninvasive diagnosis of portal hypertension (PH). Thirty-five patients (M/F 22/13, mean age 55 years) with chronic liver disease who underwent hepatic venous pressure gradient (HVPG) measurements were prospectively enrolled in this IRB-approved study. All patients underwent multiparametric MRI including gadoxetate DCE-MRI acquisition. Model-based and model-free DCE-MRI analyses were performed. The correlation between DCE-MRI parameters and HVPG was assessed. ROC analysis was employed to determine the diagnostic performance of DCE-MRI parameters alone and in combination for prediction of PH and clinically significant (CS)PH (HVPG > 5 and ≥ 10 mmHg, respectively). Mean HVPG was 7.0 ± 5.0 mmHg (range 0-18 mmHg). Twenty-one (60%) patients had PH, of whom 9 had CSPH. Modeled liver uptake fraction fi and uptake rate ki and model-free parameters liver upslope and uptake were all significantly negatively correlated with HVPG (r range - 0.490 to - 0.398, p value range 0.003-0.018), while spleen interstitial fraction ve was significantly positively correlated with HVPG (r = 0.336, p = 0.048). For PH diagnosis, liver ki showed the best diagnostic performance with an AUC, sensitivity, and specificity of 0.74 (confidence interval (CI) 0.57-0.91), 71.4%, and 78.6%. The combination of liver ki and spleen ve was selected as the best classifier for diagnosis of CSPH with an AUC, sensitivity, and specificity of 0.87 (CI 0.75-0.99), 100%, and 73.1%. Our results demonstrate the potential utility of hepatocyte uptake parameters and spleen interstitial fraction obtained with gadoxetate DCE-MRI for the diagnosis of PH and CSPH. • Liver uptake and spleen interstitial fraction estimates from gadoxetate DCE-MRI are significantly correlated with portal pressure measurements. • Liver uptake rate shows good diagnostic performance for the diagnosis of portal hypertension. • The combination of liver uptake rate with spleen interstitial fraction exhibits excellent diagnostic performance for the diagnosis of clinically significant portal hypertension.

Noninvasive Diagnosis of Portal Hypertension in Patients With Compensated Advanced Chronic Liver Disease.

We aimed to explore the prevalence of portal hypertension in the most common etiologies of patients with compensated advanced chronic liver disease (cACLD) and develop classification rules, based on liver stiffness measurement (LSM), that could be readily used to diagnose or exclude clinically significant portal hypertension (CSPH) in clinical practice. This is an international cohort study including patients with paired LSM/hepatic venous pressure gradient (HVPG), LSM ≥10 kPa, and no previous decompensation. Portal hypertension was defined by an HVPG >5 mm Hg. A positive predictive value ≥90% was considered to validate LSM cutoffs for CSPH (HVPG ≥10 mm Hg), whereas a negative predictive value ≥90% ruled out CSPH. A total of 836 patients with hepatitis C (n = 358), nonalcoholic steatohepatitis (NASH, n = 248), alcohol use (n = 203), and hepatitis B (n = 27) were evaluated. Portal hypertension prevalence was >90% in all cACLD etiologies, except for patients with NASH (60.9%), being even lower in obese patients with NASH (53.3%); these lower prevalences of portal hypertension in patients with NASH were maintained across different strata of LSM values. LSM ≥25 kPa was the best cutoff to rule in CSPH in alcoholic liver disease, chronic hepatitis B, chronic hepatitis C, and nonobese patients with NASH, whereas in obese NASH patients, the positive predictive value was only 62.8%. A new model for patients with NASH (ANTICIPATE-NASH model) to predict CSPH considering body mass index, LSM, and platelet count was developed, and a nomogram was constructed. LSM ≤15 kPa plus platelets ≥150 × 10/L ruled out CSPH in most etiologies. Patients with cACLD of NASH etiology, especially obese patients with NASH, present lower prevalences of portal hypertension compared with other cACLD etiologies. LSM ≥25 kPa is sufficient to rule in CSPH in most etiologies, including nonobese patients with NASH, but not in obese patients with NASH.

Virtual Hepatic Venous Pressure Gradient with CT Angiography (CHESS 1601): A Prospective Multicenter Study for the Noninvasive Diagnosis of Portal Hypertension.

Purpose To develop and validate a computational model for estimating hepatic venous pressure gradient (HVPG) based on CT angiographic images, termed virtual HVPG, to enable the noninvasive diagnosis of portal hypertension in patients with cirrhosis. Materials and Methods In this prospective multicenter diagnostic trial (ClinicalTrials.gov identifier: NCT02842697), 102 consecutive eligible participants (mean age, 47 years [range, 21-75 years]; 68 men with a mean age of 44 years [range, 21-73 years] and 34 women with a mean age of 52 years [range, 24-75 years]) were recruited from three high-volume liver centers between August 2016 and April 2017. All participants with cirrhosis of various causes underwent transjugular HVPG measurement, Doppler US, and CT angiography. Virtual HVPG was developed with a three-dimensional reconstructed model and computational fluid dynamics. Results In the training cohort (n = 29), the area under the receiver operating characteristic curve (AUC) of virtual HVPG in the prediction of clinically significant portal hypertension (CSPH) was 0.83 (95% confidence interval [CI]: 0.58, 1.00). The diagnostic performance was prospectively confirmed in the validation cohort (n = 73), with an AUC of 0.89 (95% CI: 0.81, 0.96). Inter- and intraobserver agreement was 0.88 and 0.96, respectively, suggesting the good reproducibility of virtual HVPG measurements. There was good correlation between virtual HVPG and invasive HVPG (R = 0.61, P < .001), with a satisfactory performance to rule out (7.3 mm Hg) and rule in (13.0 mm Hg) CSPH. Conclusion The accuracy of a computational model of virtual hepatic venous pressure gradient (HVPG) shows significant correlation with invasive HVPG. The virtual HVPG also showed a good performance in the noninvasive diagnosis of clinically significant portal hypertension in cirrhosis. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Malayeri in this issue.

Non-invasive diagnosis of portal hypertension in cirrhosis using ultrasound based elastography.

Liver stiffness measurement (LSM) by ultrasound-based elastography may be used to non-invasively discriminate betweenthe stages of liver fibrosis, rule out cirrhosis and follow its evolution, including the prediction of the presence ofoesophageal varices. The same is possible in order to diagnose clinically significant portal hypertension, referring primarilyto transient elastography and LSM values ≥20-25 kPa. The same approach may be used to reliably rule out the presence ofoesophageal varices (LSM <20 kPa + platelets >150x109/L). These recommendations refer primarily to patients with viral aetiologyof chronic liver disease (hepatitis C), while additional studies are required for other aetiologies. While spleen stiffnessmeasurement (SSM) also poses a logical choice in this indication, controversial results have nevertheless been published on this issue. It should be emphasized, however, that more recent data indicate that this parameter should be included in the diagnosticalgorithm for portal hypertension, if not as the sole then as a part of a sequential algorithm, combined with LSM. Untilnow, transient elastography has been most extensively studied and founded on scientific evidence, although the results of otherultrasound-based elastography techniques demonstrate the same trend for the non-invasive assessment of portal hypertension.

Correlation analysis between liver and spleen stiffness measured by acoustic radiation force impulse and hepatic venous pressure gradient

Objective To investigate the correlation between liver and spleen stiffness measured by acoustic radiation force impulse (ARFI) and hepatic venous pressure gradient (HVPG), and to evaluate its efficiency in the diagnosis of portal hypertension. Methods From April 2014 to March 2016, 20 cases underwent HVPG measurement because of liver cirrhosis were enrolled. Before HVPG measurement, liver and spleen stiffness were assessed with ARFI. The correlation between HVPG and age, alanine aminotransferase (ALT), aspartate aminotransferase (AST), total bilirubin, serum albumin, platelet count, prothrombin time, aspartate aminotransferase to platelet ratio index (APRI) score, Child-Pugh score, model for end-stage liver disease (MELD) score, liver stiffness and spleen stiffness were analyzed. Pearson correlation and Spearman rank correlation were performed for statistical analysis. Results HVPG, liver and spleen stiffness were successfully measured in all 20 patients. The mean liver stiffness was (1.78±0.29) m/s, the mean spleen stiffness was (3.37±0.44) m/s and HVPG was (16.10±5.14) mmHg (1 mmHg=0.133 kPa). Age, ALT, AST, total bilirubin, serum albumin, platelet count, prothrombin time, APRI score, Child-Pugh score and MELD score were all not correlated with HVPG (all P>0.05). But HVPG was positively correlated with liver and spleen stiffness (r=0.449, P=0.047; r=0.487, P=0.030). In the diagnosis of HVPG≥12 mmHg, the area under curve (AUC) of liver stiffness was 0.875, the optimal cut-off value was 1.77 m/s, the sensitivity was 68.6% and the specificity was 100.0%. In the diagnosis of HPVG≥20 mmHg, the AUC of liver stiffness was 0.798, the optimal cut off value was 1.85 m/s, the sensitivity was 100.0% and the specificity was 68.8%. The AUC of spleen stiffness was 0.820, the optimal cut-off value was 3.23 m/s, the sensitivity was 100.0 % and the specificity was 56.3%. Conclusion In patients with liver cirrhosis, liver stiffness and spleen stiffness assessed by ARFI are positively correlated with HVPG and therefore ARFI has certain application value in the noninvasive diagnosis of portal hypertension. Key words: Liver cirrhosis; Acoustic radiation force impulse; Hepatic venous pressure gradient; Noninvasive diagnosis

Seguimiento de los pacientes con infección crónica por virus B sin indicación de tratamiento. Seguimiento ecográfico en los portadores del antígeno de superficie del virus de la hepatitis B

Ultrasonography enables us to easily study HBV liver disease progression. The presence of an irregular border in the liver, a hyperechoic pattern and an increase in the size of the caudate lobe are objective signs of cirrhosis. The slowing of the portal flow measured by Doppler echocardiography has a high specificity and sensitivity for establishing the noninvasive diagnosis of portal hypertension. For HBV carriers with no active replication data and no associated liver disease, the periodicity of ultrasound examinations for the early diagnosis of hepatocarcinoma has not been established. One of the limitations of this technique is the interobserver and intraobserver variability. Staff who are assigned to this technique need sufficient experience and dedication.

Invasive and Non-invasive Diagnosis of Portal Hypertension in Cirrhosis

In the natural history of any chronic liver disease the occurrence of liver related complications is related to the portal hypertension development. Therefore, in the diagnosis work up of any liver disease the portal hypertension assessment is an indispensable step. The most accurate method for portal hypertension diagnosis is hepatic venous pressure gradient (HVPG), which implies central venous access and the catheterization of the hepatic vein. HVPG is the strongest prognostic marker in chronic liver diseases. It accurately predicts the risk of esophageal varices development and hemorrhage, the risk of decompensation as well as the mortality. Also HVPG represents a method to tailor portal hypertension treatment. However, due to the invasiveness of the procedure, there is an extensive effort to find non-invasive methods that could replace HVPG measurement. By now, only liver stiffness measuring proves to have good performances even there are issues about cut-offs and feasibility in overweight patients.

S07 * NONINVASIVE SCREENING TOOLS FOR LIVER CIRRHOSIS IN ADDICTED PATIENTS

S07 * NONINVASIVE SCREENING TOOLS FOR LIVER CIRRHOSIS IN ADDICTED PATIENTS