Performance of two-dimensional shear wave elastography and transient elastography compared to liver biopsy for staging of liver fibrosis

A comprehensive evaluation system for ultrasound-guided infusion of human umbilical cord-derived MSCs in liver cirrhosis patients

BACKGROUND

Infusion of mesenchymal stem cells (MSCs) via portal vein is one of the main ways for MSCs transplantation to treat liver cirrhosis (LC). As the tissue of LC showed diffuse fibrosis and thickened Glission sheath, the soft pig-tail catheter, or central venous catheter can not successfully insert the portal vein. Thus, our study used an improved method and performed a relatively comprehensive system to evaluate the effect for human umbilical cord-derived mesenchymal stem cells (hUC-MSCs) transplantation.

METHOD

Fifteen patients with hepatitis B-related cirrhosis were enrolled in the study, and we performed hUC-MSCs transplantation via portal vein by using an 16-G needle and 0.035-inch guide wire combined with 7FR "retentional metal stiffner trocar" of pig-tail catheter under the guidance of contrast-enhanced ultrasound. Serum liver function, fibrotic indicators, tissue stiffness, coagulation function, and hemodynamics were measured at weeks 4, 12, and 24 after MSCs transplantation. Liver biopsy was performed before and 24 weeks after hUC-MSCs transplantation.

RESULT

After hUC-MSCs transplantation, the prothrombin time was lower than before. The levels of hyaluronic acid and IV-C(Type IV collagen) in fibrotic indicators were significantly reduced, and the Young's modulus was also decreased. Moreover, liver biopsy showed that the lytic necrosis of hepatocyte was decreased. In liver hemodynamics, the portal vein diameter was decreased after hUC-MSCs transplantation.

CONCLUSION

hUC-MSCs transplantation can alleviate liver damage caused by LC. The improved "retentional metal stiffner trocar" of pig-tail catheter was safe and effective in the infusion of hUC-MSCs transplantation, which is worth promoting in clinical practice.

Liver fibrosis stage classification in stacked microvascular images based on deep learning

BACKGROUND

Monitoring fibrosis in patients with chronic liver disease (CLD) is an important management strategy. We have already reported a novel stacked microvascular imaging (SMVI) technique and an examiner scoring evaluation method to improve fibrosis assessment accuracy and demonstrate its high sensitivity. In the present study, we analyzed the effectiveness and objectivity of SMVI in diagnosing the liver fibrosis stage based on artificial intelligence (AI).

METHODS

This single-center, cross-sectional study included 517 patients with CLD who underwent ultrasonography and liver stiffness testing between August 2019 and October 2022. A convolutional neural network model was constructed to evaluate the degree of liver fibrosis from stacked microvascular images generated by accumulating high-sensitivity Doppler (i.e., high-definition color) images from these patients. In contrast, as a method of judgment by the human eye, we focused on three hallmarks of intrahepatic microvessel morphological changes in the stacked microvascular images: narrowing, caliber irregularity, and tortuosity. The degree of liver fibrosis was classified into five stages according to etiology based on liver stiffness measurement: F0-1Low (< 5.0 kPa), F0-1High (≥ 5.0 kPa), F2, F3, and F4.

RESULTS

The AI classification accuracy was 53.8% for a 5-class classification, 66.3% for a 3-class classification (F0-1Low vs. F0-1High vs. F2-4), and 83.8% for a 2-class classification (F0-1 vs. F2-4). The diagnostic accuracy for ≥ F2 was 81.6% in the examiner's score assessment, compared with 83.8% in AI assessment, indicating that AI achieved higher diagnostic accuracy. Similarly, AI demonstrated higher sensitivity and specificity of 84.2% and 83.5%, respectively. Comparing human judgement with AI judgement, the AI analysis was a superior model with a higher F1 score in the 2-class classification.

CONCLUSIONS

In detecting significant fibrosis (≥ F2) using the SMVI method, AI-based assessments are more accurate than human judgement; moreover, AI-based SMVI analysis eliminating human subjectivity bias and determining patients with objective fibrosis development is considered an important improvement.

Ultrasound Versus Elastography in the Diagnosis of Hepatic Steatosis: Evaluation of Traditional Machine Learning Versus Deep Learning

The prevalence of fatty liver disease is on the rise, posing a significant global health concern. If left untreated, it can progress into more serious liver diseases. Therefore, accurately diagnosing the condition at an early stage is essential for more effective intervention and management. This study uses images acquired via ultrasound and elastography to classify liver steatosis using classical machine learning classifiers, including random forest and support vector machine, as well as deep learning architectures, such as ResNet50V2 and DenseNet-201. The neural network demonstrated the most optimal performance, achieving an F1 score of 99.5% on the ultrasound dataset, 99.2% on the elastography dataset, and 98.9% on the mixed dataset. The results from the deep learning approach are comparable to those of machine learning, despite objectively not achieving the highest results. This research offers valuable insights into the domain of medical image classification and advocates the integration of advanced machine learning and deep learning technologies in diagnosing steatosis.

Implementation of Machine Learning Algorithms to Screen for Advanced Liver Fibrosis in Metabolic Dysfunction-Associated Steatotic Liver Disease: An In-Depth Explanatory Analysis

INTRODUCTION

This study aimed to train machine learning algorithms (MLAs) to detect advanced fibrosis (AF) in metabolic dysfunction-associated steatotic liver disease (MASLD) patients at the level of primary care setting and to explain the predictions to ensure responsible use by clinicians.

METHODS

Readily available features of 618 MASLD patients followed up at a tertiary center were used to train five MLAs. AF was defined as liver stiffness ≥9.3 kPa, measured via 2-dimension shear wave elastography (n = 495) or liver biopsy ≥F3 (n = 123). MLAs were compared to Fibrosis-4 index (FIB-4) and non-alcoholic fatty liver disease (NAFLD) fibrosis score (NFS) on 540 MASLD patients from the primary care setting as validation. Feature importance, partial dependence, and shapely additive explanations (SHAPs) were utilized for explanation.

RESULTS

Extreme gradient boosting (XGBoost) achieved an AUC = 0.91, outperforming FIB-4 (AUC = 0.78) and NFS (AUC = 0.81, both p < 0.05) with specificity = 76% versus 59% and 48% for FIB-4 ≥1.3 and NFS ≥-1.45, respectively (p < 0.05). Its sensitivity (91%) was superior to FIB-4 (79%). XGBoost confidently excluded AF (negative predictive value = 99%) with the highest positive predictive value (31%), superior to FIB-4 and NFS (all p < 0.05). The most important features were HbA1c and gamma glutamyl transpeptidase (GGT) with a steep increase in AF probability at HbA1c >6.5%. The strongest interaction was between AST and age. XGBoost, but not logistic regression, extracted informative patterns from ALT, low-density lipoprotein cholesterol, and alkaline phosphatase (p < 0.001). One-quarter of the false positives (FPs) were correctly reclassified with only one additional false negative based on the SHAP values of GGT, platelets, and ALT which were found to be associated with a FP classification.

CONCLUSIONS

An explainable XGBoost algorithm was demonstrated superior to FIB-4 and NFS for screening of AF in MASLD patients at the primary care setting. The algorithm also proved safe for use as clinicians can understand the predictions and flag FP classifications.

Progress in the diagnosis and treatment of graft fibrosis after liver transplantation

Liver transplantation (LT) is considered one of the best treatments for patients with end‐stage liver diseases. However, some patients with no significant clinical manifestations or abnormal laboratory tests still experience graft fibrosis during postoperative follow‐up, which is often recognized by graft histopathology. Graft fibrosis can lead to graft dysfunction, thereby reducing the survival time of the recipient and even requiring re‐transplantation. Currently, noninvasive methods are widely applied in the assessment of hepatic and allograft fibrosis. Although both noninvasive diagnostic models based on laboratory examination indicators and elastography technology that can quantify liver stiffness have some value in the evaluation of fibrosis, the diagnostic accuracy and characteristics of these various methods vary and cannot replace liver biopsy completely. In recent years, some liver‐protective drugs and proprietary Chinese traditional medicines have been proven to delay or reverse chronic liver fibrosis. Nevertheless, their efficacy and safety for LT recipients need to be further verified. This article reviews the diagnosis and treatment of graft fibrosis after LT to provide a reference for improving the overall survival rate of LT recipients.

Suboptimal reliability of FIB-4 and NAFLD-fibrosis scores for staging of liver fibrosis in general population

Background and Aim

The burden and incidence of liver cirrhosis are increasing worldwide. Early detection of liver fibrosis would help in early interventions and preventing the progression of fibrosis and cirrhosis. The accepted noninvasive markers for liver fibrosis staging, namely fibrosis-4 (FIB-4) and nonalcoholic fatty liver disease fibrosis score (NFS), have shown inconsistent performance for detecting the fibrosis stage. We aimed to evaluate the efficacy of FIB-4 score and NFS for the detection of liver fibrosis in the general population.

Methods

From a general population referred from a single, community-based family-physician clinic, we included study participants between the ages of 45 and 65 years, with no knowledge of liver disease and no record of alcohol consumption. Liver fibrosis was evaluated by the FIB-4 score and NFS using shear wave elastography (SWE) or transient elastography (TE) measurements as a reference.

Results

A total of 76 participants (aged 61.5 ± 0.37 years, 33% females) were included in the study cohort. We observed a nonsignificant correlation between liver stiffness measurement (LSM) and FIB-4 and NFS (r = 0.1, P = 0.37; r = 0.16, P = 0.15, respectively). Our results showed that only 5.2% with FIB-4 >3.25 and 9.7% with NFS >0.675 had LSM >12 kPa. The compatibility of fibrosis staging was 55% between FIB-4 score and LSM and only 18% between NFS and LSM.

Conclusion

We found that FIB-4 and NFS are unreliable tools for liver fibrosis estimation in the general population. There is a need for more reliable noninvasive methods for the early detection of liver fibrosis.

The application of a novel platform of multiparametric magnetic resonance imaging in a bioenvironmental toxic carbon tetrachloride-induced mouse model of liver fibrosis

The use of multiparametric magnetic resonance imaging (MRI) to distinguish complex histopathological changes in liver fibrosis has not yet been systematically established. The purpose of this study is to gauge the efficacy of a cutting-edge MRI platform for evaluating ecotoxicologically hazardous carbon tetrachloride (CCl4) induced liver fibrosis, while also scrutinizing the relationship between MRI and its histopathological features. Thirty-six mice were randomly divided into 6 groups, each with 6 mice. Control mice received an intraperitoneal injection of olive oil, while the experimental mice received different doses of intraperitoneal injection of CCl4. Both sets underwent this process twice per week over a duration of 5 weeks. MRI measurements encompassed T1WI, T2WI, T1 mapping, T2 mapping, T2* mapping. Liver fibrosis and inflammation were assessed and classified using Metavir and activity scoring systems. CCl4 successfully induced liver fibrosis in mice, showing an increasing extent of liver fibrosis and liver function damage with the increasing dosage of CCl4. Compared with the control group, T1, ΔT1, and T2 in the experimental group were considerably elevated (P < 0.05) than those in the control group. Spearman's correlation showed that the correlation of Native T1 and △T1 with fibrosis (r = 0.712, 0.678) was better than with inflammation (r = 0.688, 0.536). T2 correlation with inflammation (r = 0.803) was superior to fibrosis (r = 0.568). ROC analysis showed that the AUC of Native T1 was highest (0.906), followed by ΔT1 (0.852), while the AUC increased to 0.945 when all relevant MRI parameters were combined. T1 is the most potent MRI parameter for evaluating CCl4-induced liver fibrosis, followed by ΔT1. Meanwhile, T2 may not be suitable for evaluating liver fibrosis but is more suitable for evaluating liver inflammation.