Automated CNN-Based Analysis Versus Manual Analysis for MR Elastography in Nonalcoholic Fatty Liver Disease: Inter-method Agreement and Fibrosis Stage Discriminative Performance

Advances in imaging-Elastography

Chronic liver disease affects over a billion people worldwide. Liver fibrosis is the key driver of liver-related complications and mortality. Elastography has been a transformative tool in hepatology, allowing for the diagnosis and staging of liver fibrosis noninvasively, and is evolving beyond these purposes into a prognostication tool. By measuring tissue stiffness, elastography techniques such as shear-wave and magnetic resonance elastography offer critical insights into liver fibrosis, portal hypertension, and the progression of disease. Magnetic resonance elastography stands out for its reliability across fibrosis stages and robustness in obese patients affected by metabolic liver disease. Spleen stiffness measurement complements liver assessments, enhancing the identification of portal hypertension and refining patient risk stratification. This review covers current clinical applications but also anticipates future innovations such as artificial intelligence-based algorithms that could expand elastography's clinical impact, thereby improving patient outcomes.

Automated liver magnetic resonance elastography quality control and liver stiffness measurement using deep learning

PURPOSE

Magnetic resonance elastography (MRE) measures liver stiffness for fibrosis staging, but its utility can be hindered by quality control (QC) challenges and measurement variability. The objective of the study was to fully automate liver MRE QC and liver stiffness measurement (LSM) using a deep learning (DL) method.

METHODS

In this retrospective, single center, IRB-approved human study, a curated dataset involved 897 MRE magnitude slices from 146 2D MRE scans [1.5 T and 3 T MRI, 2D Gradient Echo (GRE), and 2D Spin Echo-Echo Planar Imaging (SE-EPI)] of 69 patients (37 males, mean age 51.6 years). A SqueezeNet-based binary QC model was trained using combined and individual inputs of MRE magnitude slices and their 2D Fast-Fourier transforms to detect artifacts from patient motion, aliasing, and blurring. Three independent observers labeled MRE magnitude images as 0 (non-diagnostic quality) or 1 (diagnostic quality) to create a reference standard. A 2D U-Net segmentation model was trained on diagnostic slices with liver masks to support LSM. Intersection over union between the predicted segmentation and confidence masks identified measurable areas for LSM on elastograms. Cohen's unweighted Kappa coefficient, mean LSM error (%), and intra-class correlation coefficient were calculated to compare the DL-assisted approach with the observers' annotations. An efficiency analysis compared the DL-assisted vs manual LSM durations.

RESULTS

The top QC ensemble model (using MRE magnitude alone) achieved accuracy, precision, and recall of 0.958, 0.982, and 0.886, respectively. The mean LSM error between the DL-assisted approach and the reference standard was 1.9% ± 4.6%. DL-assisted approach completed LSM for 29 diagnostic slices in under 1 s, compared to 20 min manually.

CONCLUSION

An automated DL-based classification of liver MRE diagnostic quality, liver segmentation, and LSM approach demonstrates a promising high performance, with potential for clinical adoption.

Self-Gated Radial Free-Breathing Liver MR Elastography: Assessment of Technical Performance in Children at 3 T

BACKGROUND

Conventional liver magnetic resonance elastography (MRE) requires breath-holding (BH) to avoid motion artifacts, which is challenging for children. While radial free-breathing (FB)-MRE is an alternative for quantifying liver stiffness (LS), previous methods had limitations of long scan times, acquiring two slices in 5 minutes, and not resolving motion during reconstruction.

PURPOSE

To reduce FB-MRE scan time to 4 minutes for four slices and to investigate the impact of self-gated (SG) motion compensation on FB-MRE LS quantification in terms of agreement, intrasession repeatability, and technical quality compared to conventional BH-MRE.

STUDY TYPE

Prospective.

POPULATION

Twenty-six children without fibrosis (median age: 12.9 years, 15 females).

FIELD STRENGTH/SEQUENCE

3 T; Cartesian gradient-echo (GRE) BH-MRE, research application radial GRE FB-MRE.

ASSESSMENT

Participants were scanned twice to measure repeatability, without moving the table or changing the participants' position. LS was measured in areas of the liver with numerical confidence ≥90%. Technical quality was examined using measurable liver area (%).

STATISTICAL TESTS

Agreement of LS between BH-MRE and FB-MRE was evaluated using Bland-Altman analysis for SG acceptance rates of 40%, 60%, 80%, and 100%. LS repeatability was assessed using within-subject coefficient of variation (wCV). The differences in LS and measurable liver area were examined using Kruskal-Wallis and Wilcoxon signed-rank tests. P < 0.05 was considered significant.

RESULTS

FB-MRE with 60% SG achieved the closest agreement with BH-MRE (mean difference 0.00 kPa). The LS ranged from 1.70 to 1.83 kPa with no significant differences between BH-MRE and FB-MRE with varying SG rates (P = 0.52). All tested methods produced repeatable LS with wCV from 4.4% to 6.5%. The median measurable liver area was smaller for FB-MRE (32%-45%) than that for BH-MRE (91%-93%) (P < 0.05).

DATA CONCLUSION

FB-MRE with 60% SG can quantify LS with close agreement and comparable repeatability with respect to BH-MRE in children.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY: Stage 1.

Practical approach to quantitative liver and pancreas MRI in children

Quantitative abdominal magnetic resonance imaging (MRI) offers non-invasive, objective assessment of diseases in the liver, pancreas, and other organs and is increasingly being used in the pediatric population. Certain quantitative MRI techniques, such as liver proton density fat fraction (PDFF), R2* mapping, and MR elastography, are already in wide clinical use. Other techniques, such as liver T1 mapping and pancreas quantitative imaging methods, are emerging and show promise for enhancing diagnostic sensitivity and treatment monitoring. Quantitative imaging techniques have historically required a breath-hold, making them more difficult to implement in the pediatric population. However, technological advances, including free-breathing techniques and compressed sensing imaging, are making these techniques easier to implement. The purpose of this article is to review current liver and pancreas quantitative techniques and to provide a practical guide for implementing these techniques in pediatric practice. Future directions of liver and pancreas quantitative imaging will be briefly discussed.

Neural Network Classification Algorithm Based on Self-attention Mechanism and Ensemble Learning for MASLD Ultrasound Images

BACKGROUND

Ultrasound image examination has become the preferred choice for diagnosing metabolic dysfunction-associated steatotic liver disease (MASLD) due to its non-invasive nature. Computer-aided diagnosis (CAD) technology can assist doctors in avoiding deviations in the detection and classification of MASLD.

METHOD

We propose a hybrid model that integrates the pre-trained VGG16 network with an attention mechanism and a stacking ensemble learning model, which is capable of multi-scale feature aggregation based on the self-attention mechanism and multi-classification model fusion (Logistic regression, random forest, support vector machine) based on stacking ensemble learning. The proposed hybrid method achieves four classifications of normal, mild, moderate, and severe fatty liver based on ultrasound images.

RESULT AND CONCLUSION

Our proposed hybrid model reaches an accuracy of 91.34% and exhibits superior robustness against interference, which is better than traditional neural network algorithms. Experimental results show that, compared with the pre-trained VGG16 model, adding the self-attention mechanism improves the accuracy by 3.02%. Using the stacking ensemble learning model as a classifier further increases the accuracy to 91.34%, exceeding any single classifier such as LR (89.86%) and SVM (90.34%) and RF (90.73%). The proposed hybrid method can effectively improve the efficiency and accuracy of MASLD ultrasound image detection.

Interpretation, Reporting, and Clinical Applications of Liver MR Elastography

Chronic liver disease is highly prevalent and often leads to fibrosis or cirrhosis and complications such as liver failure and hepatocellular carcinoma. The diagnosis and staging of liver fibrosis is crucial to determine management and mitigate complications. Liver biopsy for histologic assessment has limitations such as sampling bias and high interreader variability that reduce precision, which is particularly challenging in longitudinal monitoring. MR elastography (MRE) is considered the most accurate noninvasive technique for diagnosing and staging liver fibrosis. In MRE, low-frequency vibrations are applied to the abdomen, and the propagation of shear waves through the liver is analyzed to measure liver stiffness, a biomarker for the detection and staging of liver fibrosis. As MRE has become more widely used in clinical care and research, different contexts of use have emerged. This review focuses on the latest developments in the use of MRE for the assessment of liver fibrosis; provides guidance for image acquisition and interpretation; summarizes diagnostic performance, along with thresholds for diagnosis and staging of liver fibrosis; discusses current and emerging clinical applications; and describes the latest technical developments.

Clinical applications of artificial intelligence in liver imaging

This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that "segmentation," "hepatocellular carcinoma and radiomics," "metastasis," "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.

Noninvasive imaging biomarkers for liver fibrosis in nonalcoholic fatty liver disease: current and future

Nonalcoholic fatty liver disease (NAFLD) is increasingly prevalent worldwide and becoming a major cause of liver disease-related morbidity and mortality. The presence of liver fibrosis in patients with NAFLD is closely related to prognosis, including the development of hepatocellular carcinoma and other complications of cirrhosis. Therefore, assessment of the presence of significant or advanced liver fibrosis is crucial. Although liver biopsy has been considered the "gold standard" method for evaluating the degree of liver fibrosis, it is not suitable for extensive use in all patients with NAFLD owing to its invasiveness and high cost. Therefore, noninvasive biochemical and imaging biomarkers have been developed to overcome the limitations of liver biopsy. Imaging biomarkers for the stratification of liver fibrosis have been evaluated in patients with NAFLD using different imaging techniques, such as transient elastography, shear wave elastography, and magnetic resonance elastography. Furthermore, artificial intelligence and deep learning methods are increasingly being applied to improve the diagnostic accuracy of imaging techniques and overcome the pitfalls of existing imaging biomarkers. In this review, we describe the usefulness and future prospects of noninvasive imaging biomarkers that have been studied and used to evaluate the degree of liver fibrosis in patients with NAFLD.

Dapagliflozin Presented Nonalcoholic Fatty Liver Through Metabolite Extraction and AMPK/NLRP3 Signaling Pathway

In recent years, the incidence rate of nonalcoholic fatty liver disease (NAFLD) has been increasing year by year. The experiments conducted on rat elucidated the effect and underlying mechanism of dapagliflozin in NAFLD. Sprague Dawley rats were fed with HFD (Fat accounts for 52%, carbohydrate 34% and protein 14%) for 12 weeks as NAFLD model. Dapagliflozin presented NAFLD in rat model. Dapagliflozin reduced oxidative stress and inflammation in rat model of NAFLD. Dapagliflozin reduced oxidative stress and inflammation in vitro model of NAFLD. Dapagliflozin in a model of NAFLD metabolized into histamine H1 receptor, caffeine metabolism, mannose type O-glycan biosynthesis, choline metabolism in cancer, tryptophan metabolism, and glycerophospholipid metabolism. Dapagliflozin induced AMPK/NLRP3 signaling pathway. The regulation of AMPK/NLRP3 signaling pathway affected the effects of dapagliflozin on nonalcoholic fatty liver. In summary, dapagliflozin plays a preventative role in NAFLD through metabolite extraction, the inhibition of oxidative stress, and inflammation by AMPK/NLRP3 signaling pathway. Dapagliflozin may be a potential therapeutic agent for oxidative stress and inflammation in model of NAFLD.