Advances in ultrasound elastography for nonalcoholic fatty liver disease

Estimation of non-alcoholic steatohepatitis (NASH) disease using clinical information based on the optimal combination of intelligent algorithms for feature selection and classification

The early diagnosis of NASH disease can decrease the risk of proceeding elements and treatment costs for patients. This study aims to present an optimal combination of intelligent algorithms using advanced machine learning methods, including different feature selections and classifications based on clinical data and blood factors. In this work, collected data were from 176 patients to investigate NASH disease, and 19 features were extracted. We then sought to find the best combination of features based on different feature selection algorithms such as Feature Forward Selection (FFS), Minimum Redundancy Maximum Relevance (MRMR), and Mutual Information (MI). Finally, we used nine classifier frameworks with different mathematical mechanisms, including random forest (RF), logistic regression (LR), Linear Discriminant Analysis (LDA), AdaBoost, K nearest neighbors (KNN), multilayer perceptron model (MLP), support vector machine (SVM), and decision tree (DT) to estimate NASH disease. Our investigation revealed that the combination of dominant features, namely body mass index (BMI), glutamic pyruvic transaminase (GPT), total cholesterol (TC), high-density lipoprotein (HDL), Ezetimibe, lipoprotein level Lp(a), Loge(Lp(a)), total triglyceride (TG), Creatinine (Cre), HbA1c, Fibrate, and Sex, selected by the MRMR algorithm and classified by the RF method can provide the most appropriate performance based on less computation effort and maximum performance with accuracy, AUC, precision, and recall indices, which are 81.51 ± 9.35 , 82.53 ± 11.24 , 85.28 ± 9.68 , and 89.49 ± 7.92 , respectively. This study investigated the configuration of feature selection and classifier that is most suitable for classifying NASH disease based on clinical data and blood factors. The proposed intelligent algorithm based on MRMR and RF classifier can automatically diagnose NASH disease with appropriate performance and present an initial report without any further invasive methods. It also clarifies the diagnostic process and, as a result, the continuation of their prevention and treatment cycle.

CGMap: Characterizing continuous glucose monitor data in thousands of non-diabetic individuals

Despite its rising prevalence, diabetes diagnosis still relies on measures from blood tests. Technological advances in continuous glucose monitoring (CGM) devices introduce a potential tool to expand our understanding of glucose control and variability in people with and without diabetes. Yet CGM data have not been characterized in large-scale healthy cohorts, creating a lack of reference for CGM data research. Here we present CGMap, a characterization of CGM data collected from over 7,000 non-diabetic individuals, aged 40-70 years, between 2019 and 2022. We provide reference values of key CGM-derived clinical measures that can serve as a tool for future CGM research. We further explored the relationship between CGM-derived measures and diabetes-related clinical parameters, uncovering several significant relationships, including associations of mean blood glucose with measures from fundus imaging and sleep monitoring. These findings offer novel research directions for understanding the influence of glucose levels on various aspects of human health.

Lipid accumulation product (LAP) index for the diagnosis of nonalcoholic fatty liver disease (NAFLD): a systematic review and meta-analysis

BACKGROUND

Lipid accumulation product (LAP) is an index calculated by waist circumference (WC) and triglyceride (TG), which reflects lipid toxicity. This study aims to investigate the association between the LAP index and nonalcoholic fatty liver disease (NAFLD) in a systematic review and meta-analysis.

METHODS AND RESULTS

PubMed, Scopus, and Web of Science online databases were searched for eligible studies that investigated the association of the LAP index and NAFLD. Sixteen observational studies with 96,101 participants, including four cohort studies, one case‒control study and 11 cross-sectional studies with baseline data, were entered into this analysis. Fourteen studies reported a significant association between the LAP index and NAFLD, and two reported that this relation was not significant; two different meta-analyses (1- mean difference (MD) and 2- bivariate diagnostic test accuracy [DTA]) were conducted using Stata version 14. The LAP index was compared in subjects with and without NAFLD, and the difference was significant with 34.90 units (CI 95: 30.59-39.31, P < 0.001) of the LAP index. The DTA meta-analysis was conducted and showed that the LAP index pooled sensitivity and specificity for screening of NAFLD were 94% (CI95: 72%-99%, I2 = 99%, P < 0.001) and 85% (CI95: 62%-96%, I2 = 99%, P < 0.001), respectively.

CONCLUSION

The LAP Index is an inexpensive, sensitive, and specific method to evaluate NAFLD and may be valuable for NAFLD screening.

Deep attenuation transducer to measure liver stiffness in obese patients with liver disease

PURPOSE

Deep attenuation transducers (DAX) are capable of imaging at diagnostic depths of up to 40 cm. The feasibility of DAX for liver stiffness measurement (LSM) has not been reported clinically. We aimed to assess the feasibility and reliability of DAX for LSM.

METHODS

Overall, 219 patients with chronic liver disease were enrolled. The success rate (acquired after ≥ 10 valid measurements) and inadequate measurements (interquartile range/median ≥ 0.3) for DAX were compared with those of conventional convex (c-convex) probes and M and XL probes of vibration-controlled transient elastography.

RESULTS

LSM was successfully performed for all patients using DAX through all degrees of skin-to-liver capsular distance (SCD). Especially in patients with an SCD ≥ 30 mm, the difference in the rate of acquisition of 10 valid measurements was remarkable: M probe (8/33, 24.2%), XL probe (26/33, 78.8%), c-convex probe (33/43, 76.7%), and DAX (44/44, 100%). In patients with an SCD ≥ 30 mm, the inadequate measurement rate of M probe (1/8, 12.5%), XL probe (8/26, 30.8%), and c-convex probe (6/33, 18.2%) was higher than that of DAX (1/43, 2.3%). The areas under the curve for diagnosis of F4 with shear wave speed by c-convex and DAX were 0.916 and 0.918, respectively. Between DAX and c-convex probes, the intraclass correlation coefficient of 0.937 (95% CI 0.918-0.952) was excellent. Bland-Altman plots revealed that there was no statistically significant bias.

CONCLUSION

Liver stiffness measured by DAX is feasible and reliable for all patient populations, while the XL probe is limited to use in obese patients.

Changing clinical management of NAFLD in Asia

Non-alcoholic fatty liver disease (NAFLD) has become the leading cause of chronic liver disease, affecting approximately 25% of the world's population. Recently, because of the sedentary lifestyle and overnutrition resulting from urbanisation, the burden of NAFLD has rapidly increased in many Asian countries. Currently, the prevalence of NAFLD in Asia is approximately 30%, as is the case in many Western countries. In Asia, the prevalence and presentation of NAFLD vary widely across regions because of the substantial diversity in race, socioeconomic status and living environment. Furthermore, the dual aetiology of fatty liver, particularly with viral hepatitis in Asia, makes it complex and challenging to manage. Because Asians are likely to have central adiposity and insulin resistance, approximately 7%-20% of non-obese Asians with body mass indexes of less than 25 kg/m² are estimated to have NAFLD. Accumulating evidence indicates that NAFLD is associated with various extrahepatic comorbidities such as cardiovascular disease, chronic kidney disease, malignancy, in addition to liver-specific complications. Therefore, NAFLD should be managed as a multisystem disease in conjunction with metabolic syndrome. Lifestyle modification remains the basis of NAFLD management, but few patients can achieve adequate weight loss and maintain it long term. While various pharmacological agents are in phase 3 trials for steatohepatitis, Asian patients are underrepresented in most trials. This article reviews the epidemiological trends, clinical features, optimal assessment and current management practices for NAFLD in Asia.

Noninvasive assessment of liver fibrosis and its clinical significance in nonalcoholic fatty liver disease

Liver fibrosis is the most important prognostic factor in patients with nonalcoholic fatty liver disease (NAFLD). Several noninvasive markers for fibrosis, including blood-based markers and imaging based-markers have been developed. Indirect fibrosis markers (e.g., fibrosis-4 index and NAFLD fibrosis score) consist of standard laboratory data and clinical parameters. Given its availability and high negative predictive value for advanced fibrosis, these markers are suitable for screening at primary care. Blood-based fibrogenesis markers (enhanced liver fibrosis and N-terminal propeptide of type 3 collagen), ultrasound-based modalities (vibration-controlled transient elastography, point shear wave elastography [SWE], and two-dimensional SWE), and magnetic resonance elastography have high diagnostic accuracy for liver fibrosis and are suitable for diagnosing liver fibrosis at secondary care centers. Sequential use of these markers can increase diagnostic accuracy and reduce health care costs. Furthermore, combining noninvasive makers may assist in identifying candidates for pharmacological trials and reducing screening failure. Emerging data suggest that these noninvasive markers are associated with liver-related events (hepatocellular carcinoma and decompensation) and mortality. Furthermore, delta change in noninvasive markers over time is also associated with time-course change in fibrosis, liver-related event risk, and mortality risk. However, the association between liver fibrosis and cardiovascular disease (CVD) risk is still controversial. CVD risk may decrease in patients with decompensated liver disease and noninvasive markers may be useful for assessing CVD risk in these patients. Therefore, noninvasive markers may be utilized as measures of fibrosis as well as real-time prognostic tools, in place of liver biopsy.

The effect of the skin-liver capsule distance on the accuracy of ultrasound diagnosis for liver steatosis and fibrosis

PURPOSE

Transient elastography (TE) and the controlled attenuation parameter (CAP) have been used for diagnosis of liver fibrosis and steatosis. Obesity is a limiting factor to the accuracy of elastography; however, an XL probe was validated for use in obese patients. Two-dimensional shear wave elastography (2D-SWE) and attenuation imaging (ATI) have also been developed. It is unknown if obesity affects 2D-SWE/ATI values for evaluation of liver fibrosis and steatosis. We assessed the reliability of the measurement rate and the diagnostic performance of TE/CAP versus SWE/ATI.

METHODS

The patients (n = 85) underwent TE/CAP, 2D-SWE/ATI, and liver biopsy on the same day. They were diagnosed with chronic hepatitis based on liver biopsy. The patients were divided into three groups by skin-liver capsule distance (SCD).

RESULTS

The reliability of the measurement rate for the M probe was lower than that for the XL probe in the group with SCD over 22.5 mm. The rate achieved with 2D-SWE was high in all groups regardless of the SCD. In the assessment of the diagnostic performance, there was no difference between the area under the receiver-operating curve (AUROC) of TE compared to 2D-SWE to stratify the fibrosis stage. There was no difference in the AUROC for the stratification of the steatosis grades between CAP and ATI. The diagnostic accuracy of TE for F ≥ 3 fibrosis evaluated with the M probe and 2D-SWE was lower than that of TE evaluated with the XL probe in the group with SCD over 22.5 mm.

CONCLUSION

The ability of 2D-SWE to stratify fibrosis stage and steatosis grade was as good as FibroScan. However, 2D-SWE had a high reliability in the measurement rate regardless of the SCD with one probe. And the XL probe showed high diagnostic accuracy for severe fibrosis in the group with SCD over 22.5 mm.

A novel quantitative ultrasound technique for identifying non-alcoholic steatohepatitis

BACKGROUND AND AIMS

There remains a need to develop a non-invasive, accurate and easy-to-use tool to identify patients with non-alcoholic steatohepatitis (NASH). Successful clinical and preclinical applications demonstrate the ability of quantitative ultrasound (QUS) techniques to improve medical diagnostics. We aimed to develop and validate a diagnostic tool, based on QUS analysis, for identifying NASH.

METHODS

A total of 259 Chinese individuals with biopsy-proven non-alcoholic fatty liver disease (NAFLD) were enrolled in the study. The histological spectrum of NAFLD was classified according to the NASH clinical research network scoring system. Radiofrequency (RF) data, raw data of iLivTouch, was acquired for further QUS analysis. The least absolute shrinkage and selection operator (LASSO) method was used to select the most useful predictive features.

RESULTS

Eighteen candidate RF parameters were reduced to two significant parameters by shrinking the regression coefficients with the LASSO method. We built a novel QUS score based on these two parameters, and this QUS score showed good discriminatory capacity and calibration for identifying NASH both in the training set (area under the ROC curve [AUROC]: 0.798, 95% confidence interval [CI] 0.731-0.865; Hosmer-Lemeshow test, P = .755) and in the validation set (AUROC: 0.816, 95% CI 0.725-0.906; Hosmer-Lemeshow test, P = .397). Subgroup analysis showed that the QUS score performed well in different subgroups.

CONCLUSIONS

The QUS score, which was developed from QUS, provides a novel, non-invasive and practical way for identifying NASH.

Evaluation of ultrasonic fibrosis diagnostic system using convolutional network for ordinal regression

PURPOSE

Diagnosis of liver fibrosis is important for establishing treatment and assessing the risk of carcinogenesis. Ultrasound imaging is an excellent diagnostic method as a screening test in terms of non-invasiveness and simplicity. The purpose of this study was to automatically diagnose liver fibrosis using ultrasound images to reduce the burden on physicians.

METHODS

We proposed and implemented a system for extracting regions of liver parenchyma utilizing U-Net. Using regions of interest, the stage of fibrosis was classified as F0, F1, F2, F3, or F4 utilizing CORALNet, an ordinal regression model based on ResNet18. The effectiveness of the proposed system was verified.

RESULTS

The system implemented using U-Net had a maximum mean Dice coefficient of 0.929. The results of classification of liver fibrosis utilizing CORALNet had a mean absolute error (MAE) of 1.22 and root mean square error (RMSE) of 1.60. The per-case results had a MAE of 1.55 and RMSE of 1.34.

CONCLUSION

U-Net extracted regions of liver parenchyma from the images with high accuracy, and CORALNet showed effectiveness using ordinal information to classify fibrosis in the images. As a future task, we will study a model that is less dependent on teaching data.

Diagnostic performance of ultrasound attenuation imaging for assessing low-grade hepatic steatosis

OBJECTIVES

To investigate the diagnostic performance of attenuation imaging (ATI) for the assessment of low-grade hepatic steatosis using liver biopsy as the reference standard.

METHODS

The study included 57 potential donor candidates for living liver transplantation who underwent ATI, transient elastography (TE), and liver biopsy for evaluation of hepatic steatosis between February 2020 and April 2020. The attenuation coefficient (AC) from ATI and the controlled attenuation parameter (CAP) from TE were measured for each participant in a random and blind manner. The histologic hepatic fat fraction (HFF) was graded (S0, < 5%; S1, 5-33%; S2, 33-66%; S3, > 66%). The accuracy of ATI for diagnosing hepatic steatosis was compared with that of CAP using ROC analysis. Correlations between AC and HFF were evaluated, and factors affecting AC were determined by linear regression analysis.

RESULTS

The median HFF was 3% (range: 0-35%), with 31 (54.4%), 24 (42.0%), and 2 (3.5%) participants being graded as S0, S1, and S2, respectively. The AUCs for the ROCs of AC and CAP for the detection of hepatic steatosis were 0.808 (95% CI: 0.682-0.900) and 0.829 (95% CI: 0.706-0.916), respectively, with the difference not being statistically significant (p = 0.762). AC showed 61.5% of sensitivity and 90.3% of specificity. AC was positively correlated with HFF (p < 0.001). HFF was the only factor significantly affecting AC.

CONCLUSIONS

ATI showed moderate sensitivity and high specificity in the diagnosis and quantification of hepatic steatosis in low-grade steatosis without fibrosis. Only HFF significantly affected AC.

KEY POINTS

• Attenuation imaging showed moderate sensitivity and high specificity performance in the diagnosis and quantification of hepatic steatosis in low-grade steatosis without fibrosis. • The diagnostic performance of the attenuation coefficient by attenuation imaging did not significantly differ from that of the controlled attenuation parameter by transient elastography in quantifying low-grade steatosis. • The histopathologically determined hepatic fat fraction was the only factor significantly affecting the attenuation coefficient.

The FibroScan-aspartate aminotransferase score can stratify the disease severity in a Japanese cohort with fatty liver diseases

This study aimed to prove that the FibroScan-aspartate aminotransferase (FAST) scores can be used to stratify disease severity in a Japanese cohort with fatty liver diseases [metabolic dysfunction-associated fatty liver disease (MAFLD) and nonalcoholic fatty liver disease (NAFLD)]. All the participants (n = 2254) underwent liver stiffness measurements and controlled attenuation parameter assessments. We compared the clinical characteristics of the patients with MAFLD and NAFLD using the FAST scores and explored the independent determinants of FAST scores ≥ 0.35, which indicated possible progressive disease. Overall, MAFLD was diagnosed in 789 patients (35.0%), while NAFLD was diagnosed in 618 (27.4%). The proportion of patients that had a condition that suggested progressive liver disease was higher in those with MAFLD than in those with NAFLD [68 (8.6%) vs 48 (7.7%)]. The area under the receiver-operating characteristic curve of the FAST score for diagnosing advanced fibrosis was 0.969 in MAFLD and 0.965 in NAFLD. Multivariate analyses determined that diabetes mellitus, alanine aminotransferase (ALT) levels, fatty liver index, and Fibrosis-4 index independently predict FAST scores ≥ 0.35 in patients with MAFLD. ALT levels had the strongest correlation with the FAST scores (p = 0.7817). The FAST score could stratify the disease severity in the Japanese cohort with fatty liver diseases.

Validation of a two-step approach combining serum biomarkers and liver stiffness measurement to predict advanced fibrosis

Background and Aim

The Gut and Obesity in Asia Workgroup recently reported that a two‐step approach using fibrosis scores followed by liver stiffness measurement (LSM) could accurately detect patients with non‐alcoholic fatty liver disease (NAFLD) having advanced fibrosis in low‐risk fibrosis populations. This study aimed to validate the utility of this approach using a Japanese health checkup registry.

Methods

This cross‐sectional study included subjects who underwent a health checkup from 2014 to 2019. Using estimated fibrosis stage measured by LSM as a standard, we calculated the percentage of misclassification from assessments made based on fibrosis scores (NAFLD fibrosis score [NFS] or Fibrosis‐4 score [FIB‐4]) and LSM, alone or in combination.

Results

Of 630 subjects with NAFLD, 4 (0.8%) had advanced fibrosis. In the first‐step evaluation, only 21.4–38.0% of subjects needed further testing. This approach was associated with a high specificity of approximately 100% and a negative predictive value of 99.7%. The percentage of misclassification based on NFS or FIB‐4 values followed by LSM in all subjects and using LSM after NFS or FIB‐4 determination only in subjects with indeterminate/high NFS or FIB‐4 values (two‐step approach) was 0% and 0.3% and 0.16% and 0.3%, respectively. In addition, very few false negatives occurred for both NFS and FIB‐4.

Conclusion

The two‐step approach helps to identify the subjects with NAFLD who have advanced fibrosis during a routine health checkup and is associated with only a few false negatives.

A review of physical and engineering factors potentially affecting shear wave elastography

It has been recognized that tissue stiffness provides useful diagnostic information, as with palpation as a screening for diseases such as cancer. In recent years, shear wave elastography (SWE), a technique for evaluating and imaging tissue elasticity quantitatively and objectively in diagnostic imaging, has been put into practical use, and the amount of clinical knowledge about SWE has increased. In addition, some guidelines and review papers regarding technology and clinical applications have been published, and the status as a diagnostic technology is in the process of being established. However, there are still unclear points about the interpretation of shear wave speed (SWS) and converted elastic modulus in SWE. To clarify these, it is important to investigate the factors that affect the SWS and elastic modulus. Therefore, physical and engineering factors that potentially affect the SWS and elastic modulus are discussed in this review paper, based on the principles of SWE and a literature review. The physical factors include the propagation properties of shear waves, mechanical properties (viscoelasticity, nonlinearity, and anisotropy), and size and shape of target tissues. The engineering factors include the region of interest depth and signal processing. The aim of this review paper is not to provide an answer to the interpretation of SWS. It is to provide information for readers to formulate and verify the hypothesis for the interpretation. Therefore, methods to verify the hypothesis for the interpretation are also reviewed. Finally, studies on the safety of SWE are discussed.

Diagnostic Accuracy of FibroScan and Factors Affecting Measurements

Evaluating liver steatosis and fibrosis is important for patients with non-alcoholic fatty liver disease. Although liver biopsy and pathological assessment is the gold standard for these conditions, this technique has several disadvantages. The evaluation of steatosis and fibrosis using ultrasound B-mode imaging is qualitative and subjective. The liver stiffness measurement (LSM) and controlled attenuation parameter (CAP) determined using FibroScan are the evidence-based non-invasive measures of liver fibrosis and steatosis, respectively. The LSM and CAP measurements are carried out simultaneously, and the median values of more than ten valid measurements are used to quantify liver fibrosis and steatosis. Here, we demonstrate that the reliability of the LSM depends on the interquartile range to median ratio (IQR/Med), but CAP values do not depend on IQR/Med. In addition, the LSM is affected by inflammation, congestion, and cholestasis in addition to fibrosis, while CAP values are affected by the body mass index in addition to steatosis. We also show that the M probe provides higher LSM values but lower CAP values than the XL probe in the same population. However, there was no statistically significant difference between the diagnostic accuracies of the two probes. These findings are important to understand the reliability of FibroScan measurements and the factors influencing measurement values for all patients.