qFIBS: An Automated Technique for Quantitative Evaluation of Fibrosis, Inflammation, Ballooning, and Steatosis in Patients With Nonalcoholic Steatohepatitis

Quantitative digital pathology enables automated and quantitative assessment of inflammatory activity in patients with autoimmune hepatitis

Background

Chronic liver disease diagnoses depend on liver biopsy histopathological assessment. However, due to the limitations associated with biopsy, there is growing interest in the use of quantitative digital pathology to support pathologists. We evaluated the performance of computational algorithms in the assessment of hepatic inflammation in an autoimmune hepatitis in which inflammation is a major component.

Methods

Whole-slide digital image analysis was used to quantitatively characterize the area of tissue covered by inflammation [Inflammation Density (ID)] and number of inflammatory foci per unit area [Focal Density (FD)] on tissue obtained from 50 patients with autoimmune hepatitis undergoing routine liver biopsy. Correlations between digital pathology outputs and traditional categorical histology scores, biochemical, and imaging markers were assessed. The ability of ID and FD to stratify between low-moderate (both portal and lobular inflammation ≤1) and moderate-severe disease activity was estimated using the area under the receiver operating characteristic curve (AUC).

Results

ID and FD scores increased significantly and linearly with both portal and lobular inflammation grading. Both ID and FD correlated moderately-to-strongly and significantly with histology (portal and lobular inflammation; 0.36≤R≤0.69) and biochemical markers (ALT, AST, GGT, IgG, and gamma globulins; 0.43≤R≤0.57). ID (AUC: 0.85) and FD (AUC: 0.79) had good performance for stratifying between low-moderate and moderate-severe inflammation.

Conclusion

Quantitative assessment of liver biopsy using quantitative digital pathology metrics correlates well with traditional pathology scores and key biochemical markers. Whole-slide quantification of disease can support stratification and identification of patients with more advanced inflammatory disease activity.

Artificial intelligence scoring of liver biopsies in a phase II trial of semaglutide in nonalcoholic steatohepatitis

BACKGROUND AND AIMS

Artificial intelligence-powered digital pathology offers the potential to quantify histological findings in a reproducible way. This analysis compares the evaluation of histological features of NASH between pathologists and a machine-learning (ML) pathology model.

APPROACH AND RESULTS

This post hoc analysis included data from a subset of patients (n=251) with biopsy-confirmed NASH and fibrosis stage F1-F3 from a 72-week randomized placebo-controlled trial of once-daily subcutaneous semaglutide 0.1, 0.2, or 0.4 mg (NCT02970942). Biopsies at baseline and week 72 were read by 2 pathologists. Digitized biopsy slides were evaluated by PathAI's NASH ML models to quantify changes in fibrosis, steatosis, inflammation, and hepatocyte ballooning using categorical assessments and continuous scores. Pathologist and ML-derived categorical assessments detected a significantly greater percentage of patients achieving the primary endpoint of NASH resolution without worsening of fibrosis with semaglutide 0.4 mg versus placebo (pathologist 58.5% vs. 22.0%, p < 0.0001; ML 36.9% vs. 11.9%; p =0.0015). Both methods detected a higher but nonsignificant percentage of patients on semaglutide 0.4 mg versus placebo achieving the secondary endpoint of liver fibrosis improvement without NASH worsening. ML continuous scores detected significant treatment-induced responses in histological features, including a quantitative reduction in fibrosis with semaglutide 0.4 mg versus placebo ( p =0.0099) that could not be detected using pathologist or ML categorical assessment.

CONCLUSIONS

ML categorical assessments reproduced pathologists' results of histological improvement with semaglutide for steatosis and disease activity. ML-based continuous scores demonstrated an antifibrotic effect not measured by conventional histopathology.

A machine learning-based model analysis for serum markers of liver fibrosis in chronic hepatitis B patients

Early assessment and accurate staging of liver fibrosis may be of great help for clinical diagnosis and treatment in patients with chronic hepatitis B (CHB). We aimed to identify serum markers and construct a machine learning (ML) model to reliably predict the stage of fibrosis in CHB patients. The clinical data of 618 CHB patients between February 2017 and September 2021 from Zhejiang Provincial People's Hospital were retrospectively analyzed, and these data as a training cohort to build the model. Six ML models were constructed based on logistic regression, support vector machine, Bayes, K-nearest neighbor, decision tree (DT) and random forest by using the maximum relevance minimum redundancy (mRMR) and gradient boosting decision tree (GBDT) dimensionality reduction selected features on the training cohort. Then, the resampling method was used to select the optimal ML model. In addition, a total of 571 patients from another hospital were used as an external validation cohort to verify the performance of the model. The DT model constructed based on five serological biomarkers included HBV-DNA, platelet, thrombin time, international normalized ratio and albumin, with the area under curve (AUC) values of the DT model for assessment of liver fibrosis stages (F0-1, F2, F3 and F4) in the training cohort were 0.898, 0.891, 0.907 and 0.944, respectively. The AUC values of the DT model for assessment of liver fibrosis stages (F0-1, F2, F3 and F4) in the external validation cohort were 0.906, 0.876, 0.931 and 0.933, respectively. The simulated risk classification based on the cutoff value showed that the classification performance of the DT model in distinguishing hepatic fibrosis stages can be accurately matched with pathological diagnosis results. ML model of five serum markers allows for accurate diagnosis of hepatic fibrosis stages, and beneficial for the clinical monitoring and treatment of CHB patients.

New and emerging treatments for metabolic dysfunction-associated steatohepatitis

Metabolic dysfunction-associated steatohepatitis (MASH) is a leading etiology of chronic liver disease worldwide, with increasing incidence and prevalence in the setting of the obesity epidemic. MASH is also a leading indication for liver transplantation, given its associated risk of progression to end-stage liver disease. A key challenge in managing MASH is the lack of approved pharmacotherapy. In its absence, lifestyle interventions with a focus on healthy nutrition and regular physical activity have been the cornerstone of therapy. Real-world efficacy and sustainability of lifestyle interventions are low, however. Pharmacotherapy development for MASH is emerging with promising data from several agents with different mechanisms of action (MOAs) in phase 3 clinical trials. In this review, we highlight ongoing challenges and potential solutions in drug development for MASH and provide an overview of available data from emerging therapies across multiple MOAs.

Digital pathology and spatial omics in steatohepatitis: Clinical applications and discovery potentials

Steatohepatitis with diverse etiologies is the most common histological manifestation in patients with liver disease. However, there are currently no specific histopathological features pathognomonic for metabolic dysfunction-associated steatotic liver disease, alcohol-associated liver disease, or metabolic dysfunction-associated steatotic liver disease with increased alcohol intake. Digitizing traditional pathology slides has created an emerging field of digital pathology, allowing for easier access, storage, sharing, and analysis of whole-slide images. Artificial intelligence (AI) algorithms have been developed for whole-slide images to enhance the accuracy and speed of the histological interpretation of steatohepatitis and are currently employed in biomarker development. Spatial biology is a novel field that enables investigators to map gene and protein expression within a specific region of interest on liver histological sections, examine disease heterogeneity within tissues, and understand the relationship between molecular changes and distinct tissue morphology. Here, we review the utility of digital pathology (using linear and nonlinear microscopy) augmented with AI analysis to improve the accuracy of histological interpretation. We will also discuss the spatial omics landscape with special emphasis on the strengths and limitations of established spatial transcriptomics and proteomics technologies and their application in steatohepatitis. We then highlight the power of multimodal integration of digital pathology augmented by machine learning (ML)algorithms with spatial biology. The review concludes with a discussion of the current gaps in knowledge, the limitations and premises of these tools and technologies, and the areas of future research.

Lymphocyte-Infiltrated Periportal Region Detection With Structurally-Refined Deep Portal Segmentation and Heterogeneous Infiltration Features

Goal: The early diagnosis and treatment of hepatitis is essential to reduce hepatitis-related liver function deterioration and mortality. One component of the widely-used Ishak grading system for the grading of periportal interface hepatitis is based on the percentage of portal borders infiltrated by lymphocytes. Thus, the accurate detection of lymphocyte-infiltrated periportal regions is critical in the diagnosis of hepatitis. However, the infiltrating lymphocytes usually result in the formation of ambiguous and highly-irregular portal boundaries, and thus identifying the infiltrated portal boundary regions precisely using automated methods is challenging. This study aims to develop a deep-learning-based automatic detection framework to assist diagnosis. Methods: The present study proposes a framework consisting of a Structurally-REfined Deep Portal Segmentation module and an Infiltrated Periportal Region Detection module based on heterogeneous infiltration features to accurately identify the infiltrated periportal regions in liver Whole Slide Images. Results: The proposed method achieves 0.725 in F1-score of lymphocyte-infiltrated periportal region detection. Moreover, the statistics of the ratio of the detected infiltrated portal boundary have high correlation to the Ishak grade (Spearman's correlations more than 0.87 with p-values less than 0.001) and medium correlation to the liver function index aspartate aminotransferase and alanine aminotransferase (Spearman's correlations more than 0.63 and 0.57 with p-values less than 0.001). Conclusions: The study shows the statistics of the ratio of infiltrated portal boundary have correlation to the Ishak grade and liver function index. The proposed framework provides pathologists with a useful and reliable tool for hepatitis diagnosis.

A data-driven approach to decode metabolic dysfunction-associated steatotic liver disease

Metabolic dysfunction-associated steatotic liver disease (MASLD), defined by the presence of liver steatosis together with at least one out of five cardiometabolic factors, is the most common cause of chronic liver disease worldwide, affecting around one in three people. Yet the clinical presentation of MASLD and the risk of progression to cirrhosis and adverse clinical outcomes is highly variable. It, therefore, represents both a global public health threat and a precision medicine challenge. Artificial intelligence (AI) is being investigated in MASLD to develop reproducible, quantitative, and automated methods to enhance patient stratification and to discover new biomarkers and therapeutic targets in MASLD. This review details the different applications of AI and machine learning algorithms in MASLD, particularly in analyzing electronic health record, digital pathology, and imaging data. Additionally, it also describes how specific MASLD consortia are leveraging multimodal data sources to spark research breakthroughs in the field. Using a new national-level 'data commons' (SteatoSITE) as an exemplar, the opportunities, as well as the technical challenges of large-scale databases in MASLD research, are highlighted.

Object detection: A novel AI technology for the diagnosis of hepatocyte ballooning

Metabolic dysfunction-associated fatty liver disease (MAFLD) has reached epidemic proportions worldwide and is the most frequent cause of chronic liver disease in developed countries. Within the spectrum of liver disease in MAFLD, steatohepatitis is a progressive form of liver disease and hepatocyte ballooning (HB) is a cardinal pathological feature of steatohepatitis. The accurate and reproducible diagnosis of HB is therefore critical for the early detection and treatment of steatohepatitis. Currently, a diagnosis of HB relies on pathological examination by expert pathologists, which may be a time-consuming and subjective process. Hence, there has been interest in developing automated methods for diagnosing HB. This narrative review briefly discusses the development of artificial intelligence (AI) technology for diagnosing fatty liver disease pathology over the last 30 years and provides an overview of the current research status of AI algorithms for the identification of HB, including published articles on traditional machine learning algorithms and deep learning algorithms. This narrative review also provides a summary of object detection algorithms, including the principles, historical developments, and applications in the medical image analysis. The potential benefits of object detection algorithms for HB diagnosis (specifically those combined with a transformer architecture) are discussed, along with the future directions of object detection algorithms in HB diagnosis and the potential applications of generative AI on transformer architecture in this field. In conclusion, object detection algorithms have huge potential for the identification of HB and could make the diagnosis of MAFLD more accurate and efficient in the near future.

Artificial intelligence-assisted digital pathology for non-alcoholic steatohepatitis: current status and future directions

The worldwide prevalence of non-alcoholic steatohepatitis (NASH) is increasing, causing a significant medical burden, but no approved therapeutics are currently available. NASH drug development requires histological analysis of liver biopsies by expert pathologists for trial enrolment and efficacy assessment, which can be hindered by multiple issues including sample heterogeneity, inter-reader and intra-reader variability, and ordinal scoring systems. Consequently, there is a high unmet need for accurate, reproducible, quantitative, and automated methods to assist pathologists with histological analysis to improve the precision around treatment and efficacy assessment. Digital pathology (DP) workflows in combination with artificial intelligence (AI) have been established in other areas of medicine and are being actively investigated in NASH to assist pathologists in the evaluation and scoring of NASH histology. DP/AI models can be used to automatically detect, localise, quantify, and score histological parameters and have the potential to reduce the impact of scoring variability in NASH clinical trials. This narrative review provides an overview of DP/AI tools in development for NASH, highlights key regulatory considerations, and discusses how these advances may impact the future of NASH clinical management and drug development. This should be a high priority in the NASH field, particularly to improve the development of safe and effective therapeutics.

Liver fibrosis phenotyping and severity scoring by quantitative image analysis of biopsy slides

BACKGROUND & AIMS

Digital pathology image analysis can phenotype liver fibrosis using histological traits that reflect collagen content, morphometry and architecture. Here, we aimed to calculate fibrosis severity scores to quantify these traits.

METHODS

Liver biopsy slides were categorised by Ishak stage and aetiology. We used a digital pathology technique to calculate four fibrosis severity scores: Architecture Composite Score (ACS), Collagen Composite Score (CCS), Morphometric Composite Score (MCS) and Phenotypic Fibrosis Composite Score (PH-FCS). We compared how these scores varied according to disease stage and aetiology.

RESULTS

We included 80 patients (40% female, mean age 59.0 years, mean collagen proportionate area 17.1%) with mild (F0-2, n = 28), moderate (F3-4, n = 17) or severe (F5-6, n = 35) fibrosis. All four aetiology independent scores corelated with collagen proportionate area (ACS: rp  = .512, CCS: rp  = .727, MCS: rp  = .777, PFCS: r = .772, p < .01 for all) with significant differences between moderate and severe fibrosis (p < .05). ACS increased primarily between moderate and severe fibrosis (by 95% to 226% depending on underlying aetiology), whereas MCS and CCS accumulation was more varied. We used 28 qFTs that distinguished between autoimmune- and alcohol-related liver disease to generate an MCS that significantly differed between mild and severe fibrosis for these aetiologies (p < .05).

CONCLUSIONS

We describe four aetiology-dependent and -independent severity scores that quantify fibrosis architecture, collagen content and fibre morphometry. This approach provides additional insight into how progression of architectural changes and accumulation of collagen may differ depending on underlying disease aetiology.

Design of the phase 3 MAESTRO clinical program to evaluate resmetirom for the treatment of nonalcoholic steatohepatitis

BACKGROUND

Non-alcoholic steatohepatitis (NASH) is a progressive form of non-alcoholic fatty liver disease (NAFLD) associated with steatosis, hepatocellular injury, inflammation and fibrosis. In a Phase 2 trial in adults with NASH (NCT02912260), resmetirom, an orally administered, liver-targeted thyroid hormone receptor-β selective agonist, significantly reduced hepatic fat (via imaging) and resolved NASH without worsening fibrosis (via liver biopsy) in a significant number of patients compared with placebo.

AIMS

To present the design of the Phase 3 MAESTRO clinical programme evaluating resmetirom for treatment of NASH (MAESTRO-NAFLD-1 [NCT04197479], MAESTRO-NAFLD-OLE [NCT04951219], MAESTRO-NASH [NCT03900429], MAESTRO-NASH-OUTCOMES [NCT05500222]).

METHODS

MAESTRO-NASH is a pivotal serial biopsy trial in up to 2000 adults with biopsy-confirmed at-risk NASH. Patients are randomised to a once-daily oral placebo, 80 mg resmetirom, or 100 mg resmetirom. Liver biopsies are conducted at screening, week 52 and month 54. MAESTRO-NAFLD-1 is a 52-week safety trial in ~1400 adults with NAFLD/presumed NASH (based on non-invasive testing); ~700 patients from MAESTRO-NAFLD-1 are enrolled in MAESTRO-NAFLD-OLE, a 52-week active treatment extension to further evaluate safety. MAESTRO-NASH-OUTCOMES is enrolling 700 adults with well-compensated NASH cirrhosis to evaluate the potential for resmetirom to slow progression to hepatic decompensation events. Non-invasive tests (biomarkers, imaging) are assessed longitudinally throughout, in addition to validated patient-reported outcomes.

CONCLUSION

The MAESTRO clinical programme was designed in conjunction with regulatory authorities to support approval of resmetirom for treatment of NASH. The surrogate endpoints, based on week 52 liver biopsy, serum biomarkers and imaging, are confirmed by long-term clinical liver-related outcomes in MAESTRO-NASH (month 54) and MAESTRO-NASH-OUTCOMES (time to event).

Digital pathology for nonalcoholic steatohepatitis assessment

Histological assessment of nonalcoholic fatty liver disease (NAFLD) has anchored knowledge development about the phenotypes of the condition, their natural history and their clinical course. This fact has led to the use of histological assessment as a reference standard for the evaluation of efficacy of drug interventions for nonalcoholic steatohepatitis (NASH) - the more histologically active form of NAFLD. However, certain limitations of conventional histological assessment systems pose challenges in drug development. These limitations have spurred intense scientific and commercial development of machine learning and digital approaches towards the assessment of liver histology in patients with NAFLD. This research field remains an area in rapid evolution. In this Perspective article, we summarize the current conventional assessment of NASH and its limitations, the use of specific digital approaches for histological assessment, and their application to the study of NASH and its response to therapy. Although this is not a comprehensive review, the leading tools currently used to assess therapeutic efficacy in drug development are specifically discussed. The potential translation of these approaches to support routine clinical assessment of NAFLD and an agenda for future research are also discussed.

Survey of liver pathologists to assess attitudes towards digital pathology and artificial intelligence

AIMS

A survey of members of the UK Liver Pathology Group (UKLPG) was conducted, comprising consultant histopathologists from across the UK who report liver specimens and participate in the UK National Liver Pathology External Quality Assurance scheme. The aim of this study was to understand attitudes and priorities of liver pathologists towards digital pathology and artificial intelligence (AI).

METHODS

The survey was distributed to all full consultant members of the UKLPG via email. This comprised 50 questions, with 48 multiple choice questions and 2 free-text questions at the end, covering a range of topics and concepts pertaining to the use of digital pathology and AI in liver disease.

RESULTS

Forty-two consultant histopathologists completed the survey, representing 36% of fully registered members of the UKLPG (42/116). Questions examining digital pathology showed respondents agreed with the utility of digital pathology for primary diagnosis 83% (34/41), second opinions 90% (37/41), research 85% (35/41) and training and education 95% (39/41). Fatty liver diseases were an area of demand for AI tools with 80% in agreement (33/41), followed by neoplastic liver diseases with 59% in agreement (24/41). Participants were concerned about AI development without pathologist involvement 73% (30/41), however, 63% (26/41) disagreed when asked whether AI would replace pathologists.

CONCLUSIONS

This study outlines current interest, priorities for research and concerns around digital pathology and AI for liver pathologists. The majority of UK liver pathologists are in favour of the application of digital pathology and AI in clinical practice, research and education.

Leukotriene B4 receptor 1 (BLT1) does not mediate disease progression in a mouse model of liver fibrosis

MASH is a prevalent liver disease that can progress to fibrosis, cirrhosis, hepatocellular carcinoma (HCC), and ultimately death, but there are no approved therapies. Leukotriene B4 (LTB4) is a potent pro-inflammatory chemoattractant that drives macrophage and neutrophil chemotaxis, and genetic loss or inhibition of its high affinity receptor, leukotriene B4 receptor 1 (BLT1), results in improved insulin sensitivity and decreased hepatic steatosis. To validate the therapeutic efficacy of BLT1 inhibition in an inflammatory and pro-fibrotic mouse model of MASH and fibrosis, mice were challenged with a choline-deficient, L-amino acid defined high fat diet and treated with a BLT1 antagonist at 30 or 90 mg/kg for 8 weeks. Liver function, histology, and gene expression were evaluated at the end of the study. Treatment with the BLT1 antagonist significantly reduced plasma lipids and liver steatosis but had no impact on liver injury biomarkers or histological endpoints such as inflammation, ballooning, or fibrosis compared to control. Artificial intelligence-powered digital pathology analysis revealed a significant reduction in steatosis co-localized fibrosis in livers treated with the BLT1 antagonist. Liver RNA-seq and pathway analyses revealed significant changes in fatty acid, arachidonic acid, and eicosanoid metabolic pathways with BLT1 antagonist treatment, however, these changes were not sufficient to impact inflammation and fibrosis endpoints. Targeting this LTB4-BLT1 axis with a small molecule inhibitor in animal models of chronic liver disease should be considered with caution, and additional studies are warranted to understand the mechanistic nuances of BLT1 inhibition in the context of MASH and liver fibrosis.

Clinical trial: Effects of pegozafermin on the liver and on metabolic comorbidities in subjects with biopsy-confirmed nonalcoholic steatohepatitis

BACKGROUND

An approved therapy for nonalcoholic steatohepatitis (NASH) and fibrosis remains a major unmet medical need.

AIM

To investigate the histological and metabolic benefits of pegozafermin, a glycoPEGylated FGF21 analogue, in subjects with biopsy-confirmed NASH.

METHODS

This proof-of-concept, open-label, single-cohort study, part 2 of a phase 1b/2a clinical trial, was conducted at 16 centres in the United States. Adults (age 21-75 years) with NASH (stage 2 or 3 fibrosis, NAS≥4) and magnetic resonance imaging proton density fat fraction (MRI-PDFF) ≥8% received subcutaneous pegozafermin 27 mg once weekly for 20 weeks. Primary outcomes were improvements in liver histology, and safety and tolerability.

RESULTS

Of 20 enrolled subjects, 19 completed the study. Twelve subjects (63%) met the primary endpoint of ≥2-point improvement in NAFLD activity score with ≥1-point improvement in ballooning or lobular inflammation and no worsening of fibrosis. Improvement of fibrosis without worsening of NASH was observed in 26% of subjects, and NASH resolution without worsening of fibrosis in 32%. Least-squares mean relative change from baseline in MRI-PDFF was -64.7% (95% CI: -71.7, -57.7; p < 0.0001). Significant improvements from baseline were also seen in serum aminotransferases, noninvasive fibrosis tests, serum lipids, glycaemic control and body weight. Adverse events (AEs) were reported in 18 subjects (90%). The most frequently reported AEs were mild/moderate nausea and diarrhoea. There were no serious AEs, discontinuations due to AEs, or deaths.

CONCLUSIONS

Pegozafermin treatment for 20 weeks had beneficial effects on hepatic and metabolic parameters and was well tolerated in subjects with NASH.

CLINICALTRIALS

gov: NCT04048135.

Tropifexor plus cenicriviroc combination versus monotherapy in nonalcoholic steatohepatitis: Results from the phase 2b TANDEM study

BACKGROUND AND AIMS

With distinct mechanisms of action, the combination of tropifexor (TXR) and cenicriviroc (CVC) may provide an effective treatment for NASH. This randomized, multicenter, double-blind, phase 2b study assessed the safety and efficacy of TXR and CVC combination, compared with respective monotherapies.

APPROACH AND RESULTS

Patients (N = 193) were randomized 1:1:1:1 to once-daily TXR 140 μg (TXR 140 ), CVC 150 mg (CVC), TXR 140 μg + CVC 150 mg (TXR 140 + CVC), or TXR 90 μg + CVC 150 mg (TXR 90 + CVC) for 48 weeks. The primary and secondary end points were safety and histological improvement, respectively. Rates of adverse events (AEs) were similar across treatment groups. Pruritus was the most frequently experienced AE, with highest incidence in the TXR 140 group (40.0%). In TXR and combination groups, alanine aminotransferase (ALT) decreased from baseline to 48 weeks (geometric mean change: -21%, TXR 140 ; -16%, TXR 140 + CVC; -13%, TXR 90 + CVC; and +17%, CVC). Reductions in body weight observed at week 24 (mean changes from baseline: TXR 140 , -2.5 kg; TXR 140 + CVC, -1.7 kg; TXR 90 + CVC, -1.0 kg; and CVC, -0.1 kg) were sustained to week 48. At least 1-point improvement in fibrosis stage/steatohepatitis resolution without worsening of fibrosis was observed in 32.3%/25.8%, 31.6%/15.8%, 29.7%/13.5%, and 32.5%/22.5% of patients in the TXR 140 , CVC, TXR 140 + CVC, and TXR 90 + CVC groups, respectively.

CONCLUSIONS

The safety profile of TXR + CVC combination was similar to respective monotherapies, with no new signals. TXR monotherapy showed sustained ALT and body weight decreases. No substantial incremental efficacy was observed with TXR + CVC combination on ALT, body weight, or in histological end points compared with monotherapy.

AutoFibroNet: A deep learning and multi-photon microscopy-derived automated network for liver fibrosis quantification in MAFLD

BACKGROUND

Liver fibrosis is the strongest histological risk factor for liver-related complications and mortality in metabolic dysfunction-associated fatty liver disease (MAFLD). Second harmonic generation/two-photon excitation fluorescence (SHG/TPEF) is a powerful tool for label-free two-dimensional and three-dimensional tissue visualisation that shows promise in liver fibrosis assessment.

AIM

To investigate combining multi-photon microscopy (MPM) and deep learning techniques to develop and validate a new automated quantitative histological classification tool, named AutoFibroNet (Automated Liver Fibrosis Grading Network), for accurately staging liver fibrosis in MAFLD.

METHODS

AutoFibroNet was developed in a training cohort that consisted of 203 Chinese adults with biopsy-confirmed MAFLD. Three deep learning models (VGG16, ResNet34, and MobileNet V3) were used to train pre-processed images and test data sets. Multi-layer perceptrons were used to fuse data (deep learning features, clinical features, and manual features) to build a joint model. This model was then validated in two further independent cohorts.

RESULTS

AutoFibroNet showed good discrimination in the training set. For F0, F1, F2 and F3-4 fibrosis stages, the area under the receiver operating characteristic curves (AUROC) of AutoFibroNet were 1.00, 0.99, 0.98 and 0.98. The AUROCs of F0, F1, F2 and F3-4 fibrosis stages for AutoFibroNet in the two validation cohorts were 0.99, 0.83, 0.80 and 0.90 and 1.00, 0.83, 0.80 and 0.94, respectively, showing a good discriminatory ability in different cohorts.

CONCLUSION

AutoFibroNet is an automated quantitative tool that accurately identifies histological stages of liver fibrosis in Chinese individuals with MAFLD.

Recent advances in fibrosis assessment for metabolic dysfunction-associated fatty liver disease

This article is linked to Zhan et al papers. To view these articles, visit https://doi.org/10.1111/apt.17635 and https://doi.org/10.1111/apt.17660

Identification of key modules and driving genes in nonalcoholic fatty liver disease by weighted gene co-expression network analysis

BACKGROUND

Nonalcoholic fatty liver disease (NAFLD) is characterized by excessive liver fat deposition, and progresses to liver cirrhosis, and even hepatocellular carcinoma. However, the invasive diagnosis of NAFLD with histopathological evaluation remains risky. This study investigated potential genes correlated with NAFLD, which may serve as diagnostic biomarkers and even potential treatment targets.

METHODS

The weighted gene co-expression network analysis (WGCNA) was constructed based on dataset E-MEXP-3291. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were performed to evaluate the function of genes.

RESULTS

Blue module was positively correlated, and turquoise module negatively correlated with the severity of NAFLD. Furthermore, 8 driving genes (ANXA9, FBXO2, ORAI3, NAGS, C/EBPα, CRYAA, GOLM1, TRIM14) were identified from the overlap of genes in blue module and GSE89632. And another 8 driving genes were identified from the overlap of turquoise module and GSE89632. Among these driving genes, C/EBPα (CCAAT/enhancer binding protein α) was the most notable. By validating the expression of C/EBPα in the liver of NAFLD mice using immunohistochemistry, we discovered a significant upregulation of C/EBPα protein in NAFLD.

CONCLUSION

we identified two modules and 16 driving genes associated with the progression of NAFLD, and confirmed the protein expression of C/EBPα, which had been paid little attention to in the context of NAFLD, in the present study. Our study will advance the understanding of NAFLD. Moreover, these driving genes may serve as biomarkers and therapeutic targets of NAFLD.

Collagen co-localized with macrovesicular steatosis better differentiates fibrosis progression in non-alcoholic fatty liver disease mouse models

Background

Non-alcoholic fatty liver disease (NAFLD) is a global commonly occurring liver disease. However, its exact pathogenesis is not fully understood. The purpose of this study was to quantitatively evaluate the progression of steatosis and fibrosis by examining their distribution, morphology, and co-localization in NAFLD animal models.

Methods

Six mouse NAFLD groups were established: (1) western diet (WD) group; (2) WD with fructose in drinking water (WDF) group; (3) WDF + carbon tetrachloride (CCl4) group, WDF plus intraperitoneal injection of CCl4; (4) high-fat diet (HFD) group, (5) HFD with fructose (HFDF) group; and (6) HFDF + CCl4 group, HFDF plus intraperitoneal injection of CCl4. Liver tissue specimens from NAFLD model mice were collected at different time points. All the tissues were serially sectioned for histological staining and second-harmonic generation (SHG)/two-photon excitation fluorescence imaging (TPEF) imaging. The progression of steatosis and fibrosis was analyzed using SHG/TPEF quantitative parameters with respect to the non-alcoholic steatohepatitis Clinical Research Network scoring system.

Results

qSteatosis showed a good correlation with steatosis grade (R: 0.823-0.953, p < 0.05) and demonstrated high performance (area under the curve [AUC]: 0.617-1) in six mouse models. Based on their high correlation with histological scoring, qFibrosis containing four shared parameters (#LongStrPS, #ThinStrPS, #ThinStrPSAgg, and #LongStrPSDis) were selected to create a linear model that could accurately identify differences among fibrosis stages (AUC: 0.725-1). qFibrosis co-localized with macrosteatosis generally correlated better with histological scoring and had a higher AUC in six animal models (AUC: 0.846-1).

Conclusion

Quantitative assessment using SHG/TPEF technology can be used to monitor different types of steatosis and fibrosis progression in NAFLD models. The collagen co-localized with macrosteatosis could better differentiate fibrosis progression and might aid in developing a more reliable and translatable fibrosis evaluation tool for animal models of NAFLD.

Automated Segmentation and Morphological Characterization of Hepatic Steatosis and Correlation with Histopathology

Background/objectives

Prevalence of nonalcoholic fatty liver disease (NAFLD) has increased to 25% of the world population. Hepatic steatosis is a hallmark feature of NAFLD and is assessed histologically using visual and ordinal fat grading criteria (0-3) from the Nonalcoholic Steatohepatitis (NASH) Clinical Research Network (CRN) scoring system. The purpose of this study is to automatically segment and extract morphological characteristics and distributions of fat droplets (FDs) on liver histology images and find associations with severity of steatosis.

Methods

A previously published human cohort of 68 NASH candidates was graded for steatosis by an experienced pathologist using the Fat CRN grading system. The automated segmentation algorithm quantified fat fraction (FF) and fat-affected hepatocyte ratio (FHR), extracted fat morphology by calculating radius and circularity of FDs, and examined FDs distribution and heterogeneity using nearest neighbor distance and regional isotropy.

Results

Regression analysis and Spearman correlation (ρ) yielded high correlations for radius (R2 = 0.86, ρ = 0.72), nearest neighbor distance (R2 = 0.82, ρ = -0.82), regional isotropy (R2 = 0.84, ρ = 0.74), and FHR (R2 = 0.90, ρ = 0.85), and low correlation for circularity (R2 = 0.48, ρ = -0.32) with FF and pathologist grades, respectively. FHR showed a better distinction between pathologist Fat CRN grades compared to conventional FF measurements, making it a potential surrogate measure for Fat CRN scores. Our results showed variation in distribution of morphological features and steatosis heterogeneity within the same patient's biopsy sample as well as between patients of similar FF.

Conclusions

The fat percentage measurements, specific morphological characteristics, and patterns of distribution quantified with the automated segmentation algorithm showed associations with steatosis severity; however, future studies are warranted to evaluate the clinical significance of these steatosis features in progression of NAFLD and NASH.

Machine learning liver histology scores correlate with portal hypertension assessments in nonalcoholic steatohepatitis cirrhosis

BACKGROUND AND AIMS

In cirrhotic nonalcoholic steatohepatitis (NASH) clinical trials, primary efficacy endpoints have been hepatic venous pressure gradient (HVPG), liver histology and clinical liver outcomes. Important histologic features, such as septa thickness, nodules features and fibrosis area have not been included in the histologic assessment and may have important clinical relevance. We assessed these features with a machine learning (ML) model.

METHODS

NASH patients with compensated cirrhosis and HVPG ≥6 mm Hg (n = 143) from the Belapectin phase 2b trial were studied. Liver biopsies, HVPG measurements and upper endoscopies were performed at baseline and at end of treatment (EOT). A second harmonic generation/two-photon excitation fluorescence provided an automated quantitative assessment of septa, nodules and fibrosis (SNOF). We created ML scores and tested their association with HVPG, clinically significant HVPG (≥10 mm Hg) and the presence of varices (SNOF-V).

RESULTS

We derived 448 histologic variables (243 related to septa, 21 related to nodules and 184 related to fibrosis). The SNOF score (≥11.78) reliably distinguished CSPH at baseline and in the validation cohort (baseline + EOT) [AUC = 0.85 and 0.74, respectively]. The SNOF-V score (≥0.57) distinguished the presence of varices at baseline and in the same validation cohort [AUC = 0.86 and 0.73, respectively]. Finally, the SNOF-C score differentiated those who had >20% change in HVPG against those who did not, with an AUROC of 0.89.

CONCLUSION

The ML algorithm accurately predicted HVPG, CSPH, the development of varices and HVPG changes in patients with NASH cirrhosis. The use of ML histology model in NASH cirrhosis trials may improve the assessment of key outcome changes.

Non-invasive imaging biomarkers for liver steatosis in non-alcoholic fatty liver disease: present and future

Non-alcoholic fatty liver disease is currently the most common chronic liver disease, affecting up to 25% of the global population. Simple fatty liver, in which fat is deposited in the liver without fibrosis, has been regarded as a benign disease in the past, but it is now known to be prognostic. In the future, more emphasis should be placed on the quantification of liver fat. Traditionally, fatty liver has been assessed by histological evaluation, which requires an invasive examination; however, technological innovations have made it possible to evaluate fatty liver by non-invasive imaging methods, such as ultrasonography, computed tomography, and magnetic resonance imaging. In addition, quantitative as well as qualitative measurements for the detection of fatty liver have become available. In this review, we summarize the currently used qualitative evaluations of fatty liver and discuss quantitative evaluations that are expected to further develop in the future.

Non-alcoholic fatty liver disease: the pathologist's perspective

Non-alcoholic fatty liver disease (NAFLD) is a spectrum of diseases characterized by fatty accumulation in hepatocytes, ranging from steatosis, non-alcoholic steatohepatitis, to cirrhosis. While histopathological evaluation of liver biopsies plays a central role in the diagnosis of NAFLD, limitations such as the problem of interobserver variability still exist and active research is underway to improve the diagnostic utility of liver biopsies. In this article, we provide a comprehensive overview of the histopathological features of NAFLD, the current grading and staging systems, and discuss the present and future roles of liver biopsies in the diagnosis and prognostication of NAFLD.

Tropifexor for nonalcoholic steatohepatitis: an adaptive, randomized, placebo-controlled phase 2a/b trial

The multimodal activities of farnesoid X receptor (FXR) agonists make this class an attractive option to treat nonalcoholic steatohepatitis. The safety and efficacy of tropifexor, an FXR agonist, in a randomized, multicenter, double-blind, three-part adaptive design, phase 2 study, in patients with nonalcoholic steatohepatitis were therefore assessed. In Parts A + B, 198 patients were randomized to receive tropifexor (10-90 μg) or placebo for 12 weeks. In Part C, 152 patients were randomized to receive tropifexor 140 µg, tropifexor 200 µg or placebo (1:1:1) for 48 weeks. The primary endpoints were safety and tolerability to end-of-study, and dose response on alanine aminotransferase (ALT), aspartate aminotransferase (AST) and hepatic fat fraction (HFF) at week 12. Pruritus was the most common adverse event in all groups, with a higher frequency in the 140- and 200-µg tropifexor groups. Decreases from baseline in ALT and HFF were greater with tropifexor versus placebo at week 12, with a relative decrease in least squares mean from baseline observed with all tropifexor doses for ALT (tropifexor 10-90-μg dose groups ranged from -10.7 to -16.5 U l-1 versus placebo (-7.8 U l-1) and tropifexor 140- and 200-μg groups were -18.0 U l-1 and -23.0 U l-1, respectively, versus placebo (-8.3 U l-1)) and % HFF (tropifexor 10-90-μg dose groups ranged from -7.48% to -15.04% versus placebo (-6.19%) and tropifexor 140- and 200-μg groups were -19.07% and -39.41%, respectively, versus placebo (-10.77%)). Decreases in ALT and HFF were sustained up to week 48; however, similar trends in AST with tropifexor at week 12 were not observed. As with other FXR agonists, dose-related pruritus was frequently observed. Clinicaltrials.gov registration: NCT02855164.

Surveillance of the progression and assessment of treatment endpoints for nonalcoholic steatohepatitis

Nonalcoholic steatohepatitis (NASH) is an aggressive form of nonalcoholic fatty liver disease (NAFLD) characterized by steatosis-associated inflammation and liver injury. Without effective treatment or management, NASH can have life-threatening outcomes. Evaluation and identification of NASH patients at risk for adverse outcomes are therefore important. Key issues in screening NASH patients are the assessment of advanced fibrosis, differentiation of NASH from simple steatosis, and monitoring of dynamic changes during follow-up and treatment. Currently, NASH staging and evaluation of the effectiveness for drugs still rely on pathological diagnosis, despite sample error issues and the subjectivity associated with liver biopsy. Optimizing the pathological assessment of liver biopsy samples and developing noninvasive surrogate methods for accessible, accurate, and safe evaluation are therefore critical. Although noninvasive methods including elastography, serum soluble biomarkers, and combined models have been implemented in the last decade, noninvasive diagnostic measurements are not widely applied in clinical practice. More work remains to be done in establishing cost-effective strategies both for screening for at-risk NASH patients and identifying changes in disease severity. In this review, we summarize the current state of noninvasive methods for detecting steatosis, steatohepatitis, and fibrosis in patients with NASH, and discuss noninvasive assessments for screening at-risk patients with a focus on the characteristics that should be monitored at follow-up.

Non-invasive biomarkers for liver inflammation in non-alcoholic fatty liver disease: present and future

Inflammation is the key driver of liver fibrosis progression in non-alcoholic fatty liver disease (NAFLD). Unfortunately, it is often challenging to assess inflammation in NAFLD due to its dynamic nature and poor correlation with liver biochemical markers. Liver histology keeps its role as the standard tool, yet it is well-known for substantial sampling, intraobserver, and interobserver variability. Serum proinflammatory cytokines and apoptotic markers, namely cytokeratin-18, are well-studied with reasonable accuracy, whereas serum metabolomics and lipidomics have been adopted in some commercially available diagnostic models. Ultrasound and computed tomography imaging techniques are attractive due to their wide availability; yet their accuracies may not be comparable with magnetic resonance imaging-based tools. Machine learning and deep learning models, be they supervised or unsupervised learning, are promising tools to identify various subtypes of NAFLD, including those with dominating liver inflammation, contributing to sustainable care pathways for NAFLD.

Zonated quantification of immunohistochemistry in normal and steatotic livers

Immunohistochemical stains (IHC) reveal differences between liver lobule zones in health and disease, including nonalcoholic fatty liver disease (NAFLD). However, such differences are difficult to accurately quantify. In NAFLD, the presence of lipid vacuoles from macrovesicular steatosis further hampers interpretation by pathologists. To resolve this, we applied a zonal image analysis method to measure the distribution of hypoxia markers in the liver lobule of steatotic livers.The hypoxia marker pimonidazole was assessed with IHC in the livers of male C57BL/6 J mice on standard diet or choline-deficient L-amino acid-defined high-fat diet mimicking NAFLD. Another hypoxia marker, carbonic anhydrase IX, was evaluated by IHC in human liver tissue. Liver lobules were reconstructed in whole slide images, and staining positivity was quantified in different zones in hundreds of liver lobules. This method was able to quantify the physiological oxygen gradient along hepatic sinusoids in normal livers and panlobular spread of the hypoxia in NAFLD and to overcome the pronounced impact of macrovesicular steatosis on IHC. In a proof-of-concept study with an assessment of the parenchyma between centrilobular veins in human liver biopsies, carbonic anhydrase IX could be quantified correctly as well.The method of zonated quantification of IHC objectively quantifies the difference in zonal distribution of hypoxia markers (used as an example) between normal and NAFLD livers both in whole liver as well as in liver biopsy specimens. It constitutes a tool for liver pathologists to support visual interpretation and estimate the impact of steatosis on IHC results.

The role of altered lipid composition and distribution in liver fibrosis revealed by multimodal nonlinear optical microscopy

Intracellular lipid accumulation is commonly seen in fibrotic livers, but its exact role in liver fibrosis remains elusive. Here, we established a multimodal nonlinear optical microscopy to quantitatively map distribution of biomolecules in fibrotic livers. Our data revealed that unsaturated triglycerides were predominantly accumulated in central vein area during liver fibrosis but not in portal vein area. Moreover, the lipid homeostasis was remarkably dysregulated in the late-stage compared to the early-stage fibrosis, including increased unsaturated triglycerides with decreased lipid unsaturation degree and decreased membrane fluidity. Such alterations were likely due to up-regulated lipogenesis, desaturation, and peroxidation, which consequently led to endoplasmic reticulum stress and cell death. Inspiringly, injured hepatocyte could be rescued by remodeling lipid homeostasis via either supply of unsaturated fatty acids or enhancement of membrane fluidity. Collectively, our study improves current understanding of the role of lipid homeostasis in fibrosis and open opportunities for treatment.

Second-Harmonic Generated Quantifiable Fibrosis Parameters Provide Signatures for Disease Progression and Regression in Nonalcoholic Fatty Liver Disease

Introduction:

The current ordinal fibrosis staging system for nonalcoholic steatohepatitis (NASH) has a limited dynamic range. The goal of this study was to determine if second-harmonic generated (SHG) quantifiable collagen fibrillar properties (qFP) and their derived qFibrosis score capture changes in disease progression and regression in a murine model of NASH, in which disease progression can be induced by a high fat sugar water (HFSW) diet and regression by reversal to chow diet (CD).

Methods:

DIAMOND mice were fed a CD or HFSW diet for 40 to 52 weeks. Regression related changes were studied in mice with diet reversal for 4 weeks after 48 to 60 weeks of a HFSW diet.

Results:

As expected, mice on HFSW developed steatohepatitis with stage 2 to 3 fibrosis between weeks 40 and 44. Both the collagen proportionate area and the qFibrosis score based on 15 SHG-quantified collagen fibrillar properties in humans were significantly higher in mice on HFSW for 40 to 44 weeks compared to CD fed mice. These changes were greatest in the sinusoids (Zone 2) with further increase in septal and portal fibrosis related scores between weeks 44 and 48. Diet reversal led to decrease in qFibrosis, septal thickness, and cellularity with greatest changes in Zone 2. Specific qFPs associated with progression only, regression only, or both processes were identified and categorized based on direction of fibrosis change.

Conclusion:

Complementing recent human studies, these findings support the concept that changes of disease progression and regression can be assessed using SHG-based image quantification of fibrosis related parameters.

Artificial Intelligence in NAFLD: Will Liver Biopsy Still Be Necessary in the Future?

As the advanced form of nonalcoholic fatty liver disease (NAFLD), nonalcoholic steatohepatitis (NASH) will significantly increase the risks of liver fibrosis, cirrhosis, and HCC. However, there is no non-invasive method to distinguish NASH from NAFLD so far. Additionally, liver biopsy remains the gold standard to diagnose NASH, which is not appropriate for routine screening. Recently, artificial intelligence (AI) is under rapid development in many aspects of medicine. Additionally, the application of AI in clinical information may have the potential to diagnose NASH non-invasively. This review summarizes the latest research using AI, specifically machine learning, to facilitate the diagnosis, prognosis, and monitoring of NAFLD. Additionally, according to our prior results, this work proposes future development in this area.

A researcher's guide to preclinical mouse NASH models

Non-alcoholic fatty liver disease (NAFLD) and its inflammatory form, non-alcoholic steatohepatitis (NASH), have quickly risen to become the most prevalent chronic liver disease in the Western world and are risk factors for the development of hepatocellular carcinoma (HCC). HCC is not only one of the most common cancers but is also highly lethal. Nevertheless, there are currently no clinically approved drugs for NAFLD, and NASH-induced HCC poses a unique metabolic microenvironment that may influence responsiveness to certain treatments. Therefore, there is an urgent need to better understand the pathogenesis of this rampant disease to devise new therapies. In this line, preclinical mouse models are crucial tools to investigate mechanisms as well as novel treatment modalities during the pathogenesis of NASH and subsequent HCC in preparation for human clinical trials. Although, there are numerous genetically induced, diet-induced and toxin-induced models of NASH, not all of these models faithfully phenocopy and mirror the human pathology very well. In this Perspective, we shed some light onto the most widely used mouse models of NASH and highlight some of the key advantages and disadvantages of the various models with an emphasis on 'Western diets', which are increasingly recognized as some of the best models in recapitulating the human NASH pathology and comorbidities.

Digital pathology with artificial intelligence analyses provides greater insights into treatment-induced fibrosis regression in NASH

BACKGROUND & AIMS

Liver fibrosis is a key prognostic determinant for clinical outcomes in non-alcoholic steatohepatitis (NASH). Current scoring systems have limitations, especially in assessing fibrosis regression. Second harmonic generation/two-photon excitation fluorescence (SHG/TPEF) microscopy with artificial intelligence analyses provides standardized evaluation of NASH features, especially liver fibrosis and collagen fiber quantitation on a continuous scale. This approach was applied to gain in-depth understanding of fibrosis dynamics after treatment with tropifexor (TXR), a non-bile acid farnesoid X receptor agonist in patients participating in the FLIGHT-FXR study (NCT02855164).

METHOD

Unstained sections from 198 liver biopsies (paired: baseline and end-of-treatment) from 99 patients with NASH (fibrosis stage F2 or F3) who received placebo (n = 34), TXR 140 μg (n = 37), or TXR 200 μg (n = 28) for 48 weeks were examined. Liver fibrosis (qFibrosis®), hepatic fat (qSteatosis®), and ballooned hepatocytes (qBallooning®) were quantitated using SHG/TPEF microscopy. Changes in septa morphology, collagen fiber parameters, and zonal distribution within liver lobules were also quantitatively assessed.

RESULTS

Digital analyses revealed treatment-associated reductions in overall liver fibrosis (qFibrosis®), unlike conventional microscopy, as well as marked regression in perisinusoidal fibrosis in patients who had either F2 or F3 fibrosis at baseline. Concomitant zonal quantitation of fibrosis and steatosis revealed that patients with greater qSteatosis reduction also have the greatest reduction in perisinusoidal fibrosis. Regressive changes in septa morphology and reduction in septa parameters were observed almost exclusively in F3 patients, who were adjudged as 'unchanged' with conventional scoring.

CONCLUSION

Fibrosis regression following hepatic fat reduction occurs initially in the perisinusoidal regions, around areas of steatosis reduction. Digital pathology provides new insights into treatment-induced fibrosis regression in NASH, which are not captured by current staging systems.

LAY SUMMARY

The degree of liver fibrosis (tissue scarring) in non-alcoholic steatohepatitis (NASH) is the main predictor of negative clinical outcomes. Accurate assessment of the quantity and architecture of liver fibrosis is fundamental for patient enrolment in NASH clinical trials and for determining treatment efficacy. Using digital microscopy with artificial intelligence analyses, the present study demonstrates that this novel approach has greater sensitivity in demonstrating treatment-induced reversal of fibrosis in the liver than current systems. Furthermore, additional details are obtained regarding the pathogenesis of NASH disease and the effects of therapy.

Efficacy and Safety of a Botanical Formula Fuzheng Huayu for Hepatic Fibrosis in Patients with CHC: Results of a Phase 2 Clinical Trial

Background. Hepatitis C virus (HCV) is a common cause of progressive hepatic fibrosis, cirrhosis, and hepatocellular carcinoma worldwide. Despite the availability of effective direct-acting antivirals, patients often have significant hepatic fibrosis at the time of diagnosis due to delay in diagnosis and comorbidities which promote fibrogenesis. Thus, antifibrotic agents represent an attractive adjunctive therapy. Fuzheng Huayu (FZHY), a traditional Chinese medicine botanical formulation, has been used as an antifibrotic agent in chronic HBV infection. Our aim was to assess FZHY in patients with HCV infection and active viremia. Method. We randomized 118 patients with active viremia from 8 liver centers in the U.S. to receive oral FZHY (n = 59) or placebo (n = 59) for 48 weeks. Efficacy was assessed by histopathologic changes at the end of therapy. A subset of biopsies was further analyzed using qFibrosis to detect subtle changes in fibrosis in different zones of the hepatic lobules. Results. FZHY was well tolerated and safe. Patients with baseline Ishak fibrosis stages F3 and F4 had better response rates to FZHY than patients with baseline F0–F2 ( $p=0.03$ ). qFibrosis zonal analysis showed significant improvement in fibrosis in all zones in patients with regression of the fibrosis stage. Conclusions. FZHY produced antifibrotic effects in patients with baseline Ishak F3 and F4 fibrosis stages. Reduction in fibrosis severity was zonal and correlated with the severity of inflammation. Based on its tolerability, safety, and efficacy, FZHY should be further investigated as a therapy in chronic liver diseases because of its dual anti-inflammatory and antiibrotic properties. Lay Summary. This is the first US-based, multicenter and placebo-controlled clinical trial that shows statistically significant reduction in fibrosis in patients with active HCV using an antifibrotic botanical formula. This has important implications as there is an immediate need for effective antifibrotic agents in treating many chronic diseases including NASH that lead to scarring of the liver. With artificial intelligence-based methodology, qFibrosis, we may provide a more reliable way to assess the FZHY as a therapy in chronic liver diseases because of its dual anti-inflammatory and antifibrotic properties.

Developing a New qFIBS Model Assessing Histological Features in Pediatric Patients With Non-alcoholic Steatohepatitis

Background

The evolution of pediatric non-alcoholic fatty liver disease (NAFLD) to non-alcoholic steatohepatitis (NASH) is associated with unique histological features. Pathological evaluation of liver specimen is often hindered by observer variability and diagnostic consensus is not always attainable. We investigated whether the qFIBS technique derived from adult NASH could be applied to pediatric NASH.

Materials and Methods

102 pediatric patients (<18 years old) with liver biopsy-proven NASH were included. The liver biopsies were serially sectioned for hematoxylin-eosin and Masson trichrome staining for histological scoring, and for second harmonic generation (SHG) imaging. qFIBS-automated measure of fibrosis, inflammation, hepatocyte ballooning, and steatosis was estabilshed by using the NASH CRN scoring system as the reference standard.

Results

qFIBS showed the best correlation with steatosis (r = 0.84, P < 0.001); with ability to distinguish different grades of steatosis (AUROCs 0.90 and 0.98, sensitivity 0.71 and 0.93, and specificity 0.90 and 0.90). qFIBS correlation with fibrosis (r = 0.72, P < 0.001) was good with high AUROC values [qFibrosis (AUC) > 0.85 (0.85–0.95)] and ability to distinguish different stages of fibrosis. qFIBS showed weak correlation with ballooning (r = 0.38, P = 0.028) and inflammation (r = 0.46, P = 0.005); however, it could distinguish different grades of ballooning (AUROCs 0.73, sensitivity 0.36, and specificity 0.92) and inflammation (AUROCs 0.77, sensitivity 0.83, and specificity 0.53).

Conclusion

It was demonstrated that when qFIBS derived from adult NASH was performed on pediatric NASH, it could best distinguish the various histological grades of steatosis and fibrosis.

Breakthroughs in therapies for NASH and remaining challenges

Initially a condition that received limited recognition and whose clinical impact was controversial, non-alcoholic steatohepatitis (NASH) has become a leading cause of chronic liver disease. Although there are no approved therapies, major breakthroughs, which will be reviewed here, have paved the way for future therapeutic successes. The unmet medical need in NASH is no longer disputed, and progress in the understanding of its pathogenesis has resulted in the identification of many pharmacological targets. Key surrogate outcomes for therapeutic trials are now accepted by regulatory agencies, thus creating a path for drug registration. A set of non-invasive measurements enabled early-stage trials to be conducted expeditiously, thus providing early indications on the biological and possibly clinical actions of therapeutic candidates. This generated efficacy results for a number of highly promising compounds that are now in late-stage development. Intense research aimed at further improving the assessment of histological endpoints and in developing non-invasive predictive biomarkers is underway. This will help improve the design and feasibility of successful trials, ultimately providing patients with therapeutic options that can change the course of the disease.

Reliability of the nonalcoholic steatohepatitis clinical research network and steatosis activity fibrosis histological scoring systems

BACKGROUND AND AIM

We aimed to determine whether lobular inflammation and ballooning grades in the Non-alcoholic Steatohepatitis Clinical Research Network (NASH CRN) scoring system can be directly translated into the same for the Steatosis Activity Fibrosis scoring system (SAF) and to look at intra-observer and inter-observer agreement for each individual histological component and for diagnosis of non-alcoholic steatohepatitis (NASH) using the two scoring systems.

METHODS

Four pathologists from two Asian centers scored 20 digitalized slides, twice using the NASH CRN, twice using the SAF. Intra-observer and inter-observer agreement was analyzed using Fleiss' kappa, weighted kappa, or Cohen kappa, where appropriate.

RESULTS

The intra-observer discrepancy rate when using the NASH CRN compared with the SAF was higher than when using the individual scoring system for lobular inflammation (15% comparing both scoring systems vs 10% and 1.8% for the NASH CRN and the SAF, respectively) and hepatocyte ballooning (33.8% vs 12.5% and 5%, respectively), but not for diagnosis of NASH (6.3% vs 6.3% and 0%, respectively). Intra-observer and inter-observer agreement was substantial to almost perfect, except for inter-observer agreement for lobular inflammation and diagnosis of NASH, which was only fair to moderate in most instances.

CONCLUSION

These findings do not support the direct inter-translation between the NASH CRN and the SAF. However, the diagnosis of NASH during examinations using the NASH CRN may be comparable with diagnosis of NASH using the SAF, vice versa. The inter-observer agreement for lobular inflammation and NASH diagnosis needs to be improved.

Current status and challenges in the drug treatment for fibrotic nonalcoholic steatohepatitis

Currently, nonalcoholic steatohepatitis (NASH) is one of the most common forms of chronic hepatitis, increasing the burden of health care worldwide. In patients with NASH, the fibrosis stage is the most predictive factor of long-term events. However, there are still no drugs approved by the Food and Drug Administration of the United States for treating biopsy-proven NASH with fibrosis or cirrhosis. Although some novel drugs have shown promise in preclinical studies and led to improvement in terms of hepatic fat content and steatohepatitis, a considerable proportion of them have failed to achieve histological endpoints of fibrosis improvement. Due to the large number of NASH patients and adverse clinical outcomes, the search for novel drugs is necessary. In this review, we discuss current definitions for the evaluation of treatment efficacy in fibrosis improvement for NASH patients, and we summarize novel agents in the pipeline from different mechanisms and phases of trial. We also critically review the challenges we face in the development of novel agents for fibrotic NASH and NASH cirrhosis.

Histological assessment based on liver biopsy: the value and challenges in NASH drug development

Nonalcoholic steatohepatitis (NASH) is increasingly recognized as a serious disease that can lead to cirrhosis, hepatocellular carcinoma (HCC), and death. However, there is no effective drug to thwart the progression of the disease. Development of new drugs for NASH is an urgent clinical need. Liver biopsy plays a key role in the development of new NASH drugs. Histological findings based on liver biopsy are currently used as the main inclusion criteria and the primary therapeutic endpoint in NASH clinical trials. However, there are inherent challenges in the use of liver biopsy in clinical trials, such as evaluation reliability, sampling error, and invasive nature of the procedure. In this article, we review the advantages and value of liver histopathology based on liver biopsy in clinical trials of new NASH drugs. We also discuss the challenges and limitations of liver biopsy and identify future drug development directions.

Updates on novel pharmacotherapeutics for the treatment of nonalcoholic steatohepatitis

Nonalcoholic steatohepatitis (NASH) is a progressive form of nonalcoholic fatty liver disease (NAFLD), characterized with hepatocellular steatosis, ballooning, lobular inflammation, fibrotic progression, and insulin resistance. NASH may progress to cirrhosis and hepatocellular carcinoma (HCC), which are the major indications for liver transplantation and the causes for mortality. Thus far, there are no approved pharmacotherapeutics for the treatment of NASH. Given the complexity of NASH pathogenesis at multifaceted aspects, such as lipotoxicity, inflammation, insulin resistance, mitochondrial dysfunction and fibrotic progression, pharmacotherapeutics under investigation target different key pathogenic pathways to gain either the resolution of steatohepatitis or regression of fibrosis, ideally both. Varieties of pharmacologic candidates have been tested in clinical trials and have generated some positive results. On the other hand, recent failure or termination of a few phase II and III trials is disappointing in this field. In face to growing challenges in pharmaceutical development, this review intends to summarize the latest data of new medications which have completed phase II or III trials, and discuss the rationale and preliminary results of several combinatory options. It is anticipated that with improved understanding of NASH pathogenesis and critical endpoints, efficient pharmacotherapeutics will be available for the treatment of NASH with an acceptable safety profile.

Complexity of ballooned hepatocyte feature recognition: Defining a training atlas for artificial intelligence-based imaging in NAFLD

BACKGROUND & AIMS

Histologically assessed hepatocyte ballooning is a key feature discriminating non-alcoholic steatohepatitis (NASH) from steatosis (NAFL). Reliable identification underpins patient inclusion in clinical trials and serves as a key regulatory-approved surrogate endpoint for drug efficacy. High inter/intra-observer variation in ballooning measured using the NASH CRN semi-quantitative score has been reported yet no actionable solutions have been proposed.

METHODS

A focused evaluation of hepatocyte ballooning recognition was conducted. Digitized slides were evaluated by 9 internationally recognized expert liver pathologists on 2 separate occasions: each pathologist independently marked every ballooned hepatocyte and later provided an overall non-NASH NAFL/NASH assessment. Interobserver variation was assessed and a 'concordance atlas' of ballooned hepatocytes generated to train second harmonic generation/two-photon excitation fluorescence imaging-based artificial intelligence (AI).

RESULTS

The Fleiss kappa statistic for overall interobserver agreement for presence/absence of ballooning was 0.197 (95% CI 0.094-0.300), rising to 0.362 (0.258-0.465) with a ≥5-cell threshold. However, the intraclass correlation coefficient for consistency was higher (0.718 [0.511-0.900]), indicating 'moderate' agreement on ballooning burden. 133 ballooned cells were identified using a ≥5/9 majority to train AI ballooning detection (AI-pathologist pairwise concordance 19-42%, comparable to inter-pathologist pairwise concordance of between 8-75%). AI quantified change in ballooned cell burden in response to therapy in a separate slide set.

CONCLUSIONS

The substantial divergence in hepatocyte ballooning identified amongst expert hepatopathologists suggests that ballooning is a spectrum, too subjective for its presence or complete absence to be unequivocally determined as a trial endpoint. A concordance atlas may be used to train AI assistive technologies to reproducibly quantify ballooned hepatocytes that standardize assessment of therapeutic efficacy. This atlas serves as a reference standard for ongoing work to refine how ballooning is classified by both pathologists and AI.

LAY SUMMARY

For the first time, we show that, even amongst expert hepatopathologists, there is poor agreement regarding the number of ballooned hepatocytes seen on the same digitized histology images. This has important implications as the presence of ballooning is needed to establish the diagnosis of non-alcoholic steatohepatitis (NASH), and its unequivocal absence is one of the key requirements to show 'NASH resolution' to support drug efficacy in clinical trials. Artificial intelligence-based approaches may provide a more reliable way to assess the range of injury recorded as "hepatocyte ballooning".

The Placebo Response in Randomized Trials in Nonalcoholic Steatohepatitis Simply Explained

BACKGROUND & AIMS

Liver histology is the primary endpoint in phase III trials in nonalcoholic steatohepatitis (NASH). There is an appreciable response to placebo that confounds endpoint assessment. The aim of this study was to quantify contributors to the placebo response and its impact on liver fibrosis improvement.

METHODS

Estimates of fibrosis improvement in placebo-treated participants were made using probabilistic simulation. Each simulated trial included 120 participants. Parameters considered in the model included sampling and observer variability, regression to the mean, and net fibrosis progression calibrated to reported trial outcomes.

RESULTS

In large phase IIb and III trials, 22% of placebo-treated participants with fibrosis stage 2 or 3 NASH at baseline improved by at least 1 fibrosis stage with minimal net disease progression. Estimates of sampling and observer variability in simultaneous biopsy studies highlighted an imbalance where apparent fibrosis improvement was more likely than worsening. Using these estimates and known trial outcomes, net fibrosis progression was estimated at 0.05 stages per year. Simulations of the placebo response rate showed a rate of 22% with 80% of trials falling between 15 and 30%, in keeping with trials reported to date. Additional increases in observer variability further increased the placebo response.

CONCLUSIONS

The analyses presented simply define the placebo response in liver fibrosis in trials in NASH in terms of sampling and observer variability, regression to the mean, and fibrosis progression. Factors relating to liver biopsy are largely unmodifiable, and the variation in placebo response rates, both simulated and observed, challenges the role of biopsy in trial endpoint assessment.

Application of artificial intelligence in non-alcoholic fatty liver disease and liver fibrosis: a systematic review and meta-analysis

BACKGROUND

The global prevalence of non-alcoholic fatty liver disease (NAFLD) continues to rise. Non-invasive diagnostic modalities including ultrasonography and clinical scoring systems have been proposed as alternatives to liver biopsy but with limited performance. Artificial intelligence (AI) is currently being integrated with conventional diagnostic methods in the hopes of performance improvements. We aimed to estimate the performance of AI-assisted systems for diagnosing NAFLD, non-alcoholic steatohepatitis (NASH), and liver fibrosis.

METHODS

A systematic review was performed to identify studies integrating AI in the diagnosis of NAFLD, NASH, and liver fibrosis. Pooled sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and summary receiver operating characteristic curves were calculated.

RESULTS

Twenty-five studies were included in the systematic review. Meta-analysis of 13 studies showed that AI significantly improved the diagnosis of NAFLD, NASH and liver fibrosis. AI-assisted ultrasonography had excellent performance for diagnosing NAFLD, with a sensitivity, specificity, PPV, NPV of 0.97 (95% confidence interval (CI): 0.91-0.99), 0.98 (95% CI: 0.89-1.00), 0.98 (95% CI: 0.93-1.00), and 0.95 (95% CI: 0.88-0.98), respectively. The performance of AI-assisted ultrasonography was better than AI-assisted clinical data sets for the identification of NAFLD, which provided a sensitivity, specificity, PPV, NPV of 0.75 (95% CI: 0.66-0.82), 0.82 (95% CI: 0.74-0.88), 0.75 (95% CI: 0.60-0.86), and 0.82 (0.74-0.87), respectively. The area under the curves were 0.98 and 0.85 for AI-assisted ultrasonography and AI-assisted clinical data sets, respectively. AI-integrated clinical data sets had a pooled sensitivity, specificity of 0.80 (95%CI: 0.75-0.85), 0.69 (95%CI: 0.53-0.82) for identifying NASH, as well as 0.99-1.00 and 0.76-1.00 for diagnosing liver fibrosis stage F1-F4, respectively.

CONCLUSION

AI-supported systems provide promising performance improvements for diagnosing NAFLD, NASH, and identifying liver fibrosis among NAFLD patients. Prospective trials with direct comparisons between AI-assisted modalities and conventional methods are warranted before real-world implementation.

PROTOCOL REGISTRATION

PROSPERO (CRD42021230391).

Advances in liver US, CT, and MRI: moving toward the future

Over the past two decades, the epidemiology of chronic liver disease has changed with an increase in the prevalence of nonalcoholic fatty liver disease in parallel to the advent of curative treatments for hepatitis C. Recent developments provided new tools for diagnosis and monitoring of liver diseases based on ultrasound (US), computed tomography (CT), and magnetic resonance imaging (MRI), as applied for assessing steatosis, fibrosis, and focal lesions. This narrative review aims to discuss the emerging approaches for qualitative and quantitative liver imaging, focusing on those expected to become adopted in clinical practice in the next 5 to 10 years. While radiomics is an emerging tool for many of these applications, dedicated techniques have been investigated for US (controlled attenuation parameter, backscatter coefficient, elastography methods such as point shear wave elastography [pSWE] and transient elastography [TE], novel Doppler techniques, and three-dimensional contrast-enhanced ultrasound [3D-CEUS]), CT (dual-energy, spectral photon counting, extracellular volume fraction, perfusion, and surface nodularity), and MRI (proton density fat fraction [PDFF], elastography [MRE], contrast enhancement index, relative enhancement, T1 mapping on the hepatobiliary phase, perfusion). Concurrently, the advent of abbreviated MRI protocols will help fulfill an increasing number of examination requests in an era of healthcare resource constraints.

A Machine Learning Approach to Liver Histological Evaluation Predicts Clinically Significant Portal Hypertension in NASH Cirrhosis

BACKGROUND AND AIMS

The hepatic venous pressure gradient (HVPG) is the standard for estimating portal pressure but requires expertise for interpretation. We hypothesized that HVPG could be extrapolated from liver histology using a machine learning (ML) algorithm.

APPROACH AND RESULTS

Patients with NASH with compensated cirrhosis from a phase 2b trial were included. HVPG and biopsies from baseline and weeks 48 and 96 were reviewed centrally, and biopsies evaluated with a convolutional neural network (PathAI, Boston, MA). Using trichrome-stained biopsies in the training set (n = 130), an ML model was developed to recognize fibrosis patterns associated with HVPG, and the resultant ML HVPG score was validated in a held-out test set (n = 88). Associations between the ML HVPG score with measured HVPG and liver-related events, and performance of the ML HVPG score for clinically significant portal hypertension (CSPH) (HVPG ≥ 10 mm Hg), were determined. The ML-HVPG score was more strongly correlated with HVPG than hepatic collagen by morphometry (ρ = 0.47 vs. ρ = 0.28; P < 0.001). The ML HVPG score differentiated patients with normal (0-5 mm Hg) and elevated (5.5-9.5 mm Hg) HVPG and CSPH (median: 1.51 vs. 1.93 vs. 2.60; all P < 0.05). The areas under receiver operating characteristic curve (AUROCs) (95% CI) of the ML-HVPG score for CSPH were 0.85 (0.80, 0.90) and 0.76 (0.68, 0.85) in the training and test sets, respectively. Discrimination of the ML-HVPG score for CSPH improved with the addition of a ML parameter for nodularity, Enhanced Liver Fibrosis, platelets, aspartate aminotransferase (AST), and bilirubin (AUROC in test set: 0.85; 95% CI: 0.78, 0.92). Although baseline ML-HVPG score was not prognostic, changes were predictive of clinical events (HR: 2.13; 95% CI: 1.26, 3.59) and associated with hemodynamic response and fibrosis improvement.

CONCLUSIONS

An ML model based on trichrome-stained liver biopsy slides can predict CSPH in patients with NASH with cirrhosis.

Predict Early Recurrence of Resectable Hepatocellular Carcinoma Using Multi-Dimensional Artificial Intelligence Analysis of Liver Fibrosis

Simple Summary

Hepatocellular carcinoma (HCC) is the third most commonly diagnosed cancer in the world, and surgical resection is the commonly used curative management of early-stage disease. However, the recurrence rate is high after resection, and liver fibrosis has been thought to increase the risk of recurrence. Conventional histological staging of fibrosis is highly subjective to observer variations. To overcome this limitation, we used a fully quantitative fibrosis assessment tool, qFibrosis (utilizing second harmonic generation and two-photon excitation fluorescence microscopy), with multi-dimensional artificial intelligence analysis to establish a fully-quantitative, accurate fibrotic score called a “combined index”, which can predict early recurrence of HCC after curative intent resection. Therefore, we can pay more attention on the patients with high risk of early recurrence.

Abstract

Background: Liver fibrosis is thought to be associated with early recurrence of hepatocellular carcinoma (HCC) after resection. To recognize HCC patients with higher risk of early recurrence, we used a second harmonic generation and two-photon excitation fluorescence (SHG/TPEF) microscopy to create a fully quantitative fibrosis score which is able to predict early recurrence. Methods: The study included 81 HCC patients receiving curative intent hepatectomy. Detailed fibrotic features of resected hepatic tissues were obtained by SHG/TPEF microscopy, and we used multi-dimensional artificial intelligence analysis to create a recurrence prediction model “combined index” according to the morphological collagen features of each patient’s non-tumor hepatic tissues. Results: Our results showed that the “combined index” can better predict early recurrence (area under the curve = 0.917, sensitivity = 81.8%, specificity = 90.5%), compared to alpha fetoprotein level (area under the curve = 0.595, sensitivity = 68.2%, specificity = 47.6%). Using a Cox proportional hazards analysis, a higher “combined index” is also a poor prognostic factor of disease-free survival and overall survival. Conclusions: By integrating multi-dimensional artificial intelligence and SHG/TPEF microscopy, we may locate patients with a higher risk of recurrence, follow these patients more carefully, and conduct further management if needed.

Application of Artificial Intelligence for Diagnosis and Risk Stratification in NAFLD and NASH: The State of the Art

The diagnosis of nonalcoholic fatty liver disease and associated fibrosis is challenging given the lack of signs, symptoms and nonexistent diagnostic test. Furthermore, follow up and treatment decisions become complicated with a lack of a simple reproducible method to follow these patients longitudinally. Liver biopsy is the current standard to detect, risk stratify and monitor individuals with nonalcoholic fatty liver disease. However, this method is an unrealistic option in a population that affects about one in three to four individuals worldwide. There is an urgency to develop innovative methods to facilitate management at key points in an individual's journey with nonalcoholic fatty liver disease fibrosis. Artificial intelligence is an exciting field that has the potential to achieve this. In this review, we highlight applications of artificial intelligence by leveraging our current knowledge of nonalcoholic fatty liver disease to diagnose and risk stratify NASH phenotypes.

What Mediates Fibrosis in the Tumor Microenvironment of Clear Renal Cell Carcinoma

Previous studies have demonstrated that direct targeting of interstitial cancer-associated fibroblasts (CAF) and tumor fibrosis alone seemed to be an unpromising treatment option for malignant tumors. Therefore, it is necessary to further explore the mechanism of the influence of collagen and tumor fibrosis on the biological behavior of malignant tumors. The current study aimed to explore the effect of intratumor fibrosis on the prognosis of renal clear cell carcinoma (ccRCC) and its mechanism. With the bioinformatic analysis of The Cancer Genome Atlas (TCGA) database (n = 537), the study showed that high Collagen type I α 1 (COL1A1) mRNA expression indicated the poor prognosis of ccRCC patients compared with low expression ones. We further used the Two-photon-excited fluorescence (TPEF)/second harmonic generation (SHG) microscopy to determine the intratumor fibrosis of 68 patients with surgical resection of ccRCC and confirmed that a high fibrosis level in the tumor was associated with a poor prognosis compared with patients with low expression (Progression-Free Survival: p = 0.030). We further measured the protein chips of 640 cytokines in ccRCC specimens and found that several cytokines, including prolactin (PRL), were associated with the degree of fibrosis in the tumor, as confirmed by the prolactin receptor (PRLR) immunohistochemical method. In addition, the study showed that PRLR expression decreased significantly in the ccRCC compared with adjacent normal tissue (p < 0.05). Our research shows that low expression of PRLR predicted the poor survival of the patient. We used the Cell Counting Kit-8 experiment, the transwell and the plate clone formation assay to evaluate the role of PRL in the 7860 and the ACHN cell lines. We found that PRL promoted ccRCC cell proliferation and migration. JAK-STAT3 activation was found in the high prolactin expression group by mass spectrum analysis. This study delineated the fibrosis-based tumor microenvironment characteristics of ccRCC. PRL/PRLR may be involved in the fibrosis process and are essential prognostic risk factors for ccRCC.