Digital pathology for nonalcoholic steatohepatitis assessment

Hepatic Steatosis Analysis in Metabolic Dysfunction-Associated Steatotic Liver Disease Based on Artificial Intelligence

BACKGROUND

Metabolic dysfunction-associated steatotic liver disease (MASLD) is characterized by the accumulation of fat in the liver, excluding excessive alcohol consumption and other known causes of liver injury. Animal models are often used to explore different pathogenic mechanisms and therapeutic targets of MASLD. The aim of this study is to apply an artificial intelligence (AI) system based on second-harmonic generation (SHG)/two-photon-excited fluorescence (TPEF) technology to automatically assess the dynamic patterns of hepatic steatosis in MASLD mouse models.

METHODS

We evaluated the characteristics of hepatic steatosis in mouse models of MASLD using AI analysis based on SHG/TPEF images. Six different models of MASLD were induced in C57BL/6 mice by feeding with a western or high-fat diet, with or without fructose in their drinking water, and/or by weekly injections of carbon tetrachloride.

RESULTS

Body weight, serum lipids, and liver enzyme markers increased at 8 and 16 weeks in each model compared to baseline. Steatosis grade showed a steady upward trend. However, the non-alcoholic steatohepatitis (NASH) Clinical Research Network (CRN) histological scoring method detected no significant difference between 8 and 16 weeks. In contrast, AI analysis was able to quantify dynamic changes in the area, number, and size of hepatic steatosis automatically and objectively, making it more suitable for preclinical MASLD animal experiments.

CONCLUSIONS

AI recognition technology may be a new tool for the accurate diagnosis of steatosis in MASLD, providing a more precise and objective method for evaluating steatosis in preclinical murine MASLD models under various experimental and treatment conditions.

Digital quantitation of bridging fibrosis and septa reveals changes in natural history and treatment not seen with conventional histology

BACKGROUND AND AIMS

Metabolic dysfunction-associated steatohepatitis (MASH) with bridging fibrosis is a critical stage in the evolution of fatty liver disease. Second harmonic generation/two-photon excitation fluorescence (SHG/TPEF) microscopy with artificial intelligence (AI) provides sensitive and reproducible quantitation of liver fibrosis. This methodology was applied to gain an in-depth understanding of intra-stage fibrosis changes and septa analyses in a homogenous, well-characterised group with MASH F3 fibrosis.

METHODS

Paired liver biopsies (baseline [BL] and end of treatment [EOT]) of 57 patients (placebo, n = 17 and tropifexor n = 40), with F3 fibrosis stage at BL according to the clinical research network (CRN) scoring, were included. Unstained sections were examined using SHG/TPEF microscopy with AI. Changes in liver fibrosis overall and in five areas of liver lobules were quantitatively assessed by qFibrosis. Progressive, regressive septa, and 12 septa parameters were quantitatively analysed.

RESULTS

qFibrosis demonstrated fibrosis progression or regression in 14/17 (82%) patients receiving placebo, while the CRN scoring categorised 11/17 (65%) as 'no change'. Radar maps with qFibrosis readouts visualised quantitative fibrosis dynamics in different areas of liver lobules even in cases categorised as 'No Change'. Measurement of septa parameters objectively differentiated regressive and progressive septa (p < .001). Quantitative changes in individual septa parameters (BL to EOT) were observed both in the 'no change' and the 'regression' subgroups, as defined by the CRN scoring.

CONCLUSION

SHG/TPEF microscopy with AI provides greater granularity and precision in assessing fibrosis dynamics in patients with bridging fibrosis, thus advancing knowledge development of fibrosis evolution in natural history and in clinical trials.

Utility of AI digital pathology as an aid for pathologists scoring fibrosis in MASH

BACKGROUND & AIMS

Intra and inter-pathologist variability poses a significant challenge in metabolic dysfunction-associated steatohepatitis (MASH) biopsy evaluation, leading to suboptimal selection of patients and confounded assessment of histological response in clinical trials. We evaluated the utility of an artificial intelligence (AI) digital pathology (DP) platform to aid pathologists improve the reliability of fibrosis staging.

METHODS

A total of 120 digitized histology slides from two trials (NCT03517540, NCT03912532) were analysed by four expert hepatopathologists, with and without AI-assistance in a randomized, cross-over design. We utilized the HistoIndex AI DP platform, consisting of unstained second harmonic generation/two photon excitation fluorescence (SHG/TPEF) images and AI quantitative fibrosis (qF) values.

RESULTS

AI-assistance significantly improved inter-pathologist kappa for fibrosis (F)-staging, particularly for early fibrosis (F0-F2), with reduced variance around the median reads. Intra-pathologist kappa was unchanged. AI-assistance increased pathologist concordance for identifying clinical trial inclusion subjects (F2-F3) from 45% to 71%, exclusion subjects (F0/F1/F4) from 38% to 55%, and evaluation of fibrosis response to treatment from 49% to 61%. SHG/TPEF images, qFibrosis continuous values, and qF-stage were considered useful by at least 3 out of 4 pathologists in 83%, 55%, and 38% cases, respectively. In the context of a clinical trial, the increase in inter-pathologist concordance in this study is modeled to result in a ∼25% reduction in the potential need for adjudication as well as a ∼50% increase in the study power.

CONCLUSIONS

The use of AI DP enhances inter-rater reliability of fibrosis staging for MASH. This indicates that the SHG/TPEF-based AI DP tool is useful for assisting pathologists in assessing fibrosis, thereby enhancing clinical trial efficiency and reliability of fibrosis readouts in response to treatments.

A roadmap for clinical trials in MASH-related compensated cirrhosis

Although metabolic dysfunction-associated steatohepatitis (MASH) is rapidly becoming a leading cause of cirrhosis worldwide, therapeutic options are limited and the number of clinical trials in MASH-related compensated cirrhosis is low as compared to those conducted in earlier disease stages. Moreover, designing clinical trials in MASH cirrhosis presents a series of challenges regarding the understanding and conceptualization of the natural history, regulatory considerations, inclusion criteria, recruitment, end points and trial duration, among others. The first international workshop on the state of the art and future direction of clinical trials in MASH-related compensated cirrhosis was held in April 2023 at Vall d'Hebron University Hospital in Barcelona (Spain) and was attended by a group of international experts on clinical trials from academia, regulatory agencies and industry, encompassing expertise in MASH, cirrhosis, portal hypertension, and regulatory affairs. The presented Roadmap summarizes important content of the workshop on current status, regulatory requirements and end points in MASH-related compensated cirrhosis clinical trials, exploring alternative study designs and highlighting the challenges that should be considered for upcoming studies on MASH cirrhosis.

AI-based digital pathology provides newer insights into lifestyle intervention-induced fibrosis regression in MASLD: An exploratory study

BACKGROUND AND AIMS

Lifestyle intervention is the mainstay of therapy for metabolic dysfunction-associated steatohepatitis (MASH), and liver fibrosis is a key consequence of MASH that predicts adverse clinical outcomes. The placebo response plays a pivotal role in the outcome of MASH clinical trials. Second harmonic generation/two-photon excitation fluorescence (SHG/TPEF) microscopy with artificial intelligence analyses can provide an automated quantitative assessment of fibrosis features on a continuous scale called qFibrosis. In this exploratory study, we used this approach to gain insight into the effect of lifestyle intervention-induced fibrosis changes in MASH.

METHODS

We examined unstained sections from paired liver biopsies (baseline and end-of-intervention) from MASH individuals who had received either routine lifestyle intervention (RLI) (n = 35) or strengthened lifestyle intervention (SLI) (n = 17). We quantified liver fibrosis with qFibrosis in the portal tract, periportal, transitional, pericentral, and central vein regions.

RESULTS

About 20% (7/35) and 65% (11/17) of patients had fibrosis regression in the RLI and SLI groups, respectively. Liver fibrosis tended towards no change or regression after each lifestyle intervention, and this phenomenon was more prominent in the SLI group. SLI-induced liver fibrosis regression was concentrated in the periportal region.

CONCLUSION

Using digital pathology, we could detect a more pronounced fibrosis regression with SLI, mainly in the periportal region. With changes in fibrosis area in the periportal region, we could differentiate RLI and SLI patients in the placebo group in the MASH clinical trial. Digital pathology provides new insight into lifestyle-induced fibrosis regression and placebo responses, which is not captured by conventional histological staging.

Outcome prediction in metabolic dysfunction-associated steatotic liver disease using stain-free digital pathological assessment

Computational quantification reduces observer-related variability in histological assessment of metabolic dysfunction-associated steatotic liver disease (MASLD). We undertook stain-free imaging using the SteatoSITE resource to generate tools directly predictive of clinical outcomes. Unstained liver biopsy sections (n = 452) were imaged using second-harmonic generation/two-photon excitation fluorescence (TPEF) microscopy, and all-cause mortality and hepatic decompensation indices constructed. The mortality index had greater predictive power for all-cause mortality (index >.14 vs. .31 vs. Collapse

Key Words

• computer‐assisted
• cox model
• image processing
• metabolic dysfunction‐associated steatotic liver disease
• non‐alcoholic fatty liver disease
• pathology

Collapse

MESH Headings

• Humans
• Fatty Liver/pathology
• Fatty Liver/diagnostic imaging
• Liver/pathology
• Liver/diagnostic imaging
• Male
• Female
• Biopsy
• Predictive Value of Tests
• Middle Aged
• Microscopy, Fluorescence, Multiphoton/methods
• Non-alcoholic Fatty Liver Disease/pathology
• Non-alcoholic Fatty Liver Disease/complications
• Non-alcoholic Fatty Liver Disease/diagnostic imaging
• Prognosis

Collapse

Grants

• Innovate UK

Collapse

Affiliation(s)

Timothy J Kendall Centre for Inflammation Research, Institute for Regeneration and Repair, University of Edinburgh, Edinburgh, UK Edinburgh Pathology, University of Edinburgh, Edinburgh, UK
Elaine Chng HistoIndex Pte Ltd, Singapore, Singapore
Yayun Ren HistoIndex Pte Ltd, Singapore, Singapore
Dean Tai HistoIndex Pte Ltd, Singapore, Singapore
Gideon Ho HistoIndex Pte Ltd, Singapore, Singapore
Jonathan A Fallowfield Centre for Inflammation Research, Institute for Regeneration and Repair, University of Edinburgh, Edinburgh, UK

Collapse

AI Digital Pathology Using qFibrosis Shows Heterogeneity of Fibrosis Regression in Patients with Chronic Hepatitis B and C with Viral Response

This study aimed to understand the dynamic changes in fibrosis and its relationship with the evaluation of post-treatment viral hepatitis using qFibrosis. A total of 158 paired pre- and post-treatment liver samples from patients with chronic hepatitis B (CHB; n = 100) and C (CHC; n = 58) were examined. qFibrosis was employed with artificial intelligence (AI) to analyze the fibrosis dynamics in the portal tract (PT), periportal (PP), midzonal, pericentral, and central vein (CV) regions. All patients with CHB achieved a virological response after 78 weeks of treatment, whereas patients with CHC achieved a sustained viral response after 24 weeks. For patients initially staged as F5/6 (Ishak system) at baseline, the post-treatment cases exhibited a significant reduction in the collagen proportionate area (CPA) (25-69%) and number of collagen strings (#string) (9-72%) across all regions. In contrast, those initially staged as F3/4 at baseline showed a similar CPA and #string trend at 24 weeks. For regression patients, 27 parameters (25 in the CV region) in patients staged as F3/4 and 15 parameters (three in the PT and 12 in the PP regions) in those staged as F5/6 showed significant differences between the CHB and CHC groups at baseline. Following successful antiviral treatment, the pre- and post-treatment liver samples provided quantitative evidence of the heterogeneity of fibrotic features. qFibrosis has the potential to provide new insights into the characteristics of fibrosis regression in both patients with CHB and CHC as early as 24 weeks after antiviral therapy.

NAFLD (MASLD)/NASH (MASH): Does It Bother to Label at All? A Comprehensive Narrative Review

Nonalcoholic fatty liver disease (NAFLD), or metabolic dysfunction-associated steatotic liver disease (MASLD), is a liver condition that is linked to overweight, obesity, diabetes mellitus, and metabolic syndrome. Nonalcoholic steatohepatitis (NASH), or metabolic dysfunction-associated steatohepatitis (MASH), is a form of NAFLD/MASLD that progresses over time. While steatosis is a prominent histological characteristic and recognizable grossly and microscopically, liver biopsies of individuals with NASH/MASH may exhibit several other abnormalities, such as mononuclear inflammation in the portal and lobular regions, hepatocellular damage characterized by ballooning and programmed cell death (apoptosis), misfolded hepatocytic protein inclusions (Mallory-Denk bodies, MDBs), megamitochondria as hyaline inclusions, and fibrosis. Ballooning hepatocellular damage remains the defining feature of NASH/MASH. The fibrosis pattern is characterized by the initial expression of perisinusoidal fibrosis ("chicken wire") and fibrosis surrounding the central veins. Children may have an alternative form of progressive NAFLD/MASLD characterized by steatosis, inflammation, and fibrosis, mainly in Rappaport zone 1 of the liver acinus. To identify, synthesize, and analyze the scientific knowledge produced regarding the implications of using a score for evaluating NAFLD/MASLD in a comprehensive narrative review. The search for articles was conducted between 1 January 2000 and 31 December 2023, on the PubMed/MEDLINE, Scopus, Web of Science, and Cochrane databases. This search was complemented by a gray search, including internet browsers (e.g., Google) and textbooks. The following research question guided the study: "What are the basic data on using a score for evaluating NAFLD/MASLD?" All stages of the selection process were carried out by the single author. Of the 1783 articles found, 75 were included in the sample for analysis, which was implemented with an additional 25 articles from references and gray literature. The studies analyzed indicated the beneficial effects of scoring liver biopsies. Although similarity between alcoholic steatohepatitis (ASH) and NASH/MASH occurs, some patterns of hepatocellular damage seen in alcoholic disease of the liver do not happen in NASH/MASH, including cholestatic featuring steatohepatitis, alcoholic foamy degeneration, and sclerosing predominant hyaline necrosis. Generally, neutrophilic-rich cellular infiltrates, prominent hyaline inclusions and MDBs, cholestasis, and obvious pericellular sinusoidal fibrosis should favor the diagnosis of alcohol-induced hepatocellular injury over NASH/MASH. Multiple grading and staging methods are available for implementation in investigations and clinical trials, each possessing merits and drawbacks. The systems primarily used are the Brunt, the NASH CRN (NASH Clinical Research Network), and the SAF (steatosis, activity, and fibrosis) systems. Clinical investigations have utilized several approaches to link laboratory and demographic observations with histology findings with optimal platforms for clinical trials of rapidly commercialized drugs. It is promising that machine learning procedures (artificial intelligence) may be critical for developing new platforms to evaluate the benefits of current and future drug formulations.

The Use of Artificial Intelligence in the Liver Histopathology Field: A Systematic Review

Digital pathology (DP) has begun to play a key role in the evaluation of liver specimens. Recent studies have shown that a workflow that combines DP and artificial intelligence (AI) applied to histopathology has potential value in supporting the diagnosis, treatment evaluation, and prognosis prediction of liver diseases. Here, we provide a systematic review of the use of this workflow in the field of hepatology. Based on the PRISMA 2020 criteria, a search of the PubMed, SCOPUS, and Embase electronic databases was conducted, applying inclusion/exclusion filters. The articles were evaluated by two independent reviewers, who extracted the specifications and objectives of each study, the AI tools used, and the results obtained. From the 266 initial records identified, 25 eligible studies were selected, mainly conducted on human liver tissues. Most of the studies were performed using whole-slide imaging systems for imaging acquisition and applying different machine learning and deep learning methods for image pre-processing, segmentation, feature extractions, and classification. Of note, most of the studies selected demonstrated good performance as classifiers of liver histological images compared to pathologist annotations. Promising results to date bode well for the not-too-distant inclusion of these techniques in clinical practice.