Kutbuddin Akbary

Background/Objectives: Sex-specific differences in metabolic dysfunction-associated fatty liver disease (MAFLD)-related hepatocellular carcinoma (HCC) remain poorly understood. This study aimed to clarify sex-associated disparities in disease progression and recovery using a diethylnitrosamine (DEN) plus Western diet/fructose-induced murine model combined with artificial intelligence (AI)-assisted histological analysis. Methods: Male and female C57BL/6J mice received a single diethylnitrosamine injection and were fed a Western diet/fructose regimen for 38 weeks, followed by an 8-week recovery period on standard chow. Serum biochemical parameters were measured, and liver histology was assessed using second harmonic generation/two-photon excitation fluorescence (SHG/TPEF) microscopy. Steatosis and fibrosis were quantified within tumor and adjacent non-tumor regions using AI-based image analysis. Results: Male mice developed more severe disease phenotypes, including greater tumor burden and higher serum alanine aminotransferase levels, compared with females. Following dietary recovery, female mice showed substantial reductions in tumor number and hepatic steatosis, particularly in non-tumor regions; in contrast, male mice demonstrated only minimal improvement. AI-assisted quantification confirmed considerable regression of both steatosis and fibrosis in females and moderate fibrosis improvement in both sexes. Conclusions: These findings indicate sexual dimorphism in the progression and regression of MAFLD-related HCC, with females exhibiting enhanced metabolic and histological recovery. The results underscore the importance of considering sex as a biological variable in preclinical metabolic dysfunction–associated fatty liver disease-related hepatocellular carcinoma research and highlight the value of AI-enhanced imaging for precise, objective evaluation of liver histology.

Background and Aims: Metabolic dysfunction‐associated steatotic liver disease (MASLD) is a major global cause of chronic liver disease, with the potential to progress from steatosis to metabolic dysfunction‐associated steatohepatitis (MASH) and cirrhosis. Fibrosis is a key determinant of liver‐related morbidity and mortality, highlighting the need for precise, reproducible assessment methods. This study aimed to develop and validate an Artificial Intelligence (AI)‐based fibrosis detection algorithm using Second Harmonic Generation/Two Photon Excitation Fluorescence (SHG/TPEF) microscopy. Methods: The algorithm integrates SHG/TPEF microscopy, which uses ultra‐fast lasers to capture intrinsic optical signals from unstained liver biopsies, with Machine Learning (ML)‐based image analysis. The resulting qFibrosis model quantifies collagen morphology to generate a continuous fibrosis index. Results: A standardised workflow was established, encompassing sample acquisition, SHG/TPEF imaging, region‐specific analysis and collagen feature quantification. Each step of the AI‐based ML of qFibrosis algorithm used to assess and quantify liver fibrosis is described in detail in this study. Conclusions: This AI‐driven approach enables accurate, continuous quantification of liver fibrosis, overcoming the variability of traditional histopathology. The qFibrosis model has potential as a standardised tool for therapeutic evaluation and disease monitoring in MASLD/MASH, representing a significant advancement in liver fibrosis assessment.

This study addresses the need for precise histopathological assessment of liver biopsies in Metabolic dysfunction‐Associated Steatohepatitis (MASH) cirrhosis, where assessing nuanced drug effects on fibrosis becomes pivotal. The study describes a framework for the development and validation of an Artificial Intelligence (AI) model, leveraging SHG/TPE microscopy along with insights from an expert hepatopathologist, to precisely annotate fibrous septa and nodules in liver biopsies in MASH cirrhosis. A total of 25 liver biopsies from the Belapectin trial (NCT04365868) were randomly selected for training, and an additional 10 for validation. Each biopsy underwent three sections: Smooth Muscle Actin (SMA) and Sirius Red (SR) staining for septa and nodule annotation by pathologists and an unstained section for SHG/TPE imaging and AI annotation using qSepta and qNodule algorithms. Re‐training of qSepta and qNodule algorithms was executed based on pathologist annotations. Sensitivity and positive predictive value (PPV) were employed to evaluate concordance with pathologist annotations, both pre‐ and post‐training and during validation. Post‐re‐training by pathologist annotations, the AI demonstrated improved sensitivity for qSepta annotations, achieving 91% post‐training (versus 84% pre‐training). Sensitivity for qSepta in the validation cohort also improved to 91%. Additionally, PPV significantly improved from 69% pre‐training to 85% post‐training and reached 94% during validation. For qNodule annotations, sensitivity increased from 82% post‐training to 90% in the validation cohort, while the PPV was consistent at 95% across both training and validation cohorts.This study outlines a strategic framework for developing and validating an AI model tailored for precise histopathological assessment of MASH cirrhosis, using pathologist training and annotations. The outcomes emphasise the crucial role of disease‐specific customisation of AI models, based on expert pathologist training, in improving accuracy and applicability in clinical trials, marking a step forward in understanding and addressing the histopathological evaluation of MASH cirrhosis.