Abstract
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.