Machine Learning & Multimodal Approaches in MASH & IBD

  • Identify novel clinical (histological and molecular) biomarkers associated with patients’ response to treatment and disease severity
  • Key cellular /human interpretable features from the H&E images of baseline biopsy samples from UC and CD to characterise the inflammatory microenvironment with spatial contextualised single cell resolution and spatial colocalisation
  • Unlocking quantitative insights and human interpretable features of the inflammatory microenvironment (IME) has the potential to reveal biomarkers for treatment selection
  • Development of fibrosis detection models on MASH and IBD