Publications

For a full list, please see my Google Scholar. * denotes equal contribution.

MICCAI 2026
CPAgents framework

CPAgents: Agentic Composite Phenotype Generation for Cardiac Disease Association
Zuoou Li*, Wenlong Zhao*, Kelly Yu*, Weitong Zhang, Paul M. Matthews, Wenjia Bai, Bernhard Kainz, Mengyun Qiao
MICCAI 2026

  • An analyse–propose–verify loop of specialised agents (Analyst, Proposer, Verifier) builds interpretable composite cardiac phenotypes.
  • Composite phenotypes strengthen disease association and classification over raw imaging features.
MICCAI 2025
MESHAgents framework

Multi-Agent Reasoning for Cardiovascular Imaging Phenotype Analysis
Weitong Zhang*, Mengyun Qiao*, Chengqi Zang, Steven Niederer, Paul M. Matthews, Wenjia Bai, Bernhard Kainz
MICCAI 2025

  • MESHAgents: the first multi-agent system for imaging phenome-wide association studies, where domain-specialist LLM agents reach consensus on phenotype–factor associations.
  • Agent-discovered phenotypes match expert-selected ones in diagnostic performance across 38,309 UK Biobank participants.
Nature Machine Intelligence
sym

A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics
Mengyun Qiao, Kathryn A McGurk, Shuo Wang, Paul M. Matthews, Declan P O’Regan, Wenjia Bai
Nature Machine Intelligence 7, 800–811 (2025) | Imperial News

  • Developed a novel 4D mesh generative model for personalized cardiac anatomy reconstruction.
  • Demonstrated improved accuracy in representing normal heart dynamics compared to baseline models.
Nature Cardiovascular Research
Genetic and Phenotypic Architecture

Genetic and phenotypic architecture of human myocardial trabeculation
Kathryn A. McGurk, Mengyun Qiao, et al.
Nature Cardiovascular Research 3, 1503–1515 (2024)

  • Investigated genetic factors influencing myocardial trabeculation patterns.
  • Identified novel phenotypic correlations linked to cardiac health indicators.
IEEE TMI
CHeart Model

CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy
Mengyun Qiao, Shuo Wang, Huaqi Qiu, Antonio de Marvao, Declan P. O’Regan, Daniel Rueckert, Wenjia Bai

  • Introduced a conditional generative model to capture spatio-temporal variations in cardiac anatomy.
  • Achieved significant improvements in cardiac disease prediction over existing methods.

More Recent Papers