Christophe Lenglet
University of Minnesota, MN·Biomedical Engineering
Neurodegenerative diseases such as Alzheimer's disease, Parkinson's disease and multiple sclerosis affect millions of people in the United States. A digital twin is a computer model of an individual patient, kept up to date with that person's data.
- Fields
Biomedical Engineering
Mathematics & Statistics
Computer Science
- Topics
digital twins
neuroimaging
magnetic resonance imaging
- Grants
- 1 known grant, through Aug 2027
What they work on
- Develop low-dimensional manifold learning, causal pathway search and feature selection methods for digital twin models built from brain MRI of neurodegenerative disease.
- Create verification, validation and uncertainty quantification techniques for digital twins using Bayesian methods, data assimilation, resampling, empirical likelihood and topological data analysis.
- Build dynamical system models incorporating observed image data to improve computational efficiency and generate synthetic data for ethical AI use.
- Develop knowledge-graph systems that help regulatory and healthcare agencies assess digital twin technologies, and study their ethical, legal and social implications.
More about the research
Digital twins built from medical images and other data could help scientists understand these diseases and test treatments, but only if the models are reliable, trustworthy and used responsibly. This collaborative project develops the mathematical and computational foundations for digital twins built from brain magnetic resonance imaging (MRI).
Why it matters
Reliable digital twins built from brain MRI could deepen understanding of Alzheimer's disease, Parkinson's disease and multiple sclerosis. They could also support efforts to prevent and treat these diseases. Tools for validation, synthetic data and regulatory review could help healthcare agencies adopt such data-driven technologies safely.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Juan Cui
University of Nebraska-Lincoln, NE·Biomedical Engineering
Build a hybrid mechanistic and artificial-intelligence digital twin of skeletal muscle that predicts adaptation across different activity levels and metabolic states, organized around five interacting modules spanning mechanical loading, protein turnover, inflammation, regeneration and metabolism.
Kaizheng Wang
Columbia University, NY·Mathematics & Statistics·Early-career
Develop methods to measure the overall fidelity of black-box generative AI models using effective sample size, an interpretable estimate of how much reliable information synthetic data contain.
Jonghyun Lee
University of Hawaii at Manoa, HI·Earth & Environmental Science
Build hybrid surrogate models from neural operators, networks that imitate expensive simulations, coupled through an open-source framework so groundwater–ocean exchange is simulated quickly while conserving mass at the land–sea boundary.
The school
University of Minnesota: 88 labs on PI Pages, $1.4B a year on research, 722 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.