Please select the desired project time frame:
- July 2026
- January 2026
- July 2025
- January 2025
- July 2024
- January 2024
- July 2023
- January 2023
- July 2022
- January 2022
- July 2021
- January 2021
- July 2020
- January 2020
- July 2019
- January 2019
- July 2018
- January 2018
- July 2017
- January 2017
- July 2016
- January 2016
- July 2015
- January 2015
- July 2014
- January 2014
- July 2013
- January 2013
- July 2012
- January 2012
- July 2011
- January 2011
- July 2010
- January 2010
- July 2009
- January 2009
- July 2008
- January 2008
- July 2007
- January 2007
- July 2006
- January 2006
- July 2005
- January 2005
- July 2004
- January 2004
- July 2003
- January 2003
- July 2002
- January 2002
- July 2001
- January 2001
Start of funding 01.07.2026
Body Composition Analysis on MRI Across the Lifespan for Metabolic Health Profiling Utilizing a Visual-Tabular Foundation Model
Prof. Dr. Daniel Rückert
Technische Universität München
School of Medicine and Health - Klinikum rechts der Isar
Prof. Dr. Holden H. Wu
University of California, Los Angeles (UCLA)
Department of Radiology
Obesity and metabolic dysfunction often originate in early childhood and progress across adolescence and adulthood, requiring early metabolic characterization and longitudinal monitoring to guide lifestyle, dietary, and pharmacologic interventions such as GLP-1 receptor agonists. Multi-echo Dixon MRI enables non-invasive metabolic phenotyping through assessment of body composition, including muscle, subcutaneous adipose tissue, visceral adipose tissue, and organ fat such as hepatic fat. However, pediatric MRI translation remains limited by growth-related anatomical variability and scarce annotated pediatric datasets. Foundation models, pre-trained on broad datasets and fine-tuned for downstream tasks, offer a path to generalizable representations that transfer to data-scarce pediatric settings with minimal annotation. This project aims to develop a foundation model for rapid, automated MRI-based metabolic phenotyping by: 1. segmenting multi-class adipose tissue across infants and children where adult-centric models fail; and 2. predicting quantitative body composition metrics, including SAT, VAT, liver volume, and fat fraction.