SOURCE-LINKED INTELLIGENCE

A Data-driven Approach to Microstructural Imaging

CORDIS · observation · Publication date unknown

se multiple, independent contrast mechanisms that will provide the necessary information to distinguish reliably between microscopic substrates. Rather than relying on preconceived models, I will use machine learning to learn the appropriate models directly from the data. Rather than performing a posteriori histological validation of these new microstructural models, I will acquire a priori histological data to directly inform this learning process, guaranteeing, for the first time, a close match between microstructural readouts obtained from MRI and invasive histology. Through these innovations, ADAMI will advance the field of medical imaging by introducing a groundbreaking data-driven approach to microstructure imaging which will significantly impact the understanding, diagnosis, and monitoring of brain diseases and beyond. Magnetic resonance imaging, multimodal, diffusion magnetic resonance imaging, tissue microstructure, data-driven analysis, machine learning, deep learning, artificial intelligence, optimal experimental design, neurodegeneration, non-invasive

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

1999706

unit

EUR