Machine Learning

The IRIS Lab actively develops and applies deep learning methods to solve challenging problems in neuroimaging, from image reconstruction to anatomical segmentation and parametric mapping. Notable contributions include a 3D convolutional neural network (CNN) that simultaneously estimates CBF and ATT from multi-delay ASL data, bypassing traditional fitting approaches that are sensitive to noise. 

Arterial spin labeling (ASL) is a non-invasive MRI technique that uses magnetically labeled blood water as an endogenous tracer to measure cerebral blood flow (CBF) and arterial transit time (ATT). The IRIS Lab has been a leader in advancing ASL acquisition and analysis, developing deep-learning methods — including 3D convolutional neural networks — to generate high-fidelity parametric perfusion maps from noisy multi-delay ASL data. The lab has also contributed to large-scale clinical trials such as the U.S.