University of Michigan

Yue Cao

James Balter

Peng Wang

Josiah J Simeth

Lianli Liu

Reza Farjam

Adam Johansson

The following relates generally to motion prediction in magnetic resonance (MR) imaging. In some embodiments, a 'modular' approach is taken to motion correction. That is, individual motion sources (e.g., a patient's breathing, heartbeat, stomach contractions, peristalsis, and so forth) are accounted for individually in the motion correction. In some embodiments, to correct for a particular motion source, a reference state is created from a volume of interest (VOI), and other states are created and deformably aligned to the reference state.

Hierarchical motion modeling from dynamic magnetic resonance imaging

A robust liver function quantification algorithm to quantify regional and global liver function using temporally sparse-sampled multi-phase MRI with gadoxetic-acid injection is provided. The liver function quantification algorithm may be utilized in a liver function analysis server and indications of a patient's liver function may be provided for display on a healthcare professional's network-enabled device. The use of a single clinical multi-phase MRI with gadoxetic-acid injection may provide 1) regional liver function assessment, 2) global liver function assessment, and 3) risk analysis for future liver intervention.

Technology for robust regional and global liver function quantification from clinical multi-phase MRI

Physiological imaging-defined subvolumes of tissues/disease are identified to yield spatially-defined prognostic and/or predictive indicators and/or focal therapy targets within such tissues, in particular tumors, for evaluation over time, for example, prior to and after a therapy treatment. Medical image data is analyzed to delineate subvolumes of tissue based upon multiple physiological, metabolic, and biological imaging properties, where those subvolumes are extracted and analyzed in a probabilistic manner to associate with one or more abnormal or disease phenotype conditions.

Subvolume identification for prediction of treatment outcome

A computer-implemented method is provided for generating patient models from multiple imaging contrast sources which may be, for example from magnetic resonance imaging without computed tomography. The method includes: acquiring multiple sets of image data representing a volume of a patient using magnetic resonance imaging, wherein each set of image data is acquired in a different manner so as to create contrast amongst tissue types of the patient; classifying tissue in each voxel in the volume using the multiple sets of image data as input to a classification algorithm; and generating a patient model for the volume from probability distributions of the classes of tissue as derived from the classification algorithm.

Growing community of inventors

Ann Arbor, MI, United States of America

Yue Cao