Development of deep learning pipeline for automatic segmentation and classification of cardiac magnetic resonance images

Heart disease is the main reason of death worldwide. One way to understand better and detect heart diseases without need for biopsy via surgery is by using medical imaging such as magnetic resonance imaging (MRI). Cardiac magnetic resonance is a specific kind of MRI which allows great visualization of inner parts of the heart and can be used for measuring the size of the heart and its chambers, which can be very useful for understanding blood flow and other potential markers of disease. One problem with modern technologies for measuring parts of the heart is that they are often unreliable because of the data complexity. In this project, we use advanced artificial intelligence techniques to solve that problem. Our techniques are going to be used to obtain better representations of the internal chambers of the heart which can be useful for assessing several kinds of heart diseases.

Faculty Supervisor:

Richard Frayne

Student:

Luis Souto Maior Neto

Partner:

Circle Cardiovascular Imaging Inc

Discipline:

Engineering - biomedical

Sector:

Medical devices

University:

University of Calgary