System and method for fully automatic LV segmentation of myocardial first-pass perfusion images

A computerized system of modeling myocardial tissue perfusion, comprising:

• a computer receiving MRI image data, the computer comprising a processor and a memory storing computer implemented software configured to implement a computerized method comprising the following steps:
• acquiring a plurality of original frames of magnetic resonance imaging (MRI) data representing images of a heart of a subject;
• developing a manually segmented set of ground truth frames from the original frames;
• applying training augmentation techniques to a training set of the originals frame of MRI data;
• training at least one convolutional neural network (CNN) to segment the training set of frames according to the ground truth frames;
• testing the CNN with a set of test images from the plurality of original frames;
• pre-processing the test images to create a corresponding set of input test frames;
• applying the respective input test frames to a trained CNN for segmenting an endocardium layer and an epicardium layer within the respective images of the input test frames;
• and
• calculating myocardial blood flow into the myocardium from segmented images of the input test frames.