Pseudo-continuous arterial spin labeling (pCASL) requires careful planning of the labeling plane to achieve high labeling efficiency, which makes the quality of the imaging results dependent on the experience of the operator. Here we demonstrate the feasibility of using a convolutional neural network to automatically predict an appropriate labeling position based on angiography images, thereby allowing for fully automatic pCASL perfusion scans.
This abstract and the presentation materials are available to members only; a login is required.