In this work, we propose a method to aid the 2-D segmentation of short-axis cardiac MRI. In particular, the deformation fields obtained during the registration are used to propagate the labels to all time frames, resulting in a weakly supervised segmentation approach that benefits from the features in unlabelled volumes along with the annotated data. Experimental results over the M\&Ms datasets show that the addition of the synthetically obtained labels to the original dataset yields promising results in the performance and improves the capability of the network to generalise to scanners from different vendors.
Metadata
Item Type:
Conference or Workshop Item (Paper)
Event Type:
Conference
Refereed:
Yes
Uncontrolled Keywords:
Cardiac MRI; Image Segmentation; Semi-Supervised Learning; Image Registration; Medical Imaging