Scientific Diary of Dr. Bagci

MICCAI 2017 paper is accepted: CardiacNET!

I and my Ph.D student AliAsghar Mortazi have published an article in MICCAI 2017, the most prominent peer-reviewed conference in medical image computing.

The study achieves the state of the art segmentation accuracy and efficiency for left atrium and proximal pulmonary vein from cardiac MRI. The team collaborates with the Florida hospital’s radiologist Dr. Jeremy Burt and King’s College London’s Drs. Rhode and Karim.

Paper’s details are below. Please click on the title to download the PDF:
Aliasghar Mortazi, Rashed Karim, Kawal Rhode, Jeremy Burt, Ulas Bagci, CardiacNET: Segmentation of Left Atrium and Proximal Pulmonary Veins from MRI Using Multi-View CNN, MICCAI 2017, Quebec City, Quebec, Canada, September 10-14, 2017.
First row shows sample MRI slices from S, C, and A views (red contour is ground-truth and green one is output of proposed method). Second-to-fifth rows: 3D surface visualization for the ground-truth and the output generated by the proposed method w.r.t simple fusion (F), adaptive fusion (AF), and the new loss function (SP).