Diana M. Marin-Castrillon1, Arnaud Boucher1, Siyu Lin1, Chloe Bernard2, Marie-Catherine Morgant1,2, Alexandre Cochet1,3, Alain Lalande 1,3, Benoit Presles 1, and Olivier Bouchot 1,2
1ImViA Laboratory, University of Burgundy, Dijon, France, 2Department of Cardio-Vascular and Thoracic Surgery, University Hospital of Dijon, Dijon, France, 3Department of Medical Imaging, University Hospital of Dijon, Dijon, France
1ImViA Laboratory, University of Burgundy, Dijon, France, 2Department of Cardio-Vascular and Thoracic Surgery, University Hospital of Dijon, Dijon, France, 3Department of Medical Imaging, University Hospital of Dijon, Dijon, France
In this work, we propose an automatic 3D PC-MRI segmentation of the
aorta in systole using a multi-atlas approach. The evaluation done on 16
patients provide accurate automatic segmentations compared to the manual ones.
Figure 2. Cases with the highest
(top) and the lowest
(bottom) performance. Hausdorff
map is represented as a heat map in which the regions with intense yellows
represent high errors and dark or black represent errors close to or equal to
zero.
Figure
1. Average performance of the method during the
atlas selection process with respect to the normalized
correlation coefficient
metric. The similarities obtained between the target image and the warped
images are ordered from the highest to the lowest, to perform the majority
voting process with the best mask and add one by one the next best ones until
all the images in the atlas are used.
