Segmentation of pelvic vessels in pediatric MRI using a patch-based deep learning approach
Abstract
In this paper, we propose a patch-based deep learning ap-
proach to segment pelvic vessels in 3D MRI images of pediatric patients.
For a given T2 weighted MRI volume, a set of 2D axial patches are
extracted using a limited number of user-selected landmarks. In order
to take into account the volumetric information, successive 2D axial
patches are combined together, producing a set of pseudo RGB color
images. These RGB images are then used as input for a convolutional
neural network (CNN), pre-trained on the ImageNet dataset, which re-
sults into both segmentation and vessel labeling as veins or arteries. The
proposed method is evaluated on 35 MRI volumes of pediatric patients,
obtaining an average segmentation accuracy in terms of Average Sym-
metric Surface Distance of ASSD = 0.89 ± 0.07 mm and Dice Index of
DC = 0.79 ± 0.02.