3D FractalNet: Dense Volumetric Segmentation for Cardiovascular MRI Volumes
Refereed conference paper presented and published in conference proceedings

Times Cited
Altmetrics Information

Other information
AbstractCardiac image segmentation plays a crucial role in various medical applications. However, differentiating branchy structures and slicing fuzzy boundaries from cardiovascular MRI volumes remain very challenging tasks. In this paper, we propose a novel deeply-supervised 3D fractal network for efficient automated whole heart and great vessel segmentation in MRI volumes. The proposed 3D fractal network takes advantage of fully convolutional architecture to perform efficient, precise and volume-to-volume prediction. Notably, by recursively applying a single expansion rule, we construct our network in a novel self-similar fractal scheme and thus promote it in combining hierarchical clues for accurate segmentation. More importantly, we employ deep supervision mechanism to alleviate the vanishing gradients problem and improve the training efficiency of our network on small medical image dataset. We evaluated our method on the HVSMR 2016 Challenge dataset. Extensive experimental results demonstrated the superior performance of our method, ranking top in both two phases.
All Author(s) ListLequan Yu, Xin Yang, Jing Qin, Pheng-Ann Heng
Name of ConferenceInternational Workshop on Reconstruction and Analysis of Moving Body Organs, International Workshop on Whole-Heart and Great Vessel Segmentation from 3D Cardiovascular MRI in Congenital Heart Disease
Start Date of Conference17/10/2016
End Date of Conference21/10/2016
Place of ConferenceAthens
Country/Region of ConferenceGreece
Proceedings TitleReconstruction, Segmentation, and Analysis of Medical Images
Series TitleLecture Notes in Computer Science
Volume Number10129
Pages103 - 110
LanguagesEnglish-United States

Last updated on 2020-24-05 at 23:49