Guiding 3D U-nets with signed distance fi elds for creating 3D models from images

Kristine Aavild Juhl, Rasmus Reinhold Paulsen, Anders Bjorholm Dahl, Vedrana Andersen Dahl, Ole De Backer, Klaus Fuglsang Kofoed, Oscar Camara

Keywords: Signed distance fields, pixel-wise regression, left atrial appendage

TL;DR: 3D segmentation results can be improved by guiding the deep network with signed distance fields instead of traditional binary labelmaps.

Abstract:

Morphological analysis of the left atrial appendage is an important tool to assess risk of
ischemic stroke. Most deep learning approaches for 3D segmentation is guided by binary
labelmaps, which results in voxelized segmentations unsuitable for morphological analysis.
We propose to use signed distance fields to guide a deep network towards morphologically
consistent 3D models. The proposed strategy is evaluated on a synthetic dataset of simple
geometries, as well as a set of cardiac computed tomography images containing the left atrial
appendage. The proposed method produces smooth surfaces with a closer resemblance to
the true surface in terms of segmentation overlap and surface distance.

Code Of Conduct: I have read and accept the code of conduct.