Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Active Learning for Interactive 3D Image Segmentation Andrew Top1

Summary: Active Learning for Interactive 3D Image Segmentation
Andrew Top1
, Ghassan Hamarneh1
, and Rafeef Abugharbieh2
Medical Image Analysis Lab, Simon Fraser University
Biomedical Signal and Image Computing Lab, University of British Columbia
{atop,hamarneh}@sfu.ca, rafeef@ece.ubc.ca
Abstract. We propose a novel method for applying active learning strategies to
interactive 3D image segmentation. Active learning has been recently introduced
to the field of image segmentation. However, so far discussions have focused on
2D images only. Here, we frame interactive 3D image segmentation as a classifi-
cation problem and incorporate active learning in order to alleviate the user from
choosing where to provide interactive input. Specifically, we evaluate a given seg-
mentation by constructing an "uncertainty field" over the image domain based on
boundary, regional, smoothness and entropy terms. We then calculate and high-
light the plane of maximal uncertainty in a batch query step. The user can proceed
to guide the labeling of the data on the query plane, hence actively providing ad-
ditional training data where the classifier has the least confidence. We validate


Source: Abugharbieh, Rafeef - Department of Electrical and Computer Engineering, University of British Columbia


Collections: Biology and Medicine; Computer Technologies and Information Sciences