Surgical Planning Laboratory - Brigham & Women's Hospital - Boston, Massachusetts USA - a teaching affiliate of Harvard Medical School

Surgical Planning Laboratory

The Publication Database hosted by SPL

All Publications | Upload | Advanced Search | Gallery View | Download Statistics | Help | Import | Log in

4D Active Cut: An Interactive Tool for Pathological Anatomy Modeling

Institution:
1Scientific Computing and Imaging Institute ; School of Computing, University of Utah.
2Institute for Neuroimaging and Informatics, University of Southern California, Los Angeles, CA, USA.
3Brain Injury Research Center, University of California, Los Angeles, CA, USA.
Publisher:
ISBI 2014
Publication Date:
Apr-2014
Journal:
Proc IEEE Int Symp Biomed Imaging
Volume Number:
2014
Pages:
529-32
Citation:
Proc IEEE Int Symp Biomed Imaging. 2014 Apr;2014:529-32.
PubMed ID:
25356193
PMCID:
PMC4209480
Keywords:
Active learning, Markov Random Fields; , graph cuts, longitudinal MRI, semi-supervised learning
Appears in Collections:
NA-MIC
Sponsors:
U54 EB005149/EB/NIBIB NIH HHS/United States
Generated Citation:
Wang B., Liu W., Prastawa M., Irimia A., Vespa P.M., van Horn J.D., Fletcher P.T., Gerig G. 4D Active Cut: An Interactive Tool for Pathological Anatomy Modeling. Proc IEEE Int Symp Biomed Imaging. 2014 Apr;2014:529-32. PMID: 25356193. PMCID: PMC4209480.
Downloaded: 732 times. [view map]
Paper: Download, View online
Export citation:
Google Scholar: link

4D pathological anatomy modeling is key to understanding complex pathological brain images. It is a challenging problem due to the difficulties in detecting multiple appearing and disappearing lesions across time points and estimating dynamic changes and deformations between them. We propose a novel semi-supervised method, called 4D active cut, for lesion recognition and deformation estimation. Existing interactive segmentation methods passively wait for user to refine the segmentations which is a difficult task in 3D images that change over time. 4D active cut instead actively selects candidate regions for querying the user, and obtains the most informative user feedback. A user simply answers 'yes' or 'no' to a candidate object without having to refine the segmentation slice by slice. Compared to single-object detection of the existing methods, our method also detects multiple lesions with spatial coherence using Markov random fields constraints. Results show improvement on the lesion detection, which subsequently improves deformation estimation.

Additional Material
1 File (196.334kB)
Wang-ISBI2014-fig2.jpg (196.334kB)