liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Real-Time Interactive 3D Tumor Segmentation Using a Fast Level-Set Algorithm
Linköping University, Department of Medical and Health Sciences, Division of Radiological Sciences. Linköping University, Faculty of Medicine and Health Sciences. Linköping University, Center for Medical Image Science and Visualization (CMIV). KTH Royal Institute Technology, Sweden; Sectra AB, S-58330 Linkoping, Sweden.ORCID iD: 0000-0002-0442-3524
Linköping University, Department of Medical and Health Sciences, Division of Radiological Sciences. Linköping University, Faculty of Medicine and Health Sciences. Region Östergötland, Center for Diagnostics, Department of Radiology in Linköping. Linköping University, Center for Medical Image Science and Visualization (CMIV).ORCID iD: 0000-0002-4111-1693
Region Östergötland, Center for Diagnostics, Department of Radiology in Linköping. Linköping University, Faculty of Medicine and Health Sciences. Linköping University, Department of Medical and Health Sciences, Division of Radiological Sciences.
Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).ORCID iD: 0000-0002-9368-0177
Show others and affiliations
2015 (English)In: Journal of Medical Imaging and Health Informatics, ISSN 2156-7018, E-ISSN 2156-7026, Vol. 5, no 8, 1998-2002 p.Article in journal (Refereed) PublishedText
Abstract [en]

A new level-set based interactive segmentation framework is introduced, where the algorithm learns the intensity distributions of the tumor and surrounding tissue from a line segment drawn by the user from the middle of the lesion towards the border. This information is used to design a likelihood function, which is then incorporated into the level-set framework as an external speed function guiding the segmentation. The endpoint of the input line segment sets a limit to the propagation of 3D region, i.e., when the zero-level-set crosses this point, the propagation is forced to stop. Finally, a fast level set algorithm with coherent propagation is used to solve the level set equation in real time. This allows the user to instantly see the 3D result while adjusting the position of the line segment to tune the parameters implicitly. The "fluctuating" character of the coherent propagation also enables the contour to coherently follow the mouse cursors motion when the user tries to fine-tune the position of the contour on the boundary, where the learned likelihood function may not necessarily change much. Preliminary results suggest that radiologists can easily learn how to use the proposed segmentation tool and perform relatively accurate segmentation with much less time than the conventional slice-by-slice based manual procedure.

Place, publisher, year, edition, pages
AMER SCIENTIFIC PUBLISHERS , 2015. Vol. 5, no 8, 1998-2002 p.
Keyword [en]
Interactive Image Segmentation; Level Set; Coherent Propagation; Tumor Segmentation
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-125166DOI: 10.1166/jmihi.2015.1685ISI: 000368564700072OAI: oai:DiVA.org:liu-125166DiVA: diva2:903382
Available from: 2016-02-15 Created: 2016-02-15 Last updated: 2016-04-24

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Wang, ChunliangDahlström, NilsFransson, Sven GöranLundström, ClaesSmedby, Örjan
By organisation
Division of Radiological SciencesFaculty of Medicine and Health SciencesCenter for Medical Image Science and Visualization (CMIV)Department of Radiology in LinköpingMedia and Information TechnologyFaculty of Science & Engineering
In the same journal
Journal of Medical Imaging and Health Informatics
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 235 hits
ReferencesLink to record
Permanent link

Direct link