Automatic ischemic stroke segmentation using various techniques

Ušinskas, Andrius; Pranckevičienė, Erinija; Wittenberg, Thomas; Hastreiter, Peter; Tomandl, Bernd F

Use this URL to cite this publication: https://hdl.handle.net/20.500.14911/117971

Automatic ischemic stroke segmentation using various techniques

Details

Publication Type (CRIS)

Straipsnis konferencijos medžiagoje Web of Science duomenų bazėje / Article in conference proceedings in Web of Science database (P1a1)

Publication Type (eLABa)

Straipsnis konferencijos darbų leidinyje Web of Science DB / Article in conference proceedings Web of Science DB (P1a)

Author(s)

Author	Affiliation
Ušinskas, Andrius	Elektroninių sistemų katedra / Department of Electronic Systems (0549)
Pranckevičienė, Erinija	Kauno technologijos universitetas
Wittenberg, Thomas	Fraunhofer Institute for Integrated Circuits-Applied Electronics, Erlangen, Germany
Hastreiter, Peter	University Erlangen-Nuremberg, Erlangen, Germany
Tomandl, Bernd F	University Erlangen-Nuremberg, Erlangen, Germany

Title

Automatic ischemic stroke segmentation using various techniques

[en]

Andrius Usinskas, Erinija Pranckeviciene, Thomas Wittenberg, Peter Hastreiter, Bernd F. Tomandl

Is part of

Advances in soft computing : neural networks and soft computing : proceedings of the Sixth International Conference on Neural Network and Soft Computing, Zakopane, Poland, June 11-15, 2002

Published In

Year	Start Page	End Page
2002	498	503

Publisher

Heidelberg : Physica-Verlag, 2003

Referenced in Database(s)(DBs)

ISI Proceedings

Extent

p. 498-503

URI

URI
https://hdl.handle.net/20.500.14911/117971

Science / Art Area

Gamtos mokslai / Natural Sciences (N)

Field of Science / Art

Informatika / Informatics (N009)

Elektros ir elektronikos inžinerija / Electrical and electronic engineering (T001)

Informatikos inžinerija / Informatics engineering (T007)

Abstract (en)

Seven different methods aiming at automatic segmentation of human brain ischemic area in the computerized tomography scans are compared. The novel technique, based on the biologically inspired artificial neural networks architecture, is applied for the brain ischemic stroke recognition. The segmentation techniques were evaluated by the experts radiologists. The best viability showed Histogram, Gray level co-occurrence matrix, Mean and standard deviation methods, and Supervised Artificial Neural Networks techniques.