Brain Tissue Classification with Automated Generation of Training Data Improved by Deformable Registration

SCHWARZ, Daniel and Tomáš KAŠPÁREK. Brain Tissue Classification with Automated Generation of Training Data Improved by Deformable Registration. Online. W.G.Kropatsch, M. Kampel, A. Hanbury (Eds.). In LECTURE NOTES IN COMPUTER SCIENCE. Berlin, Heidelberg: Springer-Verlag, 2007. p. 301-308. ISBN 978-3-540-74271-5. [citováno 2024-04-24]

Basic information

• Original name: Brain Tissue Classification with Automated Generation of Training Data Improved by Deformable Registration
• Name in Czech: Klasifikace mozkových tkání s automatickým generováním trénovacích dat vylepšeným pružnou registrací
• Authors: SCHWARZ, Daniel (203 Czech Republic, guarantor) and Tomáš KAŠPÁREK (203 Czech Republic); W.G.Kropatsch, M. Kampel, A. Hanbury (Eds.).
• Edition: Berlin, Heidelberg, LECTURE NOTES IN COMPUTER SCIENCE, p. 301-308, 8 pp. 2007.
• Publisher: Springer-Verlag

Other information

• Original language: English
• Type of outcome: Proceedings paper
• Field of Study: 20200 2.2 Electrical engineering, Electronic engineering, Information engineering
• Country of publisher: Austria
• Confidentiality degree: is not subject to a state or trade secret
• Impact factor: Impact factor: 0.402 in 2005
• RIV identification code: RIV/00216224:14110/07:00020428
• Organization unit: Faculty of Medicine
• ISBN: 978-3-540-74271-5
• ISSN: 0302-9743
• UT WoS: 000249585600038
• Keywords in English: image analysis;image registration;MRI;computational neuroanatomy;brain tissue classification;atlas-based segmentation
• Tags: atlas-based segmentation, brain tissue classification, computational neuroanatomy, Image analysis, image registration, MRI
• Tags: International impact, Reviewed

Abstract

Methods of tissue classification in MRI brain images play a significant role in computational neuroanatomy, particularly in automated ROI-based volumetry. A well-known and very simple k-NN classifier is used here without the need for user input during the training process. The classifier is trained with the use of tissue probability maps which are available in selected digital atlases of brain. The influence of misalignement between images and the tissue probability maps on the classifier's efficiency is studied in this paper. Deformable registration is used here to align the images and maps. The classifier's efficiency is tested in an experiment with data obtained from standard Simulated Brain Database.

Abstract (in Czech)

Metody klasifikace tkání hrají důležitou roli ve výpočetní neuroanatomii, zvláště pak automatické volumetrii na základě oblastí zájmu. Dobře známý a velmi jednoduchý klasifikátro k-NN je zde použit bez nutnosti uživatelského vstupu ve fázi trénování. Klasifikátor je natrénováns využitím tkáňových pravděpodobnostních map. Studován je vliv rozlícování mezi obrazy a mapami na efektivitu klasifikátoru. Pro slícování je využita pružná registrace. Efektivita je vyhodnocena na simulových datech ze Simulated Brain Database.

Links

• GP102/07/P263, research and development project: Name: Nelineární multimodální registrace pro automatickou morfometrii obrazů mozku z MRI založenou na anatomicky omezených prostorových deformacích

Investor: Czech Science Foundation, Nonlinear multimodal registration for automatic morphometry of MRI brain images based on anatomically constrained spatial deformations

• MSM0021622404, plan (intention): Name: Vnitřní organizace a neurobiologické mechanismy funkčních systémů CNS

Investor: Ministry of Education, Youth and Sports of the CR, The internal organisation and neurobiological mechanisms of functional CNS systems under normal and pathological conditions.