Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Segmentation of White Matter Lesions – Using Multispectral MRI and Cascade of Support Vector Machines with Active Learning.
KTH, School of Computer Science and Communication (CSC).
2011 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Segmentation of White Matter Lesions

Using Multispectral MRI and Cascade of Support Vector Machines with Active Learning

Soheil Damangir

December 2011

The areas in cerebral white matter that appear hyperintense on T2-weighted (T2) magnetic resonance image (MRI) and hypointense on computed tomography (CT) are commonly referred as white matter lesions (WML). WML have been consistently related to vascular risk factors and they could have predictive value for future stroke, dementia and functional decline in activities of daily living.

Although, there is an important body of evidence regarding the importance of WML, the segmentation of these changes on different MRI modalities is not yet, validated and standardized.

The aim of this thesis was to segment the WML using multispectral MRIs based on a fully automated method.

A new method using a cascade of support vector machine (SVM) classifiers with active learning is proposed for the segmentation of the WML. It has been shown that this training method not only increase the speed of classification, but also helps to boost the accuracy of classification in biased datasets.

The classification method is put together with preprocessing and post-processing to form a general segmentation framework. To validate the method, a model was trained using two subjects and tested against the remaining 100 subjects. Results were validated against manually outlined WML which is the method that could provide replicable results between studies so far. Also, comparisons with other automatic segmentation procedures were performed. Results of this study proved to be comparable with the results from manual outlining in terms of both sensitivity and specificity

Abstract [sv]

Automatisk Segmentering av Vitsubstans Skador

i Magnetresonans Tomografi Bilder

Soheil Damangir

December 2011

Områden i hjärnans vitsubstans som verkar hyper-intensiva på T2 magnetresonans tomografi (MRT) bilder och hypo-intensiva på dator tomografi (DT) är så kallade vitsubstans skador. Vitsubstans skador är relaterade till vaskulära riskfaktorer och man tror att personer med dessa typer av skador löper större risk att få framtida stroke och utveckla olika former av demens sjukdomar.

även fast det finns bevis som stödjer betydelsen av vitsubstans skador så finns det fortfarande inga segmenterings metoder för kvantifiering av dessa skador som är validerade och standardiserade.

Syftet med detta examensarbete är att segmentera vitsubstans skador med multispektrala MRT bilder med hjälp av en automatiserad metod.

Vi föreslår en ny metod som använder kaskadkopplad stödvektormaskin (SVM) klassificering med aktivt inlärning. Det har visat sig att denna metod inte bara ökar hastigheten på klassificeringen, utan även bidrar till att öka antalet korrekt klassificerade dataset.

Inom denna klassificerings metod ingår både förbehandling och efterbehandling av datat. Två dataset användes för att träna metoden och resterande hundra för testning. Resultatet av den automatiserade metoden validerades emot manuell utlinjering. Manuell utlinjering är den enda metod som hittills kunnat producera jämförbara resultat mellan mätningar. Dessutom har jämförelser med andra automatiska segmentering metoder utförts. Våra resultat visar att vi med hjälp av en automatiserad metod kan erhålla jämförbara resultat med manuell utlinjering av vitsubstans skador.

Place, publisher, year, edition, pages
2011.
Series
Trita-CSC-E, ISSN 1653-5715 ; 2011:147
National Category
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-130680OAI: oai:DiVA.org:kth-130680DiVA: diva2:654127
Educational program
Master of Science - Systems, Control and Robotics
Uppsok
Technology
Supervisors
Examiners
Available from: 2013-10-07 Created: 2013-10-07

Open Access in DiVA

No full text

Other links

http://www.nada.kth.se/utbildning/grukth/exjobb/rapportlistor/2011/rapporter11/damangir_soheil_11147.pdf
By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 128 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf