Change search
ReferencesLink to record
Permanent link

Direct link
Automatic Localization of Bounding Boxes forSubcortical Structures in MR Images UsingRegression Forests
KTH, School of Computer Science and Communication (CSC).
2013 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Automatisk Lokalisering av Hjärnstrukturer i MR-bilder medhjälp av Regression Forests (Swedish)
Abstract [en]

Manual delineation of organs at risk in MR images is a very time consuming

task for physicians, and to be able to automate the process is therefore

highly desirable. This thesis project aims to explore the possibility of using

regression forests to nd bounding boxes for general subcortical structures.

This is an important preprocessing step for later implementations of full

segmentation, to improve the accuracy, and also to reduce the time consumption.

An algorithm suggested by Criminisi et al. is implemented and

extended to MR images. The extension also includes using a greater pool of

used feature types. The obtained results are very good, with an average Jaccard

similarity coecient as high as 0.696, and center mean error distance

as low as 3.14 mm. The algorithm is very fast, and is able to predict the

location of 43 bounding boxes within 14 seconds. These results indicate that

regression forests are well suited as the method of choice for preprocessing

before a full segmentation.

Abstract [sv]

Manuell segmentering av riskorgan i MR-bilder är en väldigt tidskrävande

uppgift för läkare. Att kunna automatisera denna process vore därför av

stor nytta. I detta examensarbete har vi undersökt möjligheten att använda

regression forests för att hitta en minsta bounding box för olika strukturer

i hjärnan. Detta är ett viktigt steg för att snabba upp och öka precisionen

hos en senare komplett segmentering. En algoritm utvecklad av Criminisi

med era utvidgas till att användas pa MR bilder och innefatta en rikare

bas av möjliga funktioner. De resultat som fås fram är väldigt bra, med en

genomsnittlig Jaccard similarity coecient på 0.696 och en genomsnittlig

feluppskattning av bounding box centrum pa 3.14 mm. Algoritmen är även

väldigt snabb och den lokaliserar bounding boxes for 43 strukturer på 14 s.

Dessa resultat visar tydligt att algoritmen kan användas som ett steg innan

komplett segmentering.

Place, publisher, year, edition, pages
National Category
Computer Science
URN: urn:nbn:se:kth:diva-142391OAI: diva2:700083
Educational program
Master of Science in Engineering - Computer Science and Technology
Available from: 2014-03-12 Created: 2014-03-03 Last updated: 2014-03-12Bibliographically approved

Open Access in DiVA

fulltext(2311 kB)115 downloads
File information
File name FULLTEXT01.pdfFile size 2311 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 115 downloads
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

Total: 41 hits
ReferencesLink to record
Permanent link

Direct link