A Heuristic Image Search Algorithm for Active Shape Model Segmentation of the Caudate Nucleus and Hippocampus in Brain MR Images of Children with FASD

dc.contributor.authorEicher, A A
dc.contributor.authorMarais, P
dc.contributor.authorWarton, C
dc.contributor.authorJacobson, S W
dc.contributor.authorJacobson, J L
dc.contributor.authorMolteno, C D
dc.contributor.authorMeintjes, E M
dc.date.accessioned2016-04-01T12:52:04Z
dc.date.available2016-04-01T12:52:04Z
dc.date.issued2012
dc.date.updated2016-04-01T12:39:36Z
dc.description.abstractMagnetic Resonance Imaging provides a non-invasive means to study the neural correlates of Fetal Alcohol Spectrum Disorder (FASD) - the most common form of preventable mental retardation worldwide. One approach aims to detect brain abnormalities through an assessment of volume and shape of two sub-cortical structures, the caudate nucleus and hippocampus. We present a method for automatically segmenting these structures from high-resolution MR images captured as part of an ongoing study into the neural correlates of FASD. Our method incorporates an Active Shape Model, which is used to learn shape variation from manually segmented training data. A modified discrete Geometrically Deformable Model is used to generate point correspondence between training models. An ASM is then created from the landmark points. Experiments were conducted on the image search phase of ASM segmentation, in order to find the technique best suited to segmentation of the hippocampus and caudate nucleus. Various popular image search techniques were tested, including an edge detection method and a method based on grey profile Mahalanobis distance measurement. A novel heuristic image search method was also developed and tested. This heuristic method improves image segmentation by taking advantage of characteristics specific to the target data, such as a relatively homogeneous tissue colour in target structures. Results show that ASMs that use the heuristic image search technique produce the most accurate segmentations. An ASM constructed using this technique will enable researchers to quickly, reliably, and automatically segment test data for use in the FASD study.en_ZA
dc.identifierhttp://dx.doi.org/10.18489/sacj.v49i0.143
dc.identifier.apacitationEicher, A. A., Marais, P., Warton, C., Jacobson, S. W., Jacobson, J. L., Molteno, C. D., & Meintjes, E. M. (2012). A Heuristic Image Search Algorithm for Active Shape Model Segmentation of the Caudate Nucleus and Hippocampus in Brain MR Images of Children with FASD. <i>South African Computer Journal</i>, http://hdl.handle.net/11427/18519en_ZA
dc.identifier.chicagocitationEicher, A A, P Marais, C Warton, S W Jacobson, J L Jacobson, C D Molteno, and E M Meintjes "A Heuristic Image Search Algorithm for Active Shape Model Segmentation of the Caudate Nucleus and Hippocampus in Brain MR Images of Children with FASD." <i>South African Computer Journal</i> (2012) http://hdl.handle.net/11427/18519en_ZA
dc.identifier.citationicher, A. A., Marais, P., Warton, C., Jacobson, S. W., Jacobson, J. L., Molteno, C. D., & Meintjes, E. M. (2012). A heuristic image search algorithm for Active Shape Model segmentation of the caudate nucleus and hippocampus in brain MR images of children with FASD. South African Computer Journal, 49.en_ZA
dc.identifier.issn1015-7999en_ZA
dc.identifier.ris TY - Journal Article AU - Eicher, A A AU - Marais, P AU - Warton, C AU - Jacobson, S W AU - Jacobson, J L AU - Molteno, C D AU - Meintjes, E M AB - Magnetic Resonance Imaging provides a non-invasive means to study the neural correlates of Fetal Alcohol Spectrum Disorder (FASD) - the most common form of preventable mental retardation worldwide. One approach aims to detect brain abnormalities through an assessment of volume and shape of two sub-cortical structures, the caudate nucleus and hippocampus. We present a method for automatically segmenting these structures from high-resolution MR images captured as part of an ongoing study into the neural correlates of FASD. Our method incorporates an Active Shape Model, which is used to learn shape variation from manually segmented training data. A modified discrete Geometrically Deformable Model is used to generate point correspondence between training models. An ASM is then created from the landmark points. Experiments were conducted on the image search phase of ASM segmentation, in order to find the technique best suited to segmentation of the hippocampus and caudate nucleus. Various popular image search techniques were tested, including an edge detection method and a method based on grey profile Mahalanobis distance measurement. A novel heuristic image search method was also developed and tested. This heuristic method improves image segmentation by taking advantage of characteristics specific to the target data, such as a relatively homogeneous tissue colour in target structures. Results show that ASMs that use the heuristic image search technique produce the most accurate segmentations. An ASM constructed using this technique will enable researchers to quickly, reliably, and automatically segment test data for use in the FASD study. DA - 2012 DB - OpenUCT DP - University of Cape Town J1 - South African Computer Journal LK - https://open.uct.ac.za PB - University of Cape Town PY - 2012 SM - 1015-7999 T1 - A Heuristic Image Search Algorithm for Active Shape Model Segmentation of the Caudate Nucleus and Hippocampus in Brain MR Images of Children with FASD TI - A Heuristic Image Search Algorithm for Active Shape Model Segmentation of the Caudate Nucleus and Hippocampus in Brain MR Images of Children with FASD UR - http://hdl.handle.net/11427/18519 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/18519
dc.identifier.vancouvercitationEicher AA, Marais P, Warton C, Jacobson SW, Jacobson JL, Molteno CD, et al. A Heuristic Image Search Algorithm for Active Shape Model Segmentation of the Caudate Nucleus and Hippocampus in Brain MR Images of Children with FASD. South African Computer Journal. 2012; http://hdl.handle.net/11427/18519.en_ZA
dc.languageengen_ZA
dc.publisherSouth African Institute of Computer Scientists and Information Technologistsen_ZA
dc.publisher.departmentDepartment of Computer Scienceen_ZA
dc.publisher.facultyFaculty of Scienceen_ZA
dc.publisher.institutionUniversity of Cape Town
dc.rightsCreative Commons Attribution 4.0 International (CC BY 4.0)*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en_ZA
dc.sourceSouth African Computer Journalen_ZA
dc.source.urihttp://sacj.cs.uct.ac.za/
dc.subject.otherActive Shape Model
dc.subject.otherGeometrically Deformable Model
dc.subject.otherASM
dc.titleA Heuristic Image Search Algorithm for Active Shape Model Segmentation of the Caudate Nucleus and Hippocampus in Brain MR Images of Children with FASDen_ZA
dc.typeJournal Articleen_ZA
uct.type.filetype
uct.type.filetypeText
uct.type.filetypeImage
uct.type.publicationResearchen_ZA
uct.type.resourceArticleen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Eicher_A_Heuristic_Image_Search_2012.pdf
Size:
2.45 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections