Full Text Available

Access Repository
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Cover Image

Development of a tool for automatic segmentation of the cerebellum in MR images of children

The human cerebellar cortex is a highly foliated structure that supports both motor and complex cognitive functions in humans. Magnetic Resonance Imaging (MRI) is commonly used to explore structural alterations in patients with psychiatric and neurological diseases. The ability to detect regional st...

Full description

Saved in:
Main Author: Narayanan, Priya Lakshmi
Other Authors: Ernesta, Meintjes
Format: Thesis
Language:English
Published: Division of Biomedical Engineering 2016
Subjects:
Biomedical Engineering
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1867614290445336576
access_status_str Open Access
author Narayanan, Priya Lakshmi
author2 Ernesta, Meintjes
author_browse Ernesta, Meintjes
Narayanan, Priya Lakshmi
author_facet Ernesta, Meintjes
Narayanan, Priya Lakshmi
author_sort Narayanan, Priya Lakshmi
collection Thesis
description The human cerebellar cortex is a highly foliated structure that supports both motor and complex cognitive functions in humans. Magnetic Resonance Imaging (MRI) is commonly used to explore structural alterations in patients with psychiatric and neurological diseases. The ability to detect regional structural differences in cerebellar lobules may provide valuable insights into disease biology, progression and response to treatment, but has been hampered by the lack of appropriate tools for performing automated structural cerebellar segmentation and morphometry. In this thesis, time intensive manual tracings by an expert neuroanatomist of 16 cerebellar regions on high-resolution T1-weighted MR images of 18 children aged 9-13 years were used to generate the Cape Town Pediatric Cerebellar Atlas (CAPCA18) in the age-appropriate National Institute of Health Pediatric Database (NIHPD) asymmetric template space. An automated pipeline was developed to process the MR images and generate lobule-wise segmentations, as well as a measure of the uncertainty of the label assignments. Validation in an independent group of children with ages similar to those of the children used in the construction of the atlas, yielded spatial overlaps with manual segmentations greater than 70% in all lobules, except lobules VIIb and X. Average spatial overlap of the whole cerebellar cortex was 86%, compared to 78% using the alternative Spatially Unbiased Infra-tentorial Template (SUIT), which was developed using adult images.
format Thesis
id oai:open.uct.ac.za:11427/20262
institution University of Cape Town (South Africa)
language eng
last_indexed 2026-06-10T12:49:41.751Z
license_str Not specified — see source repository
provenance_str_mv Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository
publishDate 2016
publishDateRange 2016
publishDateSort 2016
publisher Division of Biomedical Engineering
publisherStr Division of Biomedical Engineering
record_format dspace
source_str UCTD — University of Cape Town Open Access Repository
spelling oai:open.uct.ac.za:11427/20262 Development of a tool for automatic segmentation of the cerebellum in MR images of children Narayanan, Priya Lakshmi Ernesta, Meintjes Biomedical Engineering The human cerebellar cortex is a highly foliated structure that supports both motor and complex cognitive functions in humans. Magnetic Resonance Imaging (MRI) is commonly used to explore structural alterations in patients with psychiatric and neurological diseases. The ability to detect regional structural differences in cerebellar lobules may provide valuable insights into disease biology, progression and response to treatment, but has been hampered by the lack of appropriate tools for performing automated structural cerebellar segmentation and morphometry. In this thesis, time intensive manual tracings by an expert neuroanatomist of 16 cerebellar regions on high-resolution T1-weighted MR images of 18 children aged 9-13 years were used to generate the Cape Town Pediatric Cerebellar Atlas (CAPCA18) in the age-appropriate National Institute of Health Pediatric Database (NIHPD) asymmetric template space. An automated pipeline was developed to process the MR images and generate lobule-wise segmentations, as well as a measure of the uncertainty of the label assignments. Validation in an independent group of children with ages similar to those of the children used in the construction of the atlas, yielded spatial overlaps with manual segmentations greater than 70% in all lobules, except lobules VIIb and X. Average spatial overlap of the whole cerebellar cortex was 86%, compared to 78% using the alternative Spatially Unbiased Infra-tentorial Template (SUIT), which was developed using adult images. 2016-07-08T10:42:57Z 2016-07-08T10:42:57Z 2015 Doctoral Thesis Doctoral PhD http://hdl.handle.net/11427/20262 eng application/pdf Division of Biomedical Engineering Faculty of Health Sciences University of Cape Town
spellingShingle Biomedical Engineering
Narayanan, Priya Lakshmi
Development of a tool for automatic segmentation of the cerebellum in MR images of children
thesis_degree_str Doctoral
title Development of a tool for automatic segmentation of the cerebellum in MR images of children
title_full Development of a tool for automatic segmentation of the cerebellum in MR images of children
title_fullStr Development of a tool for automatic segmentation of the cerebellum in MR images of children
title_full_unstemmed Development of a tool for automatic segmentation of the cerebellum in MR images of children
title_short Development of a tool for automatic segmentation of the cerebellum in MR images of children
title_sort development of a tool for automatic segmentation of the cerebellum in mr images of children
topic Biomedical Engineering
url http://hdl.handle.net/11427/20262
work_keys_str_mv AT narayananpriyalakshmi developmentofatoolforautomaticsegmentationofthecerebelluminmrimagesofchildren

Similar Items