{"id":{"repo_id":"lsu-thes","oai_identifier":"oai:repository.lsu.edu:gradschool_dissertations-1329"},"canonical_url":"https://search.dev.ndltd.org/etd/lsu-thes/oai:repository.lsu.edu:gradschool_dissertations-1329","repository":{"repo_id":"lsu-thes","name":"Lousiana State University","base_url":"https://repository.lsu.edu/do/oai/"},"display":{"title":"Automatic segmentation of magnetic resonance images of the brain","abstract":"Magnetic resonance imaging (MRI) is a technique used primarily in medical settings to produce high quality images of the human body’s internal anatomy. Each image is of a thin slice through the body, with the typical distance between slices being a few millimeters. Brain segmentation is the delineation of one or more anatomical structures within images of the brain. It promotes greater understanding of spatial relationships to aid in such tasks as surgical planning and clinical diagnoses, particularly when the segmented outlines from each image slice are displayed together as a surface in three-dimensions. A review of the literature indicates that current brain segmentation methods require a trained human expert to inspect the images and decide appropriate parameters, thresholds, or regions of interest to achieve the proper segmentation. This is a tedious time-consuming task because of the large number of images involved. A truly automatic method is needed to transform brain segmentation into a practical clinical tool. This dissertation describes a novel pattern classification approach to the problem of automatically segmenting magnetic resonance images of the brain. Based on this approach, algorithms were designed and implemented to automatically segment a number of anatomical structures. These algorithms were applied to several standard image data sets of human subjects obtained from the Internet Brain Segmentation Repository (IBSR). The resulting segmentations of the lateral ventricles and the caudate nuclei were compared to reference manual segmentations done by expert radiologists. The Tanimoto similarity coefficient was very good for the lateral ventricles (0.81) and good for the caudate nuclei (0.67).","abstract_html":"Magnetic resonance imaging (MRI) is a technique used primarily in medical settings to produce high quality images of the human body’s internal anatomy. Each image is of a thin slice through the body, with the typical distance between slices being a few millimeters. Brain segmentation is the delineation of one or more anatomical structures within images of the brain. It promotes greater understanding of spatial relationships to aid in such tasks as surgical planning and clinical diagnoses, particularly when the segmented outlines from each image slice are displayed together as a surface in three-dimensions. A review of the literature indicates that current brain segmentation methods require a trained human expert to inspect the images and decide appropriate parameters, thresholds, or regions of interest to achieve the proper segmentation. This is a tedious time-consuming task because of the large number of images involved. A truly automatic method is needed to transform brain segmentation into a practical clinical tool. This dissertation describes a novel pattern classification approach to the problem of automatically segmenting magnetic resonance images of the brain. Based on this approach, algorithms were designed and implemented to automatically segment a number of anatomical structures. These algorithms were applied to several standard image data sets of human subjects obtained from the Internet Brain Segmentation Repository (IBSR). The resulting segmentations of the lateral ventricles and the caudate nuclei were compared to reference manual segmentations done by expert radiologists. The Tanimoto similarity coefficient was very good for the lateral ventricles (0.81) and good for the caudate nuclei (0.67).","abstract_has_math":false,"creators":["Spence, Kirk V. N."],"institution":"Computer Science","degree_name":"Doctor of Philosophy (PhD)","degree_level":"Dissertation","degree_discipline":"Computer Sciences","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2005,"date_issued":"2005-01-01T08:00:00Z","date_published":"2005-01-01T08:00:00Z","updated_at":"2026-07-24T02:57:30Z","subjects":["pattern classification","magnetic resonance imaging","brain segmentation"],"languages":[],"rights":["unrestricted","Release the entire work immediately for access worldwide."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd-04152005-114301","https://repository.lsu.edu/gradschool_dissertations/330"],"render_values":[{"text":"etd-04152005-114301","href":null,"code":true},{"text":"https://repository.lsu.edu/gradschool_dissertations/330","href":"https://repository.lsu.edu/gradschool_dissertations/330","code":true}]}]},"links":{"outbound_url":"https://doi.org/10.31390/gradschool_dissertations.330","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Spence, Kirk V. N."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2005-04-14"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-05-12T23:08:27Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Sciences"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (PhD)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["pattern classification","magnetic resonance imaging","brain segmentation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["unrestricted","Release the entire work immediately for access worldwide."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd-04152005-114301","10.31390/gradschool_dissertations.330","https://repository.lsu.edu/gradschool_dissertations/330"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Magnetic resonance imaging (MRI) is a technique used primarily in medical settings to produce high quality images of the human body’s internal anatomy. Each image is of a thin slice through the body, with the typical distance between slices being a few millimeters. Brain segmentation is the delineation of one or more anatomical structures within images of the brain. It promotes greater understanding of spatial relationships to aid in such tasks as surgical planning and clinical diagnoses, particularly when the segmented outlines from each image slice are displayed together as a surface in three-dimensions. A review of the literature indicates that current brain segmentation methods require a trained human expert to inspect the images and decide appropriate parameters, thresholds, or regions of interest to achieve the proper segmentation. This is a tedious time-consuming task because of the large number of images involved. A truly automatic method is needed to transform brain segmentation into a practical clinical tool. This dissertation describes a novel pattern classification approach to the problem of automatically segmenting magnetic resonance images of the brain. Based on this approach, algorithms were designed and implemented to automatically segment a number of anatomical structures. These algorithms were applied to several standard image data sets of human subjects obtained from the Internet Brain Segmentation Repository (IBSR). The resulting segmentations of the lateral ventricles and the caudate nuclei were compared to reference manual segmentations done by expert radiologists. The Tanimoto similarity coefficient was very good for the lateral ventricles (0.81) and good for the caudate nuclei (0.67)."]},{"key":"dc:title","label":"Title","values":["Automatic segmentation of magnetic resonance images of the brain"]}]}],"canonical_facts":{"dc:creator":["Spence, Kirk V. N."],"dc:date":["2005-04-14"],"dc:date.available":["2022-05-12T23:08:27Z"],"dc:description.abstract":["Magnetic resonance imaging (MRI) is a technique used primarily in medical settings to produce high quality images of the human body’s internal anatomy. Each image is of a thin slice through the body, with the typical distance between slices being a few millimeters. Brain segmentation is the delineation of one or more anatomical structures within images of the brain. It promotes greater understanding of spatial relationships to aid in such tasks as surgical planning and clinical diagnoses, particularly when the segmented outlines from each image slice are displayed together as a surface in three-dimensions. A review of the literature indicates that current brain segmentation methods require a trained human expert to inspect the images and decide appropriate parameters, thresholds, or regions of interest to achieve the proper segmentation. This is a tedious time-consuming task because of the large number of images involved. A truly automatic method is needed to transform brain segmentation into a practical clinical tool. This dissertation describes a novel pattern classification approach to the problem of automatically segmenting magnetic resonance images of the brain. Based on this approach, algorithms were designed and implemented to automatically segment a number of anatomical structures. These algorithms were applied to several standard image data sets of human subjects obtained from the Internet Brain Segmentation Repository (IBSR). The resulting segmentations of the lateral ventricles and the caudate nuclei were compared to reference manual segmentations done by expert radiologists. The Tanimoto similarity coefficient was very good for the lateral ventricles (0.81) and good for the caudate nuclei (0.67)."],"dc:identifier":["etd-04152005-114301","10.31390/gradschool_dissertations.330","https://repository.lsu.edu/gradschool_dissertations/330"],"dc:rights":["unrestricted","Release the entire work immediately for access worldwide."],"dc:subject":["pattern classification","magnetic resonance imaging","brain segmentation"],"dc:title":["Automatic segmentation of magnetic resonance images of the brain"],"thesis:degree_discipline":["Computer Sciences"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Doctor of Philosophy (PhD)"],"thesis:institution_name":["Computer Science"]},"updated_at":"2026-07-24T02:57:30Z"}