{"id":7010,"date":"2019-05-31T09:26:49","date_gmt":"2019-05-31T09:26:49","guid":{"rendered":"https:\/\/vicorob.udg.edu\/?p=7010"},"modified":"2019-05-31T09:26:49","modified_gmt":"2019-05-31T09:26:49","slug":"doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients","status":"publish","type":"post","link":"https:\/\/vicorob.udg.edu\/ca\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/","title":{"rendered":"DOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients."},"content":{"rendered":"

By Sandra Gonz\u00e1lez Vill\u00e0
\n<\/strong><\/p>\n

Supervised by Dr. Xavier Llad\u00f3 Bardera\u00a0 \/ Dr.\u00a0 Arnau Oliver Malagelada
\n<\/strong><\/p>\n

 <\/p>\n

Abstract<\/strong><\/h3>\n

This thesis is focused on the automated segmentation of the brain structures in magnetic resonance images, applied to multiple sclerosis (MS) patients.<\/p>\n

This disease is characterized by the presence of demyelinating lesions in the brain, that appear as focal low signal intensity areas in the T1-weighted sequence, which is the most frequently used modality to segment the brain structures.<\/p>\n

In the first place, we exhaustively analyze the state of the art on this topic, presenting a new classification of the methods based on their segmentation strategy. We further discuss each category\u2019s strengths and weaknesses and analyze its performance in segmenting different brain structures, providing a qualitative and quantitative comparison. From this first analysis, we observe that the vast majority of the reviewed methods are not designed for brains with lesions, such as those encountered in MS patients. Consequently, we also perform a thorough analysis of the effect of MS lesions on three representative state-of-the-art methods, each relying on a different category of the classification: FreeSurfer, FIRST and majority-vote label fusion.
\nThis second analysis reveals that the three segmentation approaches are indeed affected by the presence of these lesions, demonstrating that there exists a problem when using automatic methods as a tool to measure the disease progression. Therefore, based on the conclusions of these two studies, we propose a new correspondence search model able to minimize this problem on intensity-based multi-atlas label fusion strategies.<\/p>\n

Afterwards, we extend the theory of two remarkable label fusion strategies of the literature, i.e. Non-local Spatial STAPLE and Joint Label Fusion, in order to integrate our model into their corresponding estimation algorithms. Furthermore, with the aim of providing fully automated brain structure segmentation algorithms, a whole automated pipeline including lesion segmentation, pre-processing, atlas selection, masked registration and label fusion, is presented. Finally, a second extension of the theory to enable the integration of manual and automatic edits into the segmentation estimation of both strategies is also proposed.<\/p>\n

The evaluation, carried out in a quantitative and qualitative manner, includes a comparison of the proposed approaches to the original strategies when segmenting the raw images and the lesion-filled images, using both manual and automatically segmented lesion masks.<\/p>\n

The analysis of the results obtained with the proposed strategies points out a performance improvement on the lesion areas, which is also reflected on the whole brain segmentation performance.<\/p>\n

 <\/p>\n

Resum<\/strong><\/h3>\n

Aquesta tesi se centra en la segmentaci\u00f3 autom\u00e0tica de les estructures cerebrals en imatges de resson\u00e0ncia magn\u00e8tica, aplicada a pacients d\u2019esclerosi m\u00faltiple (EM).<\/p>\n

Aquesta malaltia es caracteritza per la pres\u00e8ncia de lesions desmielinitzants al cervell, que apareixen com \u00e0rees focals de baixa intensitat de senyal en la seq\u00fc\u00e8ncia T1-w, que \u00e9s la modalitat m\u00e9s utilitzada per segmentar les estructures cerebrals.<\/p>\n

En primer lloc, analitzem exhaustivament l\u2019estat de l\u2019art en aquest tema, presentant una nova classificaci\u00f3 dels m\u00e8todes basada en la seva estrat\u00e8gia de segmentaci\u00f3. A m\u00e9s, estudiem les fortaleses i inconvenients de cada categoria i analitzem el seu rendiment en la segmentaci\u00f3 de diferents estructures, proporcionant una comparaci\u00f3 qualitativa i quantitativa. En aquesta primera an\u00e0lisi, observem que la gran majoria dels m\u00e8todes revisats no estan dissenyats per a cervells amb lesions, com les que apareixen en pacients d\u2019EM. Conseq\u00fcentment, tamb\u00e9 realitzem una an\u00e0lisi exhaustiva de l\u2019efecte de les lesions d\u2019EM en tres m\u00e8todes representatius de l\u2019estat de l\u2019art, cadascun d\u2019ells basat en una categoria diferent de la classificaci\u00f3 proposada: FreeSurfer, FIRST i fusi\u00f3 d\u2019etiquetes mitjan\u00e7ant majoria de vot.<\/p>\n

Aquesta segona an\u00e0lisi, revela que els tres enfocaments de segmentaci\u00f3 es veuen afectats per la pres\u00e8ncia d\u2019aquestes lesions, el que demostra que hi ha un problema en els m\u00e8todes de segmentaci\u00f3 autom\u00e0tica quan s\u2019utilitzen com a eina per mesurar la progressi\u00f3 de la malaltia. Per tant, en base a les conclusions d\u2019aquests dos estudis, proposem un nou model de cerca de correspond\u00e8ncies capa\u00e7 de minimitzar aquest problema en les estrat\u00e8gies de fusi\u00f3 d\u2019etiquetes de m\u00faltiples atles basades en intensitat. Posteriorment, estenem la teoria de dues estrat\u00e8gies de fusi\u00f3 d\u2019etiquetes notables de la literatura, Non-local Spatial STAPLE i Joint Label Fusion, per integrar el nostre model en els seus corresponents algoritmes d\u2019estimaci\u00f3. Addicionalment, amb l\u2019objectiu de proporcionar algoritmes de segmentaci\u00f3 d\u2019estructures cerebrals totalment automatitzats, es presenta una l\u00ednia autom\u00e0tica completa que inclou la segmentaci\u00f3 de lesions, el preprocessat, la selecci\u00f3 d\u2019atles, el registre emmascarat i la fusi\u00f3 d\u2019etiquetes.<\/p>\n

Finalment, tamb\u00e9 es proposa una segona extensi\u00f3 de la teoria per permetre la integraci\u00f3 d\u2019anotacions manuals i autom\u00e0tiques en l\u2019estimaci\u00f3 de segmentaci\u00f3 de les dues estrat\u00e8gies. L\u2019avaluaci\u00f3, realitzada de manera quantitativa i qualitativa, inclou una comparaci\u00f3 dels enfocaments proposats amb les estrat\u00e8gies originals al segmentar les imatges sense processar i les imatges amb \u201clesion filling\u201d, utilitzant m\u00e0scares de lesions tant manuals com segmentades autom\u00e0ticament.<\/p>\n

L\u2019an\u00e0lisi dels resultats obtinguts amb les estrat\u00e8gies proposades demostra una millora en el rendiment dels algorismes de segmentaci\u00f3 en les \u00e0rees de lesi\u00f3, que tamb\u00e9 es veu reflectida en la segmentaci\u00f3 de tot el cervell.<\/p>\n

 <\/p>\n

\"\"<\/p>\n

 <\/p>\n

 <\/p>\n","protected":false},"excerpt":{"rendered":"

By Sandra Gonz\u00e1lez Vill\u00e0 Supervised by Dr. Xavier Llad\u00f3 Bardera\u00a0 \/ Dr.\u00a0 Arnau Oliver Malagelada   Abstract This thesis is focused on the automated segmentation of the brain structures in magnetic resonance images, applied to multiple sclerosis (MS) patients. This disease is characterized by the presence of demyelinating lesions in the brain, that appear as… DOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients.<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":7027,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"categories":[12,58],"tags":[89],"class_list":["post-7010","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","category-scientific-results","tag-multiple-sclerosi"],"acf":[],"yoast_head":"\nDOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients. - Vicorob<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/\" \/>\n<meta property=\"og:locale\" content=\"ca_ES\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"DOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients. - Vicorob\" \/>\n<meta property=\"og:description\" content=\"By Sandra Gonz\u00e1lez Vill\u00e0 Supervised by Dr. Xavier Llad\u00f3 Bardera\u00a0 \/ Dr.\u00a0 Arnau Oliver Malagelada   Abstract This thesis is focused on the automated segmentation of the brain structures in magnetic resonance images, applied to multiple sclerosis (MS) patients. This disease is characterized by the presence of demyelinating lesions in the brain, that appear as… DOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/\" \/>\n<meta property=\"og:site_name\" content=\"Vicorob\" \/>\n<meta property=\"article:published_time\" content=\"2019-05-31T09:26:49+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/vicorob.udg.edu\/wp-content\/uploads\/2019\/05\/sandra_gonzalez.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"785\" \/>\n\t<meta property=\"og:image:height\" content=\"442\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Neorg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Escrit per\" \/>\n\t<meta name=\"twitter:data1\" content=\"Neorg\" \/>\n\t<meta name=\"twitter:label2\" content=\"Temps estimat de lectura\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minuts\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/\",\"url\":\"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/\",\"name\":\"DOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients. - Vicorob\",\"isPartOf\":{\"@id\":\"https:\/\/vicorob.udg.edu\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/vicorob.udg.edu\/wp-content\/uploads\/2019\/05\/sandra_gonzalez.jpg\",\"datePublished\":\"2019-05-31T09:26:49+00:00\",\"author\":{\"@id\":\"https:\/\/vicorob.udg.edu\/#\/schema\/person\/32b8d8aa5207f27392bf3ec2d7c21ef4\"},\"breadcrumb\":{\"@id\":\"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/#breadcrumb\"},\"inLanguage\":\"ca\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"ca\",\"@id\":\"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/#primaryimage\",\"url\":\"https:\/\/vicorob.udg.edu\/wp-content\/uploads\/2019\/05\/sandra_gonzalez.jpg\",\"contentUrl\":\"https:\/\/vicorob.udg.edu\/wp-content\/uploads\/2019\/05\/sandra_gonzalez.jpg\",\"width\":785,\"height\":442},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/vicorob.udg.edu\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"DOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients.\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/vicorob.udg.edu\/#website\",\"url\":\"https:\/\/vicorob.udg.edu\/\",\"name\":\"Vicorob\",\"description\":\"Computer Vision and Robotics Research Group\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/vicorob.udg.edu\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ca\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/vicorob.udg.edu\/#\/schema\/person\/32b8d8aa5207f27392bf3ec2d7c21ef4\",\"name\":\"Neorg\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ca\",\"@id\":\"https:\/\/vicorob.udg.edu\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/10d8574102d7dcecdce3e72f5dec516c1b8a7e631542b0d0010ab70b945ea708?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/10d8574102d7dcecdce3e72f5dec516c1b8a7e631542b0d0010ab70b945ea708?s=96&d=mm&r=g\",\"caption\":\"Neorg\"},\"sameAs\":[\"https:\/\/vicorob.udg.edu\"],\"url\":\"https:\/\/vicorob.udg.edu\/ca\/author\/neorg_us\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"DOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients. - Vicorob","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/","og_locale":"ca_ES","og_type":"article","og_title":"DOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients. - Vicorob","og_description":"By Sandra Gonz\u00e1lez Vill\u00e0 Supervised by Dr. Xavier Llad\u00f3 Bardera\u00a0 \/ Dr.\u00a0 Arnau Oliver Malagelada   Abstract This thesis is focused on the automated segmentation of the brain structures in magnetic resonance images, applied to multiple sclerosis (MS) patients. This disease is characterized by the presence of demyelinating lesions in the brain, that appear as… DOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients.","og_url":"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/","og_site_name":"Vicorob","article_published_time":"2019-05-31T09:26:49+00:00","og_image":[{"width":785,"height":442,"url":"https:\/\/vicorob.udg.edu\/wp-content\/uploads\/2019\/05\/sandra_gonzalez.jpg","type":"image\/jpeg"}],"author":"Neorg","twitter_card":"summary_large_image","twitter_misc":{"Escrit per":"Neorg","Temps estimat de lectura":"4 minuts"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/","url":"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/","name":"DOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients. - Vicorob","isPartOf":{"@id":"https:\/\/vicorob.udg.edu\/#website"},"primaryImageOfPage":{"@id":"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/#primaryimage"},"image":{"@id":"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/#primaryimage"},"thumbnailUrl":"https:\/\/vicorob.udg.edu\/wp-content\/uploads\/2019\/05\/sandra_gonzalez.jpg","datePublished":"2019-05-31T09:26:49+00:00","author":{"@id":"https:\/\/vicorob.udg.edu\/#\/schema\/person\/32b8d8aa5207f27392bf3ec2d7c21ef4"},"breadcrumb":{"@id":"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/#breadcrumb"},"inLanguage":"ca","potentialAction":[{"@type":"ReadAction","target":["https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/"]}]},{"@type":"ImageObject","inLanguage":"ca","@id":"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/#primaryimage","url":"https:\/\/vicorob.udg.edu\/wp-content\/uploads\/2019\/05\/sandra_gonzalez.jpg","contentUrl":"https:\/\/vicorob.udg.edu\/wp-content\/uploads\/2019\/05\/sandra_gonzalez.jpg","width":785,"height":442},{"@type":"BreadcrumbList","@id":"https:\/\/vicorob.udg.edu\/doctoral-thesis-automated-brain-structure-segmentation-in-magnetic-resonance-images-of-multiple-sclerosis-patients\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/vicorob.udg.edu\/"},{"@type":"ListItem","position":2,"name":"DOCTORAL THESIS: Automated brain structure segmentation in magnetic resonance images of multiple sclerosis patients."}]},{"@type":"WebSite","@id":"https:\/\/vicorob.udg.edu\/#website","url":"https:\/\/vicorob.udg.edu\/","name":"Vicorob","description":"Computer Vision and Robotics Research Group","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/vicorob.udg.edu\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ca"},{"@type":"Person","@id":"https:\/\/vicorob.udg.edu\/#\/schema\/person\/32b8d8aa5207f27392bf3ec2d7c21ef4","name":"Neorg","image":{"@type":"ImageObject","inLanguage":"ca","@id":"https:\/\/vicorob.udg.edu\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/10d8574102d7dcecdce3e72f5dec516c1b8a7e631542b0d0010ab70b945ea708?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/10d8574102d7dcecdce3e72f5dec516c1b8a7e631542b0d0010ab70b945ea708?s=96&d=mm&r=g","caption":"Neorg"},"sameAs":["https:\/\/vicorob.udg.edu"],"url":"https:\/\/vicorob.udg.edu\/ca\/author\/neorg_us\/"}]}},"_links":{"self":[{"href":"https:\/\/vicorob.udg.edu\/ca\/wp-json\/wp\/v2\/posts\/7010","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/vicorob.udg.edu\/ca\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/vicorob.udg.edu\/ca\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/vicorob.udg.edu\/ca\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/vicorob.udg.edu\/ca\/wp-json\/wp\/v2\/comments?post=7010"}],"version-history":[{"count":0,"href":"https:\/\/vicorob.udg.edu\/ca\/wp-json\/wp\/v2\/posts\/7010\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/vicorob.udg.edu\/ca\/wp-json\/wp\/v2\/media\/7027"}],"wp:attachment":[{"href":"https:\/\/vicorob.udg.edu\/ca\/wp-json\/wp\/v2\/media?parent=7010"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/vicorob.udg.edu\/ca\/wp-json\/wp\/v2\/categories?post=7010"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/vicorob.udg.edu\/ca\/wp-json\/wp\/v2\/tags?post=7010"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}