{"id":992,"date":"2011-07-04T21:43:59","date_gmt":"2011-07-04T19:43:59","guid":{"rendered":"http:\/\/viscontitoscoalda.com\/?p=992"},"modified":"2011-07-04T21:43:59","modified_gmt":"2011-07-04T19:43:59","slug":"mri-pattern-recognition-in-ms","status":"publish","type":"post","link":"https:\/\/viscontitoscoalda.com\/index.php\/2011\/07\/04\/mri-pattern-recognition-in-ms\/","title":{"rendered":"MRI pattern recognition in MS"},"content":{"rendered":"

MRI pattern recognition in Multiple Sclerosis<\/a><\/p>\n

PLoS One.<\/a> 2011;6(6):e21138. Epub 2011 Jun 17.<\/div>\n

MRI pattern recognition in multiple sclerosis normal-appearing brain areas.<\/h2>\n
Weygandt M<\/a>, Hackmack K<\/a>, Pf\u00fcller C<\/a>, Bellmann-Strobl J<\/a>, Paul F<\/a>, Zipp F<\/a>, Haynes JD<\/a>.<\/div>\n
\n

Source<\/h3>\n

Bernstein Center for Computational Neuroscience Berlin, Charit\u00e9 – University Medicine, Berlin, Germany.<\/p>\n<\/div>\n

\n

Abstract<\/h3>\n

OBJECTIVE:<\/h4>\n

Here, we use pattern-classification to investigate diagnostic information for multiple sclerosis (MS; relapsing-remitting type) in lesioned areas, areas of normal-appearing grey matter (NAGM), and normal-appearing white matter (NAWM) as measured by standard MR techniques.<\/p>\n

METHODS:<\/h4>\n

A lesion mapping was carried out by an experienced neurologist for Turbo Inversion Recovery Magnitude (TIRM) images of individual subjects. Combining this mapping with templates from a neuroanatomic atlas, the TIRM images were segmented into three areas of homogenous tissue types (Lesions, NAGM, and NAWM) after spatial standardization. For each area, a linear Support Vector Machine algorithm was used in multiple local classification analyses to determine the diagnostic accuracy in separating MS patients from healthy controls based on voxel tissue intensity patterns extracted from small spherical subregions of these larger areas. To control for covariates, we also excluded group-specific biases in deformation fields as a potential source of information.<\/p>\n

RESULTS:<\/h4>\n

Among regions containing lesions a posterior parietal WM area was maximally informative about the clinical status (96% accuracy, p<10(-13)). Cerebellar regions were maximally informative among NAGM areas (84% accuracy, p<10(-7)). A posterior brain region was maximally informative among NAWM areas (91% accuracy, p<10(-10)).<\/p>\n

INTERPRETATION:<\/h4>\n

We identified regions indicating MS in lesioned, but also NAGM, and NAWM areas. This complements the current perception that standard MR techniques mainly capture macroscopic tissue variations due to focal lesion processes. Compared to current diagnostic guidelines for MS that define areas of diagnostic information with moderate spatial specificity, we identified hotspots of MS associated tissue alterations with high specificity defined on a millimeter scale.<\/p>\n<\/div>\n

\n
\n
\n
PMID:<\/dt>\n
21695053<\/dd>\n
[PubMed – in process] <\/dd>\n
<\/dd>\n
PMCID: PMC3117878<\/dt>\n
<\/dd>\n<\/dl>\n

Free PMC Article<\/p>\n<\/div>\n<\/div>\n

\n

Images from this publication.See all images (4)<\/a> Free text<\/a><\/p>\n

\n
\n
\"Figure<\/a><\/div>\n
\"Figure<\/a><\/div>\n
\"Figure<\/a><\/div>\n
\"Figure<\/a><\/div>\n<\/div>\n<\/div>\n<\/div>\n

LinkOut – more resources<\/a><\/h3>\n

Pattern recognition risonanza magnetica in diverse aree del cervello sclerosi aspetto normale.
\nWeygandt M, Hackmack K, Pf\u00fcller C, Bellmann Strobl-J, Paolo F, Zipp F, JD Haynes.
\nFonte<\/p>\n

Bernstein Center for Computational Neuroscience Berlino, Charit\u00e9 – Universit\u00e0 di Medicina, Berlino, Germania.
\nAstratto
\nOBIETTIVO:<\/p>\n

Qui, usiamo schema di classificazione per indagare le informazioni di diagnostica per la sclerosi multipla (SM; recidivante-remittente tipo) in aree di lesione, aree di aspetto normale materia grigia (NAGM), e di aspetto normale della sostanza bianca (NAWM), misurato dalla norma MR tecniche.
\nMETODI:<\/p>\n

Una mappatura lesione \u00e8 stata effettuata da un neurologo esperto per Turbo Inversion Recovery Magnitude (TIRM) le immagini dei singoli soggetti. Combinando questa mappatura con i modelli da un atlante neuroanatomic, le immagini sono state TIRM segmentato in tre aree di tipi di tessuto omogeneo (lesioni, NAGM e NAWM) dopo la standardizzazione spaziale. Per ogni area, un algoritmo lineare Vector Machine Support \u00e8 stato utilizzato in diverse analisi di classificazione locale per determinare l’accuratezza diagnostica nel separare i pazienti con SM da controlli sani sulla base di modelli tessuto intensit\u00e0 voxel estratto da piccolo subregioni sferica di queste aree pi\u00f9 grandi. Per controllare per le covariate, abbiamo anche escluso gruppi specifici pregiudizi nei campi di deformazione come una potenziale fonte di informazioni.
\nRISULTATI:<\/p>\n

Tra le regioni contenenti lesioni uno posteriore zona parietale WM \u00e8 stato al massimo informativo sullo stato clinico (96% di precisione, p <10 (-13)). Regioni cerebellari sono state al massimo informativo tra aree NAGM (84% di precisione, p <10 (-7)). Una regione del cervello posteriore era al massimo informativo tra aree NAWM (91% di precisione, p <10 (-10)).
\nINTERPRETAZIONE:<\/p>\n

Abbiamo identificato le regioni che indicano MS in lesione, ma anche NAGM, e le aree NAWM. Ci\u00f2 integra la percezione attuale che le tecniche standard di MR soprattutto catturare le variazioni del tessuto macroscopici dovuti a processi di lesione focale. Rispetto alle attuali linee guida di diagnostica per MS che definiscono le aree di informazioni diagnostiche con moderata specificit\u00e0 spaziale, abbiamo identificato gli hotspot di MS alterazioni dei tessuti associati con alta specificit\u00e0 definite su scala millimetrica.<\/p>\n

———————-<\/p>\n

Reconnaissance des formes d’IRM dans les zones de scl\u00e9rose en plaques du cerveau d’apparence normale.
\nWeygandt M, Hackmack K, C Pf\u00fcller, Bellmann-J Strobl, Paul F, F Zipp, Haynes JD.
\nSource<\/p>\n

Bernstein Center for Computational Neuroscience de Berlin, Charit\u00e9 – M\u00e9decine universitaire, Berlin, Allemagne.
\nR\u00e9sum\u00e9
\nOBJECTIF:<\/p>\n

Ici, nous utilisons mod\u00e8le de classification pour enqu\u00eater sur des informations de diagnostic de scl\u00e9rose en plaques (SEP; r\u00e9mittente type) dans les zones l\u00e9s\u00e9es, des zones d’apparence normale de la mati\u00e8re grise (Nagm), et d’apparence normale de la mati\u00e8re blanche (NAWM) tel que mesur\u00e9 par la norme techniques de RM.
\nM\u00e9thodes:<\/p>\n

Une cartographie l\u00e9sion a \u00e9t\u00e9 r\u00e9alis\u00e9e par un neurologue exp\u00e9riment\u00e9 pour Turbo Inversion Recovery Magnitude (CRIT) des images de sujets individuels. En combinant cette cartographie avec des mod\u00e8les \u00e0 partir d’un atlas neuroanatomiques, les images ont \u00e9t\u00e9 segment\u00e9es CRIT en trois zones de types de tissus homog\u00e8nes (l\u00e9sions, Nagm et NAWM) apr\u00e8s normalisation spatiale. Pour chaque domaine, un algorithme de support lin\u00e9aire Vector machine a \u00e9t\u00e9 utilis\u00e9e dans de multiples analyses de classification local pour d\u00e9terminer la pr\u00e9cision diagnostique \u00e0 s\u00e9parer les patients SEP de contr\u00f4le en sant\u00e9 bas\u00e9e sur les mod\u00e8les voxel intensit\u00e9 de tissus extraits de petits sous-sph\u00e9riques de ces grandes zones. Pour contr\u00f4ler les covariables, nous avons \u00e9galement exclus du groupe-sp\u00e9cifiques dans les champs de d\u00e9formation des pr\u00e9jug\u00e9s comme une source potentielle d’information.
\nR\u00c9SULTATS:<\/p>\n

Parmi les r\u00e9gions contenant des l\u00e9sions une zone de WM pari\u00e9tal post\u00e9rieur est au maximum d’information sur l’\u00e9tat clinique (pr\u00e9cision de 96%, p <10 (-13)). R\u00e9gions du cervelet ont \u00e9t\u00e9 au maximum d’information entre les zones Nagm (84% de pr\u00e9cision, p <10 (-7)). Une r\u00e9gion du cerveau post\u00e9rieur est au maximum d’information entre les zones NAWM (91% de pr\u00e9cision, p <10 (-10)).
\nInterpr\u00e9tation:<\/p>\n

Nous avons identifi\u00e9 des r\u00e9gions MS en indiquant l\u00e9sion, mais aussi Nagm, et les zones NAWM. Cela compl\u00e8te la perception actuelle que les techniques standard MR essentiellement capter les variations macroscopique des tissus due \u00e0 des processus l\u00e9sion focale. Compar\u00e9 aux recommandations actuelles de diagnostic pour MS qui d\u00e9finissent les zones d’informations de diagnostic avec une sp\u00e9cificit\u00e9 spatiale mod\u00e9r\u00e9e, nous avons identifi\u00e9 les points chauds des alt\u00e9rations tissulaires associ\u00e9es MS avec une grande sp\u00e9cificit\u00e9 d\u00e9finie sur une \u00e9chelle millim\u00e9trique.<\/p>\n","protected":false},"excerpt":{"rendered":"

MRI pattern recognition in Multiple Sclerosis PLoS One. 2011;6(6):e21138. Epub 2011 Jun 17. MRI pattern recognition in multiple sclerosis normal-appearing brain areas. Weygandt M, Hackmack K, Pf\u00fcller C, Bellmann-Strobl J, Paul F, Zipp F, Haynes JD. Source Bernstein Center for Computational Neuroscience Berlin, Charit\u00e9 – University Medicine, Berlin, Germany. Abstract OBJECTIVE: Here, we use pattern-classification … Continua a leggere MRI pattern recognition in MS<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[31,33],"tags":[53,217,238],"class_list":["post-992","post","type-post","status-publish","format-standard","hentry","category-scienza-ricerca-e-dintorni","category-sclerosi-multipla-e-dintorni","tag-algorithm","tag-multiple-sclerosis","tag-pattern-recognition"],"_links":{"self":[{"href":"https:\/\/viscontitoscoalda.com\/index.php\/wp-json\/wp\/v2\/posts\/992","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/viscontitoscoalda.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/viscontitoscoalda.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/viscontitoscoalda.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/viscontitoscoalda.com\/index.php\/wp-json\/wp\/v2\/comments?post=992"}],"version-history":[{"count":0,"href":"https:\/\/viscontitoscoalda.com\/index.php\/wp-json\/wp\/v2\/posts\/992\/revisions"}],"wp:attachment":[{"href":"https:\/\/viscontitoscoalda.com\/index.php\/wp-json\/wp\/v2\/media?parent=992"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/viscontitoscoalda.com\/index.php\/wp-json\/wp\/v2\/categories?post=992"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/viscontitoscoalda.com\/index.php\/wp-json\/wp\/v2\/tags?post=992"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}