Scholars Central

Conference abstractPublished 1 Sep 2015

Predicting frontotemporal lobar degeneration with meta-analyses, pattern classification and multimodal imaging

Authors: Matthias L Schroeter

Max Planck Institute for Human Cognitive and Brain Sciences, Germany

Ask about this article

Abstract

Select any words in the title or abstract, or press this and choose a sentence.

Recently, new diagnostic criteria including imaging biomarkers have been proposed for frontotemporal lobar degeneration (FTLD) in particular for its behavioural variant and language subtypes. Th ese imaging criteria shall enable individual diagnosis. New imaging criteria were validated by conducting quantitative anatomical likelihood estimate meta-analyses according to the QUOROM/PRISMA statement across studies published in the literature. Th ese meta-analyses identify the neural correlates for each of the FTLD subtypes and underline disease-specifi city of the imaging criteria. Analyses were conducted separately for atrophy measured with magnetic resonance imaging (MRI) and glucose metabolism measured with [F18] fl uorodeoxyglucose positron emission tomography (FDG-PET). Both imaging methods revealed specifi c regional patterns. Results might open the road to method-specifi c imaging criteria as already suggested for Alzheimer’s disease. If new imaging criteria are valid they shall enable early individual diagnosis in single patients. To prove the potential for individual diagnosis we investigated whether FTLD might be diagnosed with cutting edge pattern classifi cation algorithms in multimodal imaging data. Support vector machine classifi cation (SVM) with multimodal imaging data (MRI & FDG-PET) enabled early individual detection of FTLD and discrimination between FTLD and Alzheimer’s disease. Limiting SVM classifi cation regionally to meta-analytically identifi ed disease networks even improved discrimination accuracy. Analyses were also reliable in multi-centric data. In conclusion, our results support and refi ne the application of imaging criteria and suggest that pattern classifi cation algorithms enable early individual diagnosis and diff erential diagnosis of FTLD sub types, a precondition for early intervention strategies.

Ask about this article

Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.

Try:

Similar by topic

Follow

New articles from what you follow go into your email digest, once you agree to alert emails.

  • SubjectRadiology & Imaging
  • BylineArticles whose byline prints “Matthias L Schroeter”

For authors and organisers

Publish, present and keep up with your field

Find the right journal for your paper and submit your manuscript.

Photo: Pexels