English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In recent years, the number of papers on Alzheimer's disease classificationhas increased dramatically, generating interesting methodological ideas on theuse machine learning and feature extraction methods. However, practical impactis much more limited and, eventually, one could not tell which of theseapproaches are the most efficient. While over 90\% of these works make use ofADNI an objective comparison between approaches is impossible due to variationsin the subjects included, image pre-processing, performance metrics andcross-validation procedures. In this paper, we propose a framework forreproducible classification experiments using multimodal MRI and PET data fromADNI. The core components are: 1) code to automatically convert the full ADNIdatabase into BIDS format; 2) a modular architecture based on Nipype in orderto easily plug-in different classification and feature extraction tools; 3)feature extraction pipelines for MRI and PET data; 4) baseline classificationapproaches for unimodal and multimodal features. This provides a flexibleframework for benchmarking different feature extraction and classificationtools in a reproducible manner. We demonstrate its use on all (1519) baselineT1 MR images and all (1102) baseline FDG PET images from ADNI 1, GO and 2 withSPM-based feature extraction pipelines and three different classificationtechniques (linear SVM, anatomically regularized SVM and multiple kernellearning SVM). The highest accuracies achieved were: 91% for AD vs CN, 83% forMCIc vs CN, 75% for MCIc vs MCInc, 94% for AD-A$\beta$+ vs CN-A$\beta$- and 72%for MCIc-A$\beta$+ vs MCInc-A$\beta$+. The code is publicly available athttps://gitlab.icm-institute.org/aramislab/AD-ML (depends on the Clinicasoftware platform, publicly available at http://www.clinica.run).

Yet Another ADNI Machine Learning Paper? Paving The Way Towards Fully-reproducible Research on Classification of Alzheimer's Disease