Early Prediction of Alzheimer's Disease with Non-local Patch-Based Longitudinal Descriptors

Abstract : Alzheimer's disease (AD) is characterized by a progressive decline in the cognitive functions accompanied by an atrophic process which can already be observed in the early stages using magnetic resonance images (MRI). Individualized prediction of future progression to AD, when patients are still in the mild cognitive impairment (MCI) stage, has potential impact for preventive treatment. Atrophy patterns extracted from longitudinal MRI sequences provide valuable information to identify MCI patients at higher risk of developing AD in the future. We present a novel descriptor that uses the similarity between local image patches to encode local displacements due to atrophy between a pair of longitudinal MRI scans. Using a conventional logistic regression classifier, our descriptor achieves 76% accuracy in predicting which MCI patients will progress to AD up to 3 years before conversion.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01626255
Contributor : Pierrick Coupé <>
Submitted on : Monday, October 30, 2017 - 3:20:33 PM
Last modification on : Friday, April 13, 2018 - 7:56:04 PM
Document(s) archivé(s) le : Wednesday, January 31, 2018 - 12:54:16 PM

File

patchlong.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Gerard Sanroma, Víctor Andrea, Oualid Benkarim, José Manjón, Pierrick Coupé, et al.. Early Prediction of Alzheimer's Disease with Non-local Patch-Based Longitudinal Descriptors. International Workshop on Patch-based Techniques in Medical Imaging, Sep 2017, Québec, Canada. ⟨10.1007/978-3-319-67434-6_9⟩. ⟨hal-01626255⟩

Share

Metrics

Record views

243

Files downloads

82