Homogeneity-based feature extraction for classification of early-stage Alzheimer's disease from functional magnetic resonance images
Plant C, Sorg C, Riedl V, Wohlschläger A (2011)
Publication Type: Conference contribution
Publication year: 2011
Pages Range: 33-41
Conference Proceedings Title: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
ISBN: 9781450308434
Abstract
Alzheimer's disease is the most common form of age-related dementia. Early-stage diagnosis of Alzheimer is of major importance for the following reasons: Also easily curable conditions like depression, poor nutrition and drug side effects may cause symptoms like early-stage Alzheimer. Moreover, recently some medications have been developed which successfully attenuate the symptoms and delay the progression of Alzheimer, but to be effective, they need to be applied as soon as possible. However, early-stage diagnosis of Alzheimer is very difficult since the symptoms are very mild and can easily be confounded with effects of normal aging. In this paper, we introduce a bootstrapping-based feature extraction technique to identify early-stage Alzheimer's disease from resting-state functional resonance images. Our experiments demonstrate that subjects with early-stage Alzheimer's disease can be distinguished with an accuracy of 79% from age-matched healthy subjects using a support vector machine on the extracted features. © 2011 ACM.
Authors with CRIS profile
Involved external institutions
United States (USA) (US)
Germany (DE)How to cite
APA:
Plant, C., Sorg, C., Riedl, V., & Wohlschläger, A. (2011). Homogeneity-based feature extraction for classification of early-stage Alzheimer's disease from functional magnetic resonance images. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 33-41).
MLA:
Plant, Claudia, et al. "Homogeneity-based feature extraction for classification of early-stage Alzheimer's disease from functional magnetic resonance images." Proceedings of the Workshop on Data Mining for Medicine and HealthCare, DMMH'11 - Held with the KDD Conference, the 17th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD-2011 2011. 33-41.
BibTeX: Download