期刊
PLOS ONE
卷 15, 期 9, 页码 -出版社
PUBLIC LIBRARY SCIENCE
DOI: 10.1371/journal.pone.0236868
关键词
-
资金
- University of Applied Sciences and Arts Dortmund, Germany
- Heinz Nixdorf Foundation
- German Research Council (DFG) [EI 969/2-3, ER 155/6-1, ER 155/6-2, HO 3314/2-1, HO 3314/2-2, HO 3314/2-3, HO 3314/4-3, INST 58219/32-1, JO 170/81, KN 885/3-1, PE 2309/2-1, SI 236/8-1, SI 236/9-1, SI 236/10-1]
- German Ministry of Education and Science [BMBF] [01EG0401, 01GI0856, 01GI0860, 01GS0820_WB2-C, 01ER1001D, 01GI0205]
- Ministry of Innovation, Science, Research and Technology, North Rhine-Westphalia (MIWFTNRW)
- Else Kroner-Fresenius-Stiftung [2015_A119]
- German Social Accident Insurance [DGUV project] [FF-FP295]
- Competence Network for HIV/AIDS
- deanship of the university hospital of the university Duisburg-Essen
- IFORES of the university Duisburg-Essen
- European Union
- German Competence Network Heart Failure
- Kulturstiftung Essen
- Protein Research Unit within Europe (PURE)
- Celgene GmbH Munchen
- Imatron/GE-Imatron
- Janssen
- Merck KG
- Philips
- ResMed Foundation
- Roche Diagnostics
- Sarstedt AGCo
- Siemens HealthCare Diagnostics
- Volkswagen Foundation
- Dr. Werner-Jackstadt Stiftung
Detection and diagnosis of early and subclinical stages of Alzheimer's Disease (AD) play an essential role in the implementation of intervention and prevention strategies. Neuroimaging techniques predominantly provide insight into anatomic structure changes associated with AD. Deep learning methods have been extensively applied towards creating and evaluating models capable of differentiating between cognitively unimpaired, patients with Mild Cognitive Impairment (MCI) and AD dementia. Several published approaches apply information fusion techniques, providing ways of combining several input sources in the medical domain, which contributes to knowledge of broader and enriched quality. The aim of this paper is to fuse sociodemographic data such as age, marital status, education and gender, and genetic data (presence of an apolipoprotein E (APOE)-epsilon 4 allele) with Magnetic Resonance Imaging (MRI) scans. This enables enriched multi-modal features, that adequately represent the MRI scan visually and is adopted for creating and modeling classification systems capable of detecting amnestic MCI (aMCI). To fully utilize the potential of deep convolutional neural networks, two extra color layers denoting contrast intensified and blurred image adaptations are virtually augmented to each MRI scan, completing the Red-Green-Blue (RGB) color channels. Deep convolutional activation features (DeCAF) are extracted from the average pooling layer of the deep learning system Inception_v3. These features from the fused MRI scans are used as visual representation for the Long Short-Term Memory (LSTM) based Recurrent Neural Network (RNN) classification model. The proposed approach is evaluated on a sub-study containing 120 participants (aMCI = 61 and cognitively unimpaired = 59) of the Heinz Nixdorf Recall (HNR) Study with a baseline model accuracy of 76%. Further evaluation was conducted on the ADNI Phase 1 dataset with 624 participants (aMCI = 397 and cognitively unimpaired = 227) with a baseline model accuracy of 66.27%. Experimental results show that the proposed approach achieves 90% accuracy and 0.90F(1)-Score at classification of aMCI vs. cognitively unimpaired participants on the HNR Study dataset, and 77% accuracy and 0.83F(1)-Score on the ADNI dataset.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据