4.5 Article

Integrating Convolutional Neural Networks and Multi-Task Dictionary Learning for Cognitive Decline Prediction with Longitudinal Images

期刊

JOURNAL OF ALZHEIMERS DISEASE
卷 75, 期 3, 页码 971-992

出版社

IOS PRESS
DOI: 10.3233/JAD-190973

关键词

Alzheimer's disease; convolutional neural networks; dictionary learning; multi-task learning; transfer learning

资金

  1. National Institute on Aging [RF1AG051710, R01EB025032, R01AG031581, P30AG19610]
  2. National Science Foundation [IIS-1421165]
  3. Arizona Alzheimer's Consortium
  4. ADNI (National Institutes of Health) [U01AG024904]
  5. DOD ADNI (Department of Defense) [W81XWH-12-2-0012]
  6. National Institute of Biomedical Imaging and Bioengineering
  7. AbbVie
  8. Alzheimer's Association
  9. Alzheimer's Drug Discovery Foundation
  10. Araclon Biotech
  11. BioClinica, Inc.
  12. Biogen
  13. BristolMyers Squibb Company
  14. CereSpir, Inc.
  15. Cogstate
  16. Eisai Inc.
  17. Elan Pharmaceuticals, Inc.
  18. Eli Lilly and Company
  19. EuroImmun
  20. F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.
  21. Fujirebio
  22. GE Healthcare
  23. IXICO Ltd.
  24. Janssen Alzheimer Immunotherapy Research & Development, LLC.
  25. Johnson & Johnson Pharmaceutical Research & Development LLC.
  26. Lumosity
  27. Lundbeck
  28. Merck Co., Inc.
  29. Meso Scale Diagnostics, LLC.
  30. NeuroRx Research
  31. Neurotrack Technologies
  32. Novartis Pharmaceuticals Corporation
  33. Pfizer Inc.
  34. Piramal Imaging
  35. Servier
  36. Takeda Pharmaceutical Company
  37. Transition Therapeutics
  38. Canadian Institutes of Health Research

向作者/读者索取更多资源

Background: Disease progression prediction based on neuroimaging biomarkers is vital in Alzheimer's disease (AD) research. Convolutional neural networks (CNN) have been proved to be powerful for various computer vision research by refining reliable and high-level feature maps from image patches. Objective: A key challenge in applying CNN to neuroimaging research is the limited labeled samples with high dimensional features. Another challenge is how to improve the prediction accuracy by joint analysis of multiple data sources (i.e., multiple time points or multiple biomarkers). To address these two challenges, we propose a novel multi-task learning framework based on CNN. Methods: First, we pre-trained CNN on the ImageNet dataset and transferred the knowledge from the pre-trained model to neuroimaging representation. We used this deep model as feature extractor to generate high-level feature maps of different tasks. Then a novel unsupervised learning method, termed Multi-task Stochastic Coordinate Coding (MSCC), was proposed for learning sparse features of multi-task feature maps by using shared and individual dictionaries. Finally, Lasso regression was performed on these multi-task sparse features to predict AD progression measured by the Mini-Mental State Examination (MMSE) and the Alzheimer's Disease Assessment Scale cognitive subscale (ADAS-Cog). Results: We applied this novel CNN-MSCC system on the Alzheimer's Disease Neuroimaging Initiative dataset to predict future MMSE/ADAS-Cog scales. We found our method achieved superior performances compared with seven other methods. Conclusion: Our work may add new insights into data augmentation and multi-task deep model research and facilitate the adoption of deep models in neuroimaging research.

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。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据