Weakly Supervised Deep Learning for Brain Disease Prognosis Using MRI and Incomplete Clinical Scores
- Authors
- Liu, Mingxia; Zhang, Jun; Lian, Chunfeng; Shen, Dinggang
- Issue Date
- 7월-2020
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Magnetic resonance imaging; Diseases; Brain modeling; Feature extraction; Training; Deep learning; Prognostics and health management; Alzheimer' s disease (AD); clinical score; disease prognosis; neural network; weakly supervised learning
- Citation
- IEEE TRANSACTIONS ON CYBERNETICS, v.50, no.7, pp.3381 - 3392
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE TRANSACTIONS ON CYBERNETICS
- Volume
- 50
- Number
- 7
- Start Page
- 3381
- End Page
- 3392
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/54897
- DOI
- 10.1109/TCYB.2019.2904186
- ISSN
- 2168-2267
- Abstract
- As a hot topic in brain disease prognosis, predicting clinical measures of subjects based on brain magnetic resonance imaging (MRI) data helps to assess the stage of pathology and predict future development of the disease. Due to incomplete clinical labels/scores, previous learning-based studies often simply discard subjects without ground-truth scores. This would result in limited training data for learning reliable and robust models. Also, existing methods focus only on using hand-crafted features (e.g., image intensity or tissue volume) of MRI data, and these features may not be well coordinated with prediction models. In this paper, we propose a weakly supervised densely connected neural network (wiseDNN) for brain disease prognosis using baseline MRI data and incomplete clinical scores. Specifically, we first extract multiscale image patches (located by anatomical landmarks) from MRI to capture local-to-global structural information of images, and then develop a weakly supervised densely connected network for task-oriented extraction of imaging features and joint prediction of multiple clinical measures. A weighted loss function is further employed to make full use of all available subjects (even those without ground-truth scores at certain time-points) for network training. The experimental results on 1469 subjects from both ADNI-1 and ADNI-2 datasets demonstrate that our proposed method can efficiently predict future clinical measures of subjects.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School > Department of Artificial Intelligence > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.