Weakly Supervised Deep Learning for Brain Disease Prognosis Using MRI and Incomplete Clinical Scores

• Published in: IEEE Transactions on Cybernetics Vol. 50; no. 7; pp. 3381 - 3392
• Main Authors: Liu, Mingxia, Zhang, Jun, Lian, Chunfeng, Shen, Dinggang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2020; Institute of Electrical and Electronics Engineers (IEEE); The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Alzheimer Disease; Alzheimer Disease - diagnostic imaging; Alzheimer’s disease (AD); Brain; Brain - diagnostic imaging; Brain diseases; Brain modeling; clinical score; Deep Learning; disease prognosis; Diseases; Feature extraction; Humans; Image Interpretation, Computer-Assisted; Image Interpretation, Computer-Assisted - methods; Magnetic Resonance Imaging; Magnetic Resonance Imaging - methods; Medical imaging; Medical prognosis; neural network; Neural networks; Prediction models; Prognosis; Prognostics and health management; Supervised Machine Learning; Training; weakly supervised learning
• ISSN: 2168-2267; 2168-2275; 2168-2275
• DOI: 10.1109/TCYB.2019.2904186

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.