Sparse shared structure based multi-task learning for MRI based cognitive performance prediction of Alzheimer's disease. (December 2017)

• Record Type: Journal Article
• Authors: Cao, Peng; Shan, Xuanfeng; Zhao, Dazhe; Huang, Min; Zaiane, Osmar
• Is Part Of: Pattern recognition. Volume 72(2017:Dec.)
• Page Start: 219
• Page End: 235
• Publication Date: 2017-12
• Subjects: Alzheimer's disease -- Multi-task learning -- Proximal gradient -- Regression -- Biomarker discovery; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.07.018
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A mixed sparse shared structure based multi-task learning is proposed. The formulation can be applied on regression, classification or clustering. An efficient optimization algorithm is derived to solve the nonsmooth formulation. Experimental results demonstrate significant performance improvements over the existing methods. Our method is able to discover the biomarkers relevant to cognitive performance and fuse the multi-modality data. Abstract: Alzheimer's disease (AD), the most common form of dementia, not only causes progressive impairment of memory and other cognitive functions of patients, but also becomes the substantial financial burden to the health care system. There is thus an urgent need to (1) accurately predict the cognitive performance of the disease, and (2) identify potential MRI-related biomarkers most predictive of the estimation of cognitive outcomes. In this paper, we develop a novel multi-task learning formulation to explore the correlation existing in Magnetic Resonance Imaging (MRI) and cognitive measures by a mixed norm incorporating a hierarchical group sparsity and shared subspace uncovering regularization, to learn a shared structure from multiple related tasks with considering implicit shared subspace structure and explicit subset of features as well as Region-of-Interests (ROIs) simultaneously. An efficient alternating optimization algorithm is derived to solve the proposed non-convex and non-smooth objective formulation. We comprehensively evaluate the proposed algorithm for the cognitive outcome prediction including all subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The experimental results not only demonstrate the proposed method has superior performance over multiple state-of-the-art comparable approaches, but also identifies cognition-relevant MRI biomarkers that are consistent with prior knowledge.