Sparse Multi-Task Regression and Feature Selection to Identify Brain Imaging Predictors for Memory Performance

By Hua Wang, Feiping Nie, Heng Huang, Shannon L. Risacher, Chris H. Q. Ding, Andrew J. Saykin, Li Shen. 2011

144 citations recorded by the source corpus.

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by progressive impairment of memory and other cognitive functions, which makes regression analysis a suitable model to study whether neuroimaging measures can help predict memory performance and track the progression of AD. Existing memory performance prediction methods via regression, however, do not take into account either the interconnected structures within imaging data or those among memory scores, which inevitably restricts their predictive capabilities. To bridge this gap, we propose a novel Sparse Multi-tAsk Regression and feaTure selection (SMART) method to jointly analyze all the imaging and clinical data under a single regression framework and with shared underlying sparse representations. Two convex regularizations are combined and used in the model to enable sparsity as well as facilitate multi-task learning. The effectiveness of the proposed method is demonstrated by both clearly improved prediction performances in all empirical test cases and a compact set of selected RAVLT-relevant MRI predictors that accord with prior studies.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yu Zhang
2. Dacheng Tao
3. Qiang Yang
4. Feiping Nie
5. Xuelong Li
6. Jie Gui
7. Mingsheng Long
8. Hua Wang

Citations in the corpus

• An Overview of Multi-task Learning (2018, neutral): “Applications of MTL based on non-facial images include object categorization [86], image segmentation [89,90], identifying brain imaging predictors [91], saliency detection [92], action recognition [93], scene classification [94], multi-attribute prediction [95], multi-camera person re-identificatio”
• A Survey on Multi-Task Learning (2017, methodology): “In [167], a multi-task feature selection method based on both the `2,1 and `1 norms is proposed to identify brain imaging predictors for memory performance.”
• Feature Selection Based on Structured Sparsity: A Comprehensive Study (2017, methodology): “In [108] and [109], a new multitask feature selection method based on MTFL is proposed.”
• Block-Row Sparse Multiview Multilabel Learning for Image Classification (2016, background): “2(a)–(c)] and joint sparse learning [see [52], [53], and the”
• High-Order Multi-Task Feature Learning to Identify Longitudinal Phenotypic Markers for Alzheimer's Disease Progression Prediction (2012, background): “Neuroimaging measures have be en widely studied to predict disease status and/or cognitive performance [1, 2, 3, 4, 5, 6, 7].”
• Robust and Discriminative Self-Taught Learning (2013, methodology): “iteratively re-weighted method (Gorodnitsky & Rao, 1997; Nie et al., 2010; Wang et al., 2011; 2012b;c; 2013) to deal with the non-smooth l2,1-norm terms.”
• Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization (2014, methodology): “Another work used similar structural regularization forms with the mixture norms for regression problems [35], which is also different from the classification scenario of FGVC.”