Structured sparsity regularized multiple kernel learning for Alzheimer’s disease diagnosis

• Published in: Pattern recognition Vol. 88; pp. 370 - 382
• Main Authors: Peng, Jialin, Zhu, Xiaofeng, Wang, Ye, An, Le, Shen, Dinggang
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.04.2019
• Subjects: Alzheimer’s disease diagnosis; Feature selection; Multimodal features; Multiple kernel learning; Structured sparsity; Multiple kernel learning; Structured sparsity; Feature selection; Alzheimer’s disease diagnosis; Multimodal features
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2018.11.027

•For Alzheimer’s disease (AD) diagnosis, we consider the integration of multi-modality imaging and genetic data which encode different level of knowledge.•With a focus on taking advantage of both phenotype and genotype information, a novel structured sparsity, defined by ℓ1, p -norm (p > 1), regularized multiple kernel learning method is designed.•An efficient block coordinate descent algorithm applicable to any case with p > 1 was derived to solve the proposed formulation. Multimodal data fusion has shown great advantages in uncovering information that could be overlooked by using single modality. In this paper, we consider the integration of high-dimensional multi-modality imaging and genetic data for Alzheimer’s disease (AD) diagnosis. With a focus on taking advantage of both phenotype and genotype information, a novel structured sparsity, defined by ℓ1, p-norm (p > 1), regularized multiple kernel learning method is designed. Specifically, to facilitate structured feature selection and fusion from heterogeneous modalities and also capture feature-wise importance, we represent each feature with a distinct kernel as a basis, followed by grouping the kernels according to modalities. Then, an optimally combined kernel presentation of multimodal features is learned in a data-driven approach. Contrary to the Group Lasso (i.e., ℓ2, 1-norm penalty) which performs sparse group selection, the proposed regularizer enforced on kernel weights is to sparselyselect concise feature set within each homogenous group and fuse the heterogeneous feature groups by taking advantage of dense norms. We have evaluated our method using data of subjects from Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. The effectiveness of the method is demonstrated by the clearly improved prediction diagnosis and also the discovered brain regions and SNPs relevant to AD.