Patch-based surface morphometry feature selection with federated group lasso regression

Collectively, vast quantities of brain imaging data exist across hospitals and research institutions, providing valuable resources to study brain disorders such as Alzheimer’s disease (AD). However, in practice, putting all these distributed datasets into a centralized platform is infeasible due to patient privacy concerns, data restrictions and legal regulations. In this study, we propose a novel federated feature selection framework that can analyze the data at each individual institution without data-sharing or accessing private patient information. In this framework, we first propose a federated group lasso optimization method based on block coordinate descent. We employ stability selection to determine statistically significant features, by solving the group lasso problem with a sequence of regularization parameters. To accelerate the stability selection, we further propose a federated screening rule, which can identify and exclude the irrelevant features before solving the group lasso. Here, we use this framework for patch based feature selection on hippocampal morphometry. Shape is characterized through two different kinds of local measures, the radial distance and the surface area determined via tensor-based morphometry (TBM). The method is tested on 1,127 T1-weighted brain magnetic resonance images (MRI) of AD, mild cognitive impairment (MCI) and elderly control subjects, randomly assigned to five independent hypothetical institutions for testing purpose. We examine the association of MRI-based anatomical measures with general cognitive assessment and amyloid burden to identify the morphometry changes related to AD deterioration and plaque accumulation. Finally, we visualize the significance of the association on the hippocampal surfaces. Our experimental results successfully demonstrate the efficiency and effectiveness of our method.

[1]  Paul M. Thompson,et al.  Mapping hippocampal and ventricular change in Alzheimer disease , 2004, NeuroImage.

[2]  M. Yuan,et al.  Model selection and estimation in regression with grouped variables , 2006 .

[3]  Jingrui He,et al.  Missing information imputation for disease-dedicated social networks with heterogeneous auxiliary data , 2020, IISE Transactions on Healthcare Systems Engineering.

[4]  Moo K. Chung,et al.  Tensor-Based Cortical Surface Morphometry via Weighted Spherical Harmonic Representation , 2008, IEEE Transactions on Medical Imaging.

[5]  Anand D. Sarwate,et al.  Large scale collaboration with autonomy: Decentralized data ICA , 2015, 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP).

[6]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[7]  Stephen Pickup,et al.  Characterizing the human hippocampus in aging and Alzheimer’s disease using a computational atlas derived from ex vivo MRI and histology , 2018, Proceedings of the National Academy of Sciences.

[8]  Jingrui He,et al.  Convolution-Consistent Collective Matrix Completion , 2019, CIKM.

[9]  Paul M. Thompson,et al.  Surface fluid registration of conformal representation: Application to detect disease burden and genetic influence on hippocampus , 2013, NeuroImage.

[10]  Moo K. Chung,et al.  Cortical thickness analysis in autism with heat kernel smoothing , 2005, NeuroImage.

[11]  Anand D. Sarwate,et al.  COINSTAC: A Privacy Enabled Model and Prototype for Leveraging and Processing Decentralized Brain Imaging Data , 2016, Front. Neurosci..

[12]  N. Meinshausen,et al.  Stability selection , 2008, 0809.2932.

[13]  Paul M. Thompson,et al.  Large-Scale Collaborative Imaging Genetics Studies of Risk Genetic Factors for Alzheimer's Disease Across Multiple Institutions , 2016, MICCAI.

[14]  Dean F. Wong,et al.  Standardization of amyloid quantitation with florbetapir standardized uptake value ratios to the Centiloid scale , 2018, Alzheimer's & Dementia.

[15]  Jie Wang,et al.  Lasso screening rules via dual polytope projection , 2012, J. Mach. Learn. Res..

[16]  Paul M. Thompson,et al.  Studying ventricular abnormalities in mild cognitive impairment with hyperbolic Ricci flow and tensor-based morphometry , 2015, NeuroImage.

[17]  Alan C. Evans,et al.  Growth patterns in the developing brain detected by using continuum mechanical tensor maps , 2000, Nature.

[18]  Katya Scheinberg,et al.  Noname manuscript No. (will be inserted by the editor) Efficient Block-coordinate Descent Algorithms for the Group Lasso , 2022 .

[19]  Jiayu Zhou,et al.  Feature selective temporal prediction of Alzheimer's disease progression using hippocampus surface morphometry , 2017, Brain and behavior.

[20]  Yang Song,et al.  Surface-based Tbm Boosts Power to Detect Disease Effects on the Brain: an N = 804 Adni Study ☆ and the Alzheimer's Disease Neuroimaging Initiative , 2022 .

[21]  Roger P. Woods,et al.  Characterizing volume and surface deformations in an atlas framework: theory, applications, and implementation , 2003, NeuroImage.

[22]  C. Davatzikos Spatial normalization of 3D brain images using deformable models. , 1996, Journal of computer assisted tomography.

[23]  Mark W. Woolrich,et al.  Advances in functional and structural MR image analysis and implementation as FSL , 2004, NeuroImage.

[24]  Paul A. Yushkevich,et al.  Segmentation, registration, and measurement of shape variation via image object shape , 1999, IEEE Transactions on Medical Imaging.

[25]  Jie Zhang,et al.  Hippocampus morphometry study on pathology-confirmed Alzheimer's disease patients with surface multivariate morphometry statistics , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[26]  Thomas E. Nichols,et al.  The ENIGMA Consortium: large-scale collaborative analyses of neuroimaging and genetic data , 2014, Brain Imaging and Behavior.