Multimodal active subspace analysis for computing assessment oriented subspaces from neuroimaging data
Journal of Neuroscience Methods · 2024
DOI: 10.1016/j.jneumeth.2024.110109 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neuroscience Methods, 2024. Verfasst von Ishaan Batta und 3 weiteren Autor:innen. Beteiligte Einrichtung: Center for Translational Research in Neuroimaging and Data Science (TReNDS): Georgia State University, Georgia Institute of Technology, and Emory Uni…. Hauptthemen laut MEDLINE: Alzheimer Disease, Brain, Neuroimaging, Machine Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS, National Science Foundation, National Institutes of Health.
Abstract (Originalsprache)
BACKGROUND: For successful biomarker discovery, it is essential to develop computational frameworks that summarize high-dimensional neuroimaging data in terms of involved sub-systems of the brain, while also revealing underlying heterogeneous functional and structural changes covarying with specific cognitive and biological traits. However, unsupervised decompositions do not inculcate clinical assessment information, while supervised approaches extract only individual feature importance, thereby impeding qualitative interpretation at the level of subspaces. NEW METHOD: We present a novel framework to extract robust multimodal brain subspaces associated with changes in a given cognitive or biological trait. Our approach involves active subspace learning on the gradients of a trained machine learning model followed by clustering to extract and summarize the most salient and consistent subspaces associated with the target variable. RESULTS: Through a rigorous cross-validation procedure on an Alzheimer's disease (AD) dataset, our framework successfully extracts multimodal subspaces specific to a given clinical assessment (e.g., memory and other cognitive skills), and also retains predictive performance in standard machine learning algorithms. We also show that the salient active subspace directions occur consistently across randomly sub-sampled repetitions of the analysis. COMPARISON WITH EXISTING METHOD(S): Compared to existing unsupervised decompositions based on principle component analysis, the subspace components in our framework retain higher predictive information. CONCLUSIONS: As an important step towards biomarker discovery, our framework not only uncovers AD-related brain regions in the associated brain subspaces, but also enables automated identification of multiple underlying structural and functional sub-systems of the brain that collectively characterize changes in memory and proficiency in cognitive skills related to brain disorders like AD.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center for Translational Research in Neuroimaging and Data Science (TReNDS): Georgia State University, Georgia Institute of Technology, and Emory University, Atlanta, USA; Department of Electrical and Computer Engineeri…
- Center for Translational Research in Neuroimaging and Data Science (TReNDS): Georgia State University, Georgia Institute of Technology, and Emory University, Atlanta, USA.
Förderung
- NIA NIH HHS
- National Science Foundation
- National Institutes of Health
Zitieren
APA
Batta, I., Abrol, A., Calhoun, V. D., & Alzheimer’s Disease Neuroimaging Initiative (2024). Multimodal active subspace analysis for computing assessment oriented subspaces from neuroimaging data. Journal of Neuroscience Methods. https://doi.org/10.1016/j.jneumeth.2024.110109
Vancouver
Batta I, Abrol A, Calhoun VD, Alzheimer’s Disease Neuroimaging Initiative. Multimodal active subspace analysis for computing assessment oriented subspaces from neuroimaging data. Journal of Neuroscience Methods. 2024. doi:10.1016/j.jneumeth.2024.110109
BibTeX
@article{Batta2024,
author = {Batta, Ishaan and Abrol, Anees and Calhoun, Vince D and Alzheimer’s Disease Neuroimaging Initiative, Alzheimer’s Disease Neuroimaging Initiative},
title = {Multimodal active subspace analysis for computing assessment oriented subspaces from neuroimaging data},
journal = {Journal of Neuroscience Methods},
year = {2024},
doi = {10.1016/j.jneumeth.2024.110109}
}
EUVIMED