Data-specific feature selection method identification for most reproducible connectomic feature discovery fingerprinting brain states

Nicolas Georges, Islem Rekik (Lead / Corresponding author),

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)
69 Downloads (Pure)

Abstract

Machine learning methods present unprecedented opportunities to advance our understanding of the connectomics of brain disorders. With the proliferation of extremely high-dimensional connectomic data drawn from multiple neuroimaging sources (e.g., functional and structural MRIs), effective feature selection (FS) methods have become indispensable components for (i) disentangling brain states (e.g., early vs late mild cognitive impairment) and (ii) identifying connectional features that might serve as biomarkers for treatment. Strangely, despite the extensive work on identifying stable discriminative features using a particular FS method, the challenge of choosing the best one from a large pool of existing FS techniques for optimally achieving (i) and (ii) using a dataset of interest remains unexplored. In essence, the question that we aim to address in this work is: “Given a set of feature selection methods {FS1,&FSk}, and a dataset of interest, which FS method might produce the most reproducible and ‘trustworthy’ connectomic features that accurately differentiate between two brain states?” This paper is an attempt to address this question by evaluating the performance of a particular feature selection for a specific data type in fulfilling criteria (i) and (ii). To this aim, we propose to model the relationships between a set of FS methods using a multi-graph architecture, where each graph quantifies the feature reproducibility power between graph nodes at a fixed number of top ranked features. Next, we integrate the reproducibility graphs with a discrepancy graph which captures the difference in classification performance between FS methods. This allows to identify, for a dataset of interest, the ‘central’ node with the highest degree, which reveals the most reliable and reproducible FS method for the target brain state classification task along with the most discriminative features fingerprinting these brain states. We evaluated our method on multi-view brain connectomic data for late mild cognitive impairment vs Alzheimer’s disease classification. Our experiments give insights into reproducible connectional features fingerprinting late dementia brain states.

Original languageEnglish
Title of host publicationConnectomics in NeuroImaging
Subtitle of host publicationSecond International Workshop, CNI 2018, Held in Conjunction with MICCAI 2018, Proceedings
EditorsGuorong Wu, Markus D. Schirmer, Ai Wern Chung, Islem Rekik, Brent Munsell
Place of PublicationSwitzerland
PublisherSpringer Verlag
Pages99-106
Number of pages8
Volume11083
ISBN (Electronic)9783030007553
ISBN (Print)9783030007546
DOIs
Publication statusPublished - 2018
Event2nd International Workshop on Connectomics in NeuroImaging, CNI 2018 held in conjunction with the 21st International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018 - Granada, Spain
Duration: 20 Sep 201820 Sep 2018

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11083
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference2nd International Workshop on Connectomics in NeuroImaging, CNI 2018 held in conjunction with the 21st International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018
CountrySpain
CityGranada
Period20/09/1820/09/18

    Fingerprint

Cite this

Georges, N., Rekik, I. (2018). Data-specific feature selection method identification for most reproducible connectomic feature discovery fingerprinting brain states. In G. Wu, M. D. Schirmer, A. W. Chung, I. Rekik, & B. Munsell (Eds.), Connectomics in NeuroImaging: Second International Workshop, CNI 2018, Held in Conjunction with MICCAI 2018, Proceedings (Vol. 11083, pp. 99-106). (Lecture Notes in Computer Science; Vol. 11083). Springer Verlag. https://doi.org/10.1007/978-3-030-00755-3_11