On statistical tests of functional connectome fingerprinting. Issue 1 (19th February 2021)
- Record Type:
- Journal Article
- Title:
- On statistical tests of functional connectome fingerprinting. Issue 1 (19th February 2021)
- Main Title:
- On statistical tests of functional connectome fingerprinting
- Authors:
- Wang, Zeyi
Sair, Haris I.
Crainiceanu, Ciprian
Lindquist, Martin
Landman, Bennett A.
Resnick, Susan
Vogelstein, Joshua T.
Caffo, Brian - Abstract:
- Abstract: Fingerprinting of functional connectomes is an increasingly standard measure of reproducibility in functional magnetic resonance imaging connectomics. In such studies, one attempts to match a subject's first session image with their second, in a blinded fashion, in a group of subjects measured twice. The number or percentage of correct matches is usually reported as a statistic, which is then used in permutation tests. Despite the simplicity and increasing popularity of such procedures, the soundness of the statistical tests, the power, and the factors impacting the test are unstudied. In this article, we investigate the statistical tests of matching based on exchangeability assumption in the fingerprinting analysis. We show that a nearly universal Poisson(1) approximation applies for different matching schemes. We theoretically investigate the permutation tests and explore the issue that the test is overly sensitive to uninteresting directions in the alternative hypothesis, such as clustering due to familial status or demographics. We perform a numerical study on two functional magnetic resonance imaging (fMRI) resting‐state datasets, the Human Connectome Project (HCP) and the Baltimore Longitudinal Study of Aging (BLSA). These datasets are instructive, as the HCP includes technical replications of long scans and includes monozygotic and dizygotic twins, as well as non‐twin siblings. In contrast, the BLSA study incorporates more typical length resting‐state scansAbstract: Fingerprinting of functional connectomes is an increasingly standard measure of reproducibility in functional magnetic resonance imaging connectomics. In such studies, one attempts to match a subject's first session image with their second, in a blinded fashion, in a group of subjects measured twice. The number or percentage of correct matches is usually reported as a statistic, which is then used in permutation tests. Despite the simplicity and increasing popularity of such procedures, the soundness of the statistical tests, the power, and the factors impacting the test are unstudied. In this article, we investigate the statistical tests of matching based on exchangeability assumption in the fingerprinting analysis. We show that a nearly universal Poisson(1) approximation applies for different matching schemes. We theoretically investigate the permutation tests and explore the issue that the test is overly sensitive to uninteresting directions in the alternative hypothesis, such as clustering due to familial status or demographics. We perform a numerical study on two functional magnetic resonance imaging (fMRI) resting‐state datasets, the Human Connectome Project (HCP) and the Baltimore Longitudinal Study of Aging (BLSA). These datasets are instructive, as the HCP includes technical replications of long scans and includes monozygotic and dizygotic twins, as well as non‐twin siblings. In contrast, the BLSA study incorporates more typical length resting‐state scans in a longitudinal study. Finally, a study of single regional connections is performed on the HCP data. Résumé: La prise d'empreintes du connectome fonctionnel est une mesure de reproductibilité de plus en plus courante pour la connectomique fonctionnelle en imagerie par résonnance magnétique. De telles études consistent à apparier à l'aveugle les images de la première séance d'un sujet avec celles d'une seconde séance, et ce pour tous les participants. Le nombre ou la proportion d'appariements corrects est habituellement rapporté comme statistique qui est ensuite utilisée dans des tests de permutations. Malgré la simplicité et la popularité croissante de telles procédures, la justesse des tests statistiques, leur puissance et les facteurs pouvant les influencer n'ont pas été étudiés. Les auteurs s'intéressent aux tests statistiques d'appariements exploitant le caractère échangeable des analyses d'empreintes du connectome. Ils montrent une approximation de Poisson(1) presque universelle s'appliquant à différents schémas d'appariements. Ils examinent d'un point de vue théorique les tests de permutation, notamment les enjeux liés à leur sensibilité trop grande dans des directions inintéressantes de la contre‐hypothèse, par exemple des regroupements dus à un statut familial ou démographique. Les auteurs procèdent à l'analyse numérique de deux jeux de données de résonnance magnétique fonctionnelle (fMRI) au repos, nommément le projet du connectome humain (PCH) et l'étude longitudinale de Baltimore sur le vieillissement (ELBV). Ces jeux de données sont instructifs. En effet, le PCH comporte des répétitions techniques de longs scans et compte des sujets qui proviennent d'une même famille, notamment des jumeaux monozygotes et dizygotes. À l'opposé, l'ELBV comporte des durées de repos qui sont plus typiques des études longitudinales. Finalement, les auteurs procèdent à une étude des connections régionales uniques avec les données du PCH. … (more)
- Is Part Of:
- Canadian journal of statistics. Volume 49:Issue 1(2021)
- Journal:
- Canadian journal of statistics
- Issue:
- Volume 49:Issue 1(2021)
- Issue Display:
- Volume 49, Issue 1 (2021)
- Year:
- 2021
- Volume:
- 49
- Issue:
- 1
- Issue Sort Value:
- 2021-0049-0001-0000
- Page Start:
- 63
- Page End:
- 88
- Publication Date:
- 2021-02-19
- Subjects:
- Permutation test -- exchangeability -- hypothesis testing -- imaging -- neuroimaging
Mathematical statistics -- Periodicals
519.5 - Journal URLs:
- http://archimede.mat.ulaval.ca/cjs/ ↗
http://onlinelibrary.wiley.com/journal/10.1002/(ISSN)1708-945X/issues ↗
http://www.jstor.org/journals/03195724.html ↗
http://onlinelibrary.wiley.com/ ↗
http://www.ingentaconnect.com/content/ssc/cjs ↗
http://www.mat.ulaval.ca/rcs/indexe.shtml ↗ - DOI:
- 10.1002/cjs.11591 ↗
- Languages:
- English
- ISSNs:
- 0319-5724
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 3035.760000
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 17405.xml