Healthy core: Harmonizing brain MRI for supporting multicenter migraine classification studies.

Multicenter and multi-scanner imaging studies may be necessary to ensure sufficiently large sample sizes for developing accurate predictive models. However, multicenter studies, incorporating varying research participant characteristics, MRI scanners, and imaging acquisition protocols, may introduce...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyunsoo Yoon, Todd J Schwedt, Catherine D Chong, Oyekanmi Olatunde, Teresa Wu
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2024-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0288300
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850024973026983936
author Hyunsoo Yoon
Todd J Schwedt
Catherine D Chong
Oyekanmi Olatunde
Teresa Wu
author_facet Hyunsoo Yoon
Todd J Schwedt
Catherine D Chong
Oyekanmi Olatunde
Teresa Wu
author_sort Hyunsoo Yoon
collection DOAJ
description Multicenter and multi-scanner imaging studies may be necessary to ensure sufficiently large sample sizes for developing accurate predictive models. However, multicenter studies, incorporating varying research participant characteristics, MRI scanners, and imaging acquisition protocols, may introduce confounding factors, potentially hindering the creation of generalizable machine learning models. Models developed using one dataset may not readily apply to another, emphasizing the importance of classification model generalizability in multi-scanner and multicenter studies for producing reproducible results. This study focuses on enhancing generalizability in classifying individual migraine patients and healthy controls using brain MRI data through a data harmonization strategy. We propose identifying a 'healthy core'-a group of homogeneous healthy controls with similar characteristics-from multicenter studies. The Maximum Mean Discrepancy (MMD) in Geodesic Flow Kernel (GFK) space is employed to compare two datasets, capturing data variabilities and facilitating the identification of this 'healthy core'. Homogeneous healthy controls play a vital role in mitigating unwanted heterogeneity, enabling the development of highly accurate classification models with improved performance on new datasets. Extensive experimental results underscore the benefits of leveraging a 'healthy core'. We utilized two datasets: one comprising 120 individuals (66 with migraine and 54 healthy controls), and another comprising 76 individuals (34 with migraine and 42 healthy controls). Notably, a homogeneous dataset derived from a cohort of healthy controls yielded a significant 25% accuracy improvement for both episodic and chronic migraineurs.
format Article
id doaj-art-8bfb8fef1bd64642b319069b2df9608b
institution DOAJ
issn 1932-6203
language English
publishDate 2024-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-8bfb8fef1bd64642b319069b2df9608b2025-08-20T03:00:58ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-011912e028830010.1371/journal.pone.0288300Healthy core: Harmonizing brain MRI for supporting multicenter migraine classification studies.Hyunsoo YoonTodd J SchwedtCatherine D ChongOyekanmi OlatundeTeresa WuMulticenter and multi-scanner imaging studies may be necessary to ensure sufficiently large sample sizes for developing accurate predictive models. However, multicenter studies, incorporating varying research participant characteristics, MRI scanners, and imaging acquisition protocols, may introduce confounding factors, potentially hindering the creation of generalizable machine learning models. Models developed using one dataset may not readily apply to another, emphasizing the importance of classification model generalizability in multi-scanner and multicenter studies for producing reproducible results. This study focuses on enhancing generalizability in classifying individual migraine patients and healthy controls using brain MRI data through a data harmonization strategy. We propose identifying a 'healthy core'-a group of homogeneous healthy controls with similar characteristics-from multicenter studies. The Maximum Mean Discrepancy (MMD) in Geodesic Flow Kernel (GFK) space is employed to compare two datasets, capturing data variabilities and facilitating the identification of this 'healthy core'. Homogeneous healthy controls play a vital role in mitigating unwanted heterogeneity, enabling the development of highly accurate classification models with improved performance on new datasets. Extensive experimental results underscore the benefits of leveraging a 'healthy core'. We utilized two datasets: one comprising 120 individuals (66 with migraine and 54 healthy controls), and another comprising 76 individuals (34 with migraine and 42 healthy controls). Notably, a homogeneous dataset derived from a cohort of healthy controls yielded a significant 25% accuracy improvement for both episodic and chronic migraineurs.https://doi.org/10.1371/journal.pone.0288300
spellingShingle Hyunsoo Yoon
Todd J Schwedt
Catherine D Chong
Oyekanmi Olatunde
Teresa Wu
Healthy core: Harmonizing brain MRI for supporting multicenter migraine classification studies.
PLoS ONE
title Healthy core: Harmonizing brain MRI for supporting multicenter migraine classification studies.
title_full Healthy core: Harmonizing brain MRI for supporting multicenter migraine classification studies.
title_fullStr Healthy core: Harmonizing brain MRI for supporting multicenter migraine classification studies.
title_full_unstemmed Healthy core: Harmonizing brain MRI for supporting multicenter migraine classification studies.
title_short Healthy core: Harmonizing brain MRI for supporting multicenter migraine classification studies.
title_sort healthy core harmonizing brain mri for supporting multicenter migraine classification studies
url https://doi.org/10.1371/journal.pone.0288300
work_keys_str_mv AT hyunsooyoon healthycoreharmonizingbrainmriforsupportingmulticentermigraineclassificationstudies
AT toddjschwedt healthycoreharmonizingbrainmriforsupportingmulticentermigraineclassificationstudies
AT catherinedchong healthycoreharmonizingbrainmriforsupportingmulticentermigraineclassificationstudies
AT oyekanmiolatunde healthycoreharmonizingbrainmriforsupportingmulticentermigraineclassificationstudies
AT teresawu healthycoreharmonizingbrainmriforsupportingmulticentermigraineclassificationstudies