Universität zu Köln

Monte-Rubio, Gemma C. ORCID: 0000-0002-3532-2224, Segura, Barbara ORCID: 0000-0002-9673-5479, Strafella, Antonio P., van Eimeren, Thilo, Ibarretxe-Bilbao, Naroa ORCID: 0000-0002-2434-5252, Diez-Cirarda, Maria, Eggers, Carsten, Lucas-Jimenez, Olaia, Ojeda, Natalia, Pena, Javier, Ruppert, Marina C., Sala-Llonch, Roser ORCID: 0000-0003-3576-0475, Theis, Hendrik, Uribe, Carme ORCID: 0000-0002-1415-687X and Junque, Carme ORCID: 0000-0002-6381-3063 (2022). Parameters from site classification to harmonize MRI clinical studies: Application to a multi-site Parkinson's disease dataset. Hum. Brain Mapp., 43 (10). S. 3130 - 3143. HOBOKEN: WILEY. ISSN 1097-0193

Full text not available from this repository.

Abstract

Multi-site MRI datasets are crucial for big data research. However, neuroimaging studies must face the batch effect. Here, we propose an approach that uses the predictive probabilities provided by Gaussian processes (GPs) to harmonize clinical-based studies. A multi-site dataset of 216 Parkinson's disease (PD) patients and 87 healthy subjects (HS) was used. We performed a site GP classification using MRI data. The outcomes estimated from this classification, redefined like Weighted HARMonization PArameters (WHARMPA), were used as regressors in two different clinical studies: A PD versus HS machine learning classification using GP, and a VBM comparison (FWE-p < .05, k = 100). Same studies were also conducted using conventional Boolean site covariates, and without information about site belonging. The results from site GP classification provided high scores, balanced accuracy (BAC) was 98.39% for grey matter images. PD versus HS classification performed better when the WHARMPA were used to harmonize (BAC = 78.60%; AUC = 0.90) than when using the Boolean site information (BAC = 56.31%; AUC = 0.71) and without it (BAC = 57.22%; AUC = 0.73). The VBM analysis harmonized using WHARMPA provided larger and more statistically robust clusters in regions previously reported in PD than when the Boolean site covariates or no corrections were added to the model. In conclusion, WHARMPA might encode global site-effects quantitatively and allow the harmonization of data. This method is user-friendly and provides a powerful solution, without complex implementations, to clean the analyses by removing variability associated with the differences between sites.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Monte-Rubio, Gemma C. UNSPECIFIED orcid.org/0000-0002-3532-2224 UNSPECIFIED Segura, Barbara UNSPECIFIED orcid.org/0000-0002-9673-5479 UNSPECIFIED Strafella, Antonio P. UNSPECIFIED UNSPECIFIED UNSPECIFIED van Eimeren, Thilo UNSPECIFIED UNSPECIFIED UNSPECIFIED Ibarretxe-Bilbao, Naroa UNSPECIFIED orcid.org/0000-0002-2434-5252 UNSPECIFIED Diez-Cirarda, Maria UNSPECIFIED UNSPECIFIED UNSPECIFIED Eggers, Carsten UNSPECIFIED UNSPECIFIED UNSPECIFIED Lucas-Jimenez, Olaia UNSPECIFIED UNSPECIFIED UNSPECIFIED Ojeda, Natalia UNSPECIFIED UNSPECIFIED UNSPECIFIED Pena, Javier UNSPECIFIED UNSPECIFIED UNSPECIFIED Ruppert, Marina C. UNSPECIFIED UNSPECIFIED UNSPECIFIED Sala-Llonch, Roser UNSPECIFIED orcid.org/0000-0003-3576-0475 UNSPECIFIED Theis, Hendrik UNSPECIFIED UNSPECIFIED UNSPECIFIED Uribe, Carme UNSPECIFIED orcid.org/0000-0002-1415-687X UNSPECIFIED Junque, Carme UNSPECIFIED orcid.org/0000-0002-6381-3063 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-692810
DOI:	10.1002/hbm.25838
Journal or Publication Title:	Hum. Brain Mapp.
Volume:	43
Number:	10
Page Range:	S. 3130 - 3143
Date:	2022
Publisher:	WILEY
Place of Publication:	HOBOKEN
ISSN:	1097-0193
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language RELIABILITY; SCANNER; EXPRESSION; ATROPHY Multiple languages Neurosciences; Neuroimaging; Radiology, Nuclear Medicine & Medical Imaging Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/69281