RT Journal Article
T1 A hypothesis-driven method based on machine learning for neuroimaging data analysis
A1 Gorriz, J. M.
A1 Martin-Clemente, R.
A1 Puntonet, C. G.
A1 Ortiz, A.
A1 Ramirez, J.
A1 Suckling, J.
K1 General Linear Model
K1 Linear Regression Model
K1 Support Vector Regression
K1 permutation tests
K1 Magnetic Resonance Imaging
K1 Random Field Theory
K1 Support vector machine
K1 Functional mri
K1 Diagnosis
K1 Framework
AB There remains an open question about the usefulness and the interpretation of machine learning (ML) approaches for discrimination of spatial patterns of brain images between samples or activation states. In the last few decades, these approaches have limited their operation to feature extraction and linear classification tasks for between-group inference. In this context, statistical inference is assessed by ran-domly permuting image labels or by the use of random effect models that consider between-subject vari-ability. These multivariate ML-based statistical pipelines, whilst potentially more effective for detecting activations than hypotheses-driven methods, have lost their mathematical elegance, ease of interpreta-tion, and spatial localization of the ubiquitous General linear Model (GLM). Recently, the estimation of the conventional GLM parameters has been demonstrated to be connected to an univariate classification task when the design matrix in the GLM is expressed as a binary indicator matrix. In this paper we explore the complete connection between the univariate GLM and ML-based regressions. To this purpose we derive a refined statistical test with the GLM based on the parameters obtained by a linear Support Vector Regression (SVR) in the inverse problem (SVR-iGLM). Subsequently, random field theory (RFT) is employed for assessing statistical significance following a conventional GLM benchmark. Experimental results demonstrate how parameter estimations derived from each model (mainly GLM and SVR) result in different experimental design estimates that are significantly related to the predefined functional task. Moreover, using real data from a multisite initiative the proposed ML-based inference demonstrates sta-tistical power and the control of false positives, outperforming the regular GLM. 
PB Elsevier BV
SN 0925-2312
YR 2022
FD 2022-09-03
LK http://hdl.handle.net/10668/22421
UL http://hdl.handle.net/10668/22421
LA en
NO J.M. Gorriz, R. Martín-Clemente, C.G. Puntonet, A. Ortiz, J. Ramírez,  SiPBA group, J. Suckling,A hypothesis-driven method based on machine learning for neuroimaging data analysis,Neurocomputing,Volume 510,2022,Pages 159-171,ISSN 0925-2312,
DS RISalud
RD Apr 11, 2025