1. A hypothesis-driven method based on machine learning for neuroimaging data analysis
- Author
-
Gorriz, Juan M., Martín Clemente, Rubén, Puntonet, C.G., Ortiz García, Andrés, Ramírez Pérez, Javier, SiPBA Group, Suckling, John, [Gorriz, J. M.] Univ Granada, DaSCI Inst, Granada, Spain, [Ramirez, J.] Univ Granada, DaSCI Inst, Granada, Spain, [SiPBA Grp] Univ Granada, DaSCI Inst, Granada, Spain, [Gorriz, J. M.] Univ Cambridge, Dept Psychiat, Cambridge, England, [Suckling, J.] Univ Cambridge, Dept Psychiat, Cambridge, England, [Gorriz, J. M.] IbsGranada, Granada, Spain, [Puntonet, C. G.] Univ Granada, Dept Comp Architecture & Technol, Granada, Spain, [Martin-Clemente, R.] Univ Seville, Dept Signal Theory & Commun, Seville, Spain, [Ortiz, A.] Univ Malaga, Dept Commun Engn, Malaga, Spain, MCIN/AEI, FEDER ``Una manera de hacer Europa', Consejeria de Economia, Innovacion, Ciencia y Empleo (Junta de Andalucia), FEDER, research project ACACIA, Junta de Andalucia (Consejeria de Economia, Conocimiento, Empresas y Universidad), Universidad de Sevilla. Departamento de Teoría de la Señal y Comunicaciones, Universidad de Sevilla. TIC246: Tecnologías de aprendizaje automático y procesado digital de la información, Agencia Estatal de Investigación. España, Fondo Europeo de Desarrollo Regional (FEDER), Consejería de Economía, Innovación, Ciencia y Empleo. Junta de Andalucía, and Consejería de Economía, Conocimiento, Empresas y Universidad. Junta de Andalucía
- Subjects
Functional mri ,FOS: Computer and information sciences ,Computer Science - Machine Learning ,Support vector machine ,Cognitive Neuroscience ,Random Field Theory ,Framework ,Image and Video Processing (eess.IV) ,Support Vector Regression ,Machine Learning (stat.ML) ,Electrical Engineering and Systems Science - Image and Video Processing ,Statistics::Computation ,Machine Learning (cs.LG) ,Computer Science Applications ,permutation tests ,Magnetic resonance imaging ,Statistics - Machine Learning ,Artificial Intelligence ,Linear Regression Model ,Diagnosis ,FOS: Electrical engineering, electronic engineering, information engineering ,Support Vector Regression permutation tests ,Statistics::Methodology ,General Linear Model - Abstract
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 randomly permuting image labels or by the use of random effect models that consider between-subject variability. These multivariate ML-based statistical pipelines, whilst potentially more effective for detecting activations than hypotheses-driven methods, have lost their mathematical elegance, ease of interpretation, 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 statistical power and the control of false positives, outperforming the regular GLM., MCIN/AEI, FEDER ``Una manera de hacer Europa" RTI2018-098913-B100, Junta de Andalucia, European Commission CV20-45250 A-TIC-080-UGR18 B-TIC586-UGR20 P20-00525, research project ACACIA US-1264994, European Commission, Junta de Andalucia (Consejeria de Economia, Conocimiento, Empresas y Universidad)
- Published
- 2022