A Novel Bayesian Linear Regression Model for the Analysis of Neuroimaging Data
In this paper, we propose a novel Machine Learning Model based on Bayesian Linear Regression intended to deal with the low sample-to-variable ratio typically found in neuroimaging studies and focusing on mental disorders. The proposed model combines feature selection capabilities with a formulation...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-03-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/5/2571 |
_version_ | 1797475598679932928 |
---|---|
author | Albert Belenguer-Llorens Carlos Sevilla-Salcedo Manuel Desco Maria Luisa Soto-Montenegro Vanessa Gómez-Verdejo |
author_facet | Albert Belenguer-Llorens Carlos Sevilla-Salcedo Manuel Desco Maria Luisa Soto-Montenegro Vanessa Gómez-Verdejo |
author_sort | Albert Belenguer-Llorens |
collection | DOAJ |
description | In this paper, we propose a novel Machine Learning Model based on Bayesian Linear Regression intended to deal with the low sample-to-variable ratio typically found in neuroimaging studies and focusing on mental disorders. The proposed model combines feature selection capabilities with a formulation in the dual space which, in turn, enables efficient work with neuroimaging data. Thus, we have tested the proposed algorithm with real MRI data from an animal model of schizophrenia. The results show that our proposal efficiently predicts the diagnosis and, at the same time, detects regions which clearly match brain areas well-known to be related to schizophrenia. |
first_indexed | 2024-03-09T20:47:25Z |
format | Article |
id | doaj.art-2e6fa549c9f34021814b722b0cc2d913 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T20:47:25Z |
publishDate | 2022-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-2e6fa549c9f34021814b722b0cc2d9132023-11-23T22:42:57ZengMDPI AGApplied Sciences2076-34172022-03-01125257110.3390/app12052571A Novel Bayesian Linear Regression Model for the Analysis of Neuroimaging DataAlbert Belenguer-Llorens0Carlos Sevilla-Salcedo1Manuel Desco2Maria Luisa Soto-Montenegro3Vanessa Gómez-Verdejo4Department of Signal Processing and Communications, University Carlos III of Madrid Leganés, 28911 Leganés, SpainDepartment of Signal Processing and Communications, University Carlos III of Madrid Leganés, 28911 Leganés, SpainDepartment of Bioengineering and Aerospace Engineering, University Carlos III of Madrid Leganés, 28911 Leganés, SpainCIBER of Mental Health (CIBERSAM), 28029 Madrid, SpainDepartment of Signal Processing and Communications, University Carlos III of Madrid Leganés, 28911 Leganés, SpainIn this paper, we propose a novel Machine Learning Model based on Bayesian Linear Regression intended to deal with the low sample-to-variable ratio typically found in neuroimaging studies and focusing on mental disorders. The proposed model combines feature selection capabilities with a formulation in the dual space which, in turn, enables efficient work with neuroimaging data. Thus, we have tested the proposed algorithm with real MRI data from an animal model of schizophrenia. The results show that our proposal efficiently predicts the diagnosis and, at the same time, detects regions which clearly match brain areas well-known to be related to schizophrenia.https://www.mdpi.com/2076-3417/12/5/2571Bayesian learningneuroimagingfeature selectionkernel formulationmental disordersschizophrenia |
spellingShingle | Albert Belenguer-Llorens Carlos Sevilla-Salcedo Manuel Desco Maria Luisa Soto-Montenegro Vanessa Gómez-Verdejo A Novel Bayesian Linear Regression Model for the Analysis of Neuroimaging Data Applied Sciences Bayesian learning neuroimaging feature selection kernel formulation mental disorders schizophrenia |
title | A Novel Bayesian Linear Regression Model for the Analysis of Neuroimaging Data |
title_full | A Novel Bayesian Linear Regression Model for the Analysis of Neuroimaging Data |
title_fullStr | A Novel Bayesian Linear Regression Model for the Analysis of Neuroimaging Data |
title_full_unstemmed | A Novel Bayesian Linear Regression Model for the Analysis of Neuroimaging Data |
title_short | A Novel Bayesian Linear Regression Model for the Analysis of Neuroimaging Data |
title_sort | novel bayesian linear regression model for the analysis of neuroimaging data |
topic | Bayesian learning neuroimaging feature selection kernel formulation mental disorders schizophrenia |
url | https://www.mdpi.com/2076-3417/12/5/2571 |
work_keys_str_mv | AT albertbelenguerllorens anovelbayesianlinearregressionmodelfortheanalysisofneuroimagingdata AT carlossevillasalcedo anovelbayesianlinearregressionmodelfortheanalysisofneuroimagingdata AT manueldesco anovelbayesianlinearregressionmodelfortheanalysisofneuroimagingdata AT marialuisasotomontenegro anovelbayesianlinearregressionmodelfortheanalysisofneuroimagingdata AT vanessagomezverdejo anovelbayesianlinearregressionmodelfortheanalysisofneuroimagingdata AT albertbelenguerllorens novelbayesianlinearregressionmodelfortheanalysisofneuroimagingdata AT carlossevillasalcedo novelbayesianlinearregressionmodelfortheanalysisofneuroimagingdata AT manueldesco novelbayesianlinearregressionmodelfortheanalysisofneuroimagingdata AT marialuisasotomontenegro novelbayesianlinearregressionmodelfortheanalysisofneuroimagingdata AT vanessagomezverdejo novelbayesianlinearregressionmodelfortheanalysisofneuroimagingdata |