Multiparametric Microstructural MRI and Machine Learning Classification Yields High Diagnostic Accuracy in Amyotrophic Lateral Sclerosis: Proof of Concept

The potential of multiparametric quantitative neuroimaging has been extensively discussed as a diagnostic tool in amyotrophic lateral sclerosis (ALS). In the past, the integration of multimodal, quantitative data into a useful diagnostic classifier was a major challenge. With recent advances in the...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Thomas D. Kocar, Anna Behler, Albert C. Ludolph, Hans-Peter Müller, Jan Kassubek
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	diffusion tensor imaging (DTI) machine learning support vector machine (SVM) neural network amyotrophic lateral sclerosis motor neuron disease Neurology. Diseases of the nervous system RC346-429
Acceso en línea:	https://doaj.org/article/713002b89eb44a98a3eb1916bbc26b81
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:713002b89eb44a98a3eb1916bbc26b81
record_format	dspace
spelling	oai:doaj.org-article:713002b89eb44a98a3eb1916bbc26b812021-11-17T04:30:00ZMultiparametric Microstructural MRI and Machine Learning Classification Yields High Diagnostic Accuracy in Amyotrophic Lateral Sclerosis: Proof of Concept1664-229510.3389/fneur.2021.745475https://doaj.org/article/713002b89eb44a98a3eb1916bbc26b812021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fneur.2021.745475/fullhttps://doaj.org/toc/1664-2295The potential of multiparametric quantitative neuroimaging has been extensively discussed as a diagnostic tool in amyotrophic lateral sclerosis (ALS). In the past, the integration of multimodal, quantitative data into a useful diagnostic classifier was a major challenge. With recent advances in the field, machine learning in a data driven approach is a potential solution: neuroimaging biomarkers in ALS are mainly observed in the cerebral microstructure, with diffusion tensor imaging (DTI) and texture analysis as promising approaches. We set out to combine these neuroimaging markers as age-corrected features in a machine learning model with a cohort of 502 subjects, divided into 404 patients with ALS and 98 healthy controls. We calculated a linear support vector classifier (SVC) which is a very robust model and then verified the results with a multilayer perceptron (MLP)/neural network. Both classifiers were able to separate ALS patients from controls with receiver operating characteristic (ROC) curves showing an area under the curve (AUC) of 0.87–0.88 (“good”) for the SVC and 0.88–0.91 (“good” to “excellent”) for the MLP. Among the coefficients of the SVC, texture data contributed the most to a correct classification. We consider these results as a proof of concept that demonstrated the power of machine learning in the application of multiparametric quantitative neuroimaging data to ALS.Thomas D. KocarAnna BehlerAlbert C. LudolphAlbert C. LudolphHans-Peter MüllerJan KassubekJan KassubekFrontiers Media S.A.articlediffusion tensor imaging (DTI)machine learningsupport vector machine (SVM)neural networkamyotrophic lateral sclerosismotor neuron diseaseNeurology. Diseases of the nervous systemRC346-429ENFrontiers in Neurology, Vol 12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	diffusion tensor imaging (DTI) machine learning support vector machine (SVM) neural network amyotrophic lateral sclerosis motor neuron disease Neurology. Diseases of the nervous system RC346-429
spellingShingle	diffusion tensor imaging (DTI) machine learning support vector machine (SVM) neural network amyotrophic lateral sclerosis motor neuron disease Neurology. Diseases of the nervous system RC346-429 Thomas D. Kocar Anna Behler Albert C. Ludolph Albert C. Ludolph Hans-Peter Müller Jan Kassubek Jan Kassubek Multiparametric Microstructural MRI and Machine Learning Classification Yields High Diagnostic Accuracy in Amyotrophic Lateral Sclerosis: Proof of Concept
description	The potential of multiparametric quantitative neuroimaging has been extensively discussed as a diagnostic tool in amyotrophic lateral sclerosis (ALS). In the past, the integration of multimodal, quantitative data into a useful diagnostic classifier was a major challenge. With recent advances in the field, machine learning in a data driven approach is a potential solution: neuroimaging biomarkers in ALS are mainly observed in the cerebral microstructure, with diffusion tensor imaging (DTI) and texture analysis as promising approaches. We set out to combine these neuroimaging markers as age-corrected features in a machine learning model with a cohort of 502 subjects, divided into 404 patients with ALS and 98 healthy controls. We calculated a linear support vector classifier (SVC) which is a very robust model and then verified the results with a multilayer perceptron (MLP)/neural network. Both classifiers were able to separate ALS patients from controls with receiver operating characteristic (ROC) curves showing an area under the curve (AUC) of 0.87–0.88 (“good”) for the SVC and 0.88–0.91 (“good” to “excellent”) for the MLP. Among the coefficients of the SVC, texture data contributed the most to a correct classification. We consider these results as a proof of concept that demonstrated the power of machine learning in the application of multiparametric quantitative neuroimaging data to ALS.
format	article
author	Thomas D. Kocar Anna Behler Albert C. Ludolph Albert C. Ludolph Hans-Peter Müller Jan Kassubek Jan Kassubek
author_facet	Thomas D. Kocar Anna Behler Albert C. Ludolph Albert C. Ludolph Hans-Peter Müller Jan Kassubek Jan Kassubek
author_sort	Thomas D. Kocar
title	Multiparametric Microstructural MRI and Machine Learning Classification Yields High Diagnostic Accuracy in Amyotrophic Lateral Sclerosis: Proof of Concept
title_short	Multiparametric Microstructural MRI and Machine Learning Classification Yields High Diagnostic Accuracy in Amyotrophic Lateral Sclerosis: Proof of Concept
title_full	Multiparametric Microstructural MRI and Machine Learning Classification Yields High Diagnostic Accuracy in Amyotrophic Lateral Sclerosis: Proof of Concept
title_fullStr	Multiparametric Microstructural MRI and Machine Learning Classification Yields High Diagnostic Accuracy in Amyotrophic Lateral Sclerosis: Proof of Concept
title_full_unstemmed	Multiparametric Microstructural MRI and Machine Learning Classification Yields High Diagnostic Accuracy in Amyotrophic Lateral Sclerosis: Proof of Concept
title_sort	multiparametric microstructural mri and machine learning classification yields high diagnostic accuracy in amyotrophic lateral sclerosis: proof of concept
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/713002b89eb44a98a3eb1916bbc26b81
work_keys_str_mv	AT thomasdkocar multiparametricmicrostructuralmriandmachinelearningclassificationyieldshighdiagnosticaccuracyinamyotrophiclateralsclerosisproofofconcept AT annabehler multiparametricmicrostructuralmriandmachinelearningclassificationyieldshighdiagnosticaccuracyinamyotrophiclateralsclerosisproofofconcept AT albertcludolph multiparametricmicrostructuralmriandmachinelearningclassificationyieldshighdiagnosticaccuracyinamyotrophiclateralsclerosisproofofconcept AT albertcludolph multiparametricmicrostructuralmriandmachinelearningclassificationyieldshighdiagnosticaccuracyinamyotrophiclateralsclerosisproofofconcept AT hanspetermuller multiparametricmicrostructuralmriandmachinelearningclassificationyieldshighdiagnosticaccuracyinamyotrophiclateralsclerosisproofofconcept AT jankassubek multiparametricmicrostructuralmriandmachinelearningclassificationyieldshighdiagnosticaccuracyinamyotrophiclateralsclerosisproofofconcept AT jankassubek multiparametricmicrostructuralmriandmachinelearningclassificationyieldshighdiagnosticaccuracyinamyotrophiclateralsclerosisproofofconcept
_version_	1718425993317711872

Multiparametric Microstructural MRI and Machine Learning Classification Yields High Diagnostic Accuracy in Amyotrophic Lateral Sclerosis: Proof of Concept

Ejemplares similares