Cargando…

Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in Combination with Various Pre-Processing Techniques

Schizophrenia is a severe neuropsychiatric disease whose diagnosis, unfortunately, lacks an objective diagnostic tool supporting a thorough psychiatric examination of the patient. We took advantage of today’s computational abilities, structural magnetic resonance imaging, and modern machine learning...

Descripción completa

Detalles Bibliográficos
Autores principales: Vyškovský, Roman, Schwarz, Daniel, Churová, Vendula, Kašpárek, Tomáš
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9139344/
https://www.ncbi.nlm.nih.gov/pubmed/35625002
http://dx.doi.org/10.3390/brainsci12050615
_version_ 1784714837626978304
author Vyškovský, Roman
Schwarz, Daniel
Churová, Vendula
Kašpárek, Tomáš
author_facet Vyškovský, Roman
Schwarz, Daniel
Churová, Vendula
Kašpárek, Tomáš
author_sort Vyškovský, Roman
collection PubMed
description Schizophrenia is a severe neuropsychiatric disease whose diagnosis, unfortunately, lacks an objective diagnostic tool supporting a thorough psychiatric examination of the patient. We took advantage of today’s computational abilities, structural magnetic resonance imaging, and modern machine learning methods, such as stacked autoencoders (SAE) and 3D convolutional neural networks (3D CNN), to teach them to classify 52 patients with schizophrenia and 52 healthy controls. The main aim of this study was to explore whether complex feature extraction methods can help improve the accuracy of deep learning-based classifiers compared to minimally preprocessed data. Our experiments employed three commonly used preprocessing steps to extract three different feature types. They included voxel-based morphometry, deformation-based morphometry, and simple spatial normalization of brain tissue. In addition to classifier models, features and their combination, other model parameters such as network depth, number of neurons, number of convolutional filters, and input data size were also investigated. Autoencoders were trained on feature pools of 1000 and 5000 voxels selected by Mann-Whitney tests, and 3D CNNs were trained on whole images. The most successful model architecture (autoencoders) achieved the highest average accuracy of 69.62% (sensitivity 68.85%, specificity 70.38%). The results of all experiments were statistically compared (the Mann-Whitney test). In conclusion, SAE outperformed 3D CNN, while preprocessing using VBM helped SAE improve the results.
format Online
Article
Text
id pubmed-9139344
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91393442022-05-28 Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in Combination with Various Pre-Processing Techniques Vyškovský, Roman Schwarz, Daniel Churová, Vendula Kašpárek, Tomáš Brain Sci Article Schizophrenia is a severe neuropsychiatric disease whose diagnosis, unfortunately, lacks an objective diagnostic tool supporting a thorough psychiatric examination of the patient. We took advantage of today’s computational abilities, structural magnetic resonance imaging, and modern machine learning methods, such as stacked autoencoders (SAE) and 3D convolutional neural networks (3D CNN), to teach them to classify 52 patients with schizophrenia and 52 healthy controls. The main aim of this study was to explore whether complex feature extraction methods can help improve the accuracy of deep learning-based classifiers compared to minimally preprocessed data. Our experiments employed three commonly used preprocessing steps to extract three different feature types. They included voxel-based morphometry, deformation-based morphometry, and simple spatial normalization of brain tissue. In addition to classifier models, features and their combination, other model parameters such as network depth, number of neurons, number of convolutional filters, and input data size were also investigated. Autoencoders were trained on feature pools of 1000 and 5000 voxels selected by Mann-Whitney tests, and 3D CNNs were trained on whole images. The most successful model architecture (autoencoders) achieved the highest average accuracy of 69.62% (sensitivity 68.85%, specificity 70.38%). The results of all experiments were statistically compared (the Mann-Whitney test). In conclusion, SAE outperformed 3D CNN, while preprocessing using VBM helped SAE improve the results. MDPI 2022-05-09 /pmc/articles/PMC9139344/ /pubmed/35625002 http://dx.doi.org/10.3390/brainsci12050615 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Vyškovský, Roman
Schwarz, Daniel
Churová, Vendula
Kašpárek, Tomáš
Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in Combination with Various Pre-Processing Techniques
title Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in Combination with Various Pre-Processing Techniques
title_full Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in Combination with Various Pre-Processing Techniques
title_fullStr Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in Combination with Various Pre-Processing Techniques
title_full_unstemmed Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in Combination with Various Pre-Processing Techniques
title_short Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in Combination with Various Pre-Processing Techniques
title_sort structural mri-based schizophrenia classification using autoencoders and 3d convolutional neural networks in combination with various pre-processing techniques
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9139344/
https://www.ncbi.nlm.nih.gov/pubmed/35625002
http://dx.doi.org/10.3390/brainsci12050615
work_keys_str_mv AT vyskovskyroman structuralmribasedschizophreniaclassificationusingautoencodersand3dconvolutionalneuralnetworksincombinationwithvariouspreprocessingtechniques
AT schwarzdaniel structuralmribasedschizophreniaclassificationusingautoencodersand3dconvolutionalneuralnetworksincombinationwithvariouspreprocessingtechniques
AT churovavendula structuralmribasedschizophreniaclassificationusingautoencodersand3dconvolutionalneuralnetworksincombinationwithvariouspreprocessingtechniques
AT kasparektomas structuralmribasedschizophreniaclassificationusingautoencodersand3dconvolutionalneuralnetworksincombinationwithvariouspreprocessingtechniques