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

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F65269705%3A_____%2F22%3A00076082" target="_blank" >RIV/65269705:_____/22:00076082 - isvavai.cz</a>

Alternative codes found

RIV/00216224:14110/22:00129674

Result on the web

<a href="https://www.mdpi.com/2076-3425/12/5/615" target="_blank" >https://www.mdpi.com/2076-3425/12/5/615</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/brainsci12050615" target="_blank" >10.3390/brainsci12050615</a>

Result language

angličtina

Original language name

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

Original language 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&apos;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.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

30103 - Neurosciences (including psychophysiology)

Project

<a href="/en/project/NV17-33136A" target="_blank" >NV17-33136A: Neurominer: unveiling hidden patterns in neuroimaging data</a><br>

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2022

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Brain Sciences

ISSN

2076-3425

e-ISSN

2076-3425

Volume of the periodical

12

Issue of the periodical within the volume

5

Country of publishing house

CH - SWITZERLAND

Number of pages

16

Pages from-to

615

UT code for WoS article

000803514900001

EID of the result in the Scopus database

2-s2.0-85130265825