VYŠKOVSKÝ, Roman, Daniel SCHWARZ, Vendula CHUROVÁ and Tomáš KAŠPÁREK. Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in Combination with Various Pre-Processing Techniques. Brain Sciences. Basel: MDPI, 2022, vol. 12, No 5, p. 1-16. ISSN 2076-3425. Available from: https://dx.doi.org/10.3390/brainsci12050615.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in Combination with Various Pre-Processing Techniques
Authors VYŠKOVSKÝ, Roman (203 Czech Republic, guarantor, belonging to the institution), Daniel SCHWARZ (203 Czech Republic, belonging to the institution), Vendula CHUROVÁ (203 Czech Republic, belonging to the institution) and Tomáš KAŠPÁREK (203 Czech Republic, belonging to the institution).
Edition Brain Sciences, Basel, MDPI, 2022, 2076-3425.
Other information
Original language English
Type of outcome Article in a journal
Field of Study 30103 Neurosciences
Country of publisher Switzerland
Confidentiality degree is not subject to a state or trade secret
WWW URL
Impact factor Impact factor: 3.300
RIV identification code RIV/00216224:14110/22:00129674
Organization unit Faculty of Medicine
Doi http://dx.doi.org/10.3390/brainsci12050615
UT WoS 000803514900001
Keywords in English schizophrenia; classification; 3D CNN; autoencoders; voxel-based morphometry; deformation-based morphometry; deep learning
Tags 14110222, 14119612, rivok
Tags International impact, Reviewed
Changed by Changed by: Mgr. Tereza Miškechová, učo 341652. Changed: 2/8/2022 07:56.
Abstract
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.
Links
NV17-33136A, research and development projectName: Neurominer: odhalování skrytých vzorů v datech ze zobrazování mozku
PrintDisplayed: 24/7/2024 18:24