View in EDS

Voxel-based morphometry in single subjects without a scanner-specific normal database using a convolutional neural network

Saved in:
Bibliographic Details
Title: Voxel-based morphometry in single subjects without a scanner-specific normal database using a convolutional neural network
Authors: Julia Krüger, Roland Opfer, Lothar Spies, Dennis Hedderich, Ralph Buchert
Source: Eur Radiol
Publisher Information: Springer Science and Business Media LLC, 2023.
Publication Year: 2023
Subject Terms: Male, Databases, Factual, Imaging Informatics and Artificial Intelligence, Magnetic resonance imaging, Brain mapping, Alzheimer disease, Deep learning, Neural networks (computer), Medical and Health Sciences, Information and Computing Sciences, Brain, Middle Aged, Magnetic Resonance Imaging, 3. Good health, ddc, Alzheimer Disease, Female [MeSH], Brain/pathology [MeSH], Atrophy [MeSH], Brain/diagnostic imaging [MeSH], Aged [MeSH], Frontotemporal Lobar Degeneration/diagnostic imaging [MeSH], Humans [MeSH], Alzheimer Disease/diagnostic imaging [MeSH], Retrospective Studies [MeSH], Middle Aged [MeSH], Neural Networks, Computer [MeSH], Databases, Factual [MeSH], Male [MeSH], Magnetic Resonance Imaging/methods [MeSH], Humans, Female, Neural Networks, Computer, Frontotemporal Lobar Degeneration, Atrophy, Aged, Retrospective Studies
Description: Objectives Reliable detection of disease-specific atrophy in individual T1w-MRI by voxel-based morphometry (VBM) requires scanner-specific normal databases (NDB), which often are not available. The aim of this retrospective study was to design, train, and test a deep convolutional neural network (CNN) for single-subject VBM without the need for a NDB (CNN-VBM). Materials and methods The training dataset comprised 8945 T1w scans from 65 different scanners. The gold standard VBM maps were obtained by conventional VBM with a scanner-specific NDB for each of the 65 scanners. CNN-VBM was tested in an independent dataset comprising healthy controls (n = 37) and subjects with Alzheimer’s disease (AD, n = 51) or frontotemporal lobar degeneration (FTLD, n = 30). A scanner-specific NDB for the generation of the gold standard VBM maps was available also for the test set. The technical performance of CNN-VBM was characterized by the Dice coefficient of CNN-VBM maps relative to VBM maps from scanner-specific VBM. For clinical testing, VBM maps were categorized visually according to the clinical diagnoses in the test set by two independent readers, separately for both VBM methods. Results The VBM maps from CNN-VBM were similar to the scanner-specific VBM maps (median Dice coefficient 0.85, interquartile range [0.81, 0.90]). Overall accuracy of the visual categorization of the VBM maps for the detection of AD or FTLD was 89.8% for CNN-VBM and 89.0% for scanner-specific VBM. Conclusion CNN-VBM without NDB provides a similar performance in the detection of AD- and FTLD-specific atrophy as conventional VBM. Clinical relevance statement A deep convolutional neural network for voxel-based morphometry eliminates the need of scanner-specific normal databases without relevant performance loss and, therefore, could pave the way for the widespread clinical use of voxel-based morphometry to support the diagnosis of neurodegenerative diseases. Key Points • The need of normal databases is a barrier for widespread use of voxel-based brain morphometry. • A convolutional neural network achieved a similar performance for detection of atrophy than conventional voxel-based morphometry. • Convolutional neural networks can pave the way for widespread clinical use of voxel-based morphometry. Graphical abstract
Document Type: Article
Other literature type
File Description: application/pdf
Language: English
ISSN: 1432-1084
DOI: 10.1007/s00330-023-10356-1
Access URL: https://pubmed.ncbi.nlm.nih.gov/37943313
https://repository.publisso.de/resource/frl:6503487
https://mediatum.ub.tum.de/doc/1761203/document.pdf
Rights: CC BY
Accession Number: edsair.doi.dedup.....4123b076f9d2bd4d89cc5a8fe70c17af
Database: OpenAIRE
Description
Abstract:Objectives Reliable detection of disease-specific atrophy in individual T1w-MRI by voxel-based morphometry (VBM) requires scanner-specific normal databases (NDB), which often are not available. The aim of this retrospective study was to design, train, and test a deep convolutional neural network (CNN) for single-subject VBM without the need for a NDB (CNN-VBM). Materials and methods The training dataset comprised 8945 T1w scans from 65 different scanners. The gold standard VBM maps were obtained by conventional VBM with a scanner-specific NDB for each of the 65 scanners. CNN-VBM was tested in an independent dataset comprising healthy controls (n = 37) and subjects with Alzheimer’s disease (AD, n = 51) or frontotemporal lobar degeneration (FTLD, n = 30). A scanner-specific NDB for the generation of the gold standard VBM maps was available also for the test set. The technical performance of CNN-VBM was characterized by the Dice coefficient of CNN-VBM maps relative to VBM maps from scanner-specific VBM. For clinical testing, VBM maps were categorized visually according to the clinical diagnoses in the test set by two independent readers, separately for both VBM methods. Results The VBM maps from CNN-VBM were similar to the scanner-specific VBM maps (median Dice coefficient 0.85, interquartile range [0.81, 0.90]). Overall accuracy of the visual categorization of the VBM maps for the detection of AD or FTLD was 89.8% for CNN-VBM and 89.0% for scanner-specific VBM. Conclusion CNN-VBM without NDB provides a similar performance in the detection of AD- and FTLD-specific atrophy as conventional VBM. Clinical relevance statement A deep convolutional neural network for voxel-based morphometry eliminates the need of scanner-specific normal databases without relevant performance loss and, therefore, could pave the way for the widespread clinical use of voxel-based morphometry to support the diagnosis of neurodegenerative diseases. Key Points • The need of normal databases is a barrier for widespread use of voxel-based brain morphometry. • A convolutional neural network achieved a similar performance for detection of atrophy than conventional voxel-based morphometry. • Convolutional neural networks can pave the way for widespread clinical use of voxel-based morphometry. Graphical abstract
ISSN:14321084
DOI:10.1007/s00330-023-10356-1