Brain tissues have single-voxel signatures in multi-spectral MRI
(2021) In NeuroImage 234.- Abstract
Since the seminal works by Brodmann and contemporaries, it is well-known that different brain regions exhibit unique cytoarchitectonic and myeloarchitectonic features. Transferring the approach of classifying brain tissues – and other tissues – based on their intrinsic features to the realm of magnetic resonance (MR) is a longstanding endeavor. In the 1990s, atlas-based segmentation replaced earlier multi-spectral classification approaches because of the large overlap between the class distributions. Here, we explored the feasibility of performing global brain classification based on intrinsic MR features, and used several technological advances: ultra-high field MRI, q-space trajectory diffusion imaging revealing voxel-intrinsic... (More)
Since the seminal works by Brodmann and contemporaries, it is well-known that different brain regions exhibit unique cytoarchitectonic and myeloarchitectonic features. Transferring the approach of classifying brain tissues – and other tissues – based on their intrinsic features to the realm of magnetic resonance (MR) is a longstanding endeavor. In the 1990s, atlas-based segmentation replaced earlier multi-spectral classification approaches because of the large overlap between the class distributions. Here, we explored the feasibility of performing global brain classification based on intrinsic MR features, and used several technological advances: ultra-high field MRI, q-space trajectory diffusion imaging revealing voxel-intrinsic diffusion properties, chemical exchange saturation transfer and semi-solid magnetization transfer imaging as a marker of myelination and neurochemistry, and current neural network architectures to analyze the data. In particular, we used the raw image data as well to increase the number of input features. We found that a global brain classification of roughly 97 brain regions was feasible with gross classification accuracy of 60%; and that mapping from voxel-intrinsic MR data to the brain region to which the data belongs is possible. This indicates the presence of unique MR signals of different brain regions, similar to their cytoarchitectonic and myeloarchitectonic fingerprints.
(Less)
- author
- organization
- publishing date
- 2021-07
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Brain, Data Analysis, High-Field Imaging, Machine Learning, MRI, Segmentation
- in
- NeuroImage
- volume
- 234
- article number
- 117986
- publisher
- Elsevier
- external identifiers
-
- pmid:33757906
- scopus:85103695851
- ISSN
- 1053-8119
- DOI
- 10.1016/j.neuroimage.2021.117986
- language
- English
- LU publication?
- yes
- id
- dcc1392a-c792-4dcc-9e35-e9aaf2b31363
- date added to LUP
- 2021-12-22 14:57:18
- date last changed
- 2024-03-23 16:16:41
@article{dcc1392a-c792-4dcc-9e35-e9aaf2b31363, abstract = {{<p>Since the seminal works by Brodmann and contemporaries, it is well-known that different brain regions exhibit unique cytoarchitectonic and myeloarchitectonic features. Transferring the approach of classifying brain tissues – and other tissues – based on their intrinsic features to the realm of magnetic resonance (MR) is a longstanding endeavor. In the 1990s, atlas-based segmentation replaced earlier multi-spectral classification approaches because of the large overlap between the class distributions. Here, we explored the feasibility of performing global brain classification based on intrinsic MR features, and used several technological advances: ultra-high field MRI, q-space trajectory diffusion imaging revealing voxel-intrinsic diffusion properties, chemical exchange saturation transfer and semi-solid magnetization transfer imaging as a marker of myelination and neurochemistry, and current neural network architectures to analyze the data. In particular, we used the raw image data as well to increase the number of input features. We found that a global brain classification of roughly 97 brain regions was feasible with gross classification accuracy of 60%; and that mapping from voxel-intrinsic MR data to the brain region to which the data belongs is possible. This indicates the presence of unique MR signals of different brain regions, similar to their cytoarchitectonic and myeloarchitectonic fingerprints.</p>}}, author = {{German, Alexander and Mennecke, Angelika and Martin, Jan and Hanspach, Jannis and Liebert, Andrzej and Herrler, Jürgen and Kuder, Tristan Anselm and Schmidt, Manuel and Nagel, Armin and Uder, Michael and Doerfler, Arnd and Winkler, Jürgen and Zaiss, Moritz and Laun, Frederik Bernd}}, issn = {{1053-8119}}, keywords = {{Brain; Data Analysis; High-Field Imaging; Machine Learning; MRI; Segmentation}}, language = {{eng}}, publisher = {{Elsevier}}, series = {{NeuroImage}}, title = {{Brain tissues have single-voxel signatures in multi-spectral MRI}}, url = {{http://dx.doi.org/10.1016/j.neuroimage.2021.117986}}, doi = {{10.1016/j.neuroimage.2021.117986}}, volume = {{234}}, year = {{2021}}, }