TY - GEN
T1 - Diffusion specific segmentation
T2 - MICCAI Workshop on Computational Diffusion MRI, CDMRI 2017
AU - The Alzheimer’s Disease Neuroimaging Initiative
AU - Reid, Robert I.
AU - Nedelska, Zuzana
AU - Schwarz, Christopher G.
AU - Ward, Chadwick
AU - Jack, Clifford R.
N1 - Funding Information:
The authors thank K. Kantarci, M. Senjem, and J. Gunter for helpful conversations and suggestions while preparing this paper. This article used images from the Longitudinal Evaluation of Familial Frontotemporal Dementia Subjects study, U01 AG045390, Advancing Research and Treatment for Frontotemporal Lobar Degeneration, AB-BFP-2015/AB-BFP-2016, the ARIC-PET Amyloid Study, R01 AG040282, the role of intracranial atherosclerosis in the development of Alzheimer’s Disease study, R01 AG054491, the ARIC study of midlife sleep and late-life brain amyloid, RF1 AG050745, Stroke and Cognitive Impairment in Aging CKD Patients, R01 AG0375, the Alzheimer’s Disease Neuroimaging Initiative (ADNI), U01 AG024904 and U01 AG024904, and the Mayo Clinic Study of Aging, U01 AG006786. Investigators within the ADNI consortium contributed to the design and implementation of ADNI and/or provided data but not all participated in the analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf.
Publisher Copyright:
© Springer International Publishing AG, part of Springer Nature 2018.
PY - 2018
Y1 - 2018
N2 - Most processing pipelines for diffusion MRI (dMRI) require an intracranial mask image to exclude voxels outside the skull, and some dMRI analyses also need a segmentation between the voxels that are primarily tissue or cerebrospinal fluid (CSF). dMRI is challenging for most segmentation methods because it usually has relatively severe image artifacts and coarse resolution. However, it does provide information about the physical properties of the material(s) in each voxel, which can be directly applied to segmentation. We describe the training of a random forest classifier to segment dMRI into intracranial, brain, and CSF masks, and compare its results to three other segmentation methods commonly used in dMRI processing. The effect of correcting smooth spatial intensity variations on dMRI segmentation is also tested.
AB - Most processing pipelines for diffusion MRI (dMRI) require an intracranial mask image to exclude voxels outside the skull, and some dMRI analyses also need a segmentation between the voxels that are primarily tissue or cerebrospinal fluid (CSF). dMRI is challenging for most segmentation methods because it usually has relatively severe image artifacts and coarse resolution. However, it does provide information about the physical properties of the material(s) in each voxel, which can be directly applied to segmentation. We describe the training of a random forest classifier to segment dMRI into intracranial, brain, and CSF masks, and compare its results to three other segmentation methods commonly used in dMRI processing. The effect of correcting smooth spatial intensity variations on dMRI segmentation is also tested.
UR - http://www.scopus.com/inward/record.url?scp=85064507957&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85064507957&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-73839-0_5
DO - 10.1007/978-3-319-73839-0_5
M3 - Conference contribution
AN - SCOPUS:85064507957
SN - 9783319738383
T3 - Mathematics and Visualization
SP - 67
EP - 80
BT - Computational Diffusion MRI - MICCAI Workshop, 2017
A2 - Kaden, Enrico
A2 - Grussu, Francesco
A2 - Ning, Lipeng
A2 - Tax, Chantal M.W.
A2 - Veraart, Jelle
PB - Springer
Y2 - 10 September 2017 through 10 September 2017
ER -