A contrast-adaptive method for simultaneous whole-brain and lesion segmentation in multiple sclerosis
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
A contrast-adaptive method for simultaneous whole-brain and lesion segmentation in multiple sclerosis. / Cerri, Stefano; Puonti, Oula; Meier, Dominik S.; Wuerfel, Jens; Mühlau, Mark; Siebner, Hartwig R.; Van Leemput, Koen.
In: NeuroImage, Vol. 225, 117471, 2021.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - A contrast-adaptive method for simultaneous whole-brain and lesion segmentation in multiple sclerosis
AU - Cerri, Stefano
AU - Puonti, Oula
AU - Meier, Dominik S.
AU - Wuerfel, Jens
AU - Mühlau, Mark
AU - Siebner, Hartwig R.
AU - Van Leemput, Koen
PY - 2021
Y1 - 2021
N2 - Here we present a method for the simultaneous segmentation of white matter lesions and normal-appearing neuroanatomical structures from multi-contrast brain MRI scans of multiple sclerosis patients. The method integrates a novel model for white matter lesions into a previously validated generative model for whole-brain segmentation. By using separate models for the shape of anatomical structures and their appearance in MRI, the algorithm can adapt to data acquired with different scanners and imaging protocols without retraining. We validate the method using four disparate datasets, showing robust performance in white matter lesion segmentation while simultaneously segmenting dozens of other brain structures. We further demonstrate that the contrast-adaptive method can also be safely applied to MRI scans of healthy controls, and replicate previously documented atrophy patterns in deep gray matter structures in MS. The algorithm is publicly available as part of the open-source neuroimaging package FreeSurfer.
AB - Here we present a method for the simultaneous segmentation of white matter lesions and normal-appearing neuroanatomical structures from multi-contrast brain MRI scans of multiple sclerosis patients. The method integrates a novel model for white matter lesions into a previously validated generative model for whole-brain segmentation. By using separate models for the shape of anatomical structures and their appearance in MRI, the algorithm can adapt to data acquired with different scanners and imaging protocols without retraining. We validate the method using four disparate datasets, showing robust performance in white matter lesion segmentation while simultaneously segmenting dozens of other brain structures. We further demonstrate that the contrast-adaptive method can also be safely applied to MRI scans of healthy controls, and replicate previously documented atrophy patterns in deep gray matter structures in MS. The algorithm is publicly available as part of the open-source neuroimaging package FreeSurfer.
KW - Generative model
KW - Lesion segmentation
KW - Multiple sclerosis
KW - Whole-brain segmentation
U2 - 10.1016/j.neuroimage.2020.117471
DO - 10.1016/j.neuroimage.2020.117471
M3 - Journal article
C2 - 33099007
AN - SCOPUS:85096184246
VL - 225
JO - NeuroImage
JF - NeuroImage
SN - 1053-8119
M1 - 117471
ER -
ID: 254779071