TY - JOUR
T1 - Groupwise multi-atlas segmentation of the spinal cord's internal structure
AU - Asman, Andrew J.
AU - Bryan, Frederick W.
AU - Smith, Seth A.
AU - Reich, Daniel S.
AU - Landman, Bennett A.
N1 - Funding Information:
This research was supported by in part by NIH 1R21NS064534 , NIH 1R03EB012461 , NIH 2R01EB006136 , NIH R01EB006193 , NIH 1T32EB014841 , the NIH/NINDS Intramural Research Program , and the National Multiple Sclerosis Society (Peter Calabresi) . The authors are grateful to Zhoubing Xu for the provided manual labels.
PY - 2014/4
Y1 - 2014/4
N2 - The spinal cord is an essential and vulnerable component of the central nervous system. Differentiating and localizing the spinal cord internal structure (i.e., gray matter vs. white matter) is critical for assessment of therapeutic impacts and determining prognosis of relevant conditions. Fortunately, new magnetic resonance imaging (MRI) sequences enable clinical study of the in vivo spinal cord's internal structure. Yet, low contrast-to-noise ratio, artifacts, and imaging distortions have limited the applicability of tissue segmentation techniques pioneered elsewhere in the central nervous system. Additionally, due to the inter-subject variability exhibited on cervical MRI, typical deformable volumetric registrations perform poorly, limiting the applicability of a typical multi-atlas segmentation framework. Thus, to date, no automated algorithms have been presented for the spinal cord's internal structure. Herein, we present a novel slice-based groupwise registration framework for robustly segmenting cervical spinal cord MRI. Specifically, we provide a method for (1) pre-aligning the slice-based atlases into a groupwise-consistent space, (2) constructing a model of spinal cord variability, (3) projecting the target slice into the low-dimensional space using a model-specific registration cost function, and (4) estimating robust segmentation susing geodesically appropriate atlas information. Moreover, the proposed framework provides a natural mechanism for performing atlas selection and initializing the free model parameters in an informed manner. In a cross-validation experiment using 67 MR volumes of the cervical spinal cord, we demonstrate sub-millimetric accuracy, significant quantitative and qualitative improvement over comparable multi-atlas frameworks, and provide insight into the sensitivity of the associated model parameters.
AB - The spinal cord is an essential and vulnerable component of the central nervous system. Differentiating and localizing the spinal cord internal structure (i.e., gray matter vs. white matter) is critical for assessment of therapeutic impacts and determining prognosis of relevant conditions. Fortunately, new magnetic resonance imaging (MRI) sequences enable clinical study of the in vivo spinal cord's internal structure. Yet, low contrast-to-noise ratio, artifacts, and imaging distortions have limited the applicability of tissue segmentation techniques pioneered elsewhere in the central nervous system. Additionally, due to the inter-subject variability exhibited on cervical MRI, typical deformable volumetric registrations perform poorly, limiting the applicability of a typical multi-atlas segmentation framework. Thus, to date, no automated algorithms have been presented for the spinal cord's internal structure. Herein, we present a novel slice-based groupwise registration framework for robustly segmenting cervical spinal cord MRI. Specifically, we provide a method for (1) pre-aligning the slice-based atlases into a groupwise-consistent space, (2) constructing a model of spinal cord variability, (3) projecting the target slice into the low-dimensional space using a model-specific registration cost function, and (4) estimating robust segmentation susing geodesically appropriate atlas information. Moreover, the proposed framework provides a natural mechanism for performing atlas selection and initializing the free model parameters in an informed manner. In a cross-validation experiment using 67 MR volumes of the cervical spinal cord, we demonstrate sub-millimetric accuracy, significant quantitative and qualitative improvement over comparable multi-atlas frameworks, and provide insight into the sensitivity of the associated model parameters.
KW - Cervical spinal cord segmentation
KW - Groupwise registration
KW - Multi-atlas segmentation
KW - Spinal cord internal structure
UR - http://www.scopus.com/inward/record.url?scp=84894115721&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84894115721&partnerID=8YFLogxK
U2 - 10.1016/j.media.2014.01.003
DO - 10.1016/j.media.2014.01.003
M3 - Article
C2 - 24556080
AN - SCOPUS:84894115721
SN - 1361-8415
VL - 18
SP - 460
EP - 471
JO - Medical image analysis
JF - Medical image analysis
IS - 3
ER -