TY - JOUR
T1 - Segmentation of neonatal brain MR images using patch-driven level sets
AU - Wang, Li
AU - Shi, Feng
AU - Li, Gang
AU - Gao, Yaozong
AU - Lin, Weili
AU - Gilmore, John H.
AU - Shen, Dinggang
N1 - Funding Information:
The authors would like to thank the editor and anonymous reviewers for their constructive comments and suggestions. The authors also thank Dr. Shu Liao and Dr. Jian Cheng for their helpful suggestions and discussions, and thank Prof. Brent Munsell for proofreading of the manuscript. This work was supported in part by the National Institutes of Health grants MH100217 , AG042599 , MH070890 , EB006733 , EB008374 , EB009634 , NS055754 , MH064065 , and HD053000 .
PY - 2014/1/1
Y1 - 2014/1/1
N2 - The segmentation of neonatal brain MR image into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF), is challenging due to the low spatial resolution, severe partial volume effect, high image noise, and dynamic myelination and maturation processes. Atlas-based methods have been widely used for guiding neonatal brain segmentation. Existing brain atlases were generally constructed by equally averaging all the aligned template images from a population. However, such population-based atlases might not be representative of a testing subject in the regions with high inter-subject variability and thus often lead to a low capability in guiding segmentation in those regions. Recently, patch-based sparse representation techniques have been proposed to effectively select the most relevant elements from a large group of candidates, which can be used to generate a subject-specific representation with rich local anatomical details for guiding the segmentation. Accordingly, in this paper, we propose a novel patch-driven level set method for the segmentation of neonatal brain MR images by taking advantage of sparse representation techniques. Specifically, we first build a subject-specific atlas from a library of aligned, manually segmented images by using sparse representation in a patch-based fashion. Then, the spatial consistency in the probability maps from the subject-specific atlas is further enforced by considering the similarities of a patch with its neighboring patches. Finally, the probability maps are integrated into a coupled level set framework for more accurate segmentation. The proposed method has been extensively evaluated on 20 training subjects using leave-one-out cross validation, and also on 132 additional testing subjects. Our method achieved a high accuracy of 0.919. ±. 0.008 for white matter and 0.901. ±. 0.005 for gray matter, respectively, measured by Dice ratio for the overlap between the automated and manual segmentations in the cortical region.
AB - The segmentation of neonatal brain MR image into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF), is challenging due to the low spatial resolution, severe partial volume effect, high image noise, and dynamic myelination and maturation processes. Atlas-based methods have been widely used for guiding neonatal brain segmentation. Existing brain atlases were generally constructed by equally averaging all the aligned template images from a population. However, such population-based atlases might not be representative of a testing subject in the regions with high inter-subject variability and thus often lead to a low capability in guiding segmentation in those regions. Recently, patch-based sparse representation techniques have been proposed to effectively select the most relevant elements from a large group of candidates, which can be used to generate a subject-specific representation with rich local anatomical details for guiding the segmentation. Accordingly, in this paper, we propose a novel patch-driven level set method for the segmentation of neonatal brain MR images by taking advantage of sparse representation techniques. Specifically, we first build a subject-specific atlas from a library of aligned, manually segmented images by using sparse representation in a patch-based fashion. Then, the spatial consistency in the probability maps from the subject-specific atlas is further enforced by considering the similarities of a patch with its neighboring patches. Finally, the probability maps are integrated into a coupled level set framework for more accurate segmentation. The proposed method has been extensively evaluated on 20 training subjects using leave-one-out cross validation, and also on 132 additional testing subjects. Our method achieved a high accuracy of 0.919. ±. 0.008 for white matter and 0.901. ±. 0.005 for gray matter, respectively, measured by Dice ratio for the overlap between the automated and manual segmentations in the cortical region.
KW - Atlas based segmentation
KW - Coupled level set (CLS)
KW - Elastic-net
KW - Neonatal brain MRI
KW - Sparse representation
UR - http://www.scopus.com/inward/record.url?scp=84883658529&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2013.08.008
DO - 10.1016/j.neuroimage.2013.08.008
M3 - Article
C2 - 23968736
AN - SCOPUS:84883658529
SN - 1053-8119
VL - 84
SP - 141
EP - 158
JO - NeuroImage
JF - NeuroImage
ER -