TY - GEN
T1 - Patch-driven neonatal brain MRI segmentation with sparse representation and level sets
AU - Wang, Li
AU - Shi, Feng
AU - Li, Gang
AU - Lin, Weili
AU - Gilmore, John H.
AU - Shen, Dinggang
PY - 2013
Y1 - 2013
N2 - Neonatal brain MR image segmentation is challenging due to the poor image quality. In this paper, we propose a novel patch-driven level sets method for segmentation of neonatal brain 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 subject-specific atlas is further enforced by considering the similarities of a patch with its neighboring patches. Finally, this subject-specific atlas is integrated into a coupled level set framework for surface-based neonatal brain segmentation. The proposed method has been extensively evaluated on 20 training subjects using leave-one-out cross validation, and on 132 additional testing subjects. Both quantitative and qualitative evaluation results demonstrate the validity of the proposed method.
AB - Neonatal brain MR image segmentation is challenging due to the poor image quality. In this paper, we propose a novel patch-driven level sets method for segmentation of neonatal brain 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 subject-specific atlas is further enforced by considering the similarities of a patch with its neighboring patches. Finally, this subject-specific atlas is integrated into a coupled level set framework for surface-based neonatal brain segmentation. The proposed method has been extensively evaluated on 20 training subjects using leave-one-out cross validation, and on 132 additional testing subjects. Both quantitative and qualitative evaluation results demonstrate the validity of the proposed method.
KW - Neonatal brain MRI
KW - atlas based segmentation
KW - coupled level set (CLS)
KW - elastic net
KW - sparse representation
UR - http://www.scopus.com/inward/record.url?scp=84881639543&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84881639543&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2013.6556668
DO - 10.1109/ISBI.2013.6556668
M3 - Conference contribution
AN - SCOPUS:84881639543
SN - 9781467364546
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 1090
EP - 1093
BT - ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging
T2 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013
Y2 - 7 April 2013 through 11 April 2013
ER -