Automatic extraction of the curved midsagittal brain surface on MR images

Authors:
Hugo J. Kuijf;Max A. Viergever;Koen L. Vincken
Affiliations:
Image Sciences Institute, University Medical Center Utrecht, The Netherlands;Image Sciences Institute, University Medical Center Utrecht, The Netherlands;Image Sciences Institute, University Medical Center Utrecht, The Netherlands
Venue:
MCV'12 Proceedings of the Second international conference on Medical Computer Vision: recognition techniques and applications in medical imaging
Year:
2012

Citing 4
Cited 0

Accurate Robust Symmetry Estimation

MICCAI '99 Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention
Evaluation of the symmetry plane in 3D MR brain images

Pattern Recognition Letters
Cerebellum segmentation in MRI using atlas registration and local multi-scale image descriptors

ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Automatic recognition of midline shift on brain CT images

Computers in Biology and Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many methods exist for the automatic extraction of the midsagittal plane from neuroimages, assuming bilateral symmetry. However, this assumption is incorrect owing to brain torque and the possible presence of pathology. In this paper, a method for extracting the curved midsagittal surface from brain images is presented. First, the method localizes the interhemispheric fissure with an existing technique for midsagittal plane extraction. Next, the plane is modelled as a bicubic spline and the configuration of the control points is optimized to obtain the midsagittal surface. The midsagittal surface results in a better segmentation of the cerebral hemispheres. Not only is the result visually more appealing, the absolute volume of misclassified tissue decreases significantly.