Authors:
Felipe P. G. Bergo
;
Guilherme C. S. Ruppert
;
Luiz F. Pinto
and
Alexandre X. Falca˜o
Affiliation:
LIV, Institute of Computing, Unicamp, Brazil
Keyword(s):
Mid-sagittal plane extraction, medical image analysis, medical image alignment, brain image segmentation.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Medical Image Detection, Acquisition, Analysis and Processing
Abstract:
Extraction of the mid-sagittal plane (MSP) is an important step for brain image registration and asymmetry analysis. We present a fast MSP extraction method for 3D MR images, which is based on automatic segmentation of the brain and on heuristic maximization of cerebro-spinal fluid within the MSP. The method is shown to be robust to severe anatomical asymmetries between the hemispheres, caused by surgical procedures and lesions. The experiments used 64 MR images (36 pathological, 20 healthy, 8 synthetic) and the method found an acceptable approximation of the MSP in all images with a mean time of 60.0 seconds per image.