TY - GEN
T1 - Combined pixel classification and atlas-based segmentation of the ventricular system in brain CT images
AU - Vos, Pieter C.
AU - Išgum, Ivana
AU - Biesbroek, J. Matthijs
AU - Velthuis, Birgitta K.
AU - Viergever, Max A.
PY - 2013
Y1 - 2013
N2 - Accurate segmentation of the brain ventricular system in Computed Tomography (CT) images is useful in neurodiagnosis, providing quantitative measures on changes in ventricular size due to stroke. Manual segmentation, however, is a time-consuming, tedious task and is prone to large inter-observer variability. This study presents an automatic ventricle system segmentation method by combining the results of supervised pixel classification based on intensities with spatial information obtained from a multi-atlas-based segmentation method. The method is applied to follow-up brain CT images which were collected from a cohort of 20 patients with proven ischemic stroke. The automatic segmentation performance was evaluated in a leave-one-out strategy by comparing with manual segmentations. The results show that combining information obtained from pixel classification and multiatlas- based segmentation significantly outperforms each method independently with a mean Dice coefficient index of 0.81±0.07. © 2013 SPIE.
AB - Accurate segmentation of the brain ventricular system in Computed Tomography (CT) images is useful in neurodiagnosis, providing quantitative measures on changes in ventricular size due to stroke. Manual segmentation, however, is a time-consuming, tedious task and is prone to large inter-observer variability. This study presents an automatic ventricle system segmentation method by combining the results of supervised pixel classification based on intensities with spatial information obtained from a multi-atlas-based segmentation method. The method is applied to follow-up brain CT images which were collected from a cohort of 20 patients with proven ischemic stroke. The automatic segmentation performance was evaluated in a leave-one-out strategy by comparing with manual segmentations. The results show that combining information obtained from pixel classification and multiatlas- based segmentation significantly outperforms each method independently with a mean Dice coefficient index of 0.81±0.07. © 2013 SPIE.
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84878289328&origin=inward
U2 - https://doi.org/10.1117/12.2006222
DO - https://doi.org/10.1117/12.2006222
M3 - Conference contribution
VL - 8669
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2013: Image Processing
T2 - Medical Imaging 2013: Image Processing
Y2 - 10 February 2013 through 12 February 2013
ER -