TY - GEN
T1 - Registration-based propagation for whole heart segmentation from compounded 3D echocardiography
AU - Zhuang, Xiahai
AU - Yao, Cheng
AU - Ma, YingLiang
AU - Hawkes, David
AU - Penney, Graeme
AU - Ourselin, Sebastien
PY - 2010
Y1 - 2010
N2 - Whole heart segmentation of 3D ultrasound (US), also referred to as echocardiography or simply echo, is useful in cardiac functional analysis to achieve quantitative diagnostic information of the heart. However, characteristics of US imaging such as limited field-of-view, artifacts and inconsistent intensity distribution makes automated approaches a challenge. In this paper, we present a framework for automatic whole heart segmentation from 3D echo. This work is motivated by the new technology of compounding 3D echo from 2D matrix array transducers. We propose to use the registration-based segmentation framework and adopt a new similarity measure combining local phase, intensity information and local geometry for registration. The experimental results demonstrated the proposed method had achieved an accuracy of 6.4% volume difference against the gold standard for the left ventricle segmentation and an average accuracy of 14% for segmentation of all four chambers and myocardium.
AB - Whole heart segmentation of 3D ultrasound (US), also referred to as echocardiography or simply echo, is useful in cardiac functional analysis to achieve quantitative diagnostic information of the heart. However, characteristics of US imaging such as limited field-of-view, artifacts and inconsistent intensity distribution makes automated approaches a challenge. In this paper, we present a framework for automatic whole heart segmentation from 3D echo. This work is motivated by the new technology of compounding 3D echo from 2D matrix array transducers. We propose to use the registration-based segmentation framework and adopt a new similarity measure combining local phase, intensity information and local geometry for registration. The experimental results demonstrated the proposed method had achieved an accuracy of 6.4% volume difference against the gold standard for the left ventricle segmentation and an average accuracy of 14% for segmentation of all four chambers and myocardium.
UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-77955197635&partnerID=MN8TOARS
U2 - 10.1109/ISBI.2010.5490183
DO - 10.1109/ISBI.2010.5490183
M3 - Conference contribution
SN - 978-1-4244-4125-9
SP - 1093
EP - 1096
BT - 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings
ER -