DocumentCode :
2570154
Title :
Registration-based auto-detection of the optimal cross sections in 3D echocardiographic images
Author :
Liu, Xiaoping ; Yang, Xin ; Wu, Lanping ; Tan, Xiao
Author_Institution :
Comput. Center, East China Normal Univ., Shanghai, China
fYear :
2010
fDate :
16-18 April 2010
Firstpage :
221
Lastpage :
225
Abstract :
In most cases, echocardiographers examine three-dimensional (3D) or four-dimensional (4D) echocardiographic images by studying several important cross sections which are defined as the optimal cross sections. It is a time-consuming and tedious task for echocardiographers to manually search the optimal cross sections by existing real-time 3D echocardiography (RT3DE) systems or off-line 3D softwares. To assist doctors´ diagnosis, we design a registration-based method to automatically detect the optimal cross sections in three-dimensional echocardiographic (3DE) images. Firstly, a normal end-diastolic (ED) volumetric data is chosen, in which its optimal cross section is predetermined. Secondly, instead of the whole ED volume, only part of it is selected as the template. Finally, all the optimal cross sections of a 3DE image are detected by aligning the 3DE image with the template image. As a preliminary study, we performed this method on 28 normal apical datasets and the error rate is 15%. The results show good prospects for implementing automatic detection, which might offer better repeatability and save time. Furthermore, it can be a prior procedure for measurement and the computer-aided diagnosis.
Keywords :
echocardiography; image registration; medical image processing; 3D echocardiography; 3DE image; automatic detection; error rate; image registration; optimal cross sections; Biomedical imaging; Echocardiography; Heart; Image processing; Image reconstruction; Image registration; Medical diagnostic imaging; Pattern recognition; Shape; Ultrasonic imaging; image registration; three-dimensional echocardiography;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Bioinformatics and Biomedical Technology (ICBBT), 2010 International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-6775-4
Type :
conf
DOI :
10.1109/ICBBT.2010.5478975
Filename :
5478975
Link To Document :
بازگشت