DocumentCode :
1772157
Title :
Standard plane localization in ultrasound by radial component
Author :
Xin Yang ; Dong Ni ; Jing Qin ; Shengli Li ; Tianfu Wang ; Siping Chen ; Pheng Ann Heng
Author_Institution :
Nat.-Regional Key Technol. Eng. Lab. for Med. Ultrasound, Shenzhen Univ., Shenzhen, China
fYear :
2014
fDate :
April 29 2014-May 2 2014
Firstpage :
1180
Lastpage :
1183
Abstract :
The acquisition of standard planes is crucial for medical ultrasound (US) diagnosis. In this paper, we present a hierarchical supervised learning framework for automatically detecting standard plane in consecutive 2D US images. The technique is demonstrated by developing a system that localizes fetal abdominal standard plane (FASP) from US videos. We first propose a novel radial component-based model (RCM) to describe the geometric constrains of key anatomical structures (KAS). In order to enhance the detection accuracy, we further adopt random forests classifier for detection of KAS within the regions constrained by RCM. Finally, a second-level classifier combines the results of component detectors to identify a US image as a “FASP” or a “nonFASP”. Experimental results show that our method significantly outperforms both the full abdomen and the separate anatomy detection methods without geometric constrains.
Keywords :
biomedical ultrasonics; image classification; learning (artificial intelligence); medical image processing; object detection; obstetrics; random processes; KAS detection; RCM; US videos; anatomy detection methods; component detectors; consecutive 2D US images; detection accuracy; fetal abdominal standard plane; full abdomen; geometric constrains; hierarchical supervised learning framework; key anatomical structures; medical ultrasound diagnosis; nonFASP; radial component-based model; random forest classifier; second-level classifier; standard plane acquisition; standard plane localization; Anatomical structure; Detectors; Radio frequency; Standards; Ultrasonic imaging; Videos; Fetal abdomen; Machine learning; Object detection; Standard plane; Ultrasound;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Imaging (ISBI), 2014 IEEE 11th International Symposium on
Conference_Location :
Beijing
Type :
conf
DOI :
10.1109/ISBI.2014.6868086
Filename :
6868086
Link To Document :
بازگشت