Topological GCN for Improving Detection of Hip Landmarks from B-Mode Ultrasound Images

doi:10.1007/978-3-031-72086-4_65

	Topological GCN for Improving Detection of Hip Landmarks from B-Mode Ultrasound Images
	Huang, Tianxiang 1; Shi, Jing 2; Jin, Ge 1,3; Li, Juncheng 1; Wang, Jun 1; Du, Jun 2; Shi, Jun 1
	2024
会议名称	27th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)
会议录名称	SPRINGER INTERNATIONAL PUBLISHING AG
页码	692-701
会议日期	OCT 06-10, 2024
会议地点	Palmeraie Conf Ctr, Marrakesh, MOROCCO
出版地	CHAM
摘要	The B-mode ultrasound based computer-aided diagnosis (CAD) has demonstrated its effectiveness for diagnosis of Developmental Dysplasia of the Hip (DDH) in infants. However, due to effect of speckle noise in ultrasound images, it is still a challenge task to accurately detect hip landmarks. In this work, we propose a novel hip landmark detection model by integrating the Topological GCN (TGCN) with an Improved Conformer (TGCN-ICF) into a unified framework to improve detection performance. The TGCN-ICF includes two subnetworks: an Improved Conformer (ICF) subnetwork to generate heatmaps and a TGCN subnetwork to additionally refine landmark detection. This TGCN can effectively improve detection accuracy with the guidance of class labels. Moreover, a Mutual Modulation Fusion (MMF) module is developed for deeply exchanging and fusing the features extracted from the U-Net and Transformer branches in ICF. The experimental results on the real DDH dataset demonstrate that the proposed TGCN-ICF outperforms all the compared algorithms.
关键词	Developmental dysplasia of the hip B-mode ultrasound images Landmark detection Topological graph convolutional network
DOI	10.1007/978-3-031-72086-4_65
收录类别	CPCI-S
语种	英语
WOS研究方向	Computer Science ; Engineering ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods ; Engineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:001342230100065
原始文献类型	Proceedings Paper
EISSN	1611-3349
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	会议论文
条目标识符	http://ir.library.ouchn.edu.cn/handle/39V7QQFX/173666
专题	国家开放大学江苏分部
通讯作者	Du, Jun
作者单位	1.Shanghai Univ, Sch Commun & Informat Engn, Shanghai 200444, Peoples R China; 2.Shanghai Jiao Tong Univ, Sch Med, Diagnost Imaging Ctr, Shanghai Childrens Med Ctr, Shanghai 200127, Peoples R China; 3.Jiangsu Open Univ, Sch Commun & Informat Engn, Nanjing 214257, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Huang, Tianxiang,Shi, Jing,Jin, Ge,et al. Topological GCN for Improving Detection of Hip Landmarks from B-Mode Ultrasound Images[C]. CHAM,2024:692-701.