单位：[a]Faculty of Information Technology, Beijing University of Technology, Beijing, China[b]School of Computer Science, Faculty of Engineering, University of Sydney, Sydney, Australia[c]Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, China医技科室影像中心放射科首都医科大学附属北京友谊医院
Vestibule Segmentation is of great significance for the clinical diagnosis of congenital ear malformations and cochlear implants. However, automated segmentation is a challenging task due to the tiny size, blur boundary, and drastic changes in shape and size. In this paper, a vestibule segmentation method from CT images has been proposed specifically, which exploits different deep feature fusion strategies, including convolutional feature fusion for different receptive fields, channel attention based feature channel fusion, and encoder-decoder feature fusion. The experimental results on the self-established vestibule segmentation dataset show that, compared with several state-of-the-art methods, our method can achieve superior segmentation accuracy.
基金：
Science and Technology Development Program of Beijing Education Committee, China [KM201810005026]
语种：
外文
被引次数：
WOS：
PubmedID：
中科院(CAS)分区：
出版当年[2020]版：
大类|3 区医学
小类|3 区工程：生物医学3 区核医学
最新[2025]版：
大类|2 区医学
小类|2 区工程：生物医学2 区核医学
JCR分区：
出版当年[2019]版：
Q1ENGINEERING, BIOMEDICALQ1RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
最新[2023]版：
Q1ENGINEERING, BIOMEDICALQ1RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
第一作者单位：[a]Faculty of Information Technology, Beijing University of Technology, Beijing, China
通讯作者：
推荐引用方式(GB/T 7714)：
Zhang R,Zhuo L,Zhang H,et al.Vestibule segmentation from CT images with integration of multiple deep feature fusion strategies[J].COMPUTERIZED MEDICAL IMAGING and GRAPHICS.2021,89:doi:10.1016/j.compmedimag.2021.101872.
APA：
Zhang, R,Zhuo, L,Zhang, H,Zhang, Y,Kim, J...&Wang, Z.(2021).Vestibule segmentation from CT images with integration of multiple deep feature fusion strategies.COMPUTERIZED MEDICAL IMAGING and GRAPHICS,89,
MLA：
Zhang, R,et al."Vestibule segmentation from CT images with integration of multiple deep feature fusion strategies".COMPUTERIZED MEDICAL IMAGING and GRAPHICS 89.(2021)
