Segmentation of intervertebral disks from videofluorographic images using convolutional neural network
Segmentation of intervertebral disks from videofluorographic images using convolutional neural network
复制标题
使用卷积神经网络从视频荧光图像中分割椎间盘
DOI：
10.1117/12.2521249
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
H. Kudo
中科院分区：
文献类型：
--
作者：
Ayano Fujinaka;Yukihoto Saito;Kojiro Mekata;H. Takizawa;H. Kudo
吞咽是通过颈部结构执行的一系列动作来实现的。虽然世界上有许多患者患有吞咽困难，但吞咽的机制和运动学还没有充分阐明。本研究旨在利用卷积神经网络(CNN)对视频透视(VF)图像中具有代表性的颈椎结构中的椎间盘(ID)进行分割。该方法包括三个步骤：宫颈口罩的提取、基于CNN的入侵检测候选区域的分割和假阳性的消除。将这种分割方法应用于11个参与者的实际VF图像，其中有51个未遮挡ID，并成功地分割了43个ID。
Swallowing is achieved by a sequence of actions performed by cervical structures. Although a lot of patients suffer from dysphagia in the world, the mechanism and kinematics of swallowing are not elucidated sufficiently. This study aims to segment intervertebral disks (IDs), which are ones of representative cervical structures, in videofluorographic (VF) images by use of convolutional neural network (CNN). The proposed method consists of three steps: extraction of cervical masks, CNN-based segmentation of candidate regions of IDs, and the elimination of false positives. This segmentation method was applied to actual VF images of eleven participants that have fifty-one not-occluded IDs, and forty-three IDs were segmented successfully.