脑血管数字减影血管造影高分辨率分割网络设计

崔颖; 付瑞; 朱佳; 高山; 陈立伟; 张广

doi:10.11990/jheu.202206003

Chinese

您当前的位置：

首页 >

文章列表页 >

脑血管数字减影血管造影高分辨率分割网络设计

更新时间：2025-09-01

- 脑血管数字减影血管造影高分辨率分割网络设计
- Design of a high-resolution segmentation network for digital subtraction angiography of cerebral vessels
- 哈尔滨工程大学学报 2024年45卷第4期页码：786-793
- 作者机构：
  
  1.哈尔滨工程大学信息与通信工程学院, 黑龙江哈尔滨 150001
  2.哈尔滨医科大学附属第一医院神经外科, 黑龙江哈尔滨 150001
- 作者简介：
  
  [ "崔颖, 女, 副教授" ]
  [ "付瑞, 男, 硕士研究生" ]
- 基金信息：
  
  国家自然科学基金项目(81901190)
- DOI：10.11990/jheu.202206003
  中图分类号： TP391
- 收稿：2022-06-02，
  
  网络首发：2024-02-01，
  
  纸质出版：2024-04-05
- 稿件说明：
移动端阅览
崔颖, 付瑞, 朱佳, 等. 脑血管数字减影血管造影高分辨率分割网络设计[J]. 哈尔滨工程大学学报, 2024,45(4):786-793.

Ying CUI, Rui FU, Jia ZHU, et al. Design of a high-resolution segmentation network for digital subtraction angiography of cerebral vessels[J]. Journal of Harbin Engineering University, 2024, 45(4): 786-793.
崔颖, 付瑞, 朱佳, 等. 脑血管数字减影血管造影高分辨率分割网络设计[J]. 哈尔滨工程大学学报, 2024,45(4):786-793. DOI： 10.11990/jheu.202206003.

Ying CUI, Rui FU, Jia ZHU, et al. Design of a high-resolution segmentation network for digital subtraction angiography of cerebral vessels[J]. Journal of Harbin Engineering University, 2024, 45(4): 786-793. DOI： 10.11990/jheu.202206003.

摘要

针对现存卷积神经网络对脑血管数字减影血管造影分割精度不高的问题

本文提出了一种基于U-Net的改进网络(IC-Net)。通过融合使用Inception和CAM通道注意力模块

以多种感受域提取更丰富的血管特征信息

并对特征信息进行筛选。增加7×7卷积层

通过压缩特征层分辨率的方式减少训练过程中产生的数据量。本文所提模型与U-Net、R2U-Net、Attention U-Net相比

IOU、Accuracy、F1-Score和ROC曲线下面积4项指标平均提升了1.82 %、0.014 %、1.19 %和0.73 %。结果验证了IC-Net模型明显提升了脑血管数字减影血管造影虚弱血管和血管末端的检测能力

提升了分辨伪影噪声的能力

为医生识别脑血管中产生的病变提供有力参考。

Abstract

To solve the problem of low accuracy of existing convolutional neural networks for cerebral vascular DSA image segmentation

an improved network based on U-Net (IC-Net) is proposed. By fusing the use of inception and channel attention modules

rich vascular feature information is extracted using multiple sensory domains and feature information is filtered. A new 7×7 convolutional layer is added to reduce the amount of data generated during training by compressing the feature layer resolution. Compared with the U-Net and common U-Net improved models

the improved model's intersection over union

accuracy

F1-score

and area under the curve increase by 1.82 %

0.014 %

1.19 %

and 0.73 % on average

respectively. The results verify that the IC-Net model remarkably improves the model's capabilities to detect weak vessels and vessel ends in cerebrovascular digital subtraction angiography images and distinguish artifactual noise. The model provides a strong reference for physicians to identify lesions within cerebrovascular vessels.

关键词

Keywords

references

丁月燕. 高压氧对脑血管疾病的治疗进展[J]. 中国医疗器械信息, 2022, 28(2): 29-31.

DING Yueyan. Progress of hyperbaric oxygen in the treatment of cerebrovascular diseases[J]. China medical device information, 2022, 28(2): 29-31.

CUI Wenchao, WANG Yi, FAN Yangyu, et al. Localized FCM clustering with spatial information for medical image segmentation and bias field estimation[J]. International journal of biomedical imaging, 2013, 2013: 930301.

江乾峰. 基于多角度空间特征点集的脑血管分割系统[D]. 大连: 大连理工大学, 2016.

JIANG Qianfeng. The vessel segmentation system for cerebralvascular images based on spatial feature point set of multi-angle[D]. Dalian: Dalian University of Technology, 2016.

王光磊, 王鹏宇, 王中阳, 等. 基于自动随机游走的DSA图像分割算法[J]. 激光杂志, 2018, 39(4): 81-85.

WANG Guanglei, WANG Pengyu, WANG Zhongyang, et al. DSA image segmentation algorithm based on automatic random walk[J]. Laser journal, 2018, 39(4): 81-85.

NASR-ESFAHANI E, SAMAVI S, KARIMI N, et al. Vessel extraction in X-ray angiograms using deep learning[C]//Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE Engineering in Medicine and Biology Society Annual International Conference, 2016: 643-646.

YANG Siyuan, YANG Jian, WANG Yachen, et al. Automatic coronary artery segmentation in X-ray angiograms by multiple convolutional neural networks: China[P]. 2018.

FAN Jingfan, YANG Jian, WANG Yachen, et al. Multichannel fully convolutional network for coronary artery segmentation in X-ray angiograms[J]. IEEE access, 2018, 6: 44635-44643.

JUN T J, KWEON J, KIM Y H, et al. T-Net: nested encoder-decoder architecture for the main vessel segmentation in coronary angiography[J]. Neural networks, 2020, 128: 216-233.

RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[M]//Lecture Notes in Computer Science. Cham: Springer International Publishing, 2015: 234-241.

王卓英, 童基均, 蒋路茸, 等. 基于U-Dense-net网络的DSA图像冠状动脉血管分割[J]. 浙江理工大学学报(自然科学版), 2021, 45(3): 390-399.

WANG Zhuoying, TONG Jijun, JIANG Lurong, et al. Coronary artery segmentation of DSA images based on U-Dense-net network[J]. Journal of Zhejiang Sci-Tech University (natural sciences), 2021, 45(3): 390-399.

OKTAY O, SCHLEMPER J, LE FOLGOC L, et al. Attention U-net: learning where to look for the pancreas[EB/OL ] . 2018: arXiv: 1804.03999. http://arxiv.org/abs/1804.03999.pdf http://arxiv.org/abs/1804.03999.pdf .

ALOM M Z, HASAN M, YAKOPCIC C, et al. Recurrent residual convolutional neural network based on U-Net (R2U-Net) for medical image segmentation[EB/OL ] . 2018: arXiv: 1802.06955. http://arxiv.org/abs/1802.06955.pdf http://arxiv.org/abs/1802.06955.pdf .

SZEGEDY C, LIU Wei, JIA Yangqing, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, 2015: 1-9.

WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[EB/OL ] . 2018: arXiv: 1807.06521. http://arxiv.org/abs/1807.06521.pdf http://arxiv.org/abs/1807.06521.pdf .

SZEGEDY Christian, VANHOUCKE Vincent, IOFFE Sergey, et al. Rethinking the inception architecture for computer vision[EB/OL ] . IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. 2015. [2022-05-28 ] . https://arxiv.org/pdf/1804.03999.pdf https://arxiv.org/pdf/1804.03999.pdf .

HU Jie, SHEN Li, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2020, 42(8): 2011-2023.

ZHOU Zongwei, SIDDIQUEE M M R, TAJBAKHSH N, et al. UNet++: a nested U-net architecture for medical image segmentation[EB/OL ] . 2018: arXiv: 1807.10165. http://arxiv.org/abs/1807.10165.pdf http://arxiv.org/abs/1807.10165.pdf .

HUANG Huimin, LIN Lanfen, TONG Ruofeng, et al. UNet 3+: a full-scale connected UNet for medical image segmentation[EB/OL ] . 2020: arXiv: 2004.08790. http://arxiv.org/abs/2004.08790.pdf http://arxiv.org/abs/2004.08790.pdf .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于深度学习的TBM密集岩碴片图像分割

基于递归图和卷积神经网络-门控循环单元的水轮机空化状态识别方法

改进YOLOv8n的热轧钢材表面缺陷检测

基于深度学习和图像处理的螺栓损伤检测

双谱分析的辐射噪声线谱源深度辨识方法