周围神经MicroCT图像中神经束轮廓获取算法的改进
CSTR:
作者:
作者单位:

1. 广东工业大学 自动化学院,广州 510006;2. 广东财经大学 信息学院,广州 510320;3. 南方医科大学珠江医院 骨科,广州 510630;4. 中山大学附属第一医院 显微外科,广州 510080

作者简介:

通讯作者:

E-mail: gdut_zyc@qq.com.

中图分类号:

TP391

基金项目:

广东省自然科学基金项目(2018A0303130137);广东省高性能计算重点实验室开放项目(TH1528);广东省哲学社会科学规划学科共建项目(GD18XJY05);国家自然科学基金项目(61975248).


An improved approach to obtain contours of fascicular groups from MicroCT images of peripheral nerve
Author:
Affiliation:

1. School of Automation,Guangdong University of Technology,Guangzhou 510006,China;2. School of Information,Guangdong University of Finance & Economics,Guangzhou 510320,China;3. Department of Bone and Joint Surgery,Zhujiang Hospital of Southern Medical University,Guangzhou 510630,China;4. Department of Orthopedics Trauma and Microsurgery,The First Affiliated Hospital of Sun Yat-sen University,Guangzhou 510080,China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    采用原始的蒙皮区域卷积神经网络(Mask R-CNN)获取周围神经MicroCT图像中的神经束轮廓时存在收敛慢、精度低等问题.首先构建两个数据子集,然后提出一种密集连接型网络结构,提取神经束区域特征.此外,改进目标检测部分候选框的得分评价规则,并结合迁移学习策略改进原始算法的训练方式.采用准确率和交并比指标评价算法的准确度,精细度阈值指标评价轮廓获取的精度,并确定了精细度阈值的最佳值.实验结果表明,改进后算法在两个数据子集中的准确率和交并比均在83%和87%以上.在精细度阈值为0.85时,获得的神经束轮廓最佳.由此可见,改进后算法能够良好地实现从周围神经MicroCT图像中获取神经束轮廓的目标,为周围神经内部结构的三维可视化奠定基础.

    Abstract:

    An improved mask region-convolutional neural network(Mask R-CNN) algorithm is proposed to conquer the shortcoming such as the slow convergence rate, low accuracy in the original Mask R-CNN algorithm to obtain contours of fascicular groups from MicroCT images of peripheral nerve. Firstly, the dataset of images is constructed and divided into two subsets. Then, the network architecture with dense connection is proposed to abstract the feature of fascicular groups. Furthermore, the regulation of proposal box scores in object detection part is improved, the transfer learning strategy is combined with the Mask R-CNN in training process. The average precision(AP) and the intersection over union(IoU) are adopted as evaluation indices of algorithm accurate, and the precision threshold is adopted as the evaluation index of algorithm precision, and the best value of the precision threshold is identified. Experiment results show that the AP and the IoU of the improved approach exceed 83% and 87% in the two peripheral nerve MicroCT image subsets. The improved algorithm has the best contours of fascicular groups at the threshold of 0.85. Experiments show that the improved algorithm can extract the contours of fascicular groups exactly and lay the foundation for the three dimensional visualization of the internal structure of peripheral nerve.□□

    参考文献
    相似文献
    引证文献
引用本文

钟映春,祝玉杰,蚁晓虹,等.周围神经MicroCT图像中神经束轮廓获取算法的改进[J].控制与决策,2021,36(7):1601-1610

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2021-06-16
  • 出版日期: 2021-07-20
文章二维码