基于喉部CT图像的气道路径规划方法、装置、计算机设备

By preprocessing and 3D segmenting laryngeal CT images, and combining obstacle weights and center point sequences, an initial path matching the airway anatomy is generated. This solves the problem that traditional CT images cannot quantitatively assess airway patency, and improves the success rate and safety of endotracheal intubation.

CN121937681BActive Publication Date: 2026-07-17EYE & ENT HOSPITAL SHANGHAI MEDICAL SCHOOL FUDAN UNIV
View PDF 4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-03-30
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Traditional CT imaging assessment cannot quantify the patency of the airway during intubation, resulting in a high risk of endotracheal intubation failure and an inability to achieve accurate prediction and pathway planning.

Method used

Preprocessing is performed on laryngeal CT images, and a three-dimensional airway structure is generated through a three-dimensional segmentation model. By combining the differential weights of obstacles and the sequence of center points, an initial airway path is planned, and the path constraints are optimized to ensure the reliability and consistency of the path.

Benefits of technology

It improves the success rate of endotracheal intubation, reduces the risk of tube entrapment and tracheal wall damage, and the generated path strictly matches the airway anatomy, improving the reliability and accuracy of path planning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121937681B_ABST
    Figure CN121937681B_ABST
Patent Text Reader

Abstract

本申请涉及一种基于喉部CT图像的气道路径规划方法、装置、计算机设备。所述方法包括：获取喉部CT图像；对喉部CT图像进行预处理，预处理包括统一喉部CT图像的厚度参数，以及采用复制方式对厚度参数一致的喉部CT图像中包括声门部位的目标层进行数据扩充处理；将预处理后的喉部CT图像输入至训练后的三维分割模型进行三维分割，得到分割后的气道三维结构；根据分割后的气道三维结构中不同区域的障碍物差异化权重，得到路径约束条件；对分割后的气道三维结构进行分层处理，得到多层气道横截面；基于多层气道横截面的中心点坐标，得到中心点序列；基于气道中的目标点、中心点序列、路径约束条件，得到喉部CT图像对应的初始气道路径。
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Autonomous navigation method for tracheal intubation robot based on self-supervised monocular depth estimation

    CN116966381A

  • Hip joint CT image segmentation method based on improved nnUNet model

    CN120612337A

  • Path planning device of bronchoscope

    CN121196730A

  • Method and device for semgneting body component for conveying fluid

    KR1020220121141A