Temporal bone key anatomical structure automatic positioning method based on spatial relative position prior

A technology of relative positional relationship and anatomical structure, applied in the field of automatic positioning of small targets in key structures of the temporal bone

Pending Publication Date: 2021-02-26
BEIJING UNIV OF TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the invention is to overcome the deficiencies of existing medical image positioning methods

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Temporal bone key anatomical structure automatic positioning method based on spatial relative position prior
  • Temporal bone key anatomical structure automatic positioning method based on spatial relative position prior
  • Temporal bone key anatomical structure automatic positioning method based on spatial relative position prior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Below in conjunction with accompanying drawing of description, the embodiment of the present invention is described:

[0054] The present invention uses the temporal bone CT data set for training and testing. A total of 64 cases contain labeled normal human temporal bone CT data. Among them, 33 were men and 31 were women, with an average age of 44 years. A total of 9 anatomical structures including malleus, incus, cochlear outer wall, cochlear cavity, external semicircular canal, posterior semicircular canal, anterior semicircular canal, vestibule and internal auditory canal were marked. In the experiment, 56 cases of data are used as the training set, and 8 cases of data are used as the training set. At the same time, using unlabeled data, the subjective performance evaluation of the positioning results is used as the generalization evaluation of the algorithm.

[0055] The data preprocessing adopted in the present invention includes resampling of CT images and labe...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a temporal bone key anatomical structure automatic positioning method based on the spatial relative position prior. According to the invention, the positioning speed and the positioning precision of the anatomical structure are improved, and meanwhile the segmentation effect on temporal bone CT data with different data distributions is improved. According to the method, spatial relative position modeling is carried out on nine key anatomical structures of the temporal bone through the adjacency matrix graph, and a self-adaptive active fine adjustment strategy is designedfor the model, so that the model is suitable for temporal bone CTs of different scales. According to the two-stage positioning algorithm provided by the invention, an easy-to-position structure is firstly positioned as a reference point, other difficult-to-position structures are roughly positioned in combination with a spatial relative position, and then accurate positioning of each anatomical structure is further performed in a rough positioning range by adopting an accurate positioning algorithm, so that the interference of a complex background to a positioning result is reduced, and the positioning accuracy is improved. The positioning precision and the positioning speed are effectively improved. Meanwhile, the model has better generalization ability in processing temporal bone CT with different data distributions.

Description

technical field [0001] The invention belongs to the field of medical image processing, and in particular relates to a method for automatically locating small targets of key temporal bone structures in combination with prior information of spatial relative positions. Background technique [0002] CT of the temporal bone can reveal fine structures such as the middle ear and inner ear, such as the cochlea, semicircular canals, vestibule, and auditory ossicles. Doctors judge the patient's symptoms by observing whether the key anatomical structures of the temporal bone are abnormal. With the continuous increase of clinical needs, the rapid increase of medical imaging data every year, and the shortage of medical resources in my country have greatly increased the workload of doctors and reduced the efficiency of patients' consultation. Therefore, quickly locating the areas that doctors need to pay attention to can greatly reduce the workload of doctors, improve diagnostic efficien...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T7/11G06T7/136G06T7/194G06T7/33G06T7/73
CPCG06T7/11G06T7/136G06T7/194G06T7/344G06T7/75G06T2207/30008G06T2207/10081G06T2207/20081G06T2207/30204
Inventor 李晓光朱梓垚伏鹏卓力张辉
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap