Method for automatically evaluating alveolar nerve injury risk under medical image

A nerve injury, medical image technology, applied in medical image, medical automatic diagnosis, medical informatics and other directions, can solve the problems of time-consuming and laborious, manual positioning workload is large, time-consuming and other problems, to reduce workload and time-consuming Effect

Pending Publication Date: 2021-11-16
NANJING UNIV OF POSTS & TELECOMM
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Manual positioning is not only a heavy workload and time-consuming, but also the difference in clinical experience, personal energy and pressure of different doctors will directly affect the accuracy of judging the relationship between mandibular wisdom teeth and neural tube, and the evaluation of wisdom teeth and inferior alveolar nerve The positional relationship is still manual, which is time-consuming and labor-intensive, and is also greatly affected by human factors.

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
  • Method for automatically evaluating alveolar nerve injury risk under medical image
  • Method for automatically evaluating alveolar nerve injury risk under medical image
  • Method for automatically evaluating alveolar nerve injury risk under medical image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Such as figure 1 , figure 2 As shown, the method for automatically assessing the risk of alveolar nerve injury under medical images provided in this embodiment, for a certain curved tomographic image to be detected, in practical application, specifically includes the following steps:

[0045](1) The data set consists of CBCT and curved tomographic images of 1535 research cases, in which the size of the curved tomographic image used for training is 2976×1536, and the pixel size is 0.07×0.07mm 2 ;

[0046] (2) Based on the CBCT images of 1535 research cases, combined with the NewTom system software, the oral and maxillofacial surgeons evaluated the three-dimensional spatial relationship between the root and the inferior alveolar canal through cross-sectional and coronal images, and observed whether the two were in contact and whether the lower teeth were in contact with each other. Whether the cortical bone of the trough neural tube is complete can judge the contact re...

Embodiment 2

[0065] This embodiment provides a device for automatically assessing the risk of alveolar nerve injury under medical images, including a processor and a storage medium;

[0066] The storage medium is used to store instructions;

[0067] The processor is configured to operate according to the instructions to perform the steps of the following method:

[0068] Obtain a training set, which includes a CBCT image and a tomographic image;

[0069] Judging the contact relationship between mandibular impacted wisdom teeth and inferior alveolar canal in CBCT images;

[0070] Use the results of the judgment to mark the positions of the mandibular impacted wisdom teeth and the inferior alveolar canal in the curved tomogram images;

[0071] Expand the way of data enhancement for training set images;

[0072] Obtaining a multi-resolution target detection model, the multi-resolution target detection model is obtained based on the construction of a convolutional neural network model;

[...

Embodiment 3

[0077] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the following method are implemented:

[0078] Obtain a training set, which includes a CBCT image and a tomographic image;

[0079] Judging the contact relationship between mandibular impacted wisdom teeth and inferior alveolar canal in CBCT images;

[0080] Use the results of the judgment to mark the positions of the mandibular impacted wisdom teeth and the inferior alveolar canal in the curved tomogram images;

[0081] Expand the way of data enhancement for training set images;

[0082] Obtaining a multi-resolution target detection model, the multi-resolution target detection model is obtained based on the construction of a convolutional neural network model;

[0083] Using the expanded training set data as input, train a multi-resolution target detection model to predict the image position of mandibular im...

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 discloses a method for automatically evaluating the alveolar nerve injury risk under a medical image, and the method comprises the following steps: obtaining a training set which comprises a CBCT image and a curved surface tomography image; judging the contact relationship between the mandibular impacted wisdom teeth of the CBCT image and the inferior alveolar neural tube; expanding the training set image in a data enhancement mode; obtaining a multi-resolution target detection model; training a multi-resolution target detection model to predict image positions of mandibular impacted wisdom teeth and inferior alveolar neural tubes; and using a non-maximum suppression algorithm to solve the final positions of the mandibular impacted wisdom teeth and the inferior alveolar neural tube and the contact relation between the two. According to the method, the specific positions of the wisdom teeth and the neural tubes in the curved surface tomography image can be automatically judged, meanwhile, the contact relation between the wisdom teeth and the neural tubes is predicted, and the workload and consumed time of manual positioning of an oral and maxillofacial department doctor are effectively reduced.

Description

technical field [0001] The invention relates to a method for automatically assessing the risk of alveolar nerve injury under medical images, and belongs to the technical field of medical image quality control. Background technique [0002] In recent years, the extraction of mandibular wisdom teeth has gradually become the most common operation in clinical clinics of oral and maxillofacial surgery. Since the position of the wisdom tooth root is quite close to the inferior alveolar nerve, if the operation is performed without accurately judging the adjoining relationship during the operation, it is extremely easy to cause damage to the inferior alveolar nerve. The damage caused includes: bleeding and swelling after tooth extraction , pain, limited mouth opening, infection, dry socket, inferior alveolar nerve injury, lingual nerve injury, lingual bone plate injury, tooth root displacement into the lingual space, and rare and severe mandibular fractures, etc., which seriously af...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G16H50/20G16H30/00G06K9/32G06K9/62
CPCG16H50/20G16H30/00G06F18/241G06F18/214
Inventor 戴修斌郑竣衔朱书进冒添逸刘天亮
Owner NANJING UNIV OF POSTS & TELECOMM
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