Skull side surface image analysis method based on neural network and random forest, and system

A side image and neural network technology, applied in the field of computer-aided diagnosis, can solve problems such as shortening the diagnosis cycle, and achieve the effects of shortening the diagnosis cycle, improving stability, high marking accuracy and reliability
CN110246580AActive Publication Date: 2019-09-17SHANGHAI UEG MEDICAL IMAGING EQUIP CO LTD
6 Cites 7 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
SHANGHAI UEG MEDICAL IMAGING EQUIP CO LTD
Publication Date
2019-09-17

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a skull side surface image analysis method based on a neural network and a random forest, and a system. After imaging equipment (commonly oral and maxillofacial tomography equipment, CBCT in short) finishes patient skull side surface exposure and picture combination, an imaging result is input into a skull side surface dissecting characteristic marking module. Through a series of computer automatic identification and marking processes, marking operation of important dissecting structures on the image is finished, and high-precision positions of characteristic points are output. Afterwards a skull side surface report generating module receives the position of each dissecting characteristic point after artificial verification and adjustment by the skull side surface dissecting characteristic marking module and finishes skull surface medical analysis, wherein a final skull side surface analysis report is used as a subsequent diagnosis basis of the doctor. The method and the system have advantages of settling a problem of performing quick automatic analysis on the skull side surface image, greatly reducing physical labor of a doctor in a skull side surface imaging analysis process, shortening a diagnosis period, improving system predicting stability and preventing abnormal results.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of computer-aided diagnosis, and relates to a method and system for automatic analysis of cranial side X-ray images, in particular to an automatic analysis of cranial side X-ray images (hereinafter referred to as cranial side images) based on random forest technology and neural network technology methods and systems. Background technique

[0002] X-ray Cranial Imaging (X-ray Cephalometry) technology is an imaging technology that uses X-rays to project radiation on the patient's head to obtain a side perspective view of the patient's head; its functional feature is to use a small radiation dose, Obtain cross-sectional image data of head bones and tissues to provide basis for clinicians' diagnosis. In the lateral imaging results of the brain, there are some characteristic points indicated by the physiological structure, which can provide auxiliary information for the doctor's diagnosis or become the basis for...

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