CN114723765A - Automatic extraction method of dental arch wire - Google Patents

Automatic extraction method of dental arch wire Download PDF

Info

Publication number
CN114723765A
CN114723765A CN202210386943.7A CN202210386943A CN114723765A CN 114723765 A CN114723765 A CN 114723765A CN 202210386943 A CN202210386943 A CN 202210386943A CN 114723765 A CN114723765 A CN 114723765A
Authority
CN
China
Prior art keywords
coronal
maximum intensity
intensity projection
slice
axial
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210386943.7A
Other languages
Chinese (zh)
Other versions
CN114723765B (en
Inventor
祝胜山
汪阳
房鹤
崔小飞
田忠正
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sichuan Fengzhun Robot Technology Co ltd
Original Assignee
Sichuan Fengzhun Robot Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sichuan Fengzhun Robot Technology Co ltd filed Critical Sichuan Fengzhun Robot Technology Co ltd
Priority to CN202210386943.7A priority Critical patent/CN114723765B/en
Publication of CN114723765A publication Critical patent/CN114723765A/en
Application granted granted Critical
Publication of CN114723765B publication Critical patent/CN114723765B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
    • A61C8/00—Means to be fixed to the jaw-bone for consolidating natural teeth or for fixing dental prostheses thereon; Dental implants; Implanting tools
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
    • A61B2034/101—Computer-aided simulation of surgical operations
    • A61B2034/105—Modelling of the patient, e.g. for ligaments or bones
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
    • A61B2034/107—Visualisation of planned trajectories or target regions
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
    • A61B2034/108—Computer aided selection or customisation of medical implants or cutting guides
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20036—Morphological image processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20076—Probabilistic image processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30036—Dental; Teeth

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Animal Behavior & Ethology (AREA)
  • Dentistry (AREA)
  • Epidemiology (AREA)
  • Orthopedic Medicine & Surgery (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Robotics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

The invention provides an automatic extraction method of dental arch wires, which comprises the following steps: performing coronal maximum intensity projection on the coronal CT slice sequence, performing pixel statistics, and generating a coronal maximum intensity projection histogram; fitting normal distribution of the binary threshold value to obtain a binary threshold value; binarizing the coronal maximum intensity projection image, and counting the number of pixels along a v axis to obtain the CT slice range of the axial maximum intensity projection; the determined axial CT slice is subjected to axial maximum intensity projection to generate an axial maximum intensity projection histogram, and the axial maximum intensity projection histogram is subjected to post-processing such as normalization to extract a final dental arch wire. The whole arch wire extraction process is automatically carried out, and the template is used for stipulating the histogram in the middle process, so that the parameters used in the region growing, morphological operation and gamma conversion have strong universality. Therefore, the whole method for extracting the dental arch line has the advantages of strong real-time performance, high robustness, high accuracy and full automation.

Description

Automatic extraction method of dental arch wire
Technical Field
The invention belongs to the technical field of machine vision, and particularly relates to an automatic extraction method of dental arch wires.
Background
At present, with the continuous improvement of living standard of people, the dental implant operation is adopted by more and more patients. Before the implantation operation is started, the position of the tooth to be implanted needs to be planned first, and the planning method comprises the following steps: it is desirable to expand the arch wire into a panoramic view for easy observation by the oral practitioner to determine where the implant is to be implanted. At this time, the panoramic image needs to be expanded along the dental arch line, so the dental arch line needs to be automatically extracted firstly when planning before operation. The existing method comprises the following steps: the dental arch line is selected at the position of the dental arch line directly depending on the clinical experience of an oral doctor, and then the dental implant software automatically fits the dental arch line according to the point selected by the doctor.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an automatic extraction method of dental arch wires, which can effectively solve the problems.
The technical scheme adopted by the invention is as follows:
the invention provides an automatic extraction method of dental arch wires, which comprises the following steps:
step S1, respectively performing coronal CT scanning and axial CT scanning on the tooth area of the head to respectively obtain a coronal CT slice sequence and an axial CT slice sequence; wherein, coronal direction means: from the posterior brain-scoop to the facial direction, i.e.: from the back to the front direction; the axial direction refers to the direction from top to bottom;
coronal CT slice sequence refers to: superposing the coronal CT slices in the front-back direction; each coronal CT slice is a vertical slice;
the axial CT slice sequence refers to: all the axial CT slices are overlapped along the up-down direction; each axial CT slice is a horizontal slice;
step S2, performing coronal maximum intensity projection on the coronal CT slice sequence to obtain a coronal maximum intensity projection image; wherein, the coronal maximum intensity projection view is a two-dimensional plane view;
step S3, counting the pixels of the coronal maximum intensity projection graph to generate a coronal maximum intensity projection histogram; the abscissa of the coronal maximum intensity projection histogram is a pixel value of 0-256, and the ordinate is: the number of occurrences of each pixel value in the coronal maximum intensity projection view;
fitting normal distribution to the coronal maximum intensity projection histogram to obtain a mean value mu after fitting normal distribution0Sum variance σ0(ii) a According to the mean value mu0Sum variance σ0Obtaining a binary threshold threshHold by adopting the following formula:
threshHold＝μ0+kσ0
wherein: k is an empirical coefficient;
a step S4 of performing binarization processing on the coronal maximum intensity projection map generated at the step S2 using the binarization threshold threshHold generated at the step S3, thereby generating a coronal binarized image;
the binarization method comprises the following steps: for each pixel point in the coronal maximum intensity projection graph, if the pixel value of the pixel point is smaller than a binarization threshold threshHold, changing the pixel value of the pixel point into 0; otherwise, changing its pixel value to 1;
step S5, the image coordinate system of the coronal binarized image is a u-v coordinate system; wherein the v-axis is in the vertical direction; the u-axis is the direction perpendicular to the v-axis in the image;
counting the number of pixels along the v-axis of the coronal binarized image, namely: drawing a straight line L1 parallel to the u axis at the position where v is 1 in the coronal binarized image, and counting the number N1 of pixels of which the pixel value is 1, through which the straight line L1 passes; drawing a straight line L2 parallel to the u axis at the position of v-2, and counting the pixel values of the coronal binarized image through which the straight line L2 passesThe number of pixels N2 being 1; according to the similarity, counting the number of pixels in the v-axis direction of the coronal binaryzation image is completed, and a plurality of discrete points in a coordinate system with the abscissa as the v-axis and the ordinate as the number N of pixel points are obtained; fitting the normal distribution of the discrete points to obtain a mean value mu after fitting the normal distribution1Sum variance σ1；
Mean value μ after fitting according to normal distribution1Sum variance σ1Obtaining a CT slice initial position downslice entering the axial maximum intensity projection and a CT slice end position upSlice entering the axial maximum intensity projection by adopting the following formula:
upSlice＝μ1+kuσ1
downSlice＝μ1-kdσ1
wherein:
kuand kdAre all empirical coefficients;
step S6, selecting all axial CT slices with slice serial numbers from down slice to up slice in the axial CT slice sequence obtained in the step S1 to form an axial CT slice sequence set;
carrying out axial maximum intensity projection on the axial CT slice sequence set to obtain an axial maximum intensity projection diagram;
step S7, counting the pixels of the axial maximum intensity projection graph to generate an axial maximum intensity projection histogram; the abscissa of the axial maximum intensity projection histogram is a pixel value of 0-256, and the ordinate is: the number of occurrences of each pixel value in the axial maximum intensity projection plot;
step S8, histogram regularization is performed on the axial maximum intensity projection histogram to obtain a histogram after regularization so that probability distributions of each pixel value of the histogram after regularization and the template histogram are consistent; wherein, the template histogram means: processing healthy oral tooth areas without implanted teeth and edentulous teeth in the mode of steps S1-S7 to generate an axial maximum intensity projection histogram;
step S9, carrying out gamma conversion on the specified histogram to obtain a gamma-converted picture;
step S10, performing region growing on the gamma-transformed picture to obtain a new binary image;
step S11, performing two-dimensional connected domain analysis on the new binary image generated in step S10, and extracting a connected domain with the largest number of pixels as an arch region;
step S12, performing morphological closing operation on the dental arch area obtained in the step S11 to fill the hole, so as to obtain the dental arch area filled with the hole;
step S13, performing axis transformation on the dental arch area filled with the holes obtained in the step S12 to generate dental arch lines, and performing deburring operation on the generated dental arch lines to generate dental arch lines with burrs removed;
in step S14, the burr-removed dental arch line generated in step S13 is sampled at an equal arc length, and a cubic spline curve is fitted to the generated sample points to extract a final dental arch line.
Preferably, in step S2, the coronal maximum intensity projection is obtained by the following method:
setting each coronal CT slice in the coronal CT slice sequence to comprise n1 × m1 pixel points; wherein n1 is the number of rows and m1 is the number of columns;
irradiating 1 x 1 pixel point of each coronal CT slice in the coronal CT slice sequence by a ray, extracting a pixel value with the maximum gray value from each 1 x 1 pixel point which passes through, and taking the pixel value as the pixel value of the 1 x 1 pixel point of the generated coronal maximum intensity projection graph;
irradiating 1 x 2 pixel points of each coronal CT slice in the coronal CT slice sequence by a ray, extracting a pixel value with the maximum gray value from each 1 x 2 pixel point which passes through, and taking the pixel value as the pixel value of the 1 x 2 pixel point of the generated coronal maximum intensity projection graph;
and so on
Irradiating a ray through the n1 m1 pixel point of each coronal CT slice in the coronal CT slice sequence, and extracting the pixel value with the maximum gray value from the n1 m1 pixel points which pass through the coronal CT slice sequence to be used as the pixel value of the n1 m1 pixel point of the generated coronal maximum intensity projection graph;
this results in a coronal maximum intensity projection.
Preferably, in step S8, the histogram is specified using the following equation:
Figure BDA0003594067380000051
Figure BDA0003594067380000052
G(zq)＝sk
zq＝G(zq)-1
wherein:
G(zq) Is the probability value of the axial maximum intensity projection histogram obtained in step S7 in the range of pixel values 0 to q;
l represents the number of levels of pixels, 256;
pz(zi) Is the probability density function of the pixel value i of the axial maximum intensity projection histogram obtained in step S7;
skis the probability value of the template histogram in the pixel value range of 0-k;
pz(zj) Is the probability density function of the pixel value j of the template histogram;
G(zq)-1represents a pair G (z)q) Inverse operation to solve to a predetermined pixel value zq。
Preferably, in step S9, the gamma conversion is performed by using the following formula:
s＝crγ
wherein:
s is the gamma transformed image pixel value;
c is a normal number;
γ is the intensity factor of the gamma transformation;
r is the image pixel value before gamma conversion.
The automatic extraction method of the dental arch thread provided by the invention has the following advantages:
the whole dental arch line extraction process is automatically carried out, and the template is used for stipulating the histogram in the middle process, so that the parameters used in the process of region growing, morphological operation and gamma conversion have strong universality. Therefore, the whole method for extracting the dental arch line has the advantages of strong real-time performance, high robustness, high accuracy and full automation.
Drawings
Fig. 1 is a schematic flow chart of an automatic extraction method of dental arch wires provided by the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides an automatic extraction method of dental arch lines, which replaces the existing process that a dentist needs to manually select connection points in an oral dental arch area, thereby improving the efficiency of planning a planting path before an operation, improving the extraction accuracy of the dental arch lines and reducing the requirements on the dentist experience.
Referring to fig. 1, the present invention provides an automatic extraction method of dental arch wires, comprising the steps of:
step S1, respectively performing coronal CT scanning and axial CT scanning on the tooth area of the head to respectively obtain a coronal CT slice sequence and an axial CT slice sequence; wherein, coronal direction means: from the posterior brain-scoop to the facial direction, i.e.: from the back to the front; the axial direction refers to the direction from top to bottom;
coronal CT slice sequence refers to: superposing the coronal CT slices in the front-back direction; each coronal CT slice is a vertical slice;
the axial CT slice sequence refers to: stacking all axial CT slices along the up-down direction; each axial CT slice is a horizontal slice;
step S2, performing coronal maximum intensity projection on the coronal CT slice sequence to obtain a coronal maximum intensity projection image; wherein, the coronal maximum intensity projection view is a two-dimensional plane view;
obtaining a coronal maximum intensity projection view by the following method:
setting each coronal CT slice in the coronal CT slice sequence to comprise n1 × m1 pixel points; wherein n1 is the number of rows and m1 is the number of columns;
irradiating 1 x 1 pixel point of each coronal CT slice in the coronal CT slice sequence by a ray, extracting a pixel value with the maximum gray value from each 1 x 1 pixel point which passes through, and taking the pixel value as the pixel value of the 1 x 1 pixel point of the generated coronal maximum intensity projection graph;
irradiating 1 x 2 pixel points of each coronal CT slice in the coronal CT slice sequence by a ray, extracting a pixel value with the maximum gray value from each 1 x 2 pixel point which passes through, and taking the pixel value as the pixel value of the 1 x 2 pixel point of the generated coronal maximum intensity projection graph;
and so on
Irradiating a ray through the n1 m1 pixel point of each coronal CT slice in the coronal CT slice sequence, and extracting the pixel value with the maximum gray value from the n1 m1 pixel points which pass through the coronal CT slice sequence to be used as the pixel value of the n1 m1 pixel point of the generated coronal maximum intensity projection graph;
this results in a coronal maximum intensity projection.
Step S3, counting the pixels of the coronal maximum intensity projection graph to generate a coronal maximum intensity projection histogram; the abscissa of the coronal maximum intensity projection histogram is a pixel value of 0-256, and the ordinate is: the number of occurrences of each pixel value in the coronal maximum intensity projection view;
fitting normal distribution to the coronal maximum intensity projection histogram to obtain a mean value mu after fitting normal distribution0Sum variance σ0(ii) a According to the mean value mu0Sum variance σ0To adoptThe binary threshold threshHold is obtained using the following formula:
threshHold＝μ0+kσ0
wherein: k is an empirical coefficient, preferably 1.98;
when the projection image with the maximum intensity in the coronal direction is binarized, the binarization threshold value obtained by calculation in the method provided by the invention can maximize the inter-class variance of the pixel value of each pixel point in the projection image with the maximum intensity in the coronal direction, so background pixels and foreground pixels can be more effectively distinguished, and the binarization precision is improved.
A step S4 of performing binarization processing on the coronal maximum intensity projection map generated at the step S2 using the binarization threshold threshHold generated at the step S3, thereby generating a coronal binarized image;
the binarization method comprises the following steps: for each pixel point in the coronal maximum intensity projection graph, if the pixel value of the pixel point is smaller than a binarization threshold threshHold, changing the pixel value of the pixel point into 0; otherwise, changing its pixel value to 1;
step S5, the image coordinate system of the coronal binarized image is a u-v coordinate system; wherein the v-axis is in the vertical direction; the u-axis is the direction perpendicular to the v-axis in the image;
counting the number of pixels along the v-axis of the coronal binarized image, namely: drawing a straight line L1 parallel to the u axis at the position where v is 1 in the coronal binarized image, and counting the number N1 of pixels of which the pixel value is 1, through which the straight line L1 passes; drawing a straight line L2 parallel to the u axis at the position where v is 2, and counting the number N2 of pixel points with the pixel value of 1 of the coronal binarized image through which the straight line L2 passes; according to the similarity, counting the number of pixels in the v-axis direction of the coronal binaryzation image is completed, and a plurality of discrete points in a coordinate system with the abscissa as the v-axis and the ordinate as the number N of pixel points are obtained; fitting the normal distribution of the discrete points to obtain a mean value mu after fitting the normal distribution1Sum variance σ1；
Mean value μ after fitting according to normal distribution1Sum variance σ1The following formula is adopted,obtaining a CT slice initial position downSlice entering the axial maximum intensity projection and a CT slice end position upSlice entering the axial maximum intensity projection:
upSlice＝μ1+kuσ1
downSlice＝μ1-kdσ1
wherein:
kuand kdThe empirical coefficients are all, and the preferred value is 2.56;
step S6, selecting all axial CT slices with slice serial numbers from down slice to up slice in the axial CT slice sequence obtained in the step S1 to form an axial CT slice sequence set;
carrying out axial maximum intensity projection on the axial CT slice sequence set to obtain an axial maximum intensity projection diagram;
therefore, in the present invention, the axial maximum intensity projection is performed only on the selected axial CT slices within the range from the down slice to the up slice, instead of performing the axial maximum intensity projection on all the axial CT slices, and the processing method has the following advantages: the selected axial CT slices in the range of the down slice to the up slice are tooth areas, and interference areas are obviously removed, so that the complexity of subsequent arch wire extraction can be reduced, and the automatic extraction precision of the subsequent arch wire is improved.
Step S7, counting the pixels of the axial maximum intensity projection graph to generate an axial maximum intensity projection histogram; the abscissa of the axial maximum intensity projection histogram is a pixel value of 0-256, and the ordinate is: the number of occurrences of each pixel value in the axial maximum intensity projection plot;
step S8, histogram regularization is performed on the axial maximum intensity projection histogram to obtain a histogram after regularization so that probability distributions of each pixel value of the histogram after regularization and the template histogram are consistent; wherein, the template histogram means: processing healthy oral tooth areas without implanted teeth and edentulous teeth in the mode of steps S1-S7 to generate an axial maximum intensity projection histogram;
in this step, histogram specification is performed using the following formula:
Figure BDA0003594067380000091
Figure BDA0003594067380000092
G(zq)＝sk
zq＝G(zq)-1
wherein:
G(zq) Is the probability value of the axial maximum intensity projection histogram obtained in step S7 in the range of pixel values 0 to q;
l represents the number of levels of pixels, 256;
pz(zi) Is the probability density function of the pixel value i of the axial maximum intensity projection histogram obtained in step S7;
skis the probability value of the template histogram in the pixel value range of 0-k;
pz(zj) Is the probability density function of the pixel value j of the template histogram;
G(zq)-1represents a pair G (z)q) Inverse operation to solve to a predetermined pixel value zq。
Step S9, carrying out gamma conversion on the specified histogram to obtain a gamma-converted picture;
in this step, gamma conversion is performed using the following formula:
S＝crγ
wherein:
s is the gamma transformed image pixel value;
c is a normal number, preferably 1;
γ is the intensity factor of the gamma transformation;
r is the image pixel value before gamma conversion.
Step S10, performing region growing on the gamma-transformed picture to obtain a new binary image;
step S11, performing two-dimensional connected domain analysis on the new binary image generated in step S10, and extracting a connected domain with the largest number of pixels as an arch region;
step S12, performing morphological closing operation on the dental arch area obtained in the step S11 to fill the hole, so as to obtain the dental arch area filled with the hole;
step S13, performing axis transformation on the dental arch area filled with the holes obtained in the step S12 to generate dental arch lines, and performing deburring operation on the generated dental arch lines to generate dental arch lines with burrs removed;
in step S14, the burr-removed dental arch line generated in step S13 is sampled at an equal arc length, and a cubic spline curve is fitted to the generated sample points to extract a final dental arch line.
The automatic extraction method of the dental arch line provided by the invention has the advantages that the whole dental arch line extraction process is automatically carried out, and the template is used for stipulating the histogram in the middle process, so that the parameters used in the processes of region growing, morphological operation and gamma conversion have strong universality. Therefore, the whole method for extracting the dental arch line has the advantages of strong real-time performance, high robustness, high accuracy and full automation.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and improvements can be made without departing from the principle of the present invention, and such modifications and improvements should also be considered within the scope of the present invention.

Claims (4)

1. An automatic extraction method of dental arch wires is characterized by comprising the following steps:
step S1, respectively performing coronal CT scanning and axial CT scanning on the tooth area of the head to respectively obtain a coronal CT slice sequence and an axial CT slice sequence; wherein, coronal direction means: from the posterior brain-scoop to the facial direction, i.e.: from the back to the front; the axial direction refers to the direction from top to bottom;
coronal CT slice sequence refers to: superposing the coronal CT slices in the front-back direction; each coronal CT slice is a vertical slice;
the axial CT slice sequence refers to: stacking all axial CT slices along the up-down direction; each axial CT slice is a horizontal slice;
step S2, performing coronal maximum intensity projection on the coronal CT slice sequence to obtain a coronal maximum intensity projection image; wherein, the coronal maximum intensity projection view is a two-dimensional plane view;
step S3, counting the pixels of the coronal maximum intensity projection graph to generate a coronal maximum intensity projection histogram; the abscissa of the coronal maximum intensity projection histogram is a pixel value of 0-256, and the ordinate is: the number of occurrences of each pixel value in the coronal maximum intensity projection graph;
fitting normal distribution to the coronal maximum intensity projection histogram to obtain a mean value mu after fitting normal distribution0Sum variance σ0(ii) a According to the mean value mu0Sum variance σ0Obtaining a binary threshold threshHold by adopting the following formula:
threshHold＝μ0+kσ0
wherein: k is an empirical coefficient;
a step S4 of performing binarization processing on the coronal maximum intensity projection map generated at the step S2 using the binarization threshold threshHold generated at the step S3, thereby generating a coronal binarized image;
the binarization method comprises the following steps: for each pixel point in the coronal maximum intensity projection graph, if the pixel value of each pixel point is smaller than a binarization threshold threshHold, changing the pixel value of each pixel point into 0; otherwise, changing the pixel value to 1;
step S5, the image coordinate system of the coronal binarized image is a u-v coordinate system; wherein the v-axis is in the vertical direction; the u-axis is the direction perpendicular to the v-axis in the image;
counting the number of pixels along the v-axis of the coronal binarized image, namely: drawing a plane parallel to the u axis at the position of v-1 in the coronal binary imageA straight line L1 of the line is obtained, and the number N1 of pixels of which the pixel value of the coronal binarized image is 1 and which the straight line L1 passes through is counted; drawing a straight line L2 parallel to the u axis at the position of v-2, and counting the number N2 of pixels with the pixel value of 1 of the crown direction binary image passed by the straight line L2; according to the similarity, counting the number of pixels in the v-axis direction of the coronal binaryzation image is completed, and a plurality of discrete points in a coordinate system with the abscissa as the v-axis and the ordinate as the number N of pixel points are obtained; fitting the normal distribution of the discrete points to obtain a mean value mu after fitting the normal distribution1Sum variance σ1；
Mean value μ after fitting according to normal distribution1Sum variance σ1Obtaining a CT slice initial position downslide slice entering the axial maximum intensity projection and a CT slice end position upslide entering the axial maximum intensity projection by adopting the following formula:
upSlice＝μ1+kuσ1
downSlice＝μ1-kdσ1
wherein:
kuand kdAre all empirical coefficients;
step S6, selecting all axial CT slices with slice serial numbers from down slice to up slice in the axial CT slice sequence obtained in the step S1 to form an axial CT slice sequence set;
carrying out axial maximum intensity projection on the axial CT slice sequence set to obtain an axial maximum intensity projection diagram;
step S7, counting the pixels of the axial maximum intensity projection graph to generate an axial maximum intensity projection histogram; the abscissa of the axial maximum intensity projection histogram is a pixel value of 0-256, and the ordinate is: the number of occurrences of each pixel value in the axial maximum intensity projection plot;
step S8, histogram regularization is performed on the axial maximum intensity projection histogram to obtain a histogram after regularization so that probability distributions of each pixel value of the histogram after regularization and the template histogram are consistent; wherein, the template histogram means: processing healthy oral tooth areas without implanted teeth and missing teeth in a mode of S1-S7 to generate an axial maximum intensity projection histogram;
step S9, carrying out gamma conversion on the specified histogram to obtain a picture after gamma conversion;
step S10, performing region growing on the gamma-transformed picture to obtain a new binary image;
step S11, performing two-dimensional connected domain analysis on the new binary image generated in step S10, and extracting a connected domain with the largest number of pixels as an arch region;
step S12, performing morphological closing operation on the dental arch area obtained in the step S11 to fill the hole, so as to obtain the dental arch area filled with the hole;
step S13, performing axis transformation on the dental arch area filled with the holes obtained in the step S12 to generate dental arch lines, and performing deburring operation on the generated dental arch lines to generate dental arch lines with burrs removed;
in step S14, the burr-removed dental arch line generated in step S13 is sampled at an equal arc length, and a cubic spline curve is fitted to the generated sample points to extract a final dental arch line.
2. The method for automatically extracting dental arch wire according to claim 1, wherein in step S2, the coronal maximum intensity projection is obtained by the following method:
setting each coronal CT slice in the coronal CT slice sequence to comprise n1 × m1 pixel points; wherein n1 is the number of rows and m1 is the number of columns;
irradiating a ray through the 1 st pixel point of each coronal CT slice in the coronal CT slice sequence, extracting the pixel value with the maximum gray value from each 1 st pixel point which passes through, and using the pixel value as the pixel value of the 1 st pixel point of the generated coronal maximum intensity projection graph;
irradiating 1 x 2 pixel points of each coronal CT slice in the coronal CT slice sequence by a ray, extracting a pixel value with the maximum gray value from each 1 x 2 pixel point which passes through, and taking the pixel value as the pixel value of the 1 x 2 pixel point of the generated coronal maximum intensity projection graph;
and so on
Irradiating a ray through the n1 m1 pixel point of each coronal CT slice in the coronal CT slice sequence, and extracting the pixel value with the maximum gray value from the n1 m1 pixel points which pass through the coronal CT slice sequence to be used as the pixel value of the n1 m1 pixel point of the generated coronal maximum intensity projection graph;
this results in a coronal maximum intensity projection.
3. The method for automatically extracting dental arch wire according to claim 1, wherein in step S8, histogram specification is performed using the following formula:
Figure FDA0003594067370000041
Figure FDA0003594067370000042
G(zq)＝sk
zq＝G(zq)-1
wherein:
G(zq) Is the probability value of the axial maximum intensity projection histogram obtained in step S7 in the range of pixel values 0 to q;
l represents the number of levels of pixels, 256;
pz(zi) Is the probability density function of the pixel value i of the axial maximum intensity projection histogram obtained in step S7;
skis the probability value of the template histogram in the pixel value range of 0-k;
pz(zj) Is the probability density function of the pixel value j of the template histogram;
G(zq)-1represents a pair G (z)q) Inverse operation, thereby resolving to the specified statePixel value z ofq。
4. The method for automatically extracting dental arch wire according to claim 1, wherein in step S9, gamma transformation is performed using the following formula:
s＝crγ
wherein:
s is the gamma transformed image pixel value;
c is a normal number;
γ is the intensity factor of the gamma transformation;
r is the image pixel value before gamma conversion.
CN202210386943.7A 2022-04-13 2022-04-13 Automatic extraction method of dental archwire Active CN114723765B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210386943.7A CN114723765B (en) 2022-04-13 2022-04-13 Automatic extraction method of dental archwire

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210386943.7A CN114723765B (en) 2022-04-13 2022-04-13 Automatic extraction method of dental archwire

Publications (2)

Publication Number Publication Date
CN114723765A true CN114723765A (en) 2022-07-08
CN114723765B CN114723765B (en) 2024-05-03

Family

ID=82244108

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210386943.7A Active CN114723765B (en) 2022-04-13 2022-04-13 Automatic extraction method of dental archwire

Country Status (1)

Country Link
CN (1) CN114723765B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108711177A (en) * 2018-05-15 2018-10-26 南方医科大学口腔医院 The fast automatic extracting method of volume data arch wire after a kind of oral cavity CBCT is rebuild
KR20190090663A (en) * 2018-01-25 2019-08-02 (주)바텍이우홀딩스 Method of automatically generating a curve corresponding to an dental arch shape on dental ct slice automatically selected from three dimensional dental ct image
CN112102495A (en) * 2020-09-15 2020-12-18 北京朗视仪器有限公司 Dental arch curved surface generation method based on CBCT image
WO2021250091A1 (en) * 2020-06-10 2021-12-16 Pearl 3D Method for automatic segmentation of a dental arch

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190090663A (en) * 2018-01-25 2019-08-02 (주)바텍이우홀딩스 Method of automatically generating a curve corresponding to an dental arch shape on dental ct slice automatically selected from three dimensional dental ct image
CN108711177A (en) * 2018-05-15 2018-10-26 南方医科大学口腔医院 The fast automatic extracting method of volume data arch wire after a kind of oral cavity CBCT is rebuild
WO2021250091A1 (en) * 2020-06-10 2021-12-16 Pearl 3D Method for automatic segmentation of a dental arch
CN112102495A (en) * 2020-09-15 2020-12-18 北京朗视仪器有限公司 Dental arch curved surface generation method based on CBCT image

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王奇峰;戴宁;郝国栋;俞青;廖文和;孙全平;: "患者个性化牙弓自动检测技术研究", 生物医学工程学杂志, no. 04, 25 August 2009 (2009-08-25), pages 27 - 30 *

Also Published As

Publication number Publication date
CN114723765B (en) 2024-05-03

Similar Documents

Publication Publication Date Title
CN112120810A (en) Three-dimensional data generation method of tooth orthodontic concealed appliance
US20210307882A1 (en) Method and system for evaluating implanting precision of an implant
CN113223010B (en) Method and system for multi-tissue full-automatic segmentation of oral cavity image
CN110889850B (en) CBCT tooth image segmentation method based on central point detection
CN109377534B (en) Nonlinear oral cavity CT panoramic image synthesis method capable of automatically sampling thickness detection
CA3114650A1 (en) Method and apparatus for generating three-dimensional model, device, and storage medium
CN112102495B (en) Dental arch surface generation method based on CBCT image
CN112515787B (en) Three-dimensional dental data analysis method
CN111260672B (en) Method for guiding and segmenting teeth by using morphological data
CN110610198A (en) Mask RCNN-based automatic oral CBCT image mandibular neural tube identification method
CN110363750B (en) Automatic extraction method for root canal morphology based on multi-mode data fusion
CN106214175B (en) Method and device for estimating three-dimensional tooth axis
US20220361992A1 (en) System and Method for Predicting a Crown and Implant Feature for Dental Implant Planning
CN108269294B (en) Oral CBCT image information analysis method and system
CN115457198A (en) Tooth model generation method and device, electronic equipment and storage medium
CN110619646B (en) Single tooth extraction method based on panorama
CN113786262B (en) Preparation method of dental crown lengthening operation guide plate
Lessard et al. Dental restoration using a multi-resolution deep learning approach
CN114723765A (en) Automatic extraction method of dental arch wire
CN117541672A (en) Method for automatically synthesizing panoramic image from oral cavity CBCT
Zhang et al. Jaw Segmentation from CBCT Images
US20220358740A1 (en) System and Method for Alignment of Volumetric and Surface Scan Images
Zhu et al. An algorithm for automatically extracting dental arch curve
CN114897786B (en) Automatic extraction method of mandibular nerve tube
Sotthivirat et al. Automatic detection of inferior alveolar nerve canals on CT images

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant