CN105405129A - Reconstruction method and device of medical image - Google Patents
Reconstruction method and device of medical image Download PDFInfo
- Publication number
- CN105405129A CN105405129A CN201510731302.0A CN201510731302A CN105405129A CN 105405129 A CN105405129 A CN 105405129A CN 201510731302 A CN201510731302 A CN 201510731302A CN 105405129 A CN105405129 A CN 105405129A
- Authority
- CN
- China
- Prior art keywords
- spinal cord
- point
- connected domain
- image
- intervertebral
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- 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
- G06T2207/30008—Bone
- G06T2207/30012—Spine; Backbone
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention provides a reconstruction method and device of a medical image. The method comprises the following steps: obtaining a body data of the medical image, extracting a target area in the body data, detecting the target area to obtain an intervertebral disc point and a spinal cord point, fitting a plane equation according to the intervertebral disc point and the spinal cord point, and reconstructing a first section image through adoption of the plane equation. The intervertebral disc point and the spinal cord point are obtained through image enhancement, morphological operation, organization structure information and the connected component analysis, image information is fully used to reconstruct the section image, calculation precision of a subsequent scanning parameter is guaranteed, and the quality of a diagnosis image is effectively improved.
Description
[technical field]
The present invention relates to field of medical image processing, particularly relate to a kind of method for reconstructing and device thereof of medical image.
[background technology]
Backbone medical image, such as backbone magnetic resonance image (MRI) has very important effect in the various spinal disease of diagnosis, such as vertebra degenerative dislocation, is to study intervertebral disc degeneration at present to sexually revise the simplest, accurate detection methods.In clinical, doctor diagnoses by observing cross-section, sagittal view picture, required cross-section image is the planform from vertebra, sagittal plane needs are as much as possible crosses backbone, and by spinal cord, and transversal section, need to be parallel to interverbebral disc, by analyzing different section to obtain more backbone information, improve diagnostic accuracy.
Determine cross-section and sagittal sweep parameter, scanning device utilizes these sweep parameters, and obtain cross-section and diagnostic image that is sagittal, the method for doctor is referred to as scan plan.The sagittal quality reconstructed determines the accuracy of transversal section sweep parameter.
Mainly contain about the method for reconstructing of spine image in scan plan in currently available technology:
A kind of interverbebral disc quantizes the method for mark.First the method is applied expert's point location and is carried out coarse segmentation based on the method for masterplate to spine regions, then Huffman change detection spinal cord is used, rear according to location criterion, along spinal cord direction of curve, each interverbebral disc of whole backbone is located, and provides quantification mark.The method by interpersonal mutual image slice now the most clearly image process, fail effectively to utilize complete image slice information, and limit by template, obtain scan image accuracy there is deviation.
CN1012018525A provides the localization method of a kind of vertebra and interverbebral disc.By the localization method according to vertebra marginal position determination vertebra and interverbebral disc position line, to improve locating speed and precision.The method fails to make full use of the effective information of osteogram picture, only positions according to interverbebral disc, can not effectively solve patient turn one's head, face upward the scanning scene such as first-class under the accurate reconstruction of positioning image.
[summary of the invention]
Technical matters to be solved by this invention is to provide a kind of method for reconstructing and device thereof of medical image, cross-section image information is made full use of for solving in scanning spondyle, rebuild vertebra cross sections image, obtain sweep parameter accurately, to improve quality and the precision of diagnostic image.
For solving above-mentioned timely problem, the invention provides a kind of method for reconstructing of medical image, comprising the following steps:
Obtain the volume data of medical image;
Extract the target area in described volume data;
Detect described target area, obtain intervertebral and make an inventory and spinal cord point;
Make an inventory and spinal cord point fit Plane equation according to described intervertebral;
Described plane equation is adopted to rebuild the first cross-section image.
Further, the method that described acquisition intervertebral is made an inventory comprises:
Obtain the two dimensional image of target area arbitrary cross-section;
Adopt two-dimensional line to strengthen described two dimensional image, obtain interverbebral disc candidate point;
Interverbebral disc candidate point described in pre-service;
Interverbebral disc candidate point according to three-dimensional communication domain analysis, removes interverbebral disc false positive, obtains intervertebral and makes an inventory.
Further, the false-positive method of described removal interverbebral disc, comprising:
Several three-dimensional communication territories are obtained according to described interverbebral disc candidate point;
Calculate the volume of each connected domain, if the volume of connected domain is positioned at threshold range, retain this connected domain, otherwise remove this connected domain, wherein described in body, the threshold range of connected domain volume is 100 to 2000 cubic millimeters;
Calculate first, second, and third direction of any connected domain; If the angle of third direction and place, head pin direction plane is less than threshold value A, then retains this connected domain, otherwise remove this connected domain;
Calculate the angle that any one connected domain central point and other any two connected domain central point line are formed, the connected domain adopting alternative manner to retain described angle to be less than the central point place of threshold value A;
Wherein, described first, second, and third direction is vertical between two.
Further, described alternative manner comprises:
Calculate the angle that any one connected domain central point and other any two connected domain central point line are formed;
The frequency that arbitrary central point that statistics angle is greater than threshold value A occurs, removes the connected domain at the maximum central point place of frequency of occurrence;
Repeat above-mentioned steps, till the angle formed until central point and other any two connected domain central point lines of any one connected domain is less than threshold value A; Wherein, described threshold value span is for being less than 45 degree.
Further, the two dimensional image of described arbitrary cross-section is identical section with described first section.
Further, the method for described acquisition spinal cord point comprises:
Adopt line to strengthen described target area, obtain spinal cord candidate point;
Spinal cord candidate point described in pre-service;
Analyze described spinal cord candidate point, remove spinal cord false positive, obtain spinal cord point.
Further, the false-positive method of described removal spinal cord comprises:
Judge according to spinal cord morphology, as spinal cord candidate point be positioned at as described in intervertebral to make an inventory the right side of region, then retain described spinal cord candidate point, otherwise get rid of this candidate point;
Several three-dimensional communication territories are obtained according to described spinal cord candidate point;
Along the arbitrary connected domain of described head pin angle detecting, obtain the connected domain of the maximum longitudinal length in head pin direction, be the region at described spinal cord point place.
For solving the problems of the technologies described above, the present invention also provides a kind of reconstructing device of medical image, comprising:
Volume data acquiring unit;
Target area extraction unit, for extracting target area in volume data;
Detecting unit, comprises intervertebral and to make an inventory acquiring unit and spinal cord point acquiring unit, makes an inventory and spinal cord point for obtaining intervertebral respectively;
Reconstruction unit, makes an inventory and spinal cord point fit Plane equation according to the described intervertebral that described detecting unit obtains, rebuilds the first cross-section image.
Further, described intervertebral acquiring unit of making an inventory comprises:
Cross-section image acquiring unit, for obtaining the two dimensional image of described target area arbitrary cross-section;
First candidate point acquiring unit, for obtaining interverbebral disc candidate point on described two dimensional image;
First analytic unit, for analyzing described interverbebral disc candidate point, removes interverbebral disc false positive, obtains intervertebral and makes an inventory; Described first analytic unit comprises the first false positive analytic unit.
Further, described spinal cord point acquiring unit comprises:
Second candidate point acquiring unit, for obtaining spinal cord candidate point in described target area;
Second false positive analytic unit, for removing interverbebral disc false positive, obtaining intervertebral and making an inventory.
The present invention contrasts prior art following beneficial effect; Be applicable to the various spinal curvature symptom such as serious SCOliOSiS, or patient such as to turn one's head at the improper scanning scene, highly versatile; Process of reconstruction gets involved without the need to user, and automatic reconstruction method speed is fast; Utilize whole image sequence information, stability and strong robustness, the continuity of scan plan can be ensured, improve the quality of diagnostic image.
[accompanying drawing explanation]
Fig. 1 is the schematic flow sheet of the method for reconstructing of medical image in the embodiment of the present invention;
Fig. 2 obtains the schematic flow sheet that intervertebral makes an inventory in the embodiment of the present invention;
Fig. 3 obtains intervertebral to make an inventory the result schematic diagram of candidate point in the embodiment of the present invention;
Fig. 4 is three principal direction schematic diagram in intervertebral disc space in the embodiment of the present invention;
Fig. 5 removes intervertebral to make an inventory the schematic flow sheet of false positive method in the embodiment of the present invention;
Fig. 6 is the schematic flow sheet obtaining spinal cord point in the embodiment of the present invention;
Fig. 7 is the result schematic diagram obtaining spinal cord point candidate point in the embodiment of the present invention;
Fig. 8 is the schematic flow sheet removing spinal cord point false positive method in the embodiment of the present invention;
Fig. 9 is the result schematic diagram obtaining the first cross-section image in the embodiment of the present invention;
Figure 10 is the schematic diagram of the reconstructing device of embodiment of the present invention traditional Chinese medicine image;
Figure 11 is the schematic diagram of the reconstructing device of another embodiment of the present invention traditional Chinese medicine image.
[embodiment]
Set forth a lot of detail in the following description so that fully understand the present invention.But the present invention can be much different from alternate manner described here to implement, those skilled in the art can when without prejudice to doing similar popularization when intension of the present invention, therefore the present invention is by the restriction of following public concrete enforcement.
Secondly, the present invention utilizes schematic diagram to be described in detail, and when describing the embodiment of the present invention in detail, for ease of illustrating, described schematic diagram is embodiment, and it should not limit the scope of protection of the invention at this.
Vertebra cross sections image is rebuild in order to solve in prior art, comprise backbone information as much as possible, to obtain sweep parameter accurately, improve the quality of diagnostic image, the present embodiment provides a kind of method for reconstructing of medical image, as shown in the schematic flow sheet of the image rebuilding method in Fig. 1 embodiment of the present invention, described method comprises:
1) volume data of medical image is obtained; Described medical image can be the magnetic resonance image (MRI) that medical imaging devices obtains, radioscopic image, PET-CT image etc., and the present invention does not do concrete restriction to this, preferred backbone magnetic resonance image (MRI) in the present embodiment; Described volume data is generally the sequence image that the coarse scanning carried out for obtaining accurate scanning parameter in scan plan obtains tens layers or tens layers two dimensional image formation.
Generally speaking, in magnetic resonance image (MRI), adipose tissue is highlighted state, so for spine regions, interverbebral disc is much bright compared with vertebral body, the brightness of the celiolymph near brain is also higher, the direction brightness downward along with spinal cord is dimmed gradually, spinal cord is gray in magnetic resonance image (MRI), therefore dorsal column nucleus magnetic resonance image (MRI) plays vital effect in diagnosis spinal disease, simultaneously, it can also help the therapeutic advance after assessing spinal surgery, therefore preferentially, carried out the reconstruction of sagittal view picture by backbone magnetic resonance image (MRI) in the present embodiment, according to the backbone information in cross-section image, obtain sweep parameter accurately, improve the accuracy of diagnostic image.
In the present embodiment, for the method for reconstructing of image in scan plan, the low-resolution image that imaging device coarse scanning obtains obtains sweep parameter by reconstruction algorithm, to improve the quality of diagnostic image, the sagittal plane reconstructed such as, be partitioned into interverbebral disc, obtain the direction of interverbebral disc, and then determine transversal section sweep parameter, thus obtain the sweep parameter of each section.
2) target area in described volume data is extracted; In the present embodiment, volume data is for backbone magnetic resonance image (MRI).Human spine borrows ligament, joint and interverbebral disc to be formed by connecting by 33 pieces of vertebras, forms a yielding backbone cylinder.Vertebrae be divided into cervical vertebra, thoracic vertebrae, lumbar vertebrae, rumpbone and coccyx.
With under patient coordinate system (for sagittal view picture, the X-direction of image is decided to be vertical direction, the Y of image is defined as head-to-toe direction, definition direction is from left to right Z axis), target area is cervical region is example, detect cervical region in described backbone magnetic resonance image (MRI), detect neck position in space particularly, intercept out the subregion comprising cervical vertebra.Concrete obtain manner is: first, asks maximal projection to all sagittal view pictures, obtains the 2D sagittal image after projecting, i.e. maximum-density projection image (MIP image).Then utilize threshold value remove background and obtain largest connected territory, obtain the template of image, i.e. binary image, wherein human region is gray-scale value 1, and the gray-scale value in other region is 0.In Y direction, search pattern from top to bottom, detect first be not 0 pixel position be position, the crown.Moving down 50mm from the crown, is 0 template-setup, to eliminate head point region to the impact of successive image process.Continue, each pixel that template is not 0 is traveled through in the Y-axis direction, find out the width that X-direction cope match-plate pattern is not 0 region, because neck area is the narrowest in the X direction, so the Yc that width is the narrowest (central point) the i.e. Y-coordinate of corresponding neck, the Xc that widthwise central is corresponding is X-coordinate corresponding to neck.According to the Xc obtained, Yc intercepts out coronal image, removes the center Zc that background obtains human body width corresponding to Y-coordinate, is the Z-direction center point coordinate that neck area is corresponding.Last is cube reference point with Xc, Yc, Zc, intercepts out the cube comprising cervical vertebra subregion.
It should be noted that, the present embodiment does not do concrete restriction to the specific implementation means extracting target area, only needs to extract the target area of such as cervical vertebra.
3) detect described target area, obtain intervertebral and make an inventory and spinal cord point;
In the present embodiment, described intervertebral makes an inventory acquisition methods as shown in Figure 2:
First, obtain the two dimensional image of target area arbitrary cross-section, the volume data normally sequence image that forms of tens layers or tens layers two dimensional image as previously mentioned, for the sagittal plane magnetic resonance image (MRI) of cervical region in the present embodiment, all sagittal two dimensional images in the described neck area that in acquisition, step is extracted.
Then, line Enhancement Method is adopted to strengthen interverbebral disc candidate point in described two dimensional image, particularly, due in the X direction, interverbebral disc in wire, therefore to every layer of sagittal view picture, utilizes 2D line Enhancement Method to strengthen interverbebral disc candidate point on every tomographic image in sagittal view picture;
Interverbebral disc candidate point described in pre-service: adopt morphological operation, such as, kernel function in X-direction, removes noise point, such as discrete isolated point, or the candidate point in the Y-axis direction in wire such as spinal cord.Particularly, because the length of noise point on two-dimentional sagittal view picture in X-direction such as such as spinal cord are shorter, therefore setting threshold value, preferred threshold value is 5 millimeters, remove the region of the pixel formation being less than 5 millimeters, thus remove the significantly noise such as spinal cord, isolated point, obtain the result schematic diagram of interverbebral disc candidate point as shown in Figure 3.
Then, adopt interverbebral disc candidate point described in three-dimensional communication domain analysis, remove interverbebral disc false positive, obtain intervertebral and make an inventory.Wherein, described false positive refers to and because of various reasons the pathology detection not possessing positive symptom is gone out positive result.In the present invention, described interverbebral disc false positive is that line strengthens and after pretreatment operation, the non-intervertebral that obtains is made an inventory, such as part spinal cord point; Particularly, the false-positive method of described removal interverbebral disc as shown in Figure 4, comprises the steps:
The interverbebral disc candidate point utilizing abovementioned steps to obtain forms several three-dimensional communication territories;
Remove interverbebral disc false positive according to the architectural feature that interverbebral disc is in the form of annular discs in space, concrete steps are as follows:
A) calculate the volume of each connected domain, remove the connected domain not meeting human intervertebral disc volume size.For example, for X, Y and Z tripartite upwards resolution be the image of 1 millimeter, general human intervertebral disc magnitude range should be 100 to 2000 millimeters, if the volume of connected domain is positioned at this threshold range, retains this connected domain, otherwise removes this connected domain.
B) any connected domain first, second, and third direction is calculated; Analyze principal direction and whether meet a morphological feature for vertebra dish.Because interverbebral disc is in the form of annular discs in space, and along X-axis parallel or left side be less than 45 degree downward-sloping, judge according to this morphological feature, if the angle of connected domain third direction and place, head pin direction plane is less than threshold value A, then retain this connected domain, otherwise remove this connected domain.Wherein in space three principal directions of disk as shown in Figure 4, three directions are vertical between two in space.
C) angle that any one connected domain central point and other any two connected domain central point line are formed is calculated; Because interverbebral disc presents tubular structure in space, so central point link group angle should be less than threshold value A, therefore interverbebral disc false positive can be removed by analytic centre's corner dimension, particularly, adopt the alternative manner shown in Fig. 5, remove the connected domain not meeting structural information feature successively, comprise the steps:
The angle that any one connected domain central point and other any two connected domain central point line are formed; The frequency that arbitrary central point that statistics angle is greater than threshold value A occurs, removes the connected domain at the maximum central point place of frequency of occurrence; Repeat above-mentioned steps, till the angle formed until any one connected domain central point and other any two connected domain central point lines is less than threshold value A; Wherein said threshold value A span is for being less than 45 degree.
The present embodiment, by the morphology synthetic determination of the volume of connected domain, principal direction characteristic and space tubular structure, makes full use of interverbebral disc morphological characteristic and removes interverbebral disc false positive, obtain stability that intervertebral makes an inventory and robustness high.It should be noted that and can also remove interverbebral disc false positive by other according to interverbebral disc morphological feature, whether be in space disc structure, the present embodiment does not do concrete restriction to this if such as detecting.
In the present embodiment, described spinal cord point acquisition methods as shown in Figure 6, comprises the steps:
Adopt line to strengthen described target area, obtain spinal cord candidate point; Because spinal cord in linear structure, so adopt three-dimensional line Enhancement Method, obtains spinal cord candidate point in the volume data of described target area;
Then, spinal cord candidate point described in pre-service; Because spinal cord is in linear structure in the volume data of described target area, the main morphological operation that adopts removes the pixel that in isolated discrete point or Y direction, length is shorter, and such as, in space, length is less than the connected domain of 3mm.Obtain pretreated spinal cord candidate point as shown in Figure 7.
Adopt spinal cord candidate point described in three-dimensional communication domain analysis, remove spinal cord false positive, obtain spinal cord point.Described spinal cord false positive is the non-spinal cord point obtained after line strengthens operation, such as, discrete point in image.
The false-positive method of described removal spinal cord as shown in Figure 8, comprises the steps:
Several three-dimensional communication territories are obtained according to described spinal cord candidate point;
Judge according to spinal cord morphology, remove spinal cord false positive, concrete steps are as follows:
According in sagittal view picture, as spinal cord candidate point be positioned at above-mentioned steps obtain as described in intervertebral to make an inventory the right side of region, then retain described spinal cord candidate point, otherwise get rid of this candidate point;
Then, along the arbitrary connected domain of described head pin angle detecting, because in myelogram picture, spinal cord is positioned at vertebra, in oval tubulose, extends from top to bottom along Y direction, therefore obtain the connected domain of head pin direction maximum radial length, be the region at described spinal cord point place.
4) make an inventory and spinal cord point fit Plane equation according to described intervertebral; Particularly, adopt least square fitting plane equation Ax+By+Cz+D=0, wherein coefficient A, the intervertebral that B, C, D, x.y.z are respectively obtained is made an inventory and the volume coordinate of spinal cord point.
5) described plane equation is adopted to rebuild the first cross-section image.Particularly, cut section in described medical image volume data according to described equation, be the first cross-section image.Such as, select in the present embodiment in backbone magnetic resonance image (MRI) and intercept sagittal plane, obtain the result schematic diagram of the first cross-section image as shown in Figure 9, described sagittal plane makes full use of the image information that all coarse scannings obtain, to make an inventory the optimum sagittal view picture obtained with the plane equation of spinal cord point matching according to intervertebral, make full use of spine form information, more backbone information can be comprised.
Be described in detail by the method for reconstructing of specific embodiment to medical image disclosed by the invention of the sagittal reconstruction method of embodiment and backbone magnetic resonance image (MRI) above, by utilizing all coarse scanning image informations, extraction spinal cord point and intervertebral make an inventory fit Plane equation to rebuild optimum sagittal view picture (i.e. the first cross-section image), described method for reconstructing stability and robustness stronger, highly versatile, be applicable to the various spinal curvature symptom such as various serious SCOliOSiSs, or patient such as to turn one's head at the improper scanning scene.In order to make those skilled in the art understand better and realize the present invention, below by way of specific embodiment, system corresponding to said method is described.
The present invention also provides a kind of method for reconstructing of medical image, as shown in Figure 10 and Figure 11:
Described device comprises volume data acquiring unit, for obtaining the magnetic resonance image (MRI) that various medical imaging devices obtains, radioscopic image, the volume datas such as PET-CT image; The present embodiment is preferably backbone magnetic resonance image (MRI).
Target area extraction unit, for extracting target area in volume data, selects target area to be cervical region in backbone magnetic resonance image (MRI) in the present embodiment.
Detecting unit, comprises intervertebral and to make an inventory acquiring unit and spinal cord point acquiring unit, makes an inventory and spinal cord point for obtaining intervertebral respectively.
Described intervertebral acquiring unit of making an inventory comprises cross-section image acquiring unit, for obtaining the two dimensional image of described target area arbitrary cross-section, and the magnetic resonance sagittal view picture of the cervical region such as, adopted in the present embodiment; With the first candidate point acquiring unit, the described two dimensional image after strengthening online carries out pre-service and obtain interverbebral disc candidate point; And first analytic unit, for analyzing described interverbebral disc candidate point, removing interverbebral disc false positive, obtaining intervertebral and making an inventory; Described first analytic unit comprises the first false positive analytic unit, by the morphological feature utilizing interverbebral disc in the form of annular discs in space, analyzes described interverbebral disc candidate point, removes interverbebral disc false positive, obtains intervertebral and makes an inventory.
Described spinal cord point acquiring unit comprises the second candidate point acquiring unit, for strengthening described target area online, and carries out pre-service, obtains spinal cord candidate point; And the second false positive analytic unit, carry out morphology judgement with the relative position of interverbebral disc in space according to spinal cord; And according to the morphological feature of spinal cord from top to bottom in wire on space Y direction of principal axis, obtain the connected domain of the maximum longitudinal length in head pin direction, be the region at described spinal cord point place.
Reconstruction unit, make an inventory and spinal cord point fit Plane equation according to the described intervertebral that described detecting unit obtains, rebuild the first cross-section image, adopt least square fitting plane equation Ax+By+Cz+D=0 to cut section in described medical image volume data according to described square of journey in the present embodiment and rebuild cervical vertebra sagittal view picture (being described first cross-section image).
In sum, the invention provides a kind of method for reconstructing and device thereof of medical image, by utilizing all image informations in volume data, the i.e. a series of images sequence of imaging device coarse scanning acquisition, according to the morphological feature of target area, automatic extraction spinal cord point and intervertebral are made an inventory, and fit Plane equation rebuilds the first cross-section image, fast according to the sweep parameter speed that described first cross-section image obtains, precision is high, strong robustness, the quality of the diagnostic image that scan plan is obtained and precision are able to effective raising.
Although the present invention discloses as above with preferred embodiment; so itself and be not used to limit the present invention, any those skilled in the art, without departing from the spirit and scope of the present invention; when doing a little amendment and perfect, therefore protection scope of the present invention is when being as the criterion of defining with claims.
Claims (10)
1. a method for reconstructing for medical image, is characterized in that comprising the following steps:
Obtain the volume data of medical image;
Extract the target area in described volume data;
Detect described target area, obtain intervertebral and make an inventory and spinal cord point;
Make an inventory and spinal cord point fit Plane equation according to described intervertebral;
Described plane equation is adopted to rebuild the first cross-section image.
2. the method for reconstructing of medical image as claimed in claim 1, it is characterized in that, the method that described acquisition intervertebral is made an inventory comprises:
Obtain the two dimensional image of target area arbitrary cross-section;
Adopt line to strengthen described two dimensional image, obtain interverbebral disc candidate point;
Interverbebral disc candidate point described in pre-service;
Interverbebral disc candidate point according to three-dimensional communication domain analysis, removes interverbebral disc false positive, obtains intervertebral and makes an inventory.
3. the method for reconstructing of medical image as claimed in claim 2, it is characterized in that, the false-positive method of described removal interverbebral disc, comprising:
Several three-dimensional communication territories are obtained according to described interverbebral disc candidate point;
Calculate the volume of each connected domain, if the volume of connected domain is positioned at threshold range, retain this connected domain, otherwise remove this connected domain, the threshold range of wherein said connected domain volume is 100 to 2000 cubic millimeters;
Calculate first, second, and third direction of any connected domain; If the angle of third direction and place, head pin direction plane is less than threshold value A, then retains this connected domain, otherwise remove this connected domain;
Calculate the angle that the central point of any one connected domain and other any two connected domain central point line are formed, employing alternative manner retains the connected domain that described angle is less than the central point place of threshold value A, wherein, described first, second, and third direction is vertical between two.
4. the method for reconstructing of medical image as claimed in claim 3, it is characterized in that, described alternative manner comprises:
Calculate the angle that any one connected domain central point and other any two connected domain central point line are formed;
The frequency that arbitrary central point that statistics angle is greater than threshold value A occurs, removes the connected domain at the maximum central point place of frequency of occurrence;
Repeat above-mentioned steps, till the angle formed until any one connected domain central point and other any two connected domain central point lines is less than threshold value A; Wherein, described threshold value A span is for being less than 45 degree.
5. the method for reconstructing of medical image as claimed in claim 2, it is characterized in that, the two dimensional image of described arbitrary cross-section is identical section with described first section.
6. the method for reconstructing of medical image as claimed in claim 1, it is characterized in that, the method for described acquisition spinal cord point comprises:
Adopt line to strengthen described target area, obtain spinal cord candidate point;
Spinal cord candidate point described in pre-service;
Analyze described spinal cord candidate point, remove spinal cord false positive, obtain spinal cord point.
7. the method for reconstructing of medical image as claimed in claim 6, it is characterized in that, the false-positive method of described removal spinal cord comprises:
Judge according to spinal cord morphology, as spinal cord candidate point be positioned at as described in intervertebral to make an inventory the right side of region, then retain described spinal cord candidate point, otherwise get rid of this candidate point;
Several three-dimensional communication territories are obtained according to described spinal cord candidate point;
Along the arbitrary connected domain of described head pin angle detecting, obtain the connected domain of the maximum longitudinal length in head pin direction, be the region at described spinal cord point place.
8. a reconstructing device for medical image, is characterized in that, comprising:
Volume data acquiring unit;
Target area extraction unit, for extracting target area in volume data;
Detecting unit, comprises intervertebral and to make an inventory acquiring unit and spinal cord point acquiring unit, makes an inventory and spinal cord point for obtaining intervertebral respectively;
Reconstruction unit, makes an inventory and spinal cord point fit Plane equation according to the described intervertebral that described detecting unit obtains, rebuilds the first cross-section image.
9. the reconstructing device of medical image as claimed in claim 8, is characterized in that, described intervertebral acquiring unit of making an inventory comprises:
Cross-section image acquiring unit, for obtaining the two dimensional image of described target area arbitrary cross-section;
First candidate point acquiring unit, for obtaining interverbebral disc candidate point on described two dimensional image;
First analytic unit, for analyzing described interverbebral disc candidate point, removes interverbebral disc false positive, obtains intervertebral and makes an inventory; Described first analytic unit comprises the first false positive analytic unit.
10. the reconstructing device of medical image as claimed in claim 8, it is characterized in that, described spinal cord point acquiring unit comprises:
Second candidate point acquiring unit, for obtaining spinal cord candidate point in described target area;
Second false positive analytic unit, for removing interverbebral disc false positive, obtaining intervertebral and making an inventory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510731302.0A CN105405129A (en) | 2015-10-31 | 2015-10-31 | Reconstruction method and device of medical image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510731302.0A CN105405129A (en) | 2015-10-31 | 2015-10-31 | Reconstruction method and device of medical image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105405129A true CN105405129A (en) | 2016-03-16 |
Family
ID=55470596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510731302.0A Pending CN105405129A (en) | 2015-10-31 | 2015-10-31 | Reconstruction method and device of medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105405129A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106600609A (en) * | 2016-11-30 | 2017-04-26 | 上海联影医疗科技有限公司 | Spine partition method and system in medical image |
| CN106683085A (en) * | 2016-12-23 | 2017-05-17 | 浙江大学 | CT image spine and spinal dura mater automation detection method |
| CN106709925A (en) * | 2016-12-30 | 2017-05-24 | 上海联影医疗科技有限公司 | Method and device for locating vertebral block in medical image |
| CN109523561A (en) * | 2018-12-19 | 2019-03-26 | 睿仁佳心(上海)科技有限公司 | Muscle and fat image dividing method in automatic abdomen |
| CN109903268A (en) * | 2019-01-24 | 2019-06-18 | 刘星宇 | It determines the method for the Exception Type of spine image collection and calculates equipment |
| CN110992243A (en) * | 2019-10-29 | 2020-04-10 | 平安科技（深圳）有限公司 | Intervertebral disc section image construction method and device, computer equipment and storage medium |
| CN111063424A (en) * | 2019-12-25 | 2020-04-24 | 上海联影医疗科技有限公司 | Intervertebral disc data processing method and device, electronic equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1766930A (en) * | 2004-08-20 | 2006-05-03 | 通用电气公司 | Method and apparatus for metal artifact reduction in three-dimensional X-ray image reproduction |
| US20060110017A1 (en) * | 2004-11-25 | 2006-05-25 | Chung Yuan Christian University | Method for spinal disease diagnosis based on image analysis of unaligned transversal slices |
| CN101836235A (en) * | 2007-08-16 | 2010-09-15 | 皇家飞利浦电子股份有限公司 | Imaging method for sampling a cross-section plane in a three-dimensional (3d) image data volume |
| CN102018525A (en) * | 2009-09-23 | 2011-04-20 | 上海西门子医疗器械有限公司 | Method and device for positioning vertebras and intervertebral discs |
| CN102663820A (en) * | 2012-04-28 | 2012-09-12 | 清华大学 | Three-dimensional head model reconstruction method |
| US20120275670A1 (en) * | 2011-04-28 | 2012-11-01 | Medtronic, Inc. | Image-based analysis of implantable medical device positioning |
| CN103295263A (en) * | 2012-03-01 | 2013-09-11 | 上海理工大学 | Spine 3D modeling method based on cone beam virtual rotation |
| CN103976756A (en) * | 2014-05-21 | 2014-08-13 | 周勇 | Real-time three-dimensional reconstruction method in spine posterior approach operation |
| CN103976790A (en) * | 2014-05-21 | 2014-08-13 | 周勇 | Real-time evaluation and correction method in spine posterior approach operation |
| CN104346799A (en) * | 2013-08-01 | 2015-02-11 | 上海联影医疗科技有限公司 | Method for extracting spinal marrow in CT (Computed Tomography) image |
| CN104851107A (en) * | 2015-06-08 | 2015-08-19 | 武汉联影医疗科技有限公司 | Vertebra positioning method based on CT sequence image |
-
2015
- 2015-10-31 CN CN201510731302.0A patent/CN105405129A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1766930A (en) * | 2004-08-20 | 2006-05-03 | 通用电气公司 | Method and apparatus for metal artifact reduction in three-dimensional X-ray image reproduction |
| US20060110017A1 (en) * | 2004-11-25 | 2006-05-25 | Chung Yuan Christian University | Method for spinal disease diagnosis based on image analysis of unaligned transversal slices |
| CN101836235A (en) * | 2007-08-16 | 2010-09-15 | 皇家飞利浦电子股份有限公司 | Imaging method for sampling a cross-section plane in a three-dimensional (3d) image data volume |
| CN102018525A (en) * | 2009-09-23 | 2011-04-20 | 上海西门子医疗器械有限公司 | Method and device for positioning vertebras and intervertebral discs |
| US20120275670A1 (en) * | 2011-04-28 | 2012-11-01 | Medtronic, Inc. | Image-based analysis of implantable medical device positioning |
| CN103295263A (en) * | 2012-03-01 | 2013-09-11 | 上海理工大学 | Spine 3D modeling method based on cone beam virtual rotation |
| CN102663820A (en) * | 2012-04-28 | 2012-09-12 | 清华大学 | Three-dimensional head model reconstruction method |
| CN104346799A (en) * | 2013-08-01 | 2015-02-11 | 上海联影医疗科技有限公司 | Method for extracting spinal marrow in CT (Computed Tomography) image |
| CN103976756A (en) * | 2014-05-21 | 2014-08-13 | 周勇 | Real-time three-dimensional reconstruction method in spine posterior approach operation |
| CN103976790A (en) * | 2014-05-21 | 2014-08-13 | 周勇 | Real-time evaluation and correction method in spine posterior approach operation |
| CN104851107A (en) * | 2015-06-08 | 2015-08-19 | 武汉联影医疗科技有限公司 | Vertebra positioning method based on CT sequence image |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106600609A (en) * | 2016-11-30 | 2017-04-26 | 上海联影医疗科技有限公司 | Spine partition method and system in medical image |
| CN106683085A (en) * | 2016-12-23 | 2017-05-17 | 浙江大学 | CT image spine and spinal dura mater automation detection method |
| CN106709925A (en) * | 2016-12-30 | 2017-05-24 | 上海联影医疗科技有限公司 | Method and device for locating vertebral block in medical image |
| CN109523561A (en) * | 2018-12-19 | 2019-03-26 | 睿仁佳心(上海)科技有限公司 | Muscle and fat image dividing method in automatic abdomen |
| CN109523561B (en) * | 2018-12-19 | 2021-04-02 | 睿佳(武汉)软件科技有限公司 | Automatic intra-abdominal muscle and fat image segmentation method |
| CN109903268A (en) * | 2019-01-24 | 2019-06-18 | 刘星宇 | It determines the method for the Exception Type of spine image collection and calculates equipment |
| CN109903268B (en) * | 2019-01-24 | 2021-05-04 | 刘星宇 | Method and computing device for determining abnormal type of spine image set |
| CN110992243A (en) * | 2019-10-29 | 2020-04-10 | 平安科技（深圳）有限公司 | Intervertebral disc section image construction method and device, computer equipment and storage medium |
| CN110992243B (en) * | 2019-10-29 | 2023-12-22 | 平安科技（深圳）有限公司 | Intervertebral disc cross-section image construction method, device, computer equipment and storage medium |
| CN111063424A (en) * | 2019-12-25 | 2020-04-24 | 上海联影医疗科技有限公司 | Intervertebral disc data processing method and device, electronic equipment and storage medium |
| WO2021129842A1 (en) * | 2019-12-25 | 2021-07-01 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for medical imaging of intervertebral discs |
| CN111063424B (en) * | 2019-12-25 | 2023-09-19 | 上海联影医疗科技股份有限公司 | Intervertebral disc data processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105405129A (en) | Reconstruction method and device of medical image | |
| CN107595387B (en) | Spine image generation system based on ultrasonic rubbing technology and spine operation navigation and positioning system | |
| Peng et al. | Automated vertebra detection and segmentation from the whole spine MR images | |
| DeKraker et al. | Unfolding the hippocampus: An intrinsic coordinate system for subfield segmentations and quantitative mapping | |
| US8953865B2 (en) | Medical image processing device and medical image processing method | |
| Law et al. | Intervertebral disc segmentation in MR images using anisotropic oriented flux | |
| CN107203997B (en) | Left and right semi-brains segmentation method | |
| US9241634B2 (en) | Analytic morphomics: high speed medical image automated analysis method | |
| US20150248593A1 (en) | Image processing device and spinal canal evaluation method | |
| US8139837B2 (en) | Bone number determination apparatus and recording medium having stored therein program | |
| Shi et al. | An efficient method for segmentation of MRI spine images | |
| CN103440665A (en) | Automatic segmentation method of knee joint cartilage image | |
| WO2008014082A2 (en) | Anatomic orientation in medical images | |
| CN109360213B (en) | Automatic vertebral body identification method based on spine ultrasonic coronal plane image | |
| CN111374712B (en) | Ultrasonic imaging method and ultrasonic imaging equipment | |
| CN103793905B (en) | Determine the method and device in brain image Coronal direction | |
| Chuang et al. | Efficient triple output network for vertebral segmentation and identification | |
| JP2009207727A (en) | Vertebral body position determining device, method, and program | |
| Hess et al. | Deep learning for multi-tissue segmentation and fully automatic personalized biomechanical models from BACPAC clinical lumbar spine MRI | |
| EP1691687A1 (en) | Automatic identification of the anterior and posterior commissure landmarks | |
| CN106709925A (en) | Method and device for locating vertebral block in medical image | |
| CN105339804A (en) | Cortical bone segmentation from MR Dixon data | |
| Kapouleas | Automatic detection of white matter lesions in magnetic resonance brain images | |
| Xu et al. | RUnT: A network combining residual U-Net and transformer for vertebral edge feature fusion constrained spine CT image segmentation | |
| JP2020005889A (en) | Magnetic resonance imaging apparatus with auto-positioning function, method of controlling magnetic resonance imaging apparatus, and program for auto-setting of imaging section |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160316 |