CN118314215A - Three-dimensional medical image mark point ordering method, system, electronic equipment and storage medium - Google Patents
Three-dimensional medical image mark point ordering method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN118314215A CN118314215A CN202410395801.6A CN202410395801A CN118314215A CN 118314215 A CN118314215 A CN 118314215A CN 202410395801 A CN202410395801 A CN 202410395801A CN 118314215 A CN118314215 A CN 118314215A
- Authority
- CN
- China
- Prior art keywords
- distance
- matrix
- row
- matched
- medical image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000011159 matrix material Substances 0.000 claims description 124
- 239000003550 marker Substances 0.000 claims description 16
- 238000012163 sequencing technique Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 238000002591 computed tomography Methods 0.000 claims description 7
- 238000002595 magnetic resonance imaging Methods 0.000 claims description 7
- 239000002184 metal Substances 0.000 claims description 3
- 238000002600 positron emission tomography Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 2
- 238000002474 experimental method Methods 0.000 description 3
- 230000005587 bubbling Effects 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- 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
- G06T2207/30244—Camera pose
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses a three-dimensional medical image mark point ordering method, a three-dimensional medical image mark point ordering system, electronic equipment and a storage medium. The method can quickly find the corresponding relation between the marking points on the calibration plate in the physical space and the marking points in the image, and the sorting is completed. The method has high efficiency, high success rate and short time.
Description
Technical Field
The invention belongs to the technical field of medical image processing, and relates to a three-dimensional medical image mark point ordering method, a system, electronic equipment and a storage medium.
Background
In a surgical robot or surgical navigation system, it is necessary to implant a plurality of marker points (typically steel balls) in a calibration plate and then scan a three-dimensional medical image. By the coordinates of the marking points relative to the calibration plate and the coordinates of the corresponding marking points in the image, a matching relationship of the image space and the physical space can be calculated, thereby mapping the surgical plan in the image to the real physical space and executing the surgical plan. It is important to find the correspondence between the mark points on the calibration plate in the physical space and the mark points in the image. The existing method needs to carry out complex similarity analysis, and has high time consumption and low success rate. For example, the automatic identification method of the marker point sequence in the three-dimensional medical image disclosed in the patent document CN107481276a also needs to generate a large number of triangles, and compares the similarity of the triangles, so that the complexity and time of the algorithm are greatly increased.
Disclosure of Invention
In order to improve the technical problems, the invention provides a three-dimensional medical image marking point ordering method, which comprises the following steps:
Designing a calibration plate, and scanning a three-dimensional medical image;
comparing the distance matrix N' to be matched with the standard distance template matrix N, and finding a row with the same similarity, wherein the row number is the actual row number of the marking point in the three-dimensional medical image in the physical space of the calibration plate; repeating the above process to find the actual line numbers of all the marking points in the three-dimensional medical image in the physical space of the calibration plate; finishing the sorting of the mark points;
The standard distance template matrix N is obtained by calculating the distance from each marking point to the rest marking points in the physical space of the calibration plate and sequencing and adding difference dimension information;
the distance from each marking point of the three-dimensional medical image to the rest marking points is calculated, and the distance matrix N' to be matched is obtained through sequencing and adding difference dimension information;
The same judging standard of the similarity is N (i, j) -0.2mm < N' (i, j) < N (i, j) +0.2mm, and i, j are row serial numbers and column serial numbers respectively.
According to embodiments of the present invention, the three-dimensional medical images include, but are not limited to, computed tomography (Computed Tomography, CT) images, magnetic resonance imaging (MagneticResonance Imaging, MRI), positron emission tomography (Positron Emission ComputedTomography, PET) and the like three-dimensional medical images.
According to an embodiment of the invention, the marking points on the calibration plate are spherical metal, preferably fixed on the calibration plate according to the design position.
According to an embodiment of the present invention, the total number of the marking points a is not less than 3, for example, 4, 5, 6 or more. The condition that the coordinates of the mark points need to satisfy is that the standard distance template matrix N generated by the points must satisfy: each row N (i) (i=0, 1, …, a-1) of N is different from all other rows N (p) (p=0, 1, …, a-1, and p+.i), the similarity is the same, the same determination method is N (p, j) -0.2mm < N (i, j) < N (p, j) +0.2mm, j is the column number, j=0, 1, …, a-1.
In one embodiment, 5 marker points are used, the coordinates of the 5 marker points within the physical space of the calibration plate being (0 mm ), (10 mm,0 mm), (30 mm,0 mm), (0 mm,20 mm), (20 mm ), respectively.
According to an embodiment of the present invention, the standard distance template matrix N is obtained by:
s1, calculating the distance D ij (j=0, 1,2, …, a-2) from each marking point P i (i=0, 1,2, …, a-1) of the physical space of the calibration plate to the rest marking points to form a distance template intermediate matrix M 1 of a row a-1 column;
S2, sorting each row of the distance template intermediate matrix M 1 from large to small or from small to large by using an bubbling sorting method, and updating the updated result into a distance template intermediate matrix M 2;
S3, calculating the difference value between the maximum value and the minimum value in each row of the distance template intermediate matrix M 2, adding the difference value into the last row to form a distance template matrix N with a row and a column as a standard distance template matrix.
According to an embodiment of the present invention, the distance matrix to be matched N' is obtained by:
S1'. Each marking point Q i (i=0, 1,2, …, a-2) in the three-dimensional medical image is calculated to obtain a distance D ' ij (j=0, 1,2, …, a-1) from the rest marking points, and a distance to be matched middle matrix M ' 1 of a row a-1 column is formed;
S2', sorting each row of the distance to be matched intermediate matrix M ' 1 from large to small or from small to large, and updating the distance to be matched intermediate matrix M ' 2 by using the updated result;
S3', calculating the difference value between the maximum value and the minimum value in each row of the intermediate matrix M ' 2 to be matched, and adding the difference value into the last row to form a row a column of the intermediate matrix M ' to be matched.
According to an embodiment of the present invention, the ordering rules of the step S2 and the step S2' are the same.
According to an embodiment of the present invention, the comparison between the distance matrix N' to be matched and the standard distance template matrix N includes: the first row of the distance matrix N' to be matched is compared in turn with the first to a rows of the distance template matrix N.
According to an embodiment of the present invention, the three-dimensional medical image marker point ordering method includes the steps of:
s1, designing a calibration plate, and scanning a three-dimensional medical image;
The total number of mark points a in the calibration plate is not less than 3, and for each mark point P i (i=0, 1,2, …, a-1) in the physical space of the calibration plate, the distance D ij (j=0, 1,2, …, a-2) between the mark points and the rest mark points is calculated to form a distance template intermediate matrix M 1 of a row a-1 column;
S2, sorting each row of the distance template intermediate matrix M 1 from large to small or from small to large by using an bubbling sorting method, and updating the updated result into a distance template intermediate matrix M 2;
S3, calculating the difference value between the maximum value and the minimum value in each row of the distance template intermediate matrix M 2, adding the difference value into the last row to form a distance template matrix N of a row and a column as a standard distance template matrix;
S4, calculating the distance D 'ij (j=0, 1,2, …, a-1) between each marking point Q i (i=0, 1,2, …, a-2) in the three-dimensional medical image and the rest marking points to form a to-be-matched distance intermediate matrix M' 1 of a row a-1;
S5, sorting each row of the distance to be matched intermediate matrix M '1 from large to small or from small to large, and updating the distance to be matched intermediate matrix M' 2 by using an updated result;
s6, calculating the difference value between the maximum value and the minimum value in each row of the intermediate matrix M '2 to be matched, and adding the difference value to the last row to form a row a column distance matrix N' to be matched;
s7, sequentially comparing a first row of the distance matrix N' to be matched with first to a rows of the distance template matrix N, and finding out a row with the same similarity, wherein the row number is an actual row number of a marking point in the three-dimensional medical image in a physical space of the calibration plate;
The same judging standard of the similarity is N (i, j) -0.2mm < N' (i, j) < N (i, j) +0.2mm, i, j are row serial numbers and column serial numbers respectively;
S8, repeating the step S7, and finding out the actual line numbers of all the marking points in the three-dimensional medical image in the physical space of the calibration plate; and finishing the mark point sorting.
The invention also provides a sorting system for the three-dimensional medical image marking points for executing the sorting method, which comprises the following steps:
the standard distance template matrix N module is used for obtaining the difference dimension information by calculating the distance from each marking point to the rest marking points in the physical space of the calibration plate and sequencing;
The distance matrix N' module to be matched is obtained by calculating the distance from each marking point of the three-dimensional medical image to the rest marking points and sequencing and adding difference dimension information;
The comparison module is used for sequentially comparing the first row of the distance matrix N' to be matched with each row of the standard distance template matrix N to find out a row with the same similarity, wherein the row number is the actual row number of the marking point 1 in the three-dimensional medical image in the physical space of the calibration plate; repeating the operation to obtain the actual line numbers of other marking points in the three-dimensional medical image in the physical space of the calibration plate.
According to an embodiment of the present invention, the standard distance template matrix N module includes:
A distance template middle matrix M 1 module, for each marking point P i (i=0, 1,2, …, a-1) of the physical space of the calibration plate, calculating the distance D ij (j=0, 1,2, …, a-2) from each other marking point to form a matrix of a row a-1;
A distance template intermediate matrix M 2 module, configured to rank each row of the distance template intermediate matrix M 1 from large to small or from small to large;
Adding a difference dimension module, calculating the difference between the maximum value and the minimum value in each row of the distance template intermediate matrix M 2, and adding the difference to the last row to form a distance template matrix N of a row and a column;
According to an embodiment of the present invention, the distance matrix to be matched N' module includes:
The distance to be matched middle matrix M ' 1 module is used for calculating the distance D ' ij (j=0, 1,2, …, a-1) between each marking point Q i (i=0, 1,2, …, a-2) in the three-dimensional medical image and the other marking points to form a distance to be matched middle matrix M ' 1 of a row a-1 column;
a distance to be matched intermediate matrix M '2 module for sorting each row of the distance to be matched intermediate matrix M' 1 from large to small or from small to large,
And adding a difference dimension module, calculating the difference between the maximum value and the minimum value in each row of the distance to be matched intermediate matrix M '2, and adding the difference to the last row to form a distance to be matched matrix N' of a row and a column.
The invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of the three-dimensional medical image marking point ordering method when executing the computer program.
The present invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of the three-dimensional medical image marker point ordering method described above.
Advantageous effects
The method for ordering the marking points in the three-dimensional medical image has the characteristics of strong robustness, high efficiency and high success rate. Experiments show that the success rate of 100 times of repeated experiments is 100 percent, and the time consumption is less than 0.5s.
Drawings
FIG. 1 is a flow chart of a method of ordering marker points of a three-dimensional medical image.
Detailed Description
The technical scheme of the invention will be further described in detail below with reference to specific embodiments. It is to be understood that the following examples are illustrative only and are not to be construed as limiting the scope of the invention. All techniques implemented based on the above description of the invention are intended to be included within the scope of the invention.
Example 1
The method for ordering the marking points of the three-dimensional medical image (shown in fig. 1) comprises the following steps:
1.5 circular metal mark points are used and fixed on the calibration plate. The coordinates of the 5 marked points in the physical space of the calibration plate were precisely calculated as (0 mm ), (10 mm,0 mm), (30 mm,0 mm), (0 mm,20 mm), (20 mm ), respectively. A three-dimensional medical image is scanned.
2. For each mark point P i (i=0, 1,2,3, 4) of the physical space of the calibration plate, the distance D ij (j=0, 1,2, 3) from each other mark point is calculated, so as to form a 5-row 4-column distance template intermediate matrix M 1.
3. The rows of matrix M 1 are sorted from large to small and updated with the updated results to distance template intermediate matrix M 2.
4. And calculating the difference value between the maximum value and the minimum value in each row of the middle matrix M 2 of the distance template, adding the difference value to the last row, adding information of one dimension, and ensuring the uniqueness of the subsequent similarity calculation. A 5-row 5-column distance template matrix N is formed as a standard distance template matrix.
5. Each marker point Q i (i=0, 1,2, 3) in the image is calculated to obtain the distance D 'ij (j=0, 1,2,3, 4) from each other marker point, and a 5-row 4-column distance to be matched intermediate matrix M' 1 is formed.
6. And sorting from large to small for each row of the distance to be matched middle matrix M '1, and updating the distance to be matched middle matrix M' 2 by using the updated result.
7. And calculating the difference between the maximum value and the minimum value in each row of the matrix M '2, adding the difference to the last row to form a 5-row and 5-column distance matrix N' to be matched.
8. And comparing the first row of the matrix N' with the first to five rows of the matrix N in sequence to find out a row with the same similarity, wherein the row number is the actual row number of the image mark point 1 in the physical space of the calibration plate. The same similarity is judged by N (i, j) -0.2mm < N' (i, j) < N (i, j) +0.2mm, i, j are row serial numbers and column serial numbers respectively.
9. And repeating the step 8 for 5 times, namely finding out the actual serial numbers of all 5 marking points in the image, and finishing the marking point sequencing.
The sorting method has the characteristics of strong robustness, high efficiency and high success rate. The success rate in 100 repeated experiments is 100%, and the time is less than 0.5s.
Example 2
A sorting system for three-dimensional medical image marker points performing the sorting method of embodiment 1, comprising:
the standard distance template matrix N module is used for obtaining the difference dimension information by calculating the distance from each marking point to the rest marking points in the physical space of the calibration plate and sequencing;
The distance matrix N' module to be matched is obtained by calculating the distance from each marking point of the three-dimensional medical image to the rest marking points and sequencing and adding difference dimension information;
The comparison module is used for sequentially comparing the first row of the distance matrix N' to be matched with each row of the standard distance template matrix N to find out a row with the same similarity, wherein the row number is the actual row number of the marking point 1 in the three-dimensional medical image in the physical space of the calibration plate; repeating the operation to obtain the actual line numbers of other marking points in the three-dimensional medical image in the physical space of the calibration plate;
specifically, the standard distance template matrix N module includes:
The distance template middle matrix M 1 module calculates the distance D ij (j=0, 1,2, 3) from each marking point P i (i=0, 1,2,3, 4) of the physical space of the calibration plate to the other marking points to form a matrix of 5 rows and 4 columns;
A distance template intermediate matrix M 2 module, configured to rank each row of the distance template intermediate matrix M 1 from large to small;
adding a difference dimension module, calculating the difference between the maximum value and the minimum value in each row of the distance template intermediate matrix M 2, and adding the difference to the last row to form a distance template matrix N with 5 rows and 5 columns;
specifically, the distance matrix to be matched N' module includes:
The distance to be matched middle matrix M ' 1 module is used for calculating the distance D ' ij (j=0, 1,2,3, 4) between each marking point Q i (i=0, 1,2, 3) in the three-dimensional medical image and each other marking point to form a 5-row 4-column distance to be matched middle matrix M ' 1;
A distance to be matched intermediate matrix M '2 module for sorting each row of the distance to be matched intermediate matrix M' 1 from large to small,
And adding a difference dimension module, calculating the difference between the maximum value and the minimum value in each row of the distance to be matched intermediate matrix M '2, and adding the difference to the last row to form a distance to be matched matrix N' with 5 rows and 5 columns.
Example 3
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of ordering marker points in a three-dimensional medical image as shown in embodiment 1 when the computer program is executed.
Example 4
A computer-readable storage medium storing computer code which, when executed, performs the steps of the method of ordering marker points in a three-dimensional medical image as shown in embodiment 1 above.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
The above three-dimensional medical images include, but are not limited to, computed tomography (Computed Tomography, CT) images, magnetic resonance imaging (MagneticResonance Imaging, MRI), positron emission tomography (Positron Emission ComputedTomography, PET), and the like.
The embodiments of the present invention have been described above. However, the present invention is not limited to the above embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for ordering marker points of a three-dimensional medical image, the method comprising the steps of:
Designing a calibration plate, and scanning a three-dimensional medical image;
comparing the distance matrix N' to be matched with the standard distance template matrix N, and finding a row with the same similarity, wherein the row number is the actual row number of the marking point in the three-dimensional medical image in the physical space of the calibration plate; repeating the above process to find the actual line numbers of all the marking points in the three-dimensional medical image in the physical space of the calibration plate; finishing the sorting of the mark points;
The standard distance template matrix N is obtained by calculating the distance from each marking point to the rest marking points in the physical space of the calibration plate and sequencing and adding difference dimension information;
the distance from each marking point of the three-dimensional medical image to the rest marking points is calculated, and the distance matrix N' to be matched is obtained through sequencing and adding difference dimension information;
The same judging standard of the similarity is N (i, j) -0.2mm < N' (i, j) < N (i, j) +0.2mm, and i, j are row serial numbers and column serial numbers respectively.
2. The sequencing method of claim 1 wherein said three-dimensional medical image includes, but is not limited to, a computed tomography image, a magnetic resonance imaging or a positron emission tomography image.
3. A sorting method according to claim 1 or 2, characterized in that the marking points on the calibration plate are spherical metal, preferably fixed to the calibration plate according to the design position.
4. A sorting method according to any of claims 1-3, characterized in that the total number of marked points a is not less than 3;
Preferably, the standard distance template matrix N generated by the marker points must satisfy: each row N (i) (i=0, 1, …, a-1) of N is different from all other rows N (p) (p=0, 1, …, a-1, and p+.i), the similarity is the same, the same determination method is N (p, j) -0.2mm < N (i, j) < N (p, j) +0.2mm, j is the column number, j=0, 1, …, a-1.
5. The method of ranking according to any one of claims 1-4, wherein the standard distance template matrix N is obtained by:
s1, calculating the distance D ij (j=0, 1,2, …, a-2) from each marking point P i (i=0, 1,2, …, a-1) of the physical space of the calibration plate to the rest marking points to form a distance template intermediate matrix M 1 of a row a-1 column;
S2, sorting each row of the distance template intermediate matrix M 1 from large to small or from small to large, and updating the distance template intermediate matrix M 2 by using an updated result;
S3, calculating the difference value between the maximum value and the minimum value in each row of the distance template intermediate matrix M 2, adding the difference value into the last row to form a distance template matrix N with a row and a column as a standard distance template matrix.
And/or, the distance matrix N' to be matched is obtained through the following operations:
S1'. Each marking point Q i (i=0, 1,2, …, a-2) in the three-dimensional medical image is calculated to obtain a distance D ' ij (j=0, 1,2, …, a-1) from the rest marking points, and a distance to be matched middle matrix M ' 1 of a row a-1 column is formed;
S2', sorting each row of the distance to be matched intermediate matrix M ' 1 from large to small or from small to large, and updating the distance to be matched intermediate matrix M ' 2 by using the updated result;
S3', calculating the difference value between the maximum value and the minimum value in each row of the intermediate matrix M ' 2 to be matched, and adding the difference value into the last row to form a row a column distance matrix N ' to be matched;
And/or, the comparison of the distance matrix N' to be matched and the standard distance template matrix N comprises the following steps: the first row of the distance matrix N' to be matched is compared in turn with the first to a rows of the distance template matrix N.
6. The method according to claim 5, wherein the ordering rules of step S2 and step S2' are the same.
7. A sorting system for three-dimensional medical image marking points performing the sorting method according to any of the claims 1-6, characterized in that the system comprises:
the standard distance template matrix N module is used for obtaining the difference dimension information by calculating the distance from each marking point to the rest marking points in the physical space of the calibration plate and sequencing;
The distance matrix N' module to be matched is obtained by calculating the distance from each marking point of the three-dimensional medical image to the rest marking points and sequencing and adding difference dimension information;
The comparison module is used for sequentially comparing the first row of the distance matrix N' to be matched with each row of the standard distance template matrix N to find out a row with the same similarity, wherein the row number is the actual row number of the marking point 1 in the three-dimensional medical image in the physical space of the calibration plate; repeating the operation to obtain the actual line numbers of other marking points in the three-dimensional medical image in the physical space of the calibration plate.
8. The ranking system of claim 7 wherein the standard distance template matrix N module comprises:
A distance template middle matrix M 1 module, for each marking point P i (i=0, 1,2, …, a-1) of the physical space of the calibration plate, calculating the distance D ij (j=0, 1,2, …, a-2) from each other marking point to form a matrix of a row a-1;
A distance template intermediate matrix M 2 module, configured to rank each row of the distance template intermediate matrix M 1 from large to small or from small to large;
Adding a difference dimension module, calculating the difference between the maximum value and the minimum value in each row of the distance template intermediate matrix M 2, and adding the difference to the last row to form a distance template matrix N of a row and a column;
and/or, the distance matrix to be matched N' module includes:
The distance to be matched middle matrix M ' 1 module is used for calculating the distance D ' ij (j=0, 1,2, …, a-1) between each marking point Q i (i=0, 1,2, …, a-2) in the three-dimensional medical image and the other marking points to form a distance to be matched middle matrix M ' 1 of a row a-1 column;
a distance to be matched intermediate matrix M '2 module for sorting each row of the distance to be matched intermediate matrix M' 1 from large to small or from small to large,
And adding a difference dimension module, calculating the difference between the maximum value and the minimum value in each row of the distance to be matched intermediate matrix M '2, and adding the difference to the last row to form a distance to be matched matrix N' of a row and a column.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the three-dimensional medical image marker point ordering method according to any one of claims 1-6 when the computer program is executed by the processor.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the three-dimensional medical image marker point ordering method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410395801.6A CN118314215A (en) | 2024-04-02 | 2024-04-02 | Three-dimensional medical image mark point ordering method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410395801.6A CN118314215A (en) | 2024-04-02 | 2024-04-02 | Three-dimensional medical image mark point ordering method, system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118314215A true CN118314215A (en) | 2024-07-09 |
Family
ID=91729402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410395801.6A Pending CN118314215A (en) | 2024-04-02 | 2024-04-02 | Three-dimensional medical image mark point ordering method, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118314215A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096207A (en) * | 2016-06-29 | 2016-11-09 | 武汉中观自动化科技有限公司 | A kind of rotor wing unmanned aerial vehicle wind resistance appraisal procedure based on multi-vision visual and system |
| CN107481276A (en) * | 2016-06-08 | 2017-12-15 | 北京天智航医疗科技股份有限公司 | The automatic identifying method of mark point sequence in a kind of 3 d medical images |
| CN112967236A (en) * | 2018-12-29 | 2021-06-15 | 上海联影智能医疗科技有限公司 | Image registration method and device, computer equipment and storage medium |
| CN113112546A (en) * | 2021-04-16 | 2021-07-13 | 北京航空航天大学 | Space target detection identification and pose tracking method based on three-X combined marker |
| CN113782159A (en) * | 2021-11-12 | 2021-12-10 | 极限人工智能有限公司 | Medical image marking point matching method and device, electronic equipment and storage medium |
| WO2022078439A1 (en) * | 2020-10-15 | 2022-04-21 | 左忠斌 | Apparatus and method for acquisition and matching of 3d information of space and object |
| WO2022247296A1 (en) * | 2021-05-27 | 2022-12-01 | 广州柏视医疗科技有限公司 | Mark point-based image registration method |
| WO2023284368A1 (en) * | 2021-07-16 | 2023-01-19 | 元化智能科技(深圳)有限公司 | Method and apparatus for verifying selection position of marker, and terminal device and storage medium |
| WO2023078169A1 (en) * | 2021-11-05 | 2023-05-11 | 极限人工智能有限公司 | Medical image mark point recognition method and apparatus, electronic device, and storage medium |
| CN116580003A (en) * | 2023-05-11 | 2023-08-11 | 北京航空航天大学 | Registration method and system for preoperative CT image and intraoperative ultrasonic image |
| US20230274526A1 (en) * | 2022-02-25 | 2023-08-31 | Hyundai Motor Company | Automatic Labeling Method for Unlabeled Data of Point Clouds |
| CN116849806A (en) * | 2023-08-01 | 2023-10-10 | 苏州微创畅行机器人有限公司 | Medical image mark point identification method and surgical robot system |
| CN117288120A (en) * | 2023-10-12 | 2023-12-26 | 合肥埃科光电科技股份有限公司 | Three-dimensional imaging measurement system based on multiple visual angles and calibration method thereof |
| CN117372661A (en) * | 2023-12-07 | 2024-01-09 | 华科精准（北京）医疗科技有限公司 | Surgical navigation system, surgical robot system and registration method |
-
2024
- 2024-04-02 CN CN202410395801.6A patent/CN118314215A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107481276A (en) * | 2016-06-08 | 2017-12-15 | 北京天智航医疗科技股份有限公司 | The automatic identifying method of mark point sequence in a kind of 3 d medical images |
| CN106096207A (en) * | 2016-06-29 | 2016-11-09 | 武汉中观自动化科技有限公司 | A kind of rotor wing unmanned aerial vehicle wind resistance appraisal procedure based on multi-vision visual and system |
| CN112967236A (en) * | 2018-12-29 | 2021-06-15 | 上海联影智能医疗科技有限公司 | Image registration method and device, computer equipment and storage medium |
| WO2022078439A1 (en) * | 2020-10-15 | 2022-04-21 | 左忠斌 | Apparatus and method for acquisition and matching of 3d information of space and object |
| CN113112546A (en) * | 2021-04-16 | 2021-07-13 | 北京航空航天大学 | Space target detection identification and pose tracking method based on three-X combined marker |
| WO2022247296A1 (en) * | 2021-05-27 | 2022-12-01 | 广州柏视医疗科技有限公司 | Mark point-based image registration method |
| WO2023284368A1 (en) * | 2021-07-16 | 2023-01-19 | 元化智能科技(深圳)有限公司 | Method and apparatus for verifying selection position of marker, and terminal device and storage medium |
| WO2023078169A1 (en) * | 2021-11-05 | 2023-05-11 | 极限人工智能有限公司 | Medical image mark point recognition method and apparatus, electronic device, and storage medium |
| CN113782159A (en) * | 2021-11-12 | 2021-12-10 | 极限人工智能有限公司 | Medical image marking point matching method and device, electronic equipment and storage medium |
| US20230274526A1 (en) * | 2022-02-25 | 2023-08-31 | Hyundai Motor Company | Automatic Labeling Method for Unlabeled Data of Point Clouds |
| CN116580003A (en) * | 2023-05-11 | 2023-08-11 | 北京航空航天大学 | Registration method and system for preoperative CT image and intraoperative ultrasonic image |
| CN116849806A (en) * | 2023-08-01 | 2023-10-10 | 苏州微创畅行机器人有限公司 | Medical image mark point identification method and surgical robot system |
| CN117288120A (en) * | 2023-10-12 | 2023-12-26 | 合肥埃科光电科技股份有限公司 | Three-dimensional imaging measurement system based on multiple visual angles and calibration method thereof |
| CN117372661A (en) * | 2023-12-07 | 2024-01-09 | 华科精准（北京）医疗科技有限公司 | Surgical navigation system, surgical robot system and registration method |
Non-Patent Citations (1)
| Title |
|---|
| 周振环, 陈思平, 陶笃纯, 陈新海: "医学图像标志点的自动配准", 中国生物医学工程学报, no. 05, 30 October 2003 (2003-10-30), pages 1 - 4 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9697602B1 (en) | System and method for auto-contouring in adaptive radiotherapy | |
| EP3518001B1 (en) | Method for increasing the reliability of determining the position of a vehicle on the basis of a plurality of detection points | |
| CN107481276B (en) | Automatic identification method for marker point sequence in three-dimensional medical image | |
| US20080260254A1 (en) | Automatic 3-D Object Detection | |
| CN111311655B (en) | Multi-mode image registration method, device, electronic equipment and storage medium | |
| CN1301369A (en) | Image tecognition and correlation system | |
| CN110555860B (en) | Method for labeling rib areas in medical image, electronic equipment and storage medium | |
| CN113112490B (en) | Three-dimensional medical image mark point extraction method and system | |
| CN115100185A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN108597589B (en) | Model generation method, target detection method and medical imaging system | |
| CN118314215A (en) | Three-dimensional medical image mark point ordering method, system, electronic equipment and storage medium | |
| EP4259023A1 (en) | Method for determining the screw trajectory of a pedicle bone screw | |
| CN109800702B (en) | Quick comparison method for finger vein identification and computer readable storage medium | |
| CN112766314A (en) | Anatomical structure recognition method, electronic device, and storage medium | |
| CN115661218B (en) | Virtual super-point-based laser point cloud registration method and system | |
| CN113537351B (en) | Remote sensing image coordinate matching method for mobile equipment shooting | |
| CN114821157B (en) | Multi-mode image classification method based on mixed model network | |
| EP3308354A1 (en) | Selection of a subset of atlases from a set of candidate atlases | |
| CN113192122B (en) | Optical center extraction method in visual detection process of assembly pose of large equipment | |
| CN112307971B (en) | Sphere target identification method and device based on three-dimensional point cloud data | |
| CN111428565A (en) | Point cloud identification point positioning method and device based on deep learning | |
| Wong et al. | Efficient multi-structure robust fitting with incremental top-k lists comparison | |
| Torres et al. | 3D facial landmark localization for cephalometric analysis | |
| CN101261735A (en) | System and method for detecting an object in a high dimensional space | |
| CN111369580B (en) | Intelligent segmentation method and terminal for X-ray image |
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 |