CN115797339B - Centrum central point positioning method, system, equipment and storage medium - Google Patents
Centrum central point positioning method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN115797339B CN115797339B CN202310052948.0A CN202310052948A CN115797339B CN 115797339 B CN115797339 B CN 115797339B CN 202310052948 A CN202310052948 A CN 202310052948A CN 115797339 B CN115797339 B CN 115797339B
- Authority
- CN
- China
- Prior art keywords
- target
- information
- cone
- point
- array
- 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.)
- Active
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to a centrum central point positioning method, a centrum central point positioning system, centrum central point positioning equipment and a storage medium, wherein the centrum central point positioning method comprises the steps of obtaining centrum mask information; determining a first central line according to a preset central line acquisition rule and cone mask information; determining a plurality of target points according to a preset center line processing rule and a first center line; determining target centrum information according to curved surface reconstruction rules and target points; determining a distance conversion image according to the image calculation rule and the target cone information; and determining a target center point according to the coordinate determination rule, the cone mask information, the target cone information and the distance conversion image. The invention reduces the influence of the transitional vertebrae on the positioning of the centrum center point.
Description
Technical Field
The application relates to the technical field of medical image processing, in particular to a centrum central point positioning method, a centrum central point positioning system, a centrum central point positioning device and a centrum central point positioning storage medium.
Background
CT (Computed Tomography) it uses precisely collimated X-ray beam, gamma ray, ultrasonic wave, etc. to scan the cross section around a certain part of human body together with a detector with very high sensitivity.
With the continuous progress of medical imaging technology, CT medical images are widely used in diagnosis of spinal diseases. When a series of computer-aided diagnosis schemes for acquiring CT images of the spine are required, such as bone density detection, the central point position information of each vertebral body is mostly required to be obtained, and then the steps of independent segmentation, numbering, bone density analysis and the like of the vertebral bodies can be performed. At present, a key point detection method based on deep learning can be used for positioning the centrum central point, but a large amount of training data is required by using the deep learning method, and the result is easily influenced by special conditions such as a transitional vertebra and the like.
The prior art solutions described above have the following drawbacks: there is a problem in that the result is easily affected by a special case such as a transitional vertebra.
Disclosure of Invention
In order to reduce the influence of the transitional vertebrae on the centrum central point positioning, the application provides a centrum central point positioning method, a centrum central point positioning system, a centrum central point positioning device and a storage medium.
In a first aspect of the present application, a method of locating a centrum center point is provided. The method comprises the following steps:
acquiring cone mask information;
determining a first central line according to a preset central line acquisition rule and the cone mask information;
determining a plurality of target points according to a preset center line processing rule and the first center line;
determining target centrum information according to curved surface reconstruction rules and the target points;
determining a distance conversion image according to an image calculation rule and the target cone information;
and determining a target center point according to a coordinate determination rule, the cone mask information, the target cone information and the distance transformation image.
According to the technical scheme, the first central line corresponding to the cone is obtained through obtaining cone mask information, the first central line is determined, the first central line is subjected to sparsification processing to obtain the target point, then the target cone information is determined according to the target point, the distance conversion image is determined according to the target cone information and the image calculation rule, the target central point is determined according to all the obtained information, the corresponding target central point is obtained through analyzing and calculating one cone, the accuracy of the target central point is improved while the calculated data quantity is reduced, and the influence of the transitional cone on the target central point is further reduced.
In one possible implementation manner, the determining the first center line according to a preset center line acquiring rule and the cone mask information includes:
the cone mask information comprises mask foreground information and mask background information, and the mask foreground information comprises cone information;
traversing the mask foreground information and acquiring the center of gravity corresponding to the mask foreground information;
and connecting the centers of gravity in sequence to form a first central line.
In one possible implementation manner, the determining a plurality of target points according to a preset centerline processing rule and the first centerline includes:
selecting a point to be processed from the first central line according to a preset distance value and a midpoint acquisition rule;
and carrying out median filtering treatment on the point to be treated, and determining a target point.
In one possible implementation manner, the determining the target cone information according to the curved surface reconstruction rule and the target point includes:
determining a second central line according to the target point and a preset interpolation rule;
determining a plurality of normal planes according to a normal plane creation rule, the target point and the second center line;
the plurality of normal planes form the targeted vertebral body information.
In one possible implementation manner, the determining a distance transformation image according to the image calculation rule and the target cone information includes:
the target cone information comprises target foreground information and target background information, and the target foreground information comprises cone information;
calculating the distance between the target foreground information and the target background information;
determining foreground pixels according to pixel correspondence rules and the distances;
the target foreground pixels and the target background information form the distance transformed image.
In one possible implementation manner, the determining the target center point according to the coordinate determining rule, the cone mask information, the target cone information and the distance conversion image includes:
determining a target array according to an image summation rule and the distance transformation image;
obtaining a maximum value point array of the target array;
determining a target coordinate point according to the maximum value point array and the target cone information;
and determining a target center point according to the target coordinate point and the cone mask information.
In one possible implementation manner, the obtaining the maximum value point array of the target array includes:
the target array includes a plurality of target elements;
sequentially calculating first difference values of two adjacent target elements in the target array, wherein the first difference values form a first array;
sequentially judging a first difference value in the first array;
when the first difference is greater than zero, the first difference is recorded as 1;
when the first difference value is less than or equal to zero, the first difference value is recorded as 0;
calculating a second difference value of two adjacent first difference values of the first array, wherein the second difference value forms a second array;
sequentially judging a second difference value in the second array;
when the second difference value is equal to a difference value preset value, the coordinate corresponding to the second difference value is a maximum value point;
the maxima points form a maxima point array.
In a second aspect of the present application, a vertebral body center point positioning system is provided. The system comprises:
the data acquisition module is used for acquiring cone mask information;
the first center determining module is used for determining a first center line according to a preset center line acquiring rule and the cone mask information;
the second center determining module is used for determining a plurality of target points according to a preset center line processing rule and the first center line;
the target cone determining module is used for determining target cone information according to the curved surface reconstruction rule and the target point;
the image calculation module is used for determining a distance conversion image according to an image calculation rule and the target cone information;
and the target center point determining module is used for determining a target center point according to a coordinate determining rule, the cone mask information, the target cone information and the distance transformation image.
In a third aspect of the present application, an electronic device is provided. The electronic device includes: the system comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the centrum center point positioning method when executing the program.
In a fourth aspect of the present application, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method as according to the first aspect of the present application.
In summary, the present application includes at least one of the following beneficial technical effects:
1. firstly, cone mask information is acquired, a first central line corresponding to a cone is determined, then the first central line is subjected to sparsification treatment to obtain a target point, corresponding target cone information can be determined according to the target point, a distance conversion image is determined according to the target cone information and an image calculation rule, a target central point is determined according to the acquired distance conversion image, the target cone information and the cone mask information, and the corresponding target central point is acquired by analyzing and calculating one cone, so that the accuracy of the target central point is improved, and the influence of a transitional cone on the target central point is reduced.
Drawings
Fig. 1 is a flow chart of a method for locating a centrum center point provided in the present application.
Fig. 2 is a schematic structural view of a centrum center point positioning system provided herein.
Fig. 3 is a schematic structural diagram of an electronic device provided in the present application.
In the figure, 200, a centrum central point positioning system; 201. a data acquisition module; 202. a first center determination module; 203. a second center determination module; 204. a targeted vertebral body determination module; 205. an image calculation module; 206. a target center point determination module; 301. a CPU; 302. a ROM; 303. a RAM; 304. an I/O interface; 305. an input section; 306. an output section; 307. a storage section; 308. a communication section; 309. a driver; 310. removable media.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.
Embodiments of the present application are described in further detail below with reference to the drawings attached hereto.
The embodiment of the application provides a centrum central point positioning method, and the main flow of the method is described as follows.
As shown in fig. 1:
step S101: and acquiring cone mask information.
Specifically, according to the CT image and the deep learning model, the whole spine is segmented, namely, all the vertebral bodies forming the spine are segmented as the foreground, different vertebral bodies are not distinguished, and other parts except the vertebral bodies are used as the background parts. For example, using deep learning, a more accurate model of the whole segmentation of the vertebral body can be trained with less data. The cone mask information includes foreground information identifying pixels of the cone portion as foreground and background information identifying remaining pixels as background. In this embodiment, the cone mask information is obtained by a segmentation method based on deep learning. Obtaining cone mask information via a deep learning model is a well-known technique for those skilled in the art, and will not be described in detail herein.
Step S102: and determining a first central line according to a preset central line acquisition rule and cone mask information.
Specifically, traversing foreground information of cone mask information, obtaining each cross section, and obtaining center points of each cross section, wherein the center points are sequentially arranged to form a first center line. In this embodiment, each cross section includes a plurality of coordinate points of foreground information, the coordinate points include x coordinate values and y coordinate values, an average value of the x coordinate values and an average value of the y coordinate values of the plurality of coordinate points are calculated, respectively, the average value of the x coordinate values is an x coordinate value of a center point, the average value of the y coordinate values is a y coordinate value of the center point, the plurality of center points form a first center line, for example, in a three-dimensional coordinate, for a certain cross section, z coordinate is the same, x coordinate values and y coordinate values of all coordinate points in the cross section are obtained, average values of all x coordinate values and y coordinate values are calculated, respectively, the x coordinate value of the center point of the cross section is an average value of all x coordinate values, and the y coordinate value of the center point of the cross section is an average value of all y coordinate values.
Step S103: and determining a plurality of target points according to a preset center line processing rule and a first center line.
Specifically, for the first center line, a point is obtained at intervals of a preset distance, namely a to-be-processed midpoint, for example, a certain endpoint of the first center line is reserved, and then a point is reserved at intervals of 30mm, so that the thinned first center line is obtained. And then median filtering is carried out on coordinate values of the thinned first central line along the x-axis direction and the y-axis direction respectively, and a plurality of target points are obtained after the median filtering is finished. The preset distance is set manually. Median filtering is a technique well known to those skilled in the art and will not be described in detail herein.
Step S104: and determining the target cone information according to the curved surface reconstruction rule and the target point.
Specifically, a second central line is determined according to the multiple target points and a preset interpolation rule, a normal plane is created for the target points along the second central line according to the target points, the second central line and a normal plane, a tangent line of the target point is made for a certain target point on the second central line, the normal plane is a plane which passes through the target point and is perpendicular to the tangent line, and the multiple normal planes form target cone information. The interpolation rule is an interpolation function, which is a technique known to those skilled in the art, and will not be described herein.
The condition of unsmooth in the first central line caused by the inclination of the edge of the cone body can be filtered through median filtering processing on the target point on the first central line, so that the obtained second central line is smooth and stable, namely the central line for straightening.
Step S105: and determining a distance conversion image according to the image calculation rule and the target cone information.
Specifically, the target cone information includes target foreground information and target background information, and euclidean distance conversion is performed on the target cone information, where the euclidean distance conversion refers to converting a pixel value corresponding to each pixel point in the foreground information into a distance that the point reaches a nearest background point. And after the Euclidean distance transformation is completed on the target cone information, obtaining a distance transformation image.
Step S106: and determining a target center point according to the coordinate determination rule, the cone mask information, the target cone information and the distance conversion image.
Specifically, each cross section of the distance conversion image is sequentially obtained, the sum value of foreground information corresponding to each cross section is calculated, each cross section obtains a corresponding sum value, and the sum values are spliced into a one-dimensional array (namely a target array) according to a certain sequence (from top to bottom or from bottom to top). Sequentially calculating first difference values of two adjacent target elements in the target array, wherein the first difference values form a first array; sequentially judging a first difference value in the first array, and recording the first difference value as 1 when the first difference value is larger than zero; and when the first difference value is less than or equal to zero, the first difference value is recorded as 0. Calculating second difference values of two adjacent first difference values of the first array, wherein the second difference values form a second array; and sequentially judging a second difference value in the second array, wherein when the second difference value is equal to a difference value preset value, the coordinate corresponding to the second difference value is a maximum value point, and the maximum value points form a maximum value point array. According to the target centrum information, layer information corresponding to each vertebra can be obtained, according to the maximum value point array, the coordinates of a central point in the foreground information can be obtained, and the coordinates of the central point and the layer information are combined, so that the three-dimensional coordinates of the central point can be obtained; and determining the position of the three-dimensional coordinates of the center point on the cone mask information according to the three-dimensional coordinates of the center point, cone mask information and the mapping relation between the cone mask information and the target cone, and determining the center point coordinates of each cone, wherein the center point coordinates of each cone are the target center points. In this embodiment, the target array is subjected to the post-term minus the pre-term calculation to obtain the first array. And carrying out binarization processing on the first array, and adding 1 to the value which is larger than 0 and 0 to the value which is smaller than or equal to 0 in the first array to obtain a second array. And continuing to perform the postterm minus antecedent processing on the second array to obtain a third array. And acquiring all pixel coordinates with the value of-1 in the third array, wherein the coordinates are the positions of the central points of each vertebra in the targeted vertebral body information. And obtaining a layer corresponding to each vertebra in the targeted vertebral body information, calculating the center coordinates of the foreground of the corresponding layers in the targeted vertebral body information, and combining the layer information to obtain the three-dimensional coordinates of the center point of each vertebra on the targeted vertebral body information. And reversely mapping the three-dimensional coordinates of the central points to the cone mask information according to the mapping relation between the target cone information and the cone mask information, so that the central point coordinates of each cone in the cone mask information are obtained.
An embodiment of the present application provides a centrum center point positioning system 200, referring to fig. 2, the centrum center point positioning system 200 includes:
a data acquisition module 201, configured to acquire cone mask information;
a first center determining module 202, configured to determine a first center line according to a preset center line acquiring rule and the cone mask information;
a second center determining module 203, configured to determine a plurality of target points according to a preset center line processing rule and the first center line;
the target cone determining module 204 is configured to determine target cone information according to a curved surface reconstruction rule and the target point;
an image calculation module 205, configured to determine a distance conversion image according to an image calculation rule and the target cone information;
the target center point determining module 206 is configured to determine a target center point according to a coordinate determining rule, the cone mask information, the target cone information, and the distance conversion image.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the described modules may refer to corresponding procedures in the method embodiments described below, and are not described herein again.
The embodiment of the application discloses electronic equipment. Referring to fig. 3, the electronic device includes a Central Processing Unit (CPU) 301 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage portion 307 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data required for the system operation are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other by a bus. An input/output (I/O) interface 304 is also connected to the bus.
The following components are connected to the I/O interface 304: an input section 305 including a keyboard, a mouse, and the like; an output portion 306 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage portion 307 including a hard disk and the like; and a communication section 308 including a network interface card such as a LAN card, a modem, or the like. The communication section 308 performs communication processing via a network such as the internet. A driver 309 is also connected to the I/O interface 304 as needed. A removable medium 310 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 309 as needed, so that a computer program read out therefrom is installed into the storage section 307 as needed.
In particular, according to embodiments of the present application, the process described above with reference to flowchart fig. 1 may be implemented as a computer software program. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a machine-readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such embodiments, the computer program may be downloaded and installed from a network via the communication portion 308, and/or installed from the removable media 310. The above-described functions defined in the system of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 301.
It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this application, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The foregoing description is only of the preferred embodiments of the present application and is presented as a description of the principles of the technology being utilized. It will be appreciated by persons skilled in the art that the scope of the application referred to in this application is not limited to the specific combinations of features described above, but it is intended to cover other embodiments in which any combination of features described above or their equivalents is possible without departing from the spirit of the application. Such as the above-mentioned features and the technical features having similar functions (but not limited to) applied for in this application are replaced with each other.
Claims (5)
1. A method of locating a centrum center point, comprising:
acquiring cone mask information, wherein the cone mask information comprises mask foreground information and mask background information, and the mask foreground information comprises cone information;
determining a first center line according to a preset center line acquisition rule and the cone mask information, wherein the method comprises the following steps: traversing mask foreground information of the cone mask information, obtaining each cross section, and obtaining a center point of each cross section, wherein the center points are arranged in sequence to form a first center line;
determining a plurality of target points according to a preset center line processing rule and the first center line, wherein the method comprises the following steps: for the first central line, acquiring a point, namely a point to be processed, at each preset distance; performing median filtering treatment on the point to be treated to determine a target point;
determining target cone information according to a curved surface reconstruction rule and the target point, wherein the method comprises the following steps: performing interpolation processing on the target points to obtain a second center line; creating a plurality of normal planes for the target points along the second central line, and making tangents to the target points on the second central line, wherein the normal planes are planes which pass through the target points and are perpendicular to the tangents; the plurality of normal planes form the targeted vertebral body information; the target cone information comprises target foreground information and target background information, and the target foreground information comprises cone information;
determining a distance conversion image according to an image calculation rule and the target cone information, wherein the distance conversion image comprises the following steps: calculating the distance between the target foreground information and the target background information; determining a target foreground pixel according to the corresponding relation between the target foreground information and the distance; the target foreground pixels and the target background information form the distance transformation image;
determining a target center point according to a coordinate determination rule, the cone mask information, the target cone information and the distance transformation image, including: sequentially acquiring each cross section of the distance conversion image, calculating the sum value of target foreground pixels corresponding to each cross section, obtaining a corresponding sum value by each cross section, and splicing the sum values into a one-dimensional array, namely a target array, according to the sequence; the target array includes a plurality of target elements; obtaining a maximum value point array of the target array; determining a target coordinate point according to the maximum value point array and the target cone information; and determining a target center point according to the target coordinate point and the cone mask information.
2. The method of locating a centrum center point as defined in claim 1, comprising: the obtaining the maximum value point array of the target array comprises the following steps:
sequentially calculating first difference values of two adjacent target elements in the target array, wherein the first difference values form a first array;
sequentially judging a first difference value in the first array;
when the first difference is greater than zero, the first difference is recorded as 1;
when the first difference value is less than or equal to zero, the first difference value is recorded as 0;
calculating a second difference value of two adjacent first difference values of the first array, wherein the second difference value forms a second array;
sequentially judging a second difference value in the second array;
when the second difference value is equal to a difference value preset value, the coordinate corresponding to the second difference value is a maximum value point;
the maxima points form a maxima point array.
3. A centrum central point positioning system, comprising:
the data acquisition module (201) is used for acquiring cone mask information, wherein the cone mask information comprises mask foreground information and mask background information, and the mask foreground information comprises cone information;
the first center determining module (202) is used for traversing the foreground information of the cone mask information, acquiring each cross section, and solving the center point of each cross section, wherein the center points are arranged in sequence to form a first center line;
a second center determining module (203) configured to obtain, for the first center line, a point, i.e. a point to be processed, at a preset distance; performing median filtering treatment on the point to be treated to determine a target point;
the target cone determining module (204) is used for carrying out interpolation processing on the target points to obtain a second central line; creating a plurality of normal planes for the target points along the second central line, and making tangents to the target points on the second central line, wherein the normal planes are planes which pass through the target points and are perpendicular to the tangents; the plurality of normal planes form the targeted vertebral body information; the target cone information comprises target foreground information and target background information, and the target foreground information comprises cone information;
an image calculation module (205) for calculating a distance between the target foreground information and the target background information; determining a target foreground pixel according to the corresponding relation between the target foreground information and the distance; the target foreground pixels and the target background information form the distance transformation image;
the target center point determining module (206) is used for sequentially acquiring each cross section of the distance conversion image, calculating the sum value of target foreground pixels corresponding to each cross section, obtaining a corresponding sum value by each cross section, and splicing the sum values into a one-dimensional array, namely a target array, according to the sequence; the target array includes a plurality of target elements; obtaining a maximum value point array of the target array; determining a target coordinate point according to the maximum value point array and the target cone information; and determining a target center point according to the target coordinate point and the cone mask information.
4. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program capable of being loaded by the processor and performing the method according to any of claims 1 to 2.
5. A computer readable storage medium, characterized in that a computer program is stored which can be loaded by a processor and which performs the method according to any of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310052948.0A CN115797339B (en) | 2023-02-03 | 2023-02-03 | Centrum central point positioning method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310052948.0A CN115797339B (en) | 2023-02-03 | 2023-02-03 | Centrum central point positioning method, system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115797339A CN115797339A (en) | 2023-03-14 |
| CN115797339B true CN115797339B (en) | 2023-05-09 |
Family
ID=85429575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310052948.0A Active CN115797339B (en) | 2023-02-03 | 2023-02-03 | Centrum central point positioning method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115797339B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113643314A (en) * | 2021-07-02 | 2021-11-12 | 阿里巴巴新加坡控股有限公司 | Spine segmentation method in medical image |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4492886B2 (en) * | 2008-04-03 | 2010-06-30 | 富士フイルム株式会社 | Three-dimensional intraperitoneal region detection apparatus, method, and program |
| JP7066490B2 (en) * | 2018-04-10 | 2022-05-13 | キヤノンメディカルシステムズ株式会社 | Support information generator and support information generation program |
| CN110264475B (en) * | 2019-06-19 | 2022-10-25 | 合肥工业大学 | CT image-based spine three-dimensional modeling method and device |
| CN111260703B (en) * | 2020-01-08 | 2023-04-11 | 浙江大学 | Method, system, medium and storage medium for obtaining spinal straightening image set |
| CN112233083B (en) * | 2020-10-13 | 2024-01-02 | 沈阳先进医疗设备技术孵化中心有限公司 | Spine detection method, spine detection device, electronic equipment and storage medium |
-
2023
- 2023-02-03 CN CN202310052948.0A patent/CN115797339B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113643314A (en) * | 2021-07-02 | 2021-11-12 | 阿里巴巴新加坡控股有限公司 | Spine segmentation method in medical image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115797339A (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111047572B (en) | Automatic spine positioning method in medical image based on Mask RCNN | |
| US8050481B2 (en) | Method and apparatus for small pulmonary nodule computer aided diagnosis from computed tomography scans | |
| US6909794B2 (en) | Automated registration of 3-D medical scans of similar anatomical structures | |
| Aykac et al. | Segmentation and analysis of the human airway tree from three-dimensional X-ray CT images | |
| EP0760624B1 (en) | Automated detection of lesions in computed tomography | |
| CN102460471B (en) | Systems for computer aided lung nodule detection in chest tomosynthesis imaging | |
| US7643663B2 (en) | Volume measurement in 3D datasets | |
| EP1791087B1 (en) | Method for point-of-interest attraction in digital images | |
| CN109124662B (en) | Rib center line detection device and method | |
| US20090074276A1 (en) | Voxel Matching Technique for Removal of Artifacts in Medical Subtraction Images | |
| JP2007537811A (en) | How to detect nodules | |
| CN113706473B (en) | Method for determining long and short axes of focus area in ultrasonic image and ultrasonic equipment | |
| EP3047455B1 (en) | Method and system for spine position detection | |
| EP2601637B1 (en) | System and method for multi-modality segmentation of internal tissue with live feedback | |
| JP5296981B2 (en) | Automatic registration of medical volume images in modalities using affine transformation | |
| US7835555B2 (en) | System and method for airway detection | |
| WO2015040547A1 (en) | Method and system for spine position detection | |
| CN115439453A (en) | Vertebral body positioning method and device, electronic equipment and storage medium | |
| CN115797339B (en) | Centrum central point positioning method, system, equipment and storage medium | |
| CN110533667B (en) | Lung tumor CT image 3D segmentation method based on image pyramid fusion | |
| US20100202674A1 (en) | Voting in mammography processing | |
| CN115439423A (en) | CT image-based identification method, device, equipment and storage medium | |
| CN115552458A (en) | Measuring changes in tumor volume in medical images | |
| EP4113439B1 (en) | Determining a location at which a given feature is represented in medical imaging data | |
| CN113516669B (en) | CT image-based trachea extraction method, device, equipment and storage medium |
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 |