CN115272375A - Three-dimensional image vertebral body point cloud segmentation method - Google Patents
Three-dimensional image vertebral body point cloud segmentation method Download PDFInfo
- Publication number
- CN115272375A CN115272375A CN202211051703.8A CN202211051703A CN115272375A CN 115272375 A CN115272375 A CN 115272375A CN 202211051703 A CN202211051703 A CN 202211051703A CN 115272375 A CN115272375 A CN 115272375A
- Authority
- CN
- China
- Prior art keywords
- image
- point cloud
- vertebral body
- dimensional
- vertebral
- 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 31
- 230000011218 segmentation Effects 0.000 title claims abstract description 24
- 238000005070 sampling Methods 0.000 claims abstract description 29
- 238000001914 filtration Methods 0.000 claims abstract description 17
- 238000012216 screening Methods 0.000 claims abstract description 11
- 210000000746 body region Anatomy 0.000 claims description 25
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 230000003628 erosive effect Effects 0.000 claims description 5
- 230000000399 orthopedic effect Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 5
- 210000000988 bone and bone Anatomy 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000001959 radiotherapy Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/06—Topological mapping of higher dimensional structures onto lower dimensional surfaces
- G06T3/067—Reshaping or unfolding 3D tree structures onto 2D planes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a point cloud segmentation method for a three-dimensional image vertebral body, which comprises the following steps: converting a three-dimensional image containing a spine into a three-dimensional point cloud, and screening to obtain a point cloud of a vertebral body area; projecting the point cloud of the vertebral body area along the left and right directions of a human body, sampling a set distance from the vertebral body direction to the spinous process direction on a projection image to obtain a sampling image range, filtering the three-dimensional point cloud in the sampling image range and generating the projection image, thereby obtaining a minimum enclosing rectangle of the vertebral body area of each vertebral section; and performing extension screening on the three-dimensional point cloud according to the minimum enclosing rectangle to obtain each centrum point cloud. The invention can rapidly complete the segmentation of a plurality of centrum three-dimensional area images in the three-dimensional image, is more convenient for the operation such as operation path planning and operation registration positioning, and has wide application scenes in the field of orthopedic operation auxiliary planning.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a point cloud segmentation method for a three-dimensional image vertebral body.
Background
With the development of biomedical engineering and computer technology, medical imaging provides multi-modal medical images for clinical diagnosis. These medical images are playing an increasingly important role in today's clinical neighborhood. The method is not only applied to medical diagnosis, but also can be used for making operation plans, making radiotherapy plans, tracking pathological changes, evaluating treatment effects and the like. The medical image segmentation technology is an important technical link in the medical image technology, and the essence of the medical image segmentation technology is to extract the concerned part features through the processing of the medical image, so as to perform more accurate diagnosis and operation.
The three-dimensional image data is mainly used by doctors for pathological judgment, has the characteristics of complete image data, high image precision and rich data details, is the image data commonly used by the existing orthopedic auxiliary navigation robot, but generally comprises a plurality of part details, for example, a three-dimensional image shot before spinal surgery may comprise one or more parts of cervical vertebra, thoracic vertebra and lumbar vertebra, and the number of vertebral segments of the spine is also generally a plurality, so that each vertebral segment region can be approximately segmented through a vertebral segment segmentation technology, and the operations such as surgical path planning, surgical registration positioning and the like are more convenient.
Disclosure of Invention
The invention aims to: in view of the above disadvantages, the present invention provides a three-dimensional image cone point cloud segmentation method based on image processing, which can rapidly complete the segmentation of a plurality of cone three-dimensional regions in an image.
The technical scheme is as follows:
a point cloud segmentation method for a three-dimensional image vertebral body comprises the following steps:
converting a three-dimensional image containing the spine into three-dimensional point clouds, and screening to obtain point clouds of approximate vertebral body areas;
projecting the point cloud of the approximate vertebral body area along the left and right directions of the human body, and sampling a set distance from the vertebral body direction to the spinous process direction on a projection image to obtain a sampling image range;
filtering the three-dimensional point cloud in a sampling image range and generating a projection image, thereby obtaining a minimum enclosing rectangle of a vertebral body region of each vertebral segment;
and performing extension screening on the three-dimensional point cloud according to the minimum bounding rectangle to obtain the point cloud of each vertebral body.
The screening to obtain the point cloud of the approximate vertebral body area specifically comprises the following steps:
acquiring spine region point clouds in the three-dimensional point clouds, projecting the spine region point clouds along the height direction of a human body, and performing binarization processing on the projected images to obtain spine region images;
and determining the minimum bounding rectangle of the vertebral body area image in the vertebral body area image, and filtering the three-dimensional point cloud to obtain the point cloud approximate to the vertebral body area.
The determining the minimum bounding rectangle of the vertebral body region image in the vertebral body region image specifically comprises:
determining a vertebral body area in the vertebral body area image, and determining a minimum enclosing rectangle of the vertebral body area image by taking the maximum coordinate difference value of each pixel point on the vertebral body area in two coordinate axes of a two-dimensional coordinate system of the vertebral body area image as the length and width of the minimum enclosing rectangle.
The determining the vertebral body region in the vertebral body region image comprises:
and performing morphological erosion and expansion operation on the image of the vertebral body area to obtain an image containing the vertebral body, the vertebral foramen area and the surrounding part area.
Determining the set distance on the projection image with a feature height jump position on the image in which the vertebral body to pedicle portion is terminated.
The set distance is 3/4 of the distance from the vertebral body direction to the spinous process direction of each vertebral body part area on the projection image.
The minimum enclosing rectangle of the vertebral body region of each vertebral segment is obtained by the following steps:
and extracting a distribution region of each vertebral body by adopting a connected domain on a projection image generated by filtering the three-dimensional point cloud in a sampling image range, and generating a minimum enclosing rectangle of the vertebral body region of each vertebral body according to the distribution region.
And screening the three-dimensional point cloud according to the energy value of the skeleton to obtain the point cloud of the vertebral region.
The filtering the three-dimensional point cloud with the sampling image range and generating the projection image comprises:
filtering the three-dimensional point cloud in a sampling image range;
and projecting the filtered three-dimensional point cloud respectively along the left and right directions and the front and back directions of the human body to generate corresponding projection images.
Has the beneficial effects that: the invention can rapidly complete the segmentation of a plurality of centrum three-dimensional area images in the three-dimensional image, is more convenient for the operation such as operation path planning and operation registration positioning, and has wide application scenes in the field of orthopedic operation auxiliary planning.
Drawings
FIG. 1 is a flow chart of the steps of point cloud segmentation of a three-dimensional image vertebral body according to the present invention;
FIG. 2 is a CT image to be segmented;
FIG. 3 is a cloud of bone points to be segmented;
FIG. 4 is a projection image of a skeletal point cloud along the height direction of the spine;
fig. 5 (a) and 5 (b) are projection images projected in the left-right direction and the front-back direction of the human body, respectively;
fig. 6 (a) and 6 (b) are projection images obtained by projecting point clouds obtained by filtering three-dimensional point clouds through a point cloud distribution range of a vertebral body along the vertebral height direction along the left-right direction and the front-back direction of a human body respectively;
FIGS. 7 (a) and 7 (b) are schematic views of the vertebral body regions extracted from the projection views projected along the left-right direction and the front-back direction of the human body, respectively;
fig. 8 is a schematic view of a point cloud of a vertebral body after segmentation.
Detailed Description
The invention is further elucidated with reference to the drawings and the embodiments.
The invention discloses a two-dimensional image based three-dimensional image vertebral body point cloud segmentation method which is shown in figure 1 and comprises the following steps:
(1) Reading a three-dimensional image containing a spine, converting the three-dimensional image into a three-dimensional point cloud containing an energy value (in the invention, a CT value or a gray value), screening the three-dimensional point cloud according to the energy value of the spine, removing characteristic information of non-bone parts in the three-dimensional image, such as tissues, organs and the like, and only keeping the point cloud information of the spine; because the obtained point cloud information of the spine part generally contains noise, the noise can be removed through a filtering algorithm to obtain relatively accurate point cloud of the spine region;
in the invention, the three-dimensional image is a CT image containing the spine acquired by CT, as shown in FIG. 2, so that the energy value is a CT value, the three-dimensional image is converted into a three-dimensional point cloud containing the CT value, and then the corresponding spine region point cloud is obtained by the above processing according to the CT value of the skeleton, as shown in FIG. 3.
(2) Projecting the point cloud of the spine region along the height direction of the human body in the three-dimensional image to obtain a projection image of the spine region;
the three-dimensional coordinate system is a coordinate system established according to the right-hand rule by taking the length direction of an operating bed bearing a human body in a three-dimensional image as a Z axis and the direction which is horizontal and vertical to the Z axis as an X axis, namely the image coordinate system, and the three-dimensional image containing the spine of the human body can be obtained by scanning the human body by laying the human body on the operating bed according to a normal body position when the three-dimensional image is scanned, so that the height direction, the left and right directions and the front and back directions of the human body in the three-dimensional image are respectively parallel to the Z axis, the X axis and the Y axis of the image coordinate system; furthermore, the human body may move in the process, so that the actual height direction, the left-right direction and the front-back direction of the human body are changed, but small angles exist among the three and the Z axis, the X axis and the Y axis of the image coordinate system, so that the corresponding height direction, the left-right direction and the front-back direction of the human body can be clearly distinguished from the three-dimensional image, and the point cloud of the spine region can be projected along the height direction of the human body in the three-dimensional image and projected along the left-right direction and the front-back direction of the human body in the subsequent steps;
of course, the present invention may also project the vertebral region point cloud directly along the Z-axis direction of the image coordinate system, and in the subsequent steps, the point cloud may also be projected along the X-axis and Y-axis directions of the image coordinate system.
The projection image is shown in fig. 4, in which each pixel value is calculated as follows: firstly, calculating the energy values of all points in the point cloud corresponding to each pixel point, accumulating and inverting the energy values, marking the sum as G, then calculating the G power of a natural constant e, and finally normalizing the pixel values of all points to the range of 0-255.
(3) Processing the spine region projection image obtained in the step (2) to obtain a minimum enclosing rectangle of the spine region image;
specifically, the method comprises the following steps:
firstly, removing a non-vertebra region through binarization processing according to the vertebra region projection image obtained in the step (2) to obtain a region-of-interest image, namely a vertebra region image;
secondly, performing operations such as morphological erosion and expansion on the image of the region of interest to obtain a vertebral body region image containing a vertebral body, a vertebral foramen region and a peripheral partial region thereof, for example, filtering out a partial transverse process region in the image of the vertebral region through operations such as morphological erosion and expansion;
then, further processing the image of the vertebral body area through Blob analysis, and further filtering noise around the vertebral body, wherein the Blob analysis is to further remove the noise around the vertebral body;
whether morphological erosion, expansion operation and Blob analysis are needed or not can be determined according to needs in the image processing process, and after the spine region image is subjected to binarization processing, morphological processing and Blob analysis are selected according to the noise condition around the vertebral body;
finally, determining a two-dimensional coordinate system according to the spine region image, and determining a minimum bounding rectangle of the spine region image by taking the maximum coordinate difference value of each pixel point of the spine region image in two coordinate axes of the two-dimensional coordinate system as the length and width of the minimum bounding rectangle; among them, according to the selection of the projection direction in the step (2), the two-dimensional coordinate system may be established with the X and Y axes of the three-dimensional coordinate system as coordinate axes, or with the left-right direction and the front-back direction of the human body as coordinate axes, and the former is preferable in the present invention.
Then, the minimum bounding rectangle of each pixel point in the region can be obtained according to the minimum coordinate range of the image of the cone region in the XY direction of the two-dimensional coordinate system.
(4) And (2) filtering the three-dimensional point cloud obtained in the step (1) according to the minimum enclosing rectangle of the image of the cone region obtained in the step (3) to obtain an approximate point cloud of the cone region, and then projecting the filtered point cloud respectively along the left and right directions and the front and back directions of the human body to generate corresponding projection images, as shown in fig. 5 (a) and 5 (b), wherein the projection image in fig. 5 (a) comprises the cone, the cone hole and part of the spinous process.
(5) Sampling a set distance from the centrum direction to the spinous process direction along the projection image obtained in the step (4) to obtain a sampling image range;
in the invention, as shown in fig. 5 (a), since the cone features in the projected image obtained by projecting along the left and right directions of the human body obtained in the step (4) are relatively clear, the set distance is sampled from right to left along the projected image to obtain the distribution range along the height direction of the spine, which is similar to the cone, namely the sampling image range; of course, the projection image may be projected from another direction in the left-right direction of the human body, and then the sampling is performed from the left to the right from the corresponding projection image.
Specifically, because there is a sudden change in the height direction of the human body (i.e., the feature height on the image) from the vertebral body to the pedicle portion on the projection image, the position of the sudden change is set as a sampling termination region, and the region obtained by sampling is the distribution range of the vertebral body approximately along the height direction of the spine;
more specifically, in the present invention, if sampling is performed from the vertebral body direction to the spinous process direction of the projection image, and the abrupt change position from the vertebral body to the pedicle portion is used as the sampling termination area, the sampling data is inaccurate due to too much noise in the sampling data, so that 3/4 of the area of each vertebral body portion from right to left can be preferably selected as the sampling termination data, and the accuracy of the sampling data is ensured.
(6) And (3) filtering the three-dimensional point cloud obtained in the step (1) according to the sampling image range obtained in the step (5), and projecting the filtered three-dimensional point cloud respectively along the left-right direction and the front-back direction of the human body to generate corresponding projection images, as shown in fig. 6 (a) and 6 (b).
(7) Searching a connected domain of the projection image obtained in the step (6) to obtain a distribution area of each vertebral body, and generating a minimum enclosing rectangle of the vertebral body area of each vertebral body according to the distribution area, as shown in fig. 7 (a) and 7 (b);
firstly, processing the projection image obtained in the step (6) through one or more of binarization, morphology and Blob analysis to obtain an image containing a part of a vertebral body;
then, a distribution region of each vertebral segment is obtained by adopting connected domain extraction, and a minimum enclosing rectangle of the vertebral body region of each vertebral segment is generated according to the distribution region, as shown in fig. 7;
specifically, the extending direction of each minimum enclosing rectangle is consistent with the width and height direction of the cone, and the position of each cone corresponds to that in fig. 3 one by one.
(8) Because the sampling in the step (5) may not include a complete vertebral body region, the minimum enclosing rectangle of each vertebral body region extracted in the step (7) is extended on the three-dimensional point cloud obtained in the step (1) along the front and back directions of the human body and is extended to the boundary of the bone point cloud (namely, fig. 3), so that an approximate vertebral joint region including the whole vertebral body can be obtained, the three-dimensional point cloud obtained in the step (1) is filtered according to the rectangular coordinates of each vertebral body region, so that the point cloud of each vertebral body can be obtained, as shown in fig. 8, and the segmentation is finished.
The method comprises the steps of analyzing three-dimensional point cloud and gray value information in a three-dimensional image, dividing a vertebral body area of each vertebral body, extracting corresponding three-dimensional point cloud according to a division result, and finally obtaining the point cloud and gray value information corresponding to each vertebral body, so that the division of the vertebral bodies in the three-dimensional image is completed. The invention can rapidly complete the segmentation of a plurality of centrum three-dimensional area images in the three-dimensional image.
Although the preferred embodiments of the present invention have been described in detail, the present invention is not limited to the details of the foregoing embodiments, and various equivalent changes (such as number, shape, position, etc.) may be made to the technical solution of the present invention within the technical spirit of the present invention, and these equivalent changes are all within the protection scope of the present invention.
Claims (9)
1. A three-dimensional image vertebral body point cloud segmentation method is characterized by comprising the following steps: the method comprises the following steps:
converting a three-dimensional image containing the spine into three-dimensional point clouds, and screening to obtain point clouds of approximate vertebral body areas;
projecting the point cloud of the approximate vertebral body area along the left and right directions of the human body, and sampling a set distance from the vertebral body direction to the spinous process direction on a projection image to obtain a sampling image range;
filtering the three-dimensional point cloud by using the sampling image range and generating a projection image, thereby obtaining a minimum enclosing rectangle of a vertebral body region of each vertebral segment;
and performing extension screening on the three-dimensional point cloud according to the minimum enclosing rectangle to obtain each centrum point cloud.
2. The point cloud segmentation method for three-dimensional image vertebral bodies according to claim 1, wherein: the screening to obtain the point cloud of the approximate vertebral body area specifically comprises the following steps:
acquiring spine region point clouds in the three-dimensional point clouds, projecting the spine region point clouds along the height direction of a human body, and performing binarization processing on the projected images to obtain spine region images;
and determining the minimum bounding rectangle of the vertebral body area image in the vertebral body area image, and filtering the three-dimensional point cloud to obtain the point cloud approximate to the vertebral body area.
3. The point cloud segmentation method for three-dimensional image vertebral bodies according to claim 2, wherein: the specific steps of determining the minimum bounding rectangle of the vertebral body region image in the vertebral body region image are as follows:
and determining a vertebral body region in the vertebral body region image, and determining a minimum enclosing rectangle of the vertebral body region image by taking the maximum coordinate difference value of each pixel point on the vertebral body region in two coordinate axes of a two-dimensional coordinate system of the vertebral body region image as the length and width of the minimum enclosing rectangle.
4. The point cloud segmentation method for three-dimensional image vertebral bodies according to claim 3, wherein: the determining a vertebral body region in the image of the vertebral body region comprises:
and performing morphological erosion and expansion operation on the image of the vertebral body area to obtain an image containing the vertebral body, the vertebral foramen area and the surrounding part area.
5. The point cloud segmentation method for three-dimensional image vertebral bodies according to claim 1, wherein: the set distance is determined on the projection image with a feature height abrupt change position on the image in which the vertebral body to the pedicle portion is terminated.
6. The point cloud segmentation method for three-dimensional image vertebral bodies according to claim 1, wherein: the set distance is 3/4 of the distance from the vertebral body direction to the spinous process direction of each vertebral body part area on the projection image.
7. The point cloud segmentation method for three-dimensional image vertebral bodies according to claim 1, wherein: the minimum bounding rectangle of the vertebral body region of each vertebral segment is obtained by:
and extracting a distribution region of each vertebral body by adopting a connected domain on a projection image generated by filtering the three-dimensional point cloud in a sampling image range, and generating a minimum bounding rectangle of the vertebral body region of each vertebral body according to the distribution region.
8. The point cloud segmentation method for three-dimensional image vertebral bodies according to claim 1, wherein: and screening the three-dimensional point cloud according to the energy value of the skeleton to obtain the point cloud of the vertebral region.
9. The point cloud segmentation method for three-dimensional image vertebral bodies according to claim 1, wherein: the filtering the three-dimensional point cloud with the sampling image range and generating the projection image comprises:
filtering the three-dimensional point cloud in a sampling image range;
and projecting the filtered three-dimensional point cloud along the left and right directions and the front and back directions of the human body respectively to generate corresponding projection images.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211051703.8A CN115272375A (en) | 2022-08-31 | 2022-08-31 | Three-dimensional image vertebral body point cloud segmentation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211051703.8A CN115272375A (en) | 2022-08-31 | 2022-08-31 | Three-dimensional image vertebral body point cloud segmentation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115272375A true CN115272375A (en) | 2022-11-01 |
Family
ID=83753886
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211051703.8A Pending CN115272375A (en) | 2022-08-31 | 2022-08-31 | Three-dimensional image vertebral body point cloud segmentation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115272375A (en) |
-
2022
- 2022-08-31 CN CN202211051703.8A patent/CN115272375A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110956635B (en) | Lung segment segmentation method, device, equipment and storage medium | |
CN107595387B (en) | Spine image generation system based on ultrasonic rubbing technology and spine operation navigation and positioning system | |
JP2021154168A (en) | Surgical navigation of the hip using fluoroscopy and tracking sensors | |
CN110363765B (en) | Osteoporosis parameter automatic measurement method based on CT image | |
JPH09508994A (en) | Image forming apparatus and method | |
CN110946652B (en) | Method and device for planning screw path of bone screw | |
CN104254874A (en) | Method and system to assist 2d-3d image registration | |
Baka et al. | Statistical shape model-based femur kinematics from biplane fluoroscopy | |
CN113538533B (en) | Spine registration method, device and equipment and computer storage medium | |
CN113274129A (en) | Cardiothoracic surgery auxiliary control system based on virtual reality | |
WO2006092594A2 (en) | 3d ultrasound registration | |
CN110731817A (en) | radiationless percutaneous spine positioning method based on optical scanning automatic contour segmentation matching | |
Hosseinian et al. | 3D Reconstruction from Multi-View Medical X-ray images–review and evaluation of existing methods | |
CN115358995A (en) | Full-automatic space registration system based on multi-mode information fusion | |
CN114642444A (en) | Oral implantation precision evaluation method and system and terminal equipment | |
CN108670302B (en) | Spine three-dimensional structure reproduction method based on 2.5-dimensional ultrasonic panoramic imaging | |
CN113274130A (en) | Markless surgery registration method for optical surgery navigation system | |
CN110811829B (en) | Construction method and system based on femoral rotation axis and varus analysis model | |
JP4807819B2 (en) | Image processing device | |
CN115272375A (en) | Three-dimensional image vertebral body point cloud segmentation method | |
CN114283179A (en) | Real-time fracture far-near end space pose acquisition and registration system based on ultrasonic images | |
JPWO2015053319A1 (en) | Image processing apparatus and surgical microscope system | |
US11406471B1 (en) | Hand-held stereovision system for image updating in surgery | |
CN112862975A (en) | Bone data processing method, system, readable storage medium and device | |
CN112085698A (en) | Method and device for automatically analyzing left and right breast ultrasonic images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
CB02 | Change of applicant information |
Address after: 210000 building 3, No. 34, Dazhou Road, Yuhuatai District, Nanjing, Jiangsu Province Applicant after: Tuodao Medical Technology Co.,Ltd. Address before: 210000 building 3, No. 34, Dazhou Road, Yuhuatai District, Nanjing, Jiangsu Province Applicant before: Nanjing Tuodao Medical Technology Co.,Ltd. |
|
CB02 | Change of applicant information | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |