CN111127453A - Differential geometry-based full-automatic partitioning method for tracheal tree - Google Patents
Differential geometry-based full-automatic partitioning method for tracheal tree Download PDFInfo
- Publication number
- CN111127453A CN111127453A CN201911375621.7A CN201911375621A CN111127453A CN 111127453 A CN111127453 A CN 111127453A CN 201911375621 A CN201911375621 A CN 201911375621A CN 111127453 A CN111127453 A CN 111127453A
- Authority
- CN
- China
- Prior art keywords
- tree
- trachea
- max
- tracheal
- lung
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
The invention discloses a differential geometry-based full-automatic partitioning method for a tracheal tree, which comprises the following steps of: 1) surface modeling of lung CT; 2) calculating a principal curvature and a principal direction; 3) filtering a non-tracheal region; 4) removing non-tracheal regions; 5) extracting a communicating region; 6) rejecting connected regions with planar features; 7) fusing a trachea tree set S generated by different CT values; 8) obtaining the organ tree surface model. The invention belongs to the technical field of full-automatic segmentation of a trachea tree, and particularly relates to a full-automatic segmentation method of the trachea tree based on differential geometry, which is full-automatic, easy to realize, insensitive to noise images, and free from leakage and blockage of the segmented trachea tree.
Description
Technical Field
The invention belongs to the technical field of full-automatic segmentation of a tracheal tree, and particularly relates to a full-automatic segmentation method of the tracheal tree based on differential geometry.
Background
The accurate segmentation and quantitative analysis of the bronchial tree morphology play an important role in clinically evaluating whether specific diseases (such as the reduction of the bronchial lumen area, the thinning of the wall thickness and the like) exist and severity, the current computed tomography CT imaging technology can realize the visualization of a 3D lung structure, but cannot provide the independent display and quantitative description of the tracheal tree, the manual segmentation is time-consuming and labor-consuming due to the very complex structure of the tracheal tree, and meanwhile, a large artificial error is usually introduced due to the subjective evaluation of an operator, so that the automatic and reliable tracheal tree segmentation method has very important significance in clinical diagnosis of the lung diseases.
The leakage and the blockage are two main challenges of the automatic segmentation of the trachea tree at present, and the main reason for the leakage and the blockage is that a partial volume effect exists in a Computed Tomography (CT) image, so that the contrast between the tube wall of the trachea tree and air in an airway is reduced, and the leakage can cause the segmented trachea tree to be fused with the lung parenchyma around the segmented trachea tree; occlusion results in a broken airway tree or a discontinuity in the airway, and image noise and artifacts can also add difficulty to the segmentation of the airway tree. Especially those patients with lung diseases, such as chronic obstructive pulmonary disease or interstitial pulmonary disease, the segmentation of the airway tree is more difficult, the airway tree cannot be fully automated, the airway tree is sensitive to image noise, the segmented airway tree is easy to leak and block, and the algorithm is complex to implement.
Patent application No. cn201510009239.x discloses a method for obtaining a three-dimensional tracheal tree from a lung CT image, which includes extracting a plurality of image features for constructing energy terms in a cost function; embedding the combined kernel function of the features into a three-dimensional bronchial seed point extraction algorithm by adopting a multi-kernel learning method to obtain seed points forming the bronchial segment; according to the method, the seed points forming the bronchial segments are continuously obtained to obtain the independent bronchial segments, the method adopts a variant of a region growing method, the main bronchus and the bronchial segments are firstly segmented, then the bronchial segments and the main bronchus are subjected to 'stitching', but a large number of fine terminal bronchus are still not segmented, and the stitching operation is sensitive to a noise image, so that false bronchus misconnection can be caused. While a large number of complex "stitching" algorithms necessarily result in increased computational costs.
Disclosure of Invention
In order to solve the existing problems, the invention adopts a differential geometry-based full-automatic trachea tree segmentation method, which has the advantages of full automation, easy realization, insensitivity to noise images and no leakage and blockage of segmented trachea trees.
The technical scheme adopted by the invention is as follows: a fully-automatic trachea tree segmentation method based on differential geometry comprises the following steps:
1) surface modeling of pulmonary CT: equidistant sampling is carried out on the gray value range of-900 HU and-450 HU at the sampling interval of 10HU, the CT values of the tracheal tree at different positions are greatly changed, and the gray value range of-900 HU and-450 HU can cover all the CT values of the tracheal tree; according to the adopted CT value, iteratively adopting a Marching Cube algorithm to carry out isosurface modeling on the lung CT to obtain a triangular patch;
2) principal curvature and principal direction calculation: performing Laplacian smoothing on the triangular patch modeled in the step 1), and adopting an area smoothing operator, wherein a specific smoothing formula is as follows:
wherein A isjRepresenting the area of the jth adjacent triangle with adjacent vertex;
3) filtration of non-tracheal regions: establishing a lung tissue principal curvature characteristic classification table: classifying the shape and type characteristics of the soft tissue in the lung region of the human body according to the principal curvature values calculated in the step 2), wherein the lung tissue in the human body is mainly divided into the following 4 types: spherical, such as a nodule; planes, such as lung borders; convex cylinders, such as the vascular tree and concave cylinders, such as the tracheal tree, in which the relationship of the 4 soft tissue shapes to the major curvature values is shown in table 1:
table 1: classification table of lung tissue principal curvature features, where r is radius of cylinder and sphere
4) Removing non-tracheal regions: according to the result of the step 3), the remaining vertexes after being removed are candidate trachea region vertexes, in order to ensure that no trachea vertexes are omitted in the step, the removal range formed by the following three conditions is smaller than the set of real non-trachea region vertexes, and lung boundary fragments with plane features are brought in;
5) extracting a communicating region: dividing the vertex set which is determined as the trachea area in the step 4) into a plurality of communication areas according to the communication relation among the vertices;
6) removing connected regions with plane shape characteristics: aligning the mean direction d of the minimum principal curvature of the connected region to the Z axis, synchronously rotating the normal vector n at the vertex of the connected region, and projecting the normal vector n to an XOY plane perpendicular to the Z axis to obtain a projection normal vector n ', calculating the distribution angle theta of n' on the XOY plane, wherein theta <3 pi/2 is the lung boundary fragment with plane characteristics, as shown in FIG. 2;
7) fusing different CT values to generate a trachea tree set S: mapping the trachea tree from geometric space to volume data space, calculating the bounding box of S, wherein the vertex in S is respectively the minimum value and the maximum value [ X ] in XYZ axismin，Xmax，Ymin，Ymax，Zmin，Zmax]For each element in S, a single airway tree is sampled equidistantly along the Z-axis [ Z ]min，Zmax]Calculating an intersecting contour of each plane perpendicular to the Z axis and the surface model of the trachea tree, filling the intersecting contour by adopting a raster scanning algorithm, filling voxels in the contour with 1, filling voxels outside the contour with 0, and performing parallel operation on the voxels in the contour with 1;
8) obtaining an organ tree surface model: performing isosurface modeling on the tracheal tree body data generated in the step 7) to obtain a final tracheal tree surface model;
further, the CT value in 1) iteratively adopts Marching Cube algorithm to carry out isosurface modeling on lung CT.
Further, the Laplacian smoothness in 2) can effectively filter the problem that the triangular patch is rough after modeling due to image noise, and meanwhile, the topological structure of the triangular patch is not changed, so that accurate calculation of subsequent principal curvature and principal direction is guaranteed.
Further, 3) the maximum principal curvature and the minimum principal curvature are respectively CmaxAnd Cmin，DmaxAnd DminAre respectively CmaxAnd CminThe direction of curvature of (a).
Further, 3) the three conditions are CmaxNot less than-0.05, unit: 1/mm, | Cmin| ≧ 0.2, unit: 1/mm and AmaxIs more than 30 degrees, satisfies one of the three conditions and is determined as the non-trachea region vertex, wherein AmaxRepresenting the angle of the target vertex with the adjacent vertex in the direction of least principal curvature.
Further, the isosurface modeling of 8) adopts an MC algorithm.
By adopting the scheme, the invention has the following beneficial effects: the invention relates to a differential geometry-based full-automatic segmentation method for a trachea tree, which has the advantages of full automation, easiness in implementation, insensitivity to noise images and no leakage and blockage problems of the segmented trachea tree.
Drawings
FIG. 1 is a schematic diagram of a fully automatic segmentation process of a trachea tree based on a differential geometry full automatic segmentation method of the invention;
FIG. 2 is a diagram showing a minimum curvature direction distribution of a cylindrical blood vessel connected region and a planar connected region in a differential geometry-based trachea tree full-automatic segmentation method of the present invention;
FIG. 3 is a diagram of the trachea tree segmentation effect of the trachea tree full-automatic segmentation method based on differential geometry.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The technical scheme adopted by the invention is as follows: a fully-automatic trachea tree segmentation method based on differential geometry comprises the following steps:
1) surface modeling of pulmonary CT: equidistant sampling is carried out on the gray value range of-900 HU and-450 HU at the sampling interval of 10HU, the CT values of the tracheal tree at different positions are greatly changed, and the gray value range of-900 HU and-450 HU can cover all the CT values of the tracheal tree; according to the adopted CT value, iteratively adopting a Marching Cube algorithm to carry out isosurface modeling on the lung CT to obtain a triangular patch;
2) principal curvature and principal direction calculation: performing Laplacian smoothing on the triangular patch modeled in the step 1), and adopting an area smoothing operator, wherein a specific smoothing formula is as follows:
wherein A isjRepresenting the area of the jth adjacent triangle with adjacent vertex;
3) filtration of non-tracheal regions: establishing a lung tissue principal curvature characteristic classification table: classifying the shape and type characteristics of the soft tissue in the lung region of the human body according to the principal curvature values calculated in the step 2), wherein the lung tissue in the human body is mainly divided into the following 4 types: spherical, such as a nodule; planes, such as lung borders; convex cylinders, such as the vascular tree and concave cylinders, such as the tracheal tree, in which the relationship of the 4 soft tissue shapes to the major curvature values is shown in table 1:
table 1: classification table of lung tissue principal curvature features, where r is radius of cylinder and sphere
4) Removing non-tracheal regions: according to the result of the step 3), the remaining vertexes after being removed are candidate trachea region vertexes, in order to ensure that no trachea vertexes are omitted in the step, the removal range formed by the following three conditions is smaller than the set of real non-trachea region vertexes, and lung boundary fragments with plane features are brought in;
5) extracting a communicating region: dividing the vertex set which is determined as the trachea area in the step 4) into a plurality of communication areas according to the communication relation among the vertices;
6) removing connected regions with plane shape characteristics: aligning the mean direction d of the minimum principal curvature of the connected region to the Z axis, synchronously rotating the normal vector n at the vertex of the connected region, and projecting the normal vector n to an XOY plane perpendicular to the Z axis to obtain a projection normal vector n ', calculating the distribution angle theta of n' on the XOY plane, wherein theta <3 pi/2 is the lung boundary fragment with plane characteristics, as shown in FIG. 2;
7) fusing different CT values to generate a trachea tree set S: mapping the trachea tree from geometric space to volume data space, calculating the bounding box of S, wherein the vertex in S is respectively the minimum value and the maximum value [ X ] in XYZ axismin，Xmax，Ymin，Ymax，Zmin，Zmax]For each element in S, a single airway tree is sampled equidistantly along the Z-axis [ Z ]min，Zmax]Calculating an intersecting contour of each plane perpendicular to the Z axis and the surface model of the trachea tree, filling the intersecting contour by adopting a raster scanning algorithm, filling voxels in the contour with 1, filling voxels outside the contour with 0, and performing parallel operation on the voxels in the contour with 1;
8) obtaining an organ tree surface model: performing isosurface modeling on the tracheal tree body data generated in the step 7) to obtain a final tracheal tree surface model;
further, the CT value in 1) iteratively adopts Marching Cube algorithm to carry out isosurface modeling on lung CT.
Further, the Laplacian smoothness in 2) can effectively filter the problem that the triangular patch is rough after modeling due to image noise, and meanwhile, the topological structure of the triangular patch is not changed, so that accurate calculation of subsequent principal curvature and principal direction is guaranteed.
Further, 3) the maximum principal curvature and the minimum principal curvature are respectively CmaxAnd Cmin，DmaxAnd DminAre respectively CmaxAnd CminThe direction of curvature of (a).
Further, 3) the three conditions are CmaxNot less than-0.05, unit: 1/mm, | Cmin| ≧ 0.2, unit: 1/mm and AmaxIs more than 30 degrees, satisfies one of the three conditions and is determined as the non-trachea region vertex, wherein AmaxRepresenting the angle of the target vertex with the adjacent vertex in the direction of least principal curvature.
Further, the isosurface modeling of 8) adopts an MC algorithm.
The invention relates to a differential geometry-based full-automatic segmentation method for a trachea tree, which has the advantages of full automation, easiness in implementation, insensitivity to noise images and no leakage and blockage problems of the segmented trachea tree.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by the present specification, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (6)
1. A full-automatic segmentation method of a tracheal tree based on differential geometry is characterized by comprising the following steps:
1) surface modeling of pulmonary CT: equidistant sampling is carried out on the gray value range of-900 HU and-450 HU at the sampling interval of 10HU, the CT values of the tracheal tree at different positions are greatly changed, and the gray value range of-900 HU and-450 HU can cover all the CT values of the tracheal tree; according to the adopted CT value, iteratively adopting a Marching Cube algorithm to carry out isosurface modeling on the lung CT to obtain a triangular patch;
2) principal curvature and principal direction calculation: performing Laplacian smoothing on the triangular patch modeled in the step 1), and adopting an area smoothing operator, wherein a specific smoothing formula is as follows:
wherein A isjRepresenting the area of the jth adjacent triangle with adjacent vertex;
3) filtration of non-tracheal regions: establishing a lung tissue principal curvature characteristic classification table: classifying the shape and type characteristics of the soft tissue in the lung region of the human body according to the principal curvature values calculated in the step 2), wherein the lung tissue in the human body is mainly divided into the following 4 types: spherical, planar, convex and concave cylinders;
4) removing non-tracheal regions: according to the result of the step 3), the remaining vertexes after being removed are candidate trachea region vertexes, in order to ensure that no trachea vertexes are omitted in the step, the removal range formed by the following three conditions is smaller than the set of real non-trachea region vertexes, and lung boundary fragments with plane features are brought in;
5) extracting a communicating region: dividing the vertex set which is determined as the trachea area in the step 4) into a plurality of communication areas according to the communication relation among the vertices;
6) removing connected regions with plane shape characteristics: aligning the mean direction d of the minimum principal curvature of the connected region to a Z axis, synchronously rotating a normal vector n at the vertex of the connected region, and projecting the normal vector n to an XOY plane vertical to the Z axis to obtain a projection normal vector n ', calculating the distribution angle theta of n' on the XOY plane, wherein theta <3 pi/2 is a lung boundary fragment with plane characteristics;
7) fusing different CT values to generate a trachea tree set S: mapping the trachea tree from geometric space to volume data space, calculating the bounding box of S, wherein the vertex in S is respectively the minimum value and the maximum value [ X ] in XYZ axismin，Xmax，Ymin，Ymax，Zmin，Zmax]For each element in S, a single airway tree is sampled equidistantly along the Z-axis [ Z ]min，Zmax]Calculating an intersecting contour of each plane perpendicular to the Z axis and the surface model of the trachea tree, filling the intersecting contour by adopting a raster scanning algorithm, filling voxels in the contour with 1, filling voxels outside the contour with 0, and performing parallel operation on the voxels in the contour with 1;
8) obtaining an organ tree surface model: and 7) performing isosurface modeling on the tracheal tree body data generated in the step 7) to obtain a final tracheal tree surface model.
2. The method for fully automatically segmenting the tracheal tree based on the differential geometry as claimed in claim 1, wherein the CT value in step 1) is iteratively modeled by an iso-surface of the lung CT using Marching Cube algorithm.
3. The method according to claim 1, wherein the Laplacian smoothing in step 2) can effectively filter the problem of triangular patch roughness after modeling caused by image noise, and simultaneously, the topological structure of the triangular patch is not changed, so as to ensure accurate calculation of subsequent principal curvature and principal direction.
4. The method according to claim 1, wherein the maximum principal curvature and the minimum principal curvature in step 3) are CmaxAnd Cmin，DmaxAnd DminAre respectively CmaxAnd CminThe direction of curvature of (a).
5. The method according to claim 1, wherein the three conditions in step 3) are CmaxNot less than-0.05, unit: 1/mm, | Cmin| ≧ 0.2, unit: 1/mm and AmaxIs more than 30 degrees, satisfies one of the three conditions and is determined as the non-trachea region vertex, wherein AmaxRepresenting the angle of the target vertex with the adjacent vertex in the direction of least principal curvature.
6. The method of claim 1, wherein the iso-surface modeling adopts MC algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911375621.7A CN111127453A (en) | 2019-12-27 | 2019-12-27 | Differential geometry-based full-automatic partitioning method for tracheal tree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911375621.7A CN111127453A (en) | 2019-12-27 | 2019-12-27 | Differential geometry-based full-automatic partitioning method for tracheal tree |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111127453A true CN111127453A (en) | 2020-05-08 |
Family
ID=70503930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911375621.7A Pending CN111127453A (en) | 2019-12-27 | 2019-12-27 | Differential geometry-based full-automatic partitioning method for tracheal tree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111127453A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113888566A (en) * | 2021-09-29 | 2022-01-04 | 推想医疗科技股份有限公司 | Target contour curve determining method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106097305A (en) * | 2016-05-31 | 2016-11-09 | 上海理工大学 | The intratracheal tree dividing method that two-pass region growing combining form is rebuild |
| CN107481251A (en) * | 2017-07-17 | 2017-12-15 | 东北大学 | A kind of method that terminal bronchi tree is extracted from lung CT image |
| CN110378923A (en) * | 2019-07-25 | 2019-10-25 | 杭州健培科技有限公司 | A kind of method and apparatus that the segmentation of intelligence intratracheal tree is extracted and is classified |
-
2019
- 2019-12-27 CN CN201911375621.7A patent/CN111127453A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106097305A (en) * | 2016-05-31 | 2016-11-09 | 上海理工大学 | The intratracheal tree dividing method that two-pass region growing combining form is rebuild |
| CN107481251A (en) * | 2017-07-17 | 2017-12-15 | 东北大学 | A kind of method that terminal bronchi tree is extracted from lung CT image |
| CN110378923A (en) * | 2019-07-25 | 2019-10-25 | 杭州健培科技有限公司 | A kind of method and apparatus that the segmentation of intelligence intratracheal tree is extracted and is classified |
Non-Patent Citations (2)
| Title |
|---|
| 何瑞华 等: "基于主动轮廓的三维气管树自动分割方法" * |
| 龚华尧: "基于三维区域生长法的肺部气管CT图像自动分割算法研究" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113888566A (en) * | 2021-09-29 | 2022-01-04 | 推想医疗科技股份有限公司 | Target contour curve determining method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8750585B2 (en) | Method and system for segmenting a liver object in an image | |
| Campadelli et al. | A segmentation framework for abdominal organs from CT scans | |
| US6556696B1 (en) | Method for segmenting medical images and detecting surface anomalies in anatomical structures | |
| CN104504737B (en) | A kind of method that three-dimensional tracheae tree is obtained from lung CT image | |
| JP5258694B2 (en) | Medical image processing apparatus and method, and program | |
| CN107590809A (en) | Lung dividing method and medical image system | |
| CN110473207B (en) | Method for interactively segmenting lung lobes | |
| US20090322749A1 (en) | Systems and methods for extracting a curve-skeleton from a volumetric image of a vessel | |
| CN113112609A (en) | Navigation method and system for lung biopsy bronchoscope | |
| US20100322496A1 (en) | Method and system for anatomy structure segmentation and modeling in an image | |
| CN107895364B (en) | A kind of three-dimensional reconstruction system for the preoperative planning of virtual operation | |
| WO2006000953A1 (en) | Displaying a tracheobronchial tree | |
| Li et al. | Supervised recursive segmentation of volumetric CT images for 3D reconstruction of lung and vessel tree | |
| CN111145226B (en) | Three-dimensional lung feature extraction method based on CT image | |
| CN116580068A (en) | Multi-mode medical registration method based on point cloud registration | |
| CN111127453A (en) | Differential geometry-based full-automatic partitioning method for tracheal tree | |
| CN114266788A (en) | Anti-artifact characteristic extraction method based on ultrasonic tomography reflected image convex target | |
| CN111127488B (en) | Method for automatically constructing patient anatomical structure model based on statistical shape model | |
| CN112712540A (en) | Lung bronchus extraction method based on CT image | |
| CN112862884A (en) | Blood vessel extraction method based on graph cutting and fracture completion | |
| Shao et al. | A segmentation method of airway from chest ct image based on vgg-unet neural network | |
| CN113160417B (en) | Multi-organ three-dimensional reconstruction control method based on urinary system | |
| Tong et al. | Computer-aided lung nodule detection based on CT images | |
| Ukil et al. | Automatic lung lobe segmentation in X-ray CT images by 3D watershed transform using anatomic information from the segmented airway tree | |
| CN110599482B (en) | Method and device for determining fissured surfaces, electronic 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230413 Address after: 318000 Building 4, Building 5, Science and Technology Innovation Center, Baita Town, Xianju County Economic Development Zone, Xianju County, Taizhou City, Zhejiang Province Applicant after: Zhejiang Yingjia Medical Equipment Co.,Ltd. Address before: Room 411-10, building 2, No. 8, Jinfeng Road, high tech Zone, Suzhou, Jiangsu 215000 Applicant before: Suzhou Yingjia Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right |