CN108846847B - Mammary gland image segmentation method based on flat-plate-shaped structure shape filter - Google Patents
Mammary gland image segmentation method based on flat-plate-shaped structure shape filter Download PDFInfo
- Publication number
- CN108846847B CN108846847B CN201810429008.8A CN201810429008A CN108846847B CN 108846847 B CN108846847 B CN 108846847B CN 201810429008 A CN201810429008 A CN 201810429008A CN 108846847 B CN108846847 B CN 108846847B
- Authority
- CN
- China
- Prior art keywords
- boundary
- image
- steps
- intermediate image
- tissue
- 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
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
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- 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
- G06T2207/20076—Probabilistic image processing
-
- 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
- G06T2207/30068—Mammography; Breast
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses a mammary gland image segmentation method based on a flat plate structure, which comprises the following steps. Step S1: and inputting the MRI image to be processed. Step S2: the slab-like structure in the MRI image to be processed is enhanced based on a Hessian filter to form an intermediate image 1. Step S3: the boundary of the breast tissue and the pectoral muscle is extracted. Step S4: the boundary of the breast tissue and the in vitro region is extracted. Step S5: and (5) segmenting to obtain the mammary tissue. The mammary gland image segmentation method based on the flat plate structure disclosed by the invention replaces a mode of manually extracting a target region in an image, the algorithm is fully automatic, any manual interaction is not needed, a marker is not needed to be manually marked, the flat plate structure of an MRI image is highlighted by using a Hessian filter, and the boundary between a mammary gland tissue and an in-vitro region (air) and the boundary between the mammary gland tissue and a pectoral muscle are ingeniously distinguished.
Description
Technical Field
The invention belongs to the technical field of three-dimensional MRI image processing, and particularly relates to a mammary tissue segmentation method based on a flat-plate-shaped structure shape filter.
Background
By accurately interpreting and analyzing MRI images, powerful support can be provided for diagnosing early conditions of breast cancer. As is known, the MRI image is interpreted traditionally by a purely manual method, which relies heavily on personal experience accumulation, has strong subjectivity, and is not favorable for accurately, objectively and rapidly interpreting the MRI image. In part of high-density breast MRI images, breast tissues are not clearly distinguished from surrounding tissues, and it is difficult to accurately determine the boundaries thereof by manual means. With the rapid development of artificial intelligence technology, computer-aided diagnosis technology plays an increasingly important role in interpreting breast MRI images. However, the existing computer-aided diagnosis technology needs to reduce the false positive rate while ensuring high sensitivity.
Therefore, for such a computer-aided diagnosis system, defining the breast tissue boundary becomes important, and by segmenting the breast tissue in the MRI image, such a system only acts on the breast tissue region, and further can exclude all regions except the breast tissue, thereby achieving the purpose of reducing false positive diagnosis.
Disclosure of Invention
The invention provides a mammary gland image segmentation method based on a flat-plate structure shape filter aiming at the condition of the prior art.
The invention adopts the following technical scheme that the mammary gland image segmentation method based on the flat-plate structure shape filter comprises the following steps of:
step S1: inputting an MRI image to be processed;
step S2: enhancing a flat structure in the MRI image to be processed based on a Hessian filter;
step S3: extracting the boundary of the mammary tissue and the pectoral muscle;
step S4: extracting the boundary between the mammary tissue and the external region (air)
Step S5: and (5) segmenting to obtain the mammary tissue.
According to the above technical solution, in step S2, the method includes the following steps:
step S21: calculating the parameter S of each pixel point in the MRI image to be processed to form an intermediate image 1:
wherein R issheet＝|λ2|/|λ1|,
|λ1|≥|λ2|≥|λ3|，α＝0.5,
According to the above technical solution, in step S3, the method includes the following steps:
step S31: calculating the gradient direction of each pixel point;
step S32: and reserving the pixel point with the maximum absolute value and the negative characteristic value to obtain an intermediate image 2.
According to the above technical solution, in step S3, the method includes the following steps:
step S33: setting a threshold value of the parameter S of the pixel point in the intermediate image 2 by analyzing the probability distribution of the parameter S;
step S34: the pixel points above the threshold are retained to form the intermediate image 3.
According to the above technical solution, in step S33, the threshold of the parameter S is 0.6.
According to the above technical solution, in step S3, the method includes the following steps:
step S35: calculating the gradient direction of the pixel points of the intermediate image 3;
step S36: the gradient direction is preserved as pixels from top to bottom to form the intermediate image 4.
According to the above technical solution, in step S3, the method includes the following steps:
step S37: calculating a connected region of the pixel points of the intermediate image 4 based on the characteristic vector connectivity corresponding to the maximum characteristic value;
step S38: the largest connected region is retained to obtain the boundary of the breast tissue with the pectoral muscle, while the intermediate image 5 is formed.
According to the above technical solution, in step S4, the method includes the following steps:
step S41: executing step S21 to obtain a parameter S of each pixel point;
step S42: removing the pectoral muscle and the region below the pectoral muscle in the MRI image according to the result of step S38;
step S43: reserving pixel points with the parameter S higher than 0.8;
step S44: the maximum connected area is calculated and retained to obtain the boundary of the breast tissue with the extracorporeal region (air) (see fig. 7).
According to the above technical solution, in step S5, the method includes the following steps:
step S51: the boundary of the breast tissue and the pectoral muscle in step S38 and the boundary of the breast tissue and the in-vitro region in step S44 are synthesized as a complete boundary of the breast tissue (see fig. 8).
The mammary gland image segmentation method based on the flat-plate structure shape filter has the advantages that a mode of manually extracting a target area in an image is replaced, the algorithm is full-automatic, no manual interaction is needed, no manual marker is needed, a Hessian filter is used for highlighting the flat-plate structure of an MRI image, and the boundary between a mammary gland tissue and an in-vitro area (air) and the boundary between the mammary gland tissue and a pectoral muscle are ingeniously distinguished.
Drawings
FIG. 1 is an MRI image to be segmented of a preferred embodiment of the present invention.
Fig. 2 is an MRI image (intermediate image 1) subjected to Hessian filter enhancement processing of the preferred embodiment of the present invention.
Fig. 3 is an MRI image (intermediate image 2) of a preferred embodiment of the invention with a clearer breast tissue to extracorporeal region (air) boundary and breast tissue to pectoral muscle boundary.
Fig. 4 is an MRI image of a hidden portion of breast tissue (intermediate image 3) according to a preferred embodiment of the present invention.
Fig. 5 is an MRI image (intermediate image 4) of a preferred embodiment of the invention with breast tissue and the external region (air) boundaries hidden.
Fig. 6 is an MRI image of the breast tissue and pectoral muscle border (intermediate image 5) of the preferred embodiment of the invention.
Fig. 7 is an MRI image of the boundary of breast tissue and the extracorporeal region (air) in accordance with a preferred embodiment of the present invention.
FIG. 8 is an MRI image of the complete boundary of breast tissue of the preferred embodiment of the present invention.
Fig. 9 is a breast-to-pectoral muscle border and breast region in each image manually outlined by a radiologist.
Detailed Description
The invention discloses a mammary gland image segmentation method based on a flat-plate structure shape filter, and the specific implementation mode of the invention is further described below by combining with a preferred embodiment.
It should be noted by those skilled in the art that the present patent application relates to MRI images, which are collectively referred to as Magnetic Resonance Imaging, and the corresponding chinese name is Magnetic Resonance Imaging.
Those skilled in the art should note that the Hessian filter according to the present patent application is one of the more common feature extraction methods in the field of image processing. Meanwhile, Hessian filters with different structures can be used in specific application fields.
Referring to fig. 1 to 9 of the drawings, fig. 1 to 8 sequentially show MRI images of stages of the slab-shaped structural shape filter-based breast image segmentation method, and fig. 9 shows a breast-to-pectoral muscle boundary and a breast region in each image manually outlined by a radiologist.
Preferably, the breast image segmentation method based on the flat structure shape filter includes the following steps:
step S1: inputting an MRI image to be processed;
step S2: enhancing a flat structure in the MRI image to be processed based on a Hessian filter;
step S3: extracting the boundary of the mammary tissue and the pectoral muscle;
step S4: extracting the boundary between the breast tissue and the in-vitro region (air);
step S5: and (5) segmenting to obtain the mammary tissue.
Further, in step S2, the following steps are included:
step S21: calculating the parameter S of each pixel point in the MRI image to be processed to form an intermediate image 1:
wherein R issheet＝|λ2|/|λ1|,
|λ1|≥|λ2|≥|λ3|，α＝0.5,
Further, in step S3, the following steps are included:
step S31: calculating the gradient direction of each pixel point;
step S32: and reserving the pixel point with the maximum absolute value and the negative characteristic value to obtain an intermediate image 2.,
further, in step S3, the following steps are included:
step S33: setting a threshold value of the parameter S of the pixel point in the intermediate image 2 by analyzing the probability distribution of the parameter S;
step S34: retaining pixel points above the threshold to form an intermediate image 3;
step S35: calculating the gradient direction of the pixel points of the intermediate image 3;
step S36: keeping the pixel points with the gradient direction from top to bottom to form an intermediate image 4;
step S37: calculating a connected region of the pixel points of the intermediate image 4 based on the characteristic vector connectivity corresponding to the maximum characteristic value;
step S38: the largest connected region is retained to obtain the boundary of the breast tissue with the pectoral muscle, while the intermediate image 5 is formed.
In step S33, the threshold of the parameter S is preferably 0.6.
It should be noted that, in steps S21 and S22, since the constructed Hessian filter has particularity, the closer the parameter S is to 1, the more likely the corresponding pixel is a flat plate structure, and the less likely the pixel is a tubular structure or a spherical structure (the parameter S of the pixel of the above two structures is close to 0). Therefore, in the intermediate image 1, most of the pixels are pixels sensitive to the flat-plate structure.
It should be noted that in steps S31 and S32, the overlapping portion around the boundary can be effectively eliminated by re-adjusting the spatial scale of the pixel points, so that the boundary between the breast tissue and the in-vitro region (and the boundary between the breast tissue and the pectoral muscle) can be clearly represented in the image.
It is to be noted that, in steps S33 and S34, the threshold value of the parameter S is set, thereby further eliminating the pixels that are unlikely to have the flat plate-like structure.
It is worth mentioning that in the steps S35 and S36, by retaining the pixels whose gradient direction is from top to bottom, the boundary between the breast tissue and the external region is effectively eliminated, and preconditions are provided for clearly representing the boundary between the breast tissue and the pectoral muscle in the image.
It should be noted that in steps S37 and S38, since some pixel points of the boundary between the non-breast tissue and the pectoral muscle still remain in the intermediate image 4, the largest connected region needs to be found in the image, so that the pixel points of the breast tissue and the pectoral muscle are clearly represented in the image.
Further, in step S4, the following steps are included:
step S41: executing step S21 to obtain a parameter S of each pixel point;
step S42: removing the pectoral muscle and the region below the pectoral muscle in the MRI image (intermediate image 5) according to the result of step S38;
step S43: reserving pixel points with the parameter S higher than 0.8;
step S44: the maximum connected area is calculated and retained to obtain the boundary of the breast tissue with the extracorporeal region (air) (see fig. 7).
Further, in step S5, the following steps are included:
step S51: the boundary of the breast tissue and the pectoral muscle in step S38 and the boundary of the breast tissue and the in-vitro region in step S44 are synthesized as a complete boundary of the breast tissue (see fig. 8).
According to the above preferred embodiment, the boundary extraction result of the breast tissue and the pectoral muscle and the result of the whole breast tissue segmentation are respectively subjected to the precision analysis through two precision verification tests. Two experiments included 30 breast MRI test cases, two radiologists performed manual delineation of the breast-to-pectoral muscle boundaries and the breast regions in each image, respectively, with the manual results as the golden standard against which the MRI image breast tissue segmentation results based on the above segmentation method were compared (see fig. 9). The evaluation index is an average distance (in mm) between the boundary obtained by the division and the boundary outlined by the gold standard. Table one shows the comparison of the breast and pectoral muscle boundaries with two gold standard boundaries, respectively, based on the above segmentation method. The table lists the average distance accuracy of breast tissue to pectoral muscle boundary (1.99 mm), breast tissue to extracorporeal region boundary (2.81 mm), and breast tissue boundary (2.56 mm), respectively, after averaging 30 groups of data. Two groups of experiments show that the segmentation precision of the mammary gland image segmentation method based on the flat-plate structure shape filter meets the clinical requirement.
Table one comparison result table
Table two comparison result table
It will be apparent to those skilled in the art that modifications and equivalents may be made in the embodiments and/or portions thereof without departing from the spirit and scope of the present invention.
Claims (2)
1. A mammary gland image segmentation method based on a flat-plate structure shape filter is characterized by comprising the following steps:
step S1: inputting an MRI image to be processed;
step S2: enhancing the plate-like structure in the MRI image to be processed based on a Hessian filter to form an intermediate image 1;
in step S2, the method includes the steps of:
step S21: calculating the parameter S of each pixel point in the MRI image to be processed to obtain an intermediate image 1:
wherein R issheet＝|λ2|/|λ1|,
|λ1|≥|λ2|≥|λ3|，α＝0.5,
Step S3: extracting the boundary of the mammary tissue and the pectoral muscle;
in step S3, the method includes the steps of:
step S31: calculating the gradient direction of each pixel point;
step S32: reserving the pixel point with the maximum absolute value and the negative characteristic value to obtain an intermediate image 2;
in step S3, the method includes the steps of:
step S33: setting a threshold value of the parameter S of the pixel point in the intermediate image 2 by analyzing the probability distribution of the parameter S;
step S34: retaining pixel points above the threshold to form an intermediate image 3;
in step S33, the threshold of the parameter S is 0.6;
in step S3, the method includes the steps of:
step S35: calculating the gradient direction of the pixel points of the intermediate image 3;
step S36: keeping the pixel points with the gradient direction from top to bottom to form an intermediate image 4;
in step S3, the method includes the steps of:
step S37: calculating a connected region of the pixel points of the intermediate image 4 based on the characteristic vector connectivity corresponding to the maximum characteristic value;
step S38: reserving a maximum connected region to obtain a boundary of the breast tissue and the pectoral muscle;
step S4: extracting the boundary between the mammary tissue and the in-vitro region;
in step S4, the method includes the steps of:
step S41: executing step S21 to obtain a parameter S of each pixel point;
step S42: removing the pectoral muscle and the region below the pectoral muscle in the MRI image according to the result of step S38;
step S43: reserving pixel points with the parameter S higher than 0.8;
step S44: calculating and retaining a maximum connected region to obtain a boundary of the breast tissue with the in vitro region;
step S5: and (5) segmenting to obtain the mammary tissue.
2. The method for segmenting a mammary gland image based on a flat-plate structured shape filter according to claim 1, wherein the step S5 comprises the steps of:
step S51: the boundary of the breast tissue and the pectoral muscle in step S38 and the boundary of the breast tissue and the in-vitro region in step S44 are synthesized as a complete boundary of the breast tissue.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810429008.8A CN108846847B (en) | 2018-05-08 | 2018-05-08 | Mammary gland image segmentation method based on flat-plate-shaped structure shape filter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810429008.8A CN108846847B (en) | 2018-05-08 | 2018-05-08 | Mammary gland image segmentation method based on flat-plate-shaped structure shape filter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108846847A CN108846847A (en) | 2018-11-20 |
| CN108846847B true CN108846847B (en) | 2021-12-03 |
Family
ID=64212810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810429008.8A Active CN108846847B (en) | 2018-05-08 | 2018-05-08 | Mammary gland image segmentation method based on flat-plate-shaped structure shape filter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108846847B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101169868A (en) * | 2006-10-25 | 2008-04-30 | 爱克发医疗保健公司 | Method for segmenting a digital medical image |
| CN103700085A (en) * | 2012-09-28 | 2014-04-02 | 深圳市蓝韵实业有限公司 | Cutting method of pectoral muscle region in mammary gland X-ray image |
| CN103892848A (en) * | 2012-12-26 | 2014-07-02 | 深圳市蓝韵实业有限公司 | Calcification detection method for mammary gland X-ray image |
| CN104715259A (en) * | 2015-01-22 | 2015-06-17 | 苏州工业职业技术学院 | Nuclear self-adaptive optimizing and classifying method of X-ray mammary gland images |
| CN104978753A (en) * | 2014-04-02 | 2015-10-14 | 深圳市蓝韵实业有限公司 | Dividing algorithm for nipple area in mammary gland X-ray image |
| CN105193436A (en) * | 2014-06-20 | 2015-12-30 | 深圳市蓝韵实业有限公司 | Method for evaluating exposure dose of digital mammary X-ray imaging system |
| CN105447879A (en) * | 2015-12-15 | 2016-03-30 | 上海联影医疗科技有限公司 | Method and apparatus for detecting breast muscle in breast image |
| CN107049345A (en) * | 2017-05-23 | 2017-08-18 | 深圳艾砾拓科技有限公司 | Exposure index and bias exponent computational methods in digital X-ray mammography system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160228068A1 (en) * | 2015-02-10 | 2016-08-11 | General Electric Company | Quality assurance for mri-guided breast biopsy |
-
2018
- 2018-05-08 CN CN201810429008.8A patent/CN108846847B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101169868A (en) * | 2006-10-25 | 2008-04-30 | 爱克发医疗保健公司 | Method for segmenting a digital medical image |
| CN103700085A (en) * | 2012-09-28 | 2014-04-02 | 深圳市蓝韵实业有限公司 | Cutting method of pectoral muscle region in mammary gland X-ray image |
| CN103892848A (en) * | 2012-12-26 | 2014-07-02 | 深圳市蓝韵实业有限公司 | Calcification detection method for mammary gland X-ray image |
| CN104978753A (en) * | 2014-04-02 | 2015-10-14 | 深圳市蓝韵实业有限公司 | Dividing algorithm for nipple area in mammary gland X-ray image |
| CN105193436A (en) * | 2014-06-20 | 2015-12-30 | 深圳市蓝韵实业有限公司 | Method for evaluating exposure dose of digital mammary X-ray imaging system |
| CN104715259A (en) * | 2015-01-22 | 2015-06-17 | 苏州工业职业技术学院 | Nuclear self-adaptive optimizing and classifying method of X-ray mammary gland images |
| CN105447879A (en) * | 2015-12-15 | 2016-03-30 | 上海联影医疗科技有限公司 | Method and apparatus for detecting breast muscle in breast image |
| CN107049345A (en) * | 2017-05-23 | 2017-08-18 | 深圳艾砾拓科技有限公司 | Exposure index and bias exponent computational methods in digital X-ray mammography system |
Non-Patent Citations (1)
| Title |
|---|
| 基于乳腺X线图像的乳腺癌检测方法研究;张胜君;《中国博士学位论文全文数据库信息科技辑》;20140515(第05期);第I138-64页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108846847A (en) | 2018-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598709B (en) | Mammary gland auxiliary diagnosis system and method based on fusion depth characteristic | |
| CN109815888B (en) | Novel Pasteur staining method-based abnormal cervical cell automatic identification method | |
| Al-Shamlan et al. | Feature extraction values for breast cancer mammography images | |
| US9042631B2 (en) | Method and systems for cell-level fish dot counting | |
| CN104616307B (en) | A kind of lung CT image adhesion vascular type nodule detection methods | |
| WO2008005426A2 (en) | Computer-aided pathological diagnosis system | |
| WO1995014979A1 (en) | Automated method and system for improved computerized detection and classification of masses in mammograms | |
| CN104299242B (en) | Fluoroscopic visualization eye fundus image extracting method based on NGC ACM | |
| CN113781455B (en) | Cervical cell image anomaly detection method, device, equipment and medium | |
| US20140140629A1 (en) | Methods for processing target pattern, method for generating classification system of target patterns and method for classifying detected target patterns | |
| CN110288542A (en) | A kind of liver's pathological image sample Enhancement Method based on stochastic transformation | |
| CN113205492A (en) | Microvessel distortion degree quantification method for gastric mucosa staining amplification imaging | |
| US10943350B2 (en) | Automated segmentation of histological sections for vasculature quantification | |
| CN106023165B (en) | A kind of vessel extraction method of vivo tumor angiogenesis image under the photoacoustic microscope for optical resolution | |
| CN110533667B (en) | Lung tumor CT image 3D segmentation method based on image pyramid fusion | |
| CN108846847B (en) | Mammary gland image segmentation method based on flat-plate-shaped structure shape filter | |
| WO2022006917A1 (en) | Artificial intelligence-based lung magnetic resonance image recognition apparatus and method | |
| CN111292285B (en) | Automatic screening method for diabetes mellitus based on naive Bayes and support vector machine | |
| CN111062909A (en) | Method and equipment for judging benign and malignant breast tumor | |
| Shahin et al. | Breast cancer detection using modified Hough transform | |
| Parvaze et al. | Extraction of multiple cellular objects in HEp-2 images using LS segmentation | |
| Nakagawa et al. | Automated contour extraction of mammographic mass shadow using an improved active contour model | |
| CN112617799A (en) | Network model for endometrial tumor segmentation and segmentation method | |
| US20220335602A1 (en) | Method and system for image normalisation | |
| Hamzah et al. | MRI brain tumor detection based on soft computing |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211103 Address after: 130062 Group 15, Fannan Committee, Chengxi Town, Luyuan District, Changchun City, Jilin Province Applicant after: Wang Lei Address before: 314000 room 610, R & D building, Shanghai Jiaotong University (Jiaxing) Science Park, 321 Jiachuang Road, Xiuzhou District, Jiaxing City, Zhejiang Province Applicant before: JIAXING QUANJING MEDICAL DEVICES CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |