CN109523561B - Automatic intra-abdominal muscle and fat image segmentation method - Google Patents
Automatic intra-abdominal muscle and fat image segmentation method Download PDFInfo
- Publication number
- CN109523561B CN109523561B CN201811397835.XA CN201811397835A CN109523561B CN 109523561 B CN109523561 B CN 109523561B CN 201811397835 A CN201811397835 A CN 201811397835A CN 109523561 B CN109523561 B CN 109523561B
- Authority
- CN
- China
- Prior art keywords
- tissue
- muscle
- fat
- value
- pixel
- 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
- G06T7/11—Region-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
- G06T7/187—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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Abstract
The invention provides an automatic intra-abdominal muscle and fat image segmentation method, which is used for simultaneously segmenting abdominal muscle tissues, visceral fat tissues and subcutaneous fat tissues. The method mainly comprises the following steps: and (4) carrying out abdominal image pixel classification to obtain a preliminary fat tissue and muscle tissue and a background part pixel value change range. And secondly, further segmenting on the basis of the variation range of the pixel value of the muscle tissue to respectively obtain the outer contour part and the inner contour part of the muscle, and finishing the muscle tissue segmentation on the basis of the outer contour part and the inner contour part of the muscle. Finally, the muscle tissue divides the fat tissue divided in the first step into two parts, and the visceral fat tissue is positioned in the muscle tissue. Located outside the muscle tissue is subcutaneous adipose tissue. Compared with the prior art, the method has the advantages of high accuracy, full-automatic segmentation and the like by segmenting the muscle tissue and the adipose tissue of all slices at one time.
Description
Technical Field
The invention provides an automatic intra-abdominal muscle and fat image segmentation method.
Background
The ratio of the components of human body fat to muscle tissue is useful in predicting a number of diseases, particularly those associated with obesity.
At present, the muscle and fat segmented by general software in the market are mostly two-dimensional methods, the segmentation is semi-automatic, the segmentation depends on the professional experience of doctors, different tissues need to be marked on each layer of slices, the time consumption is too large, and the practicability needs to be improved.
Automatic segmentation algorithms have been proposed, such as FFD registration algorithm to segment muscle tissue, graph segmentation, thresholding, etc. These methods also have their own drawbacks, FFD registration is based on two-dimensional image segmentation, each image needs to be recalculated, a lot of time is consumed, the threshold and image segmentation methods rely on the prior value information of the pixels of muscles and tissues, and the probability of errors is increased.
Disclosure of Invention
The present invention proposes an automatic intra-abdominal muscle and fat image segmentation method to solve at least one aspect of the above problems.
The purpose of the invention can be realized by the following technical scheme:
an automatic intra-abdominal muscle and fat image segmentation method for simultaneously segmenting abdominal muscle tissue, visceral fat tissue and subcutaneous fat tissue pixel information comprises the following parts:
1) classifying pixels, namely classifying pixel values by using an ICM (conditional iterative model segmentation algorithm) to obtain pixel value ranges of muscle tissues and fat tissues;
2) removing in vitro pixel values on the basis of the step 1);
3) extracting a muscle tissue pixel area on the result of the step 1);
4) the adipose tissue pixel area obtained by the step 1) is divided into 2 parts by the muscle tissue obtained by the step 3); the visceral fat portion is inside the muscle tissue and the subcutaneous tissue portion is outside the muscle fat;
the step 1) is specifically as follows:
11) the CT value of the muscle tissue 082323hu ranges from [ -29,150], the CT value of the fat tissue ranges from [ -190, -30], and the CT values serve as initial values of fat and muscle tissue classes in an ICM (conditional iterative model segmentation algorithm), and the number of the classification classes is 4; the background part is divided into a low-brightness background and a high-brightness background;
12) calculating the pixel mean value of each category;
13) defining an image energy formula, including an image gray level energy value and a label energy value; calculating the energy value of each pixel point under different categories;
14) selecting the category of the maximum energy value as a new classification result of the pixel points;
15) the calculations (11-14) are iterated until the result converges or the number of iterations reaches a maximum value.
The step 2) is specifically as follows:
21) taking the part of the non-low bright background in the classification result of 1) as a new segmentation result;
22) filling the inner cavity with the result of 21) layer by layer;
23) selecting the maximum communication area from the result of 22), namely obtaining the pixel area of the abdominal tissue part;
the step 3) is specifically as follows:
31) obtaining a region enclosed by the muscle outer contour according to the classification result of 1) and a level set algorithm, morphology and a cavity filling processing method;
32) contracting the outer contour obtained in the step 31) inwards by 25mm, and obtaining a primary inner contour region by utilizing a muscle CT value;
33) extracting a pixel region of the bone tissue using a dual threshold; firstly, extracting partial bone tissues by using a larger threshold (400), and then continuously extracting the bone tissues by using a low threshold (150) around the extracted bone tissues;
34) performing morphology and cavity filling treatment on the result obtained in the step 33), then taking the maximum communication area to obtain bone tissues close to the spine, and removing rib parts;
35) on a sagittal plane, calculating a mass center point of a skeleton in the x direction, and extracting the mass center point of each line within a certain range close to the mass center point (if a certain line has no skeleton point, no extraction is performed);
36) performing curve fitting on the basis of the centroid points obtained in the step 35) to obtain a continuous curve and a width value of a continuous skeleton x axis;
37) obtaining a centroid curve and a width value according to 36) to obtain an inner contour line near the spine; further correcting 32) the inner contour;
38) and obtaining the pixel area of the muscle tissue part according to the obtained inner and outer contour lines.
The step 4) is specifically as follows:
41) filling the muscle tissue area obtained in the step 3);
42) the fat region obtained in step 1) belongs to the visceral tissue region if it is also within the filling region in step 41);
43) the fat region obtained in step 1) is not in the filling region in step 41), and belongs to the subcutaneous tissue region.
The invention has the beneficial effects that: compared with the prior art, the method has the advantages of high accuracy, full-automatic segmentation and the like by segmenting the muscle tissue and the adipose tissue of all slices at one time.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a color chart of segmentation results according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, the present invention provides an automatic intra-abdominal muscle and fat image segmentation method, which specifically comprises the following steps:
1) abdominal pixel classification. The pixel value ranges of the muscle tissue and the fat tissue are preliminarily calculated. The ICM principle is a probability theory model, and the scheme is that the classification of a pixel value depends not only on the size of the pixel value but also on the classification of neighborhood pixels. Thus, an energy value is defined, which is calculated from the image gray value and the classification to which the neighborhood pixels belong. And obtaining a classification result when the energy minimum value or the energy value of the whole image is not changed, namely the final classification result. Because the ICM considers the classification of the adjacent pixel points, the classification result obtained by the ICM has better clustering effect, namely, less occurrence of heterogeneous classification in a classification region.
The specific method comprises the following steps:
an ICM initial value is set. Empirically, the approximate range of CT values of muscle tissue is [ -29,150], the approximate range of CT values of adipose tissue is [ -190, -30], and the number of classification categories is 4 as the initial values of the categories of adipose tissue and muscle tissue in the ICM classification algorithm. The classification categories are respectively: low brightness background tissue, high brightness background tissue, muscle tissue and adipose tissue.
The pixel mean for each category is calculated.
An image energy formula is defined, including an image gray scale energy value and a label energy value. And calculating the energy value of each pixel point under different categories. The category of one pixel is not only related to the pixel value of the pixel, but also related to the category of the adjacent pixels, and the energy formula can be used for better avoiding the interference of noise.
And selecting the maximum energy value category as a new classification result of the pixel points.
And (5) iterating the calculation until the result converges or the iteration number reaches the maximum value.
Removing the in vitro pixel values on the basis of the step 1). In the process of segmenting abdominal muscles and fat, in vitro pixel values (such as bed body parts) may interfere with the segmentation result, so that they are removed first.
The specific method comprises the following steps:
and taking the part of the non-low bright background in the classification result of the step 1) as a new segmentation result.
The internal voids are filled in layers. Filling the cavity in layers is used to avoid unsegmenting the lung tissue while the lung tissue is contained.
And selecting the maximum communication area to obtain the abdominal tissue part.
3) On the result of step 1, muscle tissue is extracted. The foreground image part obtained in step 1 includes two categories, muscle and fat, but the fat does not distinguish subcutaneous fat from visceral fat part. Both belong to fat, and can be determined only by location. Visceral fat is wrapped inside the muscle, and subcutaneous fat is outside the muscle. Therefore, to distinguish between the two, the muscle portion needs to be extracted first.
The specific method comprises the following steps:
obtaining a region enclosed by the muscle outer contour according to the classification result of 1) and the level set, morphology and a cavity filling processing method. level set (level set algorithm) initial contour initialization lines are positioned in the abdomen and outside muscles, and the energy value of each pixel point is iteratively calculated according to an energy formula (an image gray value is used as internal energy, and curvature and gradient values are used as external energy). The outer contour part is obtained after convergence. However, the region obtained by the level set algorithm may not be closed, and morphology and a hole filling method may be used to obtain a closed region.
And (4) inwards contracting the outer contour obtained in the last step for a certain distance, and obtaining a primary inner contour area by utilizing a muscle pixel value range. The thickness of the other muscle tissue remains substantially uniform except near the spinal column. So that after shrinking inward on the outer contour, the inner contour portion can be obtained primarily by using the pixel values. However, in the case of the muscle tissue of the spine portion, there is a portion of the muscle tissue that is not divided. This part is followed by processing.
Bone tissue was extracted using a dual threshold. A part of the bone tissue is extracted first by using a large threshold (400), and then the extraction of the bone tissue is continued around the extracted bone tissue by using a low threshold (150).
And (3) performing morphology and cavity filling treatment on the result obtained in the last step, then taking the maximum communication area to obtain bone tissues close to the spine, and removing rib parts.
On the sagittal plane, the mass center point of the bone in the x direction is calculated, and the mass center point of each line is extracted within a certain range close to the mass center point (if a certain line has no bone point, the mass center point is not extracted). This step is segmented in the sagittal plane, since the position of the spine is well defined in the sagittal plane.
And (4) performing curve fitting on the basis of the centroid points obtained in the last step to obtain a continuous curve and a width value of a continuous skeleton x axis.
And obtaining the inner contour line near the spine according to the obtained centroid curve and the width value in the last step, and further correcting the inner contour line of the inner contour region.
Muscle tissue portions are obtained from the obtained inner and outer contours.
4) The adipose tissue obtained from step 1 is divided into 2 portions by the muscular tissue obtained from step 3. Inside the muscle tissue is the visceral fat portion and outside the muscle fat is the subcutaneous tissue portion.
The specific method comprises the following steps:
filling the cavity in the muscle tissue area obtained in the step 3).
The fat region obtained in step 1) belongs to the visceral tissue region if it is also in the filling region in step 41), otherwise it belongs to the subcutaneous tissue region.
The intra-abdominal muscle and fat sections of a plurality of patients were processed according to the above procedure, and the segmentation results are shown in fig. 2 (red is subcutaneous tissue, blue is muscle tissue, and green is visceral tissue portion).
As can be seen from the results of fig. 2, the method can segment the muscle and fat portions of all slices at once, and ensures a higher accuracy.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (5)
1. An automatic intra-abdominal muscle and fat image segmentation method for simultaneously segmenting pixel information of abdominal muscle tissue, visceral fat and subcutaneous fat tissue, the method comprising the following steps:
1) classifying pixels, namely classifying pixel values by using a conditional iteration model segmentation method to obtain pixel value ranges of muscle tissues and fat tissues;
2) removing in vitro pixels on the basis of the step 1);
3) extracting a muscle tissue pixel area on the result of the step 1);
4) the fat tissue obtained from the step 1) is divided into 2 parts by the muscle tissue obtained from the step 3); the visceral fat portion is inside the muscle tissue and the subcutaneous tissue portion is outside the muscle fat;
the step 3) is specifically as follows:
31) obtaining a region enclosed by the muscle outer contour according to the classification result of 1) and a level set algorithm, morphology and a cavity filling processing method;
32) contracting the outer contour obtained in the step 31) inwards by 25mm, and obtaining a primary inner contour region by utilizing a muscle CT value;
33) extracting bone tissues by using a double threshold, namely extracting partial bone tissues by using a larger threshold 400, and continuously extracting the bone tissues by using a low threshold 150 around the extracted bone tissues;
34) performing morphology and cavity filling treatment on the result obtained in the step 33), then taking the maximum communication area to obtain bone tissues close to the spine, and removing rib parts;
35) on a sagittal plane, calculating a mass center point of a skeleton in the x direction, extracting the mass center point of each row within a certain range close to the mass center point, and if a certain row has no skeleton point, not extracting;
36) performing curve fitting on the basis of the centroid points obtained in the step 35) to obtain a continuous curve and a width value of a continuous skeleton x axis;
37) obtaining a centroid curve and a width value according to 36) to obtain an inner contour line near the spine; further correcting 32) the inner contour of the inner contour region;
38) and obtaining the pixel area of the muscle tissue part according to the obtained inner and outer contour lines.
2. The method of claim 1, wherein the intra-abdominal fat pixel value range classification is performed by a conditional iterative model segmentation method.
3. The method of claim 1, wherein the step 1) is specifically as follows:
11) the CT value of the muscle tissue 082323hu ranges from-29,150, the CT value of the fat tissue ranges from-190 to-30, the CT value is taken as an initial value of fat and muscle tissue categories in the conditional iterative model segmentation method, and the number of classification categories is 4; the background part is divided into a low-brightness background and a high-brightness background;
12) calculating the pixel mean value of each category;
13) defining an image energy formula, including an image gray level energy value and a label energy value, and calculating the energy value of each pixel point under different categories;
14) selecting the category of the maximum energy value as a new classification result of the pixel points;
15) the calculations (11-14) are iterated until the result converges or the number of iterations reaches a maximum value.
4. The method of claim 1, wherein the step 2) is specifically:
21) taking the part of the non-low bright background in the classification result of 1) as a new segmentation result;
22) filling the inner cavity with the result of 21) layer by layer;
23) and selecting the maximum connected area from the result of 22), namely obtaining the pixel area of the abdominal part.
5. The method of claim 1, wherein the step 4) is specifically:
41) filling the muscle tissue area obtained in the step 3);
42) the fat area obtained in the step 1) belongs to the visceral tissue area when being in the filling area in the step 41);
43) the fat region obtained in step 1) is not in the filling region in step 41), and belongs to the subcutaneous tissue region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811397835.XA CN109523561B (en) | 2018-12-19 | 2018-12-19 | Automatic intra-abdominal muscle and fat image segmentation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811397835.XA CN109523561B (en) | 2018-12-19 | 2018-12-19 | Automatic intra-abdominal muscle and fat image segmentation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109523561A CN109523561A (en) | 2019-03-26 |
| CN109523561B true CN109523561B (en) | 2021-04-02 |
Family
ID=65778696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811397835.XA Active CN109523561B (en) | 2018-12-19 | 2018-12-19 | Automatic intra-abdominal muscle and fat image segmentation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109523561B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110179488B (en) * | 2019-06-11 | 2023-06-02 | 西北农林科技大学 | Method for detecting pig living body carcass composition by using CT scanning data |
| CN110610497B (en) * | 2019-08-05 | 2023-06-16 | 史记生物技术(南京)有限公司 | Method for determining content of living pig carcass tissue based on CT image processing |
| CN112168211A (en) * | 2020-03-26 | 2021-01-05 | 成都思多科医疗科技有限公司 | Fat thickness and muscle thickness measuring method and system of abdomen ultrasonic image |
| CN112037234B (en) * | 2020-08-19 | 2022-09-30 | 大连理工大学 | Method for separating liver from muscle in CT image by using bone information |
| CN116087195B (en) * | 2023-03-06 | 2023-06-16 | 华南师范大学 | Fish freshness evaluation method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1767788A (en) * | 2003-04-08 | 2006-05-03 | 株式会社日产医药 | Apparatus and method of supporting diagnostic imaging for medical use |
| CN103180876A (en) * | 2010-10-19 | 2013-06-26 | 皇家飞利浦电子股份有限公司 | Medical imaging system, computer-implemented method, and computer program product for identifying treated region in medical image |
| CN105405129A (en) * | 2015-10-31 | 2016-03-16 | 上海联影医疗科技有限公司 | Reconstruction method and device of medical image |
| CN105427273A (en) * | 2014-09-19 | 2016-03-23 | 香港中文大学深圳研究院 | Abdominal fat segmentation method and device based on nuclear magnetic resonance image |
| CN105433988A (en) * | 2015-12-28 | 2016-03-30 | 深圳开立生物医疗科技股份有限公司 | Target image recognition method and device and ultrasonic equipment thereof |
| CN106971392A (en) * | 2017-03-17 | 2017-07-21 | 国家测绘地理信息局卫星测绘应用中心 | A kind of combination DT CWT and MRF method for detecting change of remote sensing image and device |
| CN107527339A (en) * | 2017-08-21 | 2017-12-29 | 上海联影医疗科技有限公司 | A kind of magnetic resonance scanning method, apparatus and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9895126B2 (en) * | 2015-09-02 | 2018-02-20 | Mayo Foundation For Medical Education And Research | System and method for quantification of muscle and fat using abdominal CT imaging |
-
2018
- 2018-12-19 CN CN201811397835.XA patent/CN109523561B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1767788A (en) * | 2003-04-08 | 2006-05-03 | 株式会社日产医药 | Apparatus and method of supporting diagnostic imaging for medical use |
| CN103180876A (en) * | 2010-10-19 | 2013-06-26 | 皇家飞利浦电子股份有限公司 | Medical imaging system, computer-implemented method, and computer program product for identifying treated region in medical image |
| CN105427273A (en) * | 2014-09-19 | 2016-03-23 | 香港中文大学深圳研究院 | Abdominal fat segmentation method and device based on nuclear magnetic resonance image |
| CN105405129A (en) * | 2015-10-31 | 2016-03-16 | 上海联影医疗科技有限公司 | Reconstruction method and device of medical image |
| CN105433988A (en) * | 2015-12-28 | 2016-03-30 | 深圳开立生物医疗科技股份有限公司 | Target image recognition method and device and ultrasonic equipment thereof |
| CN106971392A (en) * | 2017-03-17 | 2017-07-21 | 国家测绘地理信息局卫星测绘应用中心 | A kind of combination DT CWT and MRF method for detecting change of remote sensing image and device |
| CN107527339A (en) * | 2017-08-21 | 2017-12-29 | 上海联影医疗科技有限公司 | A kind of magnetic resonance scanning method, apparatus and system |
Non-Patent Citations (4)
| Title |
|---|
| 《Unsupervised partial volume estimation using 3D and statistical priors》;Pierre Martin Tardif;《Medical Imaging 2001》;20010703;第1004-1014页 * |
| 《人体体成份分析中的MR图像处理》;龚也君;《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》;20050815(第04期);第I138-265页 * |
| 《多相期增强CT中肝内血管的自动分割》;袁戎 等;《中国图像图形学报》;20160916;第21卷(第9期);第1238-1246页 * |
| 《腹部CT图像肾脏自动分割方法研究》;赵于前 等;《计算机应用研究》;20100430;第27卷(第4期);第1591-1593页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109523561A (en) | 2019-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109523561B (en) | Automatic intra-abdominal muscle and fat image segmentation method | |
| Rusko et al. | Fully automatic liver segmentation for contrast-enhanced CT images | |
| Park et al. | Skull stripping based on region growing for magnetic resonance brain images | |
| Lassen et al. | Automatic segmentation of the pulmonary lobes from chest CT scans based on fissures, vessels, and bronchi | |
| CN109064476B (en) | CT chest radiography lung tissue image segmentation method based on level set | |
| CN108664976B (en) | Super-pixel-based fuzzy spectral clustering brain tumor image automatic segmentation method | |
| EP2598033B1 (en) | Knowledge-based automatic image segmentation | |
| CN109753997B (en) | Automatic accurate robust segmentation method for liver tumor in CT image | |
| CN110223271B (en) | Automatic level set segmentation method and device for blood vessel image | |
| Chen et al. | Pathological lung segmentation in chest CT images based on improved random walker | |
| CN103942780B (en) | Based on the thalamus and its minor structure dividing method that improve fuzzy connectedness algorithm | |
| CN104504737A (en) | Method for obtaining three-dimensional tracheal tree from lung CT (computed tomography) images | |
| CN104637056B (en) | Medicine CT image adrenal tumor dividing method based on rarefaction representation | |
| Fan et al. | Lung nodule detection based on 3D convolutional neural networks | |
| CN106780377B (en) | Contour smoothing method based on Freeman chain code in medical image segmentation | |
| Oliver et al. | One-shot segmentation of breast, pectoral muscle, and background in digitised mammograms | |
| CN111145185B (en) | Lung substance segmentation method for extracting CT image based on clustering key frame | |
| CN110288581B (en) | Segmentation method based on model for keeping shape convexity level set | |
| CN112712540B (en) | Lung bronchus extraction method based on CT image | |
| CN103236062B (en) | Based on the magnetic resonance image (MRI) blood vessel segmentation system in human brain tumour's nuclear-magnetism storehouse | |
| CN107610145A (en) | A kind of automatic pancreas dividing method based on adaptive threshold and template matches | |
| CN112037234B (en) | Method for separating liver from muscle in CT image by using bone information | |
| Zhou et al. | A robust approach for automated lung segmentation in thoracic CT | |
| Özsavaş et al. | Automatic segmentation of anatomical structures from CT scans of thorax for RTP | |
| CN112767333A (en) | CTA (computed tomography angiography) image-based double-lower-limb blood vessel region judgment method and system |
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: 20210222 Address after: Room 08, 18 / F, unit 1, building 1, jindihua mansion, 12 yujiahu Road, Donghu New Technology Development Zone, Wuhan City, Hubei Province, 430000 Applicant after: Ruijia (Wuhan) Software Technology Co.,Ltd. Address before: Room 101-41, 1559 zhuanxing East Road, Minhang District, Shanghai Applicant before: RUIREN JIAXIN (SHANGHAI) TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |