CN101138498A - Image processing process based on magnetic resonance three-dimensional renogram - Google Patents
Image processing process based on magnetic resonance three-dimensional renogram Download PDFInfo
- Publication number
- CN101138498A CN101138498A CNA2007101759974A CN200710175997A CN101138498A CN 101138498 A CN101138498 A CN 101138498A CN A2007101759974 A CNA2007101759974 A CN A2007101759974A CN 200710175997 A CN200710175997 A CN 200710175997A CN 101138498 A CN101138498 A CN 101138498A
- Authority
- CN
- China
- Prior art keywords
- image
- kidney
- magnetic resonance
- dimensional
- phase
- 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.)
- Granted
Links
Images
Landscapes
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The present invention relates to an image processing method which bases on a magnetic resonance three-dimensional renogram. The present invention includes the steps mentioned below. Firstly, a magnetic resonance three-dimensional scanning image of kidneys is read from a magnetic resonance workstation. Secondly, every phase image number and background phase, a cortex and medulla demarcation phase and a holonephros phase are ensured. Thirdly, relative vascular and renal pelvis regions in the image of the holonephros phase are excised. Fourthly, a holonephros contour is identified. The fifth step is to match the background phase with the cortex and medulla demarcation phase and silhouette. The sixth step is to segment the medulla and the cortex of the kidneys. The seventh step is to match the images of all phases. The present invention provides a novel kidney dynamic reinforced image segment and match scheme and can precisely correct the motions caused by the breath of the kidneys during the MRI image obtaining process and precisely segment the cortex and the medulla. The image processing method of the present invention is proved by the practices to be capable of obtaining the reasonable three-dimensional magnetic resonance renogram. The present invention can be widely applied to the image processing of the magnetic resonance renogram.
Description
Technical Field
The invention relates to a magnetic resonance image processing method, in particular to an image processing method based on a magnetic resonance three-dimensional nephrogram.
Background
MRI (Magnetic Resonance Imaging) dynamic enhancement scanning is used as a safe kidney function evaluation mode, can be used for evaluating the perfusion and filtration functions of the kidney, and has important clinical application prospect. In the MR (Magnetic Resonance) dynamic scan of the kidney, the Magnetic Resonance contrast agent sequentially passes through the cortex, medulla and collecting system of the kidney, the change of the signal intensity of the contrast agent in different regions with respect to time can reflect certain functions of the region, and the time-signal intensity curve formed by plotting the change of the signal intensity is called MRR (Magnetic Resonance imaging), also called Magnetic Resonance nephrogram. The magnetic resonance nephrogram has high spatial resolution, can clearly distinguish the renal cortex and medulla, and has no radioactive damage to patients in the examination process. If the MRR curves of cortex and medulla can be analyzed separately or synthetically, and the corresponding relation is established between the signal intensity of the image and the concentration of the contrast agent, then important indexes such as glomerular filtration rate and the like can be obtained, and a set of quantitative analysis system is further established to obtain index parameters corresponding to different types of kidney diseases, thereby providing important basis for the diagnosis of the kidney diseases.
In the process of collecting the kidney dynamic enhanced scanning of MRR, the abdomen of a patient is repeatedly and rapidly scanned, multi-time phase data can be obtained, a magnetic resonance nephrogram is drawn, and the total scanning time can reach 2-4 minutes. In the magnetic resonance images acquired at different times, because the kidney can be displaced to a certain extent along with the respiratory motion of the examined person, the partial volume effect of the MRR automatically drawn on the basis can be obvious, thereby influencing the accuracy of the MRR. To obtain an accurate MRR, the dynamic enhanced images of different phases need to be registered. Most of the medical image post-processing software used in hospitals at present is medical image post-processing software attached to an MRI workstation, and no workstation has been available so far, which can carry out targeted special processing on renal perfusion images, especially the correction of respiratory motion and the accurate division of renal parenchyma; the results in this respect are only on a research level, even abroad. Because the image movement caused by respiration cannot be corrected and the cortical medulla can be automatically and efficiently segmented, the nephrogram has larger error, valuable clinical information is difficult to provide, and the difficulty is brought to subsequent research.
At present, doctors can only acquire an interested region and analyze data by manually sketching a single image, but the number of three-dimensional renal perfusion images scanned by a sequence LAVA (liver three-dimensional volume ultra-fast multi-phase dynamic enhanced imaging technology) is huge, and foreign researches show that if the registration and segmentation of the images are all manually performed by researchers, about 2-3 hours are needed for processing the image of one patient, and the workload is not allowed in time and the intensity is too large for clinical application. Therefore, efficient and accurate identification and correction of the movement caused by respiration and accurate segmentation of cortical medulla become a very critical issue in current magnetic resonance nephrogram research.
Disclosure of Invention
In view of the above problems, an object of the present invention is to provide an image processing method based on a magnetic resonance three-dimensional kidney image, which can more accurately correct the movement of the kidney caused by respiration, and can accurately segment the cortex and medulla, so as to obtain a reasonable three-dimensional magnetic resonance kidney image and provide an important basis for the diagnosis of kidney diseases.
In order to achieve the purpose, the invention adopts the following technical scheme: an image processing method based on a magnetic resonance three-dimensional nephrogram comprises the following steps: (1) Reading a magnetic resonance three-dimensional scanning image of the kidney from a magnetic resonance workstation; (2) Determining the number of images in each time phase, a background time phase, a cortex and medulla boundary time phase and a whole kidney time phase; (3) Resecting relevant vessels and the renal pelvis region in a whole renal phase image; (4) identifying a whole kidney contour; (5) Matching the background time phase with the cortex and medulla demarcation time phase, and silhouette; (6) segmenting the cortex and medulla of the kidney; (7) matching the images of all phases.
Wherein the step (4) of obtaining the whole kidney contour by adopting a region growing method comprises the following steps: (1) the user selects one or a plurality of seed points P1, P2, P3, …, pn which fall in the kidney region in the whole kidney time phase; (2) taking a point Pi from all the seed points as a starting point of the region growth; (3) calculating the growth threshold value T of the seed point; (4) calculating the difference between the gray value of each point in the neighborhood of the current seed point 26 and the gray value of the worker, if the difference is smaller than the growth threshold value of the current seed point, merging the point into a result area, and calculating the point as a new seed point; (5) and (5) repeating the operations of the steps (2), (3) and (4) until the result area cannot grow.
And judging a seed point growth threshold T by adopting a linear calculation method, and enabling T = I × k, wherein I is an average value of the gray scale of a result region obtained by increasing the current region, and k is a slope set by a user.
In the step (5), the matching background time phase and the cortex-medullary demarcation time phase are obtained by using a cortex region as a template, and expanding the traditional two-dimensional correlation matching based on a correlation coefficient to a three-dimensional correlation coefficient, wherein the three-dimensional correlation coefficient is calculated according to the following formula:
wherein r, s, t, three-dimensional coordinates of pixels representing the cortical region, and f (r, s, t) is a known imageThe gray scale values of the pixels of the cortical region,
is the gray average value of the pixels in the cortical region of the known image, x, y and z are the coordinates of the translation of the kidney in the three-dimensional image to be matched, w (x + r, y + s, z + t) is the gray value of the corresponding point in the image to be matched after the cortical translation,
is the mean value thereof. Rho (x, y, z) is the calculated correlation coefficient, and rho (x, y, z) epsilon [ -1,1]。
Due to the adoption of the technical scheme, the invention has the following advantages: 1. the invention can correct the movement of the kidney caused by respiration in the MRI image acquisition process more accurately and can segment the cortex accurately, so the image space resolution is high and the MRR is more accurate. 2. The invention can analyze MRR curves of cortex and medulla separately or synthetically, and establishes a corresponding relation between the signal intensity of the image and the concentration of the contrast agent, so that the quantitative analysis of the MRR diagram becomes possible, and an important basis is provided for kidney diagnosis. 3. The invention can efficiently and accurately identify and correct the movement caused by breathing and accurately segment cortical medulla, thereby saving time and reducing working intensity. 4. The invention provides a cutting method aiming at the condition that the image is three-dimensional and has more layers to be processed, so that the complexity of the step can be greatly simplified.
Drawings
FIG. 1 is a flow chart of the present invention
FIG. 2 is a diagram of a run program launch interface
FIG. 3 is an interface diagram of selecting a list of images to be processed
FIG. 4 is an interface diagram of time phase length setting
FIG. 5 is an interface diagram of a time-sharing phase display image set structure
FIG. 6 is an interface diagram of entering a user selected specific phase number (background, CMD, whole kidney)
FIG. 7 is an interface diagram for confirming correct input phase number
FIG. 8 is a pop-up image window
FIG. 9 is a schematic view of a kidney contour obtained by confirmation and modification
FIG. 10 is a diagram showing the segmentation result of the cortical and medullary region
FIG. 11 is a graph showing the change in concentration of a contrast agent
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and examples.
As shown in fig. 1, the image processing method of a magnetic resonance three-dimensional nephrogram based on region growing and correlation matching according to the present invention has the following specific operation procedures:
the first step is as follows: the program is run, a program interface appears (as shown in fig. 2), an image processing module is called, an image directory to be processed (as shown in fig. 3) is selected, an image is read, and an MRI image obtained from the magnetic resonance workstation is in a DICOM (Digital Imaging Communications in Medicine) format.
A DICOM file refers to a medical file stored in compliance with the DICOM standard. The DICOM header contains information about the identification data set, in other words, much information about the image is stored in the header. Since the sequence of the file names of DICOM images and the order of the images in the scan do not coincide, it is a prerequisite for us to acquire the correct image number, which is stored in a label named instant number, for processing the images. By reading the value of InstanceNumber, the images can be correctly sequenced and prepared for the next processing.
The second step is that: the user enters parameters related to the currently processed image sequence, including the number of images per phase, the back Jing Shixiang, the CMD (corticocancephaly differentiation) phase, the whole kidney phase, the start and end images of the kidney in each phase. The specific operation steps are as follows:
1. input phase length (as shown in fig. 4);
2. a time-divisional phase display image set structure (shown in fig. 5);
3. inputting a specific phase number selected by the user, the phase number including background, CMD, and whole kidney (as shown in fig. 6);
4. the input phase number is confirmed to be correct (as shown in fig. 7).
The third step: a pop-up image window selects a point in the central region of the kidney by double clicking the mouse (as shown in fig. 8).
The fourth step: the resulting kidney contour is confirmed and modified, and a renal pelvis clearance operation is performed as necessary (as shown in fig. 9). In certain aspects of the whole kidney phase, these tissues and cortex are visualized simultaneously due to the presence of contrast agents in the renal vessels, renal pelvis, and renal calyces; in addition, some parts of the liver and spleen and intestinal tract of some patients are closely related to the kidney on the image, which brings great difficulty to the identification of the kidney contour, so that it is necessary to separate regions that may affect the segmentation result, especially the renal pelvis and vascular parts, from the kidney parenchyma before the whole kidney contour identification is performed.
After necessary cleaning, a region growing method is provided for acquiring a whole kidney contour, and the specific steps are as follows:
1. the user selects one or several seed points P1, P2, P3, …, pn (the seed points should fall in the kidney region) in the whole kidney phase;
2. selecting a point Pi from all the seed points as a starting point of the current region growth;
3. calculating the seed point growth threshold T: in the traditional method, T is a fixed threshold value, and an ideal result can be obtained only by adjusting for many times when different images are processed. In the kidney region, the average value of the regional gray scale is larger, so that the discrimination threshold value is larger, and certain dark points caused by noise can be merged; at the edge of the kidney region, the gray scale of the pixel point is rapidly reduced, and the judgment threshold value is also rapidly reduced due to the reduction of the region mean value, so that the overgrowth can be effectively prevented.
4. And calculating the difference of the gray values of each point and I in the neighborhood of the current seed point 26 (a set of 26 pixel points adjacent to the point in the image space), and if the difference is smaller than the growth threshold of the current seed point, merging the point into a result area and calculating the point as a new seed point.
5. Repeating the operations 2, 3 and 4 until the result area can not grow.
The fifth step: the user confirms the result of the segmentation of the corticocancellous region, including silhouette, pre-matching, corticocancellous region segmentation and contour saturation adjustment (as shown in fig. 10).
The image silhouette is obtained by subtracting the images of the CMD time phase and the background time phase of the same section, so that the influence of a background signal can be removed in the CMD time phase, the display of a contrast agent signal is highlighted, the contrast of the image is improved, and the subsequent identification and segmentation of cortex and medulla are facilitated.
The signal intensity of the cortex and medulla varies at different times due to the different concentrations of contrast agent, and the trend of the change in the brightness of the cortex and medulla is very different. The traditional correlation coefficient matching method uses an m × n sub-image as a template, and is suitable for a static image, so that the method is not suitable for matching a dynamic kidney enhancement image. Considering that the signal intensity of the whole cortex area changes relatively uniformly along with the change of the concentration of the contrast agent in the whole dynamic enhancement process, the traditional template matching mode is improved, the cortex area is used as a template, and meanwhile, the traditional two-dimensional correlation matching based on the correlation coefficient is expanded to three dimensions, so that the accuracy of the matching result is further enhanced. When the images are matched, the images with different time phases and the same section are taken out to obtain two corresponding pixel point sets according to the moving template, the correlation coefficient of the two point sets is calculated by applying a correlation coefficient calculation formula, the original image is adjusted according to the displacement of the image template corresponding to the maximum correlation coefficient, and the image matching between the two time phases is completed.
The three-dimensional correlation coefficient calculation formula used by the invention is as follows:
wherein r, s, t represents the three-dimensional coordinates of the cortical region pixels, f (r, s, t) is the gray scale value of the cortical region pixels of the known image,
is the gray average value of the pixels in the cortical area of the known image, x, y and z are the coordinates of the translation of the kidney in the three-dimensional image to be matched, w (x + r, y + s, z + t) is the gray value of the corresponding point in the image to be matched after the translation of the cortex,
is the average thereof. Rho (x, y, z) is the calculated correlation coefficient, and rho (x, y, z) epsilon [ -1,1]。
And a sixth step: still adopting a region growing segmentation method for the segmentation of cortex and medulla, taking the matched whole kidney region as a mask, and only growing the medulla in the mask. The user selects a proper seed point in medulla to obtain medullary region, the rest region can be regarded as cortex, and the result of dividing cortex and medullary makes it possible to match cortex region as template.
The seventh step: according to the three-dimensional correlation coefficient matching method, a cortex area is used as a template, all time phases are sequentially matched with the nearest matched time phase from a whole kidney time phase, and the result shows that the movement caused by breathing in all time phases is well identified. The contrast agent concentration profile shows that the profile includes three concentration profiles, whole kidney, medulla and cortex (as shown in figure 11).
As shown in fig. 1, the renal automated analysis toolkit call returns after the user is satisfied with the graph taken.
Claims (4)
1. An image processing method based on a magnetic resonance three-dimensional nephrogram comprises the following steps:
(1) Reading a magnetic resonance three-dimensional scanning image of the kidney from a magnetic resonance workstation;
(2) Determining the number of images in each time phase, a background time phase, a cortex and medulla boundary time phase and a whole kidney time phase;
(3) Resecting relevant vessels and a renal pelvis region in a whole kidney phase image;
(4) Identifying a whole kidney contour;
(5) Matching a background time phase with a cortex medulla boundary time phase, and silhouetteing;
(6) Segmenting the cortex and medulla of the kidney;
(7) The images of all phases are matched.
2. An image processing method based on a magnetic resonance three-dimensional kidney image as set forth in claim 1, characterized in that: wherein the step (4) of obtaining the whole kidney contour by adopting a region growing method comprises the following steps:
(1) the user selects one or a plurality of seed points P1, P2, P3, …, pn which fall in the kidney region in the whole kidney time phase;
(2) taking a point Pi from all the seed points as a starting point of the region growth;
(3) calculating the growth threshold value T of the seed point;
(4) calculating the difference of the gray values of each point and I in the neighborhood of the current seed point 26, if the difference is smaller than the growth threshold value of the current seed point, merging the point into a result area, and calculating as a new seed point;
(5) and (4) repeating the operations of the steps (2), (3) and (4) until the result area cannot be increased.
3. An image processing method based on a magnetic resonance three-dimensional kidney image as set forth in claim 2, characterized in that: and judging a seed point growth threshold T by adopting a linear calculation method, and enabling T = I × k, wherein I is an average value of the gray scale of a result region obtained by increasing the current region, and k is a slope set by a user.
4. An image processing method based on a magnetic resonance three-dimensional kidney image as set forth in claim 1, characterized in that: in the step (5), the matching background time phase and the cortical medullary boundary time phase take a cortical region as a template, and the traditional two-dimensional correlation matching based on the correlation coefficient is expanded to three dimensions, and the three-dimensional correlation coefficient calculation formula is as follows:
wherein r, s, t represents the three-dimensional coordinates of the cortical region pixels, f (r, s, t) is the gray scale value of the cortical region pixels of the known image,
the mean value of the gray levels of the pixels of the cortical region of the known image, x, y, z being the mean of the kidney in the three-dimensional image to be matchedThe shifted coordinates w (x + r, y + s, z + t) are the gray values of corresponding points in the image to be matched after the cortex is translated,
is the average thereof. Rho (x, y, z) is the calculated correlation coefficient, and rho (x, y, z) epsilon [ -1,1]。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200710175997A CN100586371C (en) | 2007-10-17 | 2007-10-17 | Image processing process based on magnetic resonance three-dimensional renogram |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200710175997A CN100586371C (en) | 2007-10-17 | 2007-10-17 | Image processing process based on magnetic resonance three-dimensional renogram |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101138498A true CN101138498A (en) | 2008-03-12 |
| CN100586371C CN100586371C (en) | 2010-02-03 |
Family
ID=39190718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200710175997A Expired - Fee Related CN100586371C (en) | 2007-10-17 | 2007-10-17 | Image processing process based on magnetic resonance three-dimensional renogram |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100586371C (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102103197A (en) * | 2009-12-16 | 2011-06-22 | 西门子公司 | Method to determine a background phase in phase image data sets |
| CN101612041B (en) * | 2008-06-26 | 2011-12-07 | 西门子（中国）有限公司 | Computer assistant method and computer assistant device |
| CN101702232B (en) * | 2009-10-16 | 2012-01-11 | 昆明理工大学 | Respiration correction technique in positron emission tomography |
| CN102332164A (en) * | 2011-10-31 | 2012-01-25 | 中国科学院自动化研究所 | Method for segmenting renal cortex images |
| CN102508025A (en) * | 2010-05-13 | 2012-06-20 | 特克特朗尼克公司 | Signal recognition and triggering using computer vision techniques |
| CN101711670B (en) * | 2008-10-02 | 2013-05-01 | 西门子公司 | Method for determining a kidney function parameter |
| CN103892854A (en) * | 2012-12-28 | 2014-07-02 | 上海联影医疗科技有限公司 | Digital medical image processing method and device |
| CN104318567A (en) * | 2014-10-24 | 2015-01-28 | 东北大学 | Method for segmenting kidney blood vessel atrioventricular on basis of medical images |
| CN104809730A (en) * | 2015-05-05 | 2015-07-29 | 上海联影医疗科技有限公司 | Method and device for extracting trachea from chest CT (computed tomography) image |
| CN105005012A (en) * | 2015-06-05 | 2015-10-28 | 北京大学 | Abdominal organ dynamic contrast enhanced magnetic resonance imaging method based on compressed sensing |
| CN106204409A (en) * | 2014-10-31 | 2016-12-07 | 株式会社Pfu | Image processing apparatus and image processing method |
| CN106780643A (en) * | 2016-11-21 | 2017-05-31 | 清华大学 | Magnetic resonance repeatedly excites diffusion imaging to move antidote |
| CN107106103A (en) * | 2015-01-07 | 2017-08-29 | 皇家飞利浦有限公司 | Iteration digital phase detecting circuit for embolism flow |
| CN108596933A (en) * | 2018-04-20 | 2018-09-28 | 北京大学 | A kind of kidney dynamic image full-automatic partition method for having supervision that need not be marked |
| US10181191B2 (en) | 2014-12-02 | 2019-01-15 | Shanghai United Imaging Healthcare Co., Ltd. | Methods and systems for identifying spine or bone regions in computed tomography image sequence |
| CN112426143A (en) * | 2020-11-16 | 2021-03-02 | 清华大学 | Renal artery and abdominal aorta one-stop type noninvasive magnetic resonance blood vessel wall imaging system |
-
2007
- 2007-10-17 CN CN200710175997A patent/CN100586371C/en not_active Expired - Fee Related
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101612041B (en) * | 2008-06-26 | 2011-12-07 | 西门子（中国）有限公司 | Computer assistant method and computer assistant device |
| CN101711670B (en) * | 2008-10-02 | 2013-05-01 | 西门子公司 | Method for determining a kidney function parameter |
| CN101702232B (en) * | 2009-10-16 | 2012-01-11 | 昆明理工大学 | Respiration correction technique in positron emission tomography |
| CN102103197B (en) * | 2009-12-16 | 2015-08-26 | 西门子公司 | The defining method of background phase in phase image data group |
| CN102103197A (en) * | 2009-12-16 | 2011-06-22 | 西门子公司 | Method to determine a background phase in phase image data sets |
| CN102508025B (en) * | 2010-05-13 | 2015-12-02 | 特克特朗尼克公司 | Use Signal analysis and the triggering of computer vision technique |
| CN102508025A (en) * | 2010-05-13 | 2012-06-20 | 特克特朗尼克公司 | Signal recognition and triggering using computer vision techniques |
| CN102332164A (en) * | 2011-10-31 | 2012-01-25 | 中国科学院自动化研究所 | Method for segmenting renal cortex images |
| CN103892854A (en) * | 2012-12-28 | 2014-07-02 | 上海联影医疗科技有限公司 | Digital medical image processing method and device |
| CN104318567A (en) * | 2014-10-24 | 2015-01-28 | 东北大学 | Method for segmenting kidney blood vessel atrioventricular on basis of medical images |
| CN104318567B (en) * | 2014-10-24 | 2017-05-10 | 东北大学 | Method for segmenting kidney blood vessel atrioventricular on basis of medical images |
| CN106204409A (en) * | 2014-10-31 | 2016-12-07 | 株式会社Pfu | Image processing apparatus and image processing method |
| US10181191B2 (en) | 2014-12-02 | 2019-01-15 | Shanghai United Imaging Healthcare Co., Ltd. | Methods and systems for identifying spine or bone regions in computed tomography image sequence |
| US11094067B2 (en) | 2014-12-02 | 2021-08-17 | Shanghai United Imaging Healthcare Co., Ltd. | Method and system for image processing |
| CN107106103A (en) * | 2015-01-07 | 2017-08-29 | 皇家飞利浦有限公司 | Iteration digital phase detecting circuit for embolism flow |
| US10282844B2 (en) | 2015-05-05 | 2019-05-07 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for image segmentation |
| US10482602B2 (en) | 2015-05-05 | 2019-11-19 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for image segmentation |
| CN104809730A (en) * | 2015-05-05 | 2015-07-29 | 上海联影医疗科技有限公司 | Method and device for extracting trachea from chest CT (computed tomography) image |
| CN105005012A (en) * | 2015-06-05 | 2015-10-28 | 北京大学 | Abdominal organ dynamic contrast enhanced magnetic resonance imaging method based on compressed sensing |
| CN105005012B (en) * | 2015-06-05 | 2017-09-26 | 北京大学 | Abdomen organ's Dynamic constrasted enhancement MR imaging method based on compressed sensing |
| CN106780643A (en) * | 2016-11-21 | 2017-05-31 | 清华大学 | Magnetic resonance repeatedly excites diffusion imaging to move antidote |
| CN106780643B (en) * | 2016-11-21 | 2019-07-26 | 清华大学 | Magnetic resonance repeatedly excites diffusion imaging to move antidote |
| CN108596933A (en) * | 2018-04-20 | 2018-09-28 | 北京大学 | A kind of kidney dynamic image full-automatic partition method for having supervision that need not be marked |
| CN108596933B (en) * | 2018-04-20 | 2022-03-25 | 北京大学 | Method for fully automatically segmenting supervised dynamic kidney image without marking |
| CN112426143A (en) * | 2020-11-16 | 2021-03-02 | 清华大学 | Renal artery and abdominal aorta one-stop type noninvasive magnetic resonance blood vessel wall imaging system |
| CN112426143B (en) * | 2020-11-16 | 2021-07-23 | 清华大学 | Renal artery and abdominal aorta one-stop type noninvasive magnetic resonance blood vessel wall imaging system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100586371C (en) | 2010-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101138498A (en) | Image processing process based on magnetic resonance three-dimensional renogram | |
| CN103249358B (en) | Medical image-processing apparatus | |
| US7315639B2 (en) | Method of lung lobe segmentation and computer system | |
| US9384555B2 (en) | Motion correction apparatus and method | |
| US20030086596A1 (en) | Method, computer software, and system for tracking, stabilizing, and reporting motion between vertebrae | |
| US20090285466A1 (en) | Method, Computer Software, And System For Tracking, Stabilizing, And Reporting Motion Between | |
| CN106846346B (en) | Method for rapidly extracting pelvis outline of sequence CT image based on key frame mark | |
| RU2589461C2 (en) | Device for creation of assignments between areas of image and categories of elements | |
| CN107316334B (en) | Personalized precise magnetic resonance imaging method | |
| CN111325754B (en) | Automatic lumbar vertebra positioning method based on CT sequence image | |
| CN112927187A (en) | Method for automatically identifying and positioning focal cortical dysplasia epileptic focus | |
| CN110956634A (en) | Deep learning-based automatic detection method and system for cerebral microhemorrhage | |
| CN106780491B (en) | Initial contour generation method adopted in segmentation of CT pelvic image by GVF method | |
| CN114419181A (en) | CTA image reconstruction method and device, display method and device | |
| CN106780492B (en) | Method for extracting key frame of CT pelvic image | |
| CN114847922A (en) | Brain age prediction method based on automatic fiber bundle identification | |
| CN116580033B (en) | Multi-mode medical image registration method based on image block similarity matching | |
| CN110648333B (en) | Real-time segmentation system of mammary gland ultrasonic video image based on middle-intelligence theory | |
| US10043269B2 (en) | Medical image processing apparatus, medical image diagnostic apparatus, medical image processing method, and ultrasonic image processing method | |
| EP1447772B1 (en) | A method of lung lobe segmentation and computer system | |
| CN114862799B (en) | Full-automatic brain volume segmentation method for FLAIR-MRI sequence | |
| Zikic et al. | Automatic alignment of renal DCE-MRI image series for improvement of quantitative tracer kinetic studies | |
| CN109993754B (en) | Method and system for skull segmentation from images | |
| CN114202512A (en) | Ultrasonic contrast quantitative analysis method, system and computer readable storage medium for dynamic follow-up tumor local radiotherapy and chemotherapy effect | |
| Agostini et al. | Evaluation of feature-based registration in dynamic infrared imaging for breast cancer diagnosis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100203 Termination date: 20121017 |