CN114820754B - Automatic positioning method for four-cavity heart based on template matching - Google Patents
Automatic positioning method for four-cavity heart based on template matching Download PDFInfo
- Publication number
- CN114820754B CN114820754B CN202210571524.0A CN202210571524A CN114820754B CN 114820754 B CN114820754 B CN 114820754B CN 202210571524 A CN202210571524 A CN 202210571524A CN 114820754 B CN114820754 B CN 114820754B
- Authority
- CN
- China
- Prior art keywords
- heart
- plane
- image
- template
- scanning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000009466 transformation Effects 0.000 claims abstract description 14
- 210000005242 cardiac chamber Anatomy 0.000 claims abstract description 10
- 238000004519 manufacturing process Methods 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims description 7
- 238000012952 Resampling Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 238000011478 gradient descent method Methods 0.000 claims description 5
- 238000013519 translation Methods 0.000 claims description 5
- 230000005484 gravity Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 210000005240 left ventricle Anatomy 0.000 description 8
- 210000000038 chest Anatomy 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000000747 cardiac effect Effects 0.000 description 3
- 210000004115 mitral valve Anatomy 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 241001270131 Agaricus moelleri Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 238000002595 magnetic resonance imaging Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000005241 right ventricle Anatomy 0.000 description 2
- 210000000115 thoracic cavity Anatomy 0.000 description 2
- 208000031229 Cardiomyopathies Diseases 0.000 description 1
- 208000021908 Myocardial disease Diseases 0.000 description 1
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 210000002837 heart atrium Anatomy 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 210000005246 left atrium Anatomy 0.000 description 1
- 230000002107 myocardial effect Effects 0.000 description 1
- 230000010016 myocardial function Effects 0.000 description 1
- 230000010412 perfusion Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000002861 ventricular Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4007—Scaling of whole images or parts thereof, e.g. expanding or contracting based on interpolation, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- 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
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/752—Contour matching
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30048—Heart; Cardiac
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a template matching-based automatic positioning method for four heart chambers. The invention needs to pre-manufacture a three-dimensional heart template and manually position the four-cavity heart plane position of the heart template. When the four-cavity heart positions of other hearts are positioned, registering is carried out by using the heart template and the three-dimensional chest image, a four-cavity heart plane equation of the heart template is mapped according to a transformation matrix obtained by registration, the parameters of a dicom scanning plane are obtained through calculation, and finally the scanning of the four-cavity heart plane of the heart is completed. The method is an end-to-end method, can greatly lighten the workload of doctors, and meanwhile, experimental results show that the method has good heart positioning accuracy.
Description
Technical Field
The invention relates to a template matching-based automatic positioning method for four heart chambers, and belongs to the field of computer image processing.
Background
Magnetic resonance imaging cardiac scan has 3 basic scan planes: two-chamber heart, four-chamber heart and short axial position. The two-chamber cardiac plane reflects the left ventricle and the left atrium, the four-chamber cardiac plane reflects the left and right ventricles and the left and right atria, and the short-axis bit plane reflects the cross-section of the left and right ventricles. The connecting line of the middle point of the mitral valve and the apex of the left ventricle is taken as an axis to scan the sagittal plane, the coronal plane and the cross section of the heart, and the obtained scanning planes are two-cavity heart, four-cavity heart and short axial position.
After the heart is located, the patient can perform subsequent examinations, such as: measuring ejection fraction, ventricular volume, and heart mass; observing the general morphology of the heart; performing film sequence scanning to evaluate myocardial function; myocardial perfusion and delayed enhancement are performed to diagnose myocardial disease.
At present, the manual heart positioning mode is to scan a human body cross section first and position a connecting line (long axis of the left ventricle) between the apex of the left ventricle and the midpoint of the mitral valve. Then scanning by the line to obtain two cavity heart planes (heart sagittal position); then scanning the two-cavity heart plane by connecting the midpoint of the mitral valve with the apex of the left ventricle to obtain a four-cavity heart plane (heart coronal position); finally, the four-cavity heart plane is used as a reference plane, and is continuously and vertically scanned in the long axis direction of the left ventricle to obtain a short axis bit plane (the cross section of the heart meridian). The method is complicated in process and time-consuming, and even a doctor trained in the profession needs about 3 minutes to complete the whole scanning. And when heart positioning is performed on the same patient, the results of different operators may be inconsistent, and even the results of multiple positioning of the same operator may be different.
Disclosure of Invention
Aiming at the problems existing in the manual positioning method, the invention provides a four-cavity heart automatic positioning method based on template matching. After the four-cavity heart plane is positioned, a doctor can mark a two-cavity heart and a short-axis plane on the four-cavity heart scanning plane as shown in fig. 1, so that the workload of the doctor can be reduced, and the heart positioning accuracy is improved.
In order to achieve the above object, the technical scheme of the present invention is as follows: the invention provides a template matching-based automatic positioning method for four heart chambers, which comprises the following specific steps:
step 1: manufacturing a template;
Step 2: template matching;
The specific steps of the template manufacturing are as follows:
step 11, scanning a chest transverse MR sequence;
Step 12, segmenting a heart region;
And step 13, reconstructing a three-dimensional heart image. Setting the pixel value of a non-heart region in an image to be 0, superposing a picture sequence, resampling the picture by using linear interpolation, converting voxel Spacing into (1, 1), and performing Gaussian filtering to remove noise points in the image;
and 14, manually marking the plane positions of the four cavity centers, wherein the plane parameterization is that a three-dimensional plane equation ax+by+cz+d=0, and the coefficients are a, b, c and d.
The specific steps of template matching are as follows:
Step 21, scanning a chest transverse MR sequence;
Step 22, reconstructing three-dimensional chest images. Overlapping the picture sequences, resampling the pictures by linear interpolation, converting voxelSpacing into (1, 1), performing Gaussian filtering, and removing noise points in the pictures;
And step 23, registering by taking the heart template as a floating image and the target image as a reference image. The purpose of registration is to map points from the floating image coordinate system to the coordinate system of the reference image. Registration consists of 4 parts: transformation function, similarity index, optimization method, interpolation algorithm, the details are as follows:
a. The translation rotation transformation is used as the transformation function, because the positions and angles of hearts of different individuals are different, the heart template can be translated to a proper position, and the angles of the heart template can be adjusted, so that the plane positions of four-cavity hearts accord with the target hearts. Let the coordinate of the rotation center be (C x,Cy,Cz), the translation be (T x,Ty,Tz), the rotation around XYZ axis be (θ x,θy,θz) (rotate around y axis, x axis, z axis in order), the mapping relationship between the transformed coordinate (x *,y*,z*) and the (x, y, z) before transformation be:
b. The similarity measure uses a mutual information measure. The MRI has different gray scales of different equipment and different time scanning, and the mutual information measurement index has the advantages of independent gray scales of the image and good robustness. Mutual information describes the statistical correlation between the images X and Y, and p (X) and p (Y) are the edge probability distribution functions of X and Y, respectively, and p (X, Y) is the edge probability distribution function of X and Y, then the mutual information index is defined as:
c. The optimization method uses a gradient descent method. The gradient descent method is to calculate a gradient, the direction of the gradient is the direction in which the mutual information measurement value ascends most rapidly at the point, and then update the parameters to make the mutual information measurement value reach the local optimal value. The gradient descent method has the advantages of high convergence rate, etc. Recording the conversion parameter as theta, the similarity index as J (theta) and the gradient as The learning rate is a, and then the iterative process of the t time parameter θ is:
d. The interpolation algorithm uses a three-dimensional linear interpolation algorithm. When the image is transformed, the pixel value of the input coordinate is mapped to the output coordinate, but the output coordinate may not be at the integer coordinate, and the pixel value of the integer coordinate is needed for storing the image, so the pixel value needs to be inferred according to the pixel value of the output coordinate. The linear interpolation algorithm has the advantages of high operation speed and retaining picture details to a certain extent.
Step 24, according to the plane equation ax+by+cz+d=0 obtained in step 4 and the mapping relationship between the coordinates (x *,y*,z*) and (x, y, z) obtained by the transformation matrix obtained in step 3:
Bringing (x *,y*,z*) into the plane equation ax+by+cz+d=0 yields ax *+by*+cz*+d* =0, and expanding (x *,y*,z*) yields a new coefficient (a *,b*,c*,d*), i.e. the transformed plane equation is:
a*x+b*y+c*z+d*=0
recording the upper left corner coordinate of the MR scanning parameter as fov, and the transverse axis direction vector as Vertical axis direction vector/>The normal vector is normal. The direction vector of the plane is known as/>The side length of the scanning surface is L, the gravity center of the three-dimensional heart image is G, and the vector normalization operation is normalize. The parameter calculation flow is as follows:
the calculation scheme not only can keep the heart at the center of the picture, but also can make the transverse axis direction of the scanning surface parallel to the x-z plane of the world coordinate system, and accords with the habit of doctor's diagnosis.
Step 25, inputting scanning surface parameters into the machine, and scanning the four-cavity heart plane of the heart.
Compared with the prior art, the invention has the following advantages:
(1) The template has simple manufacturing flow and can be reused after the template is finished; (2) Compared with a deep learning method, the method does not need much training data, and only needs a proper piece of data for template manufacture; (3) In the registration process, the invention uses a rotary translation transformation function, and because the positions and angles of hearts of different individuals are different, the heart template can be translated to a proper position and the angle of the heart template can be adjusted; (4) The invention uses mutual information measurement in the registration process, and the index has the advantages of no dependence on the gray level of the image and good robustness; (5) The scanning surface calculation method provided by the invention can lead the finally obtained four-cavity heart scanning surface to accord with the habit of doctor's examination, and comprises 2 characteristics: the heart is kept at the center of the picture, and the horizontal axis direction is parallel to the x-z plane of the world coordinate system; (6) The invention is an automatic end-to-end method, and as shown in figure 3, after integrating the method into a piece of software, a doctor can obtain four-cavity heart scanning surface parameters only by clicking and importing a dicom sequence and waiting for a moment.
Drawings
FIG. 1 is a schematic illustration of the two chambers of a heart and the short axis.
FIG. 2 is a flow chart of the present invention.
Fig. 3 is a registration process diagram.
Fig. 4 is a diagram of the result of the software operation.
Detailed Description
The present application is further illustrated below in conjunction with specific embodiments, it being understood that these embodiments are meant to be illustrative of the application and not limiting the scope of the application, and that modifications of the application, which are equivalent to those skilled in the art to which the application pertains, fall within the scope of the application defined in the appended claims after reading the application.
Examples: referring to fig. 2, the invention provides a method for automatically positioning four heart chambers based on template matching, which comprises the following specific steps:
The specific steps are divided into 2 parts of template making and template matching.
Step 1 the specific steps of template fabrication are shown in fig. 2 (a):
step 11, scanning a chest transverse MR sequence;
Step 12, segmenting a heart region;
And 13, constructing a heart image in a three-dimensional way. Setting the pixel value of a non-heart region in an image to be 0, superposing a picture sequence, resampling the picture by using linear interpolation, converting voxel Spacing into (1, 1), and performing Gaussian filtering to remove noise points in the image;
in step 14, the plane position of the four-chamber center is manually marked (the plane parameter is ax+by+cz+d=0), and the plane parameter is recorded.
Step 2: the specific steps of template matching are shown in fig. 2 (b):
Step 21, scanning a chest transverse MR sequence;
Step 22, reconstructing three-dimensional chest images. Overlapping the picture sequences, resampling the pictures by linear interpolation, converting voxelSpacing into (1, 1), performing Gaussian filtering, and removing noise points in the pictures;
And step 23, registering by taking the heart template as a floating image and the target image as a reference image. The transformation function uses translation rotation transformation, the similarity index uses mutual information measurement, the optimization method uses a gradient descent method, and the interpolation algorithm uses a three-dimensional linear interpolation algorithm;
and step 24, calculating scanning surface parameters according to the plane equation obtained in the step 4 and the transformation matrix obtained in the step 3. Using the plane equation and the transformation matrix, the transformed plane equation a *x+b*y+c*z+d* =0 is calculated. Recording the upper left corner coordinate of the MR scanning parameter as fov, and the transverse axis direction vector as Vertical axis direction vector/>The normal vector is normal and the vector normalization operation is normalize. The direction vector of the plane is known as/>The side length of the scanning surface is L, and the gravity center of the three-dimensional heart image is G. The parameter calculation flow is as follows:
Step 25, inputting scanning surface parameters into the machine, and scanning the four-cavity heart plane of the heart.
Effect evaluation:
the invention provides a template matching-based automatic positioning method for four heart chambers, and the test result of the method is shown in figure 3. It can be seen from the figure that the invention is integrated into a piece of software, when the software clicks the 'lead-in dicom sequence' button in the test, the software can automatically complete three-dimensional thoracic image reconstruction, clicks the 'start registration', the software can register thoracic images and heart templates, after the registration is completed, the software can automatically calculate scanning surface parameters, and a doctor inputs the parameters into a nuclear magnetic resonance machine to obtain four-chamber heart scanning images of the heart. Test results show that the method can rapidly and accurately predict four-cavity heart scanning parameters, and provides an efficient scheme for a doctor to perform heart positioning.
The foregoing is merely illustrative of the embodiments of the present invention, and the scope of the present invention is not limited thereto, and any person skilled in the art will appreciate that modifications and substitutions are within the scope of the present invention, and the scope of the present invention is defined by the appended claims.
Claims (5)
1. A method for automatically positioning four heart chambers based on template matching is characterized by comprising the following specific steps:
step 1: manufacturing a template;
Step 2: template matching;
The specific process of template manufacturing is as follows:
step 11, scanning a chest transverse MR sequence;
Step 12, segmenting a heart region;
step 13, reconstructing a three-dimensional heart image;
step 14, manually marking the plane positions of the four-cavity centers;
the specific process of template matching is as follows:
Step 21, scanning a chest transverse MR sequence;
Step 22, reconstructing a three-dimensional chest image;
Step 23, taking the heart template as a floating image, and taking the target image as a reference image for registration;
step 24, calculating scanning surface parameters according to the plane equation obtained in the step 14 and the transformation matrix obtained in the step 23;
Step 25, inputting scanning surface parameters into a machine, and scanning a four-cavity heart plane of the heart;
The process of calculating the scan plane parameters mentioned in step 25 is that the mapping relationship between the coordinates (x *,y*,z*) and (x, y, z) obtained according to the plane equation ax+by+cz+d=0 obtained in step 14 and the transformation matrix obtained in step 23:
bringing (x *,y*,z*) into the plane equation ax+by+cz+d=0 to obtain ax *+by*+cz*+d* =0, and expanding the plane equation to obtain a new coefficient (a *,b*,c*,d*), namely the transformed plane equation is:
a*x+b*y+c*z+d*=0
recording the upper left corner coordinate of the MR scanning parameter as fov, and the transverse axis direction vector as Vertical axis direction vector/>The normal vector is normal, the direction vector of the known plane is/>The side length of the scanning surface is L, the gravity center of the three-dimensional heart image is G, the vector normalization operation is normalize, and the parameter calculation flow is as follows:
2. the automatic positioning method of heart four-cavity heart based on template matching as claimed in claim 1, wherein the three-dimensional heart image reconstruction mentioned in step 13 comprises the specific steps of setting the pixel value of a non-heart area in an image to be 0, overlapping a picture sequence, resampling pictures by using linear interpolation, converting voxelSpacing into (1, 1), and performing Gaussian filtering to remove noise in the image.
3. The automatic positioning method of four heart chambers based on template matching according to claim 1, wherein the plane positions of the four heart chambers are manually marked in step 14, and the plane equation is ax+by+cz+d=0, and a, b, c, d are coefficients.
4. The automatic positioning method of four heart chambers based on template matching according to claim 1, wherein the three-dimensional chest image reconstruction mentioned in the step 22 comprises the specific procedures of overlapping a picture sequence, resampling pictures by linear interpolation, converting voxelSpacing into (1, 1), performing Gaussian filtering, and removing noise points in the pictures.
5. The automatic positioning method of four heart chambers based on template matching according to claim 1, wherein the registration mentioned in step 23 comprises the specific components of translation rotation transformation, mutual information measurement of similarity index, gradient descent method, three-dimensional linear interpolation algorithm and three-dimensional linear interpolation algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210571524.0A CN114820754B (en) | 2022-05-24 | 2022-05-24 | Automatic positioning method for four-cavity heart based on template matching |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210571524.0A CN114820754B (en) | 2022-05-24 | 2022-05-24 | Automatic positioning method for four-cavity heart based on template matching |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114820754A CN114820754A (en) | 2022-07-29 |
CN114820754B true CN114820754B (en) | 2024-05-03 |
Family
ID=82517651
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210571524.0A Active CN114820754B (en) | 2022-05-24 | 2022-05-24 | Automatic positioning method for four-cavity heart based on template matching |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114820754B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011200549A (en) * | 2010-03-26 | 2011-10-13 | Fujitsu Ltd | Method and apparatus for deforming three-dimensional method and program |
CN107563998A (en) * | 2017-08-30 | 2018-01-09 | 上海联影医疗科技有限公司 | Medical image cardiac image processing method |
CN114419071A (en) * | 2022-01-23 | 2022-04-29 | 东南大学 | Heart three-dimensional positioning method based on MR transverse axis image segmentation |
CN114419157A (en) * | 2022-01-23 | 2022-04-29 | 东南大学 | Heart four-chamber heart automatic positioning method based on deep learning |
-
2022
- 2022-05-24 CN CN202210571524.0A patent/CN114820754B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011200549A (en) * | 2010-03-26 | 2011-10-13 | Fujitsu Ltd | Method and apparatus for deforming three-dimensional method and program |
CN107563998A (en) * | 2017-08-30 | 2018-01-09 | 上海联影医疗科技有限公司 | Medical image cardiac image processing method |
CN114419071A (en) * | 2022-01-23 | 2022-04-29 | 东南大学 | Heart three-dimensional positioning method based on MR transverse axis image segmentation |
CN114419157A (en) * | 2022-01-23 | 2022-04-29 | 东南大学 | Heart four-chamber heart automatic positioning method based on deep learning |
Also Published As
Publication number | Publication date |
---|---|
CN114820754A (en) | 2022-07-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102251830B1 (en) | Systems and methods for registration of ultrasound and ct images | |
WO2019000455A1 (en) | Method and system for segmenting image | |
CN114119549B (en) | Multi-mode medical image three-dimensional point cloud registration optimization method | |
US8948484B2 (en) | Method and system for automatic view planning for cardiac magnetic resonance imaging acquisition | |
CN107038728A (en) | Profile automation based on iterative approximation is determined | |
CN108830852B (en) | Three-dimensional ultrasonic tumor auxiliary measurement system and method | |
BR112015004061B1 (en) | ULTRASOUND IMAGING SYSTEM FOR INSPECTION OF AN OBJECT IN A VOLUME, AND METHOD FOR PROVISION OF A THREE-DIMENSIONAL ULTRASOUND IMAGE OF AN OBJECT IN A VOLUME. | |
CN110599499B (en) | MRI image heart structure segmentation method based on multipath convolutional neural network | |
JP7270319B2 (en) | Left ventricle automatic segmentation method of SPECT three-dimensional reconstructed image | |
CN110163877A (en) | A kind of method and system of MRI ventricular structure segmentation | |
CN111584066A (en) | Brain medical image diagnosis method based on convolutional neural network and symmetric information | |
CN113057677B (en) | Heart image modeling method, system and equipment for fusing ultrasonic image and CT image | |
Li et al. | Automatic generation of object shape models and their application to tomographic image segmentation | |
CN109741439A (en) | A kind of three-dimensional rebuilding method of two dimension MRI fetus image | |
WO2020007026A1 (en) | Segmentation model training method and apparatus, and computer-readable storage medium | |
CN114820754B (en) | Automatic positioning method for four-cavity heart based on template matching | |
CN116269496A (en) | Heart three-dimensional ultrasonic imaging and heart function evaluation system based on implicit neural representation | |
CN114419157A (en) | Heart four-chamber heart automatic positioning method based on deep learning | |
Erdt et al. | Computer aided segmentation of kidneys using locally shape constrained deformable models on CT images | |
CN113902738A (en) | Heart MRI segmentation method and system | |
CN114419071A (en) | Heart three-dimensional positioning method based on MR transverse axis image segmentation | |
CN111166373B (en) | Positioning registration method, device and system | |
CN113269741A (en) | Heart MR image segmentation system based on improved U-Net | |
Roy et al. | MDL-IWS: multi-view deep learning with iterative watershed for pulmonary fissure segmentation | |
Shanmuganathan et al. | Image registration for multi-view three-dimensional echocardiography sequences |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |