CN116958456B - Heart three-dimensional model construction method, system and storage medium based on image registration - Google Patents
Heart three-dimensional model construction method, system and storage medium based on image registration Download PDFInfo
- Publication number
- CN116958456B CN116958456B CN202311222620.5A CN202311222620A CN116958456B CN 116958456 B CN116958456 B CN 116958456B CN 202311222620 A CN202311222620 A CN 202311222620A CN 116958456 B CN116958456 B CN 116958456B
- Authority
- CN
- China
- Prior art keywords
- real
- time
- screening
- image data
- heart
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 23
- 238000012216 screening Methods 0.000 claims abstract description 206
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims description 12
- 241001270131 Agaricus moelleri Species 0.000 claims description 9
- 238000010187 selection method Methods 0.000 claims description 9
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000009432 framing Methods 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims description 3
- 239000002699 waste material Substances 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000000547 structure data Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- 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
- 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
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Multimedia (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a method, a system and a storage medium for constructing a heart three-dimensional model based on image registration, which relate to the technical field of heart three-dimensional model construction and comprise the following steps: comparing the real-time physical sign data with a plurality of groups of historical physical sign data, comparing the real-time image data with the to-be-determined image data, and marking a historical heart three-dimensional model corresponding to the screened image data as a basic three-dimensional model; calibrating the basic three-dimensional model based on the comparison result of the real-time image data and the screening image data to obtain a real-time three-dimensional model; the method and the device can quickly and accurately build the heart three-dimensional model by comparing the historical data, acquiring the basic three-dimensional model and carrying out image registration on the basic three-dimensional model, and are used for solving the problems that the building efficiency of the heart three-dimensional model is low and the repeated waste of data processing resources exists in the prior art.
Description
Technical Field
The invention relates to the technical field of heart three-dimensional model construction, in particular to a heart three-dimensional model construction method, system and storage medium based on image registration.
Background
The heart is one of the most important organs of a human body, and by building a heart three-dimensional model, medical staff can be assisted to judge the structure of the heart and the health condition of the heart more clearly and accurately, so that the accuracy and the comprehensiveness of diagnosis and treatment can be improved.
In the prior art, in the process of constructing a heart model, detailed heart structure data are usually required to be acquired, in the process of acquiring the detailed heart structure data, the acquisition amount of the data is often required to be increased, for example, a heart model is constructed by analyzing a CT image and an ultrasonic image, but a three-dimensional model is required to be constructed again each time, the method is suitable for accurate heart operation treatment, for example, a method, a device, equipment and a storage medium for generating the heart three-dimensional model are disclosed in patent document with application publication number of CN 114663410A.
Disclosure of Invention
The invention aims to solve at least one of the technical problems in the prior art to a certain extent, obtains a basic three-dimensional model by comparing historical data, and performs image registration on the basic three-dimensional model, so that the heart three-dimensional model can be quickly and accurately built, and the problems that the building efficiency of the heart three-dimensional model is lower and the repeated waste of data processing resources exists in the prior art are solved.
To achieve the above object, in a first aspect, the present invention provides a method for constructing a three-dimensional model of a heart based on image registration, including: acquiring a plurality of groups of historical heart three-dimensional models, historical sign data and historical image data of users from a heart model database;
acquiring real-time image data and real-time physical sign data of a user;
comparing the real-time sign data with a plurality of groups of historical sign data, screening a plurality of groups of to-be-determined sign data from the plurality of groups of historical sign data, and marking a historical heart three-dimensional model corresponding to the to-be-determined sign data as a to-be-determined heart three-dimensional model; marking the historical image data corresponding to the three-dimensional model of the heart to be determined as the image data to be determined;
comparing the real-time image data with the to-be-determined image data to obtain a comparison similarity absolute difference value, setting the to-be-determined image data with the minimum comparison similarity absolute difference value as screening image data, and marking a historical heart three-dimensional model corresponding to the screening image data as a basic three-dimensional model;
Calibrating the basic three-dimensional model based on the comparison result of the real-time image data and the screening image data to obtain a real-time three-dimensional model;
the real-time three-dimensional model is stored in a heart model database.
Further, the historical image data and the real-time image data each comprise a CT image, and the historical sign data and the real-time sign data comprise height, weight, age and heart rate respectively.
Further, comparing the real-time sign data with a plurality of groups of historical sign data, and screening a plurality of groups of to-be-determined sign data from the plurality of groups of historical sign data comprises: acquiring the height, weight, age and heart rate in the real-time physical sign data, and setting the height, weight, age and heart rate in the real-time physical sign data as the real-time height, real-time weight, real-time age and real-time heart rate respectively;
setting the height, weight, age and heart rate in the historical sign data as historical height, historical weight, historical age and historical heart rate respectively;
adding a first age threshold to the real-time age to obtain an age screening upper limit value, subtracting the first age threshold from the real-time age to obtain an age screening lower limit value, and setting a section from the age screening lower limit value to the age screening upper limit value as an age screening section, wherein the age screening section comprises the age screening upper limit value and the age screening lower limit value;
And acquiring historical sign data in the age screening interval, and marking the historical sign data in the age screening interval as age screening sign data.
Further, comparing the real-time sign data with a plurality of groups of historical sign data, and screening a plurality of groups of to-be-determined sign data from the plurality of groups of historical sign data further comprises: calculating the historical height and the historical weight in the age screening sign data, the real-time height and the real-time weight in the historical heart rate and the real-time sign data and the real-time heart rate through a depth screening calculation formula to obtain a sign comparison absolute difference value;
the depth screening calculation formula is configured as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Ctb is the absolute difference of sign comparison, ss is the real-time height, sl is the historical height, ts is the real-time weight, tl is the historical weight, xs is the real-time heart rate, and Xl is the historical heart rate;
sequencing the sign comparison absolute differences from small to large to obtain a sign comparison sequencing, and marking age screening sign data corresponding to the sign comparison absolute differences of the first comparison quantity before the sign comparison sequencing as sign data to be determined.
Further, comparing the real-time image data with the image data to be determined to obtain a comparison similar absolute difference value, including: obtaining a heart image contour from the real-time image data through an image contour extraction method;
Setting the heart image outline of the real-time image data as a real-time outline, acquiring the heart image outline of the screened image data, and setting the heart image outline as a screened outline;
vertically placing the real-time profile and the screening profile according to the direction in which the human body vertically stands, and obtaining profile parameters by a profile frame selection method, wherein the profile parameters comprise profile length and profile width;
setting the contour length and the contour width of the real-time contour as the real-time length and the real-time width respectively, and setting the contour length and the contour width of the screening contour as the screening length and the screening width respectively;
calculating the real-time length, the real-time width, the screening length and the screening width through an image comparison formula to obtain comparison similarity absolute differences;
the image comparison formula is configured to:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Cbd is the comparison similarity absolute difference, css is the real-time length, csx is the screening length, kss is the real-time width, and Ksx is the screening width.
Further, the contour extraction method includes: respectively carrying out graying treatment on the real-time image data and the screened image data to obtain a graying image;
acquiring a plurality of groups of edge pixel points of a heart region of the graying image corresponding to the screened image data, setting the edge pixel points as screened edge pixel points, calculating an average value of gray values of the plurality of screened edge pixel points, and setting the average value as reference edge gray;
Acquiring pixel points which are adjacent to the pixel points at the screening edge and do not belong to the heart region, setting the pixel points as adjacent pixel points, calculating the average value of gray values of a plurality of adjacent pixel points, and setting the average value as adjacent reference gray;
calculating the average value of adjacent reference gray scales and reference edge gray scales, and setting the average value as divided gray scales;
taking the divided gray scale as a divided intermediate value to carry out binarization processing on the gray scale image to obtain a binarized image;
and extracting the outline of the heart image in the binarized image.
Further, the contour framing method comprises the following steps: placing the real-time profile and the screening profile vertically according to the direction in which the human body stands vertically, placing the real-time profile and the screening profile into a plane coordinate system, and marking the real-time profile or the screening profile placed into the plane coordinate system as a profile to be framed;
the plane coordinate system comprises an X axis and a Y axis, the maximum value and the minimum value of the profile to be framed in the X axis direction are obtained, the maximum value and the minimum value of the width are respectively set, and the width is obtained by subtracting the minimum value of the width from the maximum value of the width; and obtaining the maximum value and the minimum value of the profile to be framed in the Y-axis direction, respectively setting the maximum value and the minimum value of the length, and subtracting the minimum value of the length from the maximum value of the length.
Further, calibrating the basic three-dimensional model based on the comparison result of the real-time image data and the screening image data, the obtaining the real-time three-dimensional model includes: acquiring real-time image data and screening image data, wherein the acquisition directions of the real-time image data and the screening image data are the same, and the acquisition directions of the real-time image data and the screening image data are set to be first directions;
the first direction is any direction on the plane and is perpendicular to the vertical direction;
making a vertical line in a first direction on a plane, setting the direction of the vertical line as a second direction, acquiring real-time image data and screening image data in the second direction, and setting the real-time image data and the screening image data as a second real-time image and a second screening direction respectively;
processing the second real-time image and the second screening image sequentially through a contour extraction method and a contour frame selection method to obtain contour parameters; extracting outline widths of the second real-time image and the second screening image, and setting the outline widths as a second direction real-time width and a second direction screening width respectively;
establishing a three-dimensional coordinate system, and placing the basic three-dimensional model into the three-dimensional coordinate system, wherein the three-dimensional coordinate system comprises an X axis, a Y axis and a Z axis; the X axis is parallel to the first direction, the Y axis is parallel to the vertical direction, and the Z axis is parallel to the second direction;
Establishing cubes in a first length unit, and dividing a basic three-dimensional model in three-dimensional coordinates through a plurality of cubes;
dividing the real-time length by the screening length to obtain a length ratio, dividing the real-time width by the screening width to obtain a first width ratio, and dividing the real-time width in the second direction by the screening width in the second direction to obtain a second width ratio;
multiplying the side length of a cube in the basic three-dimensional model on the X axis by a first width ratio to obtain a first side length, multiplying the side length of the cube on the Y axis by a length ratio to obtain a second side length, and multiplying the side length of the cube on the Z axis by a second width ratio to obtain a third side length;
and transforming all cubes in the basic three-dimensional model according to the first side length, the second side length and the third side length to obtain the real-time three-dimensional model.
In a second aspect, the present invention provides a system for constructing a three-dimensional model of a heart based on image registration, comprising: the system comprises a heart model database, an image acquisition module, a sign acquisition module, a comparison registration module and a three-dimensional construction module;
the heart model database stores a plurality of groups of historical heart three-dimensional models, historical sign data and historical image data of users;
the image acquisition module is used for acquiring real-time image data; the physical sign acquisition module is used for acquiring real-time physical sign data of a user;
The comparison registration module is used for comparing the real-time sign data with a plurality of groups of historical sign data, screening a plurality of groups of to-be-determined sign data from the plurality of groups of historical sign data, and marking a historical heart three-dimensional model corresponding to the to-be-determined sign data as a to-be-determined heart three-dimensional model; marking the historical image data corresponding to the three-dimensional model of the heart to be determined as the image data to be determined;
the three-dimensional construction module comprises an image comparison screening unit, a three-dimensional construction unit and a storage unit, wherein the image comparison screening unit is used for comparing real-time image data with to-be-determined image data to obtain comparison similar absolute differences, setting to-be-determined image data with the smallest comparison similar absolute differences as screened image data, and marking a historical heart three-dimensional model corresponding to the screened image data as a basic three-dimensional model;
the three-dimensional construction unit calibrates the basic three-dimensional model based on the comparison result of the real-time image data and the screening image data to obtain a real-time three-dimensional model;
the storage unit is used for storing the real-time three-dimensional model into a heart model database.
In a third aspect, the present application provides a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method as claimed in any one of the preceding claims.
The invention has the beneficial effects that: according to the method, a plurality of groups of historical heart three-dimensional models, historical sign data and historical image data of users are obtained from a heart model database; acquiring real-time image data and real-time physical sign data of a user; comparing the real-time sign data with a plurality of groups of historical sign data, screening a plurality of groups of to-be-determined sign data from the plurality of groups of historical sign data, and marking a historical heart three-dimensional model corresponding to the to-be-determined sign data as a to-be-determined heart three-dimensional model; marking the historical image data corresponding to the three-dimensional model of the heart to be determined as the image data to be determined; several groups of approximate sign data can be preliminarily screened through sign data comparison, so that data screening time is saved for the subsequent image registration process, and the efficiency of building a heart three-dimensional model is improved;
comparing real-time image data with undetermined image data to obtain comparison similar absolute difference values, setting undetermined image data with the smallest comparison similar absolute difference values as screening image data, and marking a historical heart three-dimensional model corresponding to the screening image data as a basic three-dimensional model; calibrating the basic three-dimensional model based on the comparison result of the real-time image data and the screening image data to obtain a real-time three-dimensional model; real-time three-dimensional models can be obtained rapidly through the approximate basic three-dimensional models, the construction efficiency of the heart three-dimensional models can be improved, and the early-stage data processing time is saved for heart structure analysis.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.
Drawings
FIG. 1 is a flow chart of the steps of the method of the present application;
FIG. 2 is a schematic block diagram of the system of the present application;
FIG. 3 is a schematic diagram of the acquisition of profile parameters according to the present application;
FIG. 4 is a schematic diagram of transformation of cubes in a basic three-dimensional model of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Embodiment 1 referring to fig. 2, the application provides a heart three-dimensional model construction system based on image registration, which is used for acquiring a basic three-dimensional model by comparing historical data and carrying out image registration on the basic three-dimensional model, so that the heart three-dimensional model can be quickly and accurately constructed, and the problems of low construction efficiency of the heart three-dimensional model and repeated waste of data processing resources in the prior art are solved;
Specifically, the heart three-dimensional model construction system based on image registration includes: the system comprises a heart model database, an image acquisition module, a sign acquisition module, a comparison registration module and a three-dimensional construction module;
the heart model database stores a plurality of groups of historical heart three-dimensional models, historical sign data and historical image data of users; the historical image data and the real-time image data comprise CT images, the historical sign data and the real-time sign data comprise height, weight, age and heart rate respectively, and in the process of acquiring the historical data, the data of each age stage has at least 1 group; the heart model database is used for storing a built heart three-dimensional model in the existing medical system;
the image acquisition module is used for acquiring real-time image data; the sign acquisition module is used for acquiring real-time sign data of a user;
the comparison registration module is used for comparing the real-time sign data with a plurality of groups of historical sign data, screening a plurality of groups of to-be-determined sign data from the plurality of groups of historical sign data, and marking a three-dimensional model of the history heart corresponding to the to-be-determined sign data as a three-dimensional model of the heart to be determined; marking the historical image data corresponding to the three-dimensional model of the heart to be determined as the image data to be determined; the comparison registration module is configured with a preliminary screening strategy comprising: acquiring the height, weight, age and heart rate in the real-time physical sign data, and setting the height, weight, age and heart rate in the real-time physical sign data as the real-time height, real-time weight, real-time age and real-time heart rate respectively;
Setting the height, weight, age and heart rate in the historical sign data as historical height, historical weight, historical age and historical heart rate respectively;
adding a first age threshold to the real-time age to obtain an age screening upper limit value, subtracting the first age threshold from the real-time age to obtain an age screening lower limit value, and setting a section from the age screening lower limit value to the age screening upper limit value as an age screening section, wherein the age screening section comprises the age screening upper limit value and the age screening lower limit value; because the data of each age stage are stored in the heart model database, in the process of preliminary screening through age, the first age threshold is set to be 5 years old, and at least 10 groups of data can be screened under the condition that the age screening interval is ensured to be 10; in general, cardiac data at the same age stage can be more fit to the overall situation at that age stage;
and acquiring historical sign data in the age screening interval, and marking the historical sign data in the age screening interval as age screening sign data.
The comparison registration module is further configured with a depth screening strategy, the depth screening strategy comprising: calculating the historical height and the historical weight in the age screening sign data, the real-time height and the real-time weight in the historical heart rate and the real-time sign data and the real-time heart rate through a depth screening calculation formula to obtain a sign comparison absolute difference value;
The depth filter calculation formula is configured as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Ctb is the absolute difference of sign comparison, ss is the real-time height, sl is the historical height, ts is the real-time weight, tl is the historical weight, xs is the real-time heart rate, and Xl is the historical heart rate; usually, the size and health condition of the heart are very similar under the condition that the age, the height, the weight and the heart rate of a person are very similar, and a plurality of groups of data very similar to the real-time detected user can be screened through the screening;
sequencing the sign comparison absolute differences from small to large to obtain a sign comparison sequencing, marking age screening sign data corresponding to the sign comparison absolute differences of a first comparison quantity before the sign comparison sequencing as sign data to be determined, wherein the first comparison quantity is set to be 3, the reference age screening interval is 10, and at least 10 groups of age screening sign data can be screened, so that three pieces of sign data to be determined can be screened through a deep screening strategy.
The three-dimensional construction module comprises an image comparison screening unit, a three-dimensional construction unit and a storage unit, wherein the image comparison screening unit is used for comparing real-time image data with undetermined image data to obtain comparison similarity absolute difference values, undetermined image data with the smallest comparison similarity absolute difference values are set as screened image data, and a historical heart three-dimensional model corresponding to the screened image data is marked as a basic three-dimensional model; the image comparison screening unit is configured with an image comparison screening strategy, and the image comparison screening strategy comprises: obtaining a heart image contour from the real-time image data through an image contour extraction method;
Setting the heart image outline of the real-time image data as a real-time outline, acquiring the heart image outline of the screened image data, and setting the heart image outline as a screened outline;
vertically placing the real-time profile and the screening profile according to the direction in which the human body vertically stands, and obtaining profile parameters by a profile frame selection method, wherein the profile parameters comprise profile length and profile width;
setting the contour length and the contour width of the real-time contour as the real-time length and the real-time width respectively, and setting the contour length and the contour width of the screening contour as the screening length and the screening width respectively;
calculating the real-time length, the real-time width, the screening length and the screening width through an image comparison formula to obtain comparison similarity absolute differences;
the image comparison formula is configured as:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Cbd is the comparison similarity absolute difference, css is the real-time length, csx is the screening length, kss is the real-time width, and Ksx is the screening width;
and setting the undetermined image data with the smallest comparison similarity absolute difference as screening image data, marking a historical heart three-dimensional model corresponding to the screening image data as a basic three-dimensional model, and selecting the nearest basic three-dimensional model from the size of the heart by comparing the contours of the images after three groups of undetermined sign data which are primarily screened by the sign data.
The contour extraction method comprises the following steps: respectively carrying out graying treatment on the real-time image data and the screened image data to obtain a graying image;
acquiring a plurality of groups of edge pixel points of a heart region of the graying image corresponding to the screened image data, setting the edge pixel points as screened edge pixel points, calculating an average value of gray values of the plurality of screened edge pixel points, and setting the average value as reference edge gray;
acquiring pixel points which are adjacent to the pixel points at the screening edge and do not belong to the heart region, setting the pixel points as adjacent pixel points, calculating the average value of gray values of a plurality of adjacent pixel points, and setting the average value as adjacent reference gray;
calculating the average value of adjacent reference gray scales and reference edge gray scales, and setting the average value as divided gray scales; for example, the obtained reference edge gray is 50, the adjacent reference gray is 150, and the obtained division gray is 100;
taking the divided gray scale as a divided intermediate value to carry out binarization processing on the gray scale image to obtain a binarized image;
and extracting the outline of the heart image in the binarized image.
Referring to fig. 3, the contour selection method includes: placing the real-time profile and the screening profile vertically according to the direction in which the human body stands vertically, placing the real-time profile and the screening profile into a plane coordinate system, and marking the real-time profile or the screening profile placed into the plane coordinate system as a profile to be framed;
The plane coordinate system comprises an X axis and a Y axis, the maximum value and the minimum value of the profile to be framed in the X axis direction are obtained, the maximum value and the minimum value of the width are respectively set, and the width is obtained by subtracting the minimum value of the width from the maximum value of the width; obtaining the maximum value and the minimum value of the outline to be framed in the Y-axis direction, respectively setting the maximum value and the minimum value of the length, subtracting the minimum value of the length from the maximum value of the length, and obtaining the size of the outline of the heart by a outline framing method; in fig. 3, X1 and X2 are coordinate points where the minimum value and the maximum value of the outline to be framed are located in the X-axis direction, and Y1 and Y2 are coordinate points where the minimum value and the maximum value of the outline to be framed are located in the Y-axis direction, respectively;
the three-dimensional building unit calibrates the basic three-dimensional model based on the comparison result of the real-time image data and the screening image data to obtain a real-time three-dimensional model; the three-dimensional building unit is configured with a calibration building strategy comprising: acquiring real-time image data and screening image data, wherein the acquisition directions of the real-time image data and the screening image data are the same, and the acquisition directions of the real-time image data and the screening image data are set to be first directions;
The first direction is any direction on the plane and is perpendicular to the vertical direction;
making a vertical line in a first direction on a plane, setting the direction of the vertical line as a second direction, acquiring real-time image data and screening image data in the second direction, and setting the real-time image data and the screening image data as a second real-time image and a second screening direction respectively;
processing the second real-time image and the second screening image sequentially through a contour extraction method and a contour frame selection method to obtain contour parameters; extracting outline widths of the second real-time image and the second screening image, and setting the outline widths as a second direction real-time width and a second direction screening width respectively;
establishing a three-dimensional coordinate system, and placing the basic three-dimensional model into the three-dimensional coordinate system, wherein the three-dimensional coordinate system comprises an X axis, a Y axis and a Z axis; the X axis is parallel to the first direction, the Y axis is parallel to the vertical direction, and the Z axis is parallel to the second direction;
establishing cubes in a first length unit, and dividing a basic three-dimensional model in three-dimensional coordinates through a plurality of cubes; the first length is set to 0.5cm;
dividing the real-time length by the screening length to obtain a length ratio, dividing the real-time width by the screening width to obtain a first width ratio, and dividing the real-time width in the second direction by the screening width in the second direction to obtain a second width ratio;
Multiplying the side length of a cube in the basic three-dimensional model on the X axis by a first width ratio to obtain a first side length, multiplying the side length of the cube on the Y axis by a length ratio to obtain a second side length, and multiplying the side length of the cube on the Z axis by a second width ratio to obtain a third side length;
referring to fig. 4, all cubes in the basic three-dimensional model are transformed according to the first side length, the second side length and the third side length to obtain a real-time three-dimensional model, the basic three-dimensional model is adjusted according to the ratio of the data in the three directions, the real-time three-dimensional model can be quickly obtained through the approximate basic three-dimensional model, the obtained real-time three-dimensional model is used for assisting heart diagnosis and treatment, the construction efficiency of the heart three-dimensional model can be improved, and the early-stage data processing time is saved for heart assisted treatment.
The storage unit is used for storing the real-time three-dimensional model into the heart model database, and the number of models in the heart model database can be expanded by storing the real-time three-dimensional model into the heart model database.
Embodiment 2 referring to fig. 1, the present invention further provides a method for constructing a three-dimensional heart model based on image registration, comprising the following steps: step S1, acquiring a plurality of groups of historical heart three-dimensional models, historical sign data and historical image data of users from a heart model database; wherein, historical image data and real-time image data all include CT image, and historical sign data and real-time sign data include height, weight, age and rhythm of the heart respectively.
Step S2, acquiring real-time image data and real-time physical sign data of a user;
s3, comparing the real-time sign data with a plurality of groups of historical sign data, screening a plurality of groups of to-be-determined sign data from the plurality of groups of historical sign data, and marking a historical heart three-dimensional model corresponding to the to-be-determined sign data as a to-be-determined heart three-dimensional model; marking the historical image data corresponding to the three-dimensional model of the heart to be determined as the image data to be determined; step S3 comprises the following sub-steps: step S31, acquiring the height, weight, age and heart rate in the real-time physical sign data, and setting the height, weight, age and heart rate in the real-time physical sign data as the real-time height, real-time weight, real-time age and real-time heart rate respectively;
step S32, setting the height, weight, age and heart rate in the historical sign data as historical height, historical weight, historical age and historical heart rate respectively;
step S33, adding a first age threshold to the real-time age to obtain an age screening upper limit, subtracting the first age threshold from the real-time age to obtain an age screening lower limit, and setting a section from the age screening lower limit to the age screening upper limit as an age screening section, wherein the age screening section comprises an age screening upper limit and an age screening lower limit;
Step S34, acquiring historical sign data in the age screening interval, and marking the historical sign data in the age screening interval as age screening sign data.
Step S35, calculating the historical height, the historical weight, the historical heart rate and the real-time height, the real-time weight and the real-time heart rate in the age screening sign data through a depth screening calculation formula to obtain a sign comparison absolute difference value;
in step S36, the depth filter calculation formula is configured as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Ctb is the absolute difference of sign comparison, ss is the real-time height, sl is the historical height, ts is the real-time weight, tl is the historical weight, xs is the real-time heart rate, and Xl is the historical heart rate;
step S37, sorting the sign comparison absolute differences from small to large to obtain a sign comparison sorting, and marking age screening sign data corresponding to the first comparison quantity of the sign comparison absolute differences before the sign comparison sorting as sign data to be determined.
S4, comparing the real-time image data with the undetermined image data to obtain comparison similar absolute differences, setting undetermined image data with the smallest comparison similar absolute differences as screening image data, and marking a historical heart three-dimensional model corresponding to the screening image data as a basic three-dimensional model; step S4 further comprises the sub-steps of: step S41, obtaining a heart image contour from the real-time image data through an image contour extraction method;
Step S42, setting the heart image outline of the real-time image data as a real-time outline, acquiring the heart image outline of the screened image data, and setting the heart image outline as a screened outline;
step S43, vertically placing the real-time profile and the screening profile according to the direction in which the human body vertically stands, and obtaining profile parameters through a profile frame selection method, wherein the profile parameters comprise profile length and profile width;
step S44, setting the contour length and the contour width of the real-time contour as the real-time length and the real-time width respectively, and setting the contour length and the contour width of the screening contour as the screening length and the screening width respectively;
step S45, calculating the real-time length, the real-time width, the screening length and the screening width through an image comparison formula to obtain comparison similarity absolute differences;
in step S46, the image comparison formula is configured as:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Cbd is the comparison similarity absolute difference, css is the real-time length, csx is the screening length, kss is the real-time width, and Ksx is the screening width.
The contour extraction method comprises the following steps: step S411, respectively carrying out gray scale processing on the real-time image data and the screened image data to obtain a gray scale image;
step S412, obtaining a plurality of groups of edge pixel points of the heart region of the graying image corresponding to the screened image data, setting the edge pixel points as screened edge pixel points, obtaining an average value of gray values of the plurality of screened edge pixel points, and setting the average value as reference edge gray;
Step S413, obtaining the adjacent pixel points which are not in the heart area and are screened by the edge pixel points, setting the adjacent pixel points as adjacent pixel points, obtaining the average value of gray values of a plurality of adjacent pixel points, and setting the average value as adjacent reference gray;
step S414, the average value of the adjacent reference gray level and the reference edge gray level is calculated and set as the divided gray level;
step S415, carrying out binarization processing on the gray-scale image by taking the divided gray scale as a divided intermediate value to obtain a binarized image;
in step S416, a heart image contour in the binarized image is extracted.
The contour framing method comprises the following steps: step S431, placing the real-time profile and the screening profile vertically according to the direction in which the human body stands vertically, placing the real-time profile and the screening profile into a plane coordinate system, and marking the real-time profile or the screening profile placed into the plane coordinate system as a profile to be framed;
step S432, a plane coordinate system comprises an X axis and a Y axis, a maximum value and a minimum value of the profile to be framed in the X axis direction are obtained, the maximum value and the minimum value of the width are respectively set, and the maximum value of the width is subtracted from the minimum value of the width to obtain the width of the profile; and obtaining the maximum value and the minimum value of the profile to be framed in the Y-axis direction, respectively setting the maximum value and the minimum value of the length, and subtracting the minimum value of the length from the maximum value of the length.
Step S5, calibrating the basic three-dimensional model based on the comparison result of the real-time image data and the screening image data to obtain a real-time three-dimensional model; step S5 further comprises the sub-steps of: step S51, acquiring real-time image data and screening image data, wherein the acquisition directions of the real-time image data and the screening image data are the same, and the acquisition directions of the real-time image data and the screening image data are set to be the first direction;
step S52, the first direction is any direction on the plane, and the first direction is perpendicular to the vertical direction;
step S53, making a vertical line in the first direction on the plane, setting the direction of the vertical line as a second direction, acquiring real-time image data and screening image data in the second direction, and setting the real-time image data and the screening image data as a second real-time image and a second screening direction respectively;
step S54, processing the second real-time image and the second screening image sequentially through a contour extraction method and a contour frame selection method to obtain contour parameters; extracting outline widths of the second real-time image and the second screening image, and setting the outline widths as a second direction real-time width and a second direction screening width respectively;
step S55, a three-dimensional coordinate system is established, a basic three-dimensional model is placed in the three-dimensional coordinate system, and the three-dimensional coordinate system comprises an X axis, a Y axis and a Z axis; the X axis is parallel to the first direction, the Y axis is parallel to the vertical direction, and the Z axis is parallel to the second direction;
Step S56, establishing cubes in a first length unit, and dividing a basic three-dimensional model in three-dimensional coordinates through a plurality of cubes;
step S57, dividing the real-time length by the screening length to obtain a length ratio, dividing the real-time width by the screening width to obtain a first width ratio, and dividing the real-time width in the second direction by the screening width in the second direction to obtain a second width ratio;
step S58, the side length of the cube in the basic three-dimensional model on the X axis is multiplied by a first width ratio to obtain a first side length, the side length on the Y axis is multiplied by a length ratio to obtain a second side length, and the side length on the Z axis is multiplied by a second width ratio to obtain a third side length;
and step S59, transforming all cubes in the basic three-dimensional model according to the first side length, the second side length and the third side length to obtain the real-time three-dimensional model.
And step S6, storing the real-time three-dimensional model into a heart model database.
Embodiment 3 the invention also provides a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of any of the methods described above. By the above technical solution, the computer program, when executed by the processor, performs the method in any of the alternative implementations of the above embodiments to implement the following functions: acquiring a plurality of groups of historical heart three-dimensional models, historical sign data and historical image data of users from a heart model database; acquiring real-time image data and real-time physical sign data of a user; comparing the real-time sign data with a plurality of groups of historical sign data, screening a plurality of groups of to-be-determined sign data from the plurality of groups of historical sign data, and marking a historical heart three-dimensional model corresponding to the to-be-determined sign data as a to-be-determined heart three-dimensional model; marking the historical image data corresponding to the three-dimensional model of the heart to be determined as the image data to be determined; comparing the real-time image data with the to-be-determined image data to obtain a comparison similarity absolute difference value, setting the to-be-determined image data with the minimum comparison similarity absolute difference value as screening image data, and marking a historical heart three-dimensional model corresponding to the screening image data as a basic three-dimensional model; calibrating the basic three-dimensional model based on the comparison result of the real-time image data and the screening image data to obtain a real-time three-dimensional model; the real-time three-dimensional model is stored in a heart model database.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied therein. The storage medium may be implemented by any type or combination of volatile or nonvolatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM), electrically erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
Claims (8)
1. The method for constructing the heart three-dimensional model based on image registration is characterized by comprising the following steps of: acquiring a plurality of groups of historical heart three-dimensional models, historical sign data and historical image data of users from a heart model database;
acquiring real-time image data and real-time physical sign data of a user;
comparing the real-time sign data with a plurality of groups of historical sign data, screening a plurality of groups of to-be-determined sign data from the plurality of groups of historical sign data, and marking a historical heart three-dimensional model corresponding to the to-be-determined sign data as a to-be-determined heart three-dimensional model; marking the historical image data corresponding to the three-dimensional model of the heart to be determined as the image data to be determined;
Comparing the real-time image data with the to-be-determined image data to obtain a comparison similarity absolute difference value, setting the to-be-determined image data with the minimum comparison similarity absolute difference value as screening image data, and marking a historical heart three-dimensional model corresponding to the screening image data as a basic three-dimensional model;
calibrating the basic three-dimensional model based on the comparison result of the real-time image data and the screening image data to obtain a real-time three-dimensional model;
storing the real-time three-dimensional model into a heart model database;
comparing the real-time sign data with a plurality of groups of historical sign data, and screening a plurality of groups of to-be-determined sign data from the plurality of groups of historical sign data comprises the following steps: acquiring the height, weight, age and heart rate in the real-time physical sign data, and setting the height, weight, age and heart rate in the real-time physical sign data as the real-time height, real-time weight, real-time age and real-time heart rate respectively;
setting the height, weight, age and heart rate in the historical sign data as historical height, historical weight, historical age and historical heart rate respectively;
adding a first age threshold to the real-time age to obtain an age screening upper limit value, subtracting the first age threshold from the real-time age to obtain an age screening lower limit value, and setting a section from the age screening lower limit value to the age screening upper limit value as an age screening section, wherein the age screening section comprises the age screening upper limit value and the age screening lower limit value;
Acquiring historical sign data in an age screening interval, and marking the historical sign data in the age screening interval as age screening sign data;
calculating the historical height and the historical weight in the age screening sign data, the real-time height and the real-time weight in the historical heart rate and the real-time sign data and the real-time heart rate through a depth screening calculation formula to obtain a sign comparison absolute difference value;
the depth screening calculation formula is configured as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Ctb is the absolute difference of sign comparison, ss is the real-time height, sl is the historical height, ts is the real-time weight, tl is the historical weight, xs is the real-time heart rate, and Xl is the historical heart rate;
sequencing the sign comparison absolute differences from small to large to obtain a sign comparison sequencing, and marking age screening sign data corresponding to the sign comparison absolute differences of the first comparison quantity before the sign comparison sequencing as sign data to be determined.
2. The image registration-based heart three-dimensional model construction method according to claim 1, wherein the historical image data and the real-time image data each comprise CT images, and the historical and real-time sign data comprise height, weight, age, and heart rate, respectively.
3. The method for constructing a three-dimensional model of a heart based on image registration according to claim 2, wherein comparing the real-time image data with the image data to be determined to obtain a comparison-like absolute difference value comprises: obtaining a heart image contour from the real-time image data through an image contour extraction method;
setting the heart image outline of the real-time image data as a real-time outline, acquiring the heart image outline of the screened image data, and setting the heart image outline as a screened outline;
vertically placing the real-time profile and the screening profile according to the direction in which the human body vertically stands, and obtaining profile parameters by a profile frame selection method, wherein the profile parameters comprise profile length and profile width;
setting the contour length and the contour width of the real-time contour as the real-time length and the real-time width respectively, and setting the contour length and the contour width of the screening contour as the screening length and the screening width respectively;
calculating the real-time length, the real-time width, the screening length and the screening width through an image comparison formula to obtain comparison similarity absolute differences;
the image comparison formula is configured to:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Cbd is the comparison similarity absolute difference, css is the real-time length, csx is the screening length, kss is the real-time width, and Ksx is the screening width.
4. A method of constructing a three-dimensional model of a heart based on image registration as claimed in claim 3, wherein the contour extraction method comprises: respectively carrying out graying treatment on the real-time image data and the screened image data to obtain a graying image;
acquiring a plurality of groups of edge pixel points of a heart region of the graying image corresponding to the screened image data, setting the edge pixel points as screened edge pixel points, calculating an average value of gray values of the plurality of screened edge pixel points, and setting the average value as reference edge gray;
acquiring pixel points which are adjacent to the pixel points at the screening edge and do not belong to the heart region, setting the pixel points as adjacent pixel points, calculating the average value of gray values of a plurality of adjacent pixel points, and setting the average value as adjacent reference gray;
calculating the average value of adjacent reference gray scales and reference edge gray scales, and setting the average value as divided gray scales;
taking the divided gray scale as a divided intermediate value to carry out binarization processing on the gray scale image to obtain a binarized image;
and extracting the outline of the heart image in the binarized image.
5. The image registration-based heart three-dimensional model construction method according to claim 4, wherein the contour framing method comprises: placing the real-time profile and the screening profile vertically according to the direction in which the human body stands vertically, placing the real-time profile and the screening profile into a plane coordinate system, and marking the real-time profile or the screening profile placed into the plane coordinate system as a profile to be framed;
The plane coordinate system comprises an X axis and a Y axis, the maximum value and the minimum value of the profile to be framed in the X axis direction are obtained, the maximum value and the minimum value of the width are respectively set, and the width is obtained by subtracting the minimum value of the width from the maximum value of the width; and obtaining the maximum value and the minimum value of the profile to be framed in the Y-axis direction, respectively setting the maximum value and the minimum value of the length, and subtracting the minimum value of the length from the maximum value of the length.
6. The method for constructing a three-dimensional model of a heart based on image registration according to claim 3, wherein calibrating the basic three-dimensional model based on the comparison result of the real-time image data and the screening image data, the obtaining the real-time three-dimensional model comprises: acquiring real-time image data and screening image data, wherein the acquisition directions of the real-time image data and the screening image data are the same, and the acquisition directions of the real-time image data and the screening image data are set to be first directions;
the first direction is any direction on the plane and is perpendicular to the vertical direction;
making a vertical line in a first direction on a plane, setting the direction of the vertical line as a second direction, acquiring real-time image data and screening image data in the second direction, and setting the real-time image data and the screening image data as a second real-time image and a second screening direction respectively;
Processing the second real-time image and the second screening image sequentially through a contour extraction method and a contour frame selection method to obtain contour parameters; extracting outline widths of the second real-time image and the second screening image, and setting the outline widths as a second direction real-time width and a second direction screening width respectively;
establishing a three-dimensional coordinate system, and placing the basic three-dimensional model into the three-dimensional coordinate system, wherein the three-dimensional coordinate system comprises an X axis, a Y axis and a Z axis; the X axis is parallel to the first direction, the Y axis is parallel to the vertical direction, and the Z axis is parallel to the second direction;
establishing cubes in a first length unit, and dividing a basic three-dimensional model in three-dimensional coordinates through a plurality of cubes;
dividing the real-time length by the screening length to obtain a length ratio, dividing the real-time width by the screening width to obtain a first width ratio, and dividing the real-time width in the second direction by the screening width in the second direction to obtain a second width ratio;
multiplying the side length of a cube in the basic three-dimensional model on the X axis by a first width ratio to obtain a first side length, multiplying the side length of the cube on the Y axis by a length ratio to obtain a second side length, and multiplying the side length of the cube on the Z axis by a second width ratio to obtain a third side length;
and transforming all cubes in the basic three-dimensional model according to the first side length, the second side length and the third side length to obtain the real-time three-dimensional model.
7. A system adapted for use in the image registration-based method of constructing a three-dimensional model of the heart of any one of claims 1-6, comprising: the system comprises a heart model database, an image acquisition module, a sign acquisition module, a comparison registration module and a three-dimensional construction module;
the heart model database stores a plurality of groups of historical heart three-dimensional models, historical sign data and historical image data of users;
the image acquisition module is used for acquiring real-time image data; the physical sign acquisition module is used for acquiring real-time physical sign data of a user;
the comparison registration module is used for comparing the real-time sign data with a plurality of groups of historical sign data, screening a plurality of groups of to-be-determined sign data from the plurality of groups of historical sign data, and marking a historical heart three-dimensional model corresponding to the to-be-determined sign data as a to-be-determined heart three-dimensional model; marking the historical image data corresponding to the three-dimensional model of the heart to be determined as the image data to be determined;
the three-dimensional construction module comprises an image comparison screening unit, a three-dimensional construction unit and a storage unit, wherein the image comparison screening unit is used for comparing real-time image data with to-be-determined image data to obtain comparison similar absolute differences, setting to-be-determined image data with the smallest comparison similar absolute differences as screened image data, and marking a historical heart three-dimensional model corresponding to the screened image data as a basic three-dimensional model;
The three-dimensional construction unit calibrates the basic three-dimensional model based on the comparison result of the real-time image data and the screening image data to obtain a real-time three-dimensional model;
the storage unit is used for storing the real-time three-dimensional model into a heart model database.
8. A storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311222620.5A CN116958456B (en) | 2023-09-21 | 2023-09-21 | Heart three-dimensional model construction method, system and storage medium based on image registration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311222620.5A CN116958456B (en) | 2023-09-21 | 2023-09-21 | Heart three-dimensional model construction method, system and storage medium based on image registration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116958456A CN116958456A (en) | 2023-10-27 |
| CN116958456B true CN116958456B (en) | 2023-12-08 |
Family
ID=88462454
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311222620.5A Active CN116958456B (en) | 2023-09-21 | 2023-09-21 | Heart three-dimensional model construction method, system and storage medium based on image registration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116958456B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6106466A (en) * | 1997-04-24 | 2000-08-22 | University Of Washington | Automated delineation of heart contours from images using reconstruction-based modeling |
| CN105631931A (en) * | 2015-12-21 | 2016-06-01 | 电子科技大学 | Low-complexity heart surface three-dimensional shape online modeling system and method thereof |
| CN109820594A (en) * | 2018-12-20 | 2019-05-31 | 天津市胸科医院 | A method of production heart part 3D printing model is guided using ultrasonic wave initial data |
| CN111150490A (en) * | 2020-01-15 | 2020-05-15 | 陈挺 | Intelligent assistant system for cardiac radio frequency ablation surgery based on AR and AI technologies |
| CN114846557A (en) * | 2019-12-20 | 2022-08-02 | Tc1有限责任公司 | System and method for personalized cardiovascular analysis |
| CN115661149A (en) * | 2022-12-26 | 2023-01-31 | 天津医科大学总医院 | Lung image processing system based on lung tissue data |
| CN116543889A (en) * | 2023-07-05 | 2023-08-04 | 深圳市依诺普医疗设备有限公司 | Endoscope remote control system and method based on medical Internet of things |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015200552A1 (en) * | 2014-06-25 | 2015-12-30 | William Beaumont Hospital | Simulated cardiac model |
-
2023
- 2023-09-21 CN CN202311222620.5A patent/CN116958456B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6106466A (en) * | 1997-04-24 | 2000-08-22 | University Of Washington | Automated delineation of heart contours from images using reconstruction-based modeling |
| CN105631931A (en) * | 2015-12-21 | 2016-06-01 | 电子科技大学 | Low-complexity heart surface three-dimensional shape online modeling system and method thereof |
| CN109820594A (en) * | 2018-12-20 | 2019-05-31 | 天津市胸科医院 | A method of production heart part 3D printing model is guided using ultrasonic wave initial data |
| CN114846557A (en) * | 2019-12-20 | 2022-08-02 | Tc1有限责任公司 | System and method for personalized cardiovascular analysis |
| CN111150490A (en) * | 2020-01-15 | 2020-05-15 | 陈挺 | Intelligent assistant system for cardiac radio frequency ablation surgery based on AR and AI technologies |
| CN115661149A (en) * | 2022-12-26 | 2023-01-31 | 天津医科大学总医院 | Lung image processing system based on lung tissue data |
| CN116543889A (en) * | 2023-07-05 | 2023-08-04 | 深圳市依诺普医疗设备有限公司 | Endoscope remote control system and method based on medical Internet of things |
Non-Patent Citations (2)
| Title |
|---|
| "A Computational Model of Cardiac Electromechanics";David Nickerson et al.;《2006 International Conference of the IEEE Engineering in Medicine and Biology Society》;全文 * |
| "基于患者个性化虚拟心脏建模方法初探及在室速和房颤中的应用";吴政洪;《中国博士学位论文全文数据库 医药卫生科技辑》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116958456A (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805860B (en) | Image analysis method, device, program, and deep learning algorithm generation method | |
| CN102890823B (en) | Motion object outline is extracted and left ventricle image partition method and device | |
| CN109410318B (en) | Three-dimensional model generation method, device, equipment and storage medium | |
| CN111932552B (en) | Aorta modeling method and device | |
| CN108520512B (en) | Method and device for measuring eye parameters | |
| CN108805923B (en) | Physiological parameter acquisition method and device | |
| JP4138371B2 (en) | Anatomical feature position detecting device, recording medium, subject structure measuring device, and recording medium | |
| CN110097546B (en) | Method and device for evaluating defects of knee joint cartilage tissues | |
| CN110310280A (en) | Hepatic duct and the image-recognizing method of calculus, system, equipment and storage medium | |
| CN113240661B (en) | Deep learning-based lumbar vertebra bone analysis method, device, equipment and storage medium | |
| US11636695B2 (en) | Method for synthesizing image based on conditional generative adversarial network and related device | |
| CN113262070A (en) | Dental surgery equipment positioning method and system based on image recognition and storage medium | |
| CN116312986A (en) | Three-dimensional medical image labeling method and device, electronic equipment and readable storage medium | |
| CN112651389A (en) | Method and device for training, correcting and identifying correction model of non-orthoptic iris image | |
| CN114642444A (en) | Oral implantation precision evaluation method and system and terminal equipment | |
| CN116958456B (en) | Heart three-dimensional model construction method, system and storage medium based on image registration | |
| CN109934798A (en) | Internal object information labeling method and device, electronic equipment, storage medium | |
| CN110751200B (en) | Shoe stamp height estimation method based on multiple gauss | |
| CN113222996A (en) | Heart segmentation quality evaluation method, device, equipment and storage medium | |
| CN110610502A (en) | Automatic aortic arch region positioning and segmentation method based on CT image | |
| US9402549B2 (en) | Methods and apparatus to estimate ventricular volumes | |
| US20230215027A1 (en) | Oral image marker detection method, and oral image matching device and method using same | |
| CN114359317A (en) | Blood vessel reconstruction method based on small sample identification | |
| CN113907775A (en) | Hip joint image quality judgment method and system | |
| CN111627554A (en) | Fracture image automatic classification system based on deep convolutional neural network |
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 |