CN114831729A - Left auricle plugging simulation system for ultrasonic cardiogram and CT multi-mode image fusion - Google Patents
Left auricle plugging simulation system for ultrasonic cardiogram and CT multi-mode image fusion Download PDFInfo
- Publication number
- CN114831729A CN114831729A CN202210262054.XA CN202210262054A CN114831729A CN 114831729 A CN114831729 A CN 114831729A CN 202210262054 A CN202210262054 A CN 202210262054A CN 114831729 A CN114831729 A CN 114831729A
- Authority
- CN
- China
- Prior art keywords
- image
- left auricle
- atrial appendage
- fusion
- dimensional
- 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.)
- Pending
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 58
- 238000004088 simulation Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 35
- 210000005248 left atrial appendage Anatomy 0.000 claims description 56
- 238000004873 anchoring Methods 0.000 claims description 26
- 230000011218 segmentation Effects 0.000 claims description 20
- 210000003238 esophagus Anatomy 0.000 claims description 18
- 230000000694 effects Effects 0.000 claims description 15
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000002592 echocardiography Methods 0.000 claims description 9
- 210000005242 cardiac chamber Anatomy 0.000 claims description 7
- 230000002980 postoperative effect Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 210000005240 left ventricle Anatomy 0.000 claims description 5
- 210000005241 right ventricle Anatomy 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 230000002792 vascular Effects 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 210000005246 left atrium Anatomy 0.000 claims description 4
- 230000003902 lesion Effects 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 210000005245 right atrium Anatomy 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims description 4
- 238000002405 diagnostic procedure Methods 0.000 claims 2
- 238000002560 therapeutic procedure Methods 0.000 claims 2
- 238000003384 imaging method Methods 0.000 abstract description 9
- 238000013486 operation strategy Methods 0.000 abstract description 2
- 238000013175 transesophageal echocardiography Methods 0.000 description 15
- 238000002604 ultrasonography Methods 0.000 description 8
- 230000000747 cardiac effect Effects 0.000 description 4
- 210000000709 aorta Anatomy 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 229910052739 hydrogen Inorganic materials 0.000 description 3
- 238000001356 surgical procedure Methods 0.000 description 3
- 238000004195 computer-aided diagnosis Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000007536 Thrombosis Diseases 0.000 description 1
- 238000002583 angiography Methods 0.000 description 1
- 230000010100 anticoagulation Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 210000002837 heart atrium Anatomy 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 210000004115 mitral valve Anatomy 0.000 description 1
- 238000002601 radiography Methods 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- PJVWKTKQMONHTI-UHFFFAOYSA-N warfarin Chemical compound OC=1C2=CC=CC=C2OC(=O)C=1C(CC(=O)C)C1=CC=CC=C1 PJVWKTKQMONHTI-UHFFFAOYSA-N 0.000 description 1
- 229960005080 warfarin Drugs 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
- A61B2034/101—Computer-aided simulation of surgical operations
- A61B2034/102—Modelling of surgical devices, implants or prosthesis
- A61B2034/104—Modelling the effect of the tool, e.g. the effect of an implanted prosthesis or for predicting the effect of ablation or burring
Abstract
The invention relates to a left auricle plugging simulation system based on ultrasonic cardiogram and CT multi-mode image fusion, belonging to the technical field of medical instruments. The invention collects DICOM image data of the two methods respectively by the combined application of the two imaging methods, designs software to realize fusion imaging, simultaneously displays the internal structure, function and external form of the left auricle and the adjacency thereof, and then simulates the matching of the occluder, so that an operation doctor can select an operation strategy by using a left auricle occlusion simulation device before an operation, and selects the best and most appropriate occluder device, thereby improving the success rate of the operation. The image fusion simulation system provided by the invention can realize the fusion of the transesophageal real-time four-dimensional echocardiogram and the CT multi-mode image of the left auricle, and perform the fusion of the internal structure and function, the external integral form and the adjacency of the left auricle on the left auricle, thereby providing a feasible imaging method for improving the success rate of the left auricle occlusion and reducing the complications.
Description
Technical Field
The invention relates to a left auricle occlusion simulation system for ultrasonic cardiogram and CT multi-mode image fusion, belonging to the technical field of medical instruments.
Background
Currently, in left atrial appendage occlusion surgery, clinical application is mostly based on guidance of transesophageal echocardiography or CT single-mode imaging methods, and observation of left atrial appendage occlusion is realized by combining operative central angiography.
However, with the wide development of left atrial appendage occlusion, especially the very simple operation, on one hand, the left atrial appendage occlusion has a high residual shunt rate after surgery, which is still one of the important problems for the cardiovascular department doctors, and the risk of thrombosis on the surface of the occlusion device of a patient with a large residual shunt amount increases, and the residual cavity needs to be re-occluded in addition to long-term anticoagulation treatment; on the other hand, due to the fact that the anatomical forms of the left auricle are various, the conventional method has limited evaluation on the anatomical forms and the adjacent forms of the left auricle, the diameter of an anchoring area, the depth of the left auricle and the like can be measured when the left auricle radiography is carried out in the left auricle plugging operation, but the evaluation on the left auricle in the operation is limited, and the plugging strategy selected immediately is relatively short in time and is not accurate enough. The situation may cause the failure of left atrial appendage occlusion, or the occurrence of situations such as more residual flow rate after occlusion, displacement of the occluder and even falling off, and the like, and the difficulty also exists when the occluder device is selected by the operating doctor, which affects the operation effect. Therefore, the technical problem of how to simulate the left auricle plugging effect before an operation, reduce the complications such as residual shunt after the left auricle plugging operation and the like and improve the success rate of the operation is urgently needed to be solved in the technical field.
Disclosure of Invention
The invention aims to solve the technical problems of simulating the left auricle plugging effect before an operation, reducing the complications of residual shunt, displacement, even shedding and the like around the left auricle plugging device after the operation and improving the success rate of the operation.
In order to solve the above problems, the technical scheme of the invention is to provide a method for predicting left atrial appendage occlusion effect by fusing real-time four-dimensional echocardiography and CT multi-mode images through an esophagus, which comprises the following steps:
step 1: acquiring DICOM (Digital Imaging and Communications in Medicine) format image data of a real-time four-dimensional echocardiogram and CT of a left auricle of a heart of a human body through an esophagus;
step 2: carrying out threshold segmentation on the CT image of the human heart; for a typical heart segmentation task, the input CT image is generated into right ventricle/left ventricle/right atrium/left atrium and basic vascular structures by a full-convolution Neural network FCN (full-Convolutional Neural Networks); the FCN conducts model training through a U-structure network and a supervised learning framework based on a public full heart segmentation data set; extracting the main direction by adopting all grid points in the heart structure; for a given DSCT (Dual Source CT) image
Where C is the number of channels and D, H, W are the thickness, height and width of the input image, respectively.
And step 3: preprocessing and segmenting a real-time four-dimensional ultrasonic image of the left auricle of the human body through the esophagus based on an Maximization-Expectation (EM) algorithm; the segmentation process firstly selects a basic position through a four-cavity plane, local region expansion is carried out based on a Sobel operator, and time sequence weight is introduced to be used between CT and TEE (transesophageal echocardiography, TEE)A similarity measure of; given the RT4D-TEE ultrasound image sequence, N is included B A 3D-TEE image, the model will get N B Set of points Y l For characterizing the four-lumen contour in an ultrasound image.
And 4, step 4: based on the processed CT image and the processed ultrasonic image, performing the matching of an initial coarse ultrasonic frame and a CT horizon by an exhaustive discrete search method similar to the prior method; for each time point t, the section with the minimum mean square error will be transformed as a rigid to optimal match;
and 5: carrying out spatial registration on the heart chamber, the CT three-dimensional model of the left auricle and the ultrasonic four-dimensional model of the left auricle to obtain a fusion model of the left auricle image based on the ultrasonic/CT image, and realizing the joint display of two image modalities in a visualization mode to obtain the fusion model of the left auricle image of the ultrasonic/CT image;
step 6: based on the fusion model of the left auricle image, the left auricle plugging device is put into the left auricle fusion model in a simulation mode, and the left auricle plugging device is used for assisting a clinician in judging the lesion grade and guiding operation planning and postoperative effect evaluation.
Preferably, the spatial registration in step 5 includes a registration algorithm, where the registration algorithm maps two heterogeneous image modalities into the same coordinate space through feature transformation, and has better robustness for local non-rigid deformation caused by motion.
Preferably, the inner surface of the left auricle displayed by the fusion model in the step 5 is provided with a positioning anchoring area, and the bottom of the inner surface is provided with a mark point of the left auricle depth; in the step 6, the left atrial appendage occlusion device is placed in the left atrial appendage fusion model in a simulated manner, namely the left atrial appendage occlusion device is placed in the anchoring area.
The invention provides a left atrial appendage occlusion simulation system, comprising:
the data acquisition module is used for acquiring DICOM format image data of real-time four-dimensional echocardiography and CT of the left auricle of the heart of the human body through the esophagus;
the data processing module is used for processing a CT image of a human heart and a real-time four-dimensional ultrasonic image of a human left auricle through an esophagus and modeling; carrying out spatial registration on the heart chamber, the CT three-dimensional model of the left auricle and the ultrasonic four-dimensional model of the left auricle to obtain a fusion model of the left auricle image based on the ultrasonic/CT image;
the simulated operation module is used for simulating the placement of the left atrial appendage occlusion device into the left atrial appendage fusion model;
the risk evaluation module is used for assisting a clinician in distinguishing the focus and guiding operation planning and postoperative effect evaluation; and selecting a proper left auricle plugging device and a proper surgical scheme according to the simulation effect.
Preferably, matching devices for simulating different types of left atrial appendage occlusion devices are arranged in the simulated surgery module.
Preferably, the matching device is provided with a structure for anchoring with the left atrial appendage anchoring region.
The invention provides a storage device, wherein a plurality of instructions are stored in the storage device, and the instructions are suitable for executing the steps in the method for predicting the plugging effect of the left auricle by fusing the real-time four-dimensional echocardiogram and CT multi-mode images through the esophagus.
The invention provides application of the left atrial appendage occlusion simulation system in a non-diagnosis method and a non-treatment method.
The invention provides application of the method for predicting the left auricle occlusion effect by fusing the real-time four-dimensional echocardiogram and CT multi-mode images through the esophagus in a non-diagnosis method and a non-treatment method.
Compared with the prior art, the invention has the following beneficial effects:
the invention relates to a transesophageal real-time four-dimensional echocardiogram and CT multi-modal image fusion system and a left atrial appendage occlusion simulation device. Through the joint application of the two imaging methods, DICOM image data of the two are respectively collected, software is designed to realize fusion imaging, the internal structure and function and the external form and adjacency of the left auricle are simultaneously displayed, and then matching of the occluder is simulated, so that an operation doctor can select an operation strategy by using a left auricle occlusion simulation device before an operation, and select an optimal and most appropriate occluder device, and the success rate of the operation is improved through the method. The multi-mode fusion-prediction system for the left auricle can realize the fusion of the transesophageal real-time four-dimensional echocardiogram and the CT multi-mode image of the left auricle and perform the fusion of the internal structure and function, the external integral shape and the adjacency of the left auricle on the left auricle, thereby providing a feasible imaging method for improving the success rate of left auricle occlusion and reducing complications.
The left auricle occlusion simulation system provided by the invention can realize the matching of the left auricle occluder device and the left auricle and help a clinician select the most appropriate occluder device; the invention has feasibility, accuracy and generalizability for selecting the conventional left atrial appendage occluder, and provides a feasible imaging method for improving the success rate of left atrial appendage occlusion and reducing complications.
The invention is helpful for selecting the most suitable occluder device, and is helpful for judging whether the left auricle with special shape is suitable for occlusion and selecting the occluder; the invention is beneficial to designing the occluder device with special shape, guiding the design of the device and improving the device on the basis of the existing device, and lays a foundation for improving the left atrial appendage occluder device.
Drawings
Fig. 1 is a diagram of the analysis process of complications such as occluder selection and residual shunt based on fused images.
Fig. 2 is a schematic view of a left atrial appendage occlusion device for simulating placement of a left atrial appendage.
Fig. 3 is a schematic diagram of a left atrial appendage occlusion device for simulating placement of a left atrial appendage.
Detailed Description
In order to make the invention more comprehensible, preferred embodiments are described in detail below with reference to the accompanying drawings:
as shown in fig. 1-3, in order to reduce the residual shunt rate after left atrial appendage occlusion and improve the success rate of the operation, the invention provides a method for predicting the left atrial appendage occlusion effect by fusing real-time four-dimensional echocardiography and CT multi-mode images through the esophagus, which comprises the following steps:
step 1: acquiring DICOM format image data of a real-time four-dimensional echocardiogram and CT of the left auricle of the heart of the human body through an esophagus;
step 2: carrying out threshold segmentation on the CT image of the human heart; for a typical heart segmentation task, generating right ventricle/left ventricle/right atrium/left atrium and basic vascular structures from input CT images through a full convolution neural network FCN; the FCN conducts model training through a U-structure network and a supervised learning framework based on a public full heart segmentation data set; extracting the main direction by adopting all grid points in the heart structure; for a given DSCT image
Where C is the number of channels and D, H, W are the thickness, height and width of the input image, respectively.
And step 3: preprocessing and segmenting a real-time four-dimensional ultrasonic image of the left auricle of the human body through the esophagus based on an maximization-expectation EM algorithm; in the segmentation process, a basic position is selected through a four-cavity plane, local region expansion is carried out based on a Sobel operator, and time sequence weight is introduced for similarity measurement between CT and TEE; given the RT4D-TEE ultrasound image sequence, N is included B A 3D-TEE image, the model will get N B Set of points Y l For characterizing the four-lumen contour in an ultrasound image.
And 4, step 4: based on the processed CT image and the processed ultrasonic image, performing the matching of an initial coarse ultrasonic frame and a CT horizon by an exhaustive discrete search method similar to the prior method; for each time point t, the section with the minimum mean square error will be transformed as a rigid to optimal match;
and 5: carrying out spatial registration on the heart chamber, the CT three-dimensional model of the left auricle and the ultrasonic four-dimensional model of the left auricle to obtain a fusion model of the left auricle image based on the ultrasonic/CT image, and realizing the joint display of two image modalities in a visualization mode to obtain the fusion model of the left auricle image of the ultrasonic/CT image;
step 6: based on the fusion model of the left auricle image, the left auricle plugging device is put into the left auricle fusion model in a simulation mode, and the left auricle plugging device is used for assisting a clinician in judging the lesion grade and guiding operation planning and postoperative effect evaluation.
The spatial registration in the step 5 includes a registration algorithm, the registration algorithm maps two heterogeneous image modalities to the same coordinate space through feature transformation, and the registration algorithm has better robustness for local non-rigid deformation caused by motion.
The inner surface of the left auricle displayed by the fusion model in the step 5 is provided with a positioning anchoring area, and the bottom of the inner surface is provided with a mark point of the left auricle depth; in the step 6, the left atrial appendage occlusion device is placed in the left atrial appendage fusion model in a simulated manner, namely the left atrial appendage occlusion device is placed in the anchoring area.
The invention provides a left auricle plugging simulation system for fusion of an echocardiogram and a CT multi-modal image, which comprises:
the data acquisition module is used for acquiring DICOM format image data of real-time four-dimensional echocardiography and CT of the left auricle of the heart of the human body through the esophagus;
the data processing module is used for processing a CT image of a human heart and a real-time four-dimensional ultrasonic image of a human left auricle through an esophagus and modeling; carrying out spatial registration on the heart chamber, the CT three-dimensional model of the left auricle and the ultrasonic four-dimensional model of the left auricle to obtain a fusion model of the left auricle image based on the ultrasonic/CT image;
the simulated operation module is used for simulating the placement of the left atrial appendage occlusion device into the left atrial appendage fusion model;
the risk evaluation module is used for assisting a clinician in distinguishing the focus and guiding operation planning and postoperative effect evaluation; and selecting a proper left atrial appendage occlusion device and a proper surgical plan according to the simulation effect.
The simulated operation module is provided with a matching device for simulating different types of left atrial appendage plugging devices.
The matching device is provided with a structure for anchoring with the left atrial appendage anchoring area.
The invention provides a storage device, wherein the storage device stores a plurality of instructions, and the instructions are suitable for executing the steps in the method for predicting the plugging effect of the left auricle according to the real-time esophageal four-dimensional echocardiography and CT multi-modal image fusion.
The invention provides a left auricle plugging simulation system for fusing echocardiogram and CT multi-modal images, which can realize the fusion of the transesophageal real-time four-dimensional echocardiogram and CT multi-modal images of the left auricle and is applied to embedded equipment integrating the left auricle image modeling and the fusion system thereof,
the image fusion comprises the following steps: acquiring DICOM format image data of a real-time four-dimensional echocardiogram and CT of the left auricle of the heart of the human body through an esophagus; carrying out threshold segmentation on the CT image of the human heart; for a typical cardiac segmentation task, the full convolution neural network FCN generates right ventricle/left ventricle/right atrium/left atrium (RV/LV/RA/LA) and basic vascular structures such as the Aorta (Aorta) from the input CT images. The FCN performs model training through a U-fabric network and a supervised learning framework based on a public full-heart segmentation data set. On this basis, all grid points in the cardiac structure are further used for principal direction extraction. For a given DSCT image
Where C is the number of channels and D, H, W are the thickness, height and width of the input image, respectively. The real-time transesophageal real-time four-dimensional ultrasound image of the left atrial appendage of a human body is preprocessed and segmented firstly based on an Maximization-Expectation (EM) algorithm. The segmentation process firstly selects a basic position through a four-cavity plane, local region expansion is carried out based on a Sobel operator, and time sequence weight is introduced for similarity measurement between CT and TEE (transesophageal echocardiography). Given the RT4D-TEE ultrasound image sequence, N is included B A 3D-TEE image, the model will get N B Set of points Y l For characterizing the four-lumen contour in an ultrasound image.
The invention provides a transesophageal real-time four-dimensional echocardiogram and CT multi-modal image fusion left auricle plugging simulation system, which comprises a transesophageal real-time four-dimensional echocardiogram and CT multi-modal image fusion system and a matching device;
wherein, the image fusion system comprises a transesophageal echocardiogram and a CT image; transesophageal echocardiography images include two-dimensional and four-dimensional images; CT images, including two-dimensional and three-dimensional images; the matching device is used for simulating different types of left atrial appendage occluder devices; the mating device has anchoring regions for different occluder devices.
A left auricle image modeling method of a left auricle occlusion simulation system for fusing an echocardiogram and a CT multi-modal image comprises the following steps:
1. the method comprises the steps of obtaining an ultrasonic image and CT data of the left auricle of a human body, and collecting the ultrasonic image data and CT data of a patient in a DICOM format of the left auricle by using a medical detection instrument.
2. In a patient left atrial appendage ultrasound image, a pre-processing and segmentation is first performed based on the maximization-expectation EM algorithm. In the segmentation process, a basic position is selected through a four-cavity plane, local region expansion is carried out based on a Sobel operator, and time sequence weight is introduced for similarity measurement between CT and TEE.
3. In a CT image of a human heart, the basic structure of the heart is first segmented using FCN. For a typical cardiac segmentation task, the FCN generates left and right ventricles/atria (RV/LV/RA/LA) and basic vascular structures (Aorta, etc.) from the input CT images. The FCN performs model training through a U-fabric network and a supervised learning framework based on a public full-heart segmentation data set. On this basis, all grid points in the cardiac structure are further used for principal direction extraction.
4. Based on the processed CT image and the processed ultrasonic image, the initial coarse ultrasonic frame and the CT horizon matching are executed through an exhaustive discrete search method similar to the existing method. For each time point t, the section with the smallest mean square error will be transformed as a rigid transformation to the best match.
5. The method comprises the following steps of carrying out spatial registration on a heart chamber, a CT three-dimensional model of a left auricle and an ultrasonic four-dimensional model of the left auricle to obtain a fusion model of a left auricle image based on an ultrasonic-CT image, wherein the fusion model comprises the following steps: a registration algorithm is designed, two heterogeneous image modalities are mapped under the same coordinate space through feature transformation, and the method has good robustness for local non-rigid deformation caused by motion. And finally, realizing the joint display of the two image modalities in a visualization mode to obtain a fusion model of the left auricle image of the ultrasonic-CT image for clinical diagnosis.
6. Performing a computer-aided diagnosis framework study based on multimodal feature fusion: after the multi-modal registration work is completed, a corresponding computer-aided diagnosis algorithm needs to be designed based on visual image data, so as to assist a clinician in judging the lesion grade and guiding operation planning and postoperative effect evaluation.
The inner surface of the fusion model of the left auricle image is provided with a positioning anchoring area structure; the bottom of the fusion model of the left auricle image is provided with a mark point of the left auricle depth; the left atrial appendage occluder device is placed over an anchoring zone structure.
The inner surface of the fusion model of the left auricle image is provided with a positioning anchoring area structure in the direction extending to the inner position of the body of the movable part; the left auricle occluder device is placed on the anchoring area structure, so that the left auricle occluder device can be used for plugging the left auricle.
The matching device is used for simulating different types of left atrial appendage occluder devices; the matching device is provided with different anchoring areas corresponding to different occluder devices.
The fusion model of the left auricle image is positioned at the position of the inner opening and the circumflex branch of the left auricle and is respectively provided with an anchoring area. The position of the anchoring area is an adjustable structure aiming at different forms of the left atrial appendage. The position of the outer opening of the left atrial appendage is positioned between the warfarin crest and the mitral valve ring, a covering area is arranged in the area of the connecting line and the anchoring area, and the structure is adjustable for the left atrial appendage with different forms. The footprint and anchor zone may be for different types of occluder devices.
The invention provides a left auricle plugging simulation system which can realize the matching of a left auricle plugging device and a left auricle and is beneficial to selecting the most appropriate plugging device; arranging a matching device, wherein different anchoring areas corresponding to different occluder devices are arranged on the matching device; the position of the anchoring area in the fusion model of the left auricle image is an adjustable structure, and the fusion model is also provided with a covering area which is an adjustable structure aiming at the left auricle with different forms. The footprint and anchoring zone may be for different specifications, models of occluder devices.
While the invention has been described with respect to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention. Those skilled in the art can make various changes, modifications and equivalent arrangements, which are equivalent to the embodiments of the present invention, without departing from the spirit and scope of the present invention, and which may be made by utilizing the techniques disclosed above; meanwhile, any changes, modifications and variations of the above-described embodiments, which are equivalent to those of the technical spirit of the present invention, are within the scope of the technical solution of the present invention.
Claims (9)
1. A method for predicting left atrial appendage occlusion effect by fusing real-time four-dimensional echocardiography and CT multi-modal images through an esophagus is characterized by comprising the following steps of:
step 1: acquiring DICOM format image data of a real-time four-dimensional echocardiogram and CT of the left auricle of the heart of the human body through an esophagus;
step 2: carrying out threshold segmentation on the CT image of the human heart; for a typical heart segmentation task, generating right ventricle/left ventricle/right atrium/left atrium and basic vascular structures from input CT images through a full convolution neural network FCN; the FCN conducts model training through a U-structure network and a supervised learning framework based on a public full heart segmentation data set; extracting the main direction by adopting all grid points in the heart structure;
and step 3: preprocessing and segmenting a real-time four-dimensional ultrasonic image of the left auricle of the human body through the esophagus based on an maximization-expectation EM algorithm; in the segmentation process, a basic position is selected through a four-cavity plane, local region expansion is carried out based on a Sobel operator, and time sequence weight is introduced for similarity measurement between CT and TEE;
and 4, step 4: based on the processed CT image and the processed ultrasonic image, performing the matching of an initial coarse ultrasonic frame and a CT horizon by an exhaustive discrete search method similar to the prior method; for each time point t, the section with the minimum mean square error will be transformed as a rigid to optimal match;
and 5: carrying out spatial registration on the heart chamber, the CT three-dimensional model of the left auricle and the ultrasonic four-dimensional model of the left auricle to obtain a fusion model of the left auricle image based on the ultrasonic/CT image, and realizing the joint display of two image modalities in a visualization mode to obtain the fusion model of the left auricle image of the ultrasonic/CT image;
step 6: based on the fusion model of the left auricle image, the left auricle plugging device is put into the left auricle fusion model in a simulation mode, and the left auricle plugging device is used for assisting a clinician in judging the lesion grade and guiding operation planning and postoperative effect evaluation.
2. The method for predicting left atrial appendage occlusion effect by transesophageal real-time four-dimensional echocardiogram and CT multi-modality image fusion according to claim 1, wherein: the spatial registration in the step 5 comprises a registration algorithm, the registration algorithm maps two heterogeneous image modalities to the same coordinate space through feature transformation, and the registration algorithm has better robustness for local non-rigid deformation caused by motion.
3. The method for predicting left atrial appendage occlusion effect by transesophageal real-time four-dimensional echocardiogram and CT multi-modality image fusion according to claim 1, wherein: the inner surface of the left auricle displayed by the fusion model in the step 5 is provided with a positioning anchoring area, and the bottom of the left auricle is provided with a mark point of the left auricle depth; in the step 6, the left atrial appendage occlusion device is placed in the left atrial appendage fusion model in a simulated manner, namely the left atrial appendage occlusion device is placed in the anchoring area.
4. A left atrial appendage occlusion simulation system, comprising:
the data acquisition module is used for acquiring DICOM format image data of real-time four-dimensional echocardiography and CT of the left auricle of the heart of the human body through the esophagus;
the data processing module is used for processing a CT image of a human heart and a real-time four-dimensional ultrasonic image of a human left auricle through an esophagus and modeling; carrying out spatial registration on the three-dimensional model of the heart chamber and the four-dimensional model of the left auricle to obtain a fusion model of the left auricle image based on the ultrasonic/CT image;
the simulated operation module is used for simulating the placement of the left atrial appendage occlusion device into the left atrial appendage fusion model;
the risk evaluation module is used for assisting a clinician in distinguishing the focus and guiding operation planning and postoperative effect evaluation; and selecting a proper left auricle plugging device and a proper surgical scheme according to the simulation effect.
5. The left atrial appendage occlusion simulation system of claim 4, wherein: and a matching device for simulating different types of left atrial appendage plugging devices is arranged in the simulated operation module.
6. The left atrial appendage occlusion simulation system of claim 5, wherein: and the matching device is provided with an anchoring structure for anchoring with the anchoring area of the left auricle.
7. A storage device storing instructions adapted to perform the steps of a method for predicting left atrial appendage occlusion effect by transesophageal real-time four-dimensional echocardiography and CT multi-modality image fusion according to any one of claims 1 to 3.
8. Use of a left atrial appendage occlusion simulation system as in any one of claims 4-6 in a non-diagnostic method and a non-therapeutic method.
9. Use of a method for predicting left atrial appendage occlusion by transesophageal real-time four-dimensional echocardiography and CT multi-modality image fusion according to any one of claims 1 to 3 in a non-diagnostic method and a non-therapeutic method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210262054.XA CN114831729A (en) | 2022-03-17 | 2022-03-17 | Left auricle plugging simulation system for ultrasonic cardiogram and CT multi-mode image fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210262054.XA CN114831729A (en) | 2022-03-17 | 2022-03-17 | Left auricle plugging simulation system for ultrasonic cardiogram and CT multi-mode image fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114831729A true CN114831729A (en) | 2022-08-02 |
Family
ID=82562317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210262054.XA Pending CN114831729A (en) | 2022-03-17 | 2022-03-17 | Left auricle plugging simulation system for ultrasonic cardiogram and CT multi-mode image fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114831729A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108143396A (en) * | 2018-01-19 | 2018-06-12 | 苏州江奥光电科技有限公司 | A kind of portable early stage caries diagnostic device and diagnostic method based on fluorescence imaging |
| WO2024039741A1 (en) * | 2022-08-17 | 2024-02-22 | Boston Scientific Scimed, Inc. | Left atrial appendage closure pre-procedure system and methods |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110153286A1 (en) * | 2009-12-22 | 2011-06-23 | Siemens Corporation | Method and System for Virtual Percutaneous Valve Implantation |
| EP2538398A1 (en) * | 2011-06-19 | 2012-12-26 | Centrum Transferu Technologii Medycznych Park Technologiczny Sp. z o.o. | System and method for transesophageal echocardiography simulations |
| US20170217102A1 (en) * | 2016-01-29 | 2017-08-03 | Siemens Medical Solutions Usa, Inc. | Multi-Modality Image Fusion for 3D Printing of Organ Morphology and Physiology |
| CN109377520A (en) * | 2018-08-27 | 2019-02-22 | 西安电子科技大学 | Cardiac image registration arrangement and method based on semi-supervised circulation GAN |
| CN113057677A (en) * | 2021-03-30 | 2021-07-02 | 华南理工大学 | Heart image modeling method, system and equipment for fusing ultrasonic image and CT image |
-
2022
- 2022-03-17 CN CN202210262054.XA patent/CN114831729A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110153286A1 (en) * | 2009-12-22 | 2011-06-23 | Siemens Corporation | Method and System for Virtual Percutaneous Valve Implantation |
| EP2538398A1 (en) * | 2011-06-19 | 2012-12-26 | Centrum Transferu Technologii Medycznych Park Technologiczny Sp. z o.o. | System and method for transesophageal echocardiography simulations |
| US20170217102A1 (en) * | 2016-01-29 | 2017-08-03 | Siemens Medical Solutions Usa, Inc. | Multi-Modality Image Fusion for 3D Printing of Organ Morphology and Physiology |
| CN109377520A (en) * | 2018-08-27 | 2019-02-22 | 西安电子科技大学 | Cardiac image registration arrangement and method based on semi-supervised circulation GAN |
| CN113057677A (en) * | 2021-03-30 | 2021-07-02 | 华南理工大学 | Heart image modeling method, system and equipment for fusing ultrasonic image and CT image |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108143396A (en) * | 2018-01-19 | 2018-06-12 | 苏州江奥光电科技有限公司 | A kind of portable early stage caries diagnostic device and diagnostic method based on fluorescence imaging |
| WO2024039741A1 (en) * | 2022-08-17 | 2024-02-22 | Boston Scientific Scimed, Inc. | Left atrial appendage closure pre-procedure system and methods |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2472442C2 (en) | System for complex combination of data of image formation based on statistical anatomical models | |
| JP5345275B2 (en) | Superposition of ultrasonic data and pre-acquired image | |
| JP5265091B2 (en) | Display of 2D fan-shaped ultrasonic image | |
| JP5474342B2 (en) | Anatomical modeling with 3-D images and surface mapping | |
| CN109589170B (en) | Left atrial appendage closure guidance in medical imaging | |
| JP4795099B2 (en) | Superposition of electroanatomical map and pre-acquired image using ultrasound | |
| JP6388632B2 (en) | Operating method of processor unit | |
| JP5622995B2 (en) | Display of catheter tip using beam direction for ultrasound system | |
| US7855723B2 (en) | Image registration using locally-weighted fitting | |
| WO2015161728A1 (en) | Three-dimensional model construction method and device, and image monitoring method and device | |
| KR102251830B1 (en) | Systems and methods for registration of ultrasound and ct images | |
| US20070014452A1 (en) | Method and system for image processing and assessment of a state of a heart | |
| US20040153128A1 (en) | Method and system for image processing and contour assessment | |
| JP2006305359A (en) | Software product for three-dimensional cardiac imaging using ultrasound contour reconstruction | |
| JP2006305358A (en) | Three-dimensional cardiac imaging using ultrasound contour reconstruction | |
| CN114831729A (en) | Left auricle plugging simulation system for ultrasonic cardiogram and CT multi-mode image fusion | |
| US20220254131A1 (en) | Methods, apparatus, and system for synchronization between a three-dimensional vascular model and an imaging device | |
| CN114931435B (en) | Three-dimensional model processing method and device and electronic equipment | |
| WO2023283273A1 (en) | Augmented imaging for valve repair | |
| CN114283179A (en) | Real-time fracture far-near end space pose acquisition and registration system based on ultrasonic images | |
| JP2018192287A (en) | Method of operating processor device | |
| EP4299012A1 (en) | Three-dimensional shape data generation program, three-dimensional shape data generation method, and information processing apparatus | |
| JP2024049367A (en) | Image processing device and image processing method | |
| Chen | QUiLT (Quantitative Ultrasound in Longitudinal Tissue Tracking): Stitching 2D images into 3D Volumes for Organ Health Monitoring | |
| JP2023008979A (en) | Ultrasound slice enhancement |
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 |