Method and device for acquiring angle of intraoperative transesophageal ultrasound image under guidance of preoperative CT (Computed Tomography) image

Abstract

The invention relates to the technical field related to ultrasonic detection, in particular to a method and a device for acquiring an angle of a transesophageal ultrasonic image in a preoperative CT image guidance operation. The method comprises the following steps: acquiring a heart and esophagus cutting model based on a CT image; the heart and esophagus cutting model comprises a heart model and an esophagus model; determining a long-axis section of the heart based on the heart model; determining an esophagus center line based on the esophagus model; selecting a point closest to the long-axis tangent plane in the central line of the esophagus as an ultrasonic irradiation position; the long-axis section of the heart is corrected based on the ultrasonic irradiation position, so that the long-axis section passes through the ultrasonic irradiation position, and the corrected long-axis section is obtained; and determining the angle of the ultrasonic probe based on the corrected long-axis tangent plane and the tangent plane of the esophageal center line at the ultrasonic irradiation position. By means of the arrangement, a doctor can obtain the intraoperative ultrasonic irradiation angle during preoperative planning, and the operation is more accurate and normative.

Description

Technical Field

[0001] This application relates to the field of ultrasound detection technology, specifically to a method and device for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images. Background Technology

[0002] Transesophageal echocardiography (TEE) is an imaging technique that uses ultrasound waves transmitted through the esophagus to obtain images of the heart's structure and function. Compared to conventional transthoracic echocardiography, TEE provides clearer and more precise cardiac images, especially when comparing posterior cardiac structures. This technique has significant clinical value for diagnosing, evaluating, and guiding the treatment of various structural heart diseases, such as hypertrophic cardiomyopathy (HCM) and mitral / tricuspid regurgitation.

[0003] However, current transesophageal echocardiography primarily relies on intraoperative angle adjustments by the surgeon to locate the target position. Due to varying surgeons' habits, the angle of illumination can differ, and the process of finding the correct angle is highly dependent on the surgeon's experience. Transcatheter treatments for structural heart disease, such as transcatheter edge-to-edge repair (TEER) of the mitral / tricuspid valves, require precise intraoperative transesophageal ultrasound guidance. However, transesophageal ultrasound demands a high level of skill from the operator; providing accurate and clear images from the appropriate position is crucial, and significant variations exist between operators. Furthermore, intraoperative ultrasound images are difficult to compare with preoperative CT images, making it challenging to correlate preoperative surgical planning with intraoperative ultrasound imaging. Summary of the Invention

[0004] In view of this, embodiments of this application aim to provide a method and apparatus for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images.

[0005] This application provides a method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images, including: Obtain heart and esophagus cutting models based on CT images; the heart and esophagus cutting models include heart models and esophagus models; The long axis section of the heart was determined based on the aforementioned heart model; Based on the esophageal model, the esophageal centerline is determined; The point closest to the long axis section along the esophageal centerline is selected as the ultrasound irradiation location; The long axis section of the heart is corrected based on the ultrasound irradiation position, so that the long axis section, passing through the ultrasound irradiation position, is obtained as a corrected long axis section. The angle of the ultrasound probe is determined based on the corrected long axis section and the tangent plane of the esophageal centerline at the ultrasound irradiation location.

[0006] In some embodiments, obtaining the heart and esophagus dissection model based on CT images includes: Acquire CT images; Based on a pre-defined deep learning network, CT images are segmented to obtain segmentation models of the heart and esophagus.

[0007] In some embodiments, selecting the point on the esophageal centerline closest to the long axis section as the ultrasound irradiation location includes: Calculate the distances between each point on the esophageal centerline and the major axis section; The point with the shortest distance is selected as the ultrasound irradiation location.

[0008] In some embodiments, determining the long axis section of the heart based on the heart model includes: Based on the aforementioned heart model, the centerline of the left ventricle model and the aorta was determined; Based on the left ventricular model and the centerline of the aorta, the long axis section is obtained by least-squares distance fitting.

[0009] In some embodiments, the step of correcting the long axis section of the heart based on the ultrasound irradiation location, so that the long axis section passes through the ultrasound irradiation location to obtain a corrected long axis section, includes: Determine the set of planes where ultrasound irradiation occurred; Based on the left ventricular model and the aortic centerline, and combined with the least squares fitting method, the corrected long axis section is determined in the set of planes.

[0010] In some embodiments, determining the ultrasound probe angle based on the corrected long axis section and the tangent plane of the esophageal centerline at the ultrasound irradiation location includes: Determine the tangent plane of the esophageal centerline at the ultrasound irradiation location; The angle between the tangent plane and the corrected long axis tangent plane is the ultrasonic probe angle.

[0011] This application provides a device for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images, comprising: The acquisition module is used to acquire heart and esophagus cutting models based on CT images; the heart and esophagus cutting models include heart models and esophagus models; The determination module is used to determine the long axis section of the heart based on the heart model; and to determine the esophageal centerline based on the esophageal model. The selection module is used to select the point in the esophageal centerline that is closest to the long axis section as the ultrasound irradiation position; The correction module is used to correct the long axis section of the heart based on the ultrasound irradiation position, so that the long axis section, after passing through the ultrasound irradiation position, is obtained as a corrected long axis section. The angle module is used to determine the angle of the ultrasound probe based on the corrected long axis section and the tangent plane of the esophageal centerline at the ultrasound irradiation location.

[0012] This application provides an electronic device, including: A processor, and a memory for storing a processor-executable program; The processor is configured to implement the above-described method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images by running a program in the memory.

[0013] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the preoperative CT image-guided intraoperative transesophageal ultrasound image angle acquisition method described above.

[0014] This application provides a method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images. First, a heart and esophagus cutting model based on CT images is obtained; the heart and esophagus cutting model includes a heart model and an esophageal model. The long axis section of the heart is determined based on the heart model; the esophageal centerline is determined based on the esophageal model; the point on the esophageal centerline closest to the long axis section is selected as the ultrasound irradiation position; the long axis section of the heart is corrected based on the ultrasound irradiation position, so that the long axis section passes through the ultrasound irradiation position to obtain the corrected long axis section; the ultrasound probe angle is determined based on the corrected long axis section and the tangent plane of the esophageal centerline at the ultrasound irradiation position. With this setup, the technical solution provided in this application, by selecting the point closest to the long axis section as the ultrasound irradiation position, can ensure that ultrasound waves irradiate the target location with the shortest path, improving the clarity and accuracy of the ultrasound image. Determining a precise probe angle provides clearer and more accurate information about the heart structure. Furthermore, it allows doctors to obtain the intraoperative ultrasound irradiation angle during preoperative planning, enabling different doctors to obtain essentially consistent results. At the same time, the position and angle of the ultrasound probe for acquiring ideal images during the operation are predicted and suggested, making ultrasound-guided transcatheter surgery more precise and standardized. Attached Figure Description

[0015] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 This is a schematic flowchart of a method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images, provided in one embodiment of this application.

[0017] Figure 2 This is a partial flowchart provided in one embodiment of this application.

[0018] Figure 3 This is a schematic diagram of a heart and esophagus cutting model provided in one embodiment of this application.

[0019] Figure 4 This is a schematic diagram of the structure of a device for obtaining the angle of transesophageal ultrasound image during surgery guided by preoperative CT images, provided in one embodiment of this application.

[0020] Figure 5 This is a schematic diagram of an electronic device structure provided in one embodiment of this application. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Figure 1 This is a schematic flowchart illustrating a method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images, provided in one embodiment of this application. (Refer to...) Figure 1 Figure 2 and Figure 3 The methods provided in this application include the following.

[0023] Step S110: Obtain heart and esophagus cutting models based on CT images; the heart and esophagus cutting models include heart models and esophagus models; The images include: CT images (Computed Tomography images) used to obtain detailed anatomical structures of the patient's heart and esophagus; a heart cutaway model (a three-dimensional model of the heart extracted from CT images using image processing techniques); and an esophageal cutaway model (a three-dimensional model of the esophagus extracted from CT images using image processing techniques).

[0024] Step S120: Determine the long axis section of the heart based on the heart model; Specifically, the long axis section is an important perspective of the heart structure, usually referring to a section through the long axis of the heart, which is a key section used for intraoperative ultrasound imaging.

[0025] Step S130: Determine the esophageal centerline based on the esophageal model; Specifically, the esophageal centerline is the central path of the esophagus, used to determine the irradiation position of the ultrasound probe.

[0026] Step S140: Select the point on the esophageal centerline that is closest to the long axis section as the ultrasound irradiation position; The esophagus is located behind the heart, adjacent to its posterior wall. In transesophageal ultrasound, the ultrasound probe enters through the esophagus and images are taken from behind the heart. Therefore, selecting the point closest to the long axis plane as the ultrasound irradiation position ensures that the ultrasound waves reach the long axis plane of the heart via the shortest path, reducing attenuation and scattering during propagation and improving image clarity and accuracy.

[0027] Step S150: Correct the long axis section of the heart based on the ultrasound irradiation position, so that the long axis section passes through the ultrasound irradiation position to obtain the corrected long axis section. Specifically, by correcting the long axis section to align it with the ultrasound irradiation position, the ultrasound irradiation angle can be optimized, ensuring that the acquired ultrasound images are consistent with the preoperative plan and improving surgical precision. The corrected long axis section provides clearer and more accurate information about the heart's structure, helping surgeons better assess cardiac function and structure, thus improving surgical outcomes. The corrected long axis section also provides a precise reference for ultrasound probe positioning, reducing image deviations caused by operational errors and improving surgical reliability.

[0028] Step S160: Determine the angle of the ultrasound probe based on the corrected long axis section and the tangent plane of the esophageal centerline at the ultrasound irradiation position.

[0029] With this configuration, the technical solution provided in this application, by selecting the point closest to the long axis section as the ultrasound irradiation position, ensures that ultrasound waves irradiate the target location via the shortest path, improving the clarity and accuracy of the ultrasound image. Determining a precise probe angle provides clearer and more accurate information about the heart's structure, helping doctors better assess cardiac function and structure, and improving surgical outcomes.

[0030] In some embodiments, obtaining the heart and esophagus dissection model based on CT images includes: Acquire CT images; segment the CT images based on a pre-set deep learning network to obtain segmentation models of the heart and esophagus.

[0031] Specifically, acquiring CT images is the starting point of the entire technical process. CT images provide detailed anatomical information about areas such as the heart and esophagus, serving as the foundational data source for subsequent analysis and processing. In practical applications, patient CT scan data may be retrieved directly from the hospital's imaging system. This data contains rich information on human tissue density, enabling precise segmentation of the heart and esophagus.

[0032] Leveraging the powerful image recognition and processing capabilities of deep learning, pre-trained deep learning networks (such as the nnUnet neural network) are used to analyze acquired CT images. By learning from a large amount of labeled CT image data, the network can automatically identify the boundaries of the heart and esophagus in the image, thereby segmenting the heart and esophagus from the entire CT image and generating heart and esophagus segmentation models. Compared to traditional manual segmentation or segmentation based on simple algorithms, this segmentation method has higher accuracy and efficiency, enabling rapid and precise extraction of target organ models, providing a reliable data foundation for subsequent key steps such as determining the long axis section of the heart and the centerline of the esophagus.

[0033] The solution provided in this application uses a deep learning network to segment CT images, specifically the nnUnet neural network. The segmentation process mainly includes the following steps: First, the CT image is resampled so that the sampled image is the same size as the trained nnUnet image. Then, the image is input into the neural network for segmentation, directly obtaining segmentation models of the heart and esophagus. After obtaining the segmentation models, models of the left ventricle and aortic blood flow cavity are obtained. Based on these models and a centerline algorithm, the centerline of the blood flow cavity model and the aorta can be extracted. The obtained centerline is three-dimensional, and the plane containing the centerline can be obtained through least-squares distance fitting, which is the major axis section of the heart.

[0034] In some embodiments, selecting the point on the esophageal centerline closest to the long axis section as the ultrasound irradiation location includes: Calculate the distances between each point on the esophageal centerline and the long axis section; select the point with the shortest distance as the ultrasound irradiation position.

[0035] Specifically, after obtaining the long axis section of the heart and the esophageal centerline, a quantitative analysis of their spatial relationship is required. By calculating the distance from each point on the esophageal centerline to the long axis section, the spatial distance information between each location in the esophagus and the ideal key section (long axis section) for cardiac ultrasound irradiation can be accurately determined. This step is achieved using specific mathematical algorithms, such as spatial geometric distance calculation formulas. By traversing all points on the esophageal centerline and calculating their distances to the long axis section one by one, a series of distance data is generated. The point corresponding to the shortest distance is selected from the calculated distance data and determined as the ultrasound irradiation location. The point with the shortest distance is chosen as the ultrasound irradiation location because this point is closest to the long axis section of the heart in the esophagus. Ultrasound irradiation from this point can, while meeting the constraints of the esophageal position, approach the ideal ultrasound irradiation angle and position as closely as possible, helping to obtain clearer and more accurate cardiac ultrasound images and providing more precise guidance for subsequent transcatheter structural heart disease treatment. This selection method is based on the idea of ​​optimization, finding the optimal ultrasound irradiation location through quantitative analysis, improving the accuracy of ultrasound positioning and the success rate of surgery.

[0036] In practical applications, after calculating the major axis section, it is analyzed and processed with the esophageal model to obtain the irradiation angle. The specific process is as follows: For the esophageal model, the centerline of the esophagus can also be extracted using the centerline algorithm. Then, the distance between each point on the centerline and the cross-section is calculated, and the smallest distance is taken as the intraoperative ultrasound irradiation position, denoted as point [point name missing]. Due to the limitations of the esophagus's location, the long axis section of the ultrasound irradiation during surgery may differ from the ideal long axis section, thus requiring correction to determine the angle of ultrasound irradiation.

[0037] In some embodiments, determining the long axis section of the heart based on the heart model includes: Based on the aforementioned heart model, the centerline of the left ventricle model and the aorta was determined; Based on the left ventricular model and the centerline of the aorta, the long axis section is obtained by least-squares distance fitting.

[0038] Specifically, the first step is to determine the centerline of the left ventricle model and the aorta.

[0039] Left ventricular model: The three-dimensional structure of the left ventricle is extracted from the heart model. The left ventricle is the main pumping chamber of the heart, and its structure is crucial for determining the long axis section of the heart.

[0040] The centerline of the aorta: The centerline of the aorta is extracted from the heart model. The aorta is the main outflow vessel of the heart, and its course and location are of great reference value for determining the long axis section of the heart.

[0041] The major axis section is obtained through least squares distance fitting. Least squares distance fitting: The left ventricular model and the centerline of the aorta are fitted using the least squares method to calculate an optimal fitting plane, which is the major axis section of the heart. The least squares method ensures that the fitted plane is as close as possible to all reference points by minimizing the sum of the squared distances from all points to the fitted plane.

[0042] The extraction of the left ventricular model and aortic centerline involves: extracting the boundaries and internal structures of the left ventricle from the 3D data of the heart model to generate a 3D model of the left ventricle. The left ventricular model includes structures such as the inner wall of the left ventricle, myocardium, and heart chambers. The aortic centerline, i.e., the main axis of the aorta, is extracted from the 3D data of the heart model. The aortic centerline can be extracted from the 3D model of the aorta using a centerline extraction algorithm (such as a skeletonization-based method). The point cloud data of the left ventricular model and aortic centerline are input into a least squares algorithm to calculate an optimal fitting plane. This plane ensures that the fitted plane is as close as possible to all reference points by minimizing the sum of squared distances from all points to the plane. The fitted plane is the major axis section of the heart, providing a clear view of the heart's structure and function through the main structures of the left ventricle and aorta.

[0043] In some embodiments, the step of correcting the long axis section of the heart based on the ultrasound irradiation location, so that the long axis section passes through the ultrasound irradiation location to obtain a corrected long axis section, includes: A set of planes representing the locations irradiated by ultrasound is determined; based on the left ventricular model and the aortic centerline, and using a least-squares fitting method, the corrected long axis section is determined within the set of planes.

[0044] Specifically, first, it is necessary to determine a set of planes that all pass through the ultrasound irradiation location. The purpose of this step is to find all possible planes that pass through the previously determined ultrasound irradiation location. Specifically, these planes can be represented mathematically. Assuming the ultrasound irradiation location is a point P, then all planes passing through point P can be represented as: Next, the most suitable plane needs to be selected from these planes as the corrected major axis section. The key to this step is to use a left ventricular model and the aortic centerline, combined with the least squares fitting method.

[0045] The three-dimensional structure of the left ventricle and the centerline of the aorta are extracted from the heart model. This data provides key structural information about the heart. For each plane in the set of planes, the distances from points on the left ventricular model and the aortic centerline to that plane are calculated. These distances are used for least-squares fitting. Using least-squares, a plane is found that minimizes the sum of the squares of the distances from points on the left ventricular model and the aortic centerline to that plane. This plane is our corrected major axis section. Through least-squares fitting, an optimal plane is obtained that not only passes through the ultrasound irradiation position but also most closely approximates the left ventricular model and the aortic centerline. This plane is the corrected major axis section.

[0046] In practical applications, for the ultrasonic irradiation position calculated above... Any plane passing through this point can be represented as By performing least-squares fitting based on the centerlines of the left ventricle and aortic blood flow cavity model, a corrected plane can be obtained. This plane is used as the long axis plane for intraoperative ultrasound imaging of the heart and is denoted as the plane. Based on the ultrasound irradiation point and angle obtained through the above method, the optimal position and angle of the ultrasound probe during surgery can be guided by the following methods.

[0047] In some embodiments, determining the ultrasound probe angle based on the corrected long axis section and the tangent plane of the esophageal centerline at the ultrasound irradiation location includes: Determine the tangent plane of the esophageal centerline at the ultrasound irradiation location; the angle between the tangent plane and the corrected major axis tangent plane is the ultrasound probe angle. That is: based on the ultrasound irradiation location... By relating the point to the esophageal centerline, the tangent plane on the esophageal centerline can be calculated. tangent plane and the corrected long axis section The angle between the normal vectors is the angle that the ultrasound probe needs to be adjusted during the operation.

[0048] Specifically, after correcting the long axis section and determining the ultrasound irradiation location, it is necessary to further determine the tangent plane of the esophageal centerline at that irradiation location. The esophageal centerline is a key line describing the spatial orientation of the esophagus, and determining its tangent plane at the ultrasound irradiation location provides an important reference plane for subsequent calculation of the ultrasound probe angle. By analyzing the local geometric characteristics of the esophageal centerline at this point and using relevant mathematical and geometric algorithms, this tangent plane can be accurately determined. This tangent plane reflects the local directional characteristics of the esophagus at the ultrasound irradiation location and is an indispensable basic element for calculating the ultrasound probe angle. Comparing the tangent plane of the esophageal centerline at the ultrasound irradiation location determined above with the corrected long axis section, the angle between these two planes is the angle that the ultrasound probe needs to be adjusted to during the operation. This angle is used as the ultrasound probe angle because it comprehensively considers the ideal imaging direction of the cardiac long axis section (the corrected long axis section) and the actual spatial orientation of the esophagus at the ultrasound irradiation location (the tangent plane of the esophageal centerline at the ultrasound irradiation location). By adjusting the ultrasound probe to this angle, the ultrasound beam can be directed along the ideal long axis of the heart as much as possible, while also adapting to the limitations of the esophagus, thereby obtaining clearer and more accurate cardiac ultrasound images. This provides more precise intraoperative ultrasound guidance for transcatheter treatment of structural heart disease, improving the success rate of the procedure and the treatment outcome.

[0049] In summary, the solution provided in this application enables physicians to determine the intraoperative ultrasound irradiation angle during preoperative planning, ensuring consistent results across different surgeons. Furthermore, it predicts and suggests the position and angle of the ultrasound probe for acquiring ideal intraoperative images, making ultrasound-guided transcatheter surgery more precise and standardized.

[0050] The apparatus embodiments of this application can be used to execute the method embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the method embodiments of this application.

[0051] Figure 4 The diagram shown is a block diagram of a device for acquiring intraoperative transesophageal ultrasound image angles guided by preoperative CT images, according to an embodiment of this application. Figure 4 As shown, the device includes: The acquisition module 41 is used to acquire heart and esophagus cutting models based on CT images; the heart and esophagus cutting models include heart models and esophagus models; The determination module 42 is used to determine the long axis section of the heart based on the heart model; and to determine the esophageal centerline based on the esophageal model. The selection module 43 is used to select the point in the esophageal centerline that is closest to the long axis section as the ultrasound irradiation position; The correction module 44 is used to correct the long axis section of the heart based on the ultrasound irradiation position, so that the long axis section passes through the ultrasound irradiation position to obtain the corrected long axis section. Angle module 45 is used to determine the angle of the ultrasound probe based on the corrected long axis section and the tangent plane of the esophageal centerline at the ultrasound irradiation position.

[0052] In some embodiments, obtaining the heart and esophagus dissection model based on CT images includes: Acquire CT images; Based on a pre-defined deep learning network, CT images are segmented to obtain segmentation models of the heart and esophagus.

[0053] In some embodiments, selecting the point on the esophageal centerline closest to the long axis section as the ultrasound irradiation location includes: Calculate the distances between each point on the esophageal centerline and the major axis section; The point with the shortest distance is selected as the ultrasound irradiation location.

[0054] In some embodiments, determining the long axis section of the heart based on the heart model includes: Based on the aforementioned heart model, the centerline of the left ventricle model and the aorta was determined; Based on the left ventricular model and the centerline of the aorta, the long axis section is obtained by least-squares distance fitting.

[0055] In some embodiments, the step of correcting the long axis section of the heart based on the ultrasound irradiation location, so that the long axis section passes through the ultrasound irradiation location to obtain a corrected long axis section, includes: Determine the set of planes where ultrasound irradiation occurred; Based on the left ventricular model and the aortic centerline, and combined with the least squares fitting method, the corrected long axis section is determined in the set of planes.

[0056] In some embodiments, determining the ultrasound probe angle based on the corrected long axis section and the tangent plane of the esophageal centerline at the ultrasound irradiation location includes: Determine the tangent plane of the esophageal centerline at the ultrasound irradiation location; The angle between the tangent plane and the corrected long axis tangent plane is the ultrasonic probe angle.

[0057] Below, for reference Figure 5 This describes an electronic device according to embodiments of the present application. Figure 5 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0058] like Figure 5As shown, the electronic device 500 includes one or more processors 510 and memory 520.

[0059] The processor 510 may be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and may control other components in the electronic device 500 to perform desired functions.

[0060] The memory 520 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 510 may execute the program instructions to implement the preoperative CT image-guided intraoperative transesophageal ultrasound image angle acquisition method of the various embodiments of this application described above, and / or other desired functions. Various contents, such as category correspondences, may also be stored in the computer-readable storage medium.

[0061] In one example, the electronic device 500 may also include an input device 530 and an output device 540, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0062] In addition, the input device 530 may also include, for example, a keyboard, mouse, interface, etc. The output device 540 can output various information to the outside, including analysis results, etc. The output device 540 may include, for example, a display, speaker, printer, and communication network and its connected remote output devices, etc.

[0063] Of course, for the sake of simplicity, Figure 5 Only some of the components of the electronic device relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device may include any other suitable components depending on the specific application.

[0064] In addition to the methods and devices described above, embodiments of this application may also be computer program products, comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the preoperative CT image-guided intraoperative transesophageal ultrasound image angle acquisition method according to various embodiments of this application as described in the "Methods" section of this specification.

[0065] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0066] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the steps in the method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images according to various embodiments of this application as described in the "Method" section of this specification.

[0067] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0068] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images, characterized in that, include: Obtain heart and esophagus cutting models based on CT images; The heart and esophagus cutting model includes a heart model and an esophagus model; The long axis section of the heart was determined based on the aforementioned heart model; Based on the esophageal model, the esophageal centerline is determined; The point closest to the long axis section along the esophageal centerline is selected as the ultrasound irradiation location; The long axis section of the heart is corrected based on the ultrasound irradiation position, so that the long axis section, passing through the ultrasound irradiation position, is obtained as a corrected long axis section. The angle of the ultrasound probe is determined based on the corrected long axis section and the tangent plane of the esophageal centerline at the ultrasound irradiation location.

2. The method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images according to claim 1, characterized in that, The acquisition of the heart and esophagus dissection model based on CT images includes: Acquire CT images; Based on a pre-defined deep learning network, CT images are segmented to obtain segmentation models of the heart and esophagus.

3. The method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images according to claim 1, characterized in that, Selecting the point closest to the long axis section along the esophageal centerline as the ultrasound irradiation location includes: Calculate the distances between each point on the esophageal centerline and the major axis section; The point with the shortest distance is selected as the ultrasound irradiation location.

4. The method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images according to claim 1, characterized in that, Determining the long axis section of the heart based on the aforementioned heart model includes: Based on the aforementioned heart model, the centerline of the left ventricle model and the aorta was determined; Based on the left ventricular model and the centerline of the aorta, the long axis section is obtained by least-squares distance fitting.

5. The method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images according to claim 4, characterized in that, The step of correcting the long axis section of the heart based on the ultrasound irradiation position, so that the long axis section passes through the ultrasound irradiation position to obtain a corrected long axis section, includes: Determine the set of planes where ultrasound irradiation occurred; Based on the left ventricular model and the aortic centerline, and combined with the least squares fitting method, the corrected long axis section is determined in the set of planes.

6. The method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images according to claim 4, characterized in that, The determination of the ultrasound probe angle based on the corrected long axis section and the tangent plane of the esophageal centerline at the ultrasound irradiation location includes: Determine the tangent plane of the esophageal centerline at the ultrasound irradiation location; The angle between the tangent plane and the corrected long axis tangent plane is the ultrasonic probe angle.

7. A device for acquiring intraoperative transesophageal ultrasound image angles guided by preoperative CT images, characterized in that, include: The acquisition module is used to acquire heart and esophagus cutting models based on CT images; The heart and esophagus cutting model includes a heart model and an esophagus model; The determination module is used to determine the long axis section of the heart based on the heart model; and to determine the esophageal centerline based on the esophageal model. The selection module is used to select the point in the esophageal centerline that is closest to the long axis section as the ultrasound irradiation position; The correction module is used to correct the long axis section of the heart based on the ultrasound irradiation position, so that the long axis section, after passing through the ultrasound irradiation position, is obtained as a corrected long axis section. The angle module is used to determine the angle of the ultrasound probe based on the corrected long axis section and the tangent plane of the esophageal centerline at the ultrasound irradiation location.

8. An electronic device, characterized in that, include: A processor, and a memory for storing a processor-executable program; The processor is configured to implement the method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images as described in any one of claims 1 to 6 by running a program in the memory.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to perform the method for obtaining intraoperative transesophageal ultrasound image angles guided by preoperative CT images as described in any one of claims 1 to 6.

Images