Intelligent Image Measurement and Navigation Method and System for Transcatheter Aortic Valve Replacement

Abstract

This invention provides an intelligent image measurement and navigation method and system for transcatheter aortic valve replacement (TAVR), relating to the field of medical auxiliary diagnosis. Utilizing a dual-temporal collaborative repair strategy, it can use the texture information of clear temporal phases to complete the anatomical details of blurred temporal phases, obtaining complete anatomical boundaries even under imperfect cross-sections. This significantly reduces the time and frequency of physical probe adjustments during surgery, lowering the reliance on the operational skills of anesthesiologists or sonographers. Through cascaded positioning with anatomical region locking, and using a probability field strength prior forced algorithm to focus on high-probability anatomical structures, it shields background noise that is easily interfered with by the human eye, ensuring the objectivity and consistency of measurement results. This allows less experienced surgeons to achieve measurement accuracy consistent with senior experts, providing standardized data support for valve model selection. It can intelligently filter out motion interference, ensuring the safety of intraoperative navigation, and its sub-pixel accuracy meets the requirements of refined TAVR surgery.

Description

Technical Field

[0001] This invention relates to the field of medical auxiliary diagnostic technology, and in particular to a method and system for intelligent image measurement and navigation during transcatheter aortic valve replacement surgery. Background Technology

[0002] In transcatheter aortic valve replacement (TAVR), accurate preoperative and intraoperative anatomical measurements are the cornerstone of surgical success. Clinicians typically rely on transesophageal echocardiography (TEE) to obtain key parameters of the aortic root (such as annular diameter, outflow tract diameter, and coronary ostium height) in real time during the procedure to guide the selection and placement of the prosthetic valve. The heart is a dynamic organ that undergoes complex deformations in three-dimensional space with the cardiac cycle (systole / diastole) and respiratory movements.

[0003] Currently, the mainstream clinical measurement methods mainly rely on manual operation by doctors or basic semi-automatic software, which has the following insurmountable clinical pain points: 1. Single-phase analysis cannot overcome acoustic artifacts ("One-View Limitation"). Intraoperative TEE images are often limited by acoustic shadowing caused by calcified plaques or artifacts caused by leaflet movement. At the end of diastole (the standard measurement phase), key anatomical boundaries (such as the valve annulus landing area) may be obscured or blurred. Most existing technologies analyze single-frame images in isolation. If the quality of the standard frame is poor, the system cannot, like an experienced surgeon, review the clear anatomical contours during systole to infer the diastolic boundary location, leading to measurement failure or serious bias.

[0004] 2. Lack of anatomical consistency verification mechanism. When interpreting images, doctors subconsciously check whether the morphology of the same structure is reasonable at different heartbeats (i.e., topological consistency). Existing software lacks this biomimetic verification logic, often treating heart structures as independent geometric figures. When the probe shifts slightly or the patient's breathing causes changes in the cross-section, the software cannot recognize these non-anatomical changes, and the output parameters lack clinical confidence.

[0005] 3. Over-reliance on the doctor's personal experience. Accurate measurements require the doctor to manually capture the optimal moment in dynamic video, which demands extremely high hand-eye coordination and extensive anatomical knowledge. Significant inter-observer variability in measurement results among doctors of different experience levels poses a challenge to the standardization and widespread adoption of TAVR surgery.

[0006] Therefore, it is necessary to provide a new approach to solve the aforementioned technical problems. Summary of the Invention

[0007] To achieve the above-mentioned objectives and other advantages of the present invention, a first objective of the present invention is to provide a method for intelligent image measurement and navigation during transcatheter aortic valve replacement surgery, comprising the following steps: The system analyzes intraoperative ultrasound video streams in real time, automatically locks the end-diastolic and end-systolic images within the same cardiac cycle based on electrocardiogram signals or image motion analysis, and performs dual feature extraction on the end-diastolic and end-systolic images through macroscopic and microscopic sensing channels, respectively. By utilizing the physiological consistency in anatomical topology between the obtained end-diastolic and end-systolic images, for blurred or missing anatomical structures in one phase image, clear corresponding structural information is retrieved and mapped from the other phase image for complementary repair through global topological alignment and local texture compensation techniques. At the same time, adaptive artifact filtering is used to suppress signal interference from non-physiological continuity. Based on the restored image data with temporal enhancement characteristics, an anatomical probability field of the target anatomical region is generated, high-probability existence areas are delineated as anatomical priors, and fine anatomical structures are located and segmented based on these anatomical priors. Based on the high signal-to-noise ratio anatomical structures identified through localization and segmentation, a dynamic anatomical geometric model is constructed, and standardized parameter measurements for transcatheter aortic valve replacement are performed within the established local anatomical coordinate system.

[0008] Furthermore, the macroscopic sensing channel is used to extract the overall morphology and motion trend features of the heart, while the microscopic sensing channel is used to extract the texture details of the valves and blood vessel walls.

[0009] Furthermore, the global topology alignment utilizes the macroscopic morphological features of the source temporal image to calibrate the overall anatomical structure of the target temporal image; the local texture compensation retrieves high-resolution textures from the source temporal image within a local window range to fill in signal loss at corresponding positions in the target temporal image.

[0010] Furthermore, the adaptive artifact filtering is implemented through a gating screening mechanism, which determines whether the bright signal in the image shows anatomical continuity in both the end-diastolic and end-systolic images. If it only appears in a single phase and lacks a continuous physiological motion trajectory, it is determined to be an artifact and filtered out.

[0011] Furthermore, the target anatomical region is the aortic root region, and the anatomical probability field is used to mark the distal left ventricular outflow tract and mitral valve region as low-probability regions, thereby eliminating interference in subsequent localization.

[0012] Furthermore, the steps of constructing a dynamic anatomical geometric model and performing standardized parameter measurements for transcatheter aortic valve replacement within the established local anatomical coordinate system include: A virtual base plane is fitted based on the segmented aortic valve annulus feature points. When fitting the spatial center line of the aortic root, an acoustic confidence weighting mechanism is introduced to identify the acoustic shadow area and motion blur area, reduce the calculation weight of the edge points in the acoustic shadow area and motion blur area, generate an acoustically robust center line, and establish a local anatomical coordinate system based on the center line and the virtual base plane. The curvature change rate is calculated along the contour line of the aortic root, and the geometric inflection point where the contour changes from convex to concave is locked as the anatomical anchor point of the sinus junction. The contour displacement difference of multiple phases within the cardiac cycle is used to dynamically verify the position of the anchor point. The vertical projection distance between the plane where the sinus duct junction is located and the virtual base plane of the valve annulus is calculated as the height of the Warburg sinus. For each Warburg sinus visible in the current ultrasound field of view, the lowest point of the sinus floor is identified and the sinus height of the region is calculated. The system identifies the location of the coronary artery ostium, calculates its vertical distance to the annulus plane, and simulates the post-implantation state in the geometric model based on the selected artificial valve model. If the coronary artery height is lower than a preset safety threshold or the virtual leaflet covers the coronary artery ostium, a risk alarm is triggered.

[0013] Furthermore, the dynamic consistency verification includes: calculating the displacement trajectory of the candidate anchor point during the cardiac cycle; if the displacement trajectory exhibits non-physiological, non-rigid tortuous characteristics, the confidence of the candidate anchor point is downweighted or it is removed.

[0014] Furthermore, after determining the anchor points on both sides of the sinus junction, the measuring line connecting the two anchor points is forced to be geometrically orthogonal to the acoustic robust center line in order to measure the true cross-sectional diameter.

[0015] Furthermore, it also includes a cross-temporal confidence fusion step for the measurement results: The effective measurements obtained in multiple cardiac cycles at different time phases are weighted and averaged. The measurement values ​​corresponding to image frames with higher clarity and more standard cross-sections are assigned higher weights. Finally, the fused measurement result report is output.

[0016] Furthermore, the effective measurement values ​​are derived from the measurement values ​​of the end-diastolic image frames and the measurement values ​​obtained by cross-validating the end-systolic image frames by mapping them to the end-diastolic phase.

[0017] The second objective of this invention is to provide an intelligent image measurement and navigation system for transcatheter aortic valve replacement surgery, employing the aforementioned method, including a dual-channel sensing flow construction module, a multi-level collaborative repair module, a cascaded positioning module, and a parametric geometric modeling and measurement module; wherein, The dual-channel sensing stream construction module is used to analyze intraoperative ultrasound video streams in real time. Based on electrocardiogram signals or image motion analysis, it automatically locks the end-diastolic and end-systolic images within the same cardiac cycle, and performs dual feature extraction on the end-diastolic and end-systolic images through macroscopic and microscopic sensing channels, respectively. The multi-level collaborative repair module is used to utilize the physiological consistency of the obtained end-diastolic and end-systolic images in terms of anatomical topology. For blurred or missing anatomical structures in one phase image, it retrieves and maps clear corresponding structural information from the other phase image through global topological alignment and local texture compensation techniques for complementary repair. At the same time, it suppresses signal interference from non-physiological continuity through adaptive artifact filtering. The cascaded localization module is used to generate an anatomical probability field of the target anatomical region based on the repaired image data with temporal enhancement characteristics, delineate the high-probability existence area as the anatomical prior, and perform fine anatomical structure localization and segmentation based on the anatomical prior. The parametric geometry modeling and measurement module is used to construct a dynamic anatomical geometry model based on the localized and segmented high signal-to-noise ratio anatomical structures, and to perform standardized parameter measurements for transcatheter aortic valve replacement under the established local anatomical coordinate system.

[0018] A third objective of the present invention is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0019] A fourth objective of the present invention is to provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described method.

[0020] Compared with the prior art, the beneficial effects of the present invention are: This invention provides a method and system for intelligent image measurement and navigation during transcatheter aortic valve replacement (TAVR) surgery. Compared with existing manual or semi-automatic measurement methods, it has the following significant advantages in TAVR applications: This invention overcomes the bottleneck of intraoperative ultrasound imaging quality and reduces the difficulty of probe operation. In TAVR surgery, transesophageal ultrasound (TEE) often experiences signal dropout due to calcification obstruction or beam angle limitations. Existing technologies typically rely on surgeons repeatedly adjusting the probe angle to find a clear section, which is time-consuming and disruptive to the surgical process. This invention utilizes a dual-phase collaborative repair strategy, automatically using the texture information of the clear phase to complete the anatomical details of the blurred phase. Even with imperfect sections, complete anatomical boundaries can be obtained, significantly reducing the time and frequency of physical probe adjustments during surgery and decreasing reliance on the operational skills of anesthesiologists or sonographers.

[0021] This invention eliminates inter-observer variability, achieving standardization and objectivity in measurements. Traditional manual measurements heavily rely on the physician's personal experience, leading to significant inter-observer variability in the judgment of ambiguous boundaries among different physicians (and even the same physician at different times). This invention, through cascaded localization with anatomical region locking, utilizes a probabilistic field strength prior algorithm to focus on high-probability anatomical structures, shielding against background noise that is easily interfered with by the human eye. This ensures the objectivity and consistency of measurement results, enabling less experienced young physicians to achieve measurement accuracy comparable to senior experts, and providing standardized data support for valve model selection.

[0022] This invention intelligently filters out motion interference, ensuring the safety of intraoperative navigation. The violent beating of the heart often leads to misjudgments by automated algorithms. The gating mechanism and adaptive reliability assessment introduced in this invention achieve intelligent control of the system. It can identify and suppress abnormal features caused by motion artifacts in real time, using only high-confidence anatomical features for calculations, greatly improving the system's robustness in complex dynamic environments and effectively preventing serious measurement deviations caused by artifacts (such as mismeasurement of valve annulus diameter), thereby reducing the risk of postoperative paravalvular leak (PVL) or valve annulus rupture.

[0023] The subpixel-level precision provided by this invention meets the requirements of refined TAVR surgery. TAVR surgery has a low tolerance for measurement errors in the aortic valve annulus diameter (typically less than 1 mm). This invention, through probability density center estimation technology, overcomes the limitations of the physical resolution of traditional ultrasound images, achieving subpixel-level parameter output and providing measurement accuracy that surpasses the limits of human visual interpretation. This helps clinical teams more accurately match artificial valve sizes and optimize surgical planning.

[0024] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Specific embodiments of the present invention are given in detail below with reference to the accompanying drawings. Attached Figure Description

[0025] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings: Figure 1 Flowchart of intelligent image measurement and navigation method during transcatheter aortic valve replacement surgery; Figure 2 A flowchart for parametric geometric modeling and precise measurement based on temporal feature fusion; Figure 3 This is a block diagram of an intelligent image measurement and navigation system for transcatheter aortic valve replacement surgery. Figure 4 This is a schematic diagram of a computer device. Figure 5 This is a schematic diagram of a computer-readable storage medium. Detailed Implementation

[0026] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be noted that, without conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0027] Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this invention.

[0028] The drawing numbers in this application are only used to distinguish the steps in the scheme and are not used to limit the execution order of the steps. The specific execution order is as described in the specification.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0030] This invention provides a method and system for intelligent intraoperative image measurement and navigation in transcatheter valve replacement surgery. This method is not limited to static image analysis at a single moment, but rather simulates the thought process of clinical experts using dynamic information from the cardiac cycle for complementary diagnosis. The specific scheme is as follows: Example 1 A method for intelligent image measurement and navigation during transcatheter aortic valve replacement surgery, such as Figure 1 As shown, it includes the following steps: The S100 system performs real-time analysis of the intraoperative ultrasound video stream, automatically locking onto the end-diastolic (ED) and end-systolic (ES) images within the same cardiac cycle based on electrocardiogram (ECG) signals or image motion analysis. These two images are physically separated in time but possess a high degree of physiological consistency in anatomical topology. This mimics the surgeon's observational habit of comparing systolic and diastolic changes. Dual feature extraction is performed on the ED and ES images through both macroscopic and microscopic sensing channels.

[0031] This invention simulates the visual habits of clinicians who look at both the big picture and the small details, and establishes a dual-channel processing logic: the macroscopic perception channel is used to extract the overall shape and motion trend features of the heart, and the microscopic perception channel is used to extract the texture details of the valves and blood vessel walls.

[0032] Optionally, the macroscopic sensing channel employs a motion estimation algorithm based on the overall contour of the heart, while the microscopic sensing channel employs a convolutional neural network for feature extraction targeting valve edges and vascular wall texture.

[0033] This invention utilizes the complementary characteristics of ED / ES dual-temporal images to execute a hierarchical image quality restoration strategy. The system leverages the topological invariance of cardiac anatomy within a short timeframe. If the boundary of a vessel wall is blurred in the end-diastolic (ED) phase, the system automatically retrieves the corresponding clear outline in the end-systolic (ES) phase. Through global and local alignment compensation techniques, the clear morphology of the ES phase is mapped back to the ED phase, completing the complementary restoration of the anatomical structure. S200. Utilizing the physiological consistency of the obtained end-diastolic and end-systolic images in terms of anatomical topology, for blurred or missing anatomical structures in one phase image, through global topological alignment and local texture compensation techniques, clear corresponding structural information is retrieved and mapped from the image of another phase for complementary repair. At the same time, adaptive artifact filtering is used to suppress signal interference from non-physiological continuity. The global topological alignment utilizes the macroscopic morphological features of the source temporal image to calibrate the overall anatomical structure of the target temporal image, such as correcting ventricular deformation caused by misaligned sections. The local texture compensation retrieves high-resolution textures from the source temporal image within a local window and fills in signal loss at corresponding positions in the target temporal image.

[0034] The adaptive artifact filtering incorporates a gating mechanism to intelligently identify and suppress motion artifacts that may be introduced during the interaction process, ensuring that only valid anatomical features are retained. The gating mechanism determines whether the highlighted signal in the image exhibits anatomical continuity in both end-diastolic and end-systolic images. If it appears only in a single phase and lacks a continuous physiological motion trajectory (such as acoustic shadowing or electrosurgical interference), it is identified as an artifact and filtered out, retaining only the true anatomical structural information.

[0035] To prevent mis-positioning within complex cardiac chambers (such as mistaking the mitral valve for the aortic valve), this invention employs a cascaded strategy of segmentation followed by localization: S300: Based on the repaired image data with temporal enhancement characteristics, generate an anatomical probability field of the target anatomical region, delineate high-probability existence areas as anatomical priors, and perform fine anatomical structure localization and segmentation based on these anatomical priors. This invention, based on the anatomical probability field with temporal enhancement characteristics output in step S200, delineates a high-probability region in the aortic root, i.e., the target anatomical region is the aortic root region. The anatomical probability field marks the distal left ventricular outflow tract and mitral valve region as low-probability regions, thereby eliminating interference from these regions during subsequent localization. Furthermore, these high-probability regions are used as anatomical priors, forcing subsequent fine measurements to be performed only within the effective anatomical range. This is equivalent to providing the system with a priori presets, allowing it to focus solely on the target area, much like a specialist physician.

[0036] This invention does not perform pixel-level measurements directly on the raw, coarse ultrasound images. Instead, it constructs a dynamic anatomical geometry model based on the high signal-to-noise ratio, anatomically complete temporal fusion feature map output from the S300 step, and performs the following standardized measurements conforming to TAVR clinical guidelines: S400: Based on the high signal-to-noise ratio anatomical structures identified through localization and segmentation, a dynamic anatomical geometric model is constructed, and standardized parameter measurements for transcatheter aortic valve replacement are performed in the established local anatomical coordinate system.

[0037] To achieve acoustically robust centerline construction with acoustic artifact suppression, dynamic curvature extremum analysis of the STJ (sinus junction) and projection calculation of the SOV (Warshall sinus) height were performed, such as... Figure 2 As shown, the steps of constructing a dynamic anatomical geometric model and performing standardized parameter measurements for transcatheter aortic valve replacement under the established local anatomical coordinate system include: This invention simulates the operational thought process of an ultrasound physician adjusting the probe to find a standard long-axis section and define the midline of the lumen before measurement. S410, A virtual base plane is fitted based on the segmented aortic valve annulus feature points, for example, by fitting a virtual base plane using the least squares method; Unlike traditional CT images that rely solely on geometric shape to fit the centerline, this invention introduces an acoustic confidence weighting mechanism when fitting the spatial centerline of the aortic root. This mechanism automatically identifies the acoustic shadow area and motion blur area, reduces the calculation weight of edge points within the acoustic shadow area and motion blur area, and constructs an acoustically robust centerline. All subsequent parameters (such as SOV height and STJ diameter) are calculated based on the local anatomical coordinate system established by the centerline and the virtual base plane, rather than based on the screen pixel coordinates of the original image, thereby effectively avoiding measurement geometric errors caused by the tilt of the TEE probe section.

[0038] The STJ is a smooth transition zone between the ascending aorta and the Valsalva sinus. The exact boundary is difficult to determine visually and is easily affected by cardiac pulsation, causing measurement position to shift. In this invention, S420, the rate of curvature change is calculated along the aortic root contour line, automatically locking the geometric inflection point where the contour transitions from convex to concave, and marking it as the STJ anatomical anchor point.

[0039] When locking anchor points, this invention not only utilizes the texture features of the current frame but also introduces temporal constraints, using the difference in contour displacement between the systolic and diastolic phases as a verification parameter. If the displacement trajectory of a candidate point during the cardiac cycle exhibits non-physiological, non-rigid distortion, the point will be automatically downweighted or eliminated.

[0040] Connect the confirmed STJ anchor points on both sides and force the measurement line to remain geometrically orthogonal to the aforementioned acoustic robust centerline to ensure that the measured value is the true cross-sectional diameter.

[0041] Traditional manual measurements often mistakenly use the Euclidean straight-line distance from the valve annulus to the STJ, ignoring the interference of the curvature of the Warburg sinus wall and the influence of the sectional angle. This invention, in S430, calculates the vertical projection distance between the plane where the sinoduct junction is located and the virtual base plane of the valve annulus, rather than the distance between the two points, as the Warburg sinus height.

[0042] For the Valsalva sinus structures (such as left / right coronary sinuses or non-coronary sinuses) visible in the current ultrasound field of view, the lowest anatomical point at the base of each sinus is identified, and the height parameters of each region are output, providing a refined reference for valve selection for asymmetric anatomical structures.

[0043] S440. Identify the location of the coronary artery ostium. Specifically, the system automatically identifies the hyperechoic features of the coronary artery ostium, calculates its vertical distance to the annulus plane, and simulates the leaflet opening posture after valve implantation in the geometric model based on the selected virtual artificial valve model. If the measured coronary artery height is less than the preset safety threshold (e.g., 10mm), or the virtual leaflet covers the coronary artery ostium, an alarm for coronary artery obstruction risk is automatically triggered.

[0044] In some embodiments, the final output clinical parameter report is a statistically optimal solution based on multi-frame information within the cardiac cycle. Specifically, it also includes a cross-temporal confidence fusion step for the measurement results: The effective measurements obtained in multiple cardiac cycles at different time phases are weighted and averaged. The measurement values ​​corresponding to image frames with higher clarity and more standard cross-sections are assigned higher weights. Finally, the fused measurement result report is output.

[0045] The valid measurements are derived from measurements of end-diastolic image frames and measurements obtained by cross-validating end-systolic image frames mapped to the end-diastolic phase. Frames with high clarity and standard cross-sections are assigned high weights, while those with lower clarity and standard cross-sections are assigned lower weights, thereby outputting highly robust measurement results.

[0046] This invention provides an intelligent measurement method and system that mimics the dynamic image reading habits and clinical diagnostic process of clinicians. By automatically coordinating the image information of end-diastole and end-systole, it achieves standardized and automated measurement of aortic root parameters in complex intraoperative environments, reducing reliance on physician experience.

[0047] Example 2 A transcatheter aortic valve replacement (TAVR) imaging intelligent measurement and navigation system applies the above-described method. For a detailed description of the method, please refer to the corresponding description in the above method embodiments; it will not be repeated here. Figure 3 As shown, the system 500 includes a dual-channel sensing flow construction module 510, a multi-level collaborative repair module 520, a cascaded positioning module 530, and a parametric geometric modeling and measurement module 540; among which, The dual-channel sensing stream construction module is used to analyze intraoperative ultrasound video streams in real time. Based on electrocardiogram signals or image motion analysis, it automatically locks the end-diastolic and end-systolic images within the same cardiac cycle, and performs dual feature extraction on the end-diastolic and end-systolic images through macroscopic and microscopic sensing channels, respectively. The multi-level collaborative repair module is used to utilize the physiological consistency of the obtained end-diastolic and end-systolic images in terms of anatomical topology. For blurred or missing anatomical structures in one phase image, it retrieves and maps clear corresponding structural information from the other phase image through global topological alignment and local texture compensation techniques for complementary repair. At the same time, it suppresses signal interference from non-physiological continuity through adaptive artifact filtering. The cascaded localization module is used to generate an anatomical probability field of the target anatomical region based on the repaired image data with temporal enhancement characteristics, delineate the high-probability existence area as the anatomical prior, and perform fine anatomical structure localization and segmentation based on the anatomical prior. The parametric geometry modeling and measurement module is used to construct a dynamic anatomical geometry model based on the localized and segmented high signal-to-noise ratio anatomical structures, and to perform standardized parameter measurements for transcatheter aortic valve replacement under the established local anatomical coordinate system.

[0048] Example 3 A computer device 600, such as Figure 4 As shown, the system includes a memory 610, a processor 620, and a computer program 630 stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of an intelligent image measurement and navigation method for transcatheter aortic valve replacement surgery. For a detailed description of the method, please refer to the corresponding description in the above method embodiments; it will not be repeated here.

[0049] Example 4 A computer-readable storage medium, such as Figure 5 As shown, a computer program is stored thereon. When executed by a processor, the computer program implements the steps of an intelligent image measurement and navigation method for transcatheter aortic valve replacement surgery. For a detailed description of the method, please refer to the corresponding description in the above method embodiments, which will not be repeated here.

[0050] The number of devices and processing scale described herein are for the purpose of simplifying the description of the invention. Applications, modifications, and variations of the invention will be readily apparent to those skilled in the art.

[0051] Although embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. They can be applied to various fields suitable for the present invention. For those skilled in the art, other modifications can be easily made. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and illustrations shown and described herein.

[0052] The apparatus, computer device, and non-volatile computer storage medium and method provided in the embodiments of this specification are corresponding. Therefore, the apparatus, computer device, and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, computer device, and non-volatile computer storage medium will not be repeated here.

[0053] Those skilled in the art will also know that, besides implementing the controller in the form of purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller take the form of logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices included within it for implementing various functions can also be considered structures within that hardware component. Alternatively, the devices for implementing various functions can be considered as both software units implementing the method and structures within a hardware component.

[0054] The systems, apparatuses, or units described in the above embodiments can be implemented by computer chips or physical entities, or by products with certain functions. For ease of description, the above apparatuses are described separately as various units based on their functions. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0055] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0056] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0057] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0058] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0059] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0060] This specification may be described in the general context of computer-executable instructions, such as program units, that are executed by a computer. Generally, program units include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification may also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program units may reside in local and remote computer storage media, including storage devices.

[0061] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0062] The above description is merely an embodiment of this specification and is not intended to limit the scope of one or more embodiments of this specification. Various modifications and variations can be made to one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of one or more embodiments of this specification.

Claims

1. A method for intelligent image measurement and navigation during transcatheter aortic valve replacement surgery, characterized in that, Includes the following steps: The system analyzes intraoperative ultrasound video streams in real time, automatically locks the end-diastolic and end-systolic images within the same cardiac cycle based on electrocardiogram signals or image motion analysis, and performs dual feature extraction on the end-diastolic and end-systolic images through macroscopic and microscopic sensing channels, respectively. By utilizing the physiological consistency in anatomical topology between the obtained end-diastolic and end-systolic images, for blurred or missing anatomical structures in one phase image, clear corresponding structural information is retrieved and mapped from the other phase image for complementary repair through global topological alignment and local texture compensation techniques. At the same time, adaptive artifact filtering is used to suppress signal interference from non-physiological continuity. Based on the restored image data with temporal enhancement characteristics, an anatomical probability field of the target anatomical region is generated, high-probability existence areas are delineated as anatomical priors, and fine anatomical structures are located and segmented based on these anatomical priors. Based on the high signal-to-noise ratio anatomical structures identified through localization and segmentation, a dynamic anatomical geometric model is constructed, and standardized parameter measurements for transcatheter aortic valve replacement are performed within the established local anatomical coordinate system.

2. The intelligent image measurement and navigation method for transcatheter aortic valve replacement surgery as described in claim 1, characterized in that, The macroscopic sensing channel is used to extract the overall morphology and motion trend features of the heart, while the microscopic sensing channel is used to extract the texture details of the valves and blood vessel walls.

3. The intelligent image measurement and navigation method for transcatheter aortic valve replacement surgery as described in claim 1, characterized in that, The global topology alignment utilizes the macroscopic morphological features of the source temporal image to calibrate the overall anatomical structure of the target temporal image; the local texture compensation retrieves high-definition textures from the source temporal image within a local window range to fill in signal loss at corresponding positions in the target temporal image.

4. The intelligent image measurement and navigation method for transcatheter aortic valve replacement surgery as described in claim 1 or 3, characterized in that, The adaptive artifact filtering is achieved through a gating screening mechanism, which determines whether the bright signal in the image shows anatomical continuity in both the end-diastolic and end-systolic images. If it only appears in a single phase and lacks a continuous physiological motion trajectory, it is determined to be an artifact and filtered out.

5. The intelligent image measurement and navigation method for transcatheter aortic valve replacement surgery as described in claim 1, characterized in that, The target anatomical region is the aortic root region, and the anatomical probability field is used to mark the distal left ventricular outflow tract and mitral valve region as low-probability regions, thereby eliminating interference in subsequent localization.

6. The intelligent image measurement and navigation method for transcatheter aortic valve replacement surgery as described in claim 1, characterized in that, The steps of constructing a dynamic anatomical geometric model and performing standardized parameter measurements for transcatheter aortic valve replacement within the established local anatomical coordinate system include: A virtual base plane is fitted based on the segmented aortic valve annulus feature points. When fitting the spatial center line of the aortic root, an acoustic confidence weighting mechanism is introduced to identify the acoustic shadow area and motion blur area, reduce the calculation weight of the edge points in the acoustic shadow area and motion blur area, generate an acoustically robust center line, and establish a local anatomical coordinate system based on the center line and the virtual base plane. The curvature change rate is calculated along the contour line of the aortic root, and the geometric inflection point where the contour changes from convex to concave is locked as the anatomical anchor point of the sinus junction. The contour displacement difference of multiple phases within the cardiac cycle is used to dynamically verify the position of the anchor point. The vertical projection distance between the plane where the sinus duct junction is located and the virtual base plane of the valve annulus is calculated as the height of the Warburg sinus. For each Warburg sinus visible in the current ultrasound field of view, the lowest point of the sinus floor is identified and the sinus height of the region is calculated. The system identifies the location of the coronary artery ostium, calculates its vertical distance to the annulus plane, and simulates the post-implantation state in the geometric model based on the selected artificial valve model. If the coronary artery height is lower than a preset safety threshold or the virtual leaflet covers the coronary artery ostium, a risk alarm is triggered.

7. The intelligent image measurement and navigation method for transcatheter aortic valve replacement surgery as described in claim 6, characterized in that, The dynamic consistency verification includes: calculating the displacement trajectory of the candidate anchor point during the cardiac cycle; if the displacement trajectory exhibits non-physiological, non-rigid tortuous characteristics, the confidence of the candidate anchor point is downweighted or it is removed.

8. The intelligent image measurement and navigation method for transcatheter aortic valve replacement surgery as described in claim 6, characterized in that, After determining the anchor points on both sides of the sinus junction, the measuring line connecting the two anchor points is forced to be geometrically orthogonal to the acoustic robust center line in order to measure the true cross-sectional diameter.

9. The intelligent image measurement and navigation method for transcatheter aortic valve replacement surgery as described in claim 1, characterized in that, It also includes a cross-temporal confidence fusion step for measurement results: The effective measurements obtained in multiple cardiac cycles at different time phases are weighted and averaged. The measurement values ​​corresponding to image frames with higher clarity and more standard cross-sections are assigned higher weights. Finally, the fused measurement result report is output.

10. The intelligent image measurement and navigation method for transcatheter aortic valve replacement surgery as described in claim 9, characterized in that, The valid measurements are derived from measurements of the end-diastolic image frames and measurements obtained by cross-validating the end-systolic image frames to the end-diastolic phase.

11. An intelligent image measurement and navigation system for transcatheter aortic valve replacement surgery, using the method as described in any one of claims 1 to 10, characterized in that, It includes a dual-channel sensing flow construction module, a multi-level collaborative repair module, a cascaded positioning module, and a parametric geometric modeling and measurement module; among which, The dual-channel sensing stream construction module is used to analyze intraoperative ultrasound video streams in real time. Based on electrocardiogram signals or image motion analysis, it automatically locks the end-diastolic and end-systolic images within the same cardiac cycle, and performs dual feature extraction on the end-diastolic and end-systolic images through macroscopic and microscopic sensing channels, respectively. The multi-level collaborative repair module is used to utilize the physiological consistency of the obtained end-diastolic and end-systolic images in terms of anatomical topology. For blurred or missing anatomical structures in one phase image, it retrieves and maps clear corresponding structural information from the other phase image through global topological alignment and local texture compensation techniques for complementary repair. At the same time, it suppresses signal interference from non-physiological continuity through adaptive artifact filtering. The cascaded localization module is used to generate an anatomical probability field of the target anatomical region based on the repaired image data with temporal enhancement characteristics, delineate the high-probability existence area as the anatomical prior, and perform fine anatomical structure localization and segmentation based on the anatomical prior. The parametric geometry modeling and measurement module is used to construct a dynamic anatomical geometry model based on the localized and segmented high signal-to-noise ratio anatomical structures, and to perform standardized parameter measurements for transcatheter aortic valve replacement under the established local anatomical coordinate system.

12. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 10.

Images