Method and system for analyzing and processing intracardiac gas bubbles, medical management platform and medium

Abstract

The present disclosure provides an analysis and processing method and system of intracardiac bubbles, a medical management platform and a medium. The analysis and processing method comprises: obtaining target intracardiac correlation data corresponding to a target cardiac cavity region; based on the target intracardiac correlation data, obtaining a target bubble risk level of bubbles in different bubble regions in the target cardiac cavity region; wherein the bubbles are associated with a preset ablation energy output event. The present disclosure automatically determines the bubble load index and the bubble risk level by using a bubble condition prediction model and / or a bubble detection and quantification algorithm, changes "seeing bubbles" into a calculable, comparable and objective index, constructs a complete safety monitoring system which can be standardized, tracked and used to guide energy strategy adjustment, can provide effective bubble risk assessment and safety control basis for ablation scene in time and accurately, realizes image-driven, standardized and tracked bubble safety management in the ablation scene, and meets higher actual processing requirements.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a method, system, medical management platform, and medium for analyzing and processing intracardiac gas bubbles. Background Technology

[0002] Existing ablation techniques have received widespread attention in the interventional treatment of arrhythmias such as atrial fibrillation. For example, PFA (Pulsed Field Ablation) is a newly emerging myocardial ablation technique that uses irreversible electroporation as its main mechanism of action. Numerous clinical and animal studies have shown that PFA, compared with traditional radiofrequency ablation and cryoablation, has advantages in achieving pulmonary vein isolation, ablation of the left atrial posterior wall, and other myocardial target areas, including greater selectivity for the myocardium and a lower risk of thermal damage to adjacent non-target tissues such as the esophagus and phrenic nerve. However, with the increasing application of PFA, the gas microbubble phenomenon monitored during the procedure and its potential risk of cerebral microemboli have gradually attracted attention: during the energy release of PFA, a large number of transient hyperechoic bubbles or bubble clouds often appear in the cardiac chambers and great vessels. These bubbles appear as obvious hyperechoic masses on intracardiac echocardiography (ICE) or transesophageal echocardiography images, and usually dissipate within several cardiac cycles. Some imaging studies and follow-up results suggest that this type of intraoperative bubble phenomenon may be related to microembolic events such as asymptomatic cerebral infarction foci found on postoperative MRI, making the monitoring, assessment and control of bubble formation during PFA an urgent problem to be solved.

[0003] To reduce the risk of complications associated with energy ablation, existing technologies mainly attempt to address the aforementioned issues by relying on impedance and other electrical parameters or the operator's subjective observation of bubbles. However, these methods have limitations, such as failing to directly reflect the spatial distribution and dynamic changes of gas microbubbles within the cardiac chambers, difficulty in timely identifying locally high-load bubbles or bubbles migrating along blood flow to important blood supply arteries, reliance on the operator's subjective experience, and inability to achieve accurate quantitative analysis of bubbles. Consequently, they cannot meet practical needs. Summary of the Invention

[0004] The technical problem to be solved by this disclosure is to overcome the shortcomings of existing technologies that rely on electrical parameters such as impedance or subjective observation of bubbles by the surgeon's naked eye. These shortcomings include the inability to directly reflect the spatial distribution and dynamic changes of gas microbubbles in the cardiac chamber, the difficulty in timely identifying locally high-load bubbles or bubbles migrating along the blood flow to important blood supply arteries, reliance on the surgeon's subjective experience, the inability to achieve accurate quantitative analysis of bubbles, and the inability to meet practical needs. The purpose is to provide a method, system, medical management platform, and medium for analyzing and processing bubbles in the cardiac chamber.

[0005] This disclosure solves the above-mentioned technical problems through the following technical solution:

[0006] In a first aspect, this disclosure provides a method for analyzing and processing intracardiac gas bubbles, the method comprising:

[0007] Obtain the target intracardiac correlation data corresponding to the target cardiac chamber region;

[0008] Based on the target intracardiac correlation data, the target bubble danger level of bubbles in different bubble regions within the target cardiac cavity region is obtained; wherein, the bubbles are associated with preset ablation energy output events.

[0009] Optionally, the step of obtaining the target bubble hazard level of bubbles in different bubble regions within the target cardiac chamber region based on the target intracardiac correlation data includes:

[0010] The target intracardiac correlation data is input into a pre-trained bubble situation prediction model to output the target bubble danger level of bubbles in different bubble regions of the target cardiac chamber region.

[0011] Optionally, the step of obtaining the target bubble hazard level of bubbles in different bubble regions within the target cardiac chamber region based on the target intracardiac correlation data includes:

[0012] The target intracardiac correlation data is processed to obtain bubble characteristic parameters of bubbles in different bubble regions of the target cardiac chamber region;

[0013] Based on the bubble characteristic parameters, the target bubble load state of the corresponding bubble is obtained, and the target bubble hazard level of the bubble in the corresponding bubble region is determined according to the target bubble load state.

[0014] Optionally, the step of obtaining the target bubble load state of the corresponding bubble based on the bubble characteristic parameters includes:

[0015] The bubble characteristic parameters are mapped to a matching reference cardiac chamber region, and the target bubble load index value of the bubbles in the corresponding bubble region is calculated using a preset bubble load calculation formula; wherein, the reference cardiac chamber region is pre-calibrated before performing the ablation operation;

[0016] The step of determining the target bubble hazard level of bubbles in the corresponding bubble region based on the target bubble load state includes:

[0017] Based on the preset load range into which the target bubble load index value falls, the target bubble hazard level of the bubble in the corresponding bubble region is determined; wherein, different preset load ranges correspond to different target bubble hazard levels.

[0018] Optionally, the step of calculating the target bubble load index value of the bubbles in the corresponding bubble region using a preset bubble load calculation formula includes:

[0019] The different bubble characteristic parameters are normalized.

[0020] Based on different normalization results and corresponding first preset weights, the target bubble load index value of the bubbles in the corresponding bubble region is calculated.

[0021] Optionally, the step of calculating the target bubble load index value of bubbles in the corresponding bubble region based on different normalization results and corresponding first preset weights includes:

[0022] Based on different normalization results and the corresponding first preset weights, the initial bubble load index value of the bubbles in the corresponding bubble region is calculated.

[0023] Obtain the historical bubble load index value of the corresponding bubble area in the previous monitoring period;

[0024] The target bubble load index value of the bubbles in the corresponding bubble region is calculated based on the initial bubble load index value, the historical bubble load index value, and the corresponding second preset weight.

[0025] Optionally, based on the target bubble load index value falling within a first load range, the duration of the bubble falling within a first preset duration range, and / or the number of bubbles or bubble clusters falling within a first quantity range, it is determined that the bubble situation belongs to the first bubble danger level.

[0026] Based on the target bubble load index value falling into the second load range, the duration of the bubble falling into the second preset duration range, and / or the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falling into the first area range, it is determined that the bubble situation belongs to the second bubble danger level.

[0027] Based on the target bubble load index value falling into the third load range, and at least one of the following conditions: the duration of the bubble falls into the third preset duration range, the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falls into the second area range, and the target bubble load index value shows an upward trend, the bubble situation is determined to belong to the third bubble danger level.

[0028] Based on the target bubble load index value falling into the fourth load range, and at least one of the following conditions: the duration of the bubble falls into the fourth preset duration range, the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falls into the third area range, the decrease rate of the number of bubbles is less than the first preset decrease value, and the decrease rate of the bubble brightness is less than the second preset decrease value, the bubble situation is determined to belong to the fourth bubble danger level.

[0029] The values ​​of the first load range, the second load range, the third load range, and the fourth load range increase progressively, and the severity of the corresponding first bubble hazard level, second bubble hazard level, third bubble hazard level, and fourth bubble hazard level increases progressively.

[0030] Optionally, the analysis and processing method further includes:

[0031] The target bubble hazard level is input into a pre-trained bubble condition prediction model to output the target ablation damage prediction result in the corresponding bubble area.

[0032] Optionally, the bubble feature parameters correspond to at least one of the following features: number of bubbles and / or bubble clusters, area estimation, volume estimation, orientation, shape factor, average gray level, maximum gray level, and time of appearance, duration of frames, frequency of appearance, and size change trend over time.

[0033] And / or,

[0034] The target intracardiac associated data includes target intracardiac ultrasound images, target RF (radio frequency signal) data, or raw electrical signals in the target intracardiac ultrasound receiving link;

[0035] And / or,

[0036] The target intracardiac correlation data is the target intracardiac ultrasound image. The step of obtaining the target bubble risk level of bubbles in different bubble regions within the target cardiac chamber region based on the target intracardiac correlation data includes:

[0037] The target intracardiac ultrasound image is processed using a preset processing method to obtain several bubble region images, and bubble feature parameters corresponding to bubbles in each bubble region are extracted; wherein, the bubbles contained in the bubble region images are associated with preset ablation energy output events;

[0038] Based on the bubble characteristic parameters, the target bubble hazard level of bubbles in different bubble regions of the target cardiac cavity region is obtained.

[0039] Optionally, the step of obtaining the target intracardiac correlation data corresponding to the target cardiac chamber region includes:

[0040] Obtain the gated time window;

[0041] The gated time window corresponds to a time window associated with the preset ablation energy output event, and is at least one time window set before and after the preset ablation energy output event;

[0042] The first intracardiac ultrasound image or the first intracardiac ultrasound image sequence acquired within the gated time window of the target cardiac cavity region;

[0043] The obtained first intracardiac ultrasound image or the first intracardiac ultrasound image sequence is subjected to anti-artifact processing to obtain the target intracardiac ultrasound image.

[0044] And / or,

[0045] The preset processing method includes at least one of bubble detection, bubble segmentation, bubble classification, bubble positioning, and bubble enhancement.

[0046] Optionally, the step of obtaining the gated time window includes:

[0047] Acquire several second intracardiac ultrasound images within different preset time periods;

[0048] The energy state characterization parameters corresponding to the second intracardiac ultrasound image were extracted;

[0049] In response to the energy state characterization parameter indicating the occurrence of a short-term high-energy interference event, at least one gated time window is determined based on the corresponding preset time period.

[0050] And / or, obtain preset parameter information from the ablation system to determine at least one of the gated time windows.

[0051] Optionally, the analysis and processing method further includes:

[0052] Based on the target bubble hazard level and / or the target ablation damage prediction result of each bubble in the bubble region, a safety assessment result corresponding to the preset ablation energy output event is generated;

[0053] Based on the safety assessment results, a matching emergency guidance plan is generated;

[0054] And / or,

[0055] Based on the safety assessment results, an energy regulation strategy is generated to adjust the operating parameters of the preset equipment.

[0056] Optionally, the analysis and processing method further includes:

[0057] Based on the first preset parameters, generate a target analysis report;

[0058] And / or,

[0059] The second preset parameter is displayed using a preset display method;

[0060] And / or,

[0061] Store the third preset parameter to the target storage space;

[0062] The first preset parameter, the second preset parameter, and the third preset parameter include at least one of the following parameters:

[0063] The target bubble hazard level, the target ablation damage prediction results, the target intracardiac correlation data, the bubble characteristic parameters, the target bubble load status, the emergency guidance plan, and the energy regulation strategy;

[0064] And / or,

[0065] The preset ablation energy output event corresponds to either a pulsed electric field ablation energy output event or a radio frequency ablation energy output event.

[0066] A second aspect of this disclosure provides an analysis and processing system for intracardiac gas bubbles, the analysis and processing system comprising:

[0067] The target intracardiac data acquisition module is used to acquire the target intracardiac associated data corresponding to the target cardiac chamber region;

[0068] The bubble status acquisition module is used to acquire the target bubble danger level of bubbles in different bubble regions of the target cardiac cavity region based on the target intracardiac correlation data; wherein the bubbles are associated with preset ablation energy output events.

[0069] In a third aspect, this disclosure provides a medical management platform, which includes an intracardiac gas analysis and processing system as described in the second aspect, and an ablation system.

[0070] A fourth aspect of this disclosure provides an electronic device including a memory, a processor, and a computer program stored in the memory and for running on the processor, wherein the processor executes the computer program to implement the method for analyzing and processing intracardiac gas bubbles as described in the first aspect.

[0071] In a fifth aspect, this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for analyzing and processing intracardiac gas bubbles as described in the first aspect.

[0072] In a sixth aspect, this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the method for analyzing and processing intracardiac gas bubbles as described in the first aspect.

[0073] Based on common knowledge in the field, the above-mentioned preferred conditions can be combined arbitrarily to obtain various preferred embodiments of this disclosure.

[0074] The positive and progressive effects of this disclosure are as follows:

[0075] This disclosure uses target intracardiac related data (such as intracardiac ultrasound images) as the core data source, and automatically determines the bubble load index and bubble risk level using bubble condition prediction models and / or bubble detection and quantification algorithms. This transforms "seeing bubbles" into a calculable and comparable objective indicator, and allows for multi-site monitoring by cardiac chamber region. Based on this, it integrates bubble load with energy settings, catheter position, and other information to form a real-time safety assessment and energy regulation suggestion mechanism. When interfaces are available, this mechanism can be expanded to automatic or semi-automatic control. Simultaneously, relevant data is recorded throughout the process for postoperative review and model optimization. This constructs a standardized, traceable, and comprehensive safety monitoring system that can guide energy strategy adjustments. It provides timely and accurate effective bubble risk assessment and safety control basis for ablation scenarios, thereby achieving bubble safety management in image-driven, standardized, and traceable ablation scenarios that is difficult to achieve with existing technologies. Attached Figure Description

[0076] Figure 1 This is a flowchart of the method for analyzing and processing intracardiac gas bubbles according to Embodiment 1 of this disclosure;

[0077] Figure 2 This is a first flowchart of the method for analyzing and processing intracardiac gas bubbles according to Embodiment 2 of this disclosure;

[0078] Figure 3 This is a second flowchart of the method for analyzing and processing intracardiac gas bubbles according to Embodiment 2 of this disclosure;

[0079] Figure 4 This is a schematic diagram of the target intracardiac ultrasound image of Embodiment 2 of this disclosure;

[0080] Figure 5 This is a schematic diagram of the bubble region image in Embodiment 2 of this disclosure;

[0081] Figure 6 This is a schematic diagram of the bubble in Embodiment 2 of this disclosure;

[0082] Figure 7 This is the third flowchart of the method for analyzing and processing intracardiac gas bubbles in Embodiment 2 of this disclosure;

[0083] Figure 8This is a schematic diagram of the modules of the intracardiac gas analysis and processing system of Embodiment 3 of this disclosure;

[0084] Figure 9 This is a schematic diagram of the modules of the intracardiac gas analysis and processing system of Embodiment 4 of this disclosure;

[0085] Figure 10 This is a schematic diagram of the modules of the medical management platform according to Embodiment 5 of this disclosure;

[0086] Figure 11 This is a schematic diagram of the structure of the electronic device according to Embodiment 6 of this disclosure. Detailed Implementation

[0087] The present disclosure is further illustrated below by way of embodiments, but the present disclosure is not limited to the scope of the embodiments described herein.

[0088] The prefixes such as "first" and "second" used in this disclosure are merely for distinguishing different descriptive objects and do not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes used to distinguish descriptive objects in this disclosure does not constitute a limitation on the described objects. The description of the described objects is given in the claims or the context of the embodiments, and should not be construed as an unnecessary limitation. Furthermore, in the description of this embodiment, unless otherwise stated, "multiple" means two or more.

[0089] In this embodiment of the disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information comply with relevant laws and regulations and do not violate public order and good morals.

[0090] In order to reduce the risk of complications related to energy ablation, existing technologies mainly attempt to solve the above problems from two directions: (1) Starting from the energy end, the generation of bubbles can be indirectly controlled by optimizing the output form and control strategy of ablation energy. For example, in traditional radiofrequency ablation systems, some schemes infer the risk of microbubble formation by real-time monitoring of the impedance of the catheter electrode and its changes, and automatically terminate the energy output or reduce the power when the impedance rises to a certain threshold; in PFA systems, the possibility of local overheating and gas generation is minimized by selecting appropriate voltage amplitude, pulse width, number of pulses and pulse sequence structure. The common feature of these schemes is that they are mainly based on the electrical parameters of the energy generation end. (2) Starting from the imaging end, ICE or transesophageal ultrasound has been widely used in clinical practice to observe the catheter position, pulmonary vein morphology and pericardial effusion in real time during ablation surgery. For bubbles that appear during PFA, the surgeon currently relies on "visual observation" through ICE images to judge whether there are "too many" or "too long" bubbles based on experience, and then decides whether to pause ablation, adjust catheter contact or modify energy settings.

[0091] However, the above-mentioned schemes have obvious shortcomings in practical applications: (1) The detection method based on impedance and other electrical parameters cannot directly reflect the spatial distribution and dynamic changes of gas microbubbles in the heart chambers, and it is difficult to identify local high-load bubbles or bubbles migrating along the blood flow to important blood supply arteries in a timely manner; (2) The application of existing ICE in PFA surgery is mainly limited to manual observation, and a systematic bubble identification and quantification method for PFA scenarios has not yet been formed. There is a lack of unified bubble load indicators and risk level standards, and intraoperative assessment is highly dependent on the surgeon's subjective experience; Furthermore, there is a general lack of standardized time synchronization and information interaction mechanisms between the current imaging system and the PFA energy generation device, which makes it impossible to conduct multi-site joint monitoring and postoperative tracking analysis of bubble generation, migration and clearance processes in different anatomical regions, and even more impossible to effectively feed back objectively quantified bubble risk information to energy strategy decision-making.

[0092] The formation of intracardiac bubbles is influenced by a combination of factors, including ablation energy waveform, catheter contact status, local blood flow environment, and individual differences. These factors result in highly dynamic variations in spatial distribution, volume, and duration, and the specific relationship between these bubbles and potential complications such as cerebral microemboli is not yet fully elucidated. Current methods for analyzing intracardiac bubbles, relying on energy-end electrical parameters or operator visual observation, cannot uniformly quantify and rank this multidimensional dynamic information. This makes it difficult to provide timely and accurate information for effective bubble risk assessment and safety control in ablation scenarios (such as PFA), thus hindering the construction of a standardized, traceable, and comprehensive safety monitoring system that can guide energy strategy adjustments.

[0093] Based on this, this disclosure aims to solve the above-mentioned problems and proposes a novel analysis and processing scheme for intracardiac air bubbles. Compared with existing technologies that mainly rely on impedance and other electrical parameters or subjective observation of air bubbles by the operator, this disclosure uses target intracardiac related data (such as intracardiac ultrasound images) as the core data source. It utilizes air bubble prediction models and / or air bubble detection and quantification algorithms to automatically determine the air bubble load index and air bubble risk level, transforming "seeing air bubbles" into a calculable and comparable objective indicator, and enabling multi-site monitoring by cardiac chamber region. Furthermore, this disclosure comprehensively analyzes air bubble load with energy settings, catheter position, and other information to form a real-time safety assessment and energy regulation suggestion mechanism (which can be expanded to automatic or semi-automatic control when an interface is available). Simultaneously, relevant data is recorded throughout the process for postoperative review and model optimization, thereby achieving image-driven, standardized, and traceable air bubble safety management in ablation scenarios that is difficult to achieve with existing technologies. Specifically:

[0094] Example 1

[0095] like Figure 1 As shown, the method for analyzing and processing intracardiac gas bubbles in this embodiment includes:

[0096] S101. Obtain the target intracardiac correlation data corresponding to the target cardiac chamber region;

[0097] The target intracardiac associated data includes target intracardiac ultrasound images, target RF data, and target raw electrical signals in the intracardiac ultrasound receiving link.

[0098] S102. Based on the target intracardiac correlation data, obtain the target bubble hazard level of bubbles in different bubble regions within the target cardiac chamber region;

[0099] Among them, the bubbles (i.e., gas microbubbles) are associated with preset ablation energy output events. The preset ablation energy output events correspond to pulsed electric field ablation energy output events (PFA) or radio frequency ablation energy output events (RFA).

[0100] In this implementation, the actual situation of bubbles in different bubble regions within the target cardiac chamber region can be determined based on the target intracardiac correlation data corresponding to the target cardiac chamber region. This allows for the automatic and quantitative identification of the target bubble hazard level in the corresponding bubble region, turning "seeing bubbles" into a calculable and comparable objective indicator. This enables timely, efficient, and high-precision effective bubble risk assessment for ablation scenarios such as PFA.

[0101] Example 2

[0102] The method for analyzing and processing intracardiac gas bubbles in this embodiment is a further improvement on Embodiment 1, specifically:

[0103] In a feasible approach, when the target intracardiac correlation data is the target intracardiac ultrasound image, such as Figure 2 As shown, step S101 includes:

[0104] S1011, Obtain the gated time window;

[0105] Among them, the gated time window corresponds to the time window associated with the preset ablation energy output event, and is at least one time window set before and after the preset ablation energy output event;

[0106] S1012. The first intracardiac ultrasound image or the first intracardiac ultrasound image sequence acquired within the gated time window of the target cardiac chamber region.

[0107] S1013. Perform anti-artifact processing on the obtained first intracardiac ultrasound image or first intracardiac ultrasound image sequence to obtain the target intracardiac ultrasound image.

[0108] In this disclosure, the accuracy of determining the target intracardiac ultrasound image is achieved by determining the gated time window, thereby ensuring the accuracy and efficiency of subsequent bubble analysis.

[0109] In one feasible embodiment, step S1011 includes:

[0110] Acquire several second intracardiac ultrasound images within different preset time periods;

[0111] Energy state characterization parameters corresponding to the second intracardiac ultrasound image were extracted;

[0112] In response to the occurrence of a short-term high-energy interference event as indicated by the energy state characterization parameters, at least one gated time window is determined based on the corresponding preset time period; and / or, at least one gated time window is determined by acquiring preset parameter information in the ablation system.

[0113] In this disclosure, the gate control time window is effectively determined by automatically identifying short-term high-energy interference events, or by directly determining the gate control time window based on preset parameter information in the ablation system (such as the trigger signal or status information of the ablation device), thus ensuring the efficiency, feasibility and reliability of the determination of the gate control time window.

[0114] Furthermore, the process of acquiring target intracardiac ultrasound data related to the target cardiac chamber region and preprocessing the images corresponding to the ablation event to form target intracardiac ultrasound images for subsequent bubble identification and quantitative analysis is as follows:

[0115] (1) By manipulating the intracardiac ultrasound catheter and / or combining it with the navigation system, the imaging plane is adjusted to the target cardiac cavity region to be ablated by pulsed electric field, so that the target cardiac cavity region and the relevant catheter tip are stable and clearly visible on the intracardiac ultrasound image; thus ensuring that the image data acquired subsequently can cover the key anatomical areas that need to be monitored for bubble load, providing a reliable visual basis for subsequent regional calibration and bubble analysis.

[0116] (2) Before the pulsed electric field ablation energy is output, a continuous baseline intracardiac ultrasound image sequence is acquired. Based on this baseline intracardiac ultrasound image sequence, the cardiac chamber structures within the current field of view are divided and calibrated, and the image is divided into one or more predetermined cardiac chamber regions, such as corresponding to different wall segments of the left atrium, the right atrium, and the adjacent region of the interatrial septum. The baseline echo characteristics and noise levels of each region in the unablated state are extracted. This calibration process lays the foundation for subsequently mapping bubble features to specific cardiac chamber regions and distinguishing bubble signals from background noise.

[0117] (3) During the pulsed electric field ablation process, the system continuously monitors the original electrical signals, real-time intracardiac ultrasound images, RF data, etc. in the intracardiac ultrasound receiving link; analyzes the energy, amplitude, saturation ratio and spectral characteristics of each monitoring time period; when a short-term high-energy interference event that meets the preset threshold condition is detected, the short-term high-energy interference event is determined to be the time period corresponding to the high voltage pulse of the pulsed electric field, and one or more gated time windows are automatically set before and after the time period as a reference. In the gated time window, intracardiac ultrasound images and RF data of the heart chamber are collected in a focused manner; in an embodiment with an interface for docking with the pulsed electric field energy device, the system can also directly use the trigger signal or status information from the ablation device as a gated reference. Then, anti-artifact processing is performed on the intracardiac ultrasound images or RF data collected based on the gated time window to filter out abnormal components such as electromagnetic interference, instantaneous saturation and stripe noise introduced by the high voltage pulse, and retain the effective echo information related to bubble scattering to obtain a standardized gated image sequence for subsequent bubble detection and feature extraction, which is used as the target intracardiac ultrasound image.

[0118] In a feasible solution, such as Figure 3 As shown, step S102 includes:

[0119] S10211. Input the target intracardiac correlation data into the pre-trained bubble situation prediction model to output the target bubble danger level of bubbles in different bubble regions of the target cardiac chamber region.

[0120] The bubble prediction model can be based on CNN (Convolutional Neural Network), 3D-CNN (3D-Convolutional Neural Network), temporal convolutional network, recurrent neural network, spatiotemporal feature extraction network based on attention mechanism or Transformer (a deep learning model) structure, or a combination of these models, large models, etc. There are no specific restrictions, as long as the corresponding functions can be achieved.

[0121] Supervised training was performed on a large number of historical gated intracardiac ultrasound images with manually labeled bubble levels and clinical outcome labels, enabling the corresponding model to automatically learn the comprehensive characteristics of different bubble risk levels in terms of spatial distribution, brightness patterns, and temporal evolution, thereby ensuring the accuracy of the model output results.

[0122] During the inference phase, the model directly outputs a bubble hazard level label (e.g., level 0, level I, level II, or level III) for the corresponding cardiac chamber region based on the input target intracardiac correlation data (such as gated images or image sequences), along with an optional probability distribution for each level. The system can directly use the discrete levels output by the model as the level results for bubble state analysis, or fuse them with level results obtained based on threshold rules to improve overall stability and robustness.

[0123] In this disclosure, a pre-trained bubble situation prediction model is used to directly predict the bubble hazard level of bubbles in different bubble regions within the target cardiac cavity based on the input target intracardiac correlation data. This ensures both the accuracy of bubble hazard level determination and the overall efficiency of analysis and processing.

[0124] In a feasible approach, the target intracardiac correlation data is the target intracardiac ultrasound image, such as... Figure 4 As shown, step S102 includes:

[0125] S1021. Process the target intracardiac correlation data to obtain the bubble characteristic parameters of bubbles in different regions of the target cardiac chamber region;

[0126] S1022. Based on bubble characteristic parameters, obtain the target bubble hazard level of bubbles in different bubble regions within the target cardiac chamber region.

[0127] The step of processing the target intracardiac correlation data to obtain the bubble characteristic parameters of bubbles in different regions of the target cardiac chamber region includes:

[0128] The target intracardiac ultrasound image is processed using a preset processing method to obtain several bubble region images, and the bubble feature parameters corresponding to the bubbles in each bubble region are extracted; among them, the bubbles contained in the bubble region image are associated with preset ablation energy output events.

[0129] The preset processing methods include bubble detection, bubble segmentation, bubble classification, bubble positioning, and bubble enhancement.

[0130] The bubble feature parameters correspond to the number, area estimation, volume estimation, orientation, shape factor, brightness features (such as average gray level, maximum gray level, etc.) and temporal features (such as the time of appearance on the time axis, number of frames, frequency of appearance, size change trend over time, etc.), thus forming a multi-dimensional description of the number, size, brightness and temporal changes of bubbles.

[0131] In addition, for the target intracardiac ultrasound image, the bubble region can be segmented using a segmentation model and a target detection model, and the bubble feature parameters of the bubble in each bubble region can be extracted.

[0132] like Figure 5 As shown, this is a target intracardiac ultrasound image. After segmentation and other processing, the image of the bubble region containing the bubble is obtained, as detailed below. Figure 6 As shown; for Figure 6 Perform bubble recognition processing to obtain, for example Figure 7 The bubbles shown are then used to extract the corresponding bubble feature parameters.

[0133] In this disclosure, multiple bubble region images are extracted from the target intracardiac ultrasound image through relevant processing, and then each bubble region image is analyzed and processed to extract the bubble feature parameters corresponding to the bubble.

[0134] Specifically, using intracardiac ultrasound images as the core data source, high-quality images before and after PFA are automatically acquired through gated imaging and anti-artifact processing. Bubble load index and bubble risk level are constructed using bubble detection and quantification algorithms, turning "seeing bubbles" into a calculable and comparable objective indicator, and enabling multi-site monitoring by cardiac chamber region.

[0135] In one feasible embodiment, step S1022 includes:

[0136] Based on the bubble characteristic parameters, the target bubble load state of the corresponding bubble is obtained;

[0137] The target bubble hazard level of the bubbles in the corresponding bubble region is determined based on the target bubble load status.

[0138] In this disclosure, by acquiring the bubble characteristic parameters of bubbles in each bubble region, the corresponding bubble load state is specifically determined, and then the corresponding bubble hazard level is automatically determined, thereby achieving accurate detection of bubble conditions caused by ablation energy output events.

[0139] In one feasible embodiment, step S1022 includes:

[0140] The bubble characteristic parameters are mapped to the matched reference cardiac chamber region, and the target bubble load index value of the bubble in the corresponding bubble region is calculated using a preset bubble load calculation formula; wherein, the reference cardiac chamber region is obtained by pre-calibration before performing the ablation operation;

[0141] Of course, bubble characteristic parameters can also be input into a preset model to directly output the target bubble load index value of the corresponding bubble in the bubble region.

[0142] Based on the preset load range into which the target bubble load index value falls, the target bubble hazard level of the bubble in the corresponding bubble region is determined; different preset load ranges correspond to different target bubble hazard levels.

[0143] In this disclosure, based on the bubble characteristic parameters of bubbles in each bubble region, the target bubble load index value of the bubbles is accurately calculated, and the bubble hazard level of the bubbles in each bubble region is automatically matched according to the preset load range into which they fall, thus ensuring the accuracy of bubble state determination.

[0144] Specifically, after obtaining the spatial location and characteristic parameters of the bubbles, the information such as the centroid position and contour range of each bubble or bubble cluster is mapped to the previously marked cardiac cavity region, and the bubble characteristics in each preset cardiac cavity region are statistically analyzed and summarized.

[0145] Based on the statistical results, the bubble load index (i.e. the target bubble load index value) of each bubble region can be calculated according to the preset mathematical combination rules. For example, after normalizing the number of bubbles, the estimated total area or volume, the average brightness, the duration and the area proportion, a weighted sum or a comprehensive index can be obtained by combining nonlinear functions. Based on the magnitude and trend of the comprehensive index, the bubble load of each bubble region can be divided into different risk levels (such as level 0, level I, level II, and level III).

[0146] In addition, the acquired target intracardiac ultrasound images (or image blocks cropped with a preset cardiac chamber region as the center, including single-frame images, continuous multi-frame image sequences, or three-dimensional image data stacked in the time dimension, etc.) can be used as a pre-trained bubble situation prediction model to directly output the bubble danger level and the probability of danger in each bubble region in the target intracardiac ultrasound image, thereby forming a bubble risk level result that corresponds one-to-one with the cardiac chamber anatomical region, providing quantitative input for subsequent safety assessment and energy regulation.

[0147] In one feasible solution, the step of calculating the target bubble load index value of bubbles in the corresponding bubble region using a preset bubble load calculation formula includes:

[0148] Different bubble characteristic parameters are normalized;

[0149] Based on different normalization results and corresponding first preset weights, the target bubble load index value of the bubbles in the corresponding bubble region is calculated.

[0150] In this disclosure, different bubble characteristic parameters need to be normalized to ensure the feasibility of subsequent calculations. For different bubble characteristic parameters, corresponding weights are set in advance, and then the target bubble load index value of the bubble in the bubble region is accurately calculated based on different normalization results and the corresponding first preset weights.

[0151] In a feasible scheme, the step of calculating the target bubble load index value of bubbles in the corresponding bubble region based on different normalization results and corresponding first preset weights includes:

[0152] Based on different normalization results and the corresponding first preset weights, the initial bubble load index value of the bubbles in the corresponding bubble region is calculated.

[0153] The first preset weight of each bubble feature parameter is generally based on empirical preset settings, but can also be adjusted according to actual needs.

[0154] Obtain the historical bubble load index value of the corresponding bubble area in the previous monitoring period;

[0155] Based on the initial bubble load index value, the historical bubble load index value, and the corresponding second preset weight, the target bubble load index value of the bubbles in the corresponding bubble region is calculated.

[0156] In this disclosure, considering that the analysis of the bubble status during the current monitoring period is affected by the bubble load index of the previous monitoring period, the historical bubble load index value of the previous monitoring period is included in the calculation, thereby effectively ensuring the accuracy of the bubble load index value during the current monitoring period, and thus ensuring the reliability of subsequent determination of bubble hazard level, safety assessment, etc.

[0157] In one feasible scheme, the bubble situation is determined to belong to the first bubble hazard level based on the target bubble load index value falling within the first load range, the duration of the bubble falling within the first preset duration range, and / or the number of bubbles or bubble clusters falling within the first quantity range.

[0158] Based on the target bubble load index value falling into the second load range, the duration of the bubble falling into the second preset duration range, and / or the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falling into the first area range, it is determined that the bubble situation belongs to the second bubble danger level.

[0159] Based on the target bubble load index value falling into the third load range, and at least one of the following conditions: the duration of the bubble falls into the third preset duration range, the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falls into the second area range, and the target bubble load index value shows an upward trend, the bubble situation is determined to belong to the third bubble danger level.

[0160] Based on the target bubble load index value falling into the fourth load range, and at least one of the following conditions: the duration of the bubble falls into the fourth preset duration range, the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falls into the third area range, the rate of decrease in the number of bubbles is less than the first preset decrease value, and the rate of decrease in bubble brightness is less than the second preset decrease value, the bubble situation is determined to belong to the fourth bubble danger level.

[0161] Among them, the values ​​of the first load range, the second load range, the third load range, and the fourth load range increase progressively, and the severity of the corresponding first bubble hazard level, second bubble hazard level, third bubble hazard level, and fourth bubble hazard level increases progressively.

[0162] In this disclosure, by constructing constraints for different bubble hazard levels, the accuracy, rationality, and reliability of determining the actual bubble hazard level are ensured.

[0163] Of course, the constraints for different bubble hazard levels can be further optimized according to actual needs to further improve the accuracy and reliability of the quantitative analysis results of bubble conditions.

[0164] Specifically, after completing the gas microbubble detection and feature extraction, the corresponding bubble load index is calculated for each bubble region 𝑟 in each preset cardiac chamber, and the bubble hazard level is classified accordingly.

[0165] The following example illustrates this concept using a specific time window (e.g., several cardiac cycles following a PFA event). Within the bubble region 𝑟, the following characteristic parameters are statistically obtained:

[0166] The number of bubbles or bubble clusters detected within the bubble region 𝑟 (e.g., the number of connected components);

[0167] : The total area of ​​all bubbles within bubble region 𝑟, or the total volume of bubbles estimated based on the segmentation results;

[0168] The average gray value of the bubble region reflects the overall echo intensity;

[0169] The maximum gray value or saturation pixel ratio of the bubble region reflects the strongest local scattering.

[0170] The number of frames or cardiac cycles that the bubble takes from its first visible appearance to its near disappearance, used to describe the duration;

[0171] The percentage of the bubble region in the projected area of ​​the cardiac cavity region, expressed as a percentage, for example.

[0172] In practical implementation, the above parameters can be added, removed, or redefined according to the specific algorithm and imaging conditions. For example, It is divided into multiple scale intervals, and the brightness features are further broken down into texture statistics, etc.

[0173] To facilitate the combination of features with different dimensions, this scheme normalizes each feature to the [0,1] interval. Specifically, an empirical upper limit or a statistical upper limit of training data can be selected as a reference value, for example:

[0174]

[0175]

[0176]

[0177]

[0178]

[0179] in, , , , , The values ​​are preset reference values, which can be determined based on clinical experience or large-sample statistics; min(⋅,1) is used to limit the normalization result to no more than 1. Features such as these can also be normalized in a similar way, or the normalization process for these features can be omitted.

[0180] Assign weight coefficients to each feature ,For example: ;

[0181] in, correspond , correspond , correspond , correspond , correspond The weights can be set based on the experience of clinical experts, or obtained by fitting historical data using machine learning methods.

[0182] Based on the above normalization and weighting settings, the BLI (Bubble Load Index), i.e., the target bubble load index value, in this scheme can be defined in a linear weighted form as follows:

[0183]

[0184] in, Nonlinear combinations can also be used, such as introducing square terms or logarithmic terms for certain features, or directly outputting a comprehensive index from a pre-trained regression model. There are no restrictions on the specific calculation method used to obtain the target bubble load index value.

[0185] In addition, considering the time-cumulative effect of bubble load, a time-smoothing or cumulative form is introduced, for example:

[0186] in, This represents the target bubble load index value for the current monitoring period or after the current PFA event. This refers to the historical bubble load index value from the previous monitoring period. This is a smoothing coefficient used to control the relative weight of the current event and historical accumulation.

[0187] To convert continuous bubble load indices into grading information that is easy to use during surgery, this scheme allows for the preset of several thresholds for each bubble region. , , ,satisfy Based on certain constraints, the hazard levels of air bubbles are classified into four levels: Level 0, Level I, Level II, and Level III. For example:

[0188] 1. Level 0 (No significant bubble load)

[0189] The bubble hazard level of bubble region 𝑟 is determined to be level 0 when one of the following conditions is met:

[0190] 1) ,and Approximately 0 or only a very small number of isolated microbubbles;

[0191] 2) No more than one cardiac cycle, and It is lower than the preset minimum value (e.g., 5%).

[0192] 2. Level I (Light bubble load)

[0193] It is classified as Level I when the following conditions are met:

[0194] 1) Furthermore, the bubbles are mainly scattered. Below the first percentage threshold (e.g., 10%).

[0195] 2) Within the preset moderate range (e.g., no more than 2-3 cardiac cycles), no persistent high-density bubble cloud was formed.

[0196] 3. Level II (Medium bubble load)

[0197] A grade II status is determined when one of the following conditions is met:

[0198] 1) ,and It falls within the medium percentage range (e.g., 10%–30%).

[0199] 2) or If the preset threshold is exceeded (e.g., more than 3 cardiac cycles), obvious bubble clouds will repeatedly appear within a certain time window;

[0200] 3) Or after multiple consecutive PFA events, It shows a continuous upward trend, that is Reach the preset number of attempts.

[0201] 4. Level III (Severe bubble load / High risk)

[0202] The bubble hazard level of region 𝑟 will be directly determined as Level III when any of the following constraints are met:

[0203] 1) ;

[0204] 2) or Reaching a high percentage threshold (e.g., not less than 30%, or even close to the entire area being white);

[0205] 3) or The risk exceeds the preset high-risk duration (e.g., more than 5 cardiac cycles), and the number and brightness of bubbles do not show a significant decrease during this period.

[0206] In practical applications, the system can prioritize level upgrade judgments based on the above constraints to avoid underestimating risks due to abnormal local indicators; for cases where the constraints are not met, the system will primarily rely on... The range of values ​​and their changing trends are graded.

[0207] During the inference phase, the ranking results obtained based on threshold rules can be fused with the ranking results obtained based on the model to further improve the overall stability and robustness of bubble analysis.

[0208] This disclosure does not impose any limitations on this, and the technical solutions that use artificial intelligence models to quantify the bubble load in the ablation area and classify different safety levels based on intracardiac ultrasound gated images or their derived features are all within the scope of protection of this disclosure.

[0209] In one feasible approach, the analytical processing method further includes:

[0210] The target bubble hazard level is input into a pre-trained bubble condition prediction model to output the target ablation damage prediction result in the corresponding bubble area.

[0211] In this disclosure, the bubble condition prediction model automatically outputs the prediction results of the target ablation damage in the bubble area, so that relevant personnel can know the corresponding ablation damage in a timely and efficient manner, so as to intervene and treat it in a timely manner.

[0212] In one feasible approach, the analytical processing method further includes:

[0213] Based on the target bubble hazard level and / or target ablation damage prediction results of each bubble region, a safety assessment result corresponding to the preset ablation energy output event is generated.

[0214] Based on the safety assessment results, generate matching emergency guidance plans;

[0215] In this disclosure, after determining the target bubble hazard level and target ablation damage prediction results, that is, based on the completion of bubble identification and bubble load quantification, the system can automatically perform a safety assessment of preset ablation energy output events by combining the energy setting of pulsed electric field ablation and the catheter status, and output the corresponding safety assessment results, providing a matching emergency guidance plan. This allows relevant personnel to be aware of the bubble situation in a timely manner and to clearly understand how to deal with it, so as to effectively protect the user's safety and ensure that the intervention operation is reasonable, convenient and efficient.

[0216] In one feasible approach, an energy regulation strategy is generated based on the safety assessment results to adjust the operating parameters of preset equipment. This preset equipment includes an ablation system, among other things.

[0217] This disclosure enables the automatic generation of energy regulation strategies for adjusting preset equipment operating parameters based on safety assessment results, generating regulation conclusions for subsequent energy applications, and outputting and recording them in a manner suitable for intraoperative use. For example, adjusting the energy output parameters of the ablation system allows for real-time, objective, and quantitative safety assessment of gas microbubbles generated within the cardiac chambers, transforming this assessment into operable energy regulation. This allows for timely and automatic adjustment of the real-time operating parameters of relevant equipment, enabling timely intervention and processing. It transforms the aforementioned bubble characteristics and bubble load index at the data level into safety assessment results and energy regulation recommendations for clinical decision-making, achieving a closed loop from "data" to "conclusion," further ensuring user safety. Specifically, after obtaining the bubble load index and bubble risk level of each cardiac chamber region, the system comprehensively analyzes the bubble load index along with the corresponding region's pulse electric field energy setting parameters (e.g., voltage, pulse width, number of pulses, repetition frequency, etc.) and information such as catheter position and contact status, performing a safety assessment according to a preset rule base and intelligent assessment model.

[0218] For example, when the bubble load in a certain area is at a low level and there is no obvious upward trend, it is assessed that the current energy application is within an acceptable risk range, and the conclusion is "allow to maintain the current energy strategy"; when the bubble load reaches a moderate level or increases significantly in a short period of time, it is assessed that there is a potential risk, and the control recommendation is "to appropriately reduce the energy, extend the pulse interval, or postpone the additional ablation in this area"; when the bubble load reaches a severe level and persists, it is assessed as a high-risk state, and the conclusion is "to immediately stop pulse electric field ablation in this area and re-evaluate the conduit and strategy".

[0219] In the basic implementation, the safety assessment conclusions, emergency guidance plans, and control suggestions in this solution can all be provided to the operator in the form of prompts, allowing the operator to manually adjust the PFA energy. In implementations with interfaces that connect to energy devices, the system can also convert the above control suggestions into automatic or semi-automatic control commands and send them to the energy device to directly adjust or disable the corresponding energy output.

[0220] In one feasible approach, the analytical processing method further includes:

[0221] Based on the first preset parameters, generate a target analysis report;

[0222] The second preset parameter is displayed using a preset display method, which includes graphics, color coding, text prompts, etc., so that the surgeon can intuitively understand the bubble load status of different anatomical areas and the corresponding safety recommendations.

[0223] Store the third preset parameter to the target storage space;

[0224] The first preset parameter, the second preset parameter, and the third preset parameter include at least one of the following parameters:

[0225] The target bubble hazard level, target ablation damage prediction results, target intracardiac correlation data, bubble characteristic parameters, target bubble load status, emergency guidance plan and energy regulation strategy, etc.

[0226] In this disclosure, an overall analysis report can be generated based on one or more data obtained during the analysis and processing process, so that relevant personnel can clearly understand the specific situation; and it can be displayed in a timely manner in a specific way to present the relevant content more intuitively; in addition, the relevant data can be stored in the target storage space in a timely manner for subsequent retrieval, viewing, processing, etc.

[0227] Specifically, after generating safety assessment results, emergency guidance plans, and energy regulation suggestions, the system visualizes the bubble load index, risk level, assessment conclusions, and regulation suggestions for the current ablation operation in various bubble regions within the cardiac chambers on the user interface using graphics, color coding, and text prompts. This allows the operator to intuitively understand the bubble load status and corresponding safety recommendations for different anatomical regions. Simultaneously, the system records the aforementioned assessment results, regulation suggestions, and the operator's actual actions, along with the corresponding pulsed electric field ablation events, energy setting parameters, and time information, forming structured surgical procedure data. This data can be used for real-time decision support during the procedure, as well as for postoperative playback, statistical analysis, and quality control. It also provides a data foundation for subsequent construction or optimization of risk prediction models and individualized energy strategies based on large samples.

[0228] This disclosure introduces intracardiac ultrasound-based gated imaging, anti-artifact processing, and bubble detection and quantification algorithms into the ablation scenario, enabling real-time, objective, and regional safety assessment of intracardiac gas microbubbles. This allows operators to identify high-risk bubble loads and adjust energy strategies promptly without relying solely on impedance curves or visual experience, potentially reducing the risk of severe bubble loads and related complications such as cerebral microemboli. Simultaneously, the bubble load index and risk level system provide a standardized and quantifiable foundation for bubble management in the ablation scenario. Combined with full-process data recording and visualization playback, this facilitates postoperative review and in-hospital quality control, and provides high-quality training data for building large-sample AI risk prediction models and individualized energy solutions. Overall, this constructs a scalable, traceable, and co-evolving image-driven safety management platform with the ablation system (PFA).

[0229] Example 3

[0230] like Figure 8 As shown, the intracardiac gas analysis and processing system of this embodiment includes:

[0231] Target intracardiac data acquisition module 1 is used to acquire target intracardiac related data corresponding to the target cardiac chamber region;

[0232] The bubble status acquisition module 2 is used to acquire the target bubble danger level of bubbles in different bubble regions in the target cardiac cavity region based on the target intracardiac correlation data; wherein, the bubbles are associated with preset ablation energy output events.

[0233] Example 4

[0234] like Figure 9 As shown, the intracardiac gas analysis and processing system of this embodiment is a further improvement on Embodiment 3, specifically:

[0235] In one feasible scheme, the bubble state acquisition module 2 is also used to input the target intracardiac correlation data into a pre-trained bubble state prediction model to output the target bubble danger level of bubbles in different bubble regions in the target cardiac chamber region.

[0236] In one feasible solution, the bubble state acquisition module 2 includes:

[0237] The bubble feature parameter acquisition unit is used to process the target intracardiac correlation data to obtain the bubble feature parameters of bubbles in different bubble regions of the target cardiac chamber region;

[0238] The bubble load state acquisition unit is used to acquire the target bubble load state of the corresponding bubble based on the bubble characteristic parameters.

[0239] The bubble hazard level determination unit is used to determine the target bubble hazard level of bubbles in the corresponding bubble region based on the target bubble load state.

[0240] In one feasible scheme, the bubble load state acquisition unit is also used to map bubble characteristic parameters to a matching reference cardiac chamber region, and calculate the target bubble load index value of the bubble in the corresponding bubble region using a preset bubble load calculation formula; wherein, the reference cardiac chamber region is obtained by pre-calibration before performing the ablation operation;

[0241] The bubble hazard level determination unit is also used to determine the target bubble hazard level of bubbles in the corresponding bubble area based on the preset load range into which the target bubble load index value falls; wherein, different preset load ranges correspond to different target bubble hazard levels.

[0242] In one feasible scheme, the bubble load state acquisition unit is also used to normalize different bubble characteristic parameters; based on different normalization results and the corresponding first preset weight, the target bubble load index value of the bubble in the corresponding bubble region is calculated.

[0243] In one feasible scheme, the bubble load status acquisition unit is also used to calculate the initial bubble load index value of the bubbles in the corresponding bubble region based on different normalization results and the corresponding first preset weight; to acquire the historical bubble load index value of the bubbles in the corresponding bubble region in the previous monitoring period; and to calculate the target bubble load index value of the bubbles in the corresponding bubble region based on the initial bubble load index value, the historical bubble load index value and the corresponding second preset weight.

[0244] In one feasible scheme, the bubble situation is determined to belong to the first bubble hazard level based on the target bubble load index value falling within the first load range, the duration of the bubble falling within the first preset duration range, and / or the number of bubbles or bubble clusters falling within the first quantity range.

[0245] Based on the target bubble load index value falling into the second load range, the duration of the bubble falling into the second preset duration range, and / or the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falling into the first area range, it is determined that the bubble situation belongs to the second bubble danger level.

[0246] Based on the target bubble load index value falling into the third load range, and at least one of the following conditions: the duration of the bubble falls into the third preset duration range, the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falls into the second area range, and the target bubble load index value shows an upward trend, the bubble situation is determined to belong to the third bubble danger level.

[0247] Based on the target bubble load index value falling into the fourth load range, and at least one of the following conditions: the duration of the bubble falls into the fourth preset duration range, the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falls into the third area range, the rate of decrease in the number of bubbles is less than the first preset decrease value, and the rate of decrease in bubble brightness is less than the second preset decrease value, the bubble situation is determined to belong to the fourth bubble danger level.

[0248] Among them, the values ​​of the first load range, the second load range, the third load range, and the fourth load range increase progressively, and the severity of the corresponding first bubble hazard level, second bubble hazard level, third bubble hazard level, and fourth bubble hazard level increases progressively.

[0249] In one feasible embodiment, the analysis and processing system also includes:

[0250] Damage prediction module 3 is used to input the target bubble hazard level into a pre-trained bubble condition prediction model to output the target ablation damage prediction result in the corresponding bubble area.

[0251] In one feasible scheme, the bubble feature parameters correspond to at least one of the following features: number of bubbles and / or bubble clusters, area estimation, volume estimation, orientation, shape factor, average gray level, maximum gray level, and time of occurrence, duration of frames, frequency of occurrence, and size variation trend over time.

[0252] In one feasible approach, the target intracardiac associated data includes target intracardiac ultrasound images, target RF data, or raw electrical signals in the target intracardiac ultrasound receiving link.

[0253] In one feasible scheme, the target intracardiac associated data is the target intracardiac ultrasound image. The bubble state acquisition module 2 is also used to process the target intracardiac ultrasound image using a preset processing method to obtain several bubble region images and extract the bubble feature parameters corresponding to the bubbles in each bubble region. Among them, the bubbles contained in the bubble region image are associated with a preset ablation energy output event. Based on the bubble feature parameters, the target bubble danger level of bubbles in different bubble regions in the target cardiac cavity is obtained.

[0254] The preset processing methods include bubble detection, bubble segmentation, bubble classification, bubble positioning, and bubble enhancement.

[0255] In one feasible solution, the target intracardiac data acquisition module 1 is also used for

[0256] The time window acquisition unit is used to acquire the gated time window;

[0257] Among them, the gated time window corresponds to the time window associated with the preset ablation energy output event, and is at least one time window set before and after the preset ablation energy output event;

[0258] The first image acquisition unit is used to acquire the first intracardiac ultrasound image or the first intracardiac ultrasound image sequence obtained from the target cardiac chamber region within the gated time window.

[0259] The target image acquisition unit is used to perform anti-artifact processing on the obtained first intracardiac ultrasound image or first intracardiac ultrasound image sequence to obtain the target intracardiac ultrasound image.

[0260] In one feasible solution, the time window acquisition unit is also used to acquire several second intracardiac ultrasound images within different preset time periods;

[0261] Energy state characterization parameters corresponding to the second intracardiac ultrasound image were extracted;

[0262] In response to the occurrence of a short-term high-energy disturbance event as indicated by the energy state characterization parameters, at least one gated time window is determined based on the corresponding preset time period.

[0263] And / or, obtain preset parameter information from the ablation system to determine at least one gated time window.

[0264] In a feasible solution, the analysis and processing system also includes:

[0265] Safety assessment module 4 is used to generate safety assessment results corresponding to preset ablation energy output events based on the target bubble hazard level and / or target ablation damage prediction results of bubbles in each bubble region.

[0266] Emergency guidance plan generation module 5 is used to generate matching emergency guidance plans based on the safety assessment results;

[0267] In one feasible embodiment, the analysis and processing system also includes:

[0268] The energy regulation strategy generation module 6 is used to generate an energy regulation strategy for adjusting the operating parameters of preset equipment based on the safety assessment results.

[0269] In a feasible solution, the analysis and processing system also includes:

[0270] Analysis report generation module 7 is used to generate a target analysis report based on the first preset parameters;

[0271] In a feasible solution, the analysis and processing system also includes:

[0272] Display control module 8 is used to display the second preset parameter using a preset display method;

[0273] In a feasible solution, the analysis and processing system also includes:

[0274] Data storage module 9 is used to store the third preset parameter into the target storage space;

[0275] The first preset parameter, the second preset parameter, and the third preset parameter include at least one of the following parameters:

[0276] The target bubble hazard level, target ablation damage prediction results, target intracardiac correlation data, bubble characteristic parameters, target bubble load status, emergency guidance plan and energy regulation strategy;

[0277] In one feasible approach, the preset ablation energy output event corresponds to either a pulsed electric field ablation energy output event or a radio frequency ablation energy output event.

[0278] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The system embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs.

[0279] Example 5

[0280] like Figure 10 As shown, this embodiment provides a medical management platform 100, which includes an intracardiac gas analysis and processing system 200 as described in Embodiment 3 or 4, and an ablation system 300.

[0281] In this embodiment, an image-driven medical management platform that is scalable, traceable, and can evolve in tandem with the ablation system is constructed, which effectively reduces the risk of complications related to energy ablation and improves user safety.

[0282] Example 6

[0283] Figure 11 This is a schematic diagram of the structure of an electronic device according to an example embodiment of the present disclosure. The electronic device includes a memory, a processor, and a computer program stored in the memory and used to run on the processor. When the processor executes the computer program, it implements the method described in any of the above embodiments. Figure 11 The electronic device 90 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0284] like Figure 11As shown, the electronic device 90 can be manifested as a general-purpose computing device, such as a server device. The components of the electronic device 90 may include, but are not limited to: at least one processor 91, at least one memory 92, and a bus 93 connecting different system components (including memory 92 and processor 91).

[0285] Bus 93 includes a data bus, an address bus, and a control bus.

[0286] The memory 92 may include volatile memory, such as random access memory (RAM) 921 and / or cache memory 922, and may further include read-only memory (ROM) 923.

[0287] The memory 92 may also include a program tool 925 (or utility) having a set (at least one) program module 924, such program module 924 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0288] The processor 91 executes various functional applications and data processing, such as the methods provided in any of the above embodiments, by running computer programs stored in the memory 92.

[0289] Electronic device 90 can also communicate with one or more external devices 94 (e.g., keyboard, pointing device, etc.). This communication can be performed through input / output (I / O) interface 95. Furthermore, electronic device 90 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public network, such as the Internet) via network adapter 96. As shown, network adapter 96 communicates with other modules of electronic device 90 via bus 93. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with electronic device 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0290] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0291] Example 7

[0292] This disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in any of the above embodiments.

[0293] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0294] Example 8

[0295] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the above embodiments.

[0296] The program code for executing the computer program product of this disclosure can be written in any combination of one or more programming languages, and the program code can be executed entirely on a user device, partially on a user device, as a stand-alone software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0297] While specific embodiments of this disclosure have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of this disclosure is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of this disclosure, but all such changes and modifications fall within the scope of protection of this disclosure.

Claims

1. A method for analyzing and processing intracardiac gas bubbles, characterized in that, The analysis and processing method includes: Obtain the target intracardiac correlation data corresponding to the target cardiac chamber region; Based on the target intracardiac correlation data, the target bubble danger level of bubbles in different bubble regions within the target cardiac cavity region is obtained; wherein, the bubbles are associated with preset ablation energy output events.

2. The method for analyzing and processing intracardiac gas bubbles as described in claim 1, characterized in that, The step of obtaining the target bubble hazard level of bubbles in different bubble regions within the target cardiac chamber region based on the target intracardiac correlation data includes: The target intracardiac correlation data is input into a pre-trained bubble situation prediction model to output the target bubble danger level of bubbles in different bubble regions of the target cardiac chamber region.

3. The method for analyzing and processing intracardiac gas bubbles as described in claim 1, characterized in that, The step of obtaining the target bubble hazard level of bubbles in different bubble regions within the target cardiac chamber region based on the target intracardiac correlation data includes: The target intracardiac correlation data is processed to obtain bubble characteristic parameters of bubbles in different bubble regions of the target cardiac cavity region; Based on the bubble characteristic parameters, the target bubble load state of the corresponding bubble is obtained, and the target bubble hazard level of the bubble in the corresponding bubble region is determined according to the target bubble load state.

4. The method for analyzing and processing intracardiac gas bubbles as described in claim 3, characterized in that, The step of obtaining the target bubble load state of the corresponding bubble based on the bubble characteristic parameters includes: The bubble characteristic parameters are mapped to a matching reference cardiac chamber region, and the target bubble load index value of the bubbles in the corresponding bubble region is calculated using a preset bubble load calculation formula; wherein, the reference cardiac chamber region is pre-calibrated before performing the ablation operation; The step of determining the target bubble hazard level of bubbles in the corresponding bubble region based on the target bubble load state includes: Based on the preset load range into which the target bubble load index value falls, the target bubble hazard level of the bubble in the corresponding bubble region is determined; wherein, different preset load ranges correspond to different target bubble hazard levels.

5. The method for analyzing and processing intracardiac gas bubbles as described in claim 4, characterized in that, The step of calculating the target bubble load index value of bubbles in the corresponding bubble region using a preset bubble load calculation formula includes: The different bubble characteristic parameters are normalized. Based on different normalization results and corresponding first preset weights, the target bubble load index value of the bubbles in the corresponding bubble region is calculated.

6. The method for analyzing and processing intracardiac gas bubbles as described in claim 5, characterized in that, The step of calculating the target bubble load index value of bubbles in the corresponding bubble region based on different normalization results and corresponding first preset weights includes: Based on different normalization results and the corresponding first preset weights, the initial bubble load index value of the bubbles in the corresponding bubble region is calculated. Obtain the historical bubble load index value of the corresponding bubble area in the previous monitoring period; The target bubble load index value of the bubbles in the corresponding bubble region is calculated based on the initial bubble load index value, the historical bubble load index value, and the corresponding second preset weight.

7. The method for analyzing and processing intracardiac gas bubbles as described in any one of claims 3-6, characterized in that, Based on the target bubble load index value falling within the first load range, the duration of the bubble falling within the first preset duration range, and / or the number of bubbles or bubble clusters falling within the first quantity range, it is determined that the bubble situation belongs to the first bubble danger level. Based on the target bubble load index value falling into the second load range, the duration of the bubble falling into the second preset duration range, and / or the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falling into the first area range, it is determined that the bubble situation belongs to the second bubble danger level. Based on the target bubble load index value falling into the third load range, and at least one of the following conditions: the duration of the bubble falls into the third preset duration range, the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falls into the second area range, and the target bubble load index value shows an upward trend, the bubble situation is determined to belong to the third bubble danger level. Based on the target bubble load index value falling into the fourth load range, and at least one of the following conditions: the duration of the bubble falls into the fourth preset duration range, the proportion of the projected area of ​​the bubble region in the target cardiac cavity region falls into the third area range, the decrease rate of the number of bubbles is less than the first preset decrease value, and the decrease rate of the bubble brightness is less than the second preset decrease value, the bubble situation is determined to belong to the fourth bubble danger level. The values ​​of the first load range, the second load range, the third load range, and the fourth load range increase progressively, and the severity of the corresponding first bubble hazard level, second bubble hazard level, third bubble hazard level, and fourth bubble hazard level increases progressively.

8. The method for analyzing and processing intracardiac gas bubbles as described in any one of claims 3-6, characterized in that, The analysis and processing method further includes: The target bubble hazard level is input into a pre-trained bubble condition prediction model to output the target ablation damage prediction result in the corresponding bubble area.

9. The method for analyzing and processing intracardiac gas bubbles as described in any one of claims 3-6, characterized in that, The bubble feature parameters correspond to at least one of the following features: number of bubbles and / or bubble clusters, area estimation, volume estimation, orientation, shape factor, average gray level, maximum gray level, and time of appearance, duration of frames, frequency of appearance, and size change trend over time. And / or, The target intracardiac associated data includes target intracardiac ultrasound images, target RF data, or raw electrical signals in the target intracardiac ultrasound receiving link; And / or, The target intracardiac correlation data is the target intracardiac ultrasound image. The step of obtaining the target bubble risk level of bubbles in different bubble regions within the target cardiac chamber region based on the target intracardiac correlation data includes: The target intracardiac ultrasound image is processed using a preset processing method to obtain several bubble region images, and bubble feature parameters corresponding to bubbles in each bubble region are extracted; wherein, the bubbles contained in the bubble region images are associated with preset ablation energy output events; Based on the bubble characteristic parameters, the target bubble hazard level of bubbles in different bubble regions of the target cardiac cavity region is obtained.

10. The method for analyzing and processing intracardiac gas bubbles as described in claim 9, characterized in that, The step of obtaining the target intracardiac correlation data corresponding to the target cardiac chamber region includes: Obtain the gated time window; The gated time window corresponds to a time window associated with the preset ablation energy output event, and is at least one time window set before and after the preset ablation energy output event; The first intracardiac ultrasound image or the first intracardiac ultrasound image sequence acquired within the gated time window of the target cardiac cavity region; The obtained first intracardiac ultrasound image or the first intracardiac ultrasound image sequence is subjected to anti-artifact processing to obtain the target intracardiac ultrasound image. And / or, The preset processing method includes at least one of bubble detection, bubble segmentation, bubble classification, bubble positioning, and bubble enhancement.

11. The method for analyzing and processing intracardiac gas bubbles as described in claim 10, characterized in that, The step of obtaining the gated time window includes: Acquire several second intracardiac ultrasound images within different preset time periods; The energy state characterization parameters corresponding to the second intracardiac ultrasound image were extracted; In response to the energy state characterization parameter indicating the occurrence of a short-term high-energy interference event, at least one gated time window is determined based on the corresponding preset time period. And / or, obtain preset parameter information from the ablation system to determine at least one of the gated time windows.

12. The method for analyzing and processing intracardiac gas bubbles as described in claim 8, characterized in that, The analysis and processing method further includes: Based on the target bubble hazard level and / or the target ablation damage prediction result of each bubble in the bubble region, a safety assessment result corresponding to the preset ablation energy output event is generated; Based on the safety assessment results, a matching emergency guidance plan is generated; And / or, Based on the safety assessment results, an energy regulation strategy is generated to adjust the operating parameters of the preset equipment.

13. The method for analyzing and processing intracardiac gas bubbles as described in claim 12, characterized in that, The analysis and processing method further includes: Based on the first preset parameters, generate a target analysis report; And / or, The second preset parameter is displayed using a preset display method; And / or, Store the third preset parameter to the target storage space; The first preset parameter, the second preset parameter, and the third preset parameter include at least one of the following parameters: The target bubble hazard level, the target ablation damage prediction results, the target intracardiac correlation data, the bubble characteristic parameters, the target bubble load status, the emergency guidance plan, and the energy regulation strategy; And / or, The preset ablation energy output event corresponds to either a pulsed electric field ablation energy output event or a radio frequency ablation energy output event.

14. A system for analyzing and processing intracardiac gas bubbles, characterized in that, The analysis and processing system includes: The target intracardiac data acquisition module is used to acquire the target intracardiac associated data corresponding to the target cardiac chamber region; The bubble status acquisition module is used to acquire the target bubble danger level of bubbles in different bubble regions of the target cardiac cavity region based on the target intracardiac correlation data; wherein the bubbles are associated with preset ablation energy output events.

15. A medical management platform, characterized in that, The medical management platform includes the intracardiac gas analysis and processing system as described in claim 14, and the ablation system.

16. An electronic device comprising a memory, a processor, and a computer program stored in the memory and for running on the processor, characterized in that, When the processor executes the computer program, it implements the method for analyzing and processing intracardiac gas bubbles as described in any one of claims 1-13.

17. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for analyzing and processing intracardiac gas bubbles as described in any one of claims 1-13.

18. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for analyzing and processing intracardiac gas bubbles as described in any one of claims 1-13.

Images