System for automatic segmentation of anatomical structures for large area annular ablation spots

CN114052891BActive Publication Date: 2026-09-22BIOSENSE WEBSTER (ISRAEL) LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202110871327.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2021-07-21
Filing Date
2021-07-30
Publication Date
2026-09-22
Estimated Expiration
2041-07-30

AI Technical Summary

Technical Problem

然而,WACA消融点之间存在潜在间隙、所得的消融线中存在潜在间隙以及WACA依赖于解剖结构使得WACA受到限制

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114052891B_ABST
    Figure CN114052891B_ABST
Patent Text Reader

Abstract

The invention is entitled "Automatic Segmentation of Anatomy of Large Area Circular Ablation Points". The invention provides a method and apparatus for implementing an assessment engine implemented using a processor coupled to a memory. The assessment engine receives valid points corresponding to cardiac tissue of a patient. The assessment engine determines an anatomical classification for each of the valid points based on a structural segmentation of the cardiac tissue, and provides the anatomical classification with each of the plurality of valid points to support treatment of the cardiac tissue.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Cross-reference to related applications This application claims the benefit of U.S. Provisional Patent Application 63 / 059,060, filed July 30, 2020, which is incorporated herein by reference as fully illustrated. Technical Field

[0002] This invention relates to methods and systems for artificial intelligence and machine learning. More specifically, this invention relates to systems and methods utilizing machine learning algorithms to perform automatic segmentation of anatomical structures at large area ring ablation (WACA) points. Background Technology

[0003] Treatment of cardiac conditions typically requires cardiac imaging (i.e., imaging of cardiac tissue, chambers, veins, arteries, and / or pathways, also known as cardiac scans or cardiac imaging) and subsequent ablation (i.e., removal or destruction of the imaged cardiac tissue, chambers, veins, arteries, and / or pathways). In this example, cardiac conditions of atrial fibrillation can be imaged and treated using atrial fibrillation ablation. The specific type of atrial fibrillation ablation is large-area ring ablation (WACA).

[0004] Conventionally, during the cardiac mapping phase, WACA achieves point-by-point isolation (e.g., WACA ablation points) of the right and left pulmonary veins to form a ring around the left and right pulmonary veins (e.g., in some cases, the WACA may extend to the top of the atrium and into the right atrium). However, potential gaps exist between WACA ablation points, in the resulting ablation line, and the anatomical dependence of WACA makes it limited. For example, these gaps can lead to pulmonary vein reconnection and recurrent arrhythmias if left untreated during the ablation phase. To overcome these limitations, conventional methods rely on manual anatomical segmentation of ablation sites and estimation of WACA ablation point continuity by healthcare professionals. Due to these limitations and the reliance on conventional manual review methods, there is a need for improved methods for predicting potential gaps, providing anatomical segmentation, and providing continuity estimation of WACA ablation points. Summary of the Invention

[0005] A method and apparatus are provided for implementing an evaluation engine using a processor coupled to memory. The evaluation engine receives effective points corresponding to a patient's cardiac tissue. The evaluation engine determines the anatomical classification of each effective point based on structural segmentation of the cardiac tissue and provides the anatomical classification along with each of the plurality of effective points to support treatment of the cardiac tissue. Attached Figure Description

[0006] A more detailed understanding can be obtained through the following specific embodiments provided by way of example and in conjunction with the accompanying drawings, wherein similar reference numerals in the drawings indicate similar elements, and wherein: Figure 1 An illustration shows an exemplary system that can implement one or more features; Figure 2 A block diagram of an exemplary system for remotely monitoring and transmitting patient biometrics is shown; Figure 3 A graphical depiction of the artificial intelligence system is shown; Figure 4 It shows in Figure 3 A block diagram of the methods executed in an artificial intelligence system; Figure 5 A block diagram of a method according to one or more embodiments is shown; Figure 6A An example of an autoencoder structure is shown; Figure 6B It shows in Figure 6A A block diagram of the methods executed in the autoencoder; Figure 7 A block diagram of a method according to one or more embodiments is shown; Figure 8 A graphical image of an example graphical user interface is shown, which provides an image of a PV with two separate rings; Figure 9A A graphical representation of the user interface displaying the dataset is shown; Figure 9B A graphical representation of the user interface displaying the dataset is shown; Figure 10 A graphic depiction of the left and right WACAs classified into anatomical structures is shown; Figure 11A An illustration of the right anatomical structure is shown; Figure 11B An illustration of the left anatomical structure is shown; Figure 12A A block diagram of a classification method for an exemplary operation of a random forest for an acute reconnection classifier is shown; Figure 12B A block diagram is shown for a classification method that utilizes random forest classification, fully connected dense layers, and CNN architecture; Figure 13 An example random forest classifier is shown; Figure 14A A block diagram of a classification method for an exemplary operation of a random forest for an acute reconnection classifier is shown; Figure 14BA block diagram of a classification method is shown, illustrating exemplary operation of a deep learning approach for a secondary ablation / acute reconnection classifier; and Figure 14C A graphic image depicting an acute reconnection point is shown. Detailed Implementation

[0007] This paper discloses a system and method for automated segmentation of anatomical structures at large area ring ablation (WACA) points. The system and method incorporate artificial intelligence and machine learning. More specifically, this disclosure relates to a system and method for automated segmentation of anatomical structures at WACA points, comprising a machine learning algorithm that performs automated segmentation of the anatomical structures of valid WACA ablation points (e.g., valid points) during cardiac mapping. For example, the system and method include processor-executable code or software residing in the procedural operation of a medical device and in the processing hardware of the medical device to perform automated segmentation of the anatomical structures of valid points using random forest regression, fully connected dense layers, and convolutional neural network (CNN) architectures.

[0008] According to one implementation, the system and method include an evaluation engine that provides specific multi-step data manipulation of valid points for automated anatomical segmentation, continuity estimation, and gap prediction. For example, during the cardiac mapping phase, the evaluation engine can determine whether an ablation point is part of the right WACA or the left WACA (e.g., whether each WACA point is within the left ring surrounding the left pulmonary vein (PV) or the right ring surrounding the right PV), and classify the left and right WACA points into multiple (e.g., nine) anatomical structures of the PV (e.g., associating each ablation point with one of these anatomical structures). During the cardiac mapping phase, the evaluation engine can determine whether each valid point is good or correct, enabling the point to help healthcare professionals isolate these PVs. In determining good or correct valid points, the evaluation engine can use right WACA information, left WACA information, and anatomical structure classification to predict acute reconnection and secondary ablation locations.

[0009] For example, pulmonary vein isolation (PVI) can be performed using radiofrequency energy via an ablation catheter in a point-by-point WACA pattern (e.g., a WACA protocol), where the endpoint of the WACA protocol is complete pulmonary vein isolation. At the final ablation WACA point, the physician sequentially places a mapping catheter into each PV to determine if spontaneous PV reconnection has occurred. If pulmonary vein reconnection has not occurred, a large dose of intravenous adenosine is administered to expose any dormant conduction sites. Ablation can be performed at any reconnection site to achieve PVI. The assessment engine can attempt to notify the physician in advance after performing a WACA protocol at potential reconnection sites so that ablation of these sites can produce PVI. The assessment engine reduces the need for additional ablation in the second and third phases (e.g., after adenosine administration). Even with PV isolation, atrial fibrillation can recur after the patient is released from the first WACA treatment via subsequent ablation therapy. The assessment engine can prescribe the physician to reablate certain areas during the first WACA treatment (i.e., predict the location of the secondary ablation).

[0010] The assessment engine's technical effectiveness and beneficial effects include automated anatomical segmentation of ablation sites, continuity estimation, and estimation of potential long-term (secondary ablation) reconnection sites to provide improved imaging data of cardiac tissue. This improved imaging data reduces and / or eliminates the potential presence of gaps between WACA ablation sites and in the resulting ablation line, as well as the anatomical dependence of WACA. Therefore, the improved imaging data can be used to effectively treat various cardiovascular diseases by reducing or eliminating these gaps, which could lead to PV reconnection and recurrent arrhythmias. The assessment engine can be applied in practice, but not limited to, ablation-ultrasound techniques (e.g., atrial fibrillation ablation and WACA), lesion planning and diagnosis, and the evaluation and diagnosis of magnetic resonance imaging (MRI) for addressing one or more disease states, such as atrial fibrillation, atrial flutter, general electrophysiology, arrhythmias, ventricular fibrillation, and ventricular tachycardia.

[0011] Figure 1 An illustration shows an exemplary system 100 (e.g., a medical device) that can implement one or more features of the subject matter of this disclosure. All or part of system 100 can be used to collect information for an imaging dataset (e.g., a training dataset), and / or all or part of system 100 can be used to implement the machine learning algorithms and evaluation engines described herein.

[0012] System 100 may include components, such as catheter 105, configured to image organs in vivo using intravascular ultrasound and / or MRI catheter insertion. Catheter 105 may also be further configured to acquire biometric data, including electrical signals from the heart (e.g., data at multiple points, such as WACA ablation points). While catheter 105 is shown as a pointed catheter, it should be understood that catheters of any shape, including one or more elements (e.g., electrodes, tracking coils, piezoelectric transducers, etc.), may be used to implement embodiments disclosed herein.

[0013] System 100 includes a probe 110 having an axis that can be navigated by a physician or medical professional 115 to a body part (such as the heart 120) of a patient 125 lying on a bed (or table) 130. Multiple probes may be provided depending on the implementation. However, for simplicity, a single probe 110 is described herein. It should be understood, however, that probe 110 may represent multiple probes.

[0014] Exemplary system 100 can be used to detect, diagnose, and treat cardiac conditions (e.g., using an assessment engine). Cardiac conditions, such as arrhythmias (specifically atrial fibrillation), have been common and dangerous medical conditions, especially among older populations. In a patient with a normal sinus rhythm (e.g., patient 125), the heart (e.g., heart 120), comprising the atria, ventricles, and excitatory conduction tissues, is electrically stimulated to beat in a synchronized, analogous manner (note that this electrical stimulation can be detected as intracardiac signals, etc.).

[0015] In patients with arrhythmias (e.g., patient 125), abnormal areas of cardiac tissue do not follow the synchronous beating cycle associated with normal conduction tissue as in patients with normal sinus rhythm. Instead, the abnormal areas of cardiac tissue conduct abnormally to adjacent tissues, thus disrupting the cardiac cycle into an asynchronous rhythm (note that this asynchronous rhythm can also be detected as an intracardiac signal). Such aberrant conduction is previously known to occur in various regions of the heart (e.g., heart 120), such as the sinoatrial (SA) node region, the conduction pathway along the atrioventricular (AV) node, or in the myocardial tissue that forms the walls of the ventricles and atria.

[0016] Furthermore, arrhythmias, including atrial arrhythmias, can be multi-wave reentrant, characterized by multiple asynchronous loops of electrical impulses dispersed around the atrial chambers and typically self-propagating (e.g., another example of intracardiac signals). Alternatively, or in addition to multi-wave reentrant arrhythmias, arrhythmias can also have a focal source, such as when an isolated area of ​​tissue within the atrium beats spontaneously in a rapid, repetitive manner (e.g., another example of intracardiac signals). Ventricular tachycardia (V-tach or VT) is a tachycardia or rapid rhythm originating in a single ventricle. This is a potentially life-threatening arrhythmia because it can lead to ventricular fibrillation and sudden cardiac death.

[0017] Atrial fibrillation (AF) is a type of arrhythmia that occurs when normal electrical impulses generated by the sinoatrial node (e.g., another example of intracardiac signaling) are overwhelmed by disordered electrical impulses originating from the atria and pulmonary veins (e.g., signal interference), which cause irregular impulses to be transmitted to the ventricles. This results in an irregular heartbeat that can last from minutes to weeks, or even years. AF is typically a chronic condition that slightly increases the risk of death, usually caused by stroke. First-line treatment for AF is medication to slow the heart rate or restore a normal rhythm. Additionally, people with AF are often given anticoagulants to protect against their risk of stroke. The use of such anticoagulants carries the inherent risk of internal bleeding. For some patients, medication is insufficient; their AF is considered drug-resistant, meaning it cannot be treated with standard medical interventions. Synchronized cardioversion can also be used to restore AF to a normal rhythm. Alternatively, catheter ablation can be used to treat patients with AF.

[0018] Catheter ablation-based treatments can include mapping the electrical properties of cardiac tissue (particularly the endocardium and cardiac volume) and selectively ablating cardiac tissue by applying energy. Cardiac mapping (an example of cardiac imaging) includes creating mapping maps of electrical potentials propagating along cardiac tissue (e.g., voltage mapping) or mapping maps of arrival times to various tissue locations (e.g., local time activation (LAT) mapping). Cardiac mapping (e.g., cardiac mapping) can be used to detect localized cardiac tissue dysfunction. Ablation, such as cardiac mapping-based ablation, can stop or alter unwanted electrical signals propagating from one part of the heart to another.

[0019] The ablation process disrupts unwanted electrical pathways by creating a non-conductive ablation focus. Various forms of energy delivery for creating ablation focuses have been disclosed, including the use of microwave, laser, and more commonly radiofrequency energy to create conduction blocks along the cardiac tissue wall. In a two-step mapping-then-ablation procedure, electrical activity at various points in the heart is typically sensed and measured by inserting a catheter (e.g., catheter 105) containing one or more electrical sensors (e.g., at least one ablation electrode 134 of catheter 105) into the heart (e.g., heart 120) and acquiring data at multiple points. This data (e.g., WACA ablation points) is then used to select the endocardial target region to be ablated. Note that, due to the evaluation engine employed by the exemplary system 100 (e.g., a medical device), the data at multiple points (i.e., WACA ablation points) is manipulated into improved image data of the cardiac tissue, including its location within the right or left WACA, its classification into nine anatomical structures, its determination as good or correct, and the prediction of acute reconnection and secondary ablation locations. The improved image data may also include stability measurements (e.g., extracted from x, y, z localization during ablation) and ablation characteristics (e.g., power, impedance, impedance drop, stability, etc.).

[0020] As clinicians treat increasingly challenging conditions such as atrial fibrillation and ventricular tachycardia, cardiac ablation and other cardiac electrophysiological procedures become increasingly complex. Treatment of complex arrhythmias currently relies on the use of three-dimensional (3D) mapping systems to reconstruct the anatomy of the cardiac chambers of interest. In this regard, the evaluation engine employed in exemplary system 100 (e.g., a medical device) manipulates and evaluates data at said multiple points (e.g., WACA ablation points) to generate improved image data of cardiac tissue, enabling the generation of improved images, scans, and / or mappings along with predictions for the treatment of cardiac conditions.

[0021] For example, cardiologists rely on software such as CARTO, produced by BiosenseWebster, Inc. (Diamond Bar, Calif.). ® 3. A complex fragmented atrial electrocardiography (CFAE) module of the 3D mapping system to generate and analyze intracardiac electrograms (EGMs). An evaluation engine of the exemplary system 100 (e.g., a medical device) enhances this software to generate and analyze improved intracardiac images, scans, and / or mappings, enabling the identification of ablation points for the treatment of a range of cardiac conditions, including atrial fibrillation. The improved images, scans, and / or mappings supported by the evaluation engine provide multiple pieces of information relating to the electrophysiological characteristics of the in vivo organs (e.g., the heart and / or organ tissues, including scar tissue) representing the cardiac matrix (anatomy and function) of these challenging arrhythmias.

[0022] Cardiomyopathy with different etiologies (hypoxia, dilated (DCM), hypertrophic cardiomyopathy (HCM), arrhythmogenic right ventricular dysplasia (ARVD), left ventricular noncompaction (LVNC), etc.) has a recognizable matrix, characterized by a region of unhealthy tissue surrounded by normally functioning cardiomyocytes.

[0023] Abnormal tissue is typically characterized by low-voltage EGM. However, initial clinical experience in endocardial-epicardial mapping indicates that low-voltage regions are not always the sole arrhythmogenic mechanism present in such patients. In fact, low- or intermediate-voltage regions can exhibit fragmented and prolonged EGM activity during sinus rhythm, which corresponds to the critical isthmus identified during sustained and tissue ventricular arrhythmias, e.g., only in intolerable ventricular tachycardias. Furthermore, in many cases, fragmented and prolonged EGM activity is observed in regions showing normal or near-normal voltage amplitudes (>1–1.5 mV). While the latter regions can be assessed based on voltage amplitude, they cannot be considered normal based on intracardiac signals and thus represent the true arrhythmogenic matrix. 3D mapping enables the localization of the arrhythmogenic matrix on the endocardial and / or epicardial layers of the right / left ventricle, which can vary in distribution depending on the extent of the primary disease.

[0024] The matrix associated with these cardiac conditions is the presence of fragmented and elongated EGM in the endocardial and / or epicardial layers of the ventricular chambers (right and left). 3D mapping systems, such as CARTO... ® 3. It can locate the potential arrhythmogenic matrix of cardiomyopathy in abnormal EGM detection.

[0025] Electrode catheters (e.g., catheter 105) are used in medical practice. These catheters are used to stimulate and map electrical activity in the heart, and to ablate sites of abnormal electrical activity. In use, the electrode catheter is inserted into a major vein or artery, such as the femoral artery, and then guided to the cardiac chamber of interest. A typical ablation procedure involves inserting a catheter with at least one electrode at its distal end into the cardiac chamber. A reference electrode is provided, typically taped to the patient's skin, or alternatively, a second catheter positioned in or near the heart may be used to provide the reference electrode. Radiofrequency (RF) current is applied to the tip electrode of the ablation catheter, and the current flows through the surrounding medium (i.e., blood and tissue) to the reference electrode. The current distribution depends on the amount of contact between the electrode surface and the tissue, which has a higher conductivity than blood. Heating of the tissue occurs due to its resistance. The tissue is sufficiently heated to destroy cells in the cardiac tissue, resulting in the formation of a non-conductive ablation focus within the cardiac tissue. Heating of the electrode also occurs during this process due to conduction from the heated tissue to the electrode itself. If the electrode temperature becomes high enough, perhaps above 60 degrees Celsius, a thin, transparent coating of dehydrated hemoglobin can form on the electrode surface. If the temperature continues to rise, this dehydrated layer can become increasingly thick, causing blood to clot on the electrode surface. Because dehydrated biomaterials have a higher electrical resistance than endocardial tissue, the impedance to the flow of electrical energy into the tissue also increases. If the impedance increases sufficiently, an impedance rise occurs, and the catheter must be removed from the body and the tip electrode cleaned.

[0026] Treatment of cardiac conditions such as arrhythmias often requires detailed mapping of cardiac tissue, chambers, veins, arteries, and / or electrical pathways. For example, a prerequisite for successful catheter ablation is that the cause of the arrhythmia is accurately located within a cardiac chamber. Such localization can be accomplished via an electrophysiological study, during which potentials are spatially resolved using a mapping catheter introduced into the cardiac chamber. This electrophysiological study (so-called electroanatomical mapping) thus provides 3D mapping data that can be displayed on a monitor. In many cases, mapping and therapeutic functions (e.g., ablation) are provided by a single catheter or a group of catheters, allowing the mapping catheter to simultaneously function as a therapeutic (e.g., ablation) catheter. In this case, the evaluation engine can be directly stored and executed by catheter 105.

[0027] Mapping of cardiac regions (such as cardiac regions, tissues, veins, arteries, and / or electrical pathways of the heart (e.g., 120)) can lead to the identification of problem areas such as scar tissue, sources of arrhythmia (e.g., telodynamic sources), healthy areas, etc. Cardiac regions can be mapped so that a visual rendering of the mapped cardiac regions can be provided using a display, as further disclosed herein. Additionally, cardiac mapping (which is an example of cardiac imaging) can include mapping based on one or more modalities, such as, but not limited to, local activation time (LAT), electrical activity, topology, bipolar mapping, dominant frequency, or impedance. Data corresponding to multiple modalities can be captured using a catheter inserted into the patient's body, and data corresponding to multiple modalities can be provided simultaneously or at different times for rendering based on the corresponding settings and / or preferences of a medical professional.

[0028] Cardiac mapping can be achieved using one or more techniques. As an example of a first technique, cardiac mapping can be achieved by sensing the electrical properties of cardiac tissue at precise locations within the heart (e.g., LAT). The corresponding data can be acquired via one or more catheters advanced into the heart using catheters with electrical and position sensors at their distal ends. Specifically, for example, position and electrical activity can initially be measured at approximately 10 to approximately 20 points on the inner surface of the heart. These data points are typically sufficient to generate a preliminary reconstruction or mapping map of the cardiac surface of satisfactory quality. The preliminary map can be combined with data taken from additional points to produce a more comprehensive map of cardiac electrical activity. In clinical settings, it is not uncommon to accumulate data at 100 or more sites to generate a detailed and comprehensive mapping map of cardiac chamber electrical activity. The resulting detailed map can then serve as a basis for determining therapeutic actions, such as tissue ablation, to alter the propagation of cardiac electrical activity and restore normal heart rhythm.

[0029] return Figure 1 To achieve the indicated cardiac imaging, a medical professional 115 may insert the shaft 137 through the sheath 136 while manipulating the distal end of the shaft 137 using a manipulator 138 near the proximal end of the catheter 105 and / or by deflection from the sheath 136. As shown in illustration 140, the catheter 105 may be fitted at the distal end of the shaft 137. The catheter 105 may be inserted through the sheath 136 in a collapsed state and then deployed within the heart 120. As further described herein, the catheter 105 may include at least one ablation electrode 134 and a catheter needle.

[0030] According to one embodiment, catheter 105 may be configured to ablate tissue regions of the heart chambers of heart 120. Illustration 150 shows catheter 105 within the heart chambers of heart 120 in an enlarged view. As shown, catheter 105 may include at least one ablation electrode 134 coupled to the body of the catheter. According to other embodiments, multiple elements may be connected via an elongation forming the shape of catheter 105. One or more other elements (not shown) may be provided, which may be any element configured to ablate or obtain biometric data, and may be an electrode, a transducer, or one or more other elements.

[0031] According to the embodiments disclosed herein, an ablation electrode, such as at least one ablation electrode 134, can be configured to deliver energy to a tissue region of an organ in the body, such as the heart 120. The energy can be thermal and can cause damage to the tissue region by starting from the surface of the tissue region and extending into the thickness of the tissue region.

[0032] According to the embodiments disclosed herein, biometric data may include one or more of the following: LAT, electrical activity, topology, bipolar mapping, dominant frequency, impedance, etc. LAT can be a time point corresponding to a threshold activity of local excitation calculated based on a normalized initial starting point. Electrical activity can be any applicable electrical signal that can be measured based on one or more thresholds and can be sensed and / or amplified based on signal-to-noise ratio and / or other filters. Topology can correspond to the physical structure of a body part or a portion of a body part, and can correspond to variations in the physical structure relative to different parts of the body part or relative to different body parts. Dominant frequency can be a frequency or frequency range that is prevalent in a part of a body part and can differ in different parts of the same body part. For example, the dominant frequency of the PV of the heart can be different from the dominant frequency of the right atrium of the same heart. Impedance can be a resistance measurement at a given region of a body part.

[0033] like Figure 1 As shown, probe 110 and conduit 105 can be connected to console 160. Console 160 may include computing device 161 employing machine learning algorithms and evaluation engines as described herein. According to one embodiment, console 160 and / or computing device 161 include at least a processor and memory, wherein the processor executes computer instructions relating to the machine learning algorithms and evaluation engines described herein, and the memory stores instructions for execution by the processor.

[0034] The computing device 161 may be any computing device including software and / or hardware, such as a general-purpose computer, having suitable front-end and interface circuitry 162 for transmitting and receiving signals to and from the catheter 105, and other components for controlling the system 100. The computing device 161 may include a real-time noise reduction circuitry system typically configured as a field-programmable gate array (FPGA), followed by an analog-to-digital (A / D) electrocardiogram (ECG) or electrocardiogram (ECG) or electromyography (EMG) signal conversion integrated circuit. The computing device 161 may pass signals from the A / D ECG or EMG circuitry to another processor and / or may be programmed to perform one or more functions disclosed herein. For example, the one or more functions may include receiving effective points corresponding to a patient's cardiac tissue, determining the anatomical classification of each effective point based on structural segmentation of the cardiac tissue, and providing the anatomical classification along with each of the plurality of effective points to support treatment of the cardiac tissue. The front-end and interface circuitry 162 includes an input / output (I / O) communication interface that enables the console 160 to receive signals from at least one ablation electrode 134 and / or transmit signals to at least one ablation electrode 134.

[0035] In some embodiments, computing device 161 may be further configured to receive biometric data, such as electrical activity, and determine whether a given tissue region is conductive. According to one embodiment, computing device 161 may be located external to console 160 and may be located, for example, in a catheter, an external device, a mobile device, a cloud-based device, or may be a standalone processor.

[0036] As described above, computing device 161 may include a general-purpose computer that can be software-programmed to perform the functions of the machine learning algorithms and evaluation engines described herein. The software may be downloaded electronically to the general-purpose computer, for example via a network, or alternatively or additionally disposed and / or stored on a non-transitory tangible medium such as magnetic storage, optical storage, or electronic storage (e.g., any suitable volatile and / or non-volatile memory, such as random access memory or hard disk drive). Figure 1 The exemplary configurations shown can be modified to implement the embodiments disclosed herein. The embodiments disclosed herein can be applied similarly using other system components and setups. Additionally, system 100 may include additional components such as elements for sensing electrical activity, wired or wireless connectors, processing and display devices, etc.

[0037] According to one embodiment, display 165 is connected to computing device 161. During the procedure, computing device 161 may facilitate the presentation of a body part rendering to a medical professional 115 on display 165 and store data representing the body part rendering in memory. In some embodiments, medical professional 115 may be able to manipulate the body part rendering using one or more input devices, such as a touchpad, mouse, keyboard, gesture recognition device, etc. For example, the input device may be used to change the position of catheter 105 so that the rendering is updated. In an alternative embodiment, display 165 may include a touchscreen that can be configured to accept input from medical professional 115 in addition to presenting the body part rendering. It should be noted that display 165 may be located in the same location or a remote location, such as a single hospital or within a single healthcare provider network. Additionally, system 100 may be part of a surgical system configured to obtain anatomical and electrical measurements of a patient's organ (such as heart 120) and perform cardiac ablation procedures. An example of such a surgical system is Carto, sold by Biosense Webster. ® system.

[0038] The console 160 can be connected via a cable to a surface electrode, which may include an adhesive skin patch attached to the patient 125. A processor, in conjunction with a current tracking module, determines the orientation coordinates of the catheter 105 within a body part of the patient 125 (e.g., the heart 120). The position coordinates may be based on impedance or electromagnetic field measured between the surface electrode and other electromagnetic components of the electrode or catheter 105 (e.g., at least one ablation electrode 134). Additionally or alternatively, a positioning pad may be located on the surface of the bed 130 and may be detachable from the bed 130.

[0039] System 100 may also, and optionally, use ultrasound, computed tomography (CT), MRI, or other medical imaging techniques known in the art to obtain biometric data, such as anatomical measurements of the heart 120. System 100 may use catheters or other sensors that measure the electrical properties of the heart 120 to obtain ECG or electrical measurements. Biometric data, including anatomical and electrical measurements, can then be stored in a non-transitory tangible medium in console 160. Biometric data can be transferred from the non-transitory tangible medium to computing device 161. Alternatively or otherwise, biometric data can be transferred to a server, which may be local or remote, using a network as further described herein.

[0040] According to one or more embodiments, a catheter containing a position sensor can be used to determine the trajectory of points on the surface of the heart. These trajectories can be used to infer kinematic properties, such as the contractility of tissues. When trajectory information is sampled at a sufficient number of points in the heart 120, a mapping depicting such kinematic properties can be constructed.

[0041] Typically, a catheter 105 containing an electrical sensor at or near its distal end (at least one ablation electrode 134) is advanced to a point in the heart 120, where the sensor contacts the tissue and acquires data at that point, thereby measuring the electrical activity at that point in the heart 120. A drawback of mapping cardiac chambers using a catheter 105 containing only a single distal electrode is the time-consuming process of acquiring data point-by-point at the necessary number of points required for a detailed map of the overall chambers. Therefore, multi-electrode catheters have been developed to simultaneously measure electrical activity at multiple points within the cardiac chambers.

[0042] Multi-electrode catheters can be implemented using any suitable shape, such as linear catheters with multiple electrodes, balloon catheters including electrodes distributed on multiple ridges shaping the balloon, lasso or loop catheters with multiple electrodes, or any other suitable shape (e.g., the Thermocool SmartTouch perfusion tip CF sensing ablation catheter). Linear catheters can be fully or partially flexible, allowing them to twist, bend, or otherwise change shape based on received signals and / or based on external forces (e.g., cardiac tissue) applied to the linear catheter. Balloon catheters can be designed such that their electrodes remain in close contact with the endocardial surface when deployed into the patient. For example, a balloon catheter can be inserted into a lumen, such as a PV. The balloon catheter can be inserted into the PV in a contracted state such that the balloon catheter does not occupy its maximum volume when inserted into the PV. The balloon catheter can inflate within the PV such that the electrodes on the balloon catheter contact the entire circular segment of the PV. Such contact with the entire circular portion of the PV or any other lumen enables effective mapping and / or ablation.

[0043] According to one example, a multi-electrode catheter can be advanced into a chamber of the heart at 120°. Anterior and posterior fluorescein (AP) and lateral fluorescein maps are obtained to establish the position and orientation of each electrode. The electrical activity map (EGM) relative to a time reference (e.g., starting from the P wave in the sinus rhythm from a surface ECG) can be recorded by each of the electrodes in contact with the cardiac surface. As further disclosed herein, the system can distinguish which electrodes record electrical activity from those that do not, due to their less close proximity to the endocardial wall. After recording the initial EGM, the catheter can be repositioned, and fluorescein maps and EGM can be recorded again. An electrogram can then be constructed iteratively based on the above process.

[0044] According to one example, cardiac mapping can be generated based on the detection of the intracardiac electrical potential field. Non-contact techniques for simultaneously acquiring large amounts of cardiac electrical information can be implemented. For example, a catheter with a distal end portion can be provided with a series of sensor electrodes distributed on its surface and connected to an insulating electrical conductor for connection to a signal sensing and processing device. The size and shape of the end portion allow the electrodes to be substantially spaced apart from the walls of the heart chambers. The intracardiac electrical potential field can be detected during a single heartbeat. According to one example, the sensor electrodes can be distributed on a series of circumferences located in planes spaced apart from each other. These planes can be perpendicular to the long axis of the end portion of the catheter. At least two additional electrodes can be provided adjacent to each other at the ends of the long axis of the end portion. As a more specific example, the catheter can include four circumferences, with eight electrodes spaced equally angularly apart on each circumference. Thus, in this specific embodiment, the catheter can include at least 34 electrodes (32 circumferential electrodes and 2 end electrodes).

[0045] According to another example, an electrophysiological cardiac mapping system and technique based on a non-contact and non-expanding multi-electrode catheter can be realized. EGM can be obtained via a catheter having multiple electrodes (e.g., 42 to 122 electrodes). According to this specific implementation, knowledge of the relative geometry of the probe and the endocardium can be obtained, for example, through independent imaging modalities (such as transesophageal echocardiography). After independent imaging, the non-contact electrodes can be used to measure the cardiac surface potential and construct a mapping map from it. The technique may include the following steps (after the independent imaging step): (a) measuring the potential using multiple electrodes disposed on a probe positioned on the heart 120; (b) determining the geometric relationship between the probe surface and the endocardial surface; (c) generating a coefficient matrix representing the geometric relationship between the probe surface and the endocardial surface; and (d) determining the endocardial potential based on the electrode potentials and the coefficient matrix.

[0046] According to another example, techniques and devices for mapping the potential distribution of cardiac chambers are available. An intracardiac multi-electrode mapping catheter assembly can be inserted into a patient's heart 120. The mapping catheter assembly may include a multi-electrode array with an integral reference electrode, or preferably, a mating reference catheter. The electrodes may be deployed in the form of a substantially spherical array. The electrode array may be spatially referenced to points on the endocardial surface via the reference electrode or via a reference catheter in contact with the endocardial surface. A preferred electrode array catheter may carry multiple individual electrode sites (e.g., at least 24). Furthermore, this exemplary technique is achieved by understanding the location of each electrode site in the array and understanding the cardiac geometry. These locations are preferably determined using techniques of impedance plethysmography.

[0047] According to another example, the cardiac mapping catheter assembly may include an electrode array defining multiple electrode sites. The mapping catheter assembly may also include a lumen to receive a reference catheter with a distal electrode assembly that can be used to probe the heart wall. The mapping catheter may include a braid of insulated wire (e.g., having 24 to 64 wires in the braid), and each wire can be used to form an electrode site. The catheter can be easily positioned in the heart 120 for obtaining electrical activity information from a first set of non-contact electrode sites and / or a second set of contact electrode sites.

[0048] According to another example, another catheter can be implemented for mapping electrophysiological activity within the heart. The catheter body may include a distal end adapted to deliver stimulation pulses for cardiac pacing or an ablation electrode for ablating tissue in contact with said end. The catheter may also include at least one pair of orthogonal electrodes to generate a differential signal indicative of local cardiac electrical activity adjacent to said orthogonal electrode.

[0049] According to another example, a process for measuring electrophysiological data in a heart chamber can be implemented. The method may partially include positioning a set of active and passive electrodes in the heart 120, supplying current to the active electrodes to generate an electric field in the heart chamber, and measuring the electric field at the site of the passive electrodes. The passive electrodes are contained in an array positioned on an inflatable balloon of a balloon catheter. In a preferred embodiment, the array reportedly has 60 to 64 electrodes.

[0050] According to another example, cardiac mapping can be achieved using one or more ultrasound transducers. The ultrasound transducer can be inserted into a patient's heart 120 and can collect multiple ultrasound slices (e.g., two-dimensional or three-dimensional slices) at various locations and orientations within the heart 120. The location and orientation of a given ultrasound transducer can be known, and the collected ultrasound slices can be stored so that they can be displayed at a later time. One or more ultrasound slices corresponding to the location of a probe (e.g., a treatment catheter) can be displayed after a period of time, and the probe can be overlaid on one or more ultrasound slices.

[0051] According to other examples, body patches and / or surface electrodes may be positioned on or near the patient's body. A catheter having one or more electrodes may be positioned within the patient's body (e.g., within the patient's heart 120), and the location of this catheter may be determined by the system based on signals transmitted and received between the one or more electrodes of the catheter and the body patch and / or surface electrodes. Additionally, the catheter electrodes may sense biometric data (e.g., LAT values) from within the patient's body (e.g., within the heart 120). This biometric data may be correlated with the determined location of the catheter, enabling the display of a rendering of the patient's body part (e.g., the heart 120) and the display of biometric data overlaid on the body shape.

[0052] Figure 2 A block diagram of an exemplary system 200 for remotely monitoring and transmitting biometric data (i.e., patient biometrics, patient data, or patient biometric data) is shown. Figure 2 In the example shown, system 200 includes a monitoring and processing device 202 (i.e., a patient data monitoring and processing device) associated with patient 204, a local computing device 206, a remote computing system 208, a first network 210, and a second network 211. According to one or more embodiments, the monitoring and processing device 202 may be... Figure 1 Example of catheter 105, patient 204 could be Figure 1 The example of patient 125, and the local computing device 206 can be Figure 1 Example of console 160.

[0053] Monitoring and processing device 202 includes a patient biometric sensor 212, a processor 214, a user input (UI) sensor 216, a memory 218, and a transmitter-receiver (i.e., transceiver) 222. In operation, monitoring and processing device 202 acquires biometric data of patient 204 (e.g., electrical signals, blood pressure, temperature, blood glucose levels, or other biometric data), and / or receives from one or more other patient biometric monitoring and processing devices at least a portion of biometric data representing any acquired patient biometrics and additional information associated with the acquired patient biometrics. The additional information may be, for example, diagnostic information and / or additional information obtained from an add-on device such as a wearable device. Monitoring and processing device 202 may employ the machine learning algorithms and evaluation engines described herein to process the data, including the acquired biometric data and any biometric data received from one or more other patient biometric monitoring and processing devices.

[0054] Monitoring and processing device 202 can continuously or periodically monitor, store, process, and transmit any number of various patient biometrics (e.g., acquired biometric data) via network 210. Examples of patient biometrics, as described herein, include electrical signals (e.g., ECG signals and brain biometrics), blood pressure data, blood glucose data, and temperature data. Patient biometrics can be monitored and transmitted for the treatment of any number of various diseases, such as cardiovascular diseases (e.g., arrhythmias, cardiomyopathy, and coronary artery disease) and autoimmune diseases (e.g., type I and type II diabetes).

[0055] The patient biometric sensor 212 may include, for example, one or more transducers configured to convert one or more environmental conditions into electrical signals, thereby acquiring different types of biometric data. For example, the patient biometric sensor 212 may include one or more electrodes, temperature sensors (e.g., thermocouples), blood pressure sensors, blood glucose sensors, blood oxygen sensors, pH sensors, accelerometers, and microphones configured to acquire electrical signals (e.g., heart signals, brain signals, or other bioelectrical signals).

[0056] As described in more detail herein, the monitoring and processing device 202 implements machine learning algorithms and an evaluation engine to receive effective points corresponding to a patient's cardiac tissue, determine the anatomical classification of each effective point based on structural segmentation of the cardiac tissue, and provide the anatomical classification along with each of the plurality of effective points to support treatment of the cardiac tissue. The monitoring and processing device 202 implements machine learning algorithms and an evaluation engine to generate improved image data of the cardiac tissue, enabling the generation of improved images, scans, and / or mappings along with predictions for the treatment of cardiac conditions.

[0057] In another example, the monitoring and processing device 202 could be for monitoring the heart (e.g., Figure 1 An ECG monitor that receives ECG signals from the heart (120). In this regard, the patient biometric sensor 212 of the ECG monitor may include one or more electrodes for acquiring ECG signals (e.g., ...). Figure 1 (The electrode in catheter 105). ECG signals can be used to treat various cardiovascular diseases.

[0058] In another example, the monitoring and processing device 202 could be a continuous glucose monitor (CGM) for continuously monitoring a patient's blood glucose levels for ongoing treatment of various conditions, such as type 1 and type 2 diabetes. In this regard, the CGM's patient biometric sensor 212 could include subcutaneously placed electrodes (e.g., Figure 1 The catheter 105 contains an electrode that monitors blood glucose levels from the patient's interstitial fluid. The CGM can be, for example, a component of a closed-loop system where blood glucose data is sent to an insulin pump to calculate insulin delivery without user intervention.

[0059] Processor 214 may be configured to receive, process, and manage biometric data acquired by patient biometric sensor 212, and transmit the biometric data to memory 218 via transceiver 222 for storage and / or across network 210. Data from one or more other monitoring and processing devices 202 may also be received by processor 214 via transceiver 222, as described in more detail herein. As described in more detail herein, processor 214 may be configured to selectively respond to different tap patterns (e.g., single or double taps) received from UI sensor 216 (e.g., a capacitive sensor therein), enabling different tasks of the patch (e.g., data acquisition, storage, or transmission) to be activated based on the detected pattern. In some embodiments, processor 214 may generate audible feedback relative to the detected gesture.

[0060] UI sensor 216 includes, for example, a piezoelectric or capacitive sensor configured to receive user input such as a tap or touch. For example, in response to a patient 204 tapping or touching the surface of monitoring and processing device 202, UI sensor 216 can be controlled to achieve capacitive coupling. Gesture recognition can be achieved via any of a variety of capacitance types, such as resistive capacitance, surface capacitance, projected capacitance, surface acoustic waves, piezoelectric, and infrared touch. The capacitive sensor can be positioned over a small area or along the length of a surface, such that a tap or touch on the surface activates the monitoring device.

[0061] Memory 218 is any non-transitory tangible medium, such as magnetic memory, optical memory, or electronic memory (e.g., any suitable volatile and / or non-volatile memory, such as random access memory or hard disk drive).

[0062] Transceiver 222 may include a separate transmitter and a separate receiver. Alternatively, transceiver 222 may include a transmitter and receiver integrated into a single device.

[0063] According to one embodiment, the monitoring and processing device 202 may be a device located within the patient 204 (e.g., subcutaneously implantable). The monitoring and processing device 202 may be inserted into the patient 204 via any applicable means, including oral injection, surgical insertion via vein or artery, endoscopic procedure, or laparoscopic procedure.

[0064] According to one embodiment, the monitoring and processing device 202 may be a device located outside the patient 204. For example, as described in more detail herein, the monitoring and processing device 202 may include an attachable patch (e.g., which is attached to the patient's skin). The monitoring and processing device 202 may also include a catheter, probe, blood pressure cuff, scale, bracelet or smartwatch biometric tracker, glucose monitor, continuous positive airway pressure (CPAP) machine, or virtually any device that can provide input related to the patient's health or biometrics, and has one or more electrodes.

[0065] According to one implementation, the monitoring and processing device 202 may include components inside the patient and components outside the patient.

[0066] Although Figure 2 A single monitoring and processing device 202 is shown, but the exemplary system may include multiple patient biometric monitoring and processing devices. For example, monitoring and processing device 202 may communicate with one or more other patient biometric monitoring and processing devices. In addition, or alternatively, one or more other patient biometric monitoring and processing devices may communicate with network 210 and other components of system 200.

[0067] The local computing device 206 and / or the remote computing system 208, together with the monitoring and processing device 202, can be any combination of software and / or hardware that stores, executes, and implements machine learning algorithms and evaluation engines and their functions, either individually or collectively. Furthermore, the local computing device 206 and / or the remote computing system 208, together with the monitoring and processing device 202, can be an electronic computer framework, including and / or employing any number and combination of computing devices and networks utilizing various communication technologies, as described herein. The local computing device 206 and / or the remote computing system 208, together with the monitoring and processing device 202, can be easily scaled, expanded, and modularized, with the ability to change for different services or reconfigure some features independently of other functions.

[0068] According to one embodiment, the local computing device 206 and the remote computing system 208, together with the monitoring and processing device 202, include at least a processor and a memory, wherein the processor executes computer instructions concerning machine learning algorithms and evaluation engines, and the memory stores these instructions for the processor to execute.

[0069] The local computing device 206 of system 200 communicates with the monitoring and processing device 202 and can be configured to act as a gateway to the remote computing system 208 via a second network 211. For example, the local computing device 206 may be a smartphone, smartwatch, tablet, or other portable smart device configured to communicate with other devices via network 211. Alternatively, the local computing device 206 may be a fixed or standalone device, such as a fixed base station including, for example, modem and / or router capabilities, a desktop or laptop computer using an executable program to transmit information between the processing device 202 and the remote computing system 208 via the radio module of a PC, or a USB dongle. Biometric data can be transmitted between the local computing device 206 and the monitoring and processing device 202 via a short-range wireless network 210, such as a local area network (LAN) (e.g., a personal area network (PAN)), using short-range wireless technology standards (e.g., Bluetooth, Wi-Fi, ZigBee, Z-wave, and other short-range wireless standards). In some implementations, the local computing device 206 may also be configured to display the acquired patient electrical signals and information associated with the acquired patient electrical signals, as described in more detail herein.

[0070] In some implementations, the remote computing system 208 may be configured to receive at least one of monitored patient biometrics and patient-associated information via a network 211, which is a remote network. For example, if the local computing device 206 is a mobile phone, the network 211 may be a wireless cellular network, and information may be transmitted between the local computing device 206 and the remote computing system 208 via wireless technology standards such as any of the wireless technologies described above. As described in more detail herein, the remote computing system 208 may be configured to provide (e.g., visually displayed and / or audibly provided) patient biometrics and related information to healthcare professionals, physicians, or nurses.

[0071] exist Figure 2 In this context, network 210 is an example of a near-field network (e.g., a local area network (LAN) or a personal area network (PAN)). Information can be transmitted between monitoring and processing device 202 and local computing device 206 via near-field network 210 using any of a variety of near-field wireless communication protocols such as Bluetooth, Wi-Fi, Zigbee, Z-Wave, Near Field Communication (NFC), Ultraband, Zigbee, or Infrared (IR)).

[0072] Network 211 can be a wired network, a wireless network, or a network comprising one or more wired and wireless networks, such as an intranet, local area network (LAN), wide area network (WAN), metropolitan area network (MAN), direct connection or a series of connections, cellular telephone network, or any other network or medium capable of facilitating communication between local computing device 206 and remote computing system 208. Information can be transmitted via network 211 using any of a variety of remote wireless communication protocols (e.g., TCP / IP, HTTP, 3G, 4G / LTE, or 5G / new radio). Wired connections can be implemented using Ethernet, Universal Serial Bus (USB), RJ-11, or any other wired connection known in the art. Wireless connections can be implemented using Wi-Fi, WiMAX and Bluetooth, infrared, cellular networks, satellite, or any other wireless connection method. Additionally, several networks can operate independently or communicate with each other to facilitate communication within network 211. In some cases, remote computing system 208 can be implemented as a physical server on network 211. In other cases, remote computing system 208 can be implemented as a public cloud computing provider (e.g., Amazon Web Services (AWS)) on network 211. ® () virtual server.

[0073] Figure 3 A graphical depiction of an artificial intelligence system 300 according to one or more embodiments is shown. The artificial intelligence system 300 includes data 310, machine 320, model 330, multiple results 340, and underlying hardware 350. Figure 4 It shows in Figure 3 Method 400 is executed in the artificial intelligence system. For ease of understanding, refer to... Figure 2 right Figure 3 and Figure 4 Describe it.

[0074] Typically, the artificial intelligence system 300 trains the machine 320 using data 310 (e.g., Figure 2 The local computing device 206 simultaneously constructs a model 330 to achieve multiple results 340 (predictable) to operate the method 400. In this configuration, the artificial intelligence system 300 can operate relative to the hardware 350 (e.g., Figure 2 The monitoring and processing device 202 operates to train the machine 320, build a model 330, and use algorithms to predict results. These algorithms can be used to solve the trained model 330 and predict results 340 associated with the hardware 350. These algorithms can generally be categorized into classification, regression, and clustering algorithms.

[0075] At box 410, method 400 includes collecting data 310 from hardware 350. Machine 320 acts as a controller or data collection function associated with and / or with hardware 350. Data 310 (e.g., may originate from...) Figure 2 The biometric data from the monitoring and processing device 202 may be associated with the hardware 350. For example, data 310 may be data being generated or output data associated with the hardware 350. The data 310 may also include data currently collected from the hardware 350, historical data, or other data. For example, the data 310 may include measurements taken during a surgical procedure and may be associated with the outcome of the surgical procedure. For example, the temperature of the heart (e.g., the heart of patient 204) may be collected and associated with the outcome of a cardiac procedure.

[0076] At box 420, method 400 includes training machine 320, such as a machine relative to hardware 350. This training may include analysis and correlation of data 310 collected in box 410. For example, in the case of the heart, the temperature and outcome data 310 may be trained to determine whether there is a correlation or association between the temperature of the heart (e.g., the heart of patient 204) and the outcome during a cardiac procedure.

[0077] At box 430, method 400 includes building a model 330 on data 310 associated with hardware 350. Building the model 330 may include physical hardware or software modeling, algorithmic modeling, etc. This modeling may attempt to represent the collected and trained data 310. According to one embodiment, model 330 may be configured to model the operation of hardware 350 and the data 310 collected from hardware 350 in order to predict the results achieved by hardware 350. According to one or more embodiments, model 330 with respect to the evaluation engine receives valid points corresponding to a patient's cardiac tissue, determines the anatomical classification of each valid point based on the structural segmentation of the cardiac tissue, and provides the anatomical classification along with each of the plurality of valid points to support the treatment of the cardiac tissue.

[0078] At box 440, method 400 includes predicting a result 340 of model 330 associated with hardware 350. Such prediction of multiple results 340 may be based on a trained model 330. For example, to enhance understanding of this disclosure, in the case of the heart, a positive result from a cardiac procedure is produced if the temperature during the procedure is between 36.5 degrees Celsius and 37.89 degrees Celsius (i.e., 97.7 degrees Fahrenheit and 100.2 degrees Fahrenheit), which can be predicted in a given procedure based on the heart temperature during the cardiac procedure. Therefore, using the predicted result 340, hardware 350 can be configured to provide a certain desired result 340 from hardware 350.

[0079] Figure 5A block diagram of method 500 according to one or more embodiments is shown. According to one embodiment, method 500 is implemented through an evaluation engine. Any combination of software and / or hardware (e.g., local computing device 206 and remote computing system 208 together with monitoring and processing device 202) may be stored, executed, and implemented individually or jointly as the evaluation engine and its functions.

[0080] Generally, the evaluation engine provides automated anatomical segmentation, continuity estimation, and gap prediction for effective points to provide improved imaging data of cardiac tissue. The evaluation engine provides improved imaging data of cardiac tissue to support, guide, and recommend to physicians regarding the overall effectiveness of ablation procedures. Anatomical segmentation is the evaluation engine's ability to determine which segment of the left and right pulmonary veins each effective point is located in (e.g., left and right WACA detection and classification / segmentation of WACA points to nine anatomical structures). Depending on one or more implementations, other combinations of structures are envisioned regarding or replacing the nine anatomical structures, such as the left WACA, right WACA, orifice PVI, top line, left carina, right carina, posterior line, inferior line, mitral isthmus line, anterior line, and at least one of the inferior vena cava-tricuspid isthmus and superior vena cava isolation. Continuity estimation is the evaluation engine's ability to determine indirect contacts between two separate rings surrounding the left and right PVs and between these two separate rings and structural elements outside the left and right pulmonary veins. For example, a physician may wish to deliver continuous ablation foci where the center-to-center distance between two ablation sites is ≤6 mm. The evaluation engine investigates the effectiveness of each ablation site and estimates its size and depth to determine if it is sufficient. Therefore, continuity can be assessed by the evaluation engine in a local sense, i.e., the ablation sites between two ablation sites are effective. The evaluation engine also operates in a global sense, i.e., testing all ablation sites in the left (or right) WACA and estimating the likelihood of identifying potential reconnection. Gap prediction is the evaluation engine's ability to determine whether the space between effective sites is suitable for PV reconnection. Depending on one or more implementations, the evaluation engine can automatically classify / segment all ablation sites, enabling automatic detection of left and right isthmic or bulge ablation lines.

[0081] Method 500 begins at box 510, where the evaluation engine constructs a dataset comprising annotated anatomical structures of cardiac tissue (e.g., the human heart), all ablation points with their properties (e.g., force, force over time, impedance, impedance drop, duration, x, y, z position), and intracardiac ECGs (optional input to all algorithms). The annotated anatomical structures may include 3D data files depicting the human heart and validated effective points (e.g., data used to classify anatomical structures includes the x, y, z positions of the ablation points; mesh files and 3D visualizations of actual anatomical structures, such as the atria; and ablation properties that can be utilized using intracardiac ECG properties around the ablation points, if present). Depending on one or more implementations, each ablation type may be described by annotations such as: potential secondary ablation location, potential acute reconnection location, and whether it is a valid ablation point (e.g., a yes / no decision for each point).

[0082] According to one or more implementations, the annotated anatomy is initially constructed from training data built from manual continuity estimates and annotations of valid points generated during the cardiac mapping phase. Manual continuity estimates may be ablation points added after the cardiac mapping phase. Manual annotations may be markings performed by a healthcare professional. According to one or more implementations, the healthcare professional may mark the location and / or ablation type. It should be noted that ablation types may include acute reconnection points (e.g., after pacing, a physician identifies a reconnection site and adds an ablation point to isolate the vein), long-term reconnection (secondary ablation) ablation points (e.g., long after the case has ended, the patient has atrial fibrillation and the physician decides to perform another ablation procedure), and valid ablation.

[0083] At box 520, the assessment engine receives the case. This case can be received in real-time (or retrospectively) during the cardiac mapping phase of WACA treatment. The case includes valid points mapping the cardiac tissue, with the valid points forming two separate rings around the left and right PVs. This case is assessed by the assessment engine. It should be noted that, for example, tools can be provided to assist the assessment engine in retrospective analysis of physician decisions, thereby improving its work or that of its colleagues.

[0084] At box 530, the evaluation engine determines the right WACA and left WACA positions for each valid point in the received cases. For example, a sub-algorithm of the evaluation engine is used to automatically compare the positional information of the valid points with dimensional information along the axis (e.g., using an X-axis with a first range for the left position and a second range for the right position). The valid points are then segmented based on this comparison.

[0085] At box 540, the evaluation engine determines the anatomical classification for each valid point in the received cases (e.g., based on manual annotation of the training data, using the dataset from box 510; segmenting / grouping similar ablation points using the same anatomical code and associating them with the same anatomical structure). Note that the WACA anatomical structure code is as further described in this paper.

[0086] At box 550, the evaluation engine estimates the continuity of two separate rings around the left and right PVs. The output of this estimate can include the probability of continuity for each valid point. Depending on one or more implementations, each valid point is represented by 0 or 1, where 0 represents a “bad” ablation point and 1 represents a “good” ablation point. Additionally, the distance from each valid point to the next and previous ablations within the rings can aid in the “bad / good” determination.

[0087] At box 560, the evaluation engine generates improved image data of the mapped cardiac tissue (e.g., by incorporating the estimate of box 550 and the determination of boxes 530 and 540). This improved image data can then be used to predict acute reconnection and secondary ablation locations, enabling appropriate actions to be taken in real time during the ablation phase (by a physician or medical professional).

[0088] According to one or more implementations, the evaluation engine uses the training dataset to automatically generate annotated estimates and annotations on anatomical structures, allowing machine learning data to be created and added to the dataset. The machine learning data can comprise the majority of the dataset of the training data, and labeled data (e.g., labeled ablation types and / or anatomical structure types) based on feedback from medical experts can be added to the dataset.

[0089] Figure 6A An example of an autoencoder architecture 600 is shown, and Figure 6B A block diagram of method 601 executed in autoencoder architecture 600 is shown. Autoencoder architecture 600 operates to support the implementation of the machine learning algorithms and evaluation engines described herein. Autoencoder architecture 600 can be implemented in hardware such as machine 320 (e.g., Figure 2 The local computing device 206) and / or hardware 350 (e.g., Figure 2 The monitoring and processing device 202 is implemented therein. Modules 610, 630, and 650 of the autoencoder 600 collectively operate as a neural network performing the encoding portion of the autoencoder 600. Modules 750, 670, and 610 of the autoencoder 600 collectively operate as a neural network performing the decoding portion of the autoencoder 600. A neural network is a network or circuit of neurons, or in the modern sense, an artificial neural network (ANN) composed of artificial neurons or nodes.

[0090] For example, an ANN involves networks of simple processing elements (artificial neurons) that can exhibit complex global behavior determined by the connections between these processing elements and their parameters. These connections in a network or circuit of neurons are modeled as weights. Positive weights reflect excitatory connections, while negative values ​​represent inhibitory connections. The input is modified by the weights and summed using a linear combination. Activation functions control the amplitude of the output. For example, an acceptable output range is typically between 0 and 1, or it could be between -1 and 1.

[0091] In most cases, ANNs are adaptive systems that change their structure based on information flowing through the network's external or internal systems. In more practical terms, neural networks are nonlinear statistical data modeling or decision-making tools that can be used to model complex relationships between inputs and outputs or to find patterns in data. Therefore, ANNs can be used for predictive modeling and adaptive control applications, while being trained on datasets. Experience-based self-learning can occur within the network, drawing conclusions from complex and seemingly unrelated sets of information. The utility of artificial neural network models lies in their ability to infer functions from observations and also to use those functions. Unsupervised neural networks can also be used to learn representations of inputs that capture salient features of the input distribution, and recent deep learning algorithms can implicitly learn the distribution function of observed data. Learning in neural networks is particularly useful in applications where the complexity of the data or task makes manually designing such functions impractical.

[0092] Neural networks can be used in various fields. The tasks applied to ANNs often fall into the following broad categories: function approximation or regression analysis, including time series prediction and modeling; classification, including pattern and sequence recognition, novelty detection, and order decision-making; and data processing, including filtering, clustering, blind signal separation, and compression.

[0093] ANN applications encompass areas such as nonlinear system recognition and control (vehicle control, process control), game playing and decision making (backgammon, chat, competitions), pattern recognition (radar systems, facial recognition, object recognition), sequence recognition (gesture, speech, handwritten text recognition), medical diagnosis, financial applications, data mining (or knowledge discovery in databases, "KDD"), visualization, and email spam filtering. For example, semantic feature maps of user interests can be created from images trained for object recognition.

[0094] According to one or more implementations, the neural network 600 implements a long short-term memory neural network architecture, a CNN architecture, or other similar architecture. The neural network 600 can be configured with respect to multiple layers, multiple connections (e.g., encoder / decoder connections), regularization techniques (e.g., differential pressure), and optimized features.

[0095] Long Short-Term Memory (LSTM) neural network architectures include feedback connections and can process single data points (e.g., images) as well as entire sequences of data (e.g., speech or video). A unit in an LSM neural network architecture may consist of a cell, an input gate, an output gate, and a forget gate, where the cell remembers a value at any time interval, and the gates regulate the flow of information into and out of the cell.

[0096] A CNN architecture is a shared-weight architecture with translation invariance, where each neuron in one layer is connected to all neurons in the next layer. Regularization techniques in CNN architectures can leverage hierarchical patterns in the data and assemble more complex patterns using smaller, simpler patterns. If a neural network implements a CNN architecture, other configurable aspects of that architecture can include the number of filters at each stage, the kernel size, and the number of kernels per layer.

[0097] like Figure 6B As shown, method 601 describes the operation of neural network 600 (e.g., an autoencoder of an evaluation engine). In neural network 600, input layer 610 is represented by a plurality of inputs such as 612 and 614. Relative to block 620 of method 601, input layer 610 receives said plurality of inputs (e.g., data at multiple points such as WACA points) as initial operations. The plurality of inputs may be ultrasound signals, radio signals, audio signals, or two-dimensional or three-dimensional images / models. More specifically, the plurality of inputs may be represented as input data (X), which is raw data recorded from the cardiac mapping phase of WACA treatment.

[0098] At box 625 of method 601, neural network 600 utilizes an intracardiac dataset (e.g., generated by an evaluation engine in...) Figure 5 The dataset generated in box 510 encodes the plurality of inputs to produce a latent representation. The latent representation includes one or more intermediate images derived from the plurality of inputs. According to one or more embodiments, this latent representation is generated by an element-wise activation function (e.g., a sigmoid function or a rectified linear unit) of the autoencoder of the evaluation engine, which applies a weight matrix to the input intracardiac signal and adds a bias vector to the result. It should be noted that the weights and biases of the weight matrix and bias vector can be randomly initialized and then iteratively updated during training.

[0099] like Figure 6AAs shown, inputs 612 and 614 are provided to a hidden layer 630, depicted as including nodes 632, 634, 636, and 638. Therefore, layers 610, 630, and 650 can be considered encoder stages that take multiple inputs 612 and 614 and feed them to the deep neural network depicted in 630 to learn some smaller representations of the inputs (e.g., the resulting latent representation or data encoding 652). The deep neural network can be a CNN, a long short-term memory neural network, a fully connected neural network, or a combination thereof. Inputs 612 and 614 can be intracardiac ECG, ECG, or intracardiac ECG and ECG. This encoding provides a dimension-reduced intracardiac signal. Dimensionality reduction is the process of reducing the number of random variables (of multiple inputs) under consideration by obtaining a set of principal variables. For example, dimensionality reduction can be feature extraction that transforms data (e.g., multiple inputs) from a high-dimensional space (e.g., more than 10 dimensions) to a low-dimensional space (e.g., 2-3 dimensions). The beneficial effects of dimensionality reduction techniques include reduced data time and storage space, improved data visualization, and improved parameter interpretation for machine learning. This data transformation can be linear or non-linear. The operations of receiving (box 620) and encoding (box 625) can be viewed as the data preparation portion of a multi-step data manipulation performed by the autoencoder of the evaluation engine.

[0100] At box 660 of method 610, neural network 600 decodes the latent representation to produce an output intracardiac signal. The decoding stage takes the encoder output (e.g., the resulting latent representation or data encoding 652) and attempts to reconstruct some form of the inputs 612 and 614 using another deep neural network 660. In this regard, nodes 672, 674, 676, and 678 are combined to produce outputs 692 and 694 at output layer 690, as shown in box 699. That is, output layer 690 reconstructs inputs 612 and 614 in a reduced dimension, but without signal interference, signal artifacts, and signal noise. Examples of outputs 692 and 694 include intracardiac ECG, a clean version of intracardiac ECG (noise-reduced version), ECG, and noise-reduced ECG. The noise-reduced version of the intracardiac ECG may be free of one or more of the following: far-field attenuation, power line noise, contact noise, deflection noise, baseline drift, respiratory noise, and Fluro noise.

[0101] The neural network 600 performs processing via hidden layers 630 of nodes 632, 634, 636, and 638 to exhibit complex global behavior determined by the connections between processing elements and element parameters. The target data of the output layer 650 includes target data type one ventricular activity (Y1) and target data type two input data after far-field attenuation (Y2).

[0102] According to one implementation, the autoencoder of the evaluation engine can be a denoising autoencoder to find a calibration function (f, g) such that f(X) = Y1 and g(X) = Y2. Any combination of software and / or hardware (e.g., local computing device 206 and remote computing system 208 together with monitoring and processing device 202) can store, execute, and implement the denoising autoencoder and its functionality individually or jointly. The denoising autoencoder trains the autoencoder to reconstruct the input from its own corrupted version to force the hidden layer (e.g., hidden layer 630 of FIG. 6) to discover more robust features (i.e., useful features that will constitute a better higher-level representation of the input) and prevent it from learning specific identity (i.e., always returning to the same value). In this respect, the denoising autoencoder encodes the input (e.g., to retain information about the input) and reverses the effect of the corrupting process of the input randomly applied to the autoencoder.

[0103] Figure 7 A block diagram of method 700 according to one or more embodiments is shown. Any combination of software and / or hardware (e.g., local computing device 206 and remote computing system 208 together with monitoring and processing equipment 202) may be stored, executed, and implemented individually or jointly within an environment where the evaluation engine and its functions are implemented. Generally, method 700 may be implemented relative to WACA treatment, which includes WACA point mapping and WACA phases. That is, implementing method 700 relative to WACA treatment enables physicians and / or medical professionals to more effectively treat various cardiovascular diseases using ablation itself.

[0104] For example, the electrical properties of the left and right PVs are mapped using catheter-based WACA treatment using method 700, and direct information is provided to physicians and / or medical professionals. In this regard, mapping and direct information include automated anatomical segmentation of WACA points, continuity estimation, and gap prediction.

[0105] Processing flow 700 begins at box 720, where the evaluation engine receives cases. Cases can be received in real time during the WACA point mapping phase of WACA treatment. Cases include mapping WACA points for the left and right PVs, where the WACA points themselves form two separate rings around the left and right PVs.

[0106] At box 730, the evaluation engine determines the right and left WACA positions for each WACA point in the received case, or at least one of the following: left WACA, right WACA, orifice PVI, top line, left carina, right carina, posterior line, inferior line, mitral isthmus line, anterior line, anterior line, and inferior vena cava-tricuspid isthmus and superior vena cava isolation line. For example, a sub-algorithm of the evaluation engine evaluates the WACA points to estimate the left and right WACA rings. This estimation can be considered as feature extraction to determine morphological ring features. In some cases, the evaluation engine may automatically compare the positional information of the WACA points with dimensional information along the axis (e.g., using an X-axis with a first extent for the left position and a second extent for the right position). See also Figure 8 The diagram illustrates a graphical image 801 according to one or more embodiments. Graphical image 801 is an example of a graphical user interface that provides an image of a PV with two separate rings. Each ring includes WACA points, such as those generated in box 720.

[0107] At box 735, the evaluation engine utilizes the dataset. In one example, the dataset includes more than 370 cases, each with manual annotations and / or ablation features (e.g., radiofrequency index (RFIndex), force-time integral (FTI, how much force is induced during the ablation point), etc.).

[0108] See now Figure 9A and Figure 9B Graphical images 902 and 907, respectively, show user interfaces for displaying datasets according to one or more embodiments. Graphical image 902 is an example of manual annotation of nine anatomical structures. Graphical image 907 is an example of manual annotation of ablation types.

[0109] At box 740, the evaluation engine determines the anatomical classification of each WACA point in the received case (e.g., manual annotation based on training data). Anatomical classification (e.g., segmentation) is the evaluation engine's ability to determine which segment of the left and right pulmonary veins each WACA point is located in. At box 745, the evaluation engine displays the results of the anatomical classification. At this point, physicians or medical professionals use the displayed results to treat various cardiovascular diseases more effectively.

[0110] According to one or more implementation schemes, anatomical structures can be classified according to nine structures. Table 1 shows the nine structures or segments: right posterior, right inferior, right superior, right anterior, left posterior, left inferior, left superior, left vertebral, and left anterior.

[0111] Table 1 Section name right rear RPS lower right RIN Top right RRF right front RAN Left rear LPS lower left LIN Top left LRF left spine LRG left front LAN Each structure or segment can be represented by a unique code, as shown in the name column of Table 1, and / or by a set of numbers (e.g., 1 to 9). Other structural combinations relating to or replacing the nine structures or segments may be used, such as the left WACA, right WACA, orifice PVI, top line, left carina, right carina, posterior line, inferior line, mitral isthmus line, anterior line, anterior line, and at least one of the inferior vena cava-tricuspid isthmus and superior vena cava isolation.

[0112] Figure 10 A graphical depiction 1008 is shown, classifying the left and right WACA points into anatomical structures through manual annotation. The graphical depiction 1008 shows the left atrium with ablation points, where the text represents the evaluation engine's decision (if the text is a first color such as green, the evaluation engine is correct; if the text is a second color such as red, the evaluation engine is incorrect).

[0113] Figure 11A An illustration of the right anatomical structure identified as the right WACA 1100 is shown. The right WACA 1100 includes a posterior region 1110 on the right side, a lower region 1120 below, a top region 1130 above, and an anterior region 1140 on the left side.

[0114] Figure 11B An illustration of the left anatomical structure identified as the left WACA 1101 is shown. The left WACA 1101 includes a posterior region 1150 on the left side, a lower region 1160 below, a top region 1170 above, a ridge region 1180 on the upper right, and an anterior region 1190 on the lower right.

[0115] The elements in Table 1 and Figure 11A and Figure 11B The comparison of diagrams 1100 and 1101 shows nine structures or segments positioned around the right PV and left PV.

[0116] In the exemplary operation of box 740, Figure 12A A block diagram of classification method 1212 is shown, and Figure 12BA block diagram of classification method 1211 is shown. Method 1211 is an exemplary operation of a random forest for an acute reconnection classifier (e.g., a random forest classifier). In method 1212 of Figure 12, as discussed herein, the input to anatomical structure classification may include a set of properties / features for each ablation point, a 3D representation of the atrium / CT scan / ultrasound / rapid anatomical mapping / etc. (e.g., VTK file), and an IC ECG or surface ECG. The output 1249 of the anatomical structure classifier is the anatomical structure code k (k = 1…K). According to one or more embodiments, a deep CNN network can be used to process the 3D representation of the atrium to obtain an initial estimate of a KxM probability matrix, indicating the probability that each of the m (m = 1, …, M) ablation points is associated with each of the k anatomical structures (k = 1,…,K). A deep autoencoder can be used to process the IC ECG to obtain a set of features. All features (and properties) can be processed by a set of dense neural networks to produce anatomical structure predictions.

[0117] More specifically, method 1212 includes utilizing random forest classification, fully connected dense layers, and a CNN architecture. Thus, a five-layer CNN receives the anatomical structure of the left atrium from a VTK file (box 1240), fully connected layers receive ablation features (box 1241), and fully connected layers receive morphological features (box 1242) along with the ablation features. For example, as described herein, a deep CNN network is used, leveraging the VTK file to process ablation localization (x, y, z) locations and ablation properties to obtain a set of features. These features can be passed to several dense layers to generate anatomical structure codes. The outputs of the five-layer CNN and two fully connected layers are then passed through two additional fully connected networks (e.g., processed relative to boxes 1245 and 1247) to provide the final anatomical code decision (e.g., the output relative to box 1249).

[0118] Method 1211 includes providing morphological features to a random forest classifier (box 1223) and executing the random forest classifier (box 1225) to output an anatomical structure code (box 1227). The morphological features can be derived from estimations and feature extraction by sub-algorithms. In this regard, the morphological features can be organized by an evaluation engine based on left and right WACA rings. For example, since the primary "information" used to classify the anatomical structure is based on the x, y, z positions of the ablation points, the evaluation engine executes a sub-algorithm that forms rings based on the proximity of the ablation points. The evaluation engine extracts morphological features from these rings, such as the total surface area of ​​the rings, the number of points in the rings, and the angle of each point (if the rings resemble a "clock"). In one implementation, the morphological features can be numbers ranging from 10 to 50, such as 25.

[0119] According to one or more implementations, the morphological features can be nine anatomical structures defined within an algorithmic feature space. For example, the algorithmic feature space can include (x_left, y_left, z_left), (x_right, y_right, z_right), where the average of all points is associated with the left and right rings; (x_norm, y_norm, z_norm), where x, y, and z are range-normalized; and (x_norm_ring, y_norm_ring, z_norm_ring), where the normalized points are based on the range of the (left or right) ring. The algorithmic feature space may also include optional features such as VTK files, minimum distance from the ablation point to the anatomical structure, and ablation properties (e.g., power, impedance, impedance drop, stability, etc.). The output of method 1211 can be an anatomical structure code and / or a number from 1 to 9.

[0120] Generally speaking, random forest classifiers include ensemble learning methods for classification, regression and other tasks. The random forest classifier operates by constructing multiple decision trees during training and outputting the class as a pattern of classes or the average prediction of the individual trees.

[0121] Figure 13 An exemplary random forest classifier for classifying the colors of clothing is shown. Figure 13 As shown, the random forest classifier comprises five decision trees 13101, 13102, 13103, 13104, and 13105 (collectively or generally referred to as decision tree 1310). Each tree is designed to classify the color of clothing. In this example, three of the five trees (13101, 13102, and 13104) determine that the clothing is blue, one tree determines that the clothing is green (13103), and the remaining tree determines that the clothing is red (13105). The random forest takes these actual predictions from the five trees and calculates the mode of these actual predictions to provide the random forest answer that the clothing is blue.

[0122] Returning to Figure 12, method 1212 involves utilizing a random forest regression, fully connected dense layers, and a CNN architecture. Thus, a five-layer CNN receives the VTK anatomical structure (box 1240), fully connected layers receive ablation features (box 1241), and fully connected layers receive morphological features (box 1242). The VTK anatomical structure can be the anatomical structure of the left atrium stored in a VTK file. According to one or more implementations, a deep CNN network is used to process the ablation localization, location, and characteristics of the VTK file to obtain a set of features, which are then passed to several dense layers to generate anatomical structure codes. The outputs of the five-layer CNN and two fully connected layers are then passed through two additional fully connected networks (boxes 1245 and 1247) to provide the final output of the anatomical structure codes (box 1249).

[0123] return Figure 7 At box 750, the evaluation engine estimates the continuity of two separate rings around the left and right PVs (e.g., performing an acute reconnection continuity estimate). The continuity estimate is the evaluation engine's ability to determine indirect contacts between the two separate rings around the left and right PVs, and between these two separate rings and structural elements outside the left and right pulmonary veins. The output of this estimate may include the probability of continuity at each ablation point. At box 755, the evaluation engine displays the results of the continuity estimate. In this respect, physicians or medical professionals use the displayed results to more effectively treat various cardiovascular conditions. In the exemplary operation of box 750, Figure 14A A block diagram of classification method 1412 is shown. Figure 14B A block diagram of classification method 1411 is shown, and Figure 14C Graphical image 1416 is shown. Method 1411 is an exemplary operation of a random forest for an acute reconnection classifier (e.g., a random forest classifier as described herein). Method 1412 is an exemplary operation of a deep learning method for a secondary ablation / acute reconnection classifier. Graphical image 1416 depicts acute reconnection points (indicated in purple).

[0124] Method 1411 includes providing ablation features and morphological features to a random forest classifier (box 1423) and performing the random forest classifier (box 1425) to output continuity probabilities (box 1427). The ablation features and morphological features used for continuity estimation (secondary ablation or acute reconnection) include location-based features updated based on nine anatomical structures defined in the feature space as follows: (x_left, y_left, z_left), (x_right, y_right, z_right), where the average of all points is associated with the left and right rings; (x_norm, y_norm, z_norm), where x, y, and z are range-normalized; and (x_norm_ring, y_norm_ring, z_norm_ring), where the normalized points are based on the range of the (left or right) ring.

[0125] The algorithm's feature space may include optional features such as grid-based features, VTK files of atrial anatomy (e.g., CNNs for the feature phase), minimum distance from the ablation point to the anatomy, and ablation properties (e.g., power, impedance, impedance drop, stability, temperature, RFIndex, FTI, features, time-based features, etc.). The output of method 1211 may be an anatomical structure code and / or a number from 1 to 9.

[0126] return Figure 14A Method 1412, as discussed herein, may include a set of characteristics / features for each ablation site, a 3D representation of the atrium / CT scan / ultrasound / rapid anatomical mapping / etc. (e.g., VTK file), and an IC ECG or surface ECG.

[0127] The output of the secondary ablation / acute reconnection classifier may include each voxel of interest as either 1 or 0, where 1 represents an acute / long-term reconnection site. A voxel can be a point in three-dimensional space, such as a graphical information unit (e.g., a 2mm × 2mm × 2mm cube). For example, when pixels define points in two-dimensional space with x and y coordinates, a third z coordinate is required for a voxel. According to one or more embodiments, each voxel may be further defined in 3D space in terms of location, color, and density. Based on the output, acute / long-term reconnection sites can be shown.

[0128] According to one or more implementations, a 3D representation of the atrium can be processed using a deep CNN network to obtain a set of features, and an IC ECG can be processed using a deep autoencoder to obtain another set of features. Additionally, the IC ECG can be processed to obtain additional features such as bipolar voltage, conduction velocity, period length (milliseconds), spatial-temporal dispersion level, distance from the focal source, and fragmentation level for each voxel of interest. All features (and properties) can be processed by a dense set of neural networks to produce continuous predictions.

[0129] More specifically, method 1412 includes utilizing random forest classification, fully connected dense layers, and a CNN architecture. According to one or more implementations, method 1412 includes using random forest classification for acute / secondary ablation classification and utilizing a CNN dense set layer for continuity estimation. Thus, a five-layer CNN receives the anatomical structure of the left atrium from a VTK file (box 1440), fully connected layers receive ablation features (box 1441), and fully connected layers receive morphological features (box 1442) along with ablation features in some cases. For example, as described herein, a deep CNN network is used, utilizing the VTK file to process ablation localization (x, y, z) locations and ablation characteristics to obtain a set of features. All features are then passed to several dense layers to generate anatomical structure codes. The outputs of the five-layer CNN and two fully connected layers are then passed through two additional fully connected networks (e.g., processed relative to boxes 1445 and 1447) to provide the final continuity probabilities (e.g., the output relative to box 1449).

[0130] In box 760, the evaluation engine generates a secondary ablation prediction (e.g., predicting an annotated ablation point as a secondary ablation point). In box 765, the evaluation engine displays the secondary ablation prediction results. At this point, physicians or medical professionals use the displayed results to treat various cardiovascular diseases more effectively.

[0131] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible specific embodiments of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of instructions comprising one or more executable instructions for implementing a specified logical function. In some alternative embodiments, the functions indicated in the blocks may not occur in the order shown in the drawings. For example, depending on the function involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a system based on dedicated hardware that performs the specified function or action, or by a combination of dedicated hardware and computer instructions.

[0132] While features and elements have been specifically described above, those skilled in the art will recognize that each feature or element can be used alone or in any combination with other features and elements. Furthermore, the methods described herein can be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. As used herein, a computer-readable medium should not be construed as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through fiber optic cables), or electrical signals transmitted through wires.

[0133] Examples of computer-readable media include electronic signals (transmitted via wired or wireless connections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, registers, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, optical media such as optical discs (CDs) and digital versatile discs (DVDs), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), and memory sticks. A processor associated with software can be used to implement a radio frequency transceiver used in a terminal, base station, or any host computer.

[0134] It should be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, unless the context clearly indicates otherwise, the singular forms “an,” “a,” and “the / described” include plural references. It should also be understood that the terms “comprising” and / or “including”, when used in this specification, specify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0135] The descriptions of various embodiments herein are presented for illustrative purposes and are not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles of the embodiments, their practical application or improvement relative to commercially available technologies, or to enable others skilled in the art to understand the disclosed embodiments.

Claims

1. A system for automatically segmenting anatomical structures of large-area annular ablation points, comprising: The memory is configured to store processor-executable program instructions for the evaluation engine; as well as Processor, the processor being configured to execute the program instructions of the evaluation engine to cause the device to: Receive multiple large-area circular ablation (WACA) points corresponding to the patient's cardiac tissue; For the plurality of large-area annular ablation points, determine the right large-area annular ablation location and the left large-area annular ablation location corresponding to the left and right pulmonary veins of the heart tissue; The anatomical structure classification of each of the plurality of large-area annular ablation points is determined based on the structural segmentation of the heart tissue, and the anatomical structure classification is displayed on the monitor. Based on the structural segmentation, morphological ring features are extracted from the plurality of large-area annular ablation points to estimate the right large-area annular ablation ring and the left large-area annular ablation ring; Estimate the continuity of the right large-area annular ablation ring and the left large-area annular ablation ring and display the estimated continuity result on the display; as well as The acute reconnection continuity estimation of the right large-area annular ablation ring and the left large-area annular ablation ring is performed, secondary ablation predictions are generated, and they are displayed on the display.

2. The system of claim 1, wherein the evaluation engine uses manual annotation of training data to determine the anatomical structure classification.

3. The system of claim 1, wherein the structural segmentation of the cardiac tissue includes at least one of the right posterior portion, right inferior portion, right superior portion, right anterior portion, left posterior portion, left inferior portion, left superior portion, left ridge portion, and left anterior portion of the left and right pulmonary veins.

4. The system of claim 1, wherein the structural segmentation of the cardiac tissue includes at least one of the following: left WACA, right WACA, orifice PVI, top line, left carina, right carina, posterior line, lower line, mitral isthmus line, anterior line, anterior line, and inferior vena cava-tricuspid isthmus and superior vena cava isolation.

5. The system according to claim 1, wherein the algorithmic feature space of the morphological ring feature includes (x_left, y_left, z_left), (x_right, y_right, z_right); (x_norm, y_norm, z_norm); and (x_norm_ring, y_norm_ring, z_norm_ring).

6. The system of claim 1, wherein the anatomical classification comprises an anatomical code based on a set of numbers from 1 to 9.

7. The system of claim 1, wherein the evaluation engine determines the anatomical structure classification based on the large-area annular ablation point and a three-dimensional model of the atrium as input.

Citation Information

Patent Citations

  • Systems and methods for anatomic structure segmentation in image analysis

    CN110914866A

  • Estimation of effectiveness of ablation adjacency

    US20200022649A1