Classifying ablation points from catheter data

Abstract

A method includes receiving an anatomical map of wall tissue of at least a portion of a cardiac cavity, the map including different anatomical regions. A plurality of ablation points generated by a multi-electrode catheter during an ablation instance may be received. An anatomical region is identified using a classification algorithm that takes into account catheter shape data, and all ablation points are classified as belonging to the identified anatomical region. Corresponding ablation tags may also be presented on the anatomical map according to the classified ablation points and catheter shape data.

Description

Technical Field

[0001] This disclosure relates generally to cardiac ablation, and more specifically to systems and methods for generating ablation maps. Background Technology

[0002] Ablation mapping is typically a 3D rendering of at least a portion of an organ that can be overlaid with an ablation label. It is used by physicians during ablation treatments to validate their effectiveness. The 3D rendering can be an electroanatomical mapping or an anatomical surface, such as the lining of a cardiac chamber. Ablation indications on the mapping help physicians assess the status of the ablation treatment or identify characteristics associated with the ablation site. For example, physicians can use ablation indications to determine whether a sufficient number of ablations have been performed in the desired area, or to locate gaps in the ablation pathway that require further ablation closure to eliminate arrhythmias. Appropriate indication of the treated area is beneficial for easily identifying ablation characteristics and for generating the necessary information for treatment reporting and / or research purposes. Attached Figure Description

[0003] This disclosure will be more fully understood through the following detailed description of embodiments thereof, taken in conjunction with the accompanying drawings, in which: Figure 1 This is a schematic diagram of a catheter-based electroanatomical (EA) mapping and ablation system according to an example of this disclosure; Figure 2 This is a schematic diagram illustrating the classification of ablation points based on catheter data, according to an example of this disclosure; Figure 3 The ablation map of the cardiac chamber is derived from one of the algorithms disclosed in this disclosure for classifying ablation points, based on examples of the use of this disclosure; and Figure 4 This is a flowchart illustrating, according to an example of the present disclosure, a method for generating ablation maps of the heart chambers by classifying ablation points based on catheter data. Detailed Implementation

[0004] Overview In cardiac ablation procedures, such as pulmonary vein isolation (PVI) for the treatment of atrial fibrillation, a physician may ablate tissue in a specific anatomical region (e.g., the entire circumference of the pore of the PV). Ablation (such as using pulsed field ablation (PFA) or radiofrequency (RF) techniques) may require several iterations in that region to completely cover the entire circumference of the pore. Each iteration may require moving the multi-electrode ablation catheter to an area that the physician deems insufficiently ablated or not ablated at all.

[0005] Ablation mapping, which includes anatomical 3D mapping of the area, can be used to assist physicians. This mapping also shows the classification of one or more ablation tags to indicate the location where ablation has been performed.

[0006] However, this classification can be challenging for some anatomical structures. For example, in the left atrium (LA), classification can be difficult when the following conditions occur: 1. Positioning the catheter in adjacent superior or inferior veins creates closely spaced adjacent ablation points, making it difficult to classify the identification of each location, specifically when catheter positioning can cause LA wall movement (i.e., bulging effect); 2. Identify whether the goal of ablation therapy is to isolate the pulmonary vein (PV) or to create an ablation separation line near the PV (e.g., on the posterior wall of the LA or on the superior wall of the LA).

[0007] PFA multielectrode ablation exacerbates the challenges described above because each ablation sequence is performed on a specific anatomical region, but some electrodes may be located outside that specific anatomical region. Therefore, connecting a set of resulting ablation points (e.g., from several ablation iterations) would not make much sense, as each set of ablation points formed by the multielectrode catheter at a given time needs to be treated as a whole group rather than individual points, where these points can be mixed with other ablation points.

[0008] The aforementioned issues, along with others, can cause ablation labels to fail to accurately indicate the correct ablation location. This can also lead to incorrectly showing ablation sites when they were not actually ablated.

[0009] For example, any one or more of the reasons mentioned above can cause the ablation tag generated during ablation at the upper PV ostium site to incorrectly mark the lower PV ostium site. Such errors on the ablation mapping can mislead physicians or make it difficult for them to determine whether further ablation is necessary.

[0010] The examples described herein provide a technique for classifying ablation points that can eliminate inaccurate labeling caused by the aforementioned problems. As described in this disclosure, a set of ablation points can be one of: (i) the location of a set of catheter electrodes during an ablation session, and any additional information assigned to the electrodes therein, such as contact force, ablation power, and ablation duration; and (ii) a set of planned ablation points generated by a multi-electrode catheter during an ablation session.

[0011] Taking into account the specific location of the ablation area and the shape of the catheter (e.g., a circular catheter), the algorithm described in more detail below classifies a set of ablation points from ablation instances performed using a multi-electrode catheter. The disclosed method treats ablation points generated at any given instance as a set of points rather than a single, unrelated point, which helps to constrain the tissue location of the ablation points to the correct anatomical region or location (e.g., the correct mouth) on an anatomical mapping with high confidence.

[0012] Additional data related to the catheter, such as the contact force between the electrode and the heart wall tissue or the tissue proximity index (TPI), can also be used for classification.

[0013] In the first example of the disclosed technology, the processor can run the following steps of the majority voting algorithm: 1. Assign ablation instances to anatomical regions (e.g., given the ostium), where a majority of the electrodes in the catheter are considered to be in contact during the ablation; and 2. Using catheter location and the shape of the catheter in space, identify the tissue location of the electrode that is in contact with the tissue in the anatomical area to generate the correct ablation label.

[0014] In the second example, the processor can run the following centroid mapping algorithm steps: 1. Calculate the geometric center (centroid) of all electrodes of the catheter that come into contact with the tissue during the ablation sequence; and 2. Taking into account the shape of the catheter in space, for example, constraining the tissue location of the electrode contact according to the catheter model based on the electrode location (such as on the circular curve of an annular catheter around the centroid point located within a given pore), the ablation point is assigned to the region where the centroid is located.

[0015] In the third example, the processor can run the following weighted voting algorithm steps: 1. Assign weights to each electrode in the catheter based on factors such as contact quality and / or signal strength; and 2. Using catheter location and the shape of the catheter in space, identify the tissue location corresponding to the catheter electrode with the highest total weight (e.g., the sum of the combined weights of the assigned weights of a particular electrode or group of electrodes).

[0016] In the fourth example, the processor can run the following probability allocation algorithm steps: 1. Assign the probability of each ablation point belonging to one of multiple regions based on its distance from the corresponding region; 2. Aggregate probabilities to determine the region most likely associated with the ablation point; and 3. By using the position and shape of the catheter in space, the tissue location of the ablation point is constrained to the most probable area.

[0017] In the fifth example, the processor can run a machine learning (ML) classification algorithm that can be trained on existing and labeled ablation data to predict the anatomical region of each ablation sequence (e.g., a group of ablation points) based on electrode configuration and other previously mentioned data (e.g., contact force and / or catheter shape).

[0018] In the sixth example, the processor can use the output from any one or more of the first through fifth algorithms to train another ML-based algorithm, such as a random forest, to achieve the best overall results.

[0019] System Description The following detailed description should be read in conjunction with the accompanying drawings, in which the same elements are labeled the same in different figures. The drawings (not necessarily drawn to scale) depict selected examples and are not intended to limit the scope of this disclosure. The principles of this disclosure are illustrated by way of example and not by way of limitation. This specification will clearly enable those skilled in the art to make and use the invention, and describes several examples, adaptations, variations, alternatives, and uses of the invention, including those currently believed to be the best mode for carrying out the invention.

[0020] Figure 1 This is a schematic diagram of a catheter-based anatomical / electroanatomical (EA) mapping and ablation system 10 according to an example of this disclosure.

[0021] System 10 may include multiple catheters that can be percutaneously inserted by physician 24 through the patient's vascular system into the chambers or vascular structures of heart 12 (shown in illustration 45). In some examples, a delivery sheath catheter may be inserted into a heart chamber (such as the left or right atrium) near a desired location within heart 12. Subsequently, multiple catheters may be inserted into the delivery sheath catheter to reach the desired location. These multiple catheters may include catheters dedicated to pacing, catheters for sensing intracardiac electrogram signals, catheters dedicated to ablation, and / or catheters dedicated to both EA mapping and ablation. Figure 1 An example loop ablation catheter 14 is shown. In one aspect, the loop catheter 14 can be configured to sense a bipolar electrogram and apply a PFA. The physician 24 can bring the distal end assembly 28 of the catheter 14 into contact with the heart wall to ablate a target site in the heart 12.

[0022] As depicted in Illustration 65, in some examples, the distal end assembly 28 of the catheter 14 may include a plurality of electrodes 26 distributed on a curved strip 22. The catheter 14 may include a position sensor 29 embedded in or near the distal end assembly 28 on the shaft 46 of the catheter 14 to track the position and orientation of its distal end assembly 28. Optionally and preferably, the position sensor 29 may be a magnetically based position sensor having three magnetic coils for sensing three-dimensional (3D) position and orientation.

[0023] The magnetic-based position sensor 29 can operate in conjunction with a position pad 25, which may include a plurality of magnetic coils 32 configured to generate a magnetic field in a predefined workspace. Real-time positioning of the distal end assembly 28 of the conduit 14 can be tracked based on the magnetic field generated by the position pad 25 and sensed by the magnetic-based position sensor 29. Details of the magnetic-based positioning sensing technology are described in U.S. Patents Nos. 5,391,199, 5,443,489, 5,558,091, 6,172,499, 6,239,724, 6,332,089, 6,484,118, 6,618,612, 6,690,963, 6,788,967, and 6,892,091.

[0024] On the other hand, system 10 may include one or more electrode patches 38 positioned to contact the skin of patient 23 to establish a position reference for impedance-based tracking of positioning pad 25 and electrodes 26. For impedance-based tracking, current may be directed toward electrodes 26 and sensed at the electrode skin patch 38, allowing triangulation of the position of each electrode via the electrode patch 38. Details of impedance-based position tracking techniques are described in U.S. Patents 7,536,218, 7,756,576, 7,848,787, 7,869,865, and 8,456,182.

[0025] In some examples, recorder 11 may display cardiac signals 21 acquired using surface ECG electrodes 18 (e.g., electrograms acquired at separately tracked cardiac tissue locations) and intracardiac electrograms acquired using electrodes 26 of catheter 14. Recorder 11 may include pacing capabilities for pacing rhythms and / or may be electrically connected to a separate pacemaker.

[0026] System 10 may also include an ablation energy generator 50 adapted to conduct ablation energy to one or more electrodes 26 configured for ablation. The energy generated by the ablation energy generator 50 may include, but is not limited to, radio frequency (RF) energy or pulsed field (PF) energy, including unipolar or bipolar high-voltage DC pulses (i.e., PFA).

[0027] The patient interface unit (PIU) 30 is an interface configured to establish electrical communication between the catheter, electrophysiology equipment, power supply, and workstation 55 to control the operation of system 10 and receive EA signals from the catheter. The electrophysiology equipment of system 10 may include, for example, multiple catheters, positioning pads 25, surface ECG electrodes 18, electrode patches 38, ablation energy generator 50, and recorder 11. Optionally and preferably, the PIU 30 may be additionally equipped with processing capabilities for real-time calculation of catheter position and for performing ECG calculations.

[0028] Workstation 55 may include memory 57, a processor unit 56 with a memory or storage device loaded with appropriate operating software, and user interaction capabilities. In one aspect, workstation 55 may provide a variety of functions, optionally including: (i) three-dimensional (3D) modeling of the endocardial anatomy and rendering the model or anatomical mapping 20 for display on display device 27; (ii) displaying on display device 27 representative visual markers or images superimposed on the rendered anatomical mapping 20 to display activation sequences (or other data) compiled from recorded cardiac signals 21; (iii) displaying the real-time position and orientation of multiple catheters within the cardiac chambers; and (iv) displaying on display device 27 sites of interest, such as where ablation energy has been applied. A commercially available component embodying system 10 is CARTO™ 3 System, purchased from Biosense Webster, Inc.

[0029] In the disclosed example, processor 56 can run an algorithm that considers the specific location and spatial configuration (i.e., shape) of the distal end assembly 28, classifying multiple ablation points (such as points associated with each electrode of the entire annular distal end assembly 28 of catheter 14) together into a group, the spatial configuration constraining tissue location to conform to the annular shape of the catheter, such as... Figure 2 As shown.

[0030] In some examples, processor 56 may include a general-purpose computer programmed in software to perform the functions described herein. This software may be downloaded to the computer electronically, 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.

[0031] This configuration of system 10 is illustrated by way of example to illustrate certain problems addressed by the examples of this disclosure and to demonstrate the application of these examples in enhancing the performance of such systems. However, the examples of this disclosure are by no means limited to this particular example system, and the principles described herein can be similarly applied to other medical systems. For example, the systems, methods, and techniques described herein can be used in conjunction with other types of multielectrode ablation catheters, such as basket catheters, balloon catheters, or some other suitable shape of multielectrode ablation catheter.

[0032] Classification of ablation points based on catheter data Figure 2 This is a schematic diagram illustrating the classification of ablation points 220 based at least in part on data received from catheter 14, according to an example of this disclosure.

[0033] like Figure 2 As shown, the flexible tissues in the anatomical region (such as orifices 210A and 212A) may bulge or deform in response to contact with the catheter, which may result in the ablated tissue location being incorrectly reflected (e.g., marked) in the orifice mapping (200) representations 210B and 212B.

[0034] In the example shown, ablation point 220 may appear at the pushed wall of tissue 202 in orifice 210A. Based solely on the coordinates of mapping map 200, the algorithm may incorrectly assign label 222B to ablation point 220, which is located at lower orifice 212B on mapping map 200.

[0035] By applying one or more of the algorithms discussed above that take into account the shape of the distal end component 28, the disclosed technique can correctly assign an ablation tag 222A to the ablation point 220 at the mapped port 210B, instead of incorrectly assigning an ablation tag 222B to the port 212B.

[0036] Specifically, in the illustrated example, the disclosed technique can accurately assign the correct ablation label 222A by taking into account the locations of other ablation points 230 performed by the loop catheter during the same ablation instance. In one example, using one of the above classification algorithms may include determining the region by assuming that the centroid location 250 of the ablation point (220, 230) falls within the correct anatomical region associated with the ablation point.

[0037] The disclosed technique similarly ensures that ablation tags for other ablation lines (such as those made on the posterior wall of the left atrium) are correctly positioned. In this example, the tag will be correctly positioned even though the coordinates of the flexible posterior wall tissue recorded during ablation change from those represented by the mapping (i.e., representing the tissue in the absence of a catheter and without undergoing deflection or bulging).

[0038] Ablation sessions may include Figure 2 Multiple instances of the types shown. Figure 3 Ablation mappings based on the above analysis applied to multiple ablation cases are depicted.

[0039] Ablation mapping based on ablation points categorized according to catheter data Figure 3 The ablation mapping 300 of the heart chambers is derived from one of the disclosed algorithms for classifying ablation points, according to examples of this disclosure. The ablation mapping 300 may include an anatomical mapping 302 presented (e.g., overlaid) together with ablation labels such as labels 304, 306, and 310.

[0040] The cavity depicted is the left atrium, which can be visualized by graphical encoding using a segmentation algorithm. In addition: Left atrial wall and four PVs; Top left PV (LSPV); Bottom left PV (LIPV); Top right PV (RSPV); and / or Bottom right PV (RIPV) Mapping 300 can also be based on one or more of the disclosed classification algorithms, which assign each group of ablation points of the loop catheter 14 to the correct region based on catheter data. As shown, the corresponding ablation tags 304, 306, and 310 can be presented as groups, each distributed on the circular outline (322) of the distal end assembly 28. It should be noted that when the tissue returns to its normal shape (i.e., the catheter is repositioned after the ablation energy is applied so that it no longer deforms or bulges the tissue), the arc of the outline may appear as a straight line rather than a loop, as in the case of the ablation tags 310 on the ablation line above the left atrial wall.

[0041] Mapping map 300 can be generated offline using stored data, or generated during a clinical ablation procedure and updated in real time as the ablation procedure progresses. Depending on the shape of the catheter, mapping map 300 may have a slightly different appearance from the illustrated mapping map.

[0042] A method for generating ablation maps using ablation point classification. Figure 4 This is a flowchart schematically illustrating a method for generating an ablation mapping of the heart chambers using the techniques described above for classifying ablation points, according to an example of this disclosure. According to the presented example, one or more of the described algorithms are executable processes that begin with processor 56 receiving anatomical mapping 302 at mapping receiving step 402.

[0043] At step 404, the processor may also receive a set of ablation points from instances of ablation performed by catheter 14 within the cardiac chamber. Step 404 may optionally include applying ablation energy to the tissue via catheter 14 as a precursor to receiving the set of ablation points.

[0044] Next, at classification step 406, the processor may apply one or more of the disclosed classification algorithms, which take into account the shape of the catheter before assigning the ablation point to the correct area of ​​the mapping.

[0045] At the ablation tag generation step 408, the processor can generate a set of corresponding ablation tags. At the ablation tag overlay step 410, the processor can overlay the set of ablation tags 306 onto the mapping map 302 to generate an ablation mapping map 300.

[0046] At the graphic encoding step 412, the processor may graphicly encode the ablation tag 306 to indicate ablation characteristics, such as PV port identity and ablation level. Graphically encoding the tag ablation map may include coloring the ablation tag in one area with one color and coloring the ablation tag in another area with another color.

[0047] Finally, at the ablation mapping presentation step 414, the processor can present a graphically encoded ablation mapping 300 to the user on the display device 27.

[0048] Figure 4 The flowchart in the diagram is simplified to describe a single instance of ablation. However, in actual procedures, multiple ablation instances may occur (e.g., multiple ablations may be performed iteratively at step 404), causing the processor to update the ablation mapping 300 multiple times during the procedure. If the ablation procedure is fully performed, the final mapping 300 will reflect the complete treatment.

[0049] Map 300 can be generated using offline data, or generated during clinical ablation procedures and updated in real time as the ablation procedure progresses. Example

[0050] In one example, the method according to this specification may include receiving an anatomical mapping (200) of the wall tissue (202) of at least a portion of the cardiac chamber, the mapping including different anatomical regions (210, 212). The method may also include receiving one or more of the following: a set of ablation points (220, 230) generated by a multi-electrode catheter (14) and a set of planned ablation points to be generated by the multi-electrode catheter (14) at an ablation instance in one of the anatomical regions. Using a classification algorithm that takes into account catheter (14) shape and location data, one of the anatomical regions (210, 212) (210) may be identified, and all ablation points (220, 230) may be classified as belonging to the identified anatomical region (210). Appropriate ablation labels (222A) may be presented on the anatomical mapping (200) based on the classified ablation points (220, 230) and catheter shape and location data.

[0051] In another implementation, the classification algorithm may also include determining the region by considering that most of the ablation points fall within the correct anatomical region associated with the ablation point (220, 230).

[0052] In other embodiments, the classification algorithm may include determining the region by assuming that the location of the centroid (250) of the ablation point and / or the shape of the electrodes distributed around the distal end of the catheter fall within the correct anatomical region (220) associated with the ablation point.

[0053] Alternatively or otherwise, the classification algorithm may include assigning weights to each ablation point associated with the catheter (14) shape data, and identifying the correct anatomical region (210) associated with the ablation point by determining which region the subgroup of ablation points (220, 230) that produce the highest total weight is located in.

[0054] In other implementations, the classification algorithm may include determining the correct anatomical region (210) associated with the ablation point by calculating the distance between each of the plurality of ablation points (220, 230) and each of the plurality of regions, and determining the correct region (210) on the mapping map (200) associated with the ablation point based on the probability derived from the distance.

[0055] In other implementations, the classification algorithm may include training a machine learning (ML) algorithm based on a dataset of labeled ablation points, and using the trained ML algorithm to infer the correct anatomical region (210) based on a received set of ablation points (220, 230).

[0056] Training an ML model may involve training the model using data labeled with one or more of the given classification algorithms in the list: majority voting classification, centroid location classification, distance-based probabilistic classification, and weighted ablation point-based classification (each of which is described in this paper).

[0057] In another example, the system (10) according to this specification may include a memory (57) and a processor (56). The memory may be configured to store a classification algorithm. The processor may also be configured to: (i) receive an anatomical mapping (200) of the wall tissue (202) of at least a portion of the cardiac chamber, the mapping including different anatomical regions (210, 212), and (ii) receive one or more of the following: a set of ablation points (220, 230) generated by the multi-electrode catheter (14) and a set of planned ablation points to be generated by the multi-electrode catheter (14) at an ablation instance in one of the anatomical regions. In one aspect, using a classification algorithm that takes into account catheter shape and location data, the processor (56) may also be configured to: (a) identify an anatomical region (210) within the anatomical area and classify all ablation points (220, 230) as belonging to the identified anatomical region, and (b) present corresponding ablation labels (222A) on the anatomical mapping map (200) based on the classified ablation points (220, 230) and the catheter shape and location data.

[0058] It should be understood that the above embodiments are cited by way of example, and this disclosure is not limited to what has been shown and described above. Rather, the scope of this disclosure includes combinations and sub-combinations of the various features described above, as well as variations and modifications thereof, which will occur to those skilled in the art upon reading the above description and which are not disclosed in the prior art.

[0059] For example, features, materials, properties, or groups described in connection with a particular aspect, arrangement, or example should be understood to apply to any other aspect, arrangement, or example described elsewhere in this section or in this specification, unless incompatible with it. All features disclosed in this specification (including any appended claims, abstract, and drawings) and / or all steps of any method or process so disclosed may be combined in any combination except for combinations in which at least some of such features and / or steps are mutually exclusive.

[0060] While operations may be depicted in a specific order in the drawings or described in the specification, it is not necessary to perform such operations in the specific order shown or in sequential order, or to perform all operations, to achieve the desired result. Other operations not depicted or described may be incorporated into the exemplary methods and processes. For example, one or more additional operations may be performed before, after, simultaneously with, or between any described operation. Additionally, in other specific embodiments, these operations may be rearranged or reordered. Those skilled in the art will appreciate that in some arrangements, the actual steps taken in the illustrated and / or disclosed processes may differ from the steps shown in the figures. Depending on the arrangement, some of the steps described above may be removed, and other steps may be added. Furthermore, the features and properties of the specific arrangements disclosed above may be combined in different ways to form additional arrangements, all of which fall within the scope of this disclosure.

[0061] The scope of this disclosure is defined only by reference to the following claims.

Claims

1. A method for generating ablation maps of cardiac chambers, the method comprising: Receive anatomical mapping of at least a portion of the wall tissue of the heart chambers, the mapping including different anatomical regions; Receives multiple ablation points generated by a multi-electrode catheter; Using a classification algorithm that takes into account catheter shape data, anatomical regions are identified and all of the plurality of ablation points are classified as belonging to the identified anatomical regions; as well as Based on the classified ablation points and the catheter shape data, corresponding ablation labels are displayed on the anatomical mapping.

2. The method according to claim 1, wherein, Using the classification algorithm includes identifying the region by determining that a majority of the ablation points fall within the anatomical region.

3. The method according to claim 1, wherein, The classification algorithm includes identifying the region by assuming that the centroid of the ablation point falls within the anatomical region.

4. The method according to claim 1, wherein, The classification algorithm used includes: Weights are assigned to each ablation point based at least in part on the catheter shape data; and The anatomical regions are identified at least in part based on the subgroup of ablation points that produce the highest total weight.

5. The method according to claim 1, wherein, Using the classification algorithm includes: identifying the region by determining the probability that the ablation point belongs to the anatomical region, the probability being calculated based on the distance of each of the plurality of ablation points from the anatomical region on the mapping map.

6. The method according to claim 1, wherein, Using the classification algorithm includes: training a machine learning (ML)-based algorithm based on a dataset of labeled ablation points, and using the trained ML-based algorithm to infer the anatomical region of the received multiple ablation points.

7. The method according to claim 6, wherein, Training the machine learning (ML) model involves training the model using data labeled with one or more of the following given classification algorithms: majority voting classification algorithm, centroid location classification algorithm, distance-based probability classification algorithm, and weighted ablation point-based classification algorithm.

8. The method according to claim 1, wherein, The anatomical mapping is an electroanatomical (EA) mapping.

9. A system for generating ablation maps of cardiac chambers, the system comprising: A memory configured to store classification algorithms; and a processor, wherein the processor is configured to: Receive anatomical mapping of the wall tissue of at least a portion of the cardiac chamber, the mapping including different anatomical regions; Receives multiple ablation points generated by a multi-electrode catheter; Using the classification algorithm that takes into account catheter shape data, anatomical regions are identified and all of the plurality of ablation points are classified as belonging to the identified anatomical regions; as well as Based on the classified ablation points and the catheter shape data, corresponding ablation labels are displayed on the anatomical mapping.

10. The system according to claim 9, wherein, The processor is configured to identify the region by determining that most of the ablation points fall within the anatomical region, thereby using the classification algorithm.

11. The system according to claim 9, wherein, The processor is configured to identify the region by assuming that the centroid of the ablation point falls within the anatomical region, thereby using the classification algorithm.

12. The system according to claim 9, wherein, The processor is configured to use the classification algorithm in the following manner: Weights are assigned to each ablation point based at least in part on the catheter shape data; as well as The anatomical regions are identified at least in part based on the subgroup of ablation points that produce the highest total weight.

13. The system according to claim 9, wherein, The processor is configured to identify the region by determining the probability that the ablation point belongs to the anatomical region, thereby using the classification algorithm, the probability being calculated based on the distance of each of the plurality of ablation points from the anatomical region on the mapping map.

14. The system according to claim 9, wherein, The processor is configured to train a machine learning (ML)-based algorithm using a dataset of labeled ablation points, and to use the trained ML-based algorithm to infer the anatomical regions of the received multiple ablation points, thereby employing the classification algorithm.

15. The system according to claim 14, wherein, The processor is configured to train the machine learning (ML) model by using data labeled with one or more of the following given classification algorithms: majority voting classification algorithm, centroid location classification algorithm, distance-based probability classification algorithm, and weighted ablation point-based classification algorithm.

16. The system according to claim 9, wherein, The anatomical mapping is an electroanatomical (EA) mapping.

Images