Brain embolism protection selection method for TAVI operation

Abstract

It is determined whether to deploy a cerebral embolism protection (CEP) device by initially retrieving one or more images of at least a portion of the aorta. The image includes an aortic valve. The image is segmented to identify an aortic valve, an aortic arch, and a plurality of branch vessels downstream of the aortic valve. A plaque in a segment of the image located at or near the aortic valve is identified and a vulnerability score associated with the plaque is generated. The dynamics of the blood flow in the aortic arch and at least one of the plurality of branch vessels are evaluated. It is then determined whether the CEP device should be deployed based at least in part on the vulnerability score. The CEP device is selected based at least in part on the dynamics of blood flow in the aortic arch.

Description

Technical Field

[0001] The present disclosure generally relates to systems and methods for determining the need for cerebral embolic protection (CEP) during a procedure, such as a surgical procedure, and for selecting an appropriate such protection. In particular, the present disclosure relates to determining an appropriate CEP device to use during a TAVI or TAVR procedure. Background Art

[0002] Medical procedures involving arterial blood vessels often create the risk that plaque will break away from the vessel wall. For example, transcatheter aortic valve implantation or replacement (TAVI / TAVR, used interchangeably) can create the risk that plaque fragments will break away and travel with the blood through the various arteries, potentially causing a stroke, among other potential effects.

[0003] Cerebral embolic protection (CEP) devices have been available for some time and take several forms. Two examples are Boston Scientific's Sentinel system and Keystone Heart's TriGuard. The purpose of these devices is to capture plaque fragments that break away during a TAVI procedure when the prosthetic valve is inserted. Therefore, a CEP device is typically used as a filter that filters blood flowing into specific blood vessels that branch off from the aortic arch. Typically, there are three major arteries extending from the aortic arch that may need protection. While the Sentinel only covers the innominate artery and the left common carotid artery, the TriGuard additionally covers the left subclavian artery (the left vertebral artery originates from the left subclavian artery), thereby covering the three major arteries extending from the aortic arch.

[0004] Not all patients require or even benefit from the use of a CEP device in the context of a procedure such as TAVI. Furthermore, the use of a CEP device may increase the time and / or costs associated with the procedure and may not be desirable in all circumstances. Therefore, it is desirable to determine whether a patient will benefit from the use of a CEP device prior to a TAVI or TAVR procedure. Furthermore, as described above, while there are three major cerebral vessels branching from the aortic arch, not all CEP devices cover all three, and in the event that a CEP device is determined to be appropriate, not all patients will benefit from having all vessels covered.

[0005] Therefore, there is a need for a preoperative method for identifying patients who may benefit from a CEP device during a TAVI procedure, as well as a method for selecting and implanting a CEP device once such a CEP device is determined to be appropriate. Summary of the invention

[0006] The present invention provides methods and systems for selecting and implanting cerebral embolic protection devices in the context of surgery, such as TAVI surgery.

[0007] The method assumes that if the patient has plaque in the region of the aorta where the new valve is deployed, the patient will benefit from a CEP device during the TAVI procedure. Furthermore, if the angle between the aorta and the left subclavian artery is relatively small, a device covering all three brain branches of the aorta will provide benefit. The presence of two features can be detected in a computed tomography (CT) image, such as a spectral CT image.

[0008] In some embodiments, a method for deploying a cerebral embolic protection (CEP) device is provided, wherein the method includes retrieving one or more images of at least a portion of the aorta. The one or more images include the aortic valve. The method includes segmenting the one or more images to identify the aortic valve, the aortic arch, and a plurality of branch vessels located downstream of the aortic valve.

[0009] The method then identifies plaque in segments of the one or more images at or near the aortic valve and generates a vulnerability score associated with the identified plaque.The method then evaluates the dynamics of blood flow in at least one of the plurality of branch vessels and the aortic arch.

[0010] The method then determines that a CEP device should be deployed based at least in part on the vulnerability score, and selects a CEP device from a plurality of potential CEP devices based at least in part on the dynamics of blood flow in the aortic arch.

[0011] In some embodiments, the vulnerability score is associated with a risk of at least a portion of the plaque detaching during a surgical procedure performed on the aortic valve. Such a procedure may be a transcatheter aortic valve implantation (TAVI) procedure performed on the aortic valve.

[0012] In some embodiments, the vulnerability score is based at least in part on the type of implant to be used in the TAVI procedure.

[0013] In some embodiments, the vulnerability score is based at least in part on the total plaque volume and spatial organization of plaque at or near the aortic valve and the lipid fraction in the total plaque volume. In some such embodiments, the vulnerability score is also based on morphological factors associated with the plaque.

[0014] In some embodiments, the vulnerability score is determined by an artificial intelligence (AI) based model trained based on known outcomes of prior surgical interventions associated with corresponding historical images of the aorta, wherein the historical images include the corresponding aortic valve.

[0015] In some embodiments, a determination that a CEP device should be deployed is based at least in part on a vulnerability score rather than a branching angle, and a CEP device to be deployed is selected based at least in part on a branching angle rather than a vulnerability score.

[0016] In some embodiments, the one or more images are one or more computed tomography (CT) images, and segmentation of the one or more images is achieved by an artificial intelligence (AI) based model to identify the aortic arch and the left subclavian artery (LSA).

[0017] In some embodiments, the method includes identifying a branching angle between the LSA and the aortic arch, and selection of the CEP device is based on a fluid dynamic model of blood flow between the aortic arch and the LSA, the fluid dynamic model determining a likelihood that plaque in the aortic arch will enter the LSA based at least in part on the identified branching angle.

[0018] In some embodiments, the fluid dynamics model is also based on the size of the LSA, and the size of the LSA is determined from the image or is independently known.

[0019] In some embodiments, the plurality of branch vessels include the brachiocephalic artery, the left common carotid artery (CCA), and the LSA. A first CEP device in the plurality of CEP devices covers the brachiocephalic artery and the CCA, but not the LSA, and a second CEP device in the plurality of CEP devices covers the brachiocephalic artery, the CCA, and the LSA.

[0020] In some embodiments, the branch angle is located between the left subclavian artery (LSA) and the aortic arch. The method then includes determining whether the size of the LSA is greater than a threshold size, and a first CEP device in the plurality of CEP devices covers the brachiocephalic artery and the CCA but not the LSA, and a second CEP device in the plurality of CEP devices covers the brachiocephalic artery, the CCA, and the LSA. Once the method determines that a CEP device should be deployed and the LSA is greater than the threshold size or the branch angle is greater than the threshold angle, the method further determines that a second CEP device should be deployed.

[0021] A system for deploying a CEP device is also provided herein, wherein the system comprises a plurality of implantable potential CEP devices, a memory for storing a plurality of instructions, and a processor circuit coupled to the memory and configured to execute the instructions to implement the above method.

[0022] Instructions are executed to: retrieve one or more images of at least a portion of an aorta to be treated, the one or more images including the aortic valve; segment the one or more images to identify the aortic valve, the aortic arch, and a plurality of branch vessels located downstream of the aortic valve; identify plaque in a segment of the one or more images at or near the aortic valve; generate a vulnerability score associated with the identified plaque, the vulnerability score being associated with a risk that at least a portion of the plaque will detach during a surgical procedure performed on the aortic valve; determine that a CEP device should be deployed based on the vulnerability score; identify a branch angle between one of the plurality of branch vessels and the aortic arch; and select a CEP device from a plurality of potential implantable CEP devices based at least in part on the branch angle.

[0023] The selected CEP device is then implanted prior to performing the surgical procedure.

[0024] In some embodiments, the system includes a computed tomography (CT) imaging device.The processor circuit can then retrieve one or more images from the imaging device. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 is a schematic diagram of a system according to one embodiment of the present disclosure.

[0026] Figure 2 Shown is the heart and aorta assessed by a method according to the present disclosure.

[0027] Figure 3A The aortic arch is shown as assessed by a method according to the present disclosure.

[0028] Figure 3B Shown is a scan of an aortic valve assessed by a method according to the present disclosure.

[0029] Figure 3C Shown is a scan of the aortic arch assessed by a method according to the present disclosure.

[0030] Figure 4 A first potential CEP device deployed according to the method of the present disclosure is shown.

[0031] Figure 5 A second potential CEP device deployed according to the methods of the present disclosure is shown.

[0032] Figure 6 A method for processing an image according to the present disclosure is shown. DETAILED DESCRIPTION

[0033] The description of the illustrative embodiments according to the principles of the present invention is intended to be read in conjunction with the accompanying drawings, which are considered to be part of the entire written description. In the description of the embodiments of the present invention disclosed herein, any reference to direction or orientation is intended only to facilitate description and is not intended to limit the scope of the present invention in any way. Relative terms such as "lower", "upper", "horizontal", "vertical", "above", "below", "up", "down", "top" and "bottom" and their derivatives (e.g., "horizontally", "downwardly", "upwardly", etc.) should be interpreted as referring to the orientation as then described or as shown in the drawings discussed. These relative terms are only for convenience of description and do not require the device to be constructed or operated in a specific orientation unless explicitly indicated. Unless otherwise explicitly described, terms such as "attach", "attach", "connect", "couple", "interconnect" and similar terms refer to a relationship in which structures are fixed or attached to each other directly or indirectly through intermediate structures, as well as a movable or rigid attachment or relationship. In addition, the features and benefits of the present invention are explained by reference to exemplary embodiments. Therefore, the present invention should clearly not be limited to such exemplary embodiments that illustrate some possible non-limiting feature combinations that may exist alone or in other feature combinations; the scope of the present invention is defined by the attached claims.

[0034] The present disclosure describes one or more best modes of implementing the present invention currently contemplated. This specification is not intended to be understood in a restrictive sense, but rather provides examples of the present invention presented for illustrative purposes only, with reference to the accompanying drawings, so as to inform those of ordinary skill in the art of the advantages and configurations of the present invention. In the various views of the accompanying drawings, the same reference numerals represent the same or similar parts.

[0035] It is important to note that the disclosed embodiments are merely examples of the many advantageous uses of the innovative teachings herein. In general, statements made in the specification of the present application do not necessarily limit any of the various claimed disclosures. In addition, some statements may apply to some inventive features but not to others. In general, unless otherwise stated, a single element may be plural and vice versa without loss of generality.

[0036] A preoperative method for identifying patients who may benefit from a CEP device during a TAVI procedure is described herein. In general, if a patient is scheduled for a TAVI procedure, the method described herein may be applied to determine whether the patient is a good candidate for a CEP device. Once a patient is determined to be a good candidate for such a CEP device, the method includes selecting an appropriate CEP device prior to the TAVI procedure, and in some embodiments implanting the appropriate CEP device.

[0037] The method assumes that if a patient has plaque in the region of the aorta where the new valve is deployed, and if the composition of such plaque means that it is likely to detach, then the patient will benefit from a CEP device during the TAVI procedure. Furthermore, if plaque in the blood flow away from the operative site is likely to flow into the left subclavian artery, then a device covering all three cerebral branches of the aorta will provide benefit. To assess this likelihood, the method may employ a fluid dynamics-based analysis, or an alternative to such an analysis. For example, if the angle between the aortic arch and the left subclavian artery (LSA) is relatively small, then such a risk may be less likely. Similarly, a smaller LSA means there is less risk that plaque will enter the vessel. The presence of such anatomical features can be detected in medical images obtained from the patient.

[0038] Thus, the method typically includes retrieving an image of at least a portion of the aorta in which the TAVI procedure is to be performed. Such an image is typically a CT image, and may be a spectral CT image, and captures the patient's aortic valve, left ventricular outflow tract, and aortic arch. In some embodiments, as part of the method, a CT unit may be employed to generate one or more images. However, in many embodiments, imaging will be performed prior to the surgical procedure, and such existing imaging may be used to implement the methods described herein.

[0039] In addition, in some embodiments, preoperative imaging can take forms other than CT. In medical imaging other than CT, such as magnetic resonance imaging (MRI) or positron emission tomography (PET), different methods can be used to process the image, and the resulting image can take different forms. In the present disclosure, embodiments are discussed in terms of CT imaging. However, it should be understood that the methods and systems described herein can also be used in the context of other imaging modalities.

[0040] Figure 1 1 is a schematic diagram of a system 100 according to an embodiment of the present disclosure. As shown in the figure, the system 100 generally includes a processing device 110 and an imaging device 120.

[0041] The processing device 110 may apply processing routines to images or measured data, such as projection data, received from the imaging device 120. The processing device 110 may include a memory 113 and a processor circuit 111. The memory 113 may store a plurality of instructions. The processor circuit 111 may be coupled to the memory 113 and may be configured to execute instructions. The instructions stored in the memory 113 may include processing routines (such as machine learning algorithms and various filters for processing images) and data associated with the processing routines. Although all data is described as being stored in the memory 113, it should be understood that in some embodiments, some data may be stored in a database, which itself may be stored in the memory or in a separate remote system.

[0042] The processing device 110 may also include an input device 115 and an output device 117. The input device 115 may receive information, such as an image or measured data, from the imaging device 120. The output device 117 may output information, such as a processed image, to a user or a user interface device. Similarly, the output device 117 may output a determination result generated by the method described below, such as a recommendation result. The output device may include a monitor or display.

[0043] In some embodiments, processing device 110 may be directly associated with imaging device 120. In alternative embodiments, processing device 110 may be distinct from imaging device 120 such that it receives images or measured data for processing via a network or other interface at input device 115.

[0044] In some embodiments, the imaging device 120 may include an image data processing device, and a spectral or conventional CT scanning unit for generating CT projection data when scanning an object (eg, a patient).

[0045] Although a system including an imaging device 120 and a processing device 110 is shown, it should be understood that the method can be implemented directly on the processing device, such as in the case of images received at an input device 115 via a network. The methods described herein include processing images, which are typically used as part of deploying a cerebral embolic protection (CEP) device in the context of a procedure such as a TAVI procedure. As described above, prior to such a procedure, imaging is performed. In this way, previously generated imaging can be retrieved via the input device 115 and evaluated prior to or in lieu of obtaining a new image.

[0046] Figure 2 Shown are a heart 200 and aorta 210 being assessed by methods according to the present disclosure. Figure 3A Shows Figure 2 A more detailed view of the aortic arch 220 is shown and evaluated by methods according to the present disclosure. Figure 3B A scan of an aortic valve 230 is shown being assessed by a method according to the present disclosure. Figure 3C A scan of an aortic arch 220 evaluated by a method according to the present disclosure is shown.

[0047] Figure 4 A first potential CEP device 400 is shown deployed according to the methods of the present disclosure. Figure 5 A second potential CEP device 500 is shown deployed according to the methods of the present disclosure. Figure 6 A method for processing an image according to the present disclosure is shown.

[0048] like Figure 3B and Figure 3C As shown, one or more images of a portion of a patient may be retrieved to assess Figure 2 Such an image may include the left ventricular outflow tract (LVOT) 240, the aortic valve 230, the ascending aorta 250, the aortic arch 220, and the descending aorta 260. Three major branch vessels can be identified from the aortic arch, including the brachiocephalic artery (also known as the brachiocephalic trunk or innominate artery) 270, the left common carotid artery (CCA) 280, and the left subclavian artery (LSA) 290.

[0049] like Figure 4 and Figure 5 As shown, some CEP devices 400 cover all three major branch vessels 270 , 280 , 290 , while other CEP devices 500 cover only two such vessels, typically the brachiocephalic artery 270 and the CCA 280 .

[0050] In implementing the method, the described system 100 may first retrieve (600) at the input device 115 at least a portion of the aorta 210 (such as Figure 3A It should be understood that the one or more images provided should show the aortic valve 230 and the major branch vessels 270, 280, 290. However, these features are typically in different planes. Figure 3B and Figure 3C As shown, a first image 3B may be provided to show the LVOT 240 , the aortic valve 230 , and the ascending aorta 250 , and a second image 3C may be provided to show three main branch vessels 270 , 280 , 290 .

[0051] Therefore, it should be understood that in the context of the present disclosure, when referring to an image retrieved by the system 100, this may refer to one or more images.

[0052] The method then implements various image processing methods (610), and in doing so, identifies plaque (620) in segments of the image at or near the aortic valve 230 and the left ventricular outflow tract 240 (including the ascending aorta 250). The retrieved image (at 600) may be a CT scan of the patient, and in some embodiments, it may be a spectral CT scan.

[0053] Thus, the method may first implement various processing methods (at 610) and apply them to the retrieved image before identifying plaque (at 620). Such processing methods may include model-based segmentation, which may fit a surface model or voxel mask onto the image. Other segmentation methods may also be used. Such processing may then be used to identify and segment various vessels associated with the aorta, including the aortic arch 220 and the three major branch vessels 270, 280, 290.

[0054] The segmentation or other image processing performed by the method (at 610) can be implemented by an AI-based model (such as a convolutional neural network (CNN)), and such a method can then be used to identify the aortic arch 220 and the LSA 290, and the branching angle 300 can then be defined between the aortic arch and the LSA.

[0055] Once plaque is identified (at 620) and determined to be at or near the aortic valve 230, such plaque may be analyzed (630). Because the TAVI procedure involves implanting or replacing the aortic valve 230, any plaque in this area may be disturbed during the procedure, and therefore, the analysis (at 630) determines whether such plaque may become detached during the procedure.

[0056] The analysis (at 630) may consider various factors associated with the plaque, including the total volume 660 of the plaque, the precise spatial configuration 670 of the plaque, the specific composition 680 of the plaque (such as the lipid fraction in the total plaque volume), and morphological factors 690 associated with the plaque (such as the roughness of the plaque surface). Aspects of the spatial configuration 670 of the plaque considered may include circumferential coverage and coverage of the area where the implant will be deployed.

[0057] The analysis (at 630) may also take into account external factors 700, such as the type of implant to be used and the precise nature of the surgery to be performed, as well as risk factors associated with the patient. If the image retrieved (at 600) is a spectral CT scan image, some characteristics of the plaque may be more easily identified during the analysis.

[0058] The analysis (630) may then generate a vulnerability score (710) associated with the identified plaque (at 620). Such a vulnerability score may be a surrogate for, and therefore may be correlated with, the risk of the plaque becoming detached during a surgical procedure applied to the aortic valve. The analysis (630) may be an AI model independent of the segmentation model (at 610) implemented above. The AI ​​model may be, for example, a convolutional neural network and may be trained based on historical medical images (such as spectral CT scan images) of a similar type to that retrieved (at 600) paired with known outcome data for intraoperative and postoperative complications. In some embodiments, the AI ​​model may be trained based on the amount of plaque in the surgical area before and after surgery, which may be indicative of detachment of plaque during surgery.

[0059] In some embodiments, the vulnerability score is based at least in part on the type of implant used in a particular TAVI procedure. In some embodiments, the vulnerability score is based at least in part on the total plaque volume and spatial organization of plaque at or near the aortic valve and the lipid fraction in the total plaque volume. In some embodiments, the vulnerability score is also based on morphological factors associated with the plaque, such as surface roughness.

[0060] Once the analysis (at 630) generates a vulnerability score (710), such score is used to determine (720) whether a CEP device should be deployed for the patient prior to the TAVI procedure. In some embodiments, the vulnerability score (at 710) may be a single value, and the determination (at 720) is simply a determination of whether the generated value is above or below a threshold. In other embodiments, the vulnerability score (at 710) may include additional factors, including, for example, other risk factors associated with the patient 700, and the determination (at 720) may then be collated to generate a recommendation result.

[0061] In some embodiments, further analysis of the image is performed only if the method first determines (at 720) that a CEP device should be deployed. In other embodiments, all image analyses are performed in parallel.

[0062] Thus, the method also utilizes segmentation of the aortic arch 220 (performed at 610) to determine (730) whether plaque that has detached from the wall of the aorta 210 at or near the valve 230 is likely to flow into a specific branch vessel. Although all vessels can be evaluated, the LSA 290 is typically evaluated in particular. CEP devices 400, 500 contemplated for implantation typically cover and thereby protect at least the brachiocephalic artery 270 and the left CCA 280. Some CEP devices 400 also cover and thereby protect the LSA 290.

[0063] Thus, a determination is made (at 730) of the likelihood that plaque, which is typically concentrated in the blood, will flow through the aortic arch 220 into the LSA 290. This determination (at 730) may be based on a fluid dynamics model and may include an evaluation of a branching angle 300 of at least one of the branch vessels relative to the centerline 310 of the aortic arch 220. Specifically, a determination may be made (at 730) to calculate the branching angle 300 of the LSA 290 relative to the aortic arch 220. The calculation may be based on the direction of the local centerline 310 in the aortic arch 220 and the angle between the proximal LSA 290. A smaller angle 300 between the aortic arch 220 and the LSA 290 indicates that the two vessels are more similar in flow direction and, therefore, may result in a higher likelihood that plaque debris will be flushed into the LSA by blood flow in the aorta.

[0064] Thus, if the angle 300 is smaller, the method may recommend a CEP device 400 that covers all three vessels 270, 280, 290. Alternatively, if the angle 300 is larger, the method may instead recommend a CEP device 500 that covers only the brachiocephalic artery 270 and the left CCA 280. In some embodiments, a threshold angle is used, and a risk range is thus defined within which a CEP device 400 covering the LSA 290 is recommended. For example, an angle 300 of zero degrees would indicate that the LSA 290 is straight ahead relative to blood flow in the aortic arch 220, and an angle less than 90 degrees would indicate risk, while an angle greater than 90 degrees would not indicate such risk.

[0065] The method may also consider additional factors that are part of the fluid dynamics model to support the determination (730). Thus, the segmentation model may allow the method to determine the size of the LSA 290, such as the diameter of the vessel. In some embodiments, the size of the LSA 290 is not determined based on the segmentation model, but is directly known. A larger LSA 290 will result in a higher likelihood of plaque fragments being flushed into the LSA by blood flow in the aorta 210, and the method should therefore result in selecting a CEP device 400 that covers all three vessels. Alternatively, if the LSA 290 is smaller, the method may instead recommend a CEP device 500 that only covers the brachiocephalic artery 270 and the left CCA 280. In some embodiments, the assessment of the size of the LSA 290 is based on a fraction of the total luminal area of ​​all 3 arteries, and the LSA 290 is then assessed to determine whether it contains more than one-third of the total luminal area. In such an embodiment, if the LSA 290 encompasses more than one-third of the total luminal area of ​​the three vessels 270, 280, 290, it would indicate risk, and the determination (at 730) would result in a recommendation to use a CEP device 400 covering the LSA 290. In other embodiments, the LSA 290 may be evaluated in comparison to the total luminal area of ​​the aortic arch 220.

[0066] Thus, in some embodiments, the method may rely only or primarily on the branch angle 300, which may then be compared to a threshold value (e.g., ninety degrees) to determine whether the LSA 290 should be covered by the CEP device 400. Similarly, the method may rely only or primarily on the size of the LSA 290, and in such embodiments, that size may be compared to a threshold value (such as one-third of the total luminal area of ​​the three vessels 270, 280, 290) to determine whether the LSA 290 should be covered. In some embodiments, more complex fluid dynamic models may be utilized, and the determination (at 730) may be based on the branch angle 300, the size of the LSA 290, and in some cases, additional factors, such as the blood flow rate in the patient.

[0067] In some such embodiments, an AI model may be utilized to make the determination (at 730). The AI ​​model may then be trained based on the anatomical and geometric classification, plaque characteristics, and / or the device to be used, and may be provided with historical imaging (such as spectral CT imaging) paired with known outcome data for complications. The output of such an AI model may be a recommendation of which CEP device should be used. Similar training may be applied to new devices entering the market.

[0068] In some embodiments, the determination (at 720) that a CEP device should be deployed is based at least in part on the vulnerability score (at 710) rather than the branch angle 300, and the CEP devices 400, 500 to be deployed are selected based at least in part on the branch angle rather than the vulnerability score. Thus, the determination results may be discrete. Alternatively, these determination results may be used to inform each other.

[0069] Once the determination is made (at 730), and assuming the method has also determined that use of a CEP device is desirable (at 720), the method may select (at 740) a CEP device from a plurality of potential CEP devices based at least in part on the vulnerability score and the branching angle.

[0070] Once selected (at 740), the CEP device may be implanted (750) prior to a medical procedure such as TAVI.

[0071] In some embodiments, the method is implemented by the above-described system 100 (with or without an imaging device 120 (which may be a spectral CT device)). The system 100 also includes a plurality of implantable potential CEP devices 400, 500, wherein one of the CEP devices 500 is configured to cover and thereby protect only the brachiocephalic artery 270 and the left CCA 280. The second CEP device 400 is alternatively configured to cover and thereby protect the brachiocephalic artery 270, the left CCA 280, and the LSA 290.

[0072] The method is then implemented by the system 100, and once it is determined by the system that a CEP device 400, 500 should be deployed based on the vulnerability score, the system further selects the CEP device for implantation. The selected CEP device is then implanted prior to performing the surgical procedure.

[0073] Although the method and system are described in terms of TAVI / TAVR procedures, similar methods may be applied in an adapted form to identify risks during other vascular interventions. For example, the risks of abdominal artery stenting or carotid artery stenting may be similarly identified.

[0074] The method according to the present disclosure can be implemented on a computer as a computer-implemented method, or implemented in dedicated hardware, or implemented in a combination of the two. The executable code of the method according to the present disclosure can be stored on a computer program product. Examples of computer program products include memory devices, optical storage devices, integrated circuits, servers, online software, etc. Preferably, the computer program product may include a non-transitory program code stored on a computer-readable medium for executing the method according to the present disclosure when the program product is executed on a computer. In one embodiment, the computer program may include a computer program code suitable for executing all steps of the method according to the present disclosure when the computer program is running on a computer. The computer program may be contained on a computer-readable medium.

[0075] While the present disclosure has been described in detail and specifically with respect to several described embodiments, it is not intended to be limited to any such details or embodiments or to any specific embodiment, but rather is to be interpreted with reference to the appended claims so as to provide the broadest possible interpretation of such claims based on the prior art and thereby effectively encompass the intended scope of the present disclosure.

[0076] All examples and conditional language described herein are intended to be used for teaching purposes, so as to help the reader understand the principles of the present disclosure and the concepts contributed by the inventor to promote this area, and should be interpreted as not being limited to such specific examples and conditions of recording. In addition, all statements of the principles, aspects and embodiments of the present disclosure and its specific examples recorded herein are intended to cover their structural and functional equivalents. In addition, these equivalents are intended to include currently known equivalents and equivalents developed in the future, that is, any element that performs the same function developed, regardless of the structure.

Claims

1. A method for deploying a cerebral embolic protection (CEP) device, comprising: retrieving one or more images of at least a portion of the aorta, the one or more images including the aortic valve; segmenting the one or more images to identify the aortic valve, the aortic arch, and a plurality of branch vessels located downstream of the aortic valve; identifying plaque in a segment of the one or more images at or near the aortic valve; generating a vulnerability score associated with the identified plaque; evaluating the dynamics of blood flow in at least one of the plurality of branch vessels and the aortic arch; determining that the CEP device should be deployed based at least in part on the vulnerability score; as well as A CEP device is selected from a plurality of potential CEP devices based at least in part on the dynamics of blood flow in the aortic arch.

2. The method according to claim 1, wherein: The vulnerability score is associated with a risk that at least a portion of the plaque will detach during a surgical procedure performed on the aortic valve.

3. The method according to claim 2, wherein: The surgical procedure is a transcatheter aortic valve implantation (TAVI) procedure applied to the aortic valve.

4. The method according to claim 3, wherein: The vulnerability score is based at least in part on a type of implant to be used in the TAVI procedure.

5. The method according to claim 2, wherein: The vulnerability score is based at least in part on the total plaque volume and spatial organization of the plaque at or near the aortic valve and the lipid fraction in the total plaque volume.

6. The method according to claim 5, wherein: The vulnerability score is also based on morphological factors associated with the plaque.

7. The method according to claim 5, wherein: The vulnerability score is determined by an artificial intelligence (AI) based model trained based on known outcomes of prior surgical interventions associated with corresponding historical images of the aorta, each historical image including a corresponding aortic valve.

8. The method according to claim 5, wherein: A determination that a CEP device should be deployed is based at least in part on the vulnerability score rather than a branching angle, and the CEP device to be deployed is selected based at least in part on the branching angle rather than the vulnerability score.

9. The method according to claim 1, wherein: The one or more images are one or more computed tomography (CT) images, and segmentation of the one or more images is performed by an artificial intelligence (AI) based model to identify the aortic arch and the left subclavian artery (LSA).

10. The method according to claim 9, wherein: The method also includes identifying a branching angle between the LSA and the aortic arch, wherein selection of the CEP device is based on a fluid dynamic model of blood flow between the aortic arch and the LSA, the fluid dynamic model determining a likelihood that plaque in the aortic arch will enter the LSA based at least in part on the identified branching angle.

11. The method according to claim 10, wherein: The fluid dynamics model is also based on the size of the LSA, wherein the size of the LSA is determined from the image or is independently known.

12. The method according to claim 10, wherein: The multiple branch vessels include the brachiocephalic artery, the left common carotid artery (CCA) and the LSA, and a first CEP device among the multiple CEP devices covers the brachiocephalic artery and the CCA but does not cover the LSA, and a second CEP device among the multiple CEP devices covers the brachiocephalic artery, the CCA and the LSA.

13. The method according to claim 1, wherein: The branch angle is between a left subclavian artery (LSA) and the aortic arch, the method further comprising determining whether a size of the LSA is greater than a threshold size, and wherein a first CEP device among the plurality of CEP devices covers the brachiocephalic artery and the CCA but does not cover the LSA, and a second CEP device among the plurality of CEP devices covers the brachiocephalic artery, the CCA, and the LSA; When it is determined that the CEP device should be deployed and the LSA is greater than the threshold size or the branch angle is greater than the threshold angle, it is further determined that the second CEP device should be deployed.

14. A system for deploying a cerebral embolic protection (CEP) device, comprising: Multiple potential implantable CEP devices; A memory for storing a plurality of instructions; a processor circuit coupled to the memory and configured to execute the instructions to: retrieving one or more images of at least a portion of the aorta to be processed, the one or more images including the aortic valve; segmenting the one or more images to identify the aortic valve, the aortic arch, and a plurality of branch vessels located downstream of the aortic valve; identifying plaque in a segment of the one or more images at or near the aortic valve; generating a vulnerability score associated with the plaque, the vulnerability score being related to a risk of at least a portion of the plaque detaching during a surgical procedure applied to the aortic valve; Determining that the CEP device should be deployed based on the vulnerability score; identifying a branching angle between one of the plurality of branch vessels and the aortic arch; as well as selecting the CEP device from a plurality of implantable potential CEP devices based at least in part on the branch angle, Wherein, the selected CEP device is implanted prior to performing the surgical procedure.

15. The system of claim 14, wherein: The surgical procedure is a transcatheter aortic valve implantation (TAVI) procedure applied to the aortic valve.

16. The system of claim 14, wherein: The vulnerability score is based at least in part on the total plaque volume and spatial organization of the plaque at or near the aortic valve and the lipid fraction in the total plaque volume.

17. The system of claim 14, wherein: The vulnerability score is determined by an artificial intelligence (AI) based model trained based on known outcomes of prior surgical interventions associated with corresponding historical images of the aorta, each historical image including a corresponding aortic valve.

18. The system of claim 14, wherein: The one or more images are one or more spectral computed tomography (CT) images, and segmentation of the one or more images is achieved by an artificial intelligence (AI) based model to identify the aortic arch and the left subclavian artery (LSA), and the branching angle is located between the LSA and the aortic arch, and selection of the CEP device is based on a fluid dynamic model of blood flow between the aortic arch and the LSA, and the fluid dynamic model determines the likelihood that plaque in the aortic arch will enter the LSA based at least in part on the identified branching angle.

19. The system of claim 14, wherein: The branch angle is between a left subclavian artery (LSA) and the aortic arch, wherein it is determined whether a size of the LSA is greater than a threshold size, and wherein a first CEP device among the plurality of CEP devices covers the brachiocephalic artery and the CCA but does not cover the LSA when deployed, and a second CEP device among the plurality of CEP devices covers the brachiocephalic artery, the CCA and the LSA when deployed, Once it is determined that the CEP device should be deployed and the LSA is greater than the threshold size or the branch angle is greater than the threshold angle, it is further determined that the second CEP device should be deployed.

20. The system of claim 14, wherein: The system also includes a computed tomography imaging device, and the processor circuit retrieves the one or more images from the imaging device.

Images