Endovascular navigation device selection

Abstract

Selecting devices (520) for endovascular navigation includes obtaining pre-interventional imagery of a vasculature system (100A). Physical characteristics of the vasculature system (100A) are identified from the pre-interventional imagery. Device characteristics of a plurality of navigational devices (520) are obtained. Expected performance of the plurality of navigational devices (520) is assessed based on the device characteristics of the plurality of navigational devices (520) with respect to the physical characteristics of the vasculature system (100A) from the pre-interventional imagery in a first assessment. A combination of optimal navigational devices (520) to use in an interventional navigation through the vasculature system (100A) during an intervention is identified from among the plurality of navigational devices (520) and based on assessing expected performance in the first assessment.

Description

ENDOVASCUEAR NAVIGATION DEVICE SEEECTIONBACKGROUND

[0001] Endovascular procedures often involve navigating a series of guidewires and catheters to a lesion or clot and then treating the disease with one or more therapeutic devices that are delivered over the guidewire. Navigating to the lesion can be difficult and time-consuming due to a variety of factors, which can include physical characteristics of vessel tortuosity, nonstandard anatomy, calcifications, or complex branch vessel angulation.

[0002] Selecting the optimal guidewire-catheter combinations to be able to navigate tortuous, non-standard, calcified or complex vasculature can be a difficult and time-consuming process. Interventionalists often rely on a significant amount of trial and error, to be able to choose devices that enable successful and efficient navigation to the target anatomy. This can lead to device waste, extended procedure time, additional radiation exposure for the patient and staff, and increased procedure cost.SUMMARY

[0003] According to an aspect of the present disclosure, a method for selecting devices for endovascular navigation includes obtaining pre-interventional imagery of a vasculature system. The method also includes identifying physical characteristics of the vasculature system from the pre-interventional imagery; obtaining device characteristics of a plurality of navigational devices; and assessing expected performance of the plurality of navigational devices based on the device characteristics of the plurality of navigational devices with respect to the physical characteristics of the vasculature system from the pre-interventional imagery in a first assessment. The method further includes identifying, from among the plurality of navigational devices and based on assessing expected performance in the first assessment, a combination of optimal navigational devices to use in an interventional navigation through the vasculature system during an intervention.

[0004] According to another aspect of the present disclosure, a system for selecting devices for endovascular navigation includes a memory that stores instructions, and a processor that executes the instructions. When executed by the processor, the instructions cause the system to:obtain pre-interventional imagery of a vasculature system; identify physical characteristics of the vasculature system from the pre-interventional imagery; obtain device characteristics of a plurality of navigational devices; and assess expected performance of the plurality of navigational devices based on the device characteristics of the plurality of navigational devices with respect to the physical characteristics of the vasculature system from the pre-interventional imagery in a first assessment. The instructions further cause the system to identify, from among the plurality of navigational devices and based on assessing expected performance in the first assessment, a combination of optimal navigational devices to use in an interventional navigation through the vasculature system during an intervention.

[0005] According to another aspect of the present disclosure, a tangible, non-transitory computer-readable medium stores instructions. When executed by a processor, the instructions cause the processor to: obtain pre-interventional imagery of a vasculature system; identify physical characteristics of the vasculature system from the pre-interventional imagery; obtain device characteristics of a plurality of navigational devices; and assess expected performance of the plurality of navigational devices based on the device characteristics of the plurality of navigational devices with respect to the physical characteristics of the vasculature system from the pre-interventional imagery in a first assessment. The instructions further cause the system to identify, from among the plurality of navigational devices and based on assessing expected performance in the first assessment, a combination of optimal navigational devices to use in an interventional navigation through the vasculature system during an intervention.BRIEF DESCRIPTION OF THE DRAWINGS

[0006] The example embodiments are best understood from the following detailed description when read with the accompanying drawing figures. It is emphasized that the various features are not necessarily drawn to scale. In fact, the dimensions may be arbitrarily increased or decreased for clarity of discussion. Wherever applicable and practical, like reference numerals refer to like elements.

[0007] FIG. 1A illustrates a system for endovascular navigation device selection, in accordance with a representative embodiment.

[0008] FIG. IB illustrates a system for endovascular navigation device selection, in accordancewith a representative embodiment.

[0009] FIG. 2A illustrates a method for endovascular navigation device selection, in accordance with a representative embodiment.

[0010] FIG. 2B illustrates another method for endovascular navigation device selection, in accordance with a representative embodiment.

[0011] FIG. 2C illustrates another method for endovascular navigation device selection, in accordance with a representative embodiment.

[0012] FIG. 3 illustrates a user interface showing a peripheral arterial vasculature in endovascular navigation device selection, in accordance with a representative embodiment.

[0013] FIG. 4A illustrates catheter tip shapes in endovascular navigation device selection, in accordance with a representative embodiment.

[0014] FIG. 4B illustrates modelled ranges of motion for guidewire-catheter combinations in in endovascular navigation device selection, in accordance with a representative embodiment.

[0015] FIG. 5 illustrates neural network training and inferencing input and output data in endovascular navigation device selection, in accordance with a representative embodiment.

[0016] FIG. 6 illustrates a user interface showing a device pair recommendation in endovascular navigation device selection, in accordance with a representative embodiment.

[0017] FIG. 7 illustrates a user interface for device recommendation in endovascular navigation device selection, in accordance with a representative embodiment.

[0018] FIG. 8 illustrates a computer system, on which a method for endovascular navigation device selection is implemented, in accordance with another representative embodiment.DETAILED DESCRIPTION

[0019] In the following detailed description, for the purposes of explanation and not limitation, representative embodiments disclosing specific details are set forth in order to provide a thorough understanding of embodiments according to the present teachings. However, other embodiments consistent with the present disclosure that depart from specific details disclosed herein remain within the scope of the appended claims. Descriptions of known systems, devices, materials, methods of operation and methods of manufacture may be omitted so as to avoid obscuring the description of the representative embodiments. Nonetheless, systems, devices,materials and methods that are within the purview of one of ordinary skill in the art are within the scope of the present teachings and may be used in accordance with the representative embodiments. It is to be understood that the terminology used herein is for purposes of describing particular embodiments only and is not intended to be limiting. Definitions and explanations for terms herein are in addition to the technical and scientific meanings of the terms as commonly understood and accepted in the technical field of the present teachings.

[0020] It will be understood that, although the terms first, second, third etc. may be used herein to describe various elements or components, these elements or components should not be limited by these terms. These terms are only used to distinguish one element or component from another element or component. Thus, a first element or component discussed below could be termed a second element or component without departing from the teachings of the inventive concept.

[0021] As used in the specification and appended claims, the singular forms of terms ‘a’, ‘an’ and ‘the’ are intended to include both singular and plural forms, unless the context clearly dictates otherwise. Additionally, the terms "comprises", and / or "comprising," and / or similar terms when used in this specification, specify the presence of stated features, elements, and / or components, but do not preclude the presence or addition of one or more other features, elements, components, and / or groups thereof. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0022] Unless otherwise noted, when an element or component is said to be “connected to”, “coupled to”, or “adjacent to” another element or component, it will be understood that the element or component can be directly connected or coupled to the other element or component, or intervening elements or components may be present. That is, these and similar terms encompass cases where one or more intermediate elements or components may be employed to connect two elements or components. However, when an element or component is said to be “directly connected” to another element or component, this encompasses only cases where the two elements or components are connected to each other without any intermediate or intervening elements or components.

[0023] The present disclosure, through one or more of its various aspects, embodiments and / or specific features or sub-components, is thus intended to bring out one or more of the advantages as specifically noted below.

[0024] As described herein, mechanical models and machine learning models can be developed in order to eliminate the trial-and-error of the device selection process for navigation devices. The mechanical models and machine learning models may be developed to determine anatomyspecific combinations of devices such as guidewire-catheter combinations that are most likely to lead to successful and efficient navigation of complex vasculature. The teachings herein may be used to take a three-dimensional vascular image as input and generate recommendations for one or more optimal device combinations for navigating through the vasculature. Models used to generate the recommendations may take into account interaction between device combinations such as guidewire-catheter combinations, as well as data from previous similar procedures involving particular device combinations in a given anatomy.

[0025] FIG. 1A illustrates a system 100 A for endovascular navigation device selection, in accordance with a representative embodiment.

[0026] The system 100A in FIG. 1A is a system for endovascular navigation device selection and includes components that may be provided together. The system 100A includes a computer 120 and a display 180. The computer 120 includes a first interface 121, a second interface 122 and a controller 150. The controller 150 includes a memory 151 that stores instructions and a processor 152 that executes the instructions. The display 180 includes a graphical user interface 181. The first interface 121 may comprise a user interface or an interface configured to connect the computer 120 to another device. The second interface 122 of the computer 120 is used to connect the computer 120 to the display 180, wirelessly or via wire.

[0027] A computer that can be used to implement the computer 120 is depicted in FIG. 8, though a computer 120 may include more or fewer elements than depicted in FIG. 8. The computer 120 may store and execute a mechanical model and / or a data-driven model to determine anatomyspecific combinations of navigation devices that are most likely to lead to successful and efficient navigation of complex vasculature.

[0028] The display 180 may be a monitor such as a computer monitor, a display on a mobile device, an augmented reality display, a television, an electronic whiteboard, or another screen configured to display electronic imagery. The display 180 may be or include an interactive touch screen configured to display prompts to users and collect touch input from users. The display 180 may be connected to the controller 150 via a local wired interface such as an Ethernet cable orvia a local wireless interface such as a Wi-Fi connection. The display 180 may be interfaced with other user input devices by which users can input instructions, including mouses, keyboards, thumbwheels and so on. The display 180 may also include one or more input interface(s) such as those noted above with respect to the computer 120. Interfaces of the display 180 may connect to other elements or components.

[0029] One or more of the interfaces of the computer 120 and / or the display 180 may include ports, disk drives, wireless antennas, or other types of receiver circuitry that connect the computer 102 and / or the display 180 to other electronic elements. One or more of the interfaces may also include user interfaces such as buttons, keys, a mouse, a microphone, a speaker, a display separate from the display 180, or other elements that users can use to interact with the controller 150 such as to enter instructions and receive output.

[0030] The controller 150 may perform some of the operations described herein directly and may implement other operations described herein indirectly. For example, the controller 150 may indirectly control operations such as by generating and transmitting content to be displayed on the display 180. The controller 150 may directly control other operations such as logical operations performed by the processor 152 executing instructions from the memory 151 based on input received from electronic elements and / or users via the interfaces. Accordingly, the processes implemented by the controller 150 when the processor 152 executes instructions from the memory 151 may include steps not directly performed by the controller 150.

[0031] FIG. IB illustrates a system for endovascular navigation device selection, in accordance with a representative embodiment.

[0032] The system 100B in FIG. IB is a system for endovascular navigation device selection and includes components that may be provided together. The system 100B includes the computer 120 and the display 180 from FIG. IB, and also includes a server 140 connected to the computer 120 via a network 101. The controller 150 is included in the server 140 in FIG. IB, though the computer 120 in FIG. IB may also include a memory that stores instructions and a processor that executes the instructions. In FIG. IB, the relevant functionality described herein is primarily performed directly or indirectly by the controller 150 of the server 140. As shown, some of the system 100B in FIG. IB may be implemented in a networked cloud, such as by rack-mounted servers in a data center.

[0033] A computer that can be used to implement the server 140 is depicted in FIG. 8, though a server 140 may include more or fewer elements than depicted in FIG. 8. The server 140 may store and execute a mechanical model and / or a machine learning model to determine anatomyspecific combinations of navigation devices that are most likely to lead to successful and efficient navigation of complex vasculature.

[0034] FIG. 2A illustrates a method for endovascular navigation device selection, in accordance with a representative embodiment.

[0035] The method of FIG. 2A may be performed by the system 100A or the system 100B.

[0036] At S201, a list of candidate navigation devices and their device mechanical properties including device mechanical characteristics is obtained. The list may be obtained by the computer 120 or by the server 140. The device mechanical properties obtained at S201 may include one or more of a variety of device mechanical properties and device mechanical characteristics including but not limited to device size, device shape, or device stiffness. The list of candidate devices and device mechanical properties may be obtained as a predetermined set which is fixed at the time S201 is performed, or as a filtered set from a predetermined set. Filtering may be performed to identify relevant candidate devices based on the type of medical concern(s) for the patient, patient characteristics, and / or on another basis, to obtain the list of candidate devices and device mechanical properties from a master list of candidate devices and device mechanical properties.

[0037] At S205, pre-interventional imagery is obtained. The pre-interventional imagery is not required to be pre-interventional at S205 insofar as anatomical imaging may be acquired before the current intervention, or during the current intervention but prior to when a device recommendation is to be acquired. The pre-interventional imagery may be obtained by the computer 120 or by the server 140. The pre-interventional imagery may be ultrasound imagery, computed tomography imagery, magnetic resonance imagery, or another type of medical imagery.

[0038] At S207, the pre-interventional imagery is analyzed. The pre-interventional imagery may be analyzed by the computer 120 or by the server 140. The analysis may comprise image analysis, such as by applying an image analysis program to recognize anatomical structures and anomalies.

[0039] At S208, physical characteristics are identified based on analyzing the pre-interventional imagery. The physical characteristics are obtained from the pre-interventional imagery, and are physical characteristics of anatomy of a patient. The physical characteristics may be obtained as or from a three-dimensional shape of the vasculature. The physical characteristics may include one or more of a variety of features including of vessel tortuosity, branch vessel angulation, vessel length, lesion length, lesion diameter, calcifications, fat composition, blood clot composition, presence of prior implants, vessel stiffness, vessel fragility, or vessel diameter.

[0040] At S210, computational modeling is performed based on the list of candidate devices and device mechanical properties including device mechanical characteristics obtained at S201 and the physical characteristics identified at S208. The computational modeling may be performed by the computer 120 or by the server 140. A computational model may also be referred to as a mechanical model, and takes into account mechanical properties of guidewires and catheters or other types of combinable navigation devices such as sheath / needle combinations or sheath / therapeutic device combinations from the candidate list of devices obtained at S201. The computational model may be created to determine the feasible range of motion that can be achieved with each combination of navigation devices, such as when the guidewire is either extended in front of or retracted inside the catheter. The three-dimensional shape of the vasculature may be determined from the pre-interventional imagery obtained at S205 from the pre-operative imaging. Examples of pre-operative imaging may include computed tomography angiography or magnetic resonance angiography. Parameters such as bend radius through tortuous regions, take-off angle of branching vessels, vessel diameter, or vessel wall thickness may be determined by image analysis. The set of device combinations that can achieve the necessary range of motion to navigate the patient-specific anatomy may be determined by running the computational model at S210, and displayed to the user subsequently at S295. Performance of the computational modeling at S210 may be performed by utilizing device characteristics and physical characteristics of the vasculature system from the pre-interventional imagery in a computational model that utilizes mechanical properties of combinations of navigational devices to determine feasible ranges of motion that can be achieved with individual combinations of navigational devices. The device characteristics may include, for example, any one or more of device size, device shape, or device stiffness.

[0041] At S220, one or more optimal combination(s) of navigational devices is or are identified and ranked. The identification and ranking at S220 may be performed by the computer 120 or by the server 140. A ranking of which combination of navigation devices is the best choice among the combinations may be provided to help a user select the most preferable combination. Combinations of optimal navigational devices identified at S220 may comprise combinations of coaxial devices. The combinations may be identified based on compatibility characteristics, such as diameter, length, material, or other characteristics that would be relevant to make two navigational devices compatible with one another. Ranking of a plurality of combinations of navigational devices may be performed based on comparing the device characteristics of the plurality of navigational devices with the physical characteristics of the vasculature system from the pre-interventional imagery in a first comparison. The ranked list of combinations of navigational devices may include a combination of optimal navigational devices.

[0042] At S250, a determination is made whether a device selection should be updated. The determination at S250 may be skipped when no previous device selection was made. The determination at S250 may be based on input from a user, though the determination at S250 may be performed by the computer 120 or by the server 140.

[0043] At S252, if the device selection is to be updated (S250 = Yes), interventional imagery is obtained. The interventional imagery may be obtained, such as in real-time from a medical imaging system, by the computer 120 or by the server 140. The interventional imagery may be obtained during a medical intervention in real-time, such as from ultrasound imaging, x-ray imaging, or computed tomography. In at least some instances, the interventional imaging may be performed independent of S250, and in other instances the interventional imaging may be initiated specifically because of a determination at S250. If the device selection is not to be updated (S250 = No), at S295 the optimal combination of selected navigational devices is output, such as on the display 180.

[0044] In some embodiments, if the device selection is to be updated (S250 = Yes), new interventional imagery may be obtained and analyzed. Optionally, new interventional device characteristics may be obtained if the device selection is to be updated during the intervention (Yes at S250). The interventional device characteristics may be obtained from a real-time sensing method such as electromagnetic sensing or optical shape sensing, which provides thereal-time shape of the device, and these real-time interventional device characteristics may be input as parameter(s) into the computational model or the machine learning model. Other device sensing technologies such as pressure or force sensing at the tip of the device may also be used as parameter(s) input to the computational model or machine learning model to provide data for tissue characteristics or device characteristics. The device characteristics may include, for example, one or more of device size, device shape, or device stiffness.

[0045] At S253, the interventional imagery is again analyzed and at S260 the computational modeling is again performed, either by the server 140 or the server 160.

[0046] At S270, one or more optimal combinations of navigational devices are again identified and ranked, and then the optimal combination(s) are output at S295. The identification and ranking at S270 may be performed by the computer 120 or the server 140, and the outputting at S295 may be via the display 180. Combinations of optimal navigational devices identified at S270 may be obtained based on the computational modeling at S260 and may comprise combinations of coaxial devices, and may be identified and ranked based on the device mechanical properties including device mechanical characteristics identified at S201 and the interventional imagery analyzed at S253.

[0047] FIG. 2B illustrates another method for endovascular navigation device selection, in accordance with a representative embodiment.

[0048] The method of FIG. 2B may be performed by the system 100A or the system 100B. Features of FIG. 2B which are identical to features of FIG. 2A are not repeated in detail for the sake of brevity.

[0049] At S202, a list of candidate devices is obtained, either by the computer 120 or the server 140. The list of candidate devices obtained at S202 may be received alone or along with basic device characteristics such as diameter or weight. Mechanical properties of the candidate devices may also be optionally obtained at S202, though the mechanical properties are not necessarily explicitly used in the method of FIG. 2B. The mechanical properties of the devices may either be explicitly provided to the machine learning model, or the model may infer some information about the mechanical properties of the candidate devices through training.

[0050] At S205, pre-interventional imagery is obtained as in FIG. 2A. The pre-interventional imagery is not required to be pre-interventional at S205 insofar as anatomical imaging may beacquired before the current intervention, or during the current intervention but prior to when a device recommendation is to be acquired. At S207, the pre-interventional imagery may be analyzed as in FIG. 2A, though the pre-processing may be optional in embodiments based on FIG. 2B.

[0051] At S208, physical characteristics of the vasculature are identified. The physical characteristics are characteristics of anatomical structures and anomalies and may include one or more of a variety of features including of vessel tortuosity, branch vessel angulation, vessel length, lesion length, lesion diameter, calcifications, fat composition, blood clot composition, presence of prior implants, vessel stiffness, vessel fragility, or vessel diameter. Identification of the physical characteristics of the vasculature at S208 may be optional in embodiments based on FIG. 2B.

[0052] At S215, a trained machine learning model receives the anatomical images and the list of candidate devices for inferencing. Optionally, pre-processing steps S207 and S208 may be performed on the anatomical images, and the outputs of the pre-processing can be used as inputs to the machine learning model. The trained machine learning model inferencing may be run by the computer 120 or by the server 140. The trained machine learning model may be data-driven. The trained machine learning model may generate device recommendations based on input from actual procedures. Procedural data may be collected by identifying and tracking navigational devices in fluoroscopic imaging. A success metric may be calculated for each device combination and anatomy, taking into account, for example, how long it took to navigate through a segment of the vasculature or how far the devices were able to navigate through certain vessels. The machine learning model may take as input the anatomical information from pre-operative imaging and create as an output a set of device combinations that are most likely to be able to successfully navigate that specific anatomy based on data from previous procedures.

[0053] At S220, one or more optimal combinations of navigational devices is or are identified and ranked. The identification and ranking at S220 may be performed by the computer 120 or by the server 140. The ranking may include a list of the most optimal device combination, second most optimal, and so on. The ranking may be provided based on various criteria, including criteria set by a user.

[0054] At S250, a determination is made whether a device selection should be updated as in FIG.2A, and the determination at S250 may be skipped when no previous device selection was made.

[0055] As in FIG. 2A, if the device selection is to be updated (S250 = Yes), at S252 interventional imagery is obtained. The interventional imagery may be obtained, such as in realtime from a medical imaging system already being used during an intervention. If the device selection is not to be updated (S250 = No), at S295 the optimal combination of selected navigational devices is output, such as on the display 180.

[0056] At S253, the interventional imagery is again analyzed and at S265 the machine learning model is again applied either by the server 140 or the server 160.

[0057] As in FIG. 2A, at S270, one or more optimal combinations of navigational devices are again identified and ranked, and then the optimal combination(s) are output at S295.

[0058] The mechanical model from FIG. 2A and the machine learning model from FIG. 2B may be implemented independently. Alternatively, the mechanical model from FIG. 2A may be used as a starting point which is then refined using the machine learning approach from FIG. 2B. The combined approach is shown in and described next with respect to FIG. 2C.

[0059] FIG. 2C illustrates another method for endovascular navigation device selection, in accordance with a representative embodiment.

[0060] The method of FIG. 2C may be performed by the system 100A or the system 100B. The method of FIG. 2C includes combined features from the methods of FIG. 2A and FIG. 2B.

[0061] At S201, a list of candidate devices and device mechanical properties including device mechanical characteristics is obtained. At S205, pre-interventional imagery is obtained. The pre- interventional imagery is not required to be pre-interventional at S205 insofar as anatomical imaging may be acquired before the current intervention, or during the current intervention but prior to when a device recommendation is to be acquired. At S207, the pre-interventional imagery is analyzed. At S210, computational modeling is performed based on the list of candidate devices and device mechanical properties obtained at S201 and the physical characteristics identified at S208.

[0062] As an example context for the computational modeling, guidewires may be provided in a variety of stiffnesses (gram weight) and tip designs. Some guidewires are relatively floppy at the tip and become more rigid along more proximal sections. Other guidewires may have uniform stiffness along the length. The computational model may take into account the physicalproperties of navigation devices such as guidewires, such as stiffness at each point along the length, resting shape, and / or inner / outer diameter. The computational model may create a mechanical model of the interaction between a given guidewire and catheter (or any other device combination). A simulation may be created for each compatible pair of guidewire and catheter selecting from a database of available guidewires and catheters in the available inventory. Compatibility may be determined based on guidewire outer diameter fitting inside catheter inner diameter. The catheter tip angulation relative to the shaft of the catheter may be calculated for each guidewire position as the guidewire is advanced or retracted within the lumen of the catheter. For this example, information about the required range of motion for the device pair based on the anatomy may be derived from a pre-operative three-dimensional medical image that maps the vasculature. The anatomical imaging may be segmented to define the lumen of each vessel along the path from the access point to the target anatomy. The path may be manually defined by the user or by a separate model to identify the optimal navigation path. At each bifurcation or branch along the planned path, the branch angle may be calculated. The computer 120 or the server 140 may assess possible guidewire-catheter pairs based on available inventory and physical compatibility such as if / when outer diameter of guidewire is smaller than the inner diameter of the catheter. From the pool of possible device pairs, the optimal devices may be recommended based on the expected distance each pair could navigate through the vascular and various bifurcation angles based on the expected range of motion from the mechanical model for that device pair. The computational mode may be further refined by considering the deformation of the device pair due to interaction with the vessel wall. For example, if the vessel inner diameter is smaller than the width of the catheter tip bend, the bend in the catheter tip may be flattened (if the tip is pointing distally away from the access site) or tightened (if the tip is pointing proximally toward the access site). This deformation of the catheter tip due to vessel wall interaction may be considered in the computational model in order to select the optimal device pair that can navigate through each bifurcation angle along the planned path. Additional devices can be included in the computational model. For example, when crossing a chronic total occlusion (CTO) or when aspirating a thrombus, an additional catheter may be used for support or aspiration, respectively. Other anatomical features may also be included, such as tissue characteristics or shape of the plaque.

[0063] At S213, one or more subsets of device combination(s) are identified from the computational modeling at S210. At S215, a trained machine learning model is applied for the subset(s) of device combinations(s) identified at S213.

[0064] Inferencing by the trained machine learning model may be applied by the controller 150 at S215. The trained machine learning model may determine the optimal combination of navigation devices to use to navigate in a particular anatomy. The trained machine learning model may be developed using information from many previous procedures. Key elements of the training dataset for the trained machine learning model may include data collected across a large set of procedures, including detailed information about which devices were used in which parts of the vasculature, three-dimensional vascular imaging of the regions through which the devices navigated or with which they interacted, and an indicator for the success of using each device or device combination in each part of the anatomy. At inference, the controller 150 may take as input a list of available devices and the three-dimensional vessel imaging of the current patient, as well as other optional parameters such as patient’s electronic health record data, blood pressure, and smoking history. The machine learning model may generate as an output one or more sets of devices which may be used to navigate a particular anatomy.

[0065] The dataset of devices used in previous procedures may be created in order to train the machine learning model. Devices used in procedures for generating training data may be logged manually by the user at each step of the procedure. Alternatively, the devices may be automatically identified in interventional (i.e. fluoroscopic) images which are recorded throughout the procedures. Numerous devices may be used throughout each procedure and a classification model may be developed to identify each device type. The classification model identifies, for example, if there is a guidewire, catheter, and / or sheath in the image. The classification model then further classifies each device based on its key characteristics, such as: guidewire diameter, tip shape and tip stiffness; catheter French size and tip shape; and sheath French size. The classification model may be further refined by incorporating information from the procedure log to match the devices used at each phase of the procedure with the specific brand, model, and specifications of that device.

[0066] The vascular imaging and navigation path may also be used to train the machine learning model. The machine learning model may utilize pre-operative three-dimensional vascularimages, or intra-operative vascular images such as from intravascular ultrasound (IVUS) or optical coherence tomograph (OCT), which contain information about the vascular geometry and tissue characteristics. For training, the actual navigation path that was traversed by each device combination may be defined in the three-dimensional vascular imaging space via registration of the three-dimensional volume to the fluoroscopic images, or other methods, such as devicetracking sensors registered to the three-dimensional model. For inferencing, the target treatment location may be defined in the imaging volume, either by manual selection or by creating a model that automatically detects lesions that should be treated. The path from the access site to the target lesion, similarly, can either be defined manually by the user, or by a model that automatically defines the optimal access point and navigation path.

[0067] An indication of the utilization success of navigation for each device combination in each anatomical segment may be used for training the device recommendation model. Multiple different methods may be used to determine a success metric for device utilization. One method involves evaluating the distance that a particular device combination is able to travel through the vasculature, either from the introducer sheath or from beyond the point where the previous set of devices was able to reach. Time to navigate a particular anatomical region may also be used as a success metric but should take into account expected difficulty of navigating through the given anatomical feature and the skill of the interventionalist, both in terms of number of cases performed and frequency of using the given devices. Other examples for quantifying success may consider amount of X-ray usage and the number of changes in the C-arm angle during a cannulation.

[0068] At S220, one or more optimal combinations of navigational devices is or are identified and ranked.

[0069] At S250, a determination is made whether a device selection should be updated as in FIG. 2A, and the determination at S250 may be skipped when no previous device selection was made.

[0070] As in FIG. 2A and FIG. 2B, if the device selection is to be updated (S250 = Yes), at S252 interventional imagery is obtained. The interventional imagery may be obtained, such as in realtime from a medical imaging system. If the device selection is not to be updated (S250 = No), at S295 the optimal combination of selected navigational devices is output, such as on the display 180. At S253, the interventional imagery is analyzed. In some embodiments, interventionalimagery obtained during an intervention may be obtained and analyzed for the interaction between the devices and vasculature to fine-tune the device optimization for each patient.

[0071] At S260, computational modeling is performed. At S263, one or more subset(s) of device combination(s) is or are identified. At S265 the machine learning model inferencing is again applied. As in FIG. 2A and FIG. 2B, at S270, one or more optimal combination(s) of navigational devices are again identified and ranked, and then the optimal combination(s) are output at S295.

[0072] FIG. 3 illustrates a user interface showing a peripheral arterial vasculature in endovascular navigation device selection, in accordance with a representative embodiment.

[0073] The user interface 381 includes an image of peripheral arterial vasculature. As can be seen, the peripheral arterial vasculature has branches of varying lengths and widths.

[0074] FIG. 4A illustrates catheter tip shapes in endovascular navigation device selection, in accordance with a representative embodiment.

[0075] The user interface 481 A in FIG. 4A shows catheters with varied diameters and tip shapes. Guidewires may also each have a pre-shaped distal tip section or shapeable distal tip section. The varied devices on the user interface 481 A may be provided as selectable choices for navigation devices.

[0076] FIG. 4B illustrates modelled ranges of motion for guidewire-catheter combinations in endovascular navigation device selection, in accordance with a representative embodiment.

[0077] A user interface such as the user interface 48 IB may also show modelled ranges of motion and interactions between guidewires and catheters for various guidewire-catheter combinations with the guidewire either retracted inside the catheter or with the guidewire extended beyond the catheter tip. The ranges of motion and interactions show how the interaction between guidewires and catheters deforms the tip shapes. Determining expected ranges of motion for different combinations may take into account both device characteristics and physical characteristics of anatomy when determining optimal combinations of navigational devices. A mechanical model may assess the expected range of motion for each guidewirecatheter pair as the guidewire is advanced from the proximal to distal end of the catheter and extended beyond the catheter tip in the context of combinations shown on the user interface.Navigation guidewires and catheters come in a wide range of sizes, shapes, and stiffnesses, and itis important to select the appropriate device characteristics to be able to successfully maneuver through challenging anatomy. A user interface such as the user interface 481Bmay also show catheters in a variety of pre-defined tip shapes as selectable choices for navigation devices. The varied sizes and shapes may provide options for navigation through varied bends and branches in the vasculature. A user interface such as the user interface 481B may also show examples of varied guidewire shapes. Choosing compatible navigation catheters and guidewires requires ensuring that the guidewire diameter is appropriate for the inner diameter of the catheter, and ensuring that the guidewire has sufficient length to be able to extend beyond the tip of the catheter. The anatomy that can be navigated with each combination of guidewire and catheter may also depend on the characteristics of each device and the interaction between the devices. For example, when a guidewire is retracted inside the catheter proximal to the curved tip of the catheter, the catheter tip will take on its natural resting shape. However, when the guidewire is extended out in front of the catheter, the catheter tip will deform, based on the stiffness and shape of the guidewire and catheter. Therefore, choosing the optimal guidewire-catheter combinations for each specific anatomy can be challenging. Similar challenges exist for other endoluminal devices such as guide sheaths and biopsy needles that must be navigated to specific biopsy locations.

[0078] FIG. 5 illustrates neural network training and inferencing input and output data in endovascular navigation device selection, in accordance with a representative embodiment.

[0079] A neural network may be trained to identify the optimal set of devices required to navigate a particular anatomy. In FIG. 5, training is shown in the top portion from 581 to 587. Inputs for training the model include anatomical images 581 from three-dimensional vascular imaging, devices used in each location 582 from the device combinations used in each region of the vasculature. An error metric 585 is calculated based on a function of the difference 587 between ground truth device success metric(s) for each device / location 583 and the estimated device success metric(s) predicted by the model for each device / location 584. The trained model may be trained to predict the success metric for each device combination in the anatomical region in which it is used by optimizing the model weights to minimize the error metric. During inferencing, the three-dimensional vascular imaging with a defined navigation path and a list of potential navigation devices are fed into the model. The model will output the best combinationsof devices to navigate specific anatomical features as the estimated device success metric(s) for each device / location 584, along with a confidence value for the predicted metrics for each anatomical region.

[0080] The recommendation engine is shown in the bottom portion in FIG. 5, and can take into account the anatomical images 505 and which available devices 520 are currently available in the cathlab inventory. The recommendation engine may be implemented by a neural network, and may output a display of multiple combinations of best available devices to navigate each anatomical location in current patient 575 when navigating the current anatomy. The set of devices selected may also undergo post-processing to optimize for user preferences, such as minimizing device switching, reducing the total number of devices required for the procedure, or optimizing for lower cost devices. The optimal set of devices for devices-based likelihood of success in the current anatomy and user-defined parameters can then be displayed to the user on an interface, such as on the user interface 780 in FIG. 7.

[0081] FIG. 6 illustrates a user interface showing a device pair recommendation in endovascular navigation device selection, in accordance with a representative embodiment.

[0082] The user interface 681 includes labels for guidewires (GW) and catheters (Cath) for recommended combinations of navigation devices for different segments of anatomy. Towards the top, guidewire GW2 and catheter Cathl are recommended for one segment of anatomy, and towards the bottom, guidewire GW1 and catheter Cath3 are recommended for another segment of anatomy. For example, the expected ranges of motions for combinations of navigation devices shown on a user interface such as the user interface 481 A in FIG. 4 A may be combined with information about the physical morphology of the vasculature to provide recommendations on which device combinations are suitable for each different segment of the vasculature to be navigated. The recommendations may be provided adjacent to visual representations of the different segments as shown on the user interface 681 in FIG. 6.

[0083] FIG. 7 illustrates a user interface for device recommendation in endovascular navigation device selection, in accordance with a representative embodiment.

[0084] The user interface 781 in FIG. 7 is used for device recommendations. The user interface 781 shows options for sheaths, guidewires and catheters, along with inventory of listed items. As shown, the user interface 781 also includes a graphic outlining a human. Relevant anatomy of theoutlined human may be shown in color to highlight where the various listed navigation devices will be used.

[0085] Recommendations for optimal device selection can be output via a user interface 781 in a variety of contexts in which endovascular / endobronchial / intracardiac procedures are performed. As one example, optimization may be performed for determination of optimal access location, such as femoral, radial, antegrade, or retrograde, and optimal device characteristics such as introducer sheath size to use for a particular set of anatomical features and target treatment locations. As another example, optimization may be performed for determination of the optimal navigation devices to use to maneuver from a particular access point to a treatment location. Optimization may be performed for determination of optimal devices for a chronic total occlusion (CTO) crossing device in terms of crossing wire size and stiffness or a support catheter. Optimization may further be performed for determination of optimal aspiration devices and optimal positioning of devices relative to each other and the thrombus. In another context, optimization may be performed for determination of an optimal combination of guide sheath and biopsy needle to reach a biopsy target.

[0086] FIG. 8 illustrates a computer system, on which a method for endovascular navigation device selection is implemented, in accordance with another representative embodiment.

[0087] Referring to FIG. 8, the computer system 800 includes a set of software instructions that can be executed to cause the computer system 800 to perform any of the methods or computer- based functions disclosed herein. The computer system 800 may operate as a standalone device or may be connected, for example, using a network 801, to other computer systems or peripheral devices. In embodiments, a computer system 800 performs logical processing based on digital signals received via an analog-to-digital converter.

[0088] In a networked deployment, the computer system 800 operates in the capacity of a server or as a client user computer in a server-client user network environment, or as a peer computer system in a peer-to-peer (or distributed) network environment. The computer system 800 can also be implemented as or incorporated into various devices, such as a workstation that includes a controller, a stationary computer, a mobile computer, a personal computer (PC), a laptop computer, a tablet computer, or any other machine capable of executing a set of software instructions (sequential or otherwise) that specify actions to be taken by that machine. Thecomputer system 800 can be incorporated as or in a device that in turn is in an integrated system that includes additional devices. In an embodiment, the computer system 800 can be implemented using electronic devices that provide voice, video or data communication. Further, while the computer system 800 is illustrated in the singular, the term “system” shall also be taken to include any collection of systems or sub-systems that individually or jointly execute a set, or multiple sets, of software instructions to perform one or more computer functions.

[0089] As illustrated in FIG. 8, the computer system 800 includes a processor 810. The processor 810 may be considered a representative example of a processor of a controller and executes instructions to implement some or all aspects of methods and processes described herein. The processor 810 is tangible and non-transitory. As used herein, the term “non- transitory” is to be interpreted not as an eternal characteristic of a state, but as a characteristic of a state that will last for a period. The term “non-transitory” specifically disavows fleeting characteristics such as characteristics of a carrier wave or signal or other forms that exist only transitorily in any place at any time. The processor 810 is an article of manufacture and / or a machine component. The processor 810 is configured to execute software instructions to perform functions as described in the various embodiments herein. The processor 810 may be a general- purpose processor or may be part of an application specific integrated circuit (ASIC). The processor 810 may also be a microprocessor, a microcomputer, a processor chip, a controller, a microcontroller, a digital signal processor (DSP), a state machine, or a programmable logic device. The processor 810 may also be a logical circuit, including a programmable gate array (PGA), such as a field programmable gate array (FPGA), or another type of circuit that includes discrete gate and / or transistor logic. The processor 810 may be a central processing unit (CPU), a graphics processing unit (GPU), or both. Additionally, any processor described herein may include multiple processors, parallel processors, or both. Multiple processors may be included in, or coupled to, a single device or multiple devices.

[0090] The term “processor” as used herein encompasses an electronic component able to execute a program or machine executable instruction. References to a computing device comprising “a processor” should be interpreted to include more than one processor or processing core, as in a multi-core processor. A processor may also refer to a collection of processors within a single computer system or distributed among multiple computer systems. The term computingdevice should also be interpreted to include a collection or network of computing devices each including a processor or processors. Programs have software instructions performed by one or multiple processors that may be within the same computing device or which may be distributed across multiple computing devices.

[0091] The computer system 800 further includes a main memory 820 and a static memory 830, where memories in the computer system 800 communicate with each other and the processor 810 via a bus 808. Either or both of the main memory 820 and the static memory 830 may be considered representative examples of a memory of a controller, and store instructions used to implement some or all aspects of methods and processes described herein. Memories described herein are tangible storage mediums for storing data and executable software instructions and are non-transitory during the time software instructions are stored therein. As used herein, the term “non-transitory” is to be interpreted not as an eternal characteristic of a state, but as a characteristic of a state that will last for a period. The term “non-transitory” specifically disavows fleeting characteristics such as characteristics of a carrier wave or signal or other forms that exist only transitorily in any place at any time. The main memory 820 and the static memory 830 are articles of manufacture and / or machine components. The main memory 820 and the static memory 830 are computer-readable mediums from which data and executable software instructions can be read by a computer (e.g., the processor 810). Each of the main memory 820 and the static memory 830 may be implemented as one or more of random access memory (RAM), read only memory (ROM), flash memory, electrically programmable read only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, a hard disk, a removable disk, tape, compact disk read only memory (CD-ROM), digital versatile disk (DVD), floppy disk, blu-ray disk, or any other form of storage medium known in the art. The memories may be volatile or non-volatile, secure and / or encrypted, unsecure and / or unencrypted.

[0092] “Memory” is an example of a computer-readable storage medium. Computer memory is any memory which is directly accessible to a processor. Examples of computer memory include, but are not limited to RAM memory, registers, and register files. References to “computer memory” or “memory” should be interpreted as possibly being multiple memories. The memory may for instance be multiple memories within the same computer system. The memory may also be multiple memories distributed amongst multiple computer systems or computing devices.

[0093] As shown, the computer system 800 further includes a video display unit 850, such as a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid-state display, or a cathode ray tube (CRT), for example. Additionally, the computer system 800 includes an input device 860, such as a keyboard / virtual keyboard or touch-sensitive input screen or speech input with speech recognition, and a cursor control device 870, such as a mouse or touch-sensitive input screen or pad. The computer system 800 also optionally includes a disk drive unit 880, a signal generation device 890, such as a speaker or remote control, and / or a network interface device 840.

[0094] In an embodiment, as depicted in FIG. 8, the disk drive unit 880 includes a computer- readable medium 882 in which one or more sets of software instructions 884 (software) are embedded. The sets of software instructions 884 are read from the computer-readable medium 882 to be executed by the processor 810. Further, the software instructions 884, when executed by the processor 810, perform one or more steps of the methods and processes as described herein. In an embodiment, the software instructions 884 reside all or in part within the main memory 820, the static memory 830 and / or the processor 810 during execution by the computer system 800. Further, the computer-readable medium 882 may include software instructions 884 or receive and execute software instructions 884 responsive to a propagated signal, so that a device connected to a network 801 communicates voice, video or data over the network 801. The software instructions 884 may be transmitted or received over the network 801 via the network interface device 840.

[0095] In an embodiment, dedicated hardware implementations, such as application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), programmable logic arrays and other hardware components, are constructed to implement one or more of the methods described herein. One or more embodiments described herein may implement functions using two or more specific interconnected hardware modules or devices with related control and data signals that can be communicated between and through the modules. Accordingly, the present disclosure encompasses software, firmware, and hardware implementations. Nothing in the present application should be interpreted as being implemented or implementable solely with software and not hardware such as a tangible non-transitory processor and / or memory.

[0096] In accordance with various embodiments of the present disclosure, the methods described 1herein may be implemented using a hardware computer system that executes software programs. Further, in an exemplary, non-limited embodiment, implementations can include distributed processing, component / object distributed processing, and parallel processing. Virtual computer system processing may implement one or more of the methods or functionalities as described herein, and a processor described herein may be used to support a virtual processing environment.

[0097] Accordingly, endovascular navigation device selection enables development and use of mechanical models and machine learning models for selecting combinations of for navigation devices. The mechanical models and machine learning models may determine anatomy-specific combinations such as guidewire-catheter combinations that are most likely to lead to successful and efficient navigation of complex vasculature. A three-dimensional vascular image obtained from medical imaging may be taken as input and used to generate recommendations for one or more optimal navigation device combinations for navigating through the vasculature. The mechanical models and machine learning models that may be used to generate the recommendations may take into account interaction between device combinations such as guidewire and catheter, as well as data from previous similar procedures involving particular navigation device combinations in a given anatomy.

[0098] Although endovascular navigation device selection has been described with reference to several exemplary embodiments, it is understood that the words that have been used are words of description and illustration, rather than words of limitation. Changes may be made within the purview of the appended claims, as presently stated and as amended, without departing from the scope and spirit of endovascular navigation device selection in its aspects. Although endovascular navigation device selection has been described with reference to particular means, materials and embodiments, endovascular navigation device selection is not intended to be limited to the particulars disclosed; rather endovascular navigation device selection extends to all functionally equivalent structures, methods, and uses such as are within the scope of the appended claims.

[0099] The illustrations of the embodiments described herein are intended to provide a general understanding of the structure of the various embodiments. The illustrations are not intended to serve as a complete description of all of the elements and features of the disclosure describedherein. Many other embodiments may be apparent to those of skill in the art upon reviewing the disclosure. Other embodiments may be utilized and derived from the disclosure, such that structural and logical substitutions and changes may be made without departing from the scope of the disclosure. Additionally, the illustrations are merely representational and may not be drawn to scale. Certain proportions within the illustrations may be exaggerated, while other proportions may be minimized. Accordingly, the disclosure and the figures are to be regarded as illustrative rather than restrictive.

[0100] One or more embodiments of the disclosure may be referred to herein, individually and / or collectively, by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any particular invention or inventive concept. Moreover, although specific embodiments have been illustrated and described herein, it should be appreciated that any subsequent arrangement designed to achieve the same or similar purpose may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all subsequent adaptations or variations of various embodiments. Combinations of the above embodiments, and other embodiments not specifically described herein, will be apparent to those of skill in the art upon reviewing the description.

[0101] The Abstract of the Disclosure is provided to comply with 37 C.F.R. §1.72(b) and is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, various features may be grouped together or described in a single embodiment for the purpose of streamlining the disclosure. This disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter may be directed to less than all of the features of any of the disclosed embodiments. Thus, the following claims are incorporated into the Detailed Description, with each claim standing on its own as defining separately claimed subject matter.

[0102] The preceding description of the disclosed embodiments is provided to enable any person skilled in the art to practice the concepts described in the present disclosure. As such, the above disclosed subject matter is to be considered illustrative, and not restrictive, and the appended claims are intended to cover all such modifications, enhancements, and otherembodiments which fall within the true spirit and scope of the present disclosure. Thus, to the maximum extent allowed by law, the scope of the present disclosure is to be determined by the broadest permissible interpretation of the following claims and their equivalents and shall not be restricted or limited by the foregoing detailed description.

Claims

CLAIMS:

1. A method for selecting devices (520) for endovascular navigation, comprising: obtaining pre-interventional imagery of a vasculature system (100A); identifying physical characteristics of the vasculature system (100A) from the pre- interventional imagery; obtaining device characteristics of a plurality of navigational devices (520); assessing expected performance of the plurality of navigational devices (520) based on the device characteristics of the plurality of navigational devices (520) with respect to the physical characteristics of the vasculature system (100A) from the pre-interventional imagery in a first assessment, and identifying, from among the plurality of navigational devices (520) and based on assessing expected performance in the first assessment, a combination of optimal navigational devices (520) to use in an interventional navigation through the vasculature system (100A) during an intervention.

2. The method of claim 1, further comprising: obtaining interventional imagery of the vasculature system (100A) during the intervention; identifying physical characteristics of the vasculature system (100 A) from the interventional imagery; determining whether to again identify a combination of optimal navigational devices (520) to use in the interventional navigation based on the interventional imagery; obtaining the device characteristics of the plurality of navigational devices (520) during the intervention based on determining to again identify a combination of optimal navigational devices (520) to use in the interventional navigation based on the interventional imagery; assessing expected performance of the plurality of navigational devices (520) based on the device characteristics of the plurality of navigational devices (520) with respect to the physical characteristics of the vasculature system (100A) from the interventional imagery in a second assessment, andidentifying, from among the plurality of navigational devices (520) and based on assessing expected performance in the second assessment, a combination of optimal navigational devices (520) to use in the interventional navigation through the vasculature system (100A) during the intervention.

3. The method of claim 1, wherein the combination of optimal navigational devices (520) comprises combinations of coaxial devices (520).

4. The method of claim 1, wherein the physical characteristics comprise at least one of vessel tortuosity, branch vessel angulation, vessel length, lesion length, lesion diameter, calcifications, fat composition, blood clot composition, presence of prior implants, vessel stiffness, vessel fragility, or vessel diameter.

5. The method of claim 1, wherein the device characteristics comprise at least one of device size, device shape, or device stiffness.

6. The method of claim 1, further comprising: applying the physical characteristics of the vasculature system (100A) from the pre- interventional imagery and the device characteristics of the plurality of navigational devices (520) to a trained machine learning model that identifies the combination of optimal navigation devices (520).

7. The method of claim 1, wherein the device characteristics and physical characteristics of the vasculature system (100A) from the pre-interventional imagery are applied to a computational model that applies mechanical properties of combinations of navigational devices (520) to determine feasible ranges of motion that can be achieved with individual combinations of navigational devices (520).

8. The method of claim 1, further comprising:ranking a plurality of combinations of navigational devices (520) based on comparing the device characteristics of the plurality of navigational devices (520) with the physical characteristics of the vasculature system (100A) from the pre-interventional imagery in a first comparison; and outputting a ranked list of combinations of navigational devices (520) including the combination of optimal navigational devices (520).

9. The method of claim 1, wherein the physical characteristics of the vasculature system (100A) comprise a navigation path for the navigational devices (520) to take through the vasculature system (100 A), and the method further comprises determining where to navigate each of the navigational devices (520) along the navigation path.

10. The method of claim 1, further comprising: generating a display (180) projecting use of the combination of optimal navigational devices (520) in the interventional navigation through the vasculature system (100A) during an intervention.

11. A system (100A) for selecting devices (520) for endovascular navigation, comprising: a memory (151) that stores instructions; and a processor (152) that executes the instructions, wherein, when executed by the processor (152), the instructions cause the system (100 A) to: obtain pre-interventional imagery of a vasculature system (100A); identify physical characteristics of the vasculature system (100A) from the pre- interventional imagery; obtain device characteristics of a plurality of navigational devices (520); assess expected performance of the plurality of navigational devices (520) based on the device characteristics of the plurality of navigational devices (520) with respect to the physical characteristics of the vasculature system (100A) from the pre-interventional imagery in a first assessment, andidentify, from among the plurality of navigational devices (520) and based on assessing expected performance in the first assessment, a combination of optimal navigational devices (520) to use in an interventional navigation through the vasculature system (100A) during an intervention.

12. The system (100 A) of claim 11, wherein, when executed by the processor (152), the instructions further cause the system (100 A) to: obtain interventional imagery of the vasculature system (100 A) during the intervention; identify physical characteristics of the vasculature system (100 A) from the interventional imagery; determine whether to again identify a combination of optimal navigational devices (520) to use in the interventional navigation based on the interventional imagery; obtain the device characteristics of the plurality of navigational devices (520) during the intervention based on determining to again identify a combination of optimal navigational devices (520) to use in the interventional navigation based on the interventional imagery; assess expected performance of the plurality of navigational devices (520) based on the device characteristics of the plurality of navigational devices (520) with respect to the physical characteristics of the vasculature system (100A) from the interventional imagery in a second assessment, and identify, from among the plurality of navigational devices (520) and based on assessing expected performance in the second assessment, a combination of optimal navigational devices (520) to use in the interventional navigation through the vasculature system (100A) during the intervention.

13. The system (100 A) of claim 11, wherein the combination of optimal navigational devices (520) comprises combinations of coaxial devices (520).

14. The system (100A) of claim 11, wherein the physical characteristics comprise at least one of vessel tortuosity, branch vessel angulation, vessel length, lesion length, lesion diameter,calcifications, fat composition, blood clot composition, presence of prior implants, vessel stiffness, vessel fragility, or vessel diameter.

15. The system (100A) of claim 11, wherein the device characteristics comprise at least one of device size, device shape, or device stiffness.

16. The system (100 A) of claim 11, wherein, when executed by the processor (152), the instructions further cause the system (100 A) to: apply the physical characteristics of the vasculature system (100 A) from the pre- interventional imagery and the device characteristics of the plurality of navigational devices (520) to a trained machine learning model that identifies the combination of optimal navigation devices (520).

17. The system (100A) of claim 11, wherein the device characteristics and physical characteristics of the vasculature system (100A) from the pre-interventional imagery are applied to a computational model that applies mechanical properties of combinations of navigational devices (520) to determine feasible ranges of motion that can be achieved with individual combinations of navigational devices (520).

18. The system (100A) of claim 11, further comprising: a display (180) that displays a ranked list of combinations of navigational devices (520) including the combination of optimal navigational devices (520), wherein, when executed by the processor (152), the instructions further cause the system (100 A) to: rank a plurality of combinations of navigational devices (520) based on comparing the device characteristics of the plurality of navigational devices (520) with the physical characteristics of the vasculature system (100A) from the pre-interventional imagery in a first comparison.

19. The system (100A) of claim 11, wherein the system (100A) is implemented in a networked cloud.

20. A tangible, non-transitory computer-readable medium (882) that stores instructions, which when executed by a processor (152), cause the processor (152) to: obtain pre-interventional imagery of a vasculature system (100A); identify physical characteristics of the vasculature system (100A) from the pre- interventional imagery; obtain device characteristics of a plurality of navigational devices (520); assess expected performance of the plurality of navigational devices (520) based on the device characteristics of the plurality of navigational devices (520) with respect to the physical characteristics of the vasculature system (100A) from the pre-interventional imagery in a first assessment, and identify, from among the plurality of navigational devices (520) and based on assessing expected performance in the first assessment, a combination of optimal navigational devices (520) to use in an interventional navigation through the vasculature system (100A) during an intervention.

Images