Percutaneous coronary intervention therapy plan

Abstract

An example medical system includes a memory configured to store at least one of a machine learning algorithm or an artificial intelligence algorithm and processing circuitry communicatively coupled with the memory. The processing circuitry is configured to: receive preoperative data, the preoperative data comprising data relating to at least respective portions of respective vasculature of one or more patients; receiving intra-operative data, the intra-operative data being collected during a respective therapeutic medical procedure performed on the one or more patients; postoperative data is received, the post-operative data being collected after a respective therapeutic medical procedure performed on the one or more patients. Processing circuitry is configured to train at least one of the machine learning algorithm or the artificial intelligence algorithm according to the preoperative data, the intra-operative data, and the post-operative data.

Description

[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 365,935, filed on June 6, 2022, entitled “PERCUTANEOUS CORONARY INTERVENTION PLANNING.” Technical Field

[0002] The present disclosure relates to planning and assistance in medical procedures. Background Art

[0003] Percutaneous coronary intervention (PCI) is a medical procedure used to address coronary artery problems, such as lesions within a patient's vasculature. This procedure can be performed in a catheterization laboratory (cath lab) and can include inserting a catheter into a patient's vasculature to implant a stent, inflate a balloon, remove calcifications, and the like. A catheterization lab is a specialized facility that includes cardiac imaging equipment and can be located within a hospital. Clinicians can use cardiac imaging equipment to diagnose a patient's heart problems and / or assist clinicians in visualizing a patient's vasculature during a therapeutic medical procedure, such as PCI to treat a patient's heart problems. This imaging system can display anatomical structures, medical devices, and the like, and can be used to diagnose a patient's condition or to assist clinicians in moving a medical device to a desired location within the patient's body. An imaging system can use sensors to capture video images that can be displayed during a medical procedure. Imaging systems include angiography systems, ultrasound imaging systems, computed tomography (CT) scanning systems, magnetic resonance imaging (MRI) systems, isocentric C-arm fluoroscopy systems, positron emission tomography (PET) systems, intravascular ultrasound (IVUS), optical coherence tomography (OCT), and other imaging systems. Summary of the invention

[0004] In general, the present disclosure relates to various techniques and medical systems for planning medical procedures and updating medical plans during procedures. The present disclosure also relates to various techniques for training machine learning algorithms and / or artificial intelligence algorithms that can be used to plan such medical procedures and / or update plans for such medical procedures.

[0005] Currently, non-invasive coronary imaging data is primarily used to diagnose (many) coronary artery problems rather than for medical procedures such as PCI. While there are planning tools designed to facilitate clinicians using non-invasive images and planning medical procedures such as PCI, these plans may not currently be integrated with the catheterization lab where PCI can be performed.

[0006] Based on the technology of the present disclosure, a medical system can use a trained machine learning algorithm and / or an artificial intelligence algorithm to plan a medical operation, such as a PCI operation, based on data collected before the medical operation. These data may include non-invasive imaging data, invasive imaging data, and / or sensor data. For example, a medical system can generate a surgical plan that can be displayed or otherwise presented to a clinician before and during the medical operation to assist the clinician in performing the operation. During the medical operation, additional data can be collected, and the processing circuit system that executes the trained machine learning algorithm and / or the trained artificial intelligence algorithm can use this data to determine that different or additional treatments may be more likely to bring better results to the patient than the treatment in the original surgical plan. In this case, the processing circuit system can update the surgical plan to include different or additional treatments. The machine learning algorithm and / or the artificial intelligence algorithm can be trained based on a combination of preoperative data, intraoperative data, and postoperative data.

[0007] By using a trained machine learning algorithm and / or a trained artificial intelligence algorithm to generate a surgical plan and / or update a surgical plan during a medical procedure, patient outcomes can be improved, resulting in better health for the patient post-surgery.

[0008] Aspects of the present disclosure are at least applicable to catheterization laboratory procedures. Example catheterization laboratory procedures include, but are not limited to, coronary artery surgery, renal denervation (RDN) surgery, structural heart and aortic (SH&A) surgery (e.g., transcatheter aortic valve replacement (TAVR), transcatheter mitral valve replacement (TMVR), etc.), device implantation surgery (e.g., cardiac monitor, pacemaker, defibrillator, etc.), etc.

[0009] In one example, the present disclosure describes a medical system comprising a memory configured to store at least one of a machine learning algorithm or an artificial intelligence algorithm; and a processing circuit system communicatively coupled to the memory, the processing circuit system being configured to: receive preoperative data, the preoperative data comprising data related to at least a corresponding portion of a corresponding vascular system of one or more patients; receive intraoperative data, the intraoperative data collected during a corresponding therapeutic medical procedure performed on the one or more patients; receive postoperative data, the postoperative data collected after the corresponding therapeutic medical procedure performed on the one or more patients; and train at least one of the machine learning algorithm or the artificial intelligence algorithm based on the preoperative data, the intraoperative data, and the postoperative data to generate a trained machine learning algorithm or at least one of the trained artificial intelligence algorithms.

[0010] In another example, the present disclosure describes a method comprising: receiving, by a processing circuit system, preoperative data, the preoperative data comprising data relating to at least a corresponding portion of a corresponding vascular system of one or more patients; receiving, by the processing circuit system, intraoperative data, the intraoperative data being collected during a corresponding therapeutic medical procedure performed on the one or more patients; receiving, by the processing circuit system, postoperative data, the postoperative data being collected after the corresponding therapeutic medical procedure performed on the one or more patients; and training, by the processing circuit system, at least one of a machine learning algorithm or an artificial intelligence algorithm based on the preoperative data, the intraoperative data, and the postoperative data to generate at least one of a trained machine learning algorithm or a trained artificial intelligence algorithm.

[0011] In yet another example, the present disclosure describes a non-transitory computer-readable medium comprising instructions that, when executed, cause a processing circuit system to: receive preoperative data comprising data relating to at least a corresponding portion of a corresponding vascular system of one or more patients; receive intraoperative data collected during a corresponding therapeutic medical procedure performed on the one or more patients; receive postoperative data collected after performing the corresponding therapeutic medical procedure on the one or more patients; and train at least one of a machine learning algorithm or an artificial intelligence algorithm based on the preoperative data, the intraoperative data, and the postoperative data to generate at least one of a trained machine learning algorithm or a trained artificial intelligence algorithm.

[0012] These and other aspects of the present disclosure will become apparent from the following detailed description.The above summary, however, should in no way be construed as limiting the claimed subject matter, which is defined solely by the appended claims.

[0013] The present summary is intended to provide an overview of the subject matter described in the present disclosure. The present summary is not intended to provide an exclusive or exhaustive explanation of the apparatus and methods described in detail in the following figures and the specification. Further details of one or more examples are set forth in the following figures and the specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a schematic perspective illustration of an example of a system for guiding a medical device through a region of a patient.

[0015] Figure 2 yes Figure 1 A schematic diagram of an example of a computing system of a system.

[0016] Figure 3is a functional block diagram illustrating an example system that includes remote computing devices (eg, a server and one or more other computing devices) connected via a network.

[0017] Figure 4 is a flow chart of an example surgical plan generation technique according to one or more aspects of the present disclosure.

[0018] Figure 5 is a flow chart of a training technique for an example machine learning algorithm or artificial intelligence algorithm according to one or more aspects of the present disclosure.

[0019] Figure 6 is a conceptual diagram illustrating an example machine learning model according to one or more aspects of the present disclosure.

[0020] Figure 7 is a conceptual diagram illustrating an example training process for a machine learning model according to one or more aspects of the present disclosure. DETAILED DESCRIPTION

[0021] Imaging systems can be used to assist clinicians in diagnosing medical conditions (such as coronary artery problems) during or during medical procedures (such as percutaneous coronary intervention (PCI) procedures). For example, imaging systems can be used to determine whether there are lesions in the patient's vasculature that may limit or obstruct blood flow in the patient's vasculature. For example, such imaging systems can be used to identify possible coronary artery problems, including lesions such as bifurcation lesions, calcified lesions, chronic total occlusions (CTOs), in-stent restenosis (ISRs), left main disease, etc. Imaging systems can also be used when performing PCI (such as angioplasty) or other medical procedures intended to treat lesions in the patient's vasculature. Although this article is mainly described with respect to the patient's vasculature, the imaging system described herein can be used for other medical purposes, not limited to coronary purposes. The imaging system can generate static image data or video data via a sensor. The data can be recorded for later use. The data may include a representation of a portion of the patient's vasculature, including one or more lesions that may restrict blood flow through this portion of the vasculature, the geometry and location of such lesions within the vessel, and / or any medical devices that may be located within the field of view of one or more sensors of the imaging system.

[0022] As mentioned herein, a medical procedure may be a diagnostic medical procedure or a therapeutic medical procedure. A diagnostic medical procedure is a medical procedure that uses imaging or other techniques to diagnose a disease. A therapeutic medical procedure is a medical procedure that provides treatment and / or performs an intervention, such as PCI. A single catheterization room phase may include 1) only diagnostic medical procedures, such as when a lesion that requires treatment is not identified, or when treatment is too difficult for a given clinician, or when the hospital where the catheterization room is located does not have the equipment required to treat the lesion; 2) only therapeutic medical procedures, such as when a lesion has been previously diagnosed; or 3) a diagnostic medical procedure is performed first, followed by a therapeutic medical procedure. As disclosed herein, a medical system may use pre-treatment imaging data acquired prior to a therapeutic medical procedure such as PCI to determine a surgical plan. The medical system may determine a surgical plan by using a trained machine learning algorithm and / or a trained artificial intelligence algorithm to input pre-operative data (such as pre-treatment imaging data) into a trained machine learning algorithm and / or a trained artificial intelligence algorithm. For example, a trained machine learning algorithm and / or a trained artificial intelligence algorithm can be trained based on preoperative data (e.g., pre-treatment imaging data), intraoperative data (e.g., additional imaging data, which may or may not be invasive), and postoperative data. The difference between the preoperative data and the postoperative data can indicate the outcome of the therapeutic medical procedure. The data used to train the machine learning algorithm and / or the artificial intelligence algorithm can include data from multiple patients who have undergone such therapeutic medical procedures.

[0023] Clinicians can use surgical plans during therapeutic medical procedures to assist clinicians in performing therapeutic medical procedures. Data collected during therapeutic medical procedures (e.g., intraoperative data) can also be input into a trained machine learning algorithm and / or a trained artificial intelligence algorithm to determine whether the surgical plan should be updated to include different treatments not included in the surgical plan. For example, if a medical system executing a trained machine learning algorithm and / or a trained artificial intelligence algorithm determines that the likelihood of a more successful outcome would be higher if a different or additional treatment were performed, the medical system can update the surgical plan to include the different or additional treatment. By generating a surgical plan, the technology of the present disclosure can assist clinicians in performing surgery. By updating the surgical plan, the technology of the present disclosure can increase the likelihood of a successful outcome for a patient. By training the machine learning algorithms and / or artificial intelligence algorithms discussed herein, surgical plans and updates to surgical plans can be improved, which can further increase the likelihood of a successful outcome for a patient over time.

[0024] Thus, the techniques of the present disclosure bring pre-treatment imaging into the planning phase and also integrate surgical planning with the catheterization laboratory and the medical devices or equipment used in the catheterization laboratory by providing real-time guidance and / or feedback to the clinician and a record of the therapeutic medical procedure. The overall surgical plan, the record of the therapeutic medical procedure, the treatment used, and the results (e.g., determined by the difference between the pre-operative data and the post-operative data) can be used as input to a machine learning algorithm and / or an artificial intelligence algorithm to train the machine learning algorithm and / or artificial intelligence algorithm so that it can be used for future surgical planning. Such trained machine learning algorithms and / or artificial intelligence algorithms may be particularly useful for complex PCIs, of which bifurcation lesions, calcified lesions, CTOs, and ISRs are subsets.

[0025] The techniques disclosed herein bring preoperative data into the catheterization lab and can augment that preoperative data with real-time data acquired in the lab. These techniques also allow the surgical plan to be used as a map onto which completed treatments can be superimposed. All of this data can be processed by processing circuitry executing machine learning or artificial intelligence algorithms that can begin to predict outcomes by building a database of plans, treatments, and outcomes of coronary interventions and training the machine learning or artificial intelligence algorithms based on that data.

[0026] As more therapeutic medical procedures are performed, the disclosed techniques can be supported by real-world data to improve treatment recommendations. In addition, as machine learning algorithms or artificial intelligence algorithms can be further trained on more recent PCI procedures, these recommendations can keep pace with evolving or new technologies and new and existing medical devices.

[0027] Not all clinicians are willing to perform complex PCI, such as PCI for bifurcation cases, calcified lesion cases, CTO cases, ISR cases, left main disease cases, etc. However, the surgical plan generated by the technology of the present disclosure can help clinicians plan such complex cases and provide a starting point for their surgical strategy.

[0028] Figure 11 is a schematic stereogram of an example of a system for guiding a medical device through a region of a patient. At least a portion of the system 10 may be located in a catheterization room 100, which includes a guidance workstation 50, a display device 110, a table 120, a medical device 130, an imager 140, and a computing device 150. Before performing a therapeutic medical procedure such as PCI in the catheterization room 100, a clinician may perform pre-treatment imaging on a patient to diagnose coronary artery disease. The clinician may also obtain or receive sensor data from a wearable device (such as a smart watch, a fitness watch, etc.), an implantable device, or other sensor (such as a stethoscope, which may be located in the clinician's office). The sensor data may indicate a coronary artery problem. The clinician may also use one or more physiological indicators (such as blood flow reserve fraction (FFR), coronary artery blood flow reserve (CFR), instantaneous waveform-free ratio (iFR) or other blood flow reserve measurements) to identify coronary artery problems, such as major lesions, including bifurcation lesions, calcified lesions, CTO, ISR, left main stem disease, etc. Once a coronary artery problem is discovered, the clinician may decide to perform a therapeutic medical procedure (eg, in the catheterization laboratory 100 ) to address the coronary artery problem.

[0029] The guide workstation 50 may include, for example, an off-the-shelf device such as a laptop computer, a desktop computer, a tablet computer, a smartphone, or other similar device. In some examples, the guide workstation may be a device for a specific purpose. The guide workstation 50 may be configured to control an electrosurgical generator, a peristaltic pump, a power supply, or any other accessories and peripherals associated with or forming part of the system 10. The computing device 150 may include, for example, an off-the-shelf device such as a laptop computer, a desktop computer, a tablet computer, a smartphone, or other similar device, or may include a device for a specific purpose.

[0030] The display device 110 may be configured to output instructions, images, and messages related to at least one of the performance, position, orientation, or trajectory of the medical device 130, the coronary artery anatomy, patient parameters, and the like. The display device 110 may also be configured to display a surgical plan. In some examples, the display device 110 may simultaneously display the surgical plan and the imaging data collected during the therapeutic medical procedure. For example, the display device 110 may fuse the planned images or images taken before surgery (e.g., pre-treatment imaging data) with real-time images taken during the therapeutic medical procedure (e.g., fluoroscopic images, IVUS, OCT, etc.), and provide a three-dimensional (3D) image or side-by-side view of the patient's anatomy and (multiple) devices relative to the plan. For example, the processing circuit system (e.g., the processing circuit system of the computing device 150) may overlay or integrate a coronary computed tomography angiography (CCTA) image (collected before the catheterization room stage) with an angiography image collected during the catheterization room stage. For example, the plan may include strategies, medical devices, and / or equipment represented in graphical or video form to facilitate clinicians in performing therapeutic medical procedures. In some examples, the processing circuitry can track the device by using sensor(s) or automatic image segmentation. The placement of such a device can be compared to the plan. Fusion of pre-PCI images with real-time imaging (fluoroscopy, ultrasound, IVUS, OCT, etc.) can provide a 3D or side-by-side view of the anatomy and device(s) relative to the plan.

[0031] In some examples, the processing circuit system can be configured to share live case data with colleagues to collaborate on treatment strategies. For example, the processing circuit system can be configured to control the telemetry circuit system to transmit live case data (such as images, treatment plans, etc.) to one or more colleagues for display on a mobile device, tablet computer, notebook computer, desktop computer, workstation, etc.

[0032] Further, the display device 110 may be configured to output information about the medical device 130, such as an algorithm number, type, size, etc. The table 120 may be, for example, an operating table or other table suitable for use during a medical procedure, which may optionally include an electromagnetic (EM) field generator 121. The EM field generator 121 may optionally be included and used to generate an EM field during a medical procedure, and when included, may form part of an EM tracking system for tracking the location of one or more medical devices within a patient's body. The EM field generator 121 may include various components, such as a specially designed mat placed beneath or integrated into an operating table or bed.

[0033] The medical device 130 may also be visualized using imaging such as angiography (eg, contrast-enhanced coronary angiography), OCT, or intravascular ultrasound (IVUS) imaging. Figure 1 In an example of the present invention, imager 140 (e.g., an angiography device) can be used to image the vasculature of a patient during a medical procedure to visualize the vasculature of the patient, the location of medical devices (e.g., surgical instruments, device delivery or placement devices, and implants) within the patient. Although primarily described as an angiography imager, imager 140 can be any type of imaging device that includes one or more sensors.

[0034] Imager 140 can image a region of interest within the patient's body. The particular region of interest can depend on the anatomy, diagnostic procedure, and / or intended treatment. For example, when performing PCI, a portion of the vasculature may be the region of interest.

[0035] As further described herein, the imager 140 can be positioned relative to the medical device 130 so that the medical device is at an angle to the image plane, thereby enabling a clinician to visualize the spatial relationship between the medical device 130 and the ultrasound image plane and the imaged object. In some examples, if provided, the EM tracking system can also track the position of the imager 140. In one or more examples, the imager 140 can be placed in a patient's body, such as within a vascular system. The EM tracking system can then track the position of the imager 140 and the medical device 130 within the patient's body. In some examples, the functions of the computing device 150 can be performed by the guidance workstation 50, and the computing device 150 may not be present.

[0036] The position of a medical device within a patient's body can be tracked during a surgical procedure. An exemplary technique for tracking the position of a medical device includes using an imager 140. Another exemplary technique for tracking the position of a medical device includes using an EM tracking system that tracks the position of a medical device 130 by tracking a sensor attached to or contained in the medical device 130. Before starting a medical procedure, a clinician can verify the accuracy of the tracking system using one or more of any suitable techniques. Any suitable medical device 130 can be used with the system 10. Examples of medical devices or equipment include stents, catheters (including guide catheters, guide extension catheters, balloon catheters, etc.), angioplasty devices, atherectomy devices, etc.

[0037] The computing device 150 may be communicatively coupled to the imager 140, the workstation 50, the display device 110, and / or the server 160, for example, by wired, optical, or wireless communication. The server 160 may be a hospital server, a cloud-based server, or the like. The server 160 may be configured to store trained machine learning algorithms, trained artificial intelligence algorithms, patient imaging data, electronic healthcare or medical records, types of coronary problems, severity of coronary problems, complexity of coronary problems, locations of coronary problems, classification of lesions, anatomical structures of coronary problem areas, other anatomical structures, and the like. In some examples, the server 160 may further store patient metadata, such as gender, age, weight, height, body mass index, body fat percentage, comorbidities, cholesterol levels, blood pressure, blood oxygen, physical exercise levels, heart rate, and the like. In some examples, the computing device 150 may be an example of the workstation 50.

[0038] The computing device 150 may be configured to receive imaging data from the imager 140. The computing device 150 may be configured to share the imaging data with the server 160 so that the server 160 may execute a trained machine learning algorithm and / or a trained artificial intelligence algorithm to determine whether to update the surgical plan that may be displayed on the display device 110. In other examples, the computing device 150 may locally execute a trained machine learning algorithm and / or a trained artificial intelligence algorithm to determine whether to update the surgical plan. Data collected during a therapeutic medical procedure (such as angiographic images, OCT, or intravascular ultrasound, etc.) may provide more detailed anatomical and / or physiological data (e.g., FFR or other blood flow reserve measurements, vulnerable plaque identification, etc.) than pre-treatment imaging data acquired preoperatively. This data may be added to any record of the overall therapeutic medical procedure and may be used to update treatment strategies.

[0039] Computing device 150 may also be configured to present a user interface on a display, such as a display of computing device 150 or display device 110. Such a user interface may be configured to display the surgical plan and intraoperative imaging data collected by imager 140 to guide a clinician in performing a therapeutic medical procedure.

[0040] Computing device 150 may also be configured to receive imaging data from more than one type of imaging system. For example, imager 140 may be an angiographic imager, while imager 180 may be a fluoroscopic imager. Thus, computing device 150 may receive multiple different imaging data. In some examples, computing device 150 may register the multiple different imaging data and overlay the multiple imaging data. In some examples, computing device 150 may overlay any imaging data collected during a therapeutic medical procedure with the surgical plan.

[0041] The computing device 150 may be configured to receive video data captured by one or more cameras 170. Although only a single camera is shown, it should be understood that the one or more cameras 170 may include multiple cameras that may be located at different locations within the catheterization laboratory 100. The one or more cameras 170 may capture video data that includes, for example, hand movements (such as hand movements of a clinician performing a therapeutic medical procedure), robotic movements (such as movements of the robot 102 participating in or performing a therapeutic medical procedure), medical devices or equipment used (e.g., implantable devices), the time when the medical device or equipment is used, and / or the location where the medical device or equipment is used. In some examples, such video data may be used to train a machine learning algorithm and / or an artificial intelligence algorithm, and / or used as input to a machine learning algorithm and / or an artificial intelligence algorithm when determining whether to update a surgical plan.

[0042] In some examples, a machine learning application or an artificial intelligence application can be used with a robotic or robot-assisted PCI procedure. For example, the robot 102 can be programmed to follow a surgical plan determined or updated by a machine learning application or an artificial intelligence application. Although depicted as a humanoid robot, it should be understood that a robotic arm that may be located near the operating table 120 can also perform such a robotic or robot-assisted PCI procedure. Machine vision can be used to facilitate the robot 102 to follow the plan based on the imaging technology used during the procedure and / or the video captured by one or more cameras. The use of robotic technology (such as the robot 102) can reduce radiation exposure to patients and clinicians because the surgical time can be reduced, and / or for robot-assisted surgery, the clinician can be away from the patient. In a robot-assisted scenario, the computing device may include the ability for the clinician to provide input to control the therapeutic medical procedure or select options. For example, the clinician can interact through a user interface (such as a joystick, a touch screen, a mouse, etc.) and control the robot to move the guidewire to the desired location. In another example, the clinician can select a location on the imaging, such as by touching or clicking the location, and the robot can then deliver the device to the location. In some examples, the robot can provide feedback, such as imaging feedback, as the robot delivers the device to the location.

[0043] The computing device 150 may be configured to upload any data collected during the therapeutic medical procedure to the server 160. The computing device 150 may also be configured to generate a report to a clinician or patient including data collected during the therapeutic medical procedure. In some examples, the computing device 150 may upload the report to the server 160. The computing device 150 and / or the server 160 may be configured to update the report based on the postoperative data associated with the patient to generate an updated report. For example, such postoperative data may include postoperative sensor data associated with the patient, user input data associated with the patient, postoperative imaging data of the patient, or physiological data of the patient. The postoperative sensor data may include data from a wearable device (such as a smart watch or a fitness watch), such as heart rate data, blood oxygen data, number of steps, etc. The difference between the postoperative data and the preoperative data may indicate the results of the therapeutic medical procedure. The user input data may include data entered by a clinician or patient, such as how the patient feels, the amount of movement of the patient, other sensor data (e.g., sensed during a postoperative clinic), etc. The postoperative imaging data may include pre-treatment imaging data acquired during a postoperative clinic. Physiological data may include, for example, FFR or other blood flow reserve analysis, etc.

[0044] Figure 2 yes Figure 1 A schematic diagram of an example of a computing device of system 10. Computing device 200 may be Figure 1 Computing device 200 is an example of a computing device 150 or server 160 for creating a surgical plan outside of catheterization laboratory 100. Computing device 200 may also be an example of a computing device used to create a surgical plan outside of catheterization laboratory 100. Computing device 200 may include a workstation, a desktop computer, a laptop computer, a smart phone, a tablet computer, a server, a dedicated computing device, or any other computing device capable of executing the disclosed technology.

[0045] In an example where the computing device 200 is used to create a surgical plan and is not located in the catheterization lab 100, the processing circuit system 204 can control the network interface 208 to push or otherwise transmit the surgical plan 228 to the catheterization lab 100 for use by a clinician during a therapeutic medical procedure. For example, the computing device 200 can push the surgical plan 228 to the guidance workstation 50 and / or the computing device 150 in the catheterization lab 100. The computing device in the catheterization lab 100 can display the surgical plan 228 on a display device (e.g., the display device 110 and / or the display 206 (which can be part of a user interface)), such as a monitor, an augmented reality (AR) or virtual reality (VR) headset, a hologram, and / or other display device(s) in the catheterization lab 100.

[0046] The computing device 200 may be configured to perform processing, control, and other functions associated with the guidance workstation 50, the imager 140, and the optional EM tracking system. The computing device 200 may represent multiple instances of a computing device, each of which may be associated with one or more of the guidance workstation 50, the imager 140, the imager 180, the one or more cameras 170, or the EM tracking system. The computing device 200 may include, for example, a memory 202, a processing circuit system 204, a display 206, a network interface 208, an input device 210, or an output device 212, each of which may represent any one of multiple instances of such a device within a computing system for ease of description.

[0047] Although processing circuitry 204 appears Figure 2 140, imager 180, EM tracking system, other computing devices, or a combination thereof. In some examples, one or more processors associated with processing circuit system 204 in a computing system may be distributed and shared among any combination of computing device 150, server 160, boot workstation 50, imager 140, imager 180, and EM tracking system. Additionally, in some examples, processing operations or other operations performed by processing circuit system 204 may be performed by one or more remotely resident processors, such as one or more cloud servers or processors, each of which may be considered part of computing device 200. Computing device 200 may be used to perform any of the methods described in the present disclosure and may form all or part of a device or system configured to perform such a method, alone or in combination with other components (such as computing device 150, server 160, guidance workstation 50, imager 140, imager 180, an EM tracking system, or components of a system including any or all of such systems).

[0048] The memory 202 of the computing device 200 includes any non-transitory computer-readable storage medium for storing data or software that can be executed by the processing circuit system 204 and control the operation of the computing device 150, the server 160, the boot workstation 50, the imager 140, the imager 180, or the EM tracking system (as applicable). In one or more examples, the memory 202 may include one or more solid-state storage devices, such as flash memory chips. In one or more examples, the memory 202 may include one or more mass storage devices connected to the processing circuit system 204 through a mass storage controller (not shown) and a communication bus (not shown).

[0049] Although the description of computer-readable media herein refers to solid-state storage, it should be understood by those skilled in the art that computer-readable storage media can be any available media that can be accessed by processing circuit system 204. That is, computer-readable storage media include non-transitory, volatile and non-volatile, removable and non-removable media implemented in any method or technology to store information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include RAM, ROM, EPROM, EEPROM, flash memory or other solid-state memory technology, CD-ROM, DVD, Blu-ray or other optical storage, cassettes, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by computing device 200. In one or more examples, the computer-readable storage media can be stored in a cloud or remote storage device and accessed using one or more any suitable technology through at least one of a wired or wireless connection.

[0050] The memory 202 may store pre-operative data 232, intra-operative data 234, and post-operative data 236. The pre-operative data 232 may include pre-treatment imaging data, sensor data (e.g., from a wearable device, an implantable device, a stethoscope, etc.), and / or patient metadata (e.g., gender, age, weight, height, body mass index, body fat percentage, comorbidities, cholesterol level, blood pressure, blood oxygen, physical exercise level, heart rate, etc.). The intra-operative data 234 may include data collected during a therapeutic medical procedure, such as angiography data of a patient undergoing a therapeutic medical procedure, intravascular imaging data of a patient undergoing a therapeutic medical procedure, other imaging data of a patient undergoing a therapeutic medical procedure, echocardiogram data of a patient undergoing a therapeutic medical procedure, sensor data associated with a patient undergoing a therapeutic medical procedure, etc. The post-operative data 236 may include data collected after a therapeutic medical procedure, such as sensor data associated with a patient, user input data associated with a patient, post-operative imaging data of a patient (e.g., imaging data generated after a therapeutic medical procedure), physiological data of a patient (e.g., FFR or other blood flow reserve measurements), etc. In some examples, preoperative data 232, intraoperative data 234, and postoperative data 236 include data related to multiple patients and can be used by processing circuit system 204 to train one or more of (multiple) machine learning / artificial intelligence algorithms 222. In some examples, preoperative data 232, intraoperative data 234, and postoperative data 236 include data related to the current patient. Processing circuit system 204 can execute a trained machine learning algorithm and / or a trained artificial intelligence algorithm in (multiple) machine learning / artificial intelligence algorithm 222 to generate a surgical plan 228 based on preoperative data 232 of the current patient.

[0051] The surgical plan 228 may include one or more potential treatments for the current patient. In general, the surgical plan 228 may include one or more of the following: use of a diagnostic catheter, plain balloon angioplasty (POBA), mechanical atherectomy, intravascular lithotripsy (IVL), drug-coated balloon angioplasty, stent delivery (including bare metal stents, drug-eluting stents (DES), bioresorbable stents, etc.), post-stent implantation optimization, guidewire-based FFR or other blood flow reserve measurement, image-based FFR or other blood flow reserve measurement, OCT, IVUS, etc. As a specific example, for bifurcation cases, potential treatments may include temporary stenting, T-type and small protrusion (TAP), inverted temporary stenting, double anastomosis (DK) pants stenting, DK compression, etc. For calcified lesion cases, potential treatments may include lesion crossing, imaging and calcification modification, etc. For CTO cases, potential treatments may include guidewire upgrades, antegrade, retrograde, dissection and reentry, controlled antegrade and retrograde subintimal tracking (CART), reverse CART, etc. For ISR cases, potential treatments may include lesion traversal, imaging, and lesion treatment, etc. Left main disease cases often include a bifurcation, and the bifurcation may be located in the last viable vessel supplying blood to the left side of the heart, and treatment may include treatment of the bifurcation. The surgical plan 228 may also provide the clinician with an understanding of which medical devices or equipment (e.g., atherectomy, balloon, drug-coated balloon, high pressure balloon, cutting or scoring balloon, intravascular lithotripsy (IVL), specialized guidewires, specialized microcatheters, intravascular imaging, calcification modification tools, stents, drug-eluting stents, mechanical circulatory support, etc.) they may need to perform the treatment(s) specified in the surgical plan.

[0052] In some examples, the clinician or computing device can enhance the surgical plan 228 by selecting any or all data from the catheterization laboratory 100 in real time from the display 206 and / or the input device 210. Such data can include invasive angiography, intravascular coronary imaging (e.g., intravascular ultrasound (IVUS), optical coherence tomography (OCT), etc.), echocardiography (ECG), etc. In some examples, because calcium in calcified lesions can cause blooming artifacts in three-dimensional (3D) images, the processing circuit system 204 can execute a machine learning algorithm or an artificial intelligence algorithm (such as a neural network) in (multiple) machine learning / artificial intelligence algorithms 222 to reduce blooming artifacts caused by calcification in the 3D image. For example, the machine learning algorithm or artificial intelligence algorithm can be trained to separate the calcium of the blood vessel from the native vascular anatomy to generate an image of the anatomy only. For example, the machine learning algorithm or artificial intelligence algorithm can be trained based on known real data. The real data can be created based on a simulation library based on previous anatomical structures and specific intravascular images provided for a specific case.

[0053] In some examples, the clinician may edit the surgical plan 228 via the input device 210 , such as by selecting or replacing one or more suggested treatments, by selecting or replacing one or more preferred medical devices, and so on.

[0054] To determine surgical plan 228 , processing circuitry 204 may analyze coronary artery problems (e.g., bifurcation lesions, calcified lesions, CTOs, ISRs, left main disease, etc.) identified in preoperative data 232 and characterize the anatomy, physiology, morphology, pathology, etc. For example, processing circuitry 204 may execute machine vision algorithm 218 to classify the coronary artery problem, or a clinician may classify the coronary artery problem through input device 210 or from another computing device via network interface 208 .

[0055] For example, for bifurcations, the processing circuit system 204 can analyze the anatomical structure of the vascular system around the bifurcation to assist in identifying specific strategies that can be used to treat this condition. The processing circuit system 204 can identify bifurcated diseases and classify them. For example, the processing circuit system 204 can classify bifurcated diseases according to a known classification system (such as the Medina classification) and include a 3D image of at least a portion of the vascular system to convey the severity or condition of the disease to the clinician. For example, some classified bifurcated diseases may respond differently to certain treatments than other classified bifurcated diseases. The processing circuit system 204 can analyze bifurcated lesions to identify strategies for treating bifurcated lesions (e.g., by performing multiple simulations). For example, the processing circuit system 204 can perform multiple simulations using different interventions and select one or more treatments with (multiple) the best simulated patient results for PCI. The processing circuit system 204 can include such one or more treatments in the surgical plan 228. The processing circuit system 204 can analyze the anatomical structure of the patient's blood vessels to estimate the position of medical devices or equipment (such as guidewires, microcatheters, balloons, stents, etc.).

[0056] In the example of a calcified lesion, processing circuit system 204 can analyze the anatomy of the vasculature surrounding the calcified lesion to assist in identifying a specific surgical strategy that may be useful in this situation. Processing circuit system 204 can analyze the anatomy of the blood vessels to estimate the location of medical devices (such as microcatheters and guidewires) to estimate whether there is sufficient support to penetrate the calcified lesion. Processing circuit system 204 can analyze the characteristics of the blood vessel wall to predict the appropriate calcification modification tool or medical device upgrade to be used during a therapeutic medical procedure.

[0057] For CTO, the processing circuit system 204 can analyze the distal cap and the proximal cap of the CTO. The processing circuit system 204 can analyze the CTO to identify any cracks along the lesion, which can help track the guidewire. The processing circuit system 204 can analyze the anatomical structure of the blood vessel to estimate the position of medical devices (such as microcatheters and guidewires) to estimate whether there is enough support to penetrate the patient-specific cap. The processing circuit system 204 can analyze the characteristics of the blood vessel wall to predict the applicability of the dissection and reentry strategy. The processing circuit system 204 can analyze the blood vessel to identify the true lumen of the vascular system. If the guidewire position cannot be determined by angiography alone (for example, it is not certain whether the guidewire is in the true lumen or in the vessel wall), this may be useful during PCI surgery. The processing circuit system 204 can analyze the patient's vascular system to determine the retrograde method using side branches or other blood vessels, thereby allowing medical devices to travel to the distal end of the lesion.

[0058] For ISR, the processing circuit system 204 can analyze the anatomy of the blood vessel to estimate the location of medical devices (such as microcatheters and guidewires) to estimate whether there is sufficient support to penetrate the lesion. The processing circuit system 204 can analyze the characteristics of the blood vessel wall to predict the appropriate ISR treatment strategy, including which (which) medical devices to use. The processing circuit system 204 can analyze the blood vessel wall to confirm that the stent has been implanted. In some examples, the confirmation that the stent has been implanted can be manually input via the input device 210 or pulled into the surgical plan 228 from the patient's electronic medical record (not shown). The stent design can be used to reduce blooming artifacts because some stents have more blooming artifacts than other stents. The stent design can be used to ensure that the mechanical properties of the stent are taken into account in any subsequent planning or simulation performed by the processing circuit system 204. The processing circuit system 204 can analyze the implanted stent design, such as running a simulation on the performance of the implanted stent design. The processing circuit system 204 can run simulations on the performance of other stent designs and compare the performance of the implanted stent design with the performance of other stent designs.

[0059] For left main disease, the processing circuit system 204 can analyze the patient's anatomy and run a simulation to determine the risk level of the therapeutic medical procedure. The processing circuit system 204 can recommend devices such as mechanical circulatory support based on the simulation and / or based on the diagnosis of left main disease. The processing circuit system 204 can also recommend backup support options, such as a hybrid laboratory heart team, in case complications occur during the therapeutic medical procedure. The processing circuit system 204 can analyze the anatomical structure of the blood vessel to estimate the position of medical devices (such as guidewires, microcatheters, balloons, stents, etc.) during the therapeutic medical procedure. The processing circuit system 204 can use the simulation with the best results to determine one or more treatments to be included in the surgical plan 228. The processing circuit system 204 can analyze the risk level of the therapeutic medical procedure and then incorporate risk reduction strategies into the surgical plan 228. An example of such a risk reduction strategy can include connecting a side branch of a blood vessel with a guidewire to ensure access to the vessel in the event of spasm or other reactions of the vessel. In some examples, the processing circuit system 204 or the clinician may request additional information, such as renal function, ejection fraction, LV function, etc., which may affect whether the patient should be protected by mechanical circulatory support. The processing circuit system 204 can use this information to determine whether the patient should be protected by mechanical circulatory support, and can include whether the patient should be protected by mechanical circulatory support in the plan. In some examples, the processing circuit system 204 can link or contact the clinician with the sales team or representative of the company that manufactures the mechanical circulatory support device when necessary to ensure that supervisory personnel are available during therapeutic medical procedures. For example, if there is no supervisory personnel from the company, the clinician may be reluctant to use mechanical circulatory support. The processing circuit system 204 can indicate whether it is recommended to use a heart team equipped with a hybrid laboratory as backup support.

[0060] In some examples, processing circuitry 204 may request additional information, such as intravascular imaging to be completed, to improve the accuracy of any prediction of the success of any simulation.

[0061] Processing circuit system 204 may determine a surgical plan 228 for PCI, for example, based on one or more analyses performed (e.g., based on simulations). In some examples, processing circuit system 204 may execute one or more of machine learning / artificial intelligence algorithm(s) or machine vision algorithm 218 when performing such simulations. In some examples, processing circuit system 204 may present a plurality of options for surgical plan 228 to a clinician via display 206, from which the clinician may select via input device 210. In other examples, processing circuit system 204 may determine surgical plan 228 without providing a plurality of options.

[0062] In some examples, surgical plan 228 may include medical devices or equipment that can be used for therapeutic medical procedures, such as atherectomy, balloons, drug-coated balloons, high-pressure balloons, cutting or scoring balloons, intravascular lithotripsy (IVL), specialized guidewires, specialized microcatheters, intravascular imaging, calcification modification tools, stents, drug-eluting stents, mechanical circulatory support, etc.

[0063] Processing circuit system 204 may execute at least one of a machine learning algorithm or an artificial intelligence algorithm (e.g., of machine learning / artificial intelligence algorithm(s) 222) to determine surgical plan 228. For example, at least one of the machine learning algorithm or artificial intelligence algorithm may be trained using surgical plans, treatments, and outcomes for coronary interventions (including data collected before, during, and after the procedure). Thus, the machine learning algorithm or artificial intelligence algorithm may be trained based on actual treatments and actual outcomes of past PCIs, and treatments may be incorporated into surgical plan 228 based on successful outcomes.

[0064] For example, a k-means clustering model may be used, which has multiple clusters: each cluster corresponds to each treatment performed using one or more specific medical devices and / or equipment. Each identified coronary problem may be associated with a vector including variables for, for example, preoperative data, intraoperative data, and postoperative data, such as the type of coronary problem, the severity of the coronary problem, the complexity of the coronary problem, the location of the coronary problem, the classification of the lesion, the anatomical structure of the coronary problem area, other anatomical structures, patient metadata (e.g., gender, age, weight, height, body mass index, body fat percentage, comorbidities, cholesterol level, blood pressure, blood oxygen, physical exercise level, heart rate, etc.), the results of therapeutic medical surgery, etc. The position of the vector in a given cluster can indicate a specific treatment performed using one or more specific medical devices and / or equipment. For example, if the vector belongs to a TAP cluster performed using a specific medical device, the machine learning algorithm or artificial intelligence algorithm can include TAP as a treatment in the surgical plan 228, and the specific medical device can be included in the surgical plan 228. Other machine learning or artificial intelligence techniques that may be used include Naive Bayes, k-nearest neighbors, random forests, support vector machines, neural networks, linear regression, logistic regression, etc.

[0065] The processing circuit system 204 can determine a specific surgical plan for the patient, which includes one or more treatments. For example, for bifurcations, the surgical plan 228 can include any of temporary stenting, TAP, inverted temporary stenting, DK pants stenting, DK compression, etc. For calcified lesions, the surgical plan 228 can include any of lesion crossing, imaging, and calcification modification. In the example of CTO, the surgical plan 228 can include any of guidewire upgrades, antegrade, retrograde, dissection and reentry, CART, reverse CART, etc. For ISR, the surgical plan 228 can include lesion crossing, imaging, and lesion treatment. For left main disease, the surgical plan 228 can include any of the above-mentioned treatments for bifurcations and / or other treatments.

[0066] As described above, the surgical plan 228 may include which medical devices and / or equipment may be used during the therapeutic medical procedure. In some examples, the surgical plan 228 may cross-reference the medical devices and / or equipment that may be used during the therapeutic medical procedure with the inventory available at a facility (e.g., a hospital) where the therapeutic medical procedure may be performed. The surgical plan 228 may also include a cross-reference of which medical devices and / or equipment may be approved for use in the area where the catheterization lab 100 is located. The surgical plan 228 may include a step-by-step approach to the therapeutic medical procedure and indicate when, where, and how the medical devices and / or equipment may be used. In some examples, the surgical plan 228 may include warnings for using specific medical devices and / or equipment in an off-label manner. For example, the processing circuit system 204 may cross-reference the use of the equipment in the surgical plan 228 with the equipment indications, contraindications, warnings, etc.

[0067] During a therapeutic medical procedure, computing device 200 may receive intraoperative data 234, which may include angiographic data of a patient undergoing the therapeutic medical procedure, intravascular imaging data of a patient undergoing the therapeutic medical procedure, other imaging data of a patient undergoing the therapeutic medical procedure, echocardiographic data of a patient undergoing the therapeutic medical procedure, sensor data associated with the patient undergoing the therapeutic medical procedure, and the like. If the intraoperative data indicates that a different treatment plan will provide a better predicted outcome, processing circuit system 204 may change the plan in real time. This may be desirable in complex PCI procedures because it may increase the likelihood of success or improve patient outcomes. For example, processing circuit system 204 may further execute a trained machine learning algorithm and / or a trained artificial intelligence algorithm in (multiple) machine learning / artificial intelligence algorithms 222 to determine whether to update surgical plan 228 based on at least a portion of surgical plan 228 or at least one of at least a portion of intraoperative data 234 (e.g., based on imaging data). For example, processing circuitry 204 may determine, based on at least one of at least a portion of surgical plan 228 and at least a portion of intraoperative data 234, that a different treatment may increase the likelihood of a successful outcome compared to the treatment included in surgical plan 228. As such, processing circuitry 204 may update surgical plan 228 to generate updated surgical plan 230, which processing circuitry 204 may store in memory 202, display via display 206, and / or output via network interface 208 or output device 212. In some examples, processing circuitry 204 may overwrite surgical plan 228 with updated surgical plan 230.

[0068] The processing circuit system 204 may further use the current patient's preoperative data 232, intraoperative data 234, and postoperative data 236 to train the trained machine learning algorithm and / or the trained artificial intelligence algorithm in the (multiple) machine learning / artificial intelligence algorithm 222. For example, in an example using a k-means clustering model, the k-means clustering model may add the current surgery to the cluster and associate a vector with the preoperative data 232, the intraoperative data 234, and the postoperative data 236.

[0069] Postoperative data 236 may include sensor data associated with the patient, user input data associated with the patient, postoperative imaging data of the patient, physiological data (FFR) of the patient, etc. The difference between preoperative data 232 and postoperative data 236 may indicate the results of the therapeutic medical procedure. For example, processing circuit system 204 may determine the difference between preoperative data 232 and postoperative data 236 to determine the degree of success of each procedure. For example, if postoperative imaging data indicates that the lesion shown in the preoperative data no longer exists, it may indicate that the operation was successful. If FFR analysis indicates that the postoperative blood flow is 95%, but the preoperative FFR data indicates that the blood flow is 20%, it may indicate that the operation was successful. If the sensor data indicates that the patient took significantly fewer steps and had a higher heart rate before the therapeutic medical procedure than after the treatment, it may indicate that the therapeutic medical procedure has achieved some degree of success, because these data may indicate that the patient's physical fitness level has improved. The cumulative results of a specific therapeutic medical procedure using a specific medical device to treat a specific coronary artery problem can provide a measure of the likelihood of a successful outcome.

[0070] The processing circuit system 204 may be implemented by one or more processors, which may include any number of fixed function circuits, programmable circuits, or combinations thereof. As described above, the guide workstation 50 may perform various control functions with respect to the imager 140 and may interact extensively with the computing device 200. The guide workstation 50 may be communicatively coupled to the computing device 200, enabling the guide workstation 50 to control the operation of the imager 140 and receive output from the imager 140. In some examples, the computing device 200 may control various operations of the imager 140.

[0071] In various examples, the control of any function by the processing circuit system 204 can be implemented directly or in combination with any suitable electronic circuit system suitable for the specified function. Fixed-function circuits refer to circuits that provide specific functions and preset operations that can be performed. Programmable circuits refer to circuits that can be programmed to perform various tasks and provide flexible functions in the operations that can be performed. For example, a programmable circuit can execute software or firmware that causes the programmable circuit to operate in a manner defined by the instructions of the software or firmware. Fixed-function circuits can execute software instructions (e.g., to receive parameters or output parameters), but the type of operation performed by the fixed-function circuit is generally immutable. In some examples, one or more of the units can be different circuit blocks (fixed function or programmable), and in some examples, one or more units can be integrated circuits.

[0072] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), graphics processing units (GPUs), or other equivalent integrated or discrete logic circuit systems. Therefore, as used herein, the term processing circuit system 204 may refer to one or more processors in any structure having the above-mentioned processors or processing structures or any other structure suitable for implementing the techniques described herein. In addition, in some aspects, the functions described herein may be provided in dedicated hardware or software modules configured for encoding and decoding, or incorporated into a combined codec. In addition, these techniques may be fully implemented in one or more circuits or logic elements.

[0073] The display 206 may include a display 206 that may be touch-sensitive or voice-activated, thereby enabling the display to act as an input and output device. Alternatively, a keyboard (not shown), a mouse (not shown) or other data input device (e.g., input device 210) may be utilized.

[0074] The network interface 208 may be adapted to connect to a network, such as a local area network (LAN), a wide area network (WAN), a wireless mobile network, a Bluetooth network, or the Internet, including a wired network or a wireless network. For example, the guide workstation 50, the computing device 150, and / or the server 160 may receive imaging data from the imager 140 and / or the imager 180 via the network interface 208 during a medical procedure. The guide workstation 50, the computing device 150, and / or the server 160 may receive updates to its software (e.g., the application 216) via the network interface 208. The guide workstation 50, the computing device 150, and / or the server 160 may also display a notification on the display 206 that a software update is available.

[0075] Input device 210 may be any device that enables a user to interact with guidance workstation 50 and / or computing device 150, such as a mouse, keyboard, foot pedal, touch screen, augmented reality input device that receives input such as gestures or body movements, or a voice interface.

[0076] Output device 212 may include any connection port or bus, such as a parallel port, a serial port, a universal serial bus (USB), or any other similar connection port known to those skilled in the art.

[0077] Application(s) 216 may be one or more software programs stored in memory 202 and executed by processing circuitry 204 of computing device 150. Processing circuitry 204 may display surgical plan 228, updated surgical plan 230, and / or intraoperative data 234 on display 206 and / or display device 110, for example, during a therapeutic medical procedure.

[0078] Figure 3 is a functional block diagram illustrating an example system including external computing devices (such as a server and one or more other computing devices) connected via a network. Figure 3 In the example of , patient computing device 300 , access point 302 , server 306 , and computing devices 312A- 312N are interconnected and able to communicate with each other via network 304 .

[0079] Access point 302 may include a device that connects to network 304 via any of a variety of connections, such as a telephone dial-up, a digital subscriber line (DSL), a cable modem, or a fiber optic connection. In other examples, access point 302 may be coupled to network 304 via different forms of connection, including a wired connection or a wireless connection. In some examples, access point 302 may be co-located with the patient. Server 306 may be Figure 1 In some examples, the memory 308 may store (multiple) machine learning / artificial intelligence algorithms 222 and / or machine vision algorithms 218 ( Figure 2 ), and the processing circuit system 310 can execute (multiple) machine learning / artificial intelligence algorithms 222 and / or machine vision algorithms 218.

[0080] Patient computing devices and / or computing devices 312A-312N (which may be clinician computing devices) may include laptop computers, desktop computers, tablet computers, smartphones, or other similar devices, or may include special purpose devices. Although not shown, in some examples, any or all of computing devices 312A-312N may be connected to network 304 via one or more access points.

[0081] In some examples, server 306 can be configured to provide preoperative data 232, intraoperative data 234, postoperative data 236, surgical plan 228, updated surgical plan 230, report 240, updated report 242 ( Figure 2 a secure storage site for any other data collected related to the patient(s) and / or medical procedure. Figure 3 The system shown may in some aspects be implemented with general network technology and functionality similar to that developed by Medtronic plc of Dublin, Ireland. Provided by the network.

[0082] In some examples, one or more of server 306 or computing device 312 may be configured to perform the tasks described herein (eg, with respect to computing device 200 ( Figure 2)'s processing circuit system 204) may, for example, include a processing circuit system configured to perform these techniques.

[0083] In some examples, server 306 may function as a patient portal from which patients may access their medical information, including information about medical procedures at a layperson's understandable level, via patient computing device 300 and access point 302. For example, a patient portal may focus on education and engagement with patients.

[0084] In some examples, one or more of the computing devices 312 may be clinician computing devices, which may be located in a laboratory including the catheterization lab 100 ( Figure 1 ) facility or located elsewhere. In some examples, server 306 can act as a clinician portal, which can store all collected information about therapeutic medical operations, including the entire data history, all preoperative data 232, all intraoperative data 234, and all postoperative data. In some examples, a machine learning algorithm or an artificial intelligence algorithm can be trained based on the collected data in the clinician portal, the data collected by each device involved in data collection, or a combination of the two. In some examples, the clinician portal may be specific to the identification and treatment strategies of coronary artery disease (CAD). For example, a clinician can access the clinician portal via one of the computing devices 312. In some examples, the clinician portal and / or the patient portal may include encryption to prevent unauthorized access. The clinician portal may include a surgical planner that can employ the technology disclosed herein.

[0085] For example, postoperative data 236 may include data generated by sensors, such as from wearable device(s) (e.g., smartwatches, patches, etc.) and / or implantable devices. In some examples, postoperative data 236 may include thirty days or more of data generated by such sensor(s). Such data may be sent to patient computing device 300 and transmitted by patient computing device 300 to a patient portal (e.g., server 306) via access point 302 and network 304. In some examples, all or part of preoperative data 232, intraoperative data 234, and postoperative data 236 associated with a particular patient may be included in the patient's electronic medical record on server 306 to showcase the full patient journey value as part of a patient portal or clinician portal.

[0086] Figure 4is a flow chart of an example surgical plan generation technique according to one or more aspects of the present disclosure. Processing circuit system 204 may receive pre-treatment imaging data indicating a coronary artery problem in at least a portion of a patient's vasculature (400). For example, processing circuit system 204 may receive pre-operative data 232, which may include pre-treatment imaging data of the patient. Such pre-treatment imaging data may have been acquired during a diagnostic imaging procedure to assist in diagnosing a coronary artery problem (e.g., prior to PCI). The pre-treatment imaging data may indicate a coronary artery problem, such as a bifurcation lesion, a calcified lesion, a CTO, an ISR, left main disease; etc.

[0087] Processing circuitry 204 may automatically determine a surgical plan for use during a therapeutic medical procedure in a catheterization laboratory based at least in part on the pre-treatment imaging data (402). For example, processing circuitry 204 may apply at least one of a machine learning algorithm or an artificial intelligence algorithm (of machine learning / artificial intelligence algorithm(s) 222) to the pre-treatment imaging data. Additionally or alternatively, processing circuitry 204 may perform a plurality of surgical simulations to determine at least one treatment including a surgical plan.

[0088] Processing circuit system 204 may output a surgical plan (404). For example, processing circuit system 204 may output surgical plan 228 to at least one of a computing device (e.g., computing device 150, server 160, computing device 312A, etc.), a user interface (e.g., display 206 or display device 110), or robot 102. For example, a clinician may view surgical plan 228 via display 206 and may use surgical plan 228 to assist in performing a therapeutic medical procedure. A patient or caregiver may view surgical plan 228 or a simplified version of surgical plan 228. Robot 102 may use surgical plan 228 to perform a therapeutic medical procedure. In some examples, such as in a robot-assisted medical procedure, a clinician may view surgical plan 228 while robot 102 may use surgical plan 228 to assist the clinician in performing a therapeutic medical procedure.

[0089] In some examples, processing circuit system 204 may receive patient metadata (which may be part of preoperative data 232) including at least one of gender, age, weight, height, body mass index, body fat percentage, comorbidities, cholesterol level, blood pressure, blood oxygen, physical exercise level, or heart rate, and processing circuit system 204 may further automatically determine a surgical plan based on the patient metadata. For example, the patient metadata may be imported from a patient electronic medical record, may be entered by a clinician, and / or collected by providing one or more sensors (such as a wearable device (e.g., a smart watch or fitness watch), a stethoscope, etc.). In some examples, the surgical plan includes at least one of the following: data indicating one or more treatments, medical devices for performing one or more treatments, devices to be used during one or more treatments, step-by-step instructions on how to perform one or more treatments, instructions on when, where, and how to use at least one medical device or device, or a warning about unapproved use of at least one medical device or device. In some examples, the coronary artery problem includes at least one of a bifurcation lesion, a calcified lesion, a CTO, an ISR, or left main disease.

[0090] In some examples, processing circuit system 204 may receive second imaging data (e.g., intraoperative data 234) during a therapeutic medical procedure and control a display device (e.g., a display of display 206 or display device 110) to display surgical plan 228 together with the second imaging data during the therapeutic medical procedure. In some examples, processing circuit system 204 may determine to update surgical plan 288 based on at least one of at least a portion of the second imaging data or at least a portion of surgical plan 288. Processing circuit system 204 may update surgical plan 288 to generate updated surgical plan 230, and updated surgical plan 230 includes at least one treatment not included in the surgical plan. Processing circuit system 204 may control the display device to display updated surgical plan 230. For example, processing circuit system 204 may output the updated surgical plan to a computing device (e.g., computing device 150, server 160, computing device 312A, etc.), a display device (e.g., a display of display 206 or display 110), and / or robot 102.

[0091] In some examples, as part of determining an updated surgical plan or at least one of the updated surgical plans, the processing circuit system 204 may apply at least one of a machine learning application or an artificial intelligence application (e.g., one of (multiple) machine learning / artificial intelligence algorithms 222) to at least a portion of the second imaging data or at least a portion of the surgical plan 228.

[0092] In some examples, processing circuit system 204 can generate report 240, including data collected during the therapeutic medical procedure. In some examples, processing circuit system 204 can update report 240 to generate updated report 242 based on postoperative data 236 related to the patient. For example, processing circuit system 204 can make all collected data (all intraoperative data 234) from the therapeutic medical procedure available to clinicians via display 206. In some examples, processing circuit system 204 can prepare summary reports (such as report 240) for clinicians, or can facilitate clinicians to prepare such reports via display 206. In some examples, display 206 can be configured to allow clinicians to enter the results of PCI, for example, including the final pictures of angiography and / or intravascular coronary artery imaging. In some examples, clinicians can enhance the recorded results (e.g., the results in report 240) via display 206, for example, after 30 days or even longer, to create an updated report 242. In some examples, patients can enhance the recorded results of their PCI surgery via a patient portal or via wearable or implanted sensors. The processing circuit system may include captured data of the PCI procedure, the plan, the actual treatment, the recorded results, and / or the enhanced results in the patient's medical record. The processing circuit system may control the telemetry circuit system to push or otherwise transmit the data to one or more devices that may execute the machine learning algorithm or artificial intelligence algorithm to be used for further training the machine learning algorithm or artificial intelligence algorithm. For example, one or more devices may be located in a facility or in a cloud-based computing network. In this way, the machine learning algorithm or artificial intelligence algorithm can be improved to develop a surgical plan for a therapeutic medical procedure using pre-treatment imaging.

[0093] Figure 5is a flow chart of a training technique for an example machine learning algorithm or artificial intelligence algorithm according to one or more aspects of the present disclosure. The processing circuit system 204 may receive preoperative data 232 (500). For example, the processing circuit system 204 may receive preoperative data 232 from (multiple) diagnostic imaging systems (not shown), (multiple) wearable devices not shown, server 160, patient electronic medical records, clinician input, etc. The preoperative data 232 may include data related to at least a corresponding portion of the corresponding vascular system of one or more patients. In some examples, the preoperative data 232 includes at least one of the following: pre-treatment imaging data of at least a corresponding portion of the corresponding vascular system of one or more patients; or sensor data related to one or more patients, such as sensor data collected by a wearable device (such as a smart watch or fitness watch, a stethoscope, etc.). In some examples, the preoperative data 232 may include patient metadata, such as gender, age, weight, height, body mass index, body fat percentage, comorbidities, cholesterol level, blood pressure, blood oxygen, physical exercise level, or heart rate.

[0094] Processing circuitry 204 may receive intraoperative data 234 that was collected during a respective therapeutic medical procedure performed on one or more patients (502). For example, processing circuitry 204 may receive intraoperative data 234 from imager 140, imager 180, one or more cameras 190, etc., in real time while the therapeutic medical procedure is being performed. In some examples, intraoperative data 234 includes at least one of the following: angiographic data of one or more patients, intravascular imaging data of one or more patients, echocardiographic data of one or more patients, sensor data of one or more patients, or video data. In some examples, the video data includes an indication of at least one of the following: hand motion, robot motion, a medical device or equipment used, a time at which the medical device or equipment was used, or a location at which the medical device or equipment was used.

[0095] Processing circuitry 204 may receive postoperative data 236 collected after performing a corresponding therapeutic medical procedure on one or more patients (504). For example, processing circuitry 204 may receive postoperative data 236 from, for example, a wearable device, a diagnostic imaging system, a user interface, an FFR device, server 160, etc. after the corresponding therapeutic medical procedure is completed. In some examples, the postoperative data includes at least one of the following: postoperative sensor data associated with the one or more patients, user input data associated with the one or more patients, postoperative imaging data of the one or more patients, or physiological data of the one or more patients.

[0096] Processing circuit system 204 may train at least one of the machine learning algorithm or artificial intelligence algorithm (e.g., among the machine learning / artificial intelligence algorithm(s) 222) based on pre-operative data 232, intra-operative data 234, and post-operative data 236 to generate at least one of the trained machine learning algorithm or trained artificial intelligence algorithm (e.g., among the machine learning / artificial intelligence algorithm(s) 222) (506). For example, processing circuit system 204 may input pre-operative data 232, intra-operative data 234, and post-operative data 236 into the machine learning algorithm and / or artificial intelligence algorithm to train the machine learning algorithm and / or artificial intelligence algorithm.

[0097] In some examples, at least a portion of system 10 is based on a cloud computing environment. In some examples, the one or more patients include a current patient. In some examples, processing circuit system 204 can receive current preoperative data for the current patient (e.g., preoperative data 232). Processing circuit system 204 can apply at least one of a trained machine learning algorithm or a trained artificial intelligence algorithm (e.g., one of (multiple) machine learning / artificial intelligence algorithms 222) to the current preoperative data for the current patient. Processing circuit system 204 can automatically determine a surgical plan 228 for the current patient based on the application of the trained machine learning algorithm or the trained artificial intelligence algorithm to the current preoperative data for the current patient, and output surgical plan 228 for the current patient for use during a therapeutic medical procedure.

[0098] In some examples, processing circuit system 204 may receive current intraoperative data for a current patient (e.g., intraoperative data 234). Processing circuit system 204 may apply at least one of a trained machine learning algorithm or a trained artificial intelligence algorithm to at least one of at least a portion of the current intraoperative data or at least a portion of a surgical plan 228 for the current patient. Processing circuit system 204 may determine to update surgical plan 228 based on the application of the trained machine learning algorithm or the trained artificial intelligence algorithm to at least one of at least a portion of the current intraoperative data for the current patient or at least a portion of a surgical plan 228 for the current patient. Processing circuit system 204 may update surgical plan 228 to generate updated surgical plan 230, and output updated surgical plan 230 for the current patient for use during a therapeutic medical procedure.

[0099] In some examples, as part of determining updated surgical plan 230, processing circuitry 204 may determine that a second treatment not included in surgical plan 228 has a higher likelihood of a successful patient outcome than a first treatment included in surgical plan 228, and wherein updated surgical plan 230 includes the second treatment. In some examples, processing circuitry 204 may output surgical plan 228 to at least one of a computing device, display 206, or robot 102.

[0100] Figure 6 is a conceptual diagram illustrating an example machine learning model according to one or more aspects of the present disclosure. The machine learning model 600 can be an example of (multiple) machine learning / artificial intelligence algorithms 222. In some examples, the machine learning model 600 can be the Figure 2 Part of the machine vision algorithm 218 discussed. The machine learning model 600 can be an example of a deep learning model or deep learning algorithm that is trained to determine the type of patient condition and / or medical procedure. One or more of the computing devices 150 and / or the server 160 can train, store and / or utilize the machine learning model 600, but in some examples, other devices of the system 10 can apply input to the machine learning model 600. In some examples, other types of machine learning and deep learning models or algorithms can be utilized in other examples. For example, a convolutional neural network model of ResNet-18 can be used. Some non-limiting examples of models that can be used for transfer learning include AlexNet, VGGNet, GoogleNet, ResNet50, or DenseNet, etc. Some non-limiting examples of machine learning techniques include support vector machines, K nearest neighbor algorithms, and multilayer perceptrons.

[0101] like Figure 6 As shown in the example of , the machine learning model 600 may include three types of layers. The three types of layers include an input layer 602, a hidden layer 604, and an output layer 606. The output layer 606 includes the output of the transfer function 605 from the output layer 606. The input layer 602 represents each input value X1 to X4 provided to the machine learning model 600. In some examples, the input values ​​may include any value input to the machine learning model, as described above. For example, the input values ​​may include preoperative data 232, intraoperative data 234, and / or postoperative data 236 as described above. In addition, in some examples, the input values ​​of the machine learning model 600 may include additional data, such as other data that may be collected by or stored in the system 10.

[0102] Each input value of each node in the input layer 602 is provided to each node of the first hidden layer 604. Figure 6In the example of , hidden layer 604 includes two layers, one layer having four nodes and the other layer having three nodes, but fewer or greater numbers of nodes may be used in other examples. Each input from input layer 602 is multiplied by a weight and then summed at each node of hidden layer 604. During training of machine learning model 600, the weight of each input is adjusted to establish a relationship between preoperative data 232, intraoperative data 234, and / or postoperative data 236 and a surgical plan (e.g., surgical plan 228 and / or updated surgical plan 230). In some examples, one hidden layer may be incorporated into machine learning model 600, or three or more hidden layers may be incorporated into machine learning model 600, where each layer includes the same or different numbers of nodes.

[0103] The results of each node within the hidden layer 604 are applied to the transfer function of the output layer 606. The transfer function can be linear or nonlinear, depending on the number of layers within the machine learning model 600. Example nonlinear transfer functions can be sigmoid functions or rectifier functions. The output 607 of the transfer function can be a classification that the preoperative data 232, the intraoperative data 234, and / or the postoperative data 236 indicate a particular surgical plan (e.g., the surgical plan 228 and / or the updated surgical plan 230).

[0104] As shown in the above example, by applying machine learning model 600 to input data (e.g., preoperative data 232, intraoperative data 234, and / or postoperative data 236), processing circuit system 204 can generate and / or update a surgical plan. This can improve patient outcomes.

[0105] Figure 7 is a conceptual diagram illustrating an example training process of a machine learning model according to one or more aspects of the present disclosure. Process 700 can be used to train (multiple) machine learning / artificial intelligence algorithms 222 and / or machine vision algorithms 218. Machine learning model 774 (which can be an example of machine learning model 600 and / or (multiple) machine learning / artificial intelligence algorithms 222) can be implemented using any number of supervised and / or reinforcement learning models, such as but not limited to artificial neural networks, decision trees, naive Bayesian networks, support vector machines, k-nearest neighbor models, CNNs, RNNs, LSTMs, integrated networks, to name a few examples. In some examples, one or more of computing devices 150 and / or servers 160 initially train machine learning model 774 based on a corpus of training data 772. Training data 772 can include, for example, preoperative data 232, intraoperative data 234, and / or postoperative data 236, other training data that may be mentioned herein, and the like.

[0106] When training the machine learning model 774, the processing circuit system of the system 2 may compare 776 the prediction or classification with the target output 778. The processing circuit system 204 may train (learn / train 780) the machine learning model 774 using an error signal resulting from the comparison. The processing circuit system 204 may generate machine learning model weights or other modifications, which the processing circuit system 204 may use to modify the machine learning model 774. For example, the processing circuit system 204 may modify the weights of the machine learning model 600 based on the learning / training 480. For example, for each training instance in the training data 772, one or more of the computing device 150 and / or the server 160 may modify the manner in which the surgical plan is generated and / or updated based on the training data 772.

[0107] The techniques described in the present disclosure may be implemented at least in part in hardware, software, firmware, or any combination thereof. For example, the various aspects of the described techniques may be implemented in one or more processors or processing circuit systems, including one or more microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or any other equivalent integrated or discrete logic circuit systems and any combination of such components. The terms "controller," "processor," or "processing circuit system" may generally refer to any (separate or in combination with other logic circuit systems) circuit system, or any other equivalent circuit system in the aforementioned logic circuit system. A control unit including hardware may also perform one or more techniques of the present disclosure. Such hardware, software, and firmware may be implemented in the same device or in different devices to support the various operations and functions described in the present disclosure. In addition, any of the described units, circuits, or components may be implemented together or separately as discrete but mutually operable logic devices. Depicting different features as circuits or units is intended to highlight different functional aspects and does not necessarily imply that such circuits or units must be implemented by different hardware or software components. Rather, functionality associated with one or more circuits or units may be performed by different hardware or software components, or integrated within common or different hardware or software components.

[0108] These techniques described in the present disclosure may also be embedded or encoded into a computer-readable medium, such as a computer-readable storage medium containing multiple instructions. Multiple instructions embedded or encoded into a computer-readable storage medium may enable a programmable processor, or other processor to perform the method, for example, when executing these instructions. A computer-readable storage medium may include a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), or an electrically erasable programmable read-only memory (EEPROM), or other computer-readable media.

[0109] This disclosure includes the following non-limiting examples.

[0110] Example 1. A medical system comprising: a memory configured to store at least one of a machine learning algorithm or an artificial intelligence algorithm; and a processing circuit system communicatively coupled to the memory, the processing circuit system configured to: receive preoperative data, the preoperative data comprising data related to at least a corresponding portion of a corresponding vascular system of one or more patients; receive intraoperative data, the intraoperative data collected during a corresponding therapeutic medical operation performed on the one or more patients; receive postoperative data, the postoperative data collected after the corresponding therapeutic medical operation performed on the one or more patients; and train at least one of the machine learning algorithm or the artificial intelligence algorithm based on the preoperative data, the intraoperative data, and the postoperative data to generate a trained machine learning algorithm or at least one of the trained artificial intelligence algorithms.

[0111] Example 2. A medical system as described in Example 1, wherein at least a portion of the system is based on a cloud computing environment.

[0112] Example 3. A medical system as described in Example 1 or Example 2, wherein the preoperative data includes at least one of the following: pre-treatment imaging data of at least a corresponding portion of the corresponding vascular system of the one or more patients; or sensor data related to the one or more patients.

[0113] Example 4. A medical system as described in any of Examples 1-3, wherein the intraoperative data includes at least one of the following: angiography data of the one or more patients, intravascular imaging data of the one or more patients, echocardiography data of the one or more patients, sensor data of the one or more patients, or video data.

[0114] Example 5. A medical system as described in Example 4, wherein the video data includes an indication of at least one of: hand movement, robot movement, a medical instrument or device used, a time at which a medical instrument or device was used, or a location at which a medical instrument or device was used.

[0115] Example 6. A medical system as described in any of Examples 1-5, wherein the postoperative data includes at least one of the following: postoperative sensor data related to the one or more patients, user input data related to the one or more patients, postoperative imaging data of the one or more patients, or physiological data of the one or more patients.

[0116] Example 7. A medical system as described in any of Examples 1-6, wherein the one or more patients include a current patient, and wherein the processing circuit system is further configured to: receive current preoperative data of the current patient; apply at least one of the trained machine learning algorithm or the trained artificial intelligence algorithm to the current preoperative data of the current patient; automatically determine a surgical plan for the current patient based on the application of the trained machine learning algorithm or the trained artificial intelligence algorithm to the current preoperative data of the current patient; and output the surgical plan of the current patient for use during a therapeutic medical operation.

[0117] Example 8. A medical system as described in Example 7, wherein the processing circuit system is further configured to: receive current intraoperative data of the current patient; apply at least one of the trained machine learning algorithm or the trained artificial intelligence algorithm to at least a portion of the current intraoperative data or at least a portion of the surgical plan of the current patient; determine an update to the surgical plan based on the application of the trained machine learning algorithm or the trained artificial intelligence algorithm to at least a portion of the current intraoperative data of the current patient or at least a portion of the surgical plan of the current patient; update the surgical plan to generate an updated surgical plan; and output the updated surgical plan of the current patient for use during the therapeutic medical surgery.

[0118] Example 9. A medical system as described in Example 8, wherein, as part of determining to update the surgical plan, the processing circuit system is configured to determine that a second treatment not included in the surgical plan has a higher likelihood of a successful patient outcome than a first treatment included in the surgical plan, and wherein the updated surgical plan includes the second treatment.

[0119] Example 10. A medical system as described in any of Examples 7-9, wherein the processing circuit system is configured to output the surgical plan to at least one of a computing device, a user interface, or a robot.

[0120] Example 11. A method comprising: receiving, by a processing circuit system, preoperative data, the preoperative data comprising data relating to at least a corresponding portion of a corresponding vascular system of one or more patients; receiving, by the processing circuit system, intraoperative data, the intraoperative data being collected during a corresponding therapeutic medical procedure performed on the one or more patients; receiving, by the processing circuit system, postoperative data, the postoperative data being collected after the corresponding therapeutic medical procedure performed on the one or more patients; and training, by the processing circuit system, at least one of a machine learning algorithm or an artificial intelligence algorithm based on the preoperative data, the intraoperative data, and the postoperative data to generate at least one of a trained machine learning algorithm or a trained artificial intelligence algorithm.

[0121] Example 12. The method of Example 11, wherein at least a portion of the processing circuit system is based on a cloud computing environment.

[0122] Example 13. A method as described in Example 11 or Example 12, wherein the preoperative data includes at least one of the following: pre-treatment imaging data of at least a corresponding portion of the corresponding vascular system of the one or more patients; or sensor data related to the one or more patients.

[0123] Example 14. A method as described in any of Examples 11-13, wherein the intraoperative data includes at least one of the following: angiography data of the one or more patients, intravascular imaging data of the one or more patients, echocardiography data of the one or more patients, sensor data of the one or more patients, or video data.

[0124] Example 15. A method as described in Example 14, wherein the video data includes an indication of at least one of: hand movement, robot movement, a medical instrument or device used, a time when a medical instrument or device was used, or a location where a medical instrument or device was used.

[0125] Example 16. A method as described in any of Examples 11-15, wherein the postoperative data includes at least one of the following: postoperative sensor data related to the one or more patients, user input data related to the one or more patients, postoperative imaging data of the one or more patients, or physiological data of the one or more patients.

[0126] Example 17. A method as described in any of Examples 11-16, wherein the one or more patients include a current patient, and wherein the method further includes: receiving, by the processing circuit system, current preoperative data of the current patient; applying, by the processing circuit system, at least one of the trained machine learning algorithm or the trained artificial intelligence algorithm to the current preoperative data of the current patient; automatically determining, by the processing circuit system, a surgical plan for the current patient based on the application of the trained machine learning algorithm or the trained artificial intelligence algorithm to the current preoperative data of the current patient; and outputting, by the processing circuit system, the surgical plan of the current patient for use during a therapeutic medical operation.

[0127] Example 18. The method as described in Example 17 further includes: receiving, by the processing circuit system, current intraoperative data of the current patient; applying, by the processing circuit system, at least one of the trained machine learning algorithm or the trained artificial intelligence algorithm to at least a portion of the current intraoperative data or at least a portion of the surgical plan of the current patient; determining, by the processing circuit system, an update to the surgical plan based on the application of the trained machine learning algorithm or the trained artificial intelligence algorithm to at least a portion of the current intraoperative data of the current patient or at least a portion of the surgical plan of the current patient; and updating, by the processing circuit system, the surgical plan to generate an updated surgical plan; and outputting, by the processing circuit system, the updated surgical plan of the current patient for use during the therapeutic medical surgery.

[0128] Example 19. A medical system as described in Example 18, wherein determining to update the surgical plan includes determining that a second treatment not included in the surgical plan has a higher likelihood of a successful patient outcome than a first treatment included in the surgical plan, and wherein the updated surgical plan includes the second treatment.

[0129] Example 20. A method as described in any of Examples 17-19, wherein outputting the surgical plan includes outputting the surgical plan to at least one of a computing device, a user interface, or a robot.

[0130] Example 21. A non-transitory computer-readable storage medium storing instructions that, when executed, cause a processing circuit system to: receive preoperative data, the preoperative data comprising data related to at least a corresponding portion of a corresponding vascular system of one or more patients; receive intraoperative data, the intraoperative data collected during a corresponding therapeutic medical procedure performed on the one or more patients; receive postoperative data, the postoperative data collected after performing the corresponding therapeutic medical procedure on the one or more patients; and train at least one of a machine learning algorithm or an artificial intelligence algorithm based on the preoperative data, the intraoperative data, and the postoperative data to generate at least one of a trained machine learning algorithm or a trained artificial intelligence algorithm.

[0131] Various different examples have been described. These and other examples are within the scope of the following claims.

Claims

1. A medical system comprising: a memory configured to store at least one of a machine learning algorithm or an artificial intelligence algorithm; as well as processing circuitry communicatively coupled to the memory, the processing circuitry being configured to: receiving preoperative data including data related to at least respective portions of respective vasculature of one or more patients; receiving intraoperative data collected during a respective therapeutic medical procedure performed on the one or more patients; receiving post-operative data, the post-operative data collected following a corresponding therapeutic medical procedure performed on the one or more patients; as well as The machine learning algorithm or at least one of the artificial intelligence algorithms is trained based on the preoperative data, the intraoperative data, and the postoperative data to generate at least one of a trained machine learning algorithm or a trained artificial intelligence algorithm.

2. The medical system of claim 1, wherein: At least a portion of the system is based on a cloud computing environment.

3. The medical system of claim 1 or claim 2, wherein: The pre-operative data comprises at least one of: pre-treatment imaging data of at least respective portions of respective vasculature of the one or more patients; or sensor data associated with the one or more patients.

4. The medical system according to any one of claims 1 to 3, wherein: The intraoperative data includes at least one of: angiography data of the one or more patients, intravascular imaging data of the one or more patients, echocardiography data of the one or more patients, sensor data of the one or more patients, or video data.

5. The medical system of claim 4, wherein: The video data includes an indication of at least one of: hand movement, robot movement, a medical instrument or device being used, a time at which a medical instrument or device was used, or a location at which a medical instrument or device was used.

6. The medical system according to any one of claims 1 to 5, wherein: The post-operative data includes at least one of: post-operative sensor data associated with the one or more patients, user input data associated with the one or more patients, post-operative imaging data of the one or more patients, or physiological data of the one or more patients.

7. The medical system according to any one of claims 1 to 6, wherein: The one or more patients include a current patient, and wherein the processing circuitry is further configured to: receiving current preoperative data of the current patient; applying at least one of the trained machine learning algorithm or the trained artificial intelligence algorithm to the current preoperative data of the current patient; automatically determining a surgical plan for the current patient based on application of the trained machine learning algorithm or the trained artificial intelligence algorithm to the current preoperative data of the current patient; and The surgical plan for the current patient is output for use during a therapeutic medical procedure.

8. The medical system of claim 7, wherein: The processing circuit system is further configured to: receiving current intraoperative data of the current patient; applying at least one of the trained machine learning algorithm or the trained artificial intelligence algorithm to at least one of at least a portion of the current intraoperative data or at least a portion of the surgical plan for the current patient; determining an update to the surgical plan based on application of the trained machine learning algorithm or the trained artificial intelligence algorithm to at least one of at least a portion of the current intraoperative data for the current patient or at least a portion of the surgical plan for the current patient; updating the surgical plan to generate an updated surgical plan; as well as The updated surgical plan for the current patient is output for use during the therapeutic medical procedure.

9. The medical system of claim 8, wherein: As part of determining to update the surgical plan, the processing circuit system is configured to determine that a second treatment not included in the surgical plan has a higher likelihood of a successful patient outcome than a first treatment included in the surgical plan, and wherein the updated surgical plan includes the second treatment.

10. The medical system according to any one of claims 7 to 9, wherein: The processing circuitry is configured to output the surgical plan to at least one of a computing device, a user interface, or a robot.

11. A method comprising: receiving, by processing circuitry, pre-operative data including data relating to at least respective portions of respective vasculature of one or more patients; receiving, by the processing circuitry, intraoperative data collected during a respective therapeutic medical procedure performed on the one or more patients; receiving, by the processing circuitry, post-operative data collected following a respective therapeutic medical procedure performed on the one or more patients; as well as The processing circuit system trains at least one of the machine learning algorithm or the artificial intelligence algorithm based on the preoperative data, the intraoperative data, and the postoperative data to generate at least one of the trained machine learning algorithm or the trained artificial intelligence algorithm.

12. The method of claim 11, wherein: At least a portion of the processing circuitry is based on a cloud computing environment.

13. The method of claim 11 or claim 12, wherein: The pre-operative data comprises at least one of: pre-treatment imaging data of at least respective portions of respective vasculature of the one or more patients; or sensor data associated with the one or more patients.

14. The method according to any one of claims 11 to 13, wherein: The intraoperative data includes at least one of: angiography data of the one or more patients, intravascular imaging data of the one or more patients, echocardiography data of the one or more patients, sensor data of the one or more patients, or video data.

15. A non-transitory computer-readable storage medium storing instructions which, when executed, cause a processing circuit system to perform the method of any one of claims 11-14.

Images