Surgical and device evaluation using catheter chamber images

Abstract

Example systems and techniques are disclosed that may determine lesion characteristics. An example system may include a memory configured to store at least one computer vision model and processing circuitry communicatively coupled with the memory. The processing circuitry may be configured to receive imaging data of at least a portion of a patient vasculature generated during a cardiac catheter procedure. The processing circuitry may be configured to execute the at least one computer vision model to determine a characteristic of a lesion in the vasculature based on the received imaging data.

Description

[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 365,940, filed on June 6, 2022, entitled “USE OF CATH LAB IMAGES FOR PROCEDURE AND DEVICE EVALUATION.” Technical Field

[0002] The present disclosure relates to the use of images captured during medical procedures. Background Art

[0003] During medical procedures, clinicians may use imaging systems to be able to visualize the internal anatomy of a patient. Such imaging systems may display anatomical structures, medical devices, etc., and may be used to diagnose a patient condition or to assist in guiding the clinician in moving equipment, such as medical devices, to a desired location within the patient's body. Imaging systems may use sensors to capture video images, which may be displayed during medical procedures. 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 performing surgery and / or device evaluation using images captured during medical surgery. For example, the system can track the movement of medical instruments to evaluate operator skills (as a research variable), such as which operator skills can provide the best results. As used herein, medical instruments include any equipment that can be used to treat patients. The system can also connect other instruments commonly used in cardiac catheterization laboratories (catheterization rooms, Cath Labs) and integrate their respective data, such as integrating ablation data from renal denervation (RDN) generators into imaging systems (such as fluoroscopy) to evaluate the results in more detail. In addition or alternatively, the system can track the movement of the device to evaluate the device's ability to penetrate a specific type of lesion. By tracking the position of the medical instrument during therapeutic medical surgery, the system can determine, for example, which operator skills can provide the best results and / or which medical instruments can provide the best results for a specific type of lesion. The system may include a computer vision model that can be used to identify, classify and / or score specific lesions. The system may also include a machine learning model that can be used to determine potential treatments most likely to achieve a successful outcome and such potential treatment options can be presented to a clinician before, during, or after a therapeutic medical procedure.

[0005] The present disclosure also relates to various technologies and medical systems for using images captured during diagnostic medical procedures for treatment planning purposes. For example, during a diagnostic phase (e.g., diagnostic angiography), there are three possible outcomes. First, the clinician may determine that intervention is not needed. Second, the clinician may determine that urgent intervention is needed, and the clinician can handle the intervention during the same catheter room phase (e.g., without the patient leaving and coming back at another time). Third, treatment may be needed, but the clinician is unwilling to perform the treatment, or the hospital where the catheter room is located does not have the instruments required for treatment. In the case of the third possible outcome, there may be imaging data (e.g., angiography data) from diagnostic medical procedures. The example system can use such imaging data to formulate a treatment plan or assist clinicians in formulating a treatment plan. Such a system can include a computer vision model and a machine learning model. The computer vision model can be used to identify, classify and / or score specific lesions. The machine learning model can be used to determine the potential treatment that is most likely to achieve a successful outcome, and this potential treatment strategy can be presented to the clinician to formulate a treatment plan for a therapeutic medical procedure. The system can be configured to run simulations on potential treatment strategies to assist clinicians in selecting one or more treatment strategies to be used during a therapeutic medical procedure.

[0006] The present disclosure also relates to various technologies and medical systems for streaming or sharing representations of imaging data from one or more image sensors with remote clinicians during medical procedures (e.g., cardiac catheterization medical procedures). For example, when a specific clinician is performing a medical procedure in a cardiac catheterization laboratory (cath room), a medical system can establish (e.g., via a secure network) a communication session with a device associated with the remote clinician (i.e., a second clinician who is not in the catheter room). The computing system can stream or share imaging data to the remote clinician via a communication session. In this way, the medical system can enable the remote clinician to provide assistance (e.g., viewing and / or consultation) to the specific clinician (i.e., the clinician who actually performs the operation) when the operation is performed. One or more advantages can be brought about by implementing such remote assistance. As an example, remote assistance can improve the willingness and / or confidence of a specific clinician in a specific diagnosis, treatment strategy, technology, instrument or tool selection, etc. Therefore, consultation with a remote clinician via a communication session may result in more cases being converted from the third possible outcome (necessarily delaying treatment) to the second possible outcome (i.e., the operating clinician handles intervention during the same stage). Enabling remote assistance can provide the benefits described above without the burden of obtaining on-site assistance from another clinician. For example, a particular clinician may be located in a rural healthcare facility and may be the only clinician on-site with cath lab experience. The techniques of the present disclosure enable such a clinician to obtain real-time intraoperative assistance without requiring another clinician to travel to the rural facility. Although primarily described with respect to medical procedures including percutaneous coronary intervention (PCI) procedures, medical systems according to the present disclosure are applicable to other medical procedures in a catheterization laboratory. For example, a medical system according to the present disclosure can be used to perform one or more other medical procedures performed in a catheterization laboratory, including diagnostic cardiac catheterization, atrial septal atherectomy, cardiac ablation, cardiac resynchronization therapy, CardioMEMS TM HF system implantation, coronary stent implantation, coronary ultrasound, electrophysiology studies, implantable cardioverter defibrillator (ICD) placement, implantable loop recorder, intravascular ultrasound (IVUS), percutaneous transluminal angioplasty (PTCA), peripheral angioplasty, permanent pacemaker placement, rotary cutter, TAVR, three-dimensional mapping, valvuloplasty, etc. In some examples, the PCI procedure is a medical procedure performed on patients with lesions (e.g., bifurcation lesions) in the vascular system. As described herein, examples of the present disclosure relate to medical systems for treating patient conditions that are lesions. However, other patient conditions that can be treated in the catheterization room, such as structural heart disease (e.g., cardiomyopathy, congenital heart disease, heart valve disease, etc.), are also considered.

[0007] In some examples, a medical system according to the present disclosure may prevent streaming or sharing of a patient's personal health information (PHI) with a clinician who does not have permission to view the PHI. For example, the system may be configured to determine the permission status of a remote clinician, who may be located in the same hospital or network associated with the operating clinician, or may be located outside the hospital or network. In some examples, in response to determining that the permission status of the remote clinician is "external" or some other reference indicating that the remote clinician is not affiliated with the catheterization room where the intervention is being performed, the medical system may be configured to hide personal health information from the representation of the imaging data. In this way, personal health information (PHI) can be protected, and the benefits of a clinician consultation when the two clinicians view the imaging data can be achieved (e.g., without further obtaining the patient's consent to the disclosure of PHI). The systems and techniques disclosed herein may allow remote clinicians who view imaging data in real time through a communication session to provide advice or guidance. Therefore, since the patient may only need to undergo an intervention once, the risk may be reduced due to a reduction in the number of interventions, and the patient can receive necessary treatment without delay.

[0008] The present disclosure also relates to medical systems and techniques for generating and / or sharing selected video highlights or images of medical operations. According to the medical system of the present disclosure, a condensed version of imaging data (e.g., fluoroscopic imaging) sensed by one or more image sensors during a medical operation can be generated. The condensed version of the imaging data may include images corresponding to specific events during a medical operation (such as a cardiac catheterization medical operation). In some examples, the medical system of the present disclosure may be configured to receive user input to start or end a video excerpt, which may correspond to a key part of the medical operation. Additionally or alternatively, the medical system executes a computer vision model to identify a patient condition or an intraoperative event in the received imaging data. In some examples, in response to identifying a patient condition or an intraoperative event, the medical system may be configured to present an option to a clinician to provide a user input to start a video excerpt of the received imaging data. In some examples, the medical system may be configured to hide personal health information from the condensed version of the imaging data. In some examples, the medical system may be further configured to share or stream a condensed version of the imaging data with a remote clinician. Therefore, systems and techniques according to the present disclosure can allow for easy sharing of images of identified events or medical procedures before / after via a secure platform. In addition, in some examples, remote clinicians can view a condensed version of the procedure to quickly review the ongoing medical procedure.

[0009] The present disclosure also relates to medical systems and techniques for receiving imaging data including one or more identification elements from one or more image sensors and generating a de-identified version of the imaging data that does not include the one or more identification elements. In some examples, at least one of the one or more identification elements may be personal health information (PHI), which may be protected health information as defined by HIPAA or similar regulations. The medical system may be configured to hide, delete, blur text information, or otherwise make the text information illegible, such as a patient's name, date of birth, or other personal health information. In some examples, the imaging data from one or more image sensors may include PHI, and the medical system may be configured to scan the imaging data, identify text overlays, and hide, delete, blur text overlays, or otherwise make the text overlays illegible. In some examples, the medical system may be further configured to upload a de-identified version of the imaging data to a server. In some examples, the medical system may be further configured to present a clinician with the option of publishing a de-identified version of the imaging data on a social network or otherwise sharing the de-identified version of the imaging data. In some examples, the medical system may be configured to prevent or block the imaging data from being published or published to a social network before it is properly de-identified. In some examples, the social network may be a physician-only social network (e.g., Murmur). Relative to hospitals that lack secure sharing methods or rely on third-party anonymizing software, medical systems and techniques according to the present disclosure may allow for the posting and discussion of case videos, video highlights, before-and-after images, etc. in a secure manner. Medical systems and techniques according to the present disclosure may facilitate clinician discussion and education and / or enhance the reputation of operating clinicians because they are able to simply and securely share imaging data obtained from the medical procedures they perform (e.g., cardiac catheterization medical procedures).

[0010] The present disclosure also relates to medical systems and techniques for clinician education. In some examples, medical systems and techniques according to the present disclosure can allow clinicians to understand how their cases or treatment strategies differ from the strategies of another clinician (e.g., an expert) in similar cases. In some examples, a medical system according to the present disclosure can be configured to output a superposition or side-by-side representation of imaging data from a first medical operation and a second medical operation stored in a memory for display. The medical system can execute a computer vision model and / or a machine learning model to use a propensity matching to identify a second medical operation based on the similarity of one or more patient conditions of the first medical operation and the second medical operation, so as to output it together with the first medical operation for display. In some examples, the patient condition can be a lesion, and the medical system can use a propensity matching by comparing one or more lesion characteristics of the lesion associated with the first medical operation, and based on one or more lesion characteristics, identify and select individual medical operations including similar lesions (e.g., the most similar lesions) from multiple medical operations stored in the memory, to output as a second medical operation for display. In some examples, the medical system can be further configured to allow clinicians to sort and / or filter the medical operations stored in the memory in one or more ways to allow clinicians to filter the desired results. Thus, because the medical system of the present disclosure can use computer vision and / or machine learning to find and output similar medical procedures stored in memory for display to compare with the current medical procedure, the clinician can receive more relevant, targeted feedback than could otherwise be viewed. In this way, the medical system according to the present disclosure can provide desirable learning and educational benefits that can improve the skills of the clinician and better prepare them to perform the upcoming medical procedure.

[0011] The present disclosure also relates to a learning path for a clinician (e.g., an interventional cardiologist) to complete in exchange for credits. In some examples, credits can be integrated with a certification body to provide a simple procedure for reporting and receiving credits from a certification body. In some examples, a medical system can be configured to capture user information of a user interacting with the medical system to identify the user. The medical system can be configured to store data representing an excerpt of imaging data from an individual medical operation in a plurality of cardiac catheter medical operations in a memory. An excerpt of an individual medical operation can be output for display, and after the excerpt of the medical operation is output for display, the medical system can grant credits to the user who views the excerpt of the medical operation. In some examples, the medical system can be further configured to grant at least a portion of continuing medical education (CME) credits to the user. In some examples, the medical system can be configured to present to the user an option to filter through any of a plurality of acceptable medical techniques (e.g., acceptable percutaneous coronary intervention techniques). Traditionally, certain types of clinicians may lack structured courses to help them transcend a certain stage of their careers. A mechanism for setting up online courses can be provided according to a medical system disclosed herein. This mechanism can further specialize clinicians because clinicians can watch multiple medical procedures and earn credits for watching medical procedures. For example, a medical system according to the present disclosure can assist an interventional cardiologist to further specialize in complex PCI (e.g., bifurcation disease) by watching multiple medical procedures associated with one or more of the six currently recognized techniques for treating lesions.

[0012] The present disclosure also relates to monitoring and providing guidance on contrast agent usage during catheterization laboratory procedures. The amount of contrast used needs to strike a balance between: enough so that the image contains the necessary details; and not too much to avoid causing adverse side effects. In some examples, the system can track the amount of contrast agent used and provide guidance to the clinician. For example, the system can inform the clinician how the actual amount of contrast used compares to the expected / predicted amount of contrast.

[0013] 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.

[0014] In one example, a medical system includes: a memory configured to store at least one computer vision model; and a processing circuit system communicatively coupled to the memory, the processing circuit system being configured to: receive imaging data of at least a portion of a patient's vascular system generated during a cardiac catheterization procedure; and execute at least one computer vision model to determine characteristics of a lesion of the vascular system based on the received imaging data.

[0015] In another example, a method includes receiving, by a processing circuit system, imaging data of at least a portion of a patient's vascular system generated during a cardiac catheterization procedure; and executing, by the processing circuit system, at least one computer vision model to determine characteristics of a lesion in the vascular system based on the received imaging data.

[0016] In another example, a non-transitory computer-readable medium stores instructions that, when executed, cause a processing circuit system to: receive imaging data of at least a portion of a patient's vascular system generated during a cardiac catheterization procedure; and execute at least one computer vision model to determine characteristics of a lesion in the vascular system based on the received imaging data.

[0017] In another example, a medical system includes: a memory configured to store at least one computer vision model and at least one machine learning model; and a processing circuit system communicatively coupled to the memory, the processing circuit system configured to: receive diagnostic imaging data of at least a portion of a patient's vascular system generated during a cardiac diagnostic procedure; execute at least one computer vision model to determine characteristics of lesions in the vascular system based on the received diagnostic imaging data; and execute at least one machine learning model to determine at least one treatment strategy based on the determined lesion characteristics, the at least one treatment strategy comprising at least one treatment technique and at least one medical device.

[0018] In another example, a method includes: receiving, by a processing circuit system, diagnostic imaging data of at least a portion of a patient's vascular system generated during a cardiac diagnostic procedure; executing, by the processing circuit system, at least one computer vision model to determine characteristics of lesions in the vascular system based on the received diagnostic imaging data; and executing, by the processing circuit system, at least one machine learning model to determine at least one treatment strategy based on the determined lesion characteristics, the at least one treatment strategy comprising at least one treatment technique and at least one medical device.

[0019] In another example, a non-transitory computer-readable storage medium stores instructions that, when executed, cause a processing circuit system to: receive diagnostic imaging data of at least a portion of a patient's vascular system generated during a cardiac diagnostic procedure; execute at least one computer vision model to determine characteristics of lesions in the vascular system based on the received diagnostic imaging data; and execute at least one machine learning model to determine at least one treatment strategy based on the determined lesion characteristics, the at least one treatment strategy comprising at least one treatment technique and at least one medical device.

[0020] In another example, a medical system includes: a memory; one or more image sensors; and a processing circuit system communicatively coupled to the memory, the processing circuit system being configured to: receive a representation of a user input from a first clinician performing a cardiac catheterization laboratory procedure requesting a consultation with a second clinician remote from the first clinician; establish a communication session between a first computing device associated with the first clinician and a second computing device associated with the second clinician in response to receiving the representation of the user input requesting a consultation; and stream a data representation of the cardiac catheterization laboratory procedure captured by the one or more image sensors via the communication session.

[0021] In another example, a non-transitory computer-readable storage medium stores instructions that, when executed, cause a processing circuit system to: receive, from a first clinician performing a cardiac catheterization laboratory procedure, a representation of a user input requesting a consultation with a second clinician remote from the first clinician; in response to receiving the representation of the user input requesting a consultation, establish a communication session between a computing device associated with the first clinician and a computing device associated with the second clinician; and stream, via the communication session, a data representation of the cardiac catheterization laboratory procedure captured by one or more image sensors.

[0022] In another example, a method includes receiving, by a processing circuit system, a representation of user input from a first clinician performing a cardiac catheterization laboratory procedure requesting a consultation with a second clinician remote from the first clinician; in response to receiving the representation of the user input requesting the consultation, establishing a communication session between a computing device associated with the first clinician and a computing device associated with the second clinician; and streaming, via the communication session, a representation of data of the cardiac catheterization laboratory procedure captured by one or more image sensors.

[0023] In another example, a medical system includes: a memory; and a processing circuit system communicatively coupled to the memory, the processing circuit system being configured to: receive imaging data, the imaging data being sensed by one or more image sensors during a cardiac catheter medical procedure; and generate a condensed version of the imaging data based on the imaging data, the condensed version of the imaging data including images corresponding to specific events of the cardiac catheter medical procedure.

[0024] In another example, a method includes receiving, by a processing circuit system, imaging data sensed by one or more image sensors during a cardiac catheterization medical procedure and generating, based on the imaging data, a condensed version of the imaging data, the condensed version of the imaging data including images corresponding to specific events of the cardiac catheterization medical procedure.

[0025] In another example, a medical system includes: a memory; and a processing circuit system communicatively coupled to the memory, the processing circuit system being configured to: receive imaging data, the imaging data being sensed by one or more image sensors during a cardiac catheter medical procedure, the received imaging data including one or more identification elements; and generate a de-identified version of the imaging data based on the imaging data, the de-identified version of the imaging data not including at least one of the one or more identification elements.

[0026] In another example, a method includes receiving, by a processing circuit system, imaging data sensed by one or more image sensors during a cardiac catheterization medical procedure, the received imaging data including one or more identification elements; and generating, by the processing circuit system, a de-identified version of the imaging data based on the imaging data, the de-identified version of the imaging data not including at least one of the one or more identification elements.

[0027] In another example, a medical system includes: a memory; and a processing circuit system communicatively coupled to the memory, the processing circuit system being configured to: receive imaging data from one or more image sensors during a first cardiac catheter medical procedure; execute at least one computer vision model to identify a second cardiac catheter medical procedure among a plurality of cardiac catheter medical procedures stored in the memory; and output a representation of the imaging data from the first cardiac catheter medical procedure and a representation of the imaging data from the second cardiac catheter medical procedure for display.

[0028] In another example, a method includes: receiving, by a processing circuit system, imaging data from one or more image sensors during a first cardiac catheterization medical procedure; executing, by the processing circuit system, at least one computer vision model to identify a second cardiac catheterization medical procedure among a plurality of cardiac catheterization medical procedures stored in a memory; and outputting, by the processing circuit system, a representation of the imaging data from the first cardiac catheterization medical procedure and a representation of the imaging data from the second cardiac catheterization medical procedure for display via a display.

[0029] In another example, a medical system includes: a memory; and a processing circuit system communicatively coupled to the memory, the processing circuit system being configured to: capture user information of a user interacting with the medical system to identify the user; store data representing imaging data from multiple cardiac catheter medical procedures in the memory; output data representing an individual cardiac catheter medical procedure of the multiple cardiac catheter medical procedures stored in the memory for display; and after outputting the data representing the individual cardiac catheter medical procedure for display, give credit to a user who views an excerpt of the individual cardiac catheter medical procedure.

[0030] In another example, user information of a user interacting with a medical system is captured by a processing circuit system to identify the user; data representing imaging data from multiple cardiac catheter medical procedures is stored by the processing circuit system in a memory; data representing an individual cardiac catheter medical procedure of the multiple cardiac catheter medical procedures stored in the memory is output by the processing circuit system for display via a display; and credits are awarded to the user for viewing the individual cardiac catheter medical procedure after outputting the data representing the individual cardiac catheter medical procedure for display.

[0031] In another example, a medical system includes: a memory; and a processing circuit system communicatively coupled to the memory, the processing circuit system being configured to: determine a cumulative amount of contrast media used during a cardiac catheterization laboratory procedure; and output a graphical representation of the cumulative amount of contrast media used during the cardiac catheterization laboratory procedure for display.

[0032] In another example, a method includes determining a cumulative amount of contrast media used during a cardiac catheterization laboratory procedure; and outputting for display a graphical representation of the cumulative amount of contrast media used during the cardiac catheterization laboratory procedure.

[0033] In another example, a computer readable storage medium stores instructions that cause one or more processors to: determine a cumulative amount of contrast media used during a cardiac catheterization laboratory procedure; and output for display a graphical representation of the cumulative amount of contrast media used during the cardiac catheterization laboratory procedure.

[0034] 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.

[0035] 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

[0036] Figure 1 is a schematic perspective view of an example of a system for guiding a medical device through a region of a patient according to one or more aspects of the present disclosure.

[0037] Figure 2 is a block diagram of one example of a computing device according to one or more aspects of the present disclosure.

[0038] Figure 3 is a block diagram of an example of an example energy generating device according to one or more aspects of the present disclosure.

[0039] Figure 4 is a conceptual diagram showing superimposing a representation of ablated tissue on imaging data in accordance with one or more aspects of the present disclosure.

[0040] Figure 5 is a flow chart illustrating an example technique for determining lesion characteristics according to one or more aspects of the present disclosure.

[0041] Figure 6 is a schematic perspective view of an example of a system for determining a treatment strategy according to one or more aspects of the present disclosure.

[0042] Figure 7 is a schematic diagram of one example of a computing device according to one or more aspects of the present disclosure.

[0043] Figure 8 is a flow chart illustrating an example technique for determining a treatment strategy in accordance with one or more aspects of the present disclosure.

[0044] Fig. 9 is a schematic perspective view of one example of a system for establishing a communication system between an operating clinician and a remote clinician and streaming imaging data representing a medical procedure in accordance with one or more aspects of the present disclosure.

[0045] Fig.10 is a flow chart illustrating an example technique for streaming data representations to a remote clinician in accordance with one or more aspects of the present disclosure.

[0046] Fig.11 is a time diagram illustrating an example condensed version of imaging data sensed by one or more image sensors during a cardiac catheterization medical procedure in accordance with one or more aspects of the present disclosure.

[0047] Fig.12 is a flow chart illustrating an example technique for generating a condensed version of imaging data sensed by one or more image sensors in accordance with one or more aspects of the present disclosure.

[0048] Fig.13A are example conceptual screenshots illustrating example imaging data representations including identification elements according to one or more aspects of the present disclosure.

[0049] Fig. 13B It is shown that it does not include Fig.13A An example screenshot of example imaging data representation of at least one identified element in the.

[0050] Fig.14 is a flow chart illustrating an example technique for generating a de-identified version of imaging data sensed by one or more image sensors during a medical procedure in accordance with one or more aspects of the present disclosure.

[0051] Fig.15 is a screenshot illustrating an example user interface for using an example medical system of the present disclosure for educational purposes in accordance with one or more aspects of the present disclosure.

[0052] Fig.16 is a flow chart illustrating an example technique for using an example medical system of the present disclosure for educational purposes according to one or more aspects of the present disclosure.

[0053] Fig.17 is a flow chart illustrating an example technique for using an example medical system of the present disclosure for educational purposes according to one or more aspects of the present disclosure.

[0054] Fig.18 is a schematic perspective view of an example medical system configured to provide contrast media usage data according to one or more aspects of the present disclosure.

[0055] Fig.19 is a conceptual diagram illustrating an example graphical user interface (GUI) including contrast media usage data according to one or more aspects of the present disclosure.

[0056] Fig. 20 is a flow chart illustrating an example technique for providing contrast media usage data according to one or more aspects of the present disclosure.

[0057] Fig.21 is a conceptual diagram illustrating an example machine learning model according to one or more aspects of the present disclosure.

[0058] Fig. 22 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

[0059] The imaging system can be used to assist clinicians in performing medical procedures, such as diagnostic medical procedures, therapeutic medical procedures (such as percutaneous coronary intervention (PCI) procedures and RDN procedures), structural heart procedures, etc., or any combination thereof. For example, the imaging system 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. The imaging system can also be used when performing ablation procedures, angioplasty procedures, or other therapeutic medical procedures intended to treat lesions in the patient's vasculature (including the heart). 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 cardiovascular purposes. The imaging system can generate images and / or video data via sensors. The video data can be displayed and / or recorded during the medical procedure for later use. The video data can include a representation of a portion of the patient's vasculature or heart, including one or more lesions that may limit blood flow through this portion of the patient's vasculature or heart, the geometry of such lesions and the location in the blood vessel or heart, and / or any medical device that may be located within the field of view of one or more sensors of the imaging system. In some examples, contrast fluid may be injected into the patient's vasculature and the imaging data may include fluoroscopic imaging.

[0060] 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 lab session may include 1) only a diagnostic medical procedure, such as when a lesion requiring treatment is not identified, or treatment is too difficult for a given clinician, or the hospital where the catheterization lab is located does not have the equipment required to treat the lesion; 2) only a therapeutic medical procedure, such as when a lesion has been previously diagnosed; or 3) a diagnostic medical procedure is performed first, followed by a therapeutic medical procedure. An example of a medical procedure that may be performed in a catheterization lab is a cardiac catheterization procedure (which may be a diagnostic medical procedure or a therapeutic medical procedure).

[0061] In some examples, data representations from (multiple) sensors collected during a medical procedure can be shared or streamed with a remote clinician (i.e., outside the catheterization room where the medical procedure is performed). The remote clinician can provide consultations or recommendations during the medical procedure, and the medical system can allow real-time input from the remote clinician, potentially improving medical outcomes. Additionally or alternatively, imaging data from one or more sensors can be stored in a memory or uploaded to a network for training or educational purposes. A medical system according to the present disclosure may include a processing circuit system configured to use computer vision and / or machine learning to identify and select a medical procedure from a plurality of medical procedures stored in a memory using propensity matching for output to be displayed on a user interface. Thus, clinicians can see how medical procedures treating similar patient conditions (e.g., lesions of similar size, location, geometry, etc.) were handled in previous medical procedures.

[0062] Figure 11 is a schematic stereogram of an example of an example of a system for guiding a medical device through a certain area of ​​a patient according to one or more aspects of the present disclosure. System 1000 includes a guide workstation 1052, a display device 1010, a table 1020, a medical device 1030, an imager 1040, and a computing device 1050. System 1000 may be an example of a system for use in a catheterization laboratory (catheterization room). The guide workstation 1052 may include, for example, an off-the-shelf device, such as a notebook computer, a desktop computer, a tablet computer, a smart phone, or other similar device. In some examples, a controller of such a device may generate controller data. Such a device may include an atherectomy device, an energy generating device, or other device that can generate data. In some examples, the guide workstation may be a device for a specific purpose. The guide workstation 1052 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 1000. In some examples, the guide workstation 1052 may include an electrosurgical generator, such as an energy generating device 1054. For example, the energy generation device 1054 may include an RDN generator configured to generate radiofrequency energy for delivery by an ablation catheter (e.g., medical device 1030) to ablate tissue in a renal artery to treat hypertension. Although shown as part of the guidance workstation 1052, in some examples, the energy generation device 1054 may be a separate device. The computing device 1050 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. In some examples, the guidance workstation 1052 may perform various control functions with respect to the imager 1040 and may interact extensively with the computing device 1050. The guidance workstation 1052 may be communicatively coupled to the computing device 1050, enabling the guidance workstation 1052 to control the operation of the imager 1040 and receive the output of the imager 1040. In some examples, the computing device 1050 may control various operations of the imager 1040.

[0063] The display device 1010 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 1030. Further, the display device 1010 may be configured to output information about the medical device 1030, such as the model, type, size, etc. The table 1020 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 1021. The EM field generator 1021 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 position of one or more medical devices within a patient's body. The EM field generator 1021 may include various components, such as a specially designed mat placed under or integrated into an operating table or bed.

[0064] Medical devices can also be visualized through the use of imaging such as ultrasound imaging. Figure 1 In an example of, an imager 1040 (such as an intravascular ultrasound (IVUS) device, an ultrasound wand, or other imaging device) can be used to image a patient's body during a medical procedure to visualize the location of medical devices (such as surgical instruments, device delivery or placement devices, and implants) in the patient's body. The imager 1040 can be one or more sensors 1070. For example, the imager 1040 can include an interventional ultrasound probe having an ultrasound transducer array. In some examples, the imager 1040 can include an ultrasound transducer array including a plurality of transducer elements or other types of imaging sensors. These transducer elements can be configured to sense ultrasound energy reflected from the patient's anatomical structure and / or the medical device 1030. The imager 1040 can optionally have an EM tracking sensor embedded in or attached to the interventional ultrasound probe, for example, as a clip-on sensor or a sticker sensor. Although primarily described as an IVUS device, the imager 1040 can be any type of imaging device including one or more sensors, such as a CT device, an MRI device, a fluoroscopic device, a PET device, an angiography device, and the like.

[0065] Imager 1040 can image a region of interest within the patient's body. The particular region of interest can depend on the anatomy, the diagnostic medical procedure, and / or the intended treatment. For example, when performing PCI, a portion of the vasculature may be the region of interest, or when performing a cardiac medical procedure, a portion of the heart may be the region of interest.

[0066] As further described herein, the imager 1040 can be positioned relative to the medical device 130 so that the medical device is at an angle to the ultrasound 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. Further, if provided, the EM tracking system can also track the position of the imager 1040. In one or more examples, the imager 1040 can be placed inside a patient. The EM tracking system can then track the position of the imager 1040 and the medical device 1030 inside the patient. In some examples, the functions of the computing device 150 can be performed by the guidance workstation 1052, and the computing device 1050 may not be present.

[0067] The position of the medical device 1030 within the patient's body can be tracked during a therapeutic medical procedure. An exemplary technique for tracking the position of the medical device 1030 includes using an imager 1040 to track the position of the medical device 1030. Another exemplary technique for tracking the position of the medical device 1030 includes using an EM tracking system that tracks the position of the medical device 1030 by tracking a sensor attached to or contained in the medical device 1030. 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 1030 can be used with the system 1000. Examples of medical devices or equipment include stents, catheters, angioplasty devices, ablation devices, etc.

[0068] The computing device 1050 can be communicatively coupled to the imager 1040, the workstation 1052, the display device 1010, and / or the server 1060, for example, by wired, optical, or wireless communications. The server 1060 can be a hospital server (which may or may not be located in a catheterization laboratory (cath room) of the hospital), a cloud-based server, etc. The server 1060 can be configured to store patient video data, electronic healthcare or medical records, etc. In some examples, the computing device 1050 can be an example of a workstation 1052.

[0069] The computing device 1050 can be configured to receive imaging data from the imager 1040 (e.g., generated by the sensor 1070). The imaging data can include image and / or video data. The system 1000 can track the movement of a medical device 1030 (e.g., a guide catheter inserted into a target vessel in a patient's body). Such tracked movement can be saved by the computing device 1050, the guidance workstation 1052, and / or the server 1060 and used to evaluate operator technique (e.g., successful use of the medical device), for training purposes, as a variable for research, as an input to a machine learning model to train a machine learning model, etc. For example, the system 1000 can track the movement of an electrohydraulic intravascular lithotripsy device through a calcified lesion. The computing device 1050, the guidance workstation 1052, and / or the server 1060 can use the tracked movement to evaluate the penetration capability (ability to penetrate the lesion) of a particular medical device in a particular type of lesion. For example, computing device 1050, guidance station 1052, and / or server 1060 may execute a computer vision model to determine the type of lesion being treated and determine whether a medical device successfully passed through a particular lesion based on the tracked motion. In some examples, computing device 1050, guidance station 1052, and / or server 1060 may build a database of lesion types and medical devices so that computing device 1050, guidance station 1052, and / or server 1060 may determine the likelihood that a particular medical device successfully passed through or treated a particular type of lesion. In some examples, computing device 1050, guidance station 1052, and / or server 1060 may train a machine learning model based on the motion of the medical device, the type of lesion, and the type of medical device used.

[0070] In some examples, during a therapeutic medical procedure, computing device 1050, guidance workstation 1052, and / or server 1060 executes a machine learning model to propose one or more treatment strategies, which may include one or more treatment techniques and one or more medical devices. For example, computing device 1050, guidance workstation 1052, and / or server 1060 executing a machine learning model may output for display a treatment strategy that is most likely to be successful for a particular type of lesion.

[0071] In some examples, computing device 1050 , guidance workstation 1052 , and / or server 1060 may save the motion information, lesion type, and medical device type for future review by a clinician to facilitate the clinician's evaluation of a specific treatment strategy for a specific lesion type.

[0072] This technique may be useful because there are several different lesion types, such as bifurcation lesions, calcified lesions, chronic total occlusions (CTOs), in-stent restenosis (ISRs), left main disease, etc. There are also many different lesion subtypes (e.g., types within types). For example, the Medina classification system includes seven different subtypes of bifurcation lesions. In addition, there are multiple treatment techniques for different types of lesions. For example, there are at least six techniques for treating bifurcation lesions, which can include the use of different medical devices and / or the use of (multiple) medical devices in different sequences. Therefore, the number of different permutations and combinations of treatment strategies for a given lesion can be very large.

[0073] The computing device 1050, the guidance workstation 1052, and / or the server 1060 may use the imaging data to execute a computer vision model to determine the characteristics of the lesion. For example, the computing device 1050, the guidance workstation 1052, and / or the server 1060 may determine the type of lesion, the lesion subtype, or otherwise classify the lesion (e.g., provide a score or other identifier), etc. based on the determined lesion characteristics. The characteristics of the lesion may include, for example, the type of lesion (e.g., bifurcation lesions), the diameter of the lesion, the degree of stenosis, the degree of calcification, the vessel take-off angle, etc. For example, the computing device 1050, the guidance workstation 1052, and / or the server 1060 may use the classification of the lesions to execute a machine learning model to determine one or more treatment strategies that are most likely to succeed. The classification of lesions may be to classify lesions with greater similarity as being the same or close to each other, which may be referred to as "propensity matching" in some examples. In this manner, if a lesion has particular characteristics, the computing device 1050, guidance workstation 1052, and / or server 1060 can determine one or more treatment strategies that are most likely to successfully treat a lesion having those (or close to those) characteristics, and output the one or more treatment strategies for display to a clinician. By providing a clinician with one or more treatment strategies that are most likely to succeed (e.g., during a therapeutic medical procedure), the techniques of the present disclosure can enable specific treatment or prevention of a disease or medical condition. These techniques can improve patient outcomes, reduce the need for repeat therapeutic medical procedures, expedite therapeutic medical procedures, reduce patient exposure to radiocontrast agents, and conserve medical resources.

[0074] In some examples, the classification of lesions can be used as a building block to support clinical research, case planning, and / or case analysis (e.g., following a therapeutic medical procedure) for clinicians who want to understand why some techniques are effective in some cases but not in others. The classification of lesions can also be used to highlight key factors that distinguish treatment strategies for two different lesion classifications to assist clinicians in such analysis. In some examples, the classification of lesions can be used in clinical trials. For example, many people with lesions with the same (or very similar) characteristics can be treated with different treatment strategies and the results can be compared.

[0075] In some examples, computing device 1050, guidance workstation 1052, and / or server 1060 may execute a computer vision model to determine the medical device(s) used. Alternatively or additionally, a clinician may input the type of medical device(s) used to computing device 1050, guidance workstation 1052, and / or server 1060 via a user interface. Computing device 1050, guidance workstation 1052, and / or server 1060 may execute a computer vision model (e.g., via imaging data from a therapeutic medical procedure after treatment of the lesion) to determine the degree of success of the treatment of the lesion. In some examples, imaging data after the therapeutic medical procedure may be collected, and computing device 1050, guidance workstation 1052, and / or server 1060 executing a computer vision model may determine the degree of success of the treatment of the lesion. For example, the degree of success of the treatment of the lesion may include the degree of patency of the area after treatment.

[0076] In some examples, computing device 1050, guidance workstation 1052, and / or server 1060 may execute machine learning models to evaluate the performance of medical devices and provide guidance regarding specifications for new medical devices to assist manufacturers in improving the design of such medical devices to achieve a higher degree of success in treating lesions.

[0077] The energy generating device 1054 (which may be an RDN generator) may be configured to generate energy for an ablation catheter (e.g., medical device 1030) that may ablate lesions within a patient's vasculature or heart. The energy generating device 1054 may also generate information, such as the amount of energy used during ablation, the length of time of ablation, error codes, and the like. In some examples, the energy generating device 1054 may be communicatively coupled to the computing device 1050 and / or the guidance workstation 1052, and the computing device 1050 and / or the guidance workstation 1052 may integrate the generator data with the imaging data. For example, the system 1000 may introduce a timestamp into the generator data and the imaging data. The timestamp may be used to register the generator data with the imaging data. For example, the computing device 1050 and / or the guidance workstation 1052 may use the received generator data to determine the location and size of the ablated tissue. In some examples, the computing device 1050 and / or the guidance workstation may use a machine learning model to determine the location and size of the ablated tissue. In some examples, the machine learning model can reside on the server 1060 instead of the computing device 1050 or the guidance workstation 1052, and the computing device 1050 and / or the guidance workstation 1052 can communicate with the server 1060 to determine the location and size of the ablated tissue using the machine learning model. The computing device 1050 and / or the guidance workstation 1052 can output the imaging data together with the representation of the ablated tissue for display. The representation of the ablated tissue can be superimposed on the imaging data. In some examples, the computing device 1050 and / or the guidance workstation 1052 can generate a representation of the ablated tissue using different colors, different shades, different pattern fills, etc., so that the clinician can easily identify the ablated tissue on a display (such as the display device 1010). In this way, the clinician can evaluate the possible success of the ablation period and determine whether further ablation of a particular lesion is required or whether the clinician can move on from the lesion.

[0078] If the generator data includes an error code, the computing device 1050 and / or the guidance workstation 1052 can output that an error has occurred and the tissue has not been ablated as expected for display. In this case, the computing device 1050, the guidance workstation 1052, and / or the server 1060 can execute a computer vision model to determine which tissues, if any, are actually ablated. The computing device 1050 and / or the guidance workstation 1052 can then output imaging data with a representation of the tissue that is actually ablated for display. In some examples, when the generator data includes an error code, the computing device 1050 and / or the guidance workstation 1052 can control the energy generation device 1054 to shut down the energy generation device 1054 to ensure the safety of the patient until the error code can be checked by a clinician or other person. The computing device 1050 and / or the guidance workstation 1052 can also output a path through the patient's vascular system for display to guide the clinician to turn the ablation catheter for the next round (multiple) of ablations. Such a pathway may be represented using a different color, a different shade, or a different cross-hatching so that the clinician can easily see the pathway.

[0079] In some examples, the computing device 1050, the guidance workstation 1052, and / or the server 1060 can store the imaging data with the ablation representation for future review and / or training of the machine learning model. For example, the stored imaging data with the ablation representation can be used to study the patient outcome in more detail and / or for technology and / or medical device evaluation.

[0080] In some examples, the system 1000 may include an automatic contrast medium delivery device 1090. In such examples, the system 1000 may monitor the time the patient receives contrast medium and / or the amount of contrast provided to the patient by the automatic contrast medium delivery device. The computing device 1050, the guidance workstation 1052, and / or the automatic contrast medium delivery device may control the automatic contrast medium delivery device 1090 to stop delivering contrast medium when at least one of the time the patient receives contrast medium or the amount of contrast provided to the patient reaches a threshold.

[0081] Figure 2 is a block diagram of an example of a computing device according to one or more aspects of the present disclosure. The computing device 2000 may be Figure 1 Examples of computing devices 1050, boot workstations 1052, and / or servers 1060, and may include workstations, desktop computers, laptop computers, servers, smart phones, tablet computers, dedicated computing devices, or any other computing devices capable of executing the techniques of the present disclosure.

[0082] In some examples, computing device 2000 may be configured to perform processing, control, and other functions associated with guidance workstation 1052, imager 1040, and an optional EM tracking system. Figure 2 As shown, computing device 2000 represents multiple instances of computing devices, each of which may be associated with one or more of guide workstation 1052, imager 1040, or EM tracking system. Computing device 2000 may include, for example, memory 2002, processing circuit system 2004, display 2006, network interface 2008, (multiple) input device 2010, or (multiple) output device 2012, each of which may represent any one of multiple instances of such devices within a computing system for ease of description.

[0083] Although the processing circuit system 2004 appears Figure 2 1050, but in some examples, features attributed to processing circuit system 2004 may be performed by processing circuit system of any of computing device 1050, guidance workstation 1052, imager 1040, server 1060, or EM tracking system, or a combination thereof. In some examples, one or more processors associated with processing circuit system 2004 in computing device 2000 may be distributed and shared among any combination of computing device 1050, guidance workstation 1052, imager 1040, server 1060, and EM tracking system. In addition, in some examples, processing operations or other operations performed by processing circuit system 2004 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 2000. Computing device 2000 may be used to perform any of the techniques described in this disclosure and may form all or part of a device or system configured to perform such techniques, alone or in combination with other components (such as computing device 1050, guidance workstation 1052, imager 1040, server 1060, EM tracking system, or components of a system including any or all of such devices).

[0084] The memory 2002 of the computing device 2000 includes any non-transitory computer-readable storage medium for storing data or software that can be executed by the processing circuit system 2004 and control the operation of the computing device 1050, the boot workstation 1052, the imager 1040, the server 1060, or the EM tracking system (as applicable). In one or more examples, the memory 2002 may include one or more solid-state storage devices, such as flash memory chips. In one or more examples, the memory 2002 may include one or more mass storage devices connected to the processing circuit system 2004 through a mass storage controller (not shown) and a communication bus (not shown).

[0085] 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 the processing circuit system 2004. 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 the computing device 2000. 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.

[0086] Memory 2002 may store machine learning model(s) 2022 and / or computer vision model(s) 2024. In some examples, machine learning model(s) 2022 and computer vision model(s) 2024 may be the same. In other examples, machine learning model(s) 2022 and computer vision model(s) 2024 may be different.

[0087] The memory 2002 may store imaging data 2014 and controller data 2020. The imaging data 2014 may be acquired by the imager 1040 ( Figure 1) captured during a medical procedure on a patient. Processing circuit system 2004 may receive imaging data 2014 from imager 1040 and store imaging data 2014 in memory 2002. Controller data 2020 may be generated by energy generation device 1054, and processing circuit system 2004 may receive controller data 2020 from energy generation device 1054. Processing circuit system 2004 may determine lesion length and / or location based on controller data 2020 and generate a representation of ablated tissue. Processing circuit system 2004 may register controller data 2020 with imaging data 2014 using a timestamp (e.g., which may be placed in the data by energy generation device 1054, imager 1040, computing device 1050, or guidance workstation 1052). Processing circuit system 2004 may output imaging data 2014 and a representation of ablated tissue superimposed on imaging data 2014 for display, e.g., to display 2006 or display device 1010. For example, processing circuitry 2004 may execute computer vision model(s) 2024 to identify anatomical structures, such as vessels, bifurcations, ostia, etc., and may use such identified anatomical structures to align imaging data and representations of ablated tissue by associating them in the xy plane.

[0088] Memory 2002 may also store motion data 2028, medical device data 2026, and (multiple) lesion classifications 2030. Motion data 2028 may include tracked motion of medical device 1030 through a patient during a therapeutic medical procedure. Motion data 2028 may be generated by EM field generator 1021, by processing circuit system 2004 executing (multiple) computer vision models 2024 to track motion of medical device 1030 during a therapeutic medical procedure using imaging data from imager 1040, by imager 1040, or by another technique. Motion data 2028 may indicate the (multiple) treatment technique used, the performance of the clinician using the (multiple) treatment technique, the degree of success of medical device 1030 used with the (multiple) technique (e.g., the ability of the medical device to pass through a particular lesion type or classification). Medical device data 2026 may be generated by processing circuit system 2004 executing (multiple) computer vision models 2024. The computer vision model(s) may be trained to identify medical devices based on the imaging data 2014. Alternatively or additionally, the medical device data may be input into the computing device 2000 by a clinician via the input device(s) 2010 or the user interface 2018. The medical device data 2026 may include the brand and model of each medical device used during the therapeutic medical procedure. The medical device data 2026 may also include other identifying information or information that may be specific to the medical device, such as a barcode, year of manufacture, number of uses, etc.

[0089] The memory 2002 may also store a treatment strategy 2032. The processing circuit system 2004 executing the (multiple) machine learning model 2022 may determine a treatment strategy to be presented to a clinician, for example, during a therapeutic medical procedure. The treatment strategy 2032 may include one or more treatment techniques and one or more medical devices for use in a therapeutic medical procedure. In general, the treatment strategy 2032 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 blood flow reserve fraction (FFR) or other blood flow reserve measurement, image-based FFR or other blood flow reserve measurement, OCT, IVUS, etc. In some examples, the treatment strategy 2032 may also include the location of one or more medical devices during the therapeutic medical procedure and / or the order in which one or more medical devices are used. The treatment strategy 2032 may include a treatment strategy that is more likely to succeed based on past therapeutic medical procedures.

[0090] For example, data collected from past therapeutic medical procedures (such as imaging data, tracked motion of medical instruments, generator data, lesion classification, etc.) can be used to train the machine learning model(s) 2022. Thus, the machine learning model(s) 2022 can be trained based on actual treatments and actual outcomes of past therapeutic medical procedures, and treatment strategies can be included in the treatment strategies 2032 based on treatment strategies that are more likely to produce successful outcomes.

[0091] For example, a k-means clustering model can be used, which has multiple clusters: each cluster corresponds to each specific treatment technique performed using one or more specific medical devices. Each identified lesion can be associated with a vector including variables for, for example, the type of coronary artery problem, the severity of the coronary artery problem, the complexity of the coronary artery problem, the location of the coronary artery problem, the classification of the lesion, the anatomical structure of the coronary artery problem area, other anatomical structures, the patient's comorbidities, cholesterol levels, blood pressure, blood oxygen, age, physical exercise level, etc. The position of the vector in a given cluster can indicate a specific treatment performed using one or more specific medical devices. For example, if the vector belongs to the cluster of forward subintimal reentry into the true lumen (ADR) performed using a specific medical device, the (multiple) machine learning models 2022 can include ADR as a treatment technique in the treatment strategy 2032, and can include the specific medical device in the treatment strategy 2032.

[0092] Alternatively, the k-means clustering algorithm may have multiple clusters, each corresponding to a lesion classification. Each treatment strategy may be associated with a vector including variables for, for example, the type of coronary problem, the severity of the coronary problem, the complexity of the coronary problem, the location of the coronary problem, the anatomical structure of the coronary problem area, other anatomical structures, the patient's comorbidities, cholesterol level, blood pressure, blood oxygen, age, physical exercise level, etc.

[0093] 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.

[0094] The lesion classification(s) 2030 may be determined by the processing circuit system 2004 executing the computer vision model(s). For example, the computer vision model(s) 2024 may be trained to recognize characteristics of lesions and classify lesions based on their characteristics, wherein lesions having the same characteristics are classified into the same class. For example, the computer vision model(s) 2024 may include a convolutional neural network (CNN) that may extract characteristics or features of the lesions to form a vector based on the extracted characteristics. Such vectors may be used to classify lesions based on other lesions for which the computer vision model(s) 2024 were trained. Although the use of a CNN is described, other computer vision models may also be used.

[0095] Processing circuit system 2004 may execute user interface 2018 to display 2006 (and / or Figure 1 The memory 2002 may also store (multiple) machine learning models 2022, (multiple) computer vision modules 2024, and the user interface 2018.

[0096] The processing circuit system 2004 can be implemented by one or more processors, which can include any number of fixed-function circuits, programmable circuits, or combinations thereof. In various examples, the control of any function by the processing circuit system 2004 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 the 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 enables 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 in the unit can be different circuit blocks (fixed function or programmable), and in some examples, one or more units can be integrated circuits.

[0097] 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 2004 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.

[0098] Display 2006 may be touch-sensitive or voice-activated, enabling display 2006 to function as both an input and output device. Alternatively, a keyboard (not shown), a mouse (not shown), or (multiple) other data input devices (e.g., (multiple) input device 2010) may be utilized.

[0099] The network interface 2008 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. In some examples, the network interface 2008 may include one or more application programming interfaces (APIs) for facilitating communication with other devices. For example, the computing device 2000 may receive imaging data 2014 from the imager 1040 via the network interface 2008 during a therapeutic medical procedure. The computing device 2000 may also receive controller data 2020 from the energy generating device 1054 via the network interface 2008. In some examples, the computing device 2000 may receive motion data 2028 from, for example, an EM field generator 1021 via the network interface 2008. The computing device 2000 may receive updates to its software (e.g., application 216) via the network interface 2008. The computing device 2000 may also display a notification on the display 2006 that a software update is available.

[0100] The input device(s) 2010 may be any device that enables a user to interact with the computing device 2000, such as a mouse, keyboard, foot pedal, touch screen, augmented reality input device(s) that receive input such as gestures or body movements, or a voice interface.

[0101] Output device(s) 2012 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.

[0102] Applications 2016 may be one or more software programs stored in memory 2002 and executed by processing circuitry 2004 of computing device 2000. Processing circuitry 2004 may execute user interface 218, which may be displayed on display 2006 and / or display device 1010 ( Figure 1 ) displays imaging data 2014, ablated tissue representations, lesion classifications 2030, and / or treatment strategies 2032. Imaging data 2014 and / or ablated tissue representations may be stored for future use, such as training and / or performance evaluation of clinicians performing therapeutic medical procedures. In some examples, processing circuitry 2004 may communicate with server 1060 ( Figure 1 ) communications to upload imaging data during or after therapeutic medical procedures 2014.

[0103] In some examples, processing circuit system 2004 can provide real-time clinical guidance to clinicians. For example, processing circuit system 2004 can use or execute (multiple) computer vision model 2024 to determine the characteristics of the lesion and / or determine the location of the lesion, and execute (multiple) machine learning model 2022 to provide a recommended treatment strategy to the clinician.

[0104] Figure 3 is a block diagram of an example of an example energy generating device according to one or more aspects of the present disclosure. Figure 3 The energy generation device 3000 may be the energy generation device 1054 ( Figure 1 ). Figure 2 As shown, the energy generating device 3000 may include a positive terminal (+) 3012 , a negative terminal (−) 3014 , an energy generator 3002 , a processing circuit system 3004 , a user interface 3006 , a storage device 3008 , and a network interface 3020 .

[0105] The positive terminal 3012 can be coupled to the energy generator 3002 and can be configured to attach to one or more conductors of an ablation catheter (not shown) so as to conduct electricity between the energy generator 3002 and the one or more conductors. The negative terminal 3014 can be coupled to the energy generator 3002 (or alternatively coupled to ground) and can be configured to attach to one or more conductors of the ablation catheter so as to conduct electricity between the one or more conductors and the energy generator 3002. The energy generator 3002 can be configured to provide radio frequency electrical pulses to one or more conductors of the ablation catheter to perform electroporation or other ablation procedures on lesions (such as vascular lesions, cardiac lesions) or other tissues in the patient's body (such as kidney tissue, airway tissue, and organs or tissues within the cardiac space or pericardial space). Although in Figure 3 In the example of FIG. 3000 , a single energy generator is shown, but the energy generating device 3000 is not limited to this. For example, the energy generating device 3000 may include multiple energy generators, each of which is capable of generating ablation signals in parallel. In some examples, the energy generating device 3000 may include different types of energy generators, such as a radio frequency energy generator (e.g., an RDN generator), a pulsed field energy generator, and / or a cryogenic energy generator.

[0106] Processing circuit system 3004 may include one or more processors, such as any one or more of the following: a microprocessor, a controller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a discrete logic circuit system, or any other processing circuit system configured to provide the functions attributed to processing circuit system 3004, which circuit systems may be embodied in firmware, hardware, software, or any combination thereof. Processing circuit system 3004 controls energy generator 3002 to generate signals according to various settings 3010 that may be stored in storage device 3008.

[0107] The storage device 3008 may be configured to store controller data 3016 within the energy generating device 3000 during operation, respectively. The controller data 3016 may be an example of the controller data 2020, and may include the amount of energy delivered during ablation, the amount of time the energy is delivered, an error code, etc. In some examples, the generator data may include a timestamp. The storage device 3008 may include a computer-readable storage medium or a computer-readable storage device. In some examples, the storage device 3008 includes one or more of a short-term memory or a long-term memory. The storage device 3008 may include, for example, a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), a magnetic disk, an optical disk, a flash memory, or an electrically programmable memory (EPROM) or an electrically erasable programmable memory (EEPROM). In some examples, the storage device 3008 is used to store data indicating instructions, such as those executed by the processing circuit system 3004, respectively.

[0108] The user interface 3006 may include buttons or a keypad, lights, a speaker / microphone for voice commands, and / or a display such as a liquid crystal (LCD), a light emitting diode (LED), or an organic light emitting diode (OLED). The user interface 3006 may be configured to receive input from a clinician, such as selecting settings from settings 3010 for use during an ablation therapy session. In some examples, the display may be configured to display information about the ablation therapy session being performed, such as patient parameters or other information that may be useful to the clinician.

[0109] Figure 4 is a conceptual diagram showing superimposing a representation of ablated tissue on imaging data in accordance with one or more aspects of the present disclosure. Figure 4 can be displayed on display 2006 and / or display device 1010 ( Figure 1 ) by User Interface 2018( Figure 2 ) is an example of information displayed. For example, processing circuit system 2004 ( Figure 2) may generate and output a representation of the ablation catheter 4002 (which, in some examples, may be included in the imaging data 2014 ( Figure 2 ) and ablated tissue 4000 for display, and processing circuit system 2004 can overlay the representation on imaging data 4010 (which can be an example of imaging data 2014). Imaging data 4010 can include tissue 4012 surrounding ablation catheter 4002. In some examples, processing circuit system 2004 can represent ablated tissue 4000 in a manner different from imaging data 4010, for example, using a different color, different shading, different pattern fill, etc., so that the clinician can view the ablated tissue 4000 on a display (such as display 2006 ( Figure 2 ) or display device 1010( Figure 1 )) Easily identify ablated tissue 4000.

[0110] Figure 5 is a flow chart illustrating an example technique for determining lesion characteristics according to one or more aspects of the present disclosure. Figure 2 The computing device 2000 is described, but Figure 5 The technology can be provided by system 1000 ( Figure 1 ) or any combination of devices of system 1000 capable of performing such techniques. Processing circuit system 2004 may receive imaging data (5000) of at least a portion of a patient's vascular system generated during a cardiac catheterization procedure. For example, processing circuit system 2004 may receive imaging data (5000) of at least a portion of a patient's vascular system from imager 1040 ( Figure 1 ) receives imaging data 2014 of at least a portion of a patient's vasculature generated during a diagnostic medical procedure or a therapeutic medical procedure. Processing circuitry 2004 may execute at least one computer vision model to determine characteristics of a lesion in the vasculature based on the received imaging data (5002). For example, processing circuitry 2004 may execute (multiple) computer vision model(s) 2024 to determine characteristics of a lesion appearing in imaging data 2014. In some examples, processing circuitry 2004 may execute at least one computer vision model to determine, for example, a degree of success of ablation of a lesion during a therapeutic medical procedure. For example, processing circuitry 2004 may execute (multiple) computer vision model(s) 2024 to examine tissue surrounding the ablation and determine the degree of success of the ablation.

[0111] In some examples, the computer vision model is trained based on multiple lesions in past imaging data of multiple patients. In some examples, processing circuit system 2004 can execute at least one computer vision learning model to determine the medical device type of the medical device used during the cardiac catheterization procedure. For example, processing circuit system 2004 can execute (multiple) computer vision model 2024 to determine medical device 1030 ( Figure 1 ) or the brand, model, and / or other information of any other medical device used during the cardiac catheterization procedure. In some examples, at least one computer vision model is trained based on post-ablation information from past imaging data of multiple patients, and processing circuit system 2004 can execute (multiple) computer vision model 2024 to determine the degree of success of lesion ablation.

[0112] In some examples, processing circuitry 2004 may track the movement of a medical device during a cardiac catheter procedure and output a representation of the movement of the medical device for display during the cardiac catheter procedure based on the tracked movement and imaging data. For example, processing circuitry 2004 may receive motion data 2028 (e.g., from EM field generator 1021 ( Figure 1 )) or by executing computer vision model 2024 on imaging data 2014 to generate motion data 2028 to track the motion of medical device 1030. Processing circuit system 2004 can output a representation of the motion of the medical device based on motion data 2028 and imaging data 2014 (e.g., see Figure 4 In some examples, processing circuit system 2004 can determine whether at least a portion of the cardiac catheterization procedure was successful based on the tracked movement.

[0113] In some examples, the processing circuit system 2004 can execute (multiple) machine learning models 2022 to guide the clinician during the cardiac catheterization procedure. For example, the processing circuit system 2004 can output to the display 2006 a representation of the path to be followed by the clinician, one or more techniques to be adopted, one or more medical devices to be used, the order of medical devices to be used, etc. In some examples, the processing circuit system 2004 outputs guidance to the clinician based on the characteristics of the lesion during the cardiac catheterization procedure. In some examples, the processing circuit system 2004 outputs guidance to the clinician based on the identity of the clinician during the cardiac catheterization procedure. In some examples, the processing circuit system 2004 predicts the ability of the medical device to pass through the lesion based at least in part on the characteristics of the lesion. For example, the processing circuit system 2004 can execute (multiple) machine learning models 2022 to predict the ability of a medical device (e.g., medical device 1030) to pass through the lesion. In some examples, the processing circuit system 2004 determines whether the medical device passes through the lesion. In some examples, at least one machine learning model is trained based on data collected from past therapeutic medical procedures, including at least one of past imaging data, past tracked motion of a medical device, past controller data, or past lesion classifications.

[0114] In some examples, processing circuit system 2004 can receive energy from a device (e.g., energy generation device 1054 ( Figure 1 )) receives controller data 2020. Processing circuitry 2004 may process controller data 2020 to generate a representation of ablated tissue. Processing circuitry 2004 may output imaging data 2014 and the representation of ablated tissue for display.

[0115] In some examples, processing circuitry 2004 applies one or more timestamps to imaging data 2014 and applies one or more timestamps to at least one of controller data 2020 or the representation of ablated tissue prior to outputting the imaging data 2014 and the representation of ablated tissue for display. As part of outputting the imaging data 2014 and the representation of ablated tissue for display, processing circuitry 2004 may register imaging data 2014 using the one or more timestamps applied to imaging data 2014 and the one or more timestamps applied to at least one of controller data 2020 or the representation of ablated tissue. Processing circuitry 2004 may overlay the representation of ablated tissue on the imaging data.

[0116] In some examples, processing circuitry 2004 may control energy generation device 1054 to stop delivering energy based on controller data 2020. In some examples, processing circuitry 2004 may control automatic contrast agent delivery device 1090 to adjust a contrast agent delivery rate to the patient based on at least one of the quality of the imaging data or in response to the patient's tolerance for contrast agents.

[0117] Figure 6 6000 is a schematic perspective view of an example of a system for determining a treatment strategy according to one or more aspects of the present disclosure. System 6000 includes a display device 6010, a table 6020, an imager 6040, and a computing device 6050. System 6000 may be an example of a system for use in a catheterization laboratory. In some examples, system 6000 may include other devices, such as Figure 1 For simplicity, Figure 6 Such equipment is not shown in the figure. In some examples, system 6000 may also include server 6060 and / or computing device 6052, which may be located in the catheterization room or elsewhere. System 6000 can be used to diagnose cardiovascular problems of patients during the diagnostic phase. During this diagnostic phase (e.g., diagnostic angiography), there are three possible results. The first possible result is that the clinician may determine that no intervention is needed. The second possible result is that the clinician may determine that emergency intervention is needed, and the clinician can handle the intervention during the same phase (e.g., without the patient leaving and coming back at another time). The third possible result is that treatment is needed, but the clinician is unwilling to treat, or the hospital where the catheterization room is located does not have the instruments required for treatment. In the case of the third possible result, there may be imaging data (e.g., angiography data) from diagnostic medical surgery, which can be used to formulate a treatment plan for the patient. For example, the system can use such imaging data to formulate a treatment plan or assist clinicians in formulating a treatment plan.

[0118] Such a system may include a computer vision model and a machine learning model. The computer vision model may be used to identify, classify, and / or score specific lesions. The machine learning model may be used to determine potential treatments that are most likely to achieve a successful outcome, and such potential treatment strategies may be presented to a clinician to develop a treatment plan for a therapeutic medical procedure. The system may be configured to run simulations on potential treatment strategies to assist the clinician in selecting one or more treatment strategies to use during a therapeutic medical procedure.

[0119] The computing device 6050 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. The computing device 6050 may perform various control functions with respect to the imager 6040. In some examples, the computing device 6050 may include a boot workstation such as Figure 1 The computing device 6050 may control the operation of the imager 6040 and receive the output of the imager 6040.

[0120] Display device 6010 may be configured to output instructions, images, and messages related to a diagnostic medical procedure.Table 6020 may be, for example, an operating table or other table suitable for use during a medical procedure, such as a diagnostic medical procedure.

[0121] exist Figure 6 In the example of , imager 6040 (such as an angiographic imager or other imaging device) can be used to image a patient's body during a diagnostic medical procedure to visualize the characteristics and location of lesions in the patient's body. Although primarily described as an angiographic imager, imager 6040 can be any type of imaging device, such as an IVUS device, a CT device, an MRI device, a fluoroscopic device, a PET device, an ultrasound device, etc.

[0122] The imager 6040 can image a region of interest within the patient's body. The specific region of interest can depend on the anatomy, diagnostic medical procedure, and / or intended treatment. For example, when performing a diagnostic medical procedure for a cardiovascular problem, a portion of the vascular system and / or the heart can be the region of interest.

[0123] The computing device 6050 may be communicatively coupled to the imager 6040, the display device 6010, the computing device 6052, and / or the server 6060, for example, by wired, optical, or wireless communications. The server 6060 may be a hospital server (which may or may not be located in a catheterization laboratory (cath lab) of the hospital), a cloud-based server, etc. The server 6060 may be configured to store patient imaging data, electronic healthcare or medical records, etc.

[0124] The computing device 6052 may include, for example, an off-the-shelf device such as a laptop, desktop computer, tablet computer, smartphone, or other similar device, or may include a device for a specific purpose. The computing device 6052 may be a hospital computing device (e.g., owned by the hospital) or may be a personal computing device of a clinician.

[0125] Any one of the computing device 6050, computing device 6052, and / or server 6060, or any combination thereof, may include at least one computer vision model and / or at least one machine learning model. For example, the computing device 6050, computing device 6052, and / or server 6060 may receive diagnostic imaging data. The computing device 6050, computing device 6052, and / or server 6060 may execute at least one computer vision model to determine the characteristics of the lesion in the received diagnostic imaging data. The computing device 6050, computing device 6052, and / or server 6060 may execute at least one machine learning model to determine at least one treatment strategy based on the determined lesion characteristics, the at least one treatment strategy including at least one treatment technique and at least one medical device. In some examples, at least one treatment strategy may also include information related to the placement of at least one medical device during a therapeutic medical procedure and / or the order of use of at least one medical device during a therapeutic medical procedure. For example, the computing device 6050, computing device 6052, and / or server 6060 may execute at least one machine learning model to determine one or more treatment strategies that have a higher probability of success than other treatment strategies. For example, at least one machine learning model can predict the probability of success of different treatment strategies based on previous therapeutic medical procedures. For example, at least one machine learning algorithm can analyze the treatment strategies for lesions with the same or similar characteristics in previous therapeutic medical procedures. For example, the machine learning model may determine that if pre-dilation is not performed, the probability of passing through the lesion using electrohydraulic intravascular lithotripsy is 40%, but the probability of passing through the lesion using a low-profile non-compliant (NC) balloon is 75%. Computing device 6050, computing device 6052 and / or server 6060 can output at least one treatment technique for display to a clinician, for example, on display device 6010 or a display of computing device 6050 or computing device 6052.

[0126] In some examples, computing device 6050, computing device 6052, and / or server 6060 can be configured to run one or more simulations of treating a lesion using any of at least one treatment strategy in response to a clinician's input. In some examples, computing device 6050, computing device 6052, and / or server 6060 can overlay the simulation(s) or the results of the simulation(s) on the actual imaging data, or on a static image showing the lesion in the imaging data, in a display.

[0127] In some examples, computing device 6050, computing device 6052, and / or server 6060 may be configured to receive user input of at least one selected treatment technique and at least one selected medical device, and computing device 6050, computing device 6052, and / or server 6060 may modify at least one treatment strategy accordingly. For example, a clinician may determine that a particular treatment strategy is the treatment strategy that the clinician intends to use after viewing at least one treatment strategy and possibly after running one or more simulations, and may delete any other suggested treatment strategies for the lesion. Additionally or alternatively, a clinician may determine that a particular treatment strategy may be a treatment strategy that the clinician may use, but one or more treatment techniques and / or one or more medical devices in the treatment strategy need to be changed. In this case, the clinician may change any one of the treatment techniques and / or medical devices in the treatment strategy via a user interface. Additionally or alternatively, clinicians may prepare their own treatment strategies, which they may add to at least one treatment strategy, or they may replace at least one treatment strategy with the treatment strategy. In some examples, computing device 6050, computing device 6052, and / or server 6060 can, in response to the clinician's input, run further simulations using the modified treatment strategy to treat the lesion. These techniques can be repeated iteratively until the clinician is satisfied with the final at least one treatment strategy. In some examples, these techniques can be used to train fellows or can be used by clinicians to plan therapeutic medical procedures.

[0128] This technique may be useful because there are several different lesion types, such as bifurcation lesions, calcified lesions, chronic total occlusions (CTOs), in-stent restenosis (ISRs), left main disease, etc. There are also many different lesion subtypes (e.g., types within types). For example, the Medina classification system includes seven different subtypes of bifurcation lesions. In addition, there are multiple treatment techniques for different types of lesions. For example, there are at least six techniques for treating bifurcation lesions, which can include the use of different medical devices and / or the use of (multiple) medical devices in different sequences. Therefore, the number of different permutations and combinations of treatment strategies for a given lesion can be very large.

[0129] The disclosed techniques can enable specific treatment or prevention of a disease or medical condition by providing clinicians with one or more treatment strategies that are most likely to succeed (e.g., for planning a therapeutic medical procedure). These techniques can improve patient outcomes, reduce the need for repeat therapeutic medical procedures, expedite therapeutic medical procedures, reduce patient exposure to radiocontrast agents, and / or conserve medical resources.

[0130] Figure 7is a schematic diagram of an example of a computing device according to one or more aspects of the present disclosure. The computing device 7000 may be Figure 6 Examples of computing device 6050, computing device 6052, and / or server 6060 are provided and may include a workstation, a desktop computer, a laptop computer, a server, a smartphone, a tablet computer, a dedicated computing device, or any other computing device capable of executing the techniques of the present disclosure.

[0131] The computing device 7000 may include, for example, memory 7002, processing circuitry 7004, a display 7006, a network interface 7008, input device(s) 7010, and / or output device(s) 7012, each of which, for ease of description, may represent any one of multiple instances of such devices within a computing system.

[0132] Although processing circuit system 7004 appears Figure 7 7000 in computing device 7000, but in some examples, features attributed to processing circuit system 7004 may be provided by system 6000 ( Figure 6 ) or any combination thereof. In some examples, one or more processors associated with processing circuit system 7004 in computing device 7000 may be distributed and shared between any combination of computing device 6050, computing device 6052, and 6060. In addition, in some examples, processing operations or other operations performed by processing circuit system 7004 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 7000. Computing device 7000 may be used to perform any of the techniques described in this disclosure and may form all or part of a device or system configured to perform such techniques, alone or in combination with other components (such as computing device 6050, computing device 6052, server 6060, or components of a system including any or all of such devices).

[0133] The memory 7002 of the computing device 7000 includes any non-transitory computer-readable storage medium for storing data or software that can be executed by the processing circuit system 7004 and control the operation of the computing device 7000. In one or more examples, the memory 7002 may include one or more solid-state storage devices, such as flash memory chips. In one or more examples, the memory 7002 may include one or more mass storage devices connected to the processing circuit system 7004 through a mass storage controller (not shown) and a communication bus (not shown).

[0134] 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 the processing circuit system 7004. 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 desired information and can be accessed by the computing device 7000. 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.

[0135] Memory 7002 may store machine learning model(s) 7022 and / or computer vision model(s) 7024. In some examples, machine learning model(s) 7022 and computer vision model(s) 7024 may be the same. In other examples, machine learning model(s) 7022 and computer vision model(s) 7024 may be different.

[0136] The memory 7002 can store imaging data 7014. The imaging data 7014 can be obtained by the imager 6040 ( Figure 6 ) captured during a diagnostic medical procedure on a patient. Processing circuit system 7004 may receive imaging data 7014 from imager 6040 and store imaging data 7014 in memory 7002.

[0137] Memory 7002 may also store (multiple) lesion classifications 7030, such as classifications of lesions present in imaging data 7014. Processing circuitry 6004 executing (multiple) computer vision models 7024 may determine a classification of a lesion, which may be stored in (multiple) lesion classifications. For example, processing circuitry 6004 may classify a lesion based on characteristics of the lesion, as described above with respect to Figure 1 to Figure 2As discussed. The memory 7002 may also store a treatment strategy 7032. The processing circuit system 7004 executing the machine learning model 7022 may determine a treatment strategy presented to a clinician, for example, to assist in planning a therapeutic medical procedure or for training purposes. The treatment strategy 7032 may include one or more treatment techniques and one or more medical devices for use in a therapeutic medical procedure. In general, the treatment strategy 7032 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 measurements, image-based FFR or other blood flow reserve measurements, OCT, IVUS, etc. In some examples, the treatment strategy 7032 may also include the location of one or more medical devices during a therapeutic medical procedure and / or the order in which one or more medical devices are used. The treatment strategy 7032 may include a treatment strategy that is more likely to succeed based on past therapeutic medical procedures.

[0138] For example, data collected from past therapeutic medical procedures (such as imaging data, tracked motion of medical instruments, generator data, lesion classification, etc.) can be used to train the machine learning model(s) 7022. Thus, the machine learning model(s) 7022 can be trained based on actual treatments and actual outcomes of past therapeutic medical procedures, and treatment strategies can be included in the treatment strategies 7032 based on treatment strategies that are more likely to produce successful outcomes.

[0139] For example, a k-means clustering model can be used, which has multiple clusters: each cluster corresponds to each specific treatment technique performed using one or more specific medical devices. Each identified lesion can be associated with a vector including variables for, for example, the type of coronary artery problem, the severity of the coronary artery problem, the complexity of the coronary artery problem, the location of the coronary artery problem, the classification of the lesion, the anatomical structure of the coronary artery problem area, other anatomical structures, the patient's comorbidities, cholesterol levels, blood pressure, blood oxygen, age, physical exercise level, etc. The position of the vector in a given cluster can indicate a specific treatment performed using one or more specific medical devices. For example, if the vector belongs to the cluster of forward subintimal reentry into the true lumen (ADR) performed using a specific medical device, the (multiple) machine learning models 7022 can include ADR as a treatment technique in the treatment strategy 7032, and can include the specific medical device in the treatment strategy 7032.

[0140] Alternatively, the k-means clustering algorithm may have multiple clusters, each corresponding to a lesion classification. Each treatment strategy may be associated with a vector including variables for, for example, the type of coronary problem, the severity of the coronary problem, the complexity of the coronary problem, the location of the coronary problem, the anatomical structure of the coronary problem area, other anatomical structures, the patient's comorbidities, cholesterol level, blood pressure, blood oxygen, age, physical exercise level, etc.

[0141] 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.

[0142] The lesion classification(s) 7030 may be determined by the processing circuit system 7004 executing the computer vision model(s). For example, the computer vision model(s) 7024 may be trained to recognize characteristics of lesions and classify lesions based on their characteristics, wherein lesions having the same (or nearly the same) characteristics are classified into the same class. For example, the computer vision model(s) 7024 may include a convolutional neural network (CNN) that may extract characteristics or features of the lesions to form a vector based on the extracted characteristics. Such vectors may be used to classify lesions based on other lesions for which the computer vision model(s) 7024 were trained. Although the use of a CNN is described, other computer vision models may also be used.

[0143] Processing circuit system 7004 may execute user interface 7018 to display 7006 (and / or Figure 6 The display device 6010 of the patient's computer 7001 may present a user interface 7018 to a clinician preparing to perform a therapeutic medical procedure or a clinician in training. In some examples, the user interface 7018 may display (e.g., on the display 7006) a treatment strategy 7032 that the processing circuitry executing the machine learning model(s) 7022 may determine has a better chance of success than other treatment strategies for a particular classification of a patient's lesion.

[0144] In some examples, the clinician may wish to run simulations for at least one treatment strategy 7032. In such a case, the clinician may provide user input via the user interface 7018 or input device(s) 7010 indicating that the processing circuitry 7004 should run such simulations for selected ones of the treatment strategies 7032. The processing circuitry 7004 may then load the simulation application(s) 7016 from memory and execute the simulation application(s) 7016 for the selected treatment strategy.

[0145] In some examples, the clinician may wish to delete certain treatment strategies from treatment strategies 7032, change certain aspects of a given treatment strategy (e.g., one or more treatment techniques, medical devices, locations of medical devices, and / or the order in which medical devices are used), or create a treatment strategy that is not in treatment strategies 7032. In such cases, the clinician may provide user input via user interface 7018 or input device(s) 7010 indicating that the clinician wants to modify treatment strategy 7032, and processing circuit system 7004 may facilitate the clinician to modify treatment strategy 7032. Memory 7002 may also store machine learning model(s) 7022, computer vision module(s) 7024, and user interface 7018.

[0146] The processing circuit system 7004 can be implemented by one or more processors, which can include any number of fixed-function circuits, programmable circuits, or combinations thereof. In various examples, the control of any function by the processing circuit system 7004 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 the 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 enables 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 in the unit can be different circuit blocks (fixed-function or programmable), and in some examples, one or more units can be integrated circuits.

[0147] 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 7004 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.

[0148] Display 7006 can be touch-sensitive or voice-activated, enabling display 7006 to act as an input and output device. Alternatively, a keyboard (not shown), a mouse (not shown), or (multiple) other data input devices (e.g., (multiple) input devices 7010) can be utilized.

[0149] The network interface 7008 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. In some examples, the network interface 7008 may include one or more application programming interfaces (APIs) to facilitate communication with other devices. For example, the computing device 7000 may receive imaging data 7014 from the imager 6040 via the network interface 7008 during or after a diagnostic medical procedure. The computing device 7000 may receive updates to its software (e.g., application 7016) via the network interface 7008. The computing device 7000 may also display a notification on the display 2006 that a software update is available.

[0150] The input device(s) 7010 may be any device that enables a user to interact with the computing device 7000, such as a mouse, keyboard, foot pedal, touch screen, augmented reality input device(s) that receive input such as gestures or body movements, or a voice interface.

[0151] Output device(s) 7012 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.

[0152] Applications 7016 may be one or more software programs stored in memory 7002 and executed by processing circuitry 7004 of computing device 7000. Processing circuitry 7004 may execute user interface 7018, which may be displayed on display 7006 and / or display device 6010 ( Figure 6 ) displays treatment strategies 7032, simulations, (multiple) lesion classifications 7030 and / or imaging data 7014.

[0153] Figure 8 is a flow chart showing an example technique for determining a treatment strategy according to one or more aspects of the present disclosure. Figure 7 The computing device 7000 is described, but Figure 7 The technology can be used by System 6000 ( Figure 6) or any combination of devices of system 6000 capable of performing such techniques. Processing circuit system 7004 may receive diagnostic imaging data (8000) of at least a portion of a patient's vasculature generated during a cardiac diagnostic medical procedure. For example, processing circuit system 7004 may receive imaging data 7014 from imager 6040, computing device 6050, server 6060, computing device 6052, or from a memory device (e.g., a USB flash drive).

[0154] Processing circuit system 7004 may execute at least one computer vision model to determine characteristics of lesions in the vasculature based on the received diagnostic imaging data (8002). For example, processing circuit system 7004 may execute (multiple) computer vision model 7024 to determine characteristics of lesions in imaging data 7014. Processing circuit system 7004 may execute at least one machine learning model to determine at least one treatment strategy based on the determined lesion characteristics, the at least one treatment strategy including at least one treatment technique and at least one medical device (8004). For example, processing circuit system 7004 may execute (multiple) machine learning model 7022 to determine treatment strategy 7032 based on (multiple) lesion classifications 7030.

[0155] In some examples, the processing circuit system 7004 is further configured to output a treatment strategy (which may be a single treatment strategy) 7032 for display. In some examples, the treatment strategy 7032 further includes an indication of a predicted degree of success of the likelihood of success using at least one treatment technique and at least one medical device. In some examples, the processing circuit system 7004 is further configured to perform a first simulation of a first medical procedure using at least one treatment strategy in response to user input. For example, the processing circuit system 7004 can load (multiple) simulation applications 7016 and execute (multiple) simulation applications 7016 to simulate the use of a treatment strategy selected by a clinician to simulate a lesion. In some examples, the simulation is based at least in part on the received diagnostic imaging data (e.g., imaging data 7014).

[0156] In some examples, the processing circuit system 7004 can receive user input of the selected at least one treatment technique. The processing circuit system 7004 can be configured to receive user input to modify the selected at least one treatment strategy, and modify the selected at least one treatment strategy (e.g., treatment strategy 7032) based on the user input to generate at least one modified treatment strategy.

[0157] In some examples, processing circuit system 7004 can perform a second simulation of a second medical procedure using at least one modified treatment strategy. In some examples, the at least one modified treatment strategy includes at least one of the selected at least one treatment technique and / or at least one medical device. In some examples, the at least one treatment strategy does not include at least one of the selected at least one treatment technique or at least one of the selected medical devices.

[0158] In some examples, machine learning model(s) 7022 are trained on imaging data from prior therapeutic medical procedures, multiple lesion types, multiple medical devices, multiple clinicians, and multiple therapeutic medical procedures.

[0159] Fig. 9 is a schematic perspective view of an example medical system 9000. The medical system 9000 may be Figure 1 Medical Systems 1000 and / or Figure 6 Example of a medical system 6000. Fig. 9 Medical Systems 9000 and Figure 6 The medical system 9000 is similar to the medical system 6000 of the present invention, except as described below, where like reference numerals represent like elements. The medical system 9000 can provide a system for establishing a communication session between an operating clinician and a remote clinician, and transmitting imaging data representing a medical procedure to the remote clinician for consultation.

[0160] System 9000 includes a display device 9010, a table 9020, an imager 9040, a first computing device 9050, a server 9060, a network 9056, and a second computing device 9058. System 9000 may be an example of a system for use in a catheterization laboratory. In some examples, system 9000 may include other devices, such as Figure 1 Additional equipment depicted in the diagram is not shown in the figure for simplicity. Fig. 9. System 9000 can be used to diagnose cardiovascular problems in patients during the diagnostic phase. As discussed above, during this diagnostic phase (e.g., diagnostic angiography), there are three possible outcomes. The first possible outcome is that the clinician may determine that no intervention is needed. The second possible outcome is that the clinician may determine that urgent intervention is needed, and the clinician can handle the intervention during the same phase (e.g., without the patient leaving and coming back at another time). The third possible outcome is that treatment is needed, but the clinician is unwilling to perform the treatment, or the hospital where the catheter room is located does not have the instruments required for treatment. In the case of the third possible outcome, there may be imaging data (e.g., angiography data) from diagnostic medical surgery, which can be used to formulate a treatment plan for the patient. System 9000 can transform the case from the third possible outcome to the second possible outcome by allowing a remote clinician to consult, which can make the operating clinician more willing to perform the operation, thereby being able to provide the patient with necessary medical treatment during the same phase.

[0161] The first computing device 9050 can be associated with a first clinician who can be located in a catheterization lab during a medical procedure. The first computing device 9050 can be computing device 6050 or 6052 ( Figure 6 ), and may include, for example, off-the-shelf devices such as laptop computers, desktop computers, tablet computers, smart phones, or other similar devices. The first computing device 9050 includes a memory 9002 and a processing circuit system 9004. The second computing device 9058 may be associated with a remote second clinician. For example, the second computing device may be associated with a second clinician located in another part of the hospital, a specialist call center, at home, on vacation, etc. Similar to the first computing device 9050, the second computing device 9058 may include, for example, off-the-shelf devices such as laptop computers, desktop computers, tablet computers, smart phones, or other similar devices.

[0162] Although processing circuit system 9004 appears Fig. 99050, but in some examples, the features attributed to the processing circuit system 9004 can be performed by the processing circuit system of any of the first computing device 9050, the second computing device 9058, the imager 9040, the server 9060, the network 9056, other elements of the system 9000, or a combination thereof. In some examples, one or more processors associated with the processing circuit system 9004 in the first computing device 9050 can be distributed and shared between any combination of the first computing device 9050, the second computing device 9058, the imager 9040, the server 9060, the network 9056, and the display device 9010. In addition, in some examples, the processing operations or other operations performed by the processing circuit system 9004 can be performed by one or more remotely resident processors, such as one or more cloud servers or processors, each of which can be considered as part of the computing device 9050.

[0163] System 9000 includes network 9056, which can be a suitable 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. In some examples, network 9056 can be a secure network, such as a hospital network, which can restrict user access.

[0164] The processing circuit system 9004 can be communicatively coupled to a first computing device 9050 operated by a clinician or assistant in a catheterization room and a second computing device 9058 associated with a remote second clinician. In some examples, the first clinician may be performing a medical procedure, such as a cardiac catheterization laboratory procedure, and may encounter a patient condition (e.g., one or more particularly complex lesions) that they are reluctant to treat. In this case, the first clinician can enter a request through a user interface on the display device 9010, and the computing device 9050 can forward a representation of the user input to request a consultation with the second clinician, such as by calling or sending a message to a second computing device 9058 associated with a second clinician located elsewhere as discussed above. In response to receiving a representation of the user input requesting a consultation, a communication session between the first computing device 9050 and the second computing device 9058 can be established. During the communication session, the system 9000 can be configured to stream a representation of data captured by the imager 9040 of the medical procedure. As discussed above, the data representation captured by the imager 9040 can be a photo or video data.

[0165] As discussed above, the imager 9040 can be an angiographic imager or other imaging device, and can be used to image the patient's body during surgery to visualize the characteristics and location of lesions in the patient's body. The imager 9040 can be any type of imaging device, such as a CT device, an MRI device, a fluoroscopic device, a PET device, an ultrasound device, etc. As part of the normal operation of the imaging device, one or more of these imaging devices may capture the patient's personal health information (PHI), which may not be approved to be shared with certain clinicians who may serve as second remote clinicians. For example, a first clinician may request a consultation with a former attending physician, a classmate, a professor, etc., who are not affiliated with the hospital and therefore are not approved to view the PHI associated with the patient. In some examples, the processing circuit system 9004 can be configured to determine the permission status of the second clinician, and hide the personal health information from the data representation captured by one or more image sensors before streaming and in response to determining that the permission status of the second clinician is below a threshold permission status, as described below with respect to Fig.13A and Fig. 13B described in further detail.

[0166] In some examples, processing circuit system 9004 can assist the first clinician in determining when and whether to request a consultation with the second clinician. For example, processing circuit system 9004 can be configured to execute a computer vision model (such as computer vision model 2024 ( Figure 2 ) and / or machine learning models 2022( Figure 2 )) to identify a patient condition or intraoperative event in the data representation captured by the imager 9040. In response to identifying a patient condition or intraoperative event (e.g., a malfunctioning or damaged tool or instrument, proximity to a lesion, etc.), the processing circuit system 9004 may present a user interface on the display device 9010 that includes an option for the first clinician to request a consultation from the second computing device 9058.

[0167] Although the second computing device 9058 is described above as a single computing device associated with a single second clinician located remotely, in some examples, the processing circuit system 9004 can be configured to receive an indication of a request by the first clinician to send a message or make a call to more than one second computing device associated with more than one second clinician. In this way, the processing circuit system 9004 can be configured to allow a clinician to contact multiple potential consulting clinicians during a medical procedure, and to conduct a consultation even if one or more of these potential second clinicians are unavailable.

[0168] In some examples, the processing circuit system 9004 can be configured to receive a markup of the data representation from the first clinician through the first computing device 9050 or from one or both of the second clinician through the second computing device 9058, and transmit the markup to the other of the first clinician or the second clinician during the communication session. Such a markup may include, for example, a note or mark indicating a suggested path. Additionally or alternatively, the processing circuit system 9004 can be configured to capture data from one or more audio sensors (not shown) during a medical procedure and stream the data captured from the one or more audio sensors during a communication session. The audio sensor can be an off-the-shelf component of a notebook computer, a tablet computer, a mobile phone, etc., or it can be part of a catheter room.

[0169] In some examples, the processing circuitry 9004 can be configured to cause a display associated with the second computing device 9058 to display a list of medical devices available to the first clinician. The processing circuitry configured to share a list of instruments and tools available to the operating clinician can help the second clinician provide the best possible advice or recommendation based on the specific circumstances, taking into account that the operating clinician may be in a non-state-of-the-art environment when performing a medical procedure and may not have access to some or all of the best instruments and instruments.

[0170] In some examples, the processing circuit system 9004 can be configured to link the data from the imager 9040 captured during the medical procedure to the data from another medical test or operation. Other medical tests or operations may occur before or during the medical operation streamed via the communication setting. For example, the patient may be undergoing percutaneous coronary intervention, the streamed medical operation may be a cardiac catheterization operation, and the data from another medical test or operation may be data from a previous calcification test. In some examples, the calcification test may be a coronary artery calcium score, which may be generated by a computed tomography (CT). In some examples, a CT scan may be performed before a PCI operation. In some examples, other medical tests or operations may include data generated via intravascular ultrasound, which may be generated during the medical operation. In some examples, other medical tests may include data generated during an echocardiogram. In the case where the medical operation is a structural heart medical operation, echocardiogram data may be particularly important.

[0171] Fig.10 is a flow chart illustrating an example technique for streaming data representations to a remote clinician according to one or more aspects of the present disclosure. Fig. 9 The system 9000 is described, but Fig. 9 The technology can also be implemented by other systems, such as system 1000 ( Figure 1 ), System 6000( Figure 6 ) or any combination of devices of system 9000 capable of performing such technology.

[0172] Processing circuit system 9004 may receive a representation of user input from a first clinician who is performing a medical procedure and is associated with a first computing device 9050 to request a second clinician who is remote from the first clinician for a consultation (10002). In some examples, processing circuit system 9004 may execute a computer vision model to identify a patient condition or intraoperative event in a data representation captured by imager 9040. Further, in some examples, processing circuit system 9004 may cause display device 9010 to display a user interface including an option for the first clinician to request a consultation from a second computing device 9058 associated with the second clinician. In some examples, processing circuit system 9004 may receive a representation of user input requesting a second clinician for a consultation, and processing circuit system 9004 may cause first computing device 9050 to call or send a message to second computing device 9058. In some examples, the patient condition may be a lesion, and the medical procedure may be a percutaneous coronary intervention.

[0173] In response to receiving an indication of user input requesting a consultation, processing circuitry 9004 may establish a communication session between first computing device 9050 and second computing device 9058 ( 10004 ).

[0174] In some examples, Fig.10 The technology may include processing circuit system 9004 determining the clearance status of the second clinician. Processing circuit system 90004 may hide the personal health information from the data representation captured by imager 9040 before streaming and in response to determining that the clearance status of the second clinician is below a threshold clearance status.

[0175] The processing circuit system 9004 may transmit a data representation of a medical operation captured by the imager 9040 via a communication session (10006). In some examples, the data captured by the imager 9040 may include video data, fluoroscopic imaging, or both. In some examples, the processing circuit system 9004 may receive annotations of the data representation from one or both of the first clinician or the second clinician through a computing device associated with each other. In some examples, the processing circuit system 9004 may transmit the annotations to the corresponding computing device of the other of the first clinician or the second clinician during the communication session. In some examples, the stream during the communication session may further include data captured by the processing circuit system 9004 from one or more audio sensors during the medical operation. In some examples, the processing circuit system 9004 may cause a display associated with the second computing device 9058 to display a list of medical instruments available to the first clinician. In some examples, the processing circuit system 9004 may link data from the imager 9040 during the medical operation to data from another medical test or operation. In some examples, the other medical test or procedure is a calcification test, or data generated during an intravascular ultrasound medical procedure.

[0176] Fig.11 is a time diagram illustrating an example condensed version of imaging data sensed by one or more image sensors during a cardiac catheterization medical procedure in accordance with one or more aspects of the present disclosure. Fig.11 shows the time dimension along the A axis starting at time 0 and extending to time t. Also see Fig. 9 and Fig.11 , the medical system 9000 can be configured to receive imaging data from an imager 9040. The imager 9004 can sense imaging data during a medical procedure (such as a cardiac catheter procedure). The imaging data can be sensed as a substantially continuous stream of discrete images starting at time 0 (which can correspond to the time when the medical procedure begins and / or the time when the imager 9040 is turned on). The continuous stream of discrete images starts at time 0 and continues until time t.

[0177] Processing circuit system 9004 can be configured to generate a condensed version of imaging data, which includes images corresponding to specific events of the medical operation. Similarly, processing circuit system 9004 can create a shortened version of the medical operation, which includes only the key parts of the medical operation. For example, the condensed version can include an excerpt, such as video 11000A extending from time t2 to time t3. In addition or alternatively, the condensed version can include an excerpt, such as video 11000B extending from time t4 to time t5. The condensed version can further include an excerpt, such as video 11000C extending from time t6 to time t7. In some examples, the condensed version can include a continuous segment, such as video 11000A. In some examples, videos 11000A, 11000B, and 11000C (collectively referred to as "video 11000") can be added together in any combination by processing circuit system 9004 to include any portion of the duration of the medical operation that is less than the total duration of the medical operation. In some examples, as shown, video 11000 can individually include any portion of a medical procedure that is less than the length of the entire medical procedure.

[0178] Furthermore, additionally or alternatively, the condensed version of the imaging data may include one or more images 11002A, 11002B (collectively, "images 11002"). In some examples, 11002A may correspond to a "before" picture, while 11002B may correspond to an "after" picture. In this manner, a clinician may collate shortened videos and / or before-and-after still images along with key case notes and simply and efficiently share the collated portion of a medical procedure with a second clinician (e.g., a referring interventional cardiologist) who may be too busy to consult during the entire medical procedure.

[0179] In some examples, processing circuit system 9004 can be configured to receive user input to start video 11000A, i.e., an excerpt of received imaging data in the cardiac catheterization imaging data, at time t2. In some examples, processing circuit system 9004 is configured to receive user input to end video 11000A at time t3. In some examples, processing circuit system 9004 can be configured to receive audio commands to receive user input to start and / or end video excerpts.

[0180] In some examples, processing circuit system 9004 can be configured to receive user input to start video excerpting, and further configured to output a user interface via display device 9010 for display to present the clinician with an option to start video excerpting of the received imaging data. In some examples, processing circuit system 9004 can be configured to, alone or in conjunction with machine learning model 2022 ( Figure 2) combined to execute computer vision models 2024( Figure 2 ) to identify patient conditions (e.g., lesions) or intraoperative events (e.g., critical time frames such as traversing a lesion with a medical instrument). In some examples, processing circuit system 9004 can be configured to store a condensed version in memory 9002. In some examples, processing circuit system 9004 can be configured to upload a condensed version of the received imaging data to server 9060.

[0181] In some examples, the processing circuit system can be configured to receive an indication of user input from a first computing device 9050 associated with a first clinician who is performing a medical procedure to request a consultation with a second clinician who is remote from the first clinician. In response to receiving the indication of user input requesting a consultation, the processing circuit system 9004 can establish a communication session between the first computing device 9050 associated with the first clinician and the second computing device 9058 associated with the second clinician. The processing circuit system can transmit a condensed version of the imaging data from the imager 9040 via the communication session.

[0182] In some examples, as described above for Fig. 9 In the example described above (wherein a medical procedure is streamed continuously in real time), the processing circuit system 9004 can be configured to determine the clearance status of a second clinician and, prior to streaming and in response to determining that the clearance status of the second clinician is below a threshold clearance status, hide the personal health information from the condensed version of the data captured by the imager 9040.

[0183] The condensed version of the imaging data can serve as a "highlights" of the medical procedure that can be quickly shared and viewed by consulting physicians. Thus, video 11000A may include a video representation of a first specific event (e.g., traversing a first lesion), and processing circuit system 9004 may be configured to generate a second condensed version of the imaging data as video 11000B based on the imaging data from imager 9040, which may include images corresponding to a second specific event of the cardiac catheter medical procedure (e.g., traversing a second lesion). Processing circuit system 9004 may be configured to receive a case record related to the medical procedure, and may be configured to associate the received case record with the condensed version of the imaging data.

[0184] Fig.12 is a flow chart illustrating an example technique for generating a condensed version of imaging data sensed by one or more image sensors according to one or more aspects of the present disclosure. Fig. 9 System 9000 and Fig.11 The timing diagram is described, but Fig.12The technology can also be implemented by other systems, such as system 1000 ( Figure 1 ), System 6000( Figure 6 ) or any combination of devices of system 9000 capable of performing such technology.

[0185] Processing circuit system 9004 may receive imaging data sensed by imager 9040 during a medical procedure (12002). Processing circuit system 9004 may generate a condensed version of the imaging data from imager 9040 based on the sensed imaging data, the condensed version of the imaging data including images corresponding to specific events of the cardiac catheter medical procedure (12004). In some examples, processing circuit system 9004 may generate a video excerpt 11000 ( Fig.11 ) to generate a condensed version of the imaging data. In some examples, the processing circuit system 9004 can generate a video excerpt by receiving user input to start and / or end video excerpt 11000 of the received imaging data in the cardiac catheterization imaging data. In some examples, the processing circuit system 9004 can receive an audio command from a clinician to start and / or end video excerpt 11000.

[0186] The option to start a condensed version or an excerpt of the condensed version may be presented to the clinician via a user interface on the display device 9010 and then output by the processing circuit system 9004 for display. To output a user interface including the option to start a condensed version or an excerpt of the condensed version of the video excerpt 11000A for display, the processing circuit system 9004 may execute the computer vision model 2024 ( Figure 2 ) and / or machine learning models 2022( Figure 2 ) to identify a patient condition or intraoperative event in the received imaging data. Thus, in some examples, these advanced features of system 9000 can assist clinicians in identifying situations where a consultation with a second clinician may be valuable. In response to an indication of a user input requesting a consultation with a second clinician that is remote from the first clinician, processing circuit system 9004 can establish a communication session between a computing device associated with the first clinician and a computing device associated with the second clinician and stream a condensed version of the imaging data. Prior to establishing the communication session, processing circuit system 9004 can determine that the second clinician does not have the necessary authority to view the patient's personal health information, and can hide the PHI from the video 11000 and image 11002 that constitute the condensed version of the imaging data.

[0187] Processing circuit system 9004 may continue along the Fig.11The time arrow A of captures the key events of the medical procedure (e.g., videos 11000A, 11000B, 11000C). In some examples, each video 11000A in the video 11000 may represent a different specific event, and the processing circuit system may capture a different set of specific events in the video 11000B at different times. The processing circuit system 9004 may upload, mark and / or store the videos 11000A, 11000B and / or 11000C together or separately in the memory 9002 or the server 9060. In some examples, the processing circuit system 9004 may associate an associated case record with the performed medical procedure, and further associate the received case record with a condensed version of the imaging data.

[0188] Fig.13A and Fig. 13B is an example conceptual screenshot showing a second computing device 9058 ( Fig. 9 ) example representation of imaging data 13700A, 13700B on a user interface associated with the imaging data. Fig.13A An example screenshot including identification elements 13702, 13704 is shown. Identification element 13704 includes personal health information associated with a patient undergoing a medical procedure, which can only be shared with clinicians and other employees who meet a threshold permission status. For example, a clinician may need to be an employee or affiliated with the hospital where the medical procedure is performed to obtain a threshold permission status, which means that system 9000 may not be used with certain clinicians as second remote clinicians because the imaging data shared via the communication session may be collected with the patient's personal health information or information that the first clinician does not wish to share, which is superimposed or otherwise attached to the imaging data. Further, a de-identified version of the imaging data can be shared with other interested parties as a teaching tool or reputation tool, such as on a social network.

[0189] Fig. 13B Shown Fig.13A 13700B, wherein the identification elements 13702, 13704 are hidden by the hidden box 13706. In this manner, the processing circuit system 9004 ( Fig. 9 ) can be configured to be from imager 9040 ( Fig. 9 ) receives imaging data that may include one or more identification elements (13702, 13704) and generates a de-identified version of the imaging data that does not include the identification elements 13702, 13704 ( Fig. 13B ). The processing circuit system 9004 is configured to not include the identification elements 13702, 13704 ( Fig. 9) can allow imaging data from imager 90004 to be securely shared with relevant parties.

[0190] Although elements 13702, 13704 have been identified Fig. 13B is described as being obscured by hidden box 13706, but processing circuit system 9004 ( Fig. 9 ) may be configured to otherwise not include identifying elements 13702, 13704 in the de-identified version. Processing circuit system 9004 ( Fig. 9 ) can be configured to hide, delete, blur or otherwise render the identifying elements 13704 including PHI illegible to generate a de-identified version of the imaging data. For example, since the imager 9040 ( Fig. 9 ) can apply a text overlay containing the identification element to the sensed imaging data, whereby the processing circuit system 9004 ( Fig. 9 ) can be configured to scan from imager 9040 ( Fig. 9 ) to obtain text overlays, identify the text overlays, and hide, delete, blur, or make the text overlays illegible.

[0191] In some examples, processing circuit system 9004 ( Fig. 9 ) can be configured to send a de-identified version of the imaging data ( Fig. 13B ) is uploaded to server 9060. In some examples, processing circuit system 9004 ( Fig. 9 ) can be configured to publish de-identified versions of imaging data on social networks (such as physician-only social networks) Fig. 13B ).

[0192] Fig.14 is a flow chart illustrating an example technique for generating a de-identified version of imaging data sensed by one or more image sensors during a medical procedure in accordance with one or more aspects of the present disclosure. Fig. 9 System 9000 and Fig.13A and Fig. 13B Various versions of the imaging data are described, but Fig.14 The technology can also be implemented by other systems, such as system 1000 ( Figure 1 ), System 6000( Figure 6 ) or any combination of devices of system 9000 capable of performing such technology.

[0193] Processing circuit system 9004 may receive imaging data from imager 9040 during a medical procedure, the received imaging data including one or more identification elements 13702, 13704 (14002). Processing circuit system 9004 may generate a de-identified version of the imaging data based on the imaging data from imager 9040 ( Fig. 13B ), the de-identified version of the imaging data does not include the identifying elements 13702, 13704. The identifying elements 13704 may include personal health information, and the processing circuit system 9004 may generate the de-identified version by hiding, deleting, blurring, or making the personal health information illegible ( Fig. 13B ) to generate a de-identified version of the imaging data ( Fig. 13B ). In some examples, processing circuit system 9004 can scan imaging data from one or more image sensors to obtain text overlays, thereby identifying text overlays; and hide, delete, blur, or otherwise make the text overlay illegible.

[0194] In some examples, processing circuit system 9004 may include a de-identified version of the imaging data ( Fig. 13B ) to a server. In some examples, processing circuit system 9004 can post a de-identified version of the imaging data on a social network (e.g., a physician-only social network). In some examples, the imaging data from imager 9040 can include video data, fluoroscopic data, or both.

[0195] Fig.15 is a screenshot of an example user interface 15000 for using an example medical system of the present disclosure for educational purposes according to one or more aspects of the present disclosure. The user interface 15000 may be in Fig. 9 The processing circuit system 9004 ( Fig. 9 ) can be configured to output the user interface 15000 to any suitable display, such as the display device 9010 ( Fig. 9 ), and the first computing device 9050 ( Fig. 9 ) associated with the computing device, a display associated with the second computing device 9058, or another display device.

[0196] Processing circuit system 9004 ( Fig. 9 ) can be configured to output a home button 15806, a viewing window 15820, a training menu 15810, a filter menu 15812, and an operation menu 15808 for display on the user interface 15000.

[0197] The viewing window 15820 may display images from the imager 9040 ( Fig. 9 ) or a representation of imaging data from another imager, in Fig.15 In some examples, processing circuit system 9004 ( Fig. 9 ) can be configured to automatically display the data stored in the memory 9002 ( Fig. 9 ) as the first medical procedure 15802. In some examples, the processing circuit system 9004 ( Fig. 9 ) may be configured to receive user input to find and select a file stored in memory 9002 ( Fig. 9 ) to be outputted for display as the first medical procedure. Processing circuit system 9004 ( Fig. 9 ) can be configured to output multiple drop-down menus in the filter menu 15812 for display to assist the clinician in finding and selecting the first medical procedure. Additionally or alternatively, the processing circuit system 9004 ( Fig. 9 ) outputs a search bar for display and includes a search field that the clinician can use to select from memory 9002 ( Fig. 9 ) in the search function to identify and select the first medical surgery 15802.

[0198] The viewing window 15820 may also display a representation of the imaging data from the second medical procedure 15804, presented as “Expert Treatment of Similar Lesions.” The representation of the imaging data from the second medical procedure 15804 may be stored in the memory 9002 ( Fig. 9 ). Processing circuit system 9004 ( Fig. 9 ) can be configured to execute computer vision model 2024 ( Figure 2 ) and / or machine learning models 2024( Figure 2 ) to identify and / or select a second medical procedure 15804 from a plurality of medical procedures to output for display along with the first medical procedure 15802. Processing circuit system 9004 (configured to display the first medical procedure 15802 and the second medical procedure 15804) Fig. 9 ) can be a useful learning tool for clinicians to compare lesions, techniques, treatment strategies, etc. between a first medical procedure 15802 and a second medical procedure 15804. In some examples, clinicians can select a medical procedure that they recently performed as the first medical procedure 15802 and compare their strategy with that of another clinician in a similar case, where the identification of similar cases is accomplished by computer vision model 2024 and / or machine learning model 2022.

[0199] As described above, the processing circuit system 9004 ( Fig. 9 ) can execute computer vision model 2022 to use propensity matching to identify and select a medical procedure to be displayed as a second medical procedure 15804. In some examples, propensity matching can include using processing circuit system 9004 ( Fig. 9 ) to analyze the imager 9040 ( Fig. 9) to determine the lesion type, lesion subtype, or otherwise classify the lesion (e.g., provide a score or other identifier), etc. based on the determined lesion characteristics. The characteristics of the lesion may include, for example, the lesion type (e.g., bifurcation lesion), lesion diameter, degree of stenosis, degree of calcification, vessel take-off angle, etc. The classification of the lesions may be to classify lesions with greater similarity as being the same or close to each other. The processing circuit system may be configured to display a medical procedure that includes a lesion that belongs to the same classification or a similar classification as the lesion present in the first medical procedure 15802 as a second medical procedure 15804.

[0200] In some examples, processing circuit system 9004 ( Fig. 9 ) can be configured to use the computer vision model 2024( Figure 2 ) and / or machine learning models 2022( Figure 2 ) by comparing the imaging data from the first medical procedure 15802 with the imaging data stored in the memory 9002 ( Fig. 9 ) to perform propensity matching, and based on the similarity of one or more patient conditions between medical procedure 15802 and the second medical procedure, select from the plurality of medical procedures stored in memory 9002 ( Fig. 9 ) to select the most similar medical procedure to be output together with the first medical procedure 15802 for display. In some examples, the first medical procedure 15802 can be output together with the first medical procedure 15802 stored in the memory 9002 ( Fig. 9 ) and may select the medical procedure that is most similar in one or more aspects to output for display as the second medical procedure 15804. Alternatively, a threshold level of similarity (e.g., patient conditions including the same classified lesions) may be set and the processing circuit system 9004 ( Fig. 9 ) may output any one of the medical procedures that satisfies the threshold for output for display as second medical procedure 15804. In some examples, processing circuit system 9004 may be configured to compare medical procedures stored in memory 9002 that include lesions within the patient's vasculature, and may compare lesions based on lesion characteristics including at least one of lesion length, shape, geometry, location, extent, vessel exit angle, or calcification percentage.

[0201] Processing circuit system 9004 ( Fig. 9 ) can also output a filter menu 15812 for display on the user interface 1600, which can enable the clinician to filter the stored in the memory 9002 ( Fig. 9) in the first medical operation 15802 and / or the second medical operation 15804. Filters can be applied to narrow the scope of candidate medical operations for one or both of the first medical operation 15802 and / or the second medical operation 15804. As shown, the filter menu 15812 can present the clinician with the option of filtering by one or more of the patient characteristics, patient conditions, medical tools or instruments used during the cardiac catheterization medical operation, operating clinicians, treatments used or treatment classifications. Additionally or alternatively, the filter menu 15812 can present the clinician with the option of filtering by hospital type, the order of tools or treatments used, or the length of the operation. In some examples, patient characteristics can include patient age, height, weight, gender, disease, or diagnosis. In some examples, the medical equipment, tools, or instruments used can include the size or geometry of the catheter tip.

[0202] In some examples, the imaging data forming the representation of the first medical procedure 15802 may be video data. In some examples, the imaging data forming the representation of the second medical procedure 15804 may be video data. Fig.15 are shown adjacent to each other, but in some examples, processing circuit system 9004 ( Fig. 9 ) can be configured to cause the display to overlay video data from the second medical procedure 15804 on the video data of the first medical procedure 15802, and vice versa, such that the videos are superimposed on each other within the viewing window 15820. Viewing the medical procedure in this manner can facilitate a clinician to more carefully analyze the location of a lesion, the speed of an instrument through the vascular system, or other parameters. Although described herein as two different medical procedures for ease of description, in some examples, the processing circuit system 9004 ( Fig. 9 ) can be configured to output more than two medical procedures for display within viewing window 15820, such as three medical procedures, four medical procedures, or more.

[0203] Fig.16 is a flow chart illustrating an example technique for using the example medical system of the present disclosure for educational purposes. Fig. 9 System 9000 and Fig.15 The user interface 15000 is described, but Fig.16 The technology can also be implemented by other systems, such as system 1000 ( Figure 1 ), System 6000( Figure 6 ) or any combination of devices of system 9000 capable of performing such technology.

[0204] Processing circuit system 9004 ( Fig. 9 ) can be used in medical surgery 15802 ( Fig.15 ) during the period from imager 9040 ( Fig. 9) receives imaging data (16002). Processing circuit system 9004 ( Fig. 9 ) can execute computer vision models 2024( Figure 2 ) and / or machine learning models 2022( Figure 2 ) to identify and / or select stored in memory 9002 ( Fig. 9 ) of the second of the plurality of medical procedures 15804 ( Fig.15 )(16004). Processing circuit system 9004 ( Fig. 9 ) can be exported from the first medical operation 15802 ( Fig.15 ) and a representation of imaging data from a second medical procedure 15804 ( Fig.15 ) so as to be displayed on the display device 9010( Fig. 9 ) is displayed on (16006).

[0205] In some examples, the second medical procedure 15804 ( Fig.15 ) including the first medical surgery 15802 ( Fig.15 ) similar patient conditions. In some examples, processing circuit system 9004 ( Fig. 9 ) can execute computer vision models 2024( Figure 2 ), using propensity matching in memory 9002 ( Fig. 9 )Found in Second Medical Surgery 15804( Fig.15 ).

[0206] In some examples, processing circuit system 9004 ( Fig. 9 ) can use propensity matching to identify patients from the first medical surgery 15802 ( Fig.15 ) and the imaging data stored in the memory 9002 ( Fig. 9 ) and based on the first medical operation 15802 ( Fig.15 ) and Second Medical Surgery 15804( Fig.15 ) from the similarity of one or more characteristics stored in memory 9002 ( Fig. 9 ) selects a second medical procedure from among multiple medical procedures 15804 ( Fig.15 ) with the First Medical Surgery 15802( Fig.15 ) together for display.

[0207] In some examples, the patient condition may be a pathology, and the processing circuit system 9004 ( Fig. 9 ) can be transferred from the first medical operation 15802 ( Fig.15 ) and one or more lesion characteristics stored in memory 9002 ( Fig. 9) and compares multiple medical procedures in memory 9002 ( Fig. 9 ) to find the most similar lesion from multiple medical surgeries stored in memory 9002 ( Fig. 9 ) in a plurality of cardiac catheterization medical procedures, identifying and selecting a second medical procedure 15804 ( Fig.15 ). In some examples, wherein the one or more lesion characteristics include at least one of lesion length, shape, geometry, location, extent, vessel exit angle, and / or degree of calcification.

[0208] In some examples, processing circuit system 9004 ( Fig. 9 ) can make the user interface 15000 ( Fig.15 ) presents to the clinician the screening of the stored data in the memory 9002 (in one or more ways) Fig. 9 ) in multiple medical procedures. In some examples, processing circuit system 9004 ( Fig. 9 ) can make the user interface 15000 ( Fig.15 ) presents the clinician with the option to filter by one or more of the following: patient characteristics, patient conditions, medical tools or instruments used during the cardiac catheterization medical procedure, the operating clinician, the treatment or treatment category used, the type of hospital, the order of tools or treatments used, and / or the length of the procedure. In some examples, the patient characteristics include at least one of the patient's age, height, weight, gender, disease, or diagnosis. In some examples, the medical tools or instruments used include one or more of the catheter tip size or geometry.

[0209] In some examples, processing circuit system 9004 ( Fig. 9 ) can make the user interface 15000 ( Fig.15 )In the viewing window 15820( Fig.15 ) shows the first medical operation 15802 ( Fig.15 ) and Second Medical Surgery 15804( Fig.15 In some examples, processing circuit system 9004 ( Fig. 9 ) can make the user interface 15000 ( Fig.15 )In the viewing window 15820( Fig.15 ) Lieutenant General from the Second Medical Operation 15804 ( Fig.15 ) is superimposed on the video data from the first medical operation 15802 ( Fig.15 ) on the video data. Alternatively, in some examples, the video from the two medical procedures can be viewed in viewing window 15820 ( Fig.15 ) are displayed next to each other.

[0210] Fig.17 is a flow chart illustrating an example technique for using an example medical system of the present disclosure for educational purposes according to one or more aspects of the present disclosure. Fig. 9 System 9000 and Fig.15 The user interface 15000 is described, but Fig.16 The technology can also be implemented by other systems, such as system 1000 ( Figure 1 ), System 6000( Figure 6 ) or any combination of devices of system 9000 capable of performing such technology.

[0211] Processing circuit system 9004 ( Fig. 9 ) can capture user information of a user interacting with the medical system to identify the user (17002). In some examples, the processing circuit system 9004 ( Fig. 9 ) can output a user login page for display to capture user information of a user interacting with the medical system to identify the user.

[0212] Processing circuitry 9004 may store data representing imaging data from a plurality of medical procedures in memory 9002 ( Fig. 9 ) (17004). Processing circuit system 9004 ( Fig. 9 ) can output the representation stored in memory 9002 ( Fig. 9 ) of a plurality of cardiac catheterization medical procedures (17006). After the data representing the individual medical procedures are output for display, credits are awarded to the user who viewed the individual cardiac catheterization medical procedures (17008).

[0213] In some examples, granting credit to a user viewing a medical procedure excerpt may include granting at least a portion of continuing medical education (CME) credit to the user. In some examples, processing circuit system 9004 ( Fig. 9 ) can be integrated with a certification body and as part of granting at least a portion of CME credit to a user, processing circuit system 9004 ( Fig. 9 ) can report the user's name to the authentication authority. In some examples, the processing circuit system 9004 ( Fig. 9 ) can enable the display device 9010 ( Fig. 9 ) associated user interface 15000 ( Fig.15 ) provides the user with the option of filtering multiple medical procedures in one or more ways. In some examples, the processing circuit system 9004 ( Fig. 9 ) can make the user interface 15000 ( Fig.15 ) presents multiple drop-down menus as filter menus 15812 ( Fig.15 ) to display.

[0214] Fig.18 is a schematic perspective view of an example medical system 18000. The medical system 18000 may be Figure 1 Medical Systems 1000 and / or Figure 6 Example of Medical System 9000. Fig.18 Medical systems 18000 and Fig. 9 Medical system 18000 is similar to medical system 9000 except as described below, where like reference numerals represent like elements. Medical system 18000 can perform various contrast media management functions to support catheterization laboratory procedures.

[0215] System 18000 includes display device 18010, table 18020, imager 18040, computing device 18050, and server 18060. System 18000 may be an example of a system for use in a catheterization laboratory. In some examples, system 18000 may include other devices, such as Figure 1 Additional equipment depicted in the diagram is not shown in the figure for simplicity. Fig.18 The system 18000 can be used to diagnose and / or intervene in a patient's cardiovascular problems during the catheterization laboratory procedure phase.

[0216] Computing device 18050 may be associated with a clinician who may be located in a catheterization laboratory during a medical procedure. Computing device 18050 may be computing device 6050 or 6052 ( Figure 6 ) and may include, for example, off-the-shelf devices such as laptops, desktop computers, tablet computers, smartphones, or other similar devices. Computing device 18050 includes memory 18002 and processing circuit system 18004.

[0217] Although processing circuit system 18004 appears Fig.18 18050, but in some examples, features attributed to processing circuit system 18004 can be performed by processing circuit system of any of computing device 18050, imager 18040, server 18060, other elements of system 18000, or a combination thereof. In some examples, one or more processors associated with processing circuit system 18004 in computing device 18050 can be distributed and shared between any combination of computing device 18050, imager 18040, server 18060, network 18056, and display device 18010. In addition, in some examples, processing operations or other operations performed by processing circuit system 18004 can be performed by one or more remotely resident processors, such as one or more cloud servers or processors, each of which can be considered part of computing device 18050.

[0218] System 18000 includes network 18056, which can be a suitable 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. In some examples, network 18056 can be a secure network, such as a hospital network, which can restrict user access.

[0219] As discussed above, the imager 18040 can be an angiographic imager or other imaging device and can be used to image the patient's body during surgery to visualize the characteristics and location of lesions in the patient's body. The imager 9040 can be any type of imaging device, such as a CT device, an MRI device, a fluoroscopic device, a PET device, an ultrasound device, etc.

[0220] During a catheterization laboratory procedure, contrast media may be injected into the patient's vasculature. The contrast media can enhance the appearance of blood and / or other components in the imaging data captured by the imager 18040. In some examples, the contrast media can be manually injected into the vasculature by a clinician (e.g., a cardiologist, a nurse, or others) via a syringe. In other examples, the system 18000 can include a contrast media injector (e.g., a power injector) that can automatically inject / dispense contrast media.

[0221] In general, the amount of contrast used in a cath lab procedure is a balance between using enough contrast to make the resulting images useful, but not using too much to cause adverse side effects. For example, using too much contrast can lead to a condition called contrast-induced nephropathy (CIN).

[0222] Clinicians performing cath lab procedures may have a rough goal for how much contrast they plan to use during the procedure. However, tracking actual versus planned contrast usage may adversely affect clinicians' workload during the procedure.

[0223] According to one or more aspects of the present disclosure, system 18000 can provide automatic tracking of contrast agent usage. For example, computing device 18050 can determine the cumulative amount of contrast agent used during a cardiac catheterization laboratory (cath room) procedure and cause display device 18010 to display a graphical representation of the cumulative amount of contrast agent used during the catheterization laboratory procedure. Thus, system 18000 can enable a clinician to quickly determine how much contrast agent has been used (e.g., at a glance).

[0224] The graphical representation displayed on the display device 18010 can be in any suitable form. Examples include, but are not limited to, a graph (e.g., a bar graph, a pie chart, a line graph, etc.), a textual representation (e.g., a number on a display), or any other representation. As an example, the graphical representation can include a graph with a curve of the amount of contrast used over time. As another example, the textual representation can include the percentage of contrast used relative to the expected or maximum amount of contrast.

[0225] In some examples, computing device 18050 can provide contextual data to assist the clinician in better understanding the amount of contrast that has been used. For example, computing device 18050 can include in the graphical representation the amount of contrast that has been used at the current moment in the catheterization laboratory procedure. This can further assist the clinician in determining whether the contrast administration rate should be slowed down (e.g., if the actual amount used is greater than the estimated amount), or if additional contrast buffer is available (e.g., if the actual amount used is less than the estimated amount).

[0226] The computing device 18050 can output a comparison between the expected contrast dose and the actual contrast dose within each time range. As an example, the computing device 18050 can output a comparison of the contrast agent usage of the entire operation. For example, the computing device 18050 can cause the display device 18010 to display a graphical representation of the comparison between the cumulative amount of contrast agent used so far during the cardiac catheterization laboratory operation and the total amount of contrast agent expected / predicted to be used during the entire operation. As another example, the computing device 18050 can output a step-by-step comparison of the contrast agent usage. For example, when the execution of the catheterization laboratory operation includes performing multiple steps (e.g., navigating the device to the lesion, intervening the lesion with the device, measuring blood flow after intervention, etc.), the computing device 18050 can determine the individual target contrast agent doses for different steps, and display a graphical representation of the comparison between the target contrast agent dose for each step and the corresponding contrast agent dose used during the execution of these steps.

[0227] In general, the cadence of contrast usage may not be linearly distributed throughout the catheterization laboratory procedure. The execution of certain steps may utilize more contrast than other steps. Therefore, a linear representation of target contrast usage relative to a step (e.g., 37.5% of the total contrast is expected to be used at the end of step 3 of a total of 8 steps) may not be useful to the clinician. According to one or more aspects of the present disclosure, the target contrast dose for each step may be different. For example, the target contrast dose for the navigation step may be lower than the target contrast dose for the measurement step. In this way, system 18000 can provide clinicians with higher quality contrast usage guidance.

[0228] At the beginning of the catheterization laboratory procedure, there may be a planned total contrast dose (e.g., the sum of the target contrast doses for all steps). However, in some cases, events may occur that cause the clinician to want to administer more contrast than the planned total contrast dose. As discussed above, a patient receiving too much contrast may result in CIN. However, different patients may be able to tolerate different amounts of contrast without developing CIN. Therefore, the clinician may wish to determine how much more contrast can be administered to the patient without causing CIN.

[0229] According to one or more aspects of the present disclosure, the computing device 18050 can obtain the maximum contrast agent dose used for the catheterization laboratory procedure and output a comparison between the cumulative amount of contrast agent used and the maximum contrast agent dose. For example, the computing device 18050 can cause the display device 18010 to display a graphical representation of the comparison between the cumulative amount of contrast agent used and the maximum contrast agent dose (e.g., 80cc of the 120 cubic centimeters (cc) maximum dose has been used). In this way, the computing device 18050 can enable the clinician to quickly determine how much additional contrast agent can be used without causing CIN.

[0230] As discussed above, computing device 18050 can determine the amount of contrast used. In general, computing device 18050 can determine the amount of contrast used via any suitable input source. As an example, computing device 18050 can receive manual input of the amount of contrast used via a user interface (e.g., by a clinician or other person present, such as a nurse). For example, the manual input can indicate how many syringes of a specific capacity (e.g., 20cc) have been used. As another example, computing device 18050 can receive data representing the amount of contrast used via one or more sensors (e.g., a flow meter). For example, computing device 18050 can receive data from a sensor integrated in contrast agent injector 18080 or a sensor connected in series between contrast agent injector 18080 and the patient. In some examples, the connection between the sensor and computing device 18050 can be wireless (e.g., Bluetooth, Wi-FI, etc.). The received data can indicate the flow rate of the contrast agent (e.g., cc / min), or can indicate the cumulative amount of contrast agent used (e.g., cc). When the data indicates a contrast agent flow rate, the computing device 18050 can determine the cumulative amount of contrast agent used based on the contrast agent flow rate (and historical flow rate data for the procedure) (e.g., integrating the flow rate data).

[0231] As discussed above, computing device 18050 can utilize the expected / predicted contrast dose (e.g., when generating a graphical representation of actual contrast agent usage compared to the expected contrast agent usage). In some examples, the expected amount can be a universal non-patient-specific amount (e.g., a standard amount for navigation steps, measurement steps, etc.). In other examples, the expected amount can be patient-specific. For example, computing device 18050 can determine a patient-specific predicted contrast dose based on the attributes of the current patient. In some examples, the attributes can include imaging data of the current patient captured before the cardiac catheterization laboratory procedure (e.g., diagnostic angiography imaging data). For example, computing device 18050 can determine the classification of the current patient based on the imaging data (e.g., using a machine learning model as described above). Then, computing device 18050 can determine the predicted contrast dose of the current patient based on the contrast dose used by other patients with the classification. Therefore, computing device 18050 can predict the contrast dose of the current patient based on the contrast dose used in similar cases.

[0232] In some examples, computing device 18050 may perform clinician-independent contrast agent predictions. For example, computing device 18050 may predict contrast agent for the current patient regardless of the attributes of the clinician performing the procedure. In other examples, computing device 18050 may perform clinician-specific contrast agent predictions. For example, computing device 18050 may predict contrast agent for the current patient based on the attributes of the clinician performing the procedure.

[0233] In some examples, computing device 18050 can generate a clinician-specific contrast amount by adjusting the amount that is independent of the clinician. As an example, computing device 18050 can determine that the amount used by the clinician who is to perform the operation is less than the clinician-independent predicted amount by X%. In such an example, computing device 18050 can reduce the clinician-independent predicted amount by X% to generate a clinician-specific predicted amount. Similarly, if the amount that the clinician typically uses exceeds the clinician-independent predicted amount, computing device 18050 can increase the clinician-independent predicted amount.

[0234] In some examples, computing device 18050 can generate a clinician-specific contrast dose by making a prediction based on similar cases performed by the particular clinician. For example, computing device 18050 can determine a predicted dose based on the amount of contrast actually used by the particular clinician in similar cases.

[0235] As described above, the computing device 18050 can obtain the maximum contrast agent dose for the current patient and can predict the expected contrast agent usage for the current patient. In some examples, if the predicted contrast agent usage for the current patient is greater than the maximum contrast agent dose for the current patient, the computing device 18050 can output a warning or other indication to the clinician (e.g., during the planning stage). Therefore, the computing device 18050 can provide an advance warning to the clinician so that the clinician can modify their plan before actually starting the operation, which can avoid undesirable situations.

[0236] Fig.19 is a conceptual diagram illustrating an example graphical user interface (GUI) including contrast media usage data according to one or more aspects of the present disclosure. Fig.19 The GUI 19000 may be displayed on a display device such as Fig.18 18010. GUI 19000 is merely one example of a GUI containing contrast agent usage data, and other arrangements are contemplated.

[0237] like Fig.19 As shown, GUI 19000 includes contrast media usage data for five steps of a catheterization lab procedure. A computing device (such as computing device 18050) can update GUI 19000 as the catheterization lab procedure progresses. For example, GUI 19000 may initially include only a predicted bar for step 1. Then, when contrast media is administered or at the end of the execution of step 1, GUI 19000 can be updated to include an actual bar. Fig.19 As can be seen in the example of FIG1 , the amount of contrast agent actually used in step 1 is slightly less than the predicted amount. In contrast, the amount of contrast agent actually used in step 2 is slightly more than the predicted amount. Although shown as including five steps, GUI 19000 may include contrast agent information for more or fewer steps.

[0238] In some examples, GUI 19000 may omit contrast medium usage information for some steps. For example, GUI 19000 may include contrast medium usage information for the current step, but may omit or summarize contrast medium usage information for previous steps. As a specific example, when executing step 3, GUI 19000 may include an element that sums the actual and predicted amounts for completed steps (e.g., steps 1 and 2) and / or the predicted amounts for subsequent steps (e.g., steps 4 and 5).

[0239] Fig. 20 is a flow chart illustrating an example technique for providing contrast media usage data according to one or more aspects of the present disclosure. Fig.18 System 18000 and Fig.19The GUI 19000 is described, but Fig. 20 The technology can also be implemented by other systems, such as system 1000 ( Figure 1 ), System 6000( Figure 6 ) or any combination of devices of system 18000 capable of performing such technology.

[0240] Processing circuit system 18004 ( Fig.18 ) can determine a cumulative amount of contrast medium used during a cardiac catheterization laboratory (cath room) procedure (20002) and output a graphical representation of the cumulative amount of contrast medium used for display (20004). As described above, in some examples, the graphical representation can include a comparison between the cumulative amount of contrast medium used and an expected amount of contrast medium used. This comparison can be a comparison by procedure or a comparison by step (e.g., Fig.19 shows this step-by-step comparison).

[0241] Fig.21 is a conceptual diagram illustrating an example machine learning model according to one or more aspects of the present disclosure. The machine learning model 21000 may be an example of (multiple) machine learning models 2022 or any other machine learning model described herein. In some examples, the machine learning model 21000 may be part of (multiple) computer vision models 2024 or any other computer vision model described herein. The machine learning model 21000 may 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 device 1050, the computing device 2000 (or any other computing device described herein), and / or the server 1060 (or any other server described herein) may train, store, and / or utilize the machine learning model 21000, but in some examples, other devices of the system 1000 (or any other system described herein) may apply input to the machine learning model 21000. In some examples, other types of machine learning and deep learning models or algorithms may be utilized in other examples. For example, a convolutional neural network model of ResNet-18 may 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 multi-layer perceptrons.

[0242] like Fig.21As shown in the example of , the machine learning model 21000 may include three types of layers. The three types of layers include an input layer 21002, a hidden layer 21004, and an output layer 21006. The output layer 21006 includes the output of the transfer function 21005 from the output layer 21006. The input layer 21002 represents each input value X1 to X4 provided to the machine learning model 21000. In some examples, the input value may include any value input to the machine learning model, as described above. For example, the input value may include imaging data 2014, multiple lesions in past imaging data of multiple patients, post-ablation information in past imaging data from multiple patients, generator data 2020, motion data 2028, medical device data 2026, (multiple) lesion classifications 7230, data collected from past medical surgeries (including at least one of past imaging data, past tracked motion of medical devices, past controller data, or past lesion classifications), and / or other data as described above. Additionally, in some examples, input values ​​to machine learning model 21000 may include additional data, such as other data that may be collected by or stored in system 1000 (or any other system described herein).

[0243] Each input value of each node in the input layer 21002 is provided to each node of the first hidden layer 21004. Fig.21 In the example of , hidden layer 21004 includes two layers, one with four nodes and the other with three nodes, but fewer or greater numbers of nodes may be used in other examples. Each input from input layer 21002 is multiplied by a weight and then summed at each node of hidden layer 21004. During training of machine learning model 21000, the weight of each input is adjusted to establish a relationship between imaging data 2014, generator data 2020, motion data 2028, medical device data 2026, and / or any other input data and treatment strategy 2032, lesion characteristics, medical device identification, degree of success of lesion ablation, and / or any other output of machine learning model 21000. In some examples, one hidden layer may be incorporated into machine learning model 21000, or three or more hidden layers may be incorporated into machine learning model 21000, wherein each layer includes the same or different number of nodes.

[0244] The results of each node within the hidden layer 21004 are applied to the transfer function of the output layer 21006. The transfer function can be linear or nonlinear, depending on the number of layers within the machine learning model 21000. Example nonlinear transfer functions can be sigmoid functions or rectifier functions. The output 21007 of the transfer function can be a classification such as: imaging data 2014, generator data 2020, motion data 2028, medical device data 2026 indicating a specific treatment strategy, identification of a medical device, degree of success of lesion ablation, etc.

[0245] As shown in the above examples, by applying machine learning model 21000 to input data (such as imaging data 2014, generator data 2020, motion data 2028, medical device data 2026, and / or lesion classification(s) 7030), processing circuit system 2004 can determine characteristics of the lesion, one or more treatment strategies 2032, identification of the medical device, degree of success of lesion ablation, etc. This can improve patient outcomes.

[0246] Fig. 22 is a conceptual diagram illustrating an example training process for a machine learning model according to one or more aspects of the present disclosure. Process 22000 can be used to train (multiple) machine learning models 2022 (or any other machine learning model discussed herein) and / or (multiple) computer vision models 2024 (or any other computer vision model discussed herein). Machine learning model 22074 (which can be an example of machine learning model 21000, (multiple) machine learning model 2022, or any other machine learning model discussed herein) 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 device 1050 (or any other computing device discussed herein) and / or server 1060 (or any other server discussed herein) initially trains machine learning model 22074 based on a corpus of training data 22072. The training data 22072 may include, for example, data collected from past medical procedures, imaging data 2014, generator data 2020, motion data 2028, medical device data 2026, and / or any other training data described herein.

[0247] When training the machine learning model 22074, the processing circuit system 7004 (or any other processing circuit system discussed herein) may compare 22076 the prediction or classification with the target output 22078. The processing circuit system 2004 may train (learn / train 22080) the machine learning model 22074 using an error signal resulting from the comparison. The processing circuit system 2004 may generate machine learning model weights or other modifications that the processing circuit system 2004 may use to modify the machine learning model 22074. For example, the processing circuit system 2004 may modify the weights of the machine learning model 21000 based on the learning / training 22080. For example, for each training instance in the training data 22072, one or more of the computing devices 1050 and / or the server 1060 may modify the determination of lesion characteristics, medical device identification, degree of success of lesion ablation, and / or guidance of the clinician based on the training data 22072.

[0248] 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.

[0249] 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.

[0250] This disclosure includes the following non-limiting examples.

[0251] Example 1. A medical system comprising: a memory configured to store at least one computer vision model; and a processing circuit system communicatively coupled to the memory, the processing circuit system configured to: receive imaging data of at least a portion of a patient's vascular system generated during a cardiac catheterization procedure; and execute the at least one computer vision model to determine characteristics of lesions of the vascular system based on the received imaging data.

[0252] Example 2. A medical system as described in Example 1, wherein the computer vision model is trained based on multiple lesions in past imaging data of multiple patients.

[0253] Example 3. A medical system as described in Example 1 or Example 2, wherein the processing circuit system is further configured to: execute the at least one computer vision model to determine the medical device or type of medical device used during the cardiac catheterization procedure.

[0254] Example 4. A medical system as described in any of Examples 1-3, wherein the at least one computer vision model is trained based on post-ablation information in past imaging data from multiple patients, and wherein the processing circuit system is further configured to execute the at least one computer vision model to determine the success of the ablation of the lesion.

[0255] Example 5. A medical system as described in any of Examples 1-4, wherein the processing circuit system is further configured to: track the movement of a medical device during the cardiac catheterization procedure; and based on the tracked movement and the imaging data, output a representation of the movement of the medical device for display during the cardiac catheterization procedure.

[0256] Example 6. The medical system of Example 5, wherein the processing circuit system is further configured to determine whether at least a portion of the cardiac catheterization procedure was successful based on the tracked movement.

[0257] Example 7. A medical system as described in any of Examples 1-5, wherein the memory is further configured to store at least one machine learning model, and wherein the processing circuit system is further configured to: execute the at least one machine learning model to guide the clinician during the cardiac catheterization procedure.

[0258] Example 8. The medical system of Example 7, wherein the processing circuit system further outputs guidance to the clinician during the cardiac catheterization procedure based on characteristics of the lesion.

[0259] Example 9. The medical system of Example 7 or Example 8, wherein the processing circuit system further outputs guidance to the clinician during the cardiac catheterization procedure based on the clinician's identity.

[0260] Example 10. A medical system as described in any of Examples 7-9, wherein the processing circuit system is further configured to: predict the ability of a medical device to pass through the lesion based at least in part on characteristics of the lesion.

[0261] Example 11. A medical system as described in any of Examples 7-10, wherein the processing circuit system is further configured to determine whether the medical device passes through a lesion.

[0262] Example 12. A medical system as described in any of Examples 7-11, wherein at least one of the machine learning models is trained based on data collected from past medical procedures, including at least one of past imaging data, past tracked motion of a medical device, past controller data, or past lesion classifications.

[0263] Example 13. A medical system as described in any of Examples 1-12, wherein the processing circuit system is further configured to: receive controller data from a device; process the controller data to generate a representation of ablated tissue; and output the imaging data and the representation of the ablated tissue for display.

[0264] Example 14. A medical system as described in Example 13, wherein the processing circuit system is further configured to apply one or more timestamps to the imaging data and apply one or more timestamps to at least one of the controller data or the representation of the ablated tissue before outputting the imaging data and the representation of the ablated tissue for display, wherein, as part of outputting the imaging data and the representation of the ablated tissue for display, the processing circuit system is configured to: align the imaging data with the representation of the ablated tissue using one or more timestamps applied to the imaging data and one or more timestamps applied to at least one of the controller data or the representation of the ablated tissue; and superimpose the representation of the ablated tissue on the imaging data.

[0265] Example 15. A medical system as described in any of Examples 1-14, wherein the processing circuit system is further configured to control the energy generating device to stop delivering energy based on the controller data.

[0266] Example 16. A medical system as described in any of Examples 1-14, wherein the processing circuit system is further configured to control an automatic contrast agent delivery device to adjust a contrast agent delivery rate to a patient based on a quality of the imaging data or in response to at least one of the patient's tolerance to the contrast agent.

[0267] Example 17. A method comprising: receiving, by a processing circuit system, imaging data of at least a portion of a patient's vascular system generated during a cardiac catheterization procedure; and executing, by the processing circuit system, at least one computer vision model to determine characteristics of lesions in the vascular system based on the received imaging data.

[0268] Example 18. A method as described in Example 17, wherein the computer vision model is trained based on multiple lesions in past imaging data of multiple patients.

[0269] Example 19. The method of Example 17 or Example 18, further comprising: executing, by the processing circuit system, the at least one computer vision model to determine a medical device type of a medical device used during the cardiac catheterization procedure.

[0270] Example 20. A method as described in any of Examples 17-19, wherein the at least one computer vision model is trained based on post-ablation information in past imaging data, and the method further includes executing the at least one computer vision model by the processing circuit system to determine the success of the ablation of the lesion.

[0271] Example 21. The method as described in any of Examples 17 to 20 further includes: tracking the movement of a medical device during the cardiac catheterization procedure; and outputting, by the processing circuit system, a representation of the movement of the medical device for display during the cardiac catheterization procedure based on the tracked movement and the imaging data.

[0272] Example 22. The method of Example 21, further comprising determining, by the processing circuit system, whether at least a portion of the cardiac catheterization procedure was successful based on the tracked movement.

[0273] Example 23. The method of any of Examples 17-22, further comprising executing at least one machine learning model by the processing circuit system to guide a clinician during the cardiac catheterization procedure.

[0274] Example 24. The method of Example 23, wherein guiding the clinician during the cardiac catheterization procedure is based on characteristics of the lesion.

[0275] Example 25. A method as described in Example 23 or Example 24, wherein guiding the clinician during the cardiac catheterization procedure is based on the identity of the clinician.

[0276] Example 26. The method of any of Examples 23-25, further comprising predicting the ability of a medical device to pass through the lesion based at least in part on characteristics of the lesion.

[0277] Example 27. A method as described in any of Examples 23-26, further comprising determining whether the medical device passes through the lesion.

[0278] Example 28. A method as described in any of Examples 23-27, wherein at least one of the machine learning models is trained based on data collected from past medical procedures, including at least one of past imaging data, past tracked motion of a medical device, past controller data, or past lesion classifications.

[0279] Example 29. The method as described in any of Examples 17 to 28 further includes: receiving controller data from a device by the processing circuit system; processing the controller data by the processing circuit system to generate a representation of ablated tissue; and outputting the imaging data and the representation of the ablated tissue by the processing circuit system for display.

[0280] Example 30. The method as described in Example 29 further includes applying one or more timestamps to the imaging data and applying one or more timestamps to at least one of the controller data or the representation of the ablated tissue by the processing circuit system before outputting the imaging data and the representation of the ablated tissue for display, wherein outputting the imaging data and the representation of the ablated tissue for display includes: aligning the imaging data with the representation of the ablated tissue by the processing circuit system using one or more timestamps applied to the imaging data and one or more timestamps applied to at least one of the controller data or the representation of the ablated tissue; and superimposing the representation of the ablated tissue on the imaging data by the processing circuit system.

[0281] Example 31. The method of any of Examples 17-28, further comprising controlling, by the processing circuit system, the energy generating device to stop delivering energy based on the controller data.

[0282] Example 32. The method as described in any of Examples 17-31 further includes controlling the automatic contrast agent delivery device by the processing circuit system to stop delivering contrast agent to the patient based on at least one of the time the patient receives contrast agent or the amount of contrast provided to the patient by the automatic contrast agent delivery device.

[0283] Example 33. A non-transitory computer-readable storage medium storing instructions that, when executed, cause a processing circuit system to: receive imaging data of at least a portion of a patient's vascular system generated during a cardiac catheterization procedure; and execute at least one computer vision model to determine characteristics of lesions in the vascular system based on the received imaging data.

[0284] 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 computer vision model; as well as processing circuitry communicatively coupled to the memory, the processing circuitry being configured to: receiving imaging data of at least a portion of a patient's vasculature generated during a cardiac catheterization procedure; as well as The at least one computer vision model is executed to determine a characteristic of a lesion of the vasculature based on the received imaging data.

2. The medical system of claim 1, wherein: The computer vision model is trained based on multiple lesions in past imaging data of multiple patients.

3. The medical system of claim 1 or claim 2, wherein: The processing circuit system is further configured to: The at least one computer vision model is executed to determine a medical instrument or type of medical instrument used during the cardiac catheterization procedure.

4. The medical system according to any one of claims 1 to 3, wherein: The at least one computer vision model is trained based on post-ablation information in past imaging data from a plurality of patients, and wherein the processing circuit system is further configured to execute the at least one computer vision model to determine a degree of success of ablation of the lesion.

5. The medical system according to any one of claims 1 to 4, wherein: The processing circuit system is further configured to: tracking movement of a medical device during the cardiac catheterization procedure; and Based on the tracked motion and the imaging data, a representation of the motion of the medical device is output for display during the cardiac catheterization procedure.

6. The medical system of claim 5, wherein: The processing circuitry is further configured to determine whether at least a portion of the cardiac catheterization procedure was successful based on the tracked motion.

7. The medical system according to any one of claims 1 to 5, wherein: The memory is further configured to store at least one machine learning model, and wherein the processing circuitry is further configured to: The at least one machine learning model is executed to guide a clinician during the cardiac catheterization procedure.

8. The medical system of claim 7, wherein: The processing circuitry further outputs guidance to the clinician during the cardiac catheterization procedure based on characteristics of the lesion.

9. The medical system of claim 7 or claim 8, wherein: The processing circuitry further outputs guidance to the clinician during the cardiac catheterization procedure based on the clinician's identity.

10. The medical system according to any one of claims 7 to 9, wherein: The processing circuit system is further configured to: An ability of a medical device to traverse the lesion is predicted based at least in part on characteristics of the lesion.

11. The medical system according to any one of claims 7 to 10, wherein: The processing circuitry is further configured to determine whether the medical device has passed through a lesion.

12. The medical system according to any one of claims 7 to 11, wherein: The at least one machine learning model is trained based on data collected from past medical procedures, including at least one of past imaging data, past tracked motion of a medical device, past controller data, or past lesion classifications.

13. The medical system according to any one of claims 1 to 12, wherein: The processing circuit system is further configured to: Receive controller data from the device; processing the controller data to generate a representation of ablated tissue; and The imaging data and the representation of the ablated tissue are output for display.

14. The medical system of claim 13, wherein: The processing circuitry is further configured to apply one or more time stamps to the imaging data and to apply one or more time stamps to at least one of the controller data or the representation of the ablated tissue prior to outputting the imaging data and the representation of the ablated tissue for display, wherein, as part of outputting the imaging data and the representation of the ablated tissue for display, the processing circuitry is configured to: registering the imaging data with the representation of the ablated tissue using one or more time stamps applied to the imaging data and one or more time stamps applied to at least one of the controller data or the representation of the ablated tissue; and A representation of the ablated tissue is superimposed on the imaging data.

15. The medical system of any one of claims 1 to 14, wherein: The processing circuitry is further configured to control the energy generating device to stop delivering energy based on the controller data.

16. The medical system of any one of claims 1-14, wherein: The processing circuitry is further configured to control an automated contrast media delivery device to adjust a contrast media delivery rate to a patient based on at least one of a quality of the imaging data or in response to the patient's tolerance of the contrast media.

17. A method comprising: receiving, by processing circuitry, imaging data of at least a portion of a patient's vasculature generated during a cardiac catheterization procedure; as well as At least one computer vision model is executed by the processing circuitry to determine characteristics of a lesion in the vasculature based on the received imaging data.

18. A non-transitory computer-readable storage medium storing instructions that, when executed, cause a processing circuit system to: receiving imaging data of at least a portion of a patient's vasculature generated during a cardiac catheterization procedure; and At least one computer vision model is executed to determine characteristics of a lesion in the vasculature based on the received imaging data.

Images