System and method of determining preferred treatment of pulmonary embolism using thrombolytic agent

Abstract

A system for determining a preferred treatment for a pulmonary embolism. The system includes memory and a processor configured to obtain imaging data of a pulmonary embolism in a pulmonary vasculature of a patient; generate a patient specific vasculature model of the pulmonary vasculature using the imaging data; generate a predictive computational model of blood flow through the pulmonary vasculature using the patient specific vasculature model; extend the predictive computation model by applying emboli treatment models for different emboli treatment scenarios to the predictive computation model; predict outcome metrics regarding treatment of the pulmonary embolism using the extended predictive computation model, the outcome metrics indicating breakup or dissolution of the pulmonary embolism; and select a treatment scenario based on the predicted outcome metrics for treating the pulmonary embolism.

Description

SYSTEM AND METHOD OF DETERMINING PREFERRED TREATMENT OF PUEMONARY EMBOEISM USING THROMBOEYTIC AGENTBACKGROUND

[0001] Pulmonary embolism (PE) is the third most common cause of cardiovascular death in the United States, and one of the most common causes of death worldwide. Many patients die within the first few hours of presentation, making an early diagnosis and treatment paramount to survival.

[0002] Diagnosis of PE is often performed or confirmed using computed tomography pulmonary angiography (CTPA), in which a three-dimensional (3D) visualization of pulmonary arteries is created. Treatment options include surgical embolectomy, thrombolytic therapy, and catheterbased treatments, such as mechanical embolectomy or more commonly ultrasound fragmentation of the thrombus combined with in situ reduced-dose catheter directed thrombolysis (CDT), for example. Though thrombolytic agent is administered locally during CDT, there is a risk of systemic effects of thrombolysis therapy, including severe bleeding. Therefore, the main contraindication to CDT is a high risk of extracranial and intracranial bleeding.

[0003] Currently, though, there is no automated technical process that reliably and objectively predicts outcomes of various available treatments, and then selects or aids in selection of a preferred treatment based on such predicted outcomes. Rather, determination of the type of treatment is largely subjective, and may vary greatly based on experience and training of individual physicians involved.SUMMARY

[0004] In a representative embodiment, a method is provided for determining a treatment for a pulmonary embolism is a patient. The method includes: obtaining imaging data of the pulmonary embolism within a pulmonary vasculature of the patient; generating a patient specific vasculature model of the pulmonary vasculature based on the imaging data, wherein the patient specific vasculature model includes at least one of a location of the pulmonary embolism within the pulmonary vasculature or a representation of the pulmonary embolism within the pulmonaryvasculature; generating a predictive computational model of blood flow through the pulmonary vasculature using the patient specific vasculature model and the patient data; extending the predictive computation model by applying emboli treatment models for different emboli treatment scenarios to the predictive computation model; predicting outcome metrics regarding treatment of the pulmonary embolism using the extended predictive computation model; and selecting a treatment scenario from the different emboli treatment scenarios based on the predicted outcome metrics for performing the treatment of the pulmonary embolism.

[0005] In another representative embodiment, a system is provided for determining a treatment for a pulmonary embolism is a patient. The system includes a processor in communication with memory. The processor is configured to: obtain imaging data of the pulmonary embolism within a pulmonary vasculature of the patient; generate a patient specific vasculature model of the pulmonary vasculature using the imaging data, wherein the patient specific vasculature model includes at least one of a location of the pulmonary embolism within the pulmonary vasculature or a representation of the pulmonary embolism within the pulmonary vasculature; generate a predictive computational model of blood flow through the pulmonary vasculature using the patient specific vasculature model; extend the predictive computation model by applying emboli treatment models for different emboli treatment scenarios to the predictive computation model; predict outcome metrics regarding treatment of the pulmonary embolism using the extended predictive computation model; and select a treatment scenario from the different emboli treatment scenarios based on the predicted outcome metrics for performing the treatment of the pulmonary embolism.

[0006] In another representative embodiment, a non-transitory computer readable medium has stored instructions for determining a treatment for a pulmonary embolism in a patient. The instructions, when executed by a processor, cause the processor to: obtain imaging data of the pulmonary embolism within a pulmonary vasculature of the patient; generate a patient specific vasculature model of the pulmonary vasculature using the imaging data, wherein the patient specific vasculature model includes at least one of a location of the pulmonary embolism within the pulmonary vasculature or a representation of the pulmonary embolism within the pulmonary vasculature; generate a predictive computational model of blood flow through the pulmonary vasculature using the patient specific vasculature model; extend the predictive computationmodel by applying emboli treatment models for different emboli treatment scenarios to the predictive computation model; predict outcome metrics regarding treatment of the pulmonary embolism using the extended predictive computation model; and select a treatment scenario from the different emboli treatment scenarios based on the predicted outcome metrics for performing the treatment of the pulmonary embolism.

[0007] In another representative embodiment, a method is provided for determining a preferred treatment of a pulmonary embolism in a patient using a thrombolytic agent. The method includes receiving imaging data of pulmonary vasculature of the patient, the imaging data showing the pulmonary embolism within the pulmonary vasculature; receiving patient data of the patient, the patient data including at least one vital sign and at least one element of medical history of the patient; creating a patient specific (parametric) vasculature model of the pulmonary vasculature using the imaging data, where the patient specific vasculature model includes a location or a representation of the pulmonary embolism within the pulmonary vasculature; providing a predictive computational model of blood flow through the pulmonary vasculature using the patient specific vasculature model and the patient data; predicting outcome metrics regarding treatment of the pulmonary embolism by extending the predictive computational model with catheter directed thrombolysis emboli treatment models for different treatment scenarios, respectively, where the predicted outcome metrics indicate at least one of breakup or dissolution of the pulmonary embolism within the pulmonary vasculature, and where each emboli treatment model includes parameters affecting dynamics of embolism behavior in response to the thrombolytic agent; selecting a preferred treatment scenario from the different treatment scenarios based on the predicted outcome metrics from the corresponding emboli treatment models; and performing treatment of the pulmonary embolism using the preferred treatment scenario.

[0008] In another representative embodiment, a system is provided for determining a preferred treatment of a pulmonary embolism in a patient using a thrombolytic agent. The system includes a display; a processor coupled to the display; and a non-transitory memory storing instructions. When executed by the processor, the instructions cause the processor to receive imaging data of pulmonary vasculature of the patient, the imaging data showing the pulmonary embolism within the pulmonary vasculature; receive patient data of the patient, the patient data including at leastone vital sign and at least one element of medical history of the patient; create a patient specific vasculature model of the pulmonary vasculature using the imaging data, where the patient specific vasculature model includes a location or a representation of the pulmonary embolism within the pulmonary vasculature; provide a predictive computational model of blood flow through the pulmonary vasculature using the patient specific vasculature model and the patient data; predict outcome metrics regarding treatment of the pulmonary embolism by extending the predictive computational model with emboli treatment models for different treatment scenarios, respectively, where the predicted outcome metrics indicate at least one of breakup or dissolution of the pulmonary embolism within the pulmonary vasculature, and where each emboli treatment model includes parameters affecting dynamics of embolism behavior in response to the thrombolytic agent; select a preferred treatment scenario from the different treatment scenarios based on the predicted outcome metrics from the corresponding emboli treatment models for performing treatment of the pulmonary embolism.

[0009] In another representative embodiment, a non-transitory computer readable medium stores instructions for determining a preferred treatment of a pulmonary embolism in a patient using a thrombolytic agent. When executed by a processor, the instructions cause the processor to receive imaging data of pulmonary vasculature of the patient, the imaging data showing the pulmonary embolism within the pulmonary vasculature; receive patient data of the patient, the patient data including at least one vital sign and at least one element of medical history of the patient; create a patient specific vasculature model of the pulmonary vasculature using the imaging data, where the patient specific vasculature model includes a location or a representation of the pulmonary embolism within the pulmonary vasculature; provide a predictive computational model of blood flow through the pulmonary vasculature using the patient specific vasculature model and the patient data; predict outcome metrics regarding treatment of the pulmonary embolism by extending the predictive computational model with emboli treatment models for different treatment scenarios, respectively, where the predicted outcome metrics indicate at least one of breakup or dissolution of the pulmonary embolism within the pulmonary vasculature, and where each emboli treatment model includes parameters affecting dynamics of embolism behavior in response to the thrombolytic agent; and select a preferred treatment scenario from the different treatment scenarios based on the predicted outcome metrics from thecorresponding emboli treatment models for performing treatment of the pulmonary embolism.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The example embodiments are best understood from the following detailed description when read with the accompanying drawing figures. It is emphasized that the various features are not necessarily drawn to scale. In fact, the dimensions may be arbitrarily increased or decreased for clarity of discussion. Wherever applicable and practical, like reference numerals refer to like elements.

[0011] FIG. 1 is a simplified block diagram of a system for determining a preferred treatment of a pulmonary embolism in a patient using a thrombolytic agent, according to a representative embodiment.

[0012] FIG. 2 is an example of multiple pulmonary emboli in lungs of a patient for which a preferred treatment scenario is to be determined, according to a representative embodiment.

[0013] FIG. 3 is a graph showing an example of a visualization of outcome metrics of treatment scenarios involving multiple pulmonary emboli for which a preferred treatment scenario is to be determined, according to a representative embodiment.

[0014] FIG. 4 is a flow diagram showing a method of determining a preferred treatment of a pulmonary embolism in a patient using a thrombolytic agent, according to a representative embodiment.DETAILED DESCRIPTION

[0015] In the following detailed description, for the purposes of explanation and not limitation, representative embodiments disclosing specific details are set forth in order to provide a thorough understanding of an embodiment according to the present teachings. Descriptions of known systems, devices, materials, methods of operation and methods of manufacture may be omitted so as to avoid obscuring the description of the representative embodiments. Nonetheless, systems, devices, materials and methods that are within the purview of one of ordinary skill in the art are within the scope of the present teachings and may be used in accordance with the representative embodiments. It is to be understood that the terminology used herein is for purposes of describing particular embodiments only and is not intended to be limiting. Thedefined terms are in addition to the technical and scientific meanings of the defined terms as commonly understood and accepted in the technical field of the present teachings.

[0016] It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements or components, these elements or components should not be limited by these terms. These terms are only used to distinguish one element or component from another element or component. Thus, a first element or component discussed below could be termed a second element or component without departing from the teachings of the inventive concept.

[0017] The terminology used herein is for purposes of describing particular embodiments only and is not intended to be limiting. As used in the specification and appended claims, the singular forms of terms “a,” “an” and “the” are intended to include both singular and plural forms, unless the context clearly dictates otherwise. Additionally, the terms “comprises,” “comprising,” and / or similar terms specify the presence of stated features, elements, and / or components, but do not preclude the presence or addition of one or more other features, elements, components, and / or groups thereof. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items.

[0018] Unless otherwise noted, when an element or component is said to be “connected to,” “coupled to,” or “adjacent to” another element or component, it will be understood that the element or component can be directly connected or coupled to the other element or component, or intervening elements or components may be present. That is, these and similar terms encompass cases where one or more intermediate elements or components may be employed to connect two elements or components. However, when an element or component is said to be “directly connected” to another element or component, this encompasses only cases where the two elements or components are connected to each other without any intermediate or intervening elements or components.

[0019] The present disclosure, through one or more of its various aspects, embodiments and / or specific features or sub-components, is thus intended to bring out one or more of the advantages as specifically noted below. For purposes of explanation and not limitation, example embodiments disclosing specific details are set forth in order to provide a thorough understanding of an embodiment according to the present teachings. However, other embodiments consistent with the present disclosure that depart from specific details disclosedherein remain within the scope of the appended claims. Moreover, descriptions of well-known apparatuses and methods may be omitted so as to not obscure the description of the example embodiments. Such methods and apparatuses are within the scope of the present disclosure.

[0020] As mentioned above, the systemic use of thrombolytics to treat pulmonary embolism has a high risk of severe bleeding. This risk may be mitigated by employing catheter-directed treatment where more focused treatment allows for a lower dose of the thrombolytic agent to be applied. Even so, the risk of bleeding remains high.

[0021] To address the issues arising from the systemic use of thrombolytics, the various embodiments described herein generally provide an objective, software based system and method for automatically determining a preferred treatment and corresponding therapy for a pulmonary embolism in a patient using a thrombolytic agent, allowing for further reduction of the thrombolytic dose and / or a more optimal delivery rate of the thrombolytic dose. This is accomplished by employing personalized predictive modeling of the treatment with the specific patient in mind relying on knowledge of the process dynamics of the thrombolytic treatment and / or current and historic data regarding patients and levels of success of previous thrombolytic agent treatments. For example, modeling may be based in part on lab tests of thrombolytic agents dissolving artificial or real clots. The personalized predictive modeling includes the hemodynamics of the patient’s pulmonary arteries, resulting in a more optimal treatment scenario, including optimal delivery location and dose for the thrombolytic agent and treatment time.

[0022] FIG. 1 is a simplified block diagram of a system for determining a preferred treatment of a pulmonary embolism in a patient using a thrombolytic agent, according to a representative embodiment.

[0023] Referring to FIG. 1, system 100 includes a workstation 105 for implementing and / or managing the processes described herein with regard to determining a preferred treatment of a pulmonary embolism in a patient using a thrombolytic agent and patient-specific characteristics. The workstation 105 includes one or more processors indicated by processor 120, one or more memories indicated by memory 130, a user interface 122 and a display 124. The processor 120 communicates with the medical imaging system 140 through a known imaging interface (not shown). The medical imaging system 140 is operable by a user (e.g., technician, physician) toobtain medical imaging data from images of a region of interest 155 of a patient (subject) 150. Optionally, the processor 120 communicates with a medical monitoring system 141 to receive pre- or peri-interventional information on the patient 150, such as blood pressure, heart rate, and / or blood oxygenation. The medical monitoring system 141 may collect information continuously or at discrete times. Since the system 100 addresses treatment of a pulmonary embolism, the region of interest 155 is in one of the patient’s lungs. The medical imaging system 140 may be any type of compatible imaging or sensing system, such as computerized tomography (CT), magnetic resonance imaging (MRI), magnetic resonance angiography (MRA), X-ray, ultrasound, or scintigraphy, for example.

[0024] The memory 130 stores instructions executable by the processor 120. When executed, the instructions cause the processor 120 to implement one or more processes for determining a preferred treatment of a pulmonary embolism in the patient 150. The processor 120 is representative of one or more processing devices, and may be implemented by a general purpose computer, a central processing unit (CPU), a digital signal processor (DSP), a graphical processing unit, a computer processor, a microprocessor, a state machine, programmable logic device, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), or combinations thereof, using any combination of hardware, software, firmware, hardwired logic circuits, or combinations thereof. Any processor or processing unit herein may include multiple processors, parallel processors, or both. Multiple processors may be included in, or coupled to, a single device or multiple devices. The term “processor” as used herein encompasses an electronic component able to execute a program or machine executable instruction. A processor may also refer to a collection of processors within a single computer system or distributed among multiple computer systems, such as in a cloud-based or other multisite application. Programs have software instructions performed by one or multiple processors that may be within the same computing device or which may be distributed across multiple computing devices.

[0025] The memory 130 may include main memory and / or static memory, where such memories may communicate with each other and the processor 120 via one or more buses. The memory 130 may be implemented by any number, type and combination of random access memory (RAM) and read-only memory (ROM), for example, and may store various types of information,such as software algorithms, artificial intelligence (Al) machine learning models, and computer programs, all of which are executable by the processor 120. The various types of ROM and RAM may include any number, type and combination of computer readable storage media, such as a disk drive, flash memory, an electrically programmable read-only memory (EPROM), an electrically erasable and programmable read only memory (EEPROM), registers, a hard disk, a removable disk, tape, compact disk read only memory (CD-ROM), digital versatile disk (DVD), floppy disk, Blu-ray disk, a universal serial bus (USB) drive, or any other form of storage medium. The memory 130 is a tangible storage medium for storing data and executable software instructions, and is non-transitory during the time software instructions are stored therein. As used herein, the term “non-transitory” is to be interpreted not as an eternal characteristic of a state, but as a characteristic of a state that will last for a period. The term “non-transitory” specifically disavows fleeting characteristics such as characteristics of a carrier wave or signal or other forms that exist only transitorily in any place at any time. The memory 130 may store software instructions and / or computer readable code that enable performance of various functions. The memory 130 may be secure and / or encrypted, or unsecure and / or unencrypted.

[0026] The system 100 may also include a database 112 for storing information that may be used by the various software modules of the memory 130. For example, the database 112 may include anatomical information of the patient 150 and / or image data from previously obtained ultrasound images of the patient 150 and / or of other similarly situated patients. For example, the database 112 may include an electronic health records (EHR) database. The database 112 may be implemented by any number, type and combination of RAM and ROM, for example. The various types of ROM and RAM may include any number, type and combination of computer readable storage media, such as a disk drive, flash memory, EPROM, EEPROM, registers, a hard disk, a removable disk, tape, CD-ROM, DVD, floppy disk, Blu-ray disk, USB drive, or any other form of storage medium known in the art. The database 112 comprises tangible storage mediums for storing data and executable software instructions and is non-transitory during the time data and software instructions are stored therein. The database 112 may be secure and / or encrypted, or unsecure and / or unencrypted. For purposes of illustration, the database 112 is shown as a separate storage medium, although it is understood that it may be combined with and / or included in the memory 130, without departing from the scope of the present teachings.

[0027] The processor 120 may include or have access to an artificial intelligence (Al) engine, which may be implemented as software that provides artificial intelligence (e.g., neutral network models) and applies machine learning described herein. The Al engine may reside in any of various components in addition to or other than the processor 120, such as the memory 130, an external server, and / or the cloud, for example. When the Al engine is implemented in a cloud, such as at a data center, for example, the Al engine may be connected to the processor 120 via the internet or other communication network using one or more wired and / or wireless connection(s). In various embodiments, all or part of the processes provided by any of the machine learning algorithms, discussed below, may be implemented by the Al engine, for example. Training and execution of these machine learning algorithms cannot be performed in the human mind.

[0028] The user interface 122 is configured to provide information and data output by the processor 120, the memory 130 and / or the medical imaging system 140 to the user and / or for receiving information and data input by the user. That is, the user interface 122 enables the user to enter data and to control or manipulate aspects of the processes described herein, and also enables the processor 120 to indicate the effects of the user’s input. In various embodiments, the user’s input may include control or manipulation of the medical imaging system 140, such as C- arm position commands for a CT imaging system or transducer probe manipulation for an ultrasound imaging system, for example. All or a portion of the user interface 122 may be implemented by a graphical user interface (GUI), such as GUI 128 viewable on the display 124, discussed below. The user interface 122 may include one or more interface devices, such as a mouse, a keyboard, a trackball, a joystick, a microphone, a video camera, a touchpad, a touchscreen, voice or gesture recognition captured by a microphone or video camera, for example.

[0029] The display 124 may be a monitor such as a computer monitor, a television, a liquid crystal display (UCD), an organic light emitting diode (OUED), a flat panel display, a solid-state display, or a cathode ray tube (CRT) display, or an electronic whiteboard, for example. The display 124 includes a screen 126 for viewing ultrasound images of the patient 150, along with various features described herein to communicate to the user the degree of image degradation, if any, as well as the GUI 128 to enable the user to interact with the displayed images and features.In an embodiment, the medical imaging system 140 may include a separate dedicated display for acquiring the ultrasound images, where dedicated display is also represented by the display 124.

[0030] Referring to the memory 130, the various modules store sets of data and instructions executable by the processor 120 to determine a preferred treatment of a pulmonary embolism in the patient 150, as mentioned above. Medical images module 131 of the memory 130 is configured to obtain and process imaging data of the region of interest 155 of the patient 150 acquired by the medical imaging system 140. As mentioned above, the imaging data may be CT, MRI, MRA, X-ray, ultrasound imaging, or scintigraphy, for example. The imaging data shows the region of interest 155, which includes the pulmonary embolism within the pulmonary vasculature of the patient 150. The medical images module 131 may also store data associated with the medical images (metadata), such as time and date of image acquisition and identification of the medical imaging system 140.

[0031] The medical images from the imaging data may be displayed on the display 124. The medical images may be received in real-time or near real-time from the medical imaging system 140, e.g., during a contemporaneous imaging session of the patient 150. The display of real-time images, in particular, enables the operator to visualize the anatomy of the patient 150 while operating the medical imaging system 140. Alternatively, or in addition, the imaging data may be previously acquired images obtained during previous imaging session(s), which have been retrieved from storage (e.g., database 112), as mentioned above.

[0032] Vasculature model module 132 is configured to create or generate a patient-specific (parametric) vasculature model of the pulmonary vasculature using the imaging data from the medical images module 131. The patient specific vasculature model provides the pulmonary vasculature specific to the patient 150 and includes a location of the pulmonary embolism within the pulmonary vasculature. In an embodiment, the patient-specific vasculature model may be zero-dimensional (0D), one-dimensional (ID), two-dimensional (2D) or three-dimensional (3D). The patient-specific vasculature model may be generated solely based on the imaging data from the medical images module 131, or based on a template that is adapted using the acquired medical images. For example, the patient-specific vasculature model may be generated by segmenting the imaging data to identify relevant portions of the patient’s pulmonary vasculature, and then merging the identified portions of the pulmonary vasculature with a templatepulmonary vasculature model.

[0033] Predictive computational model module 133 is configured to provide and / or generate a predictive computational model of blood flow through the pulmonary vasculature using the patient specific vasculature model from the vasculature model module 132 and patient data of the patient 150 received from a database (e.g., database 112) and / or from the medical monitoring system 141. The patient data may include vital signs, such as heart rate, blood pressure, oxygenation levels, right ventricular pressure and volume, and cardiac output, for example. The patient data may also include elements of the patient’s medical history, such as age, sex, weight, history of deep vein thrombosis, medication, hypotension and / or hypertension. In some embodiments, the patient data may also include additional properties required for the predictive computational model, which may be obtained from a database (e.g., database 112) and / or the medical monitoring system 141. The additional properties are not typical medical data, and may be based on population average properties or may be made more specific through techniques such as classification, for example. As an example, average properties of a certain age group or sex may be used to determine additional properties. Generally, the additional properties are more difficult to measure than the typical medical data, such as elasticity of veins that affect compliance of blood vessels, for example. The predictive computational model of blood flow through the pulmonary vasculature is specific to the patient 150 based on the patient data., including the additional properties.

[0034] The predictive computational model predicts one or more of concentration of the thrombolytic agent in the pulmonary vasculature, flow simulation tracking of the thrombolytic agent, speed of thrombolysis, speed of dissolution of the pulmonary embolism, and speed of break-up of the pulmonary embolism, for example. The predictive computational model may be physics-based, analytical or numerical hydrodynamic model, such as a 0D model (i.e., only time dependent without a spatial dimension), ID model, a 2D model or 3D model. The higher order models enable more accurate predictions, but require better and / or more patient data than the lower order models. Analytical and / or numerical emboli treatment models of emboli breakup and / or dissolution, discussed below, are introduced in the predictive computational model based in part on dynamics of clot behavior.

[0035] Emboli treatment model module 134 is configured to provide and / or generate multipleemboli treatment models of different treatment scenarios. Each of the emboli treatment models may be a predetermined analytical model or a numerical model, for example, and includes parameters that are set, e.g., based on measurements or estimates, as would be apparent to one skilled in the art. The parameters generally affect dynamics of embolism behavior in response to the thrombolytic agent. Values of the parameters required for description of the dynamics of clot behavior may be based on measurements derived from the imaging data, or may be estimated based on the patient data and / or the additional properties, for example. These parameter values may also be estimated from a database of clot properties using a classification algorithm or other parameter estimation machine learning algorithm, for example. Alternatively, the parameter values may be provided by the user via the user interface 122. The parameters of each emboli treatment model may include at least a type of the thrombolytic agent, a dose of the thrombolytic agent, a rate of delivery of the thrombolytic agent, a duration of delivery of the thrombolytic agent, and a location of delivery of the thrombolytic agent, for example. The different treatment scenarios of the emboli treatment models may have been generated randomly within a certain solution space, or may have been generated using a specific experimental design.

[0036] In an embodiment, the parameter estimation machine learning algorithm may include linear regression of a dissolution time constant indicating how fast the pulmonary embolism dissolves when exposed to a certain concentration of the thrombolytic agent represented by that emboli treatment model. The parameter estimation machine learning algorithm may be trained in a supervised fashion using peri-interventionally collected data, for example. In an embodiment, the parameter estimation machine learning algorithm may be a convolutional neural network (CNN), an artificial neural network (ANN), a vision transformer, a U-net model, or other type of compatible machine learning algorithm, for example, without departing from the scope of the present teachings.

[0037] Outcome metrics prediction module 135 is configured to predict outcome metrics regarding treatment of the pulmonary embolism by extending the predictive computational model with the emboli treatment models for the different treatment scenarios, respectively, in order for the predictive computational model to predict the outcome metrics. The outcome metrics indicate breakup of the pulmonary embolism and / or dissolution of the pulmonary embolism within the pulmonary vasculature. Examples of outcome metrics may include one ormore of increase of perfused lung volume, increase of amount of oxygenation, reduction of right ventricular dilation, reduction of pulmonary hypertension, reduction of right heart pressure, reduction of diffusion capacity of lungs for carbon monoxide (CO), and reduction of clot burden, for example. The increase of the perfused lung volume may be determined after a certain clot has dissolved, and the amount of increased oxygenation may be determined by including appropriate numerical or analytical models or by simply correlating oxygenation with available lung volume, for example. Alternative and / or additional outcome metrics may be applied without departing from the scope of the present teachings.

[0038] Treatment selection module 136 is configured to select or recommend a preferred treatment scenario from the different treatment scenarios based on the predicted outcome metrics corresponding to emboli treatment models applied to the predictive computational model. The preferred treatment scenario is selected or recommended by the treatment selection module 136 using an optimization algorithm operating on the outcome metrics from the predictive computational model. For each treatment scenario, the predictive computational model predicts changes in the blood flow because of dissolution and / or breakup of clots and other physiological changes of the patient due to the assumed treatment and updates the associated outcome metrics. In an embodiment, the optimization algorithm accepts / receives these outcome metrics associated with the different treatment scenarios, and assigns weights to the outcome metrics in order to select the preferred treatment scenario, where the preferred treatment scenario optimizes a weighted score of the outcome metrics. The weights may be predefined or may be supplied by the user. For example, when improvement of oxygenation and volume of thrombolytic agent are outcome metrics, then depending on the weight factors, the preferred treatment will be closer to or further from 100 percent oxygenation. The optimization algorithm may be implemented as a gradient decent method, for example.

[0039] Alternatively or in addition, the optimization algorithm may select the preferred treatment scenario based on various criteria. For example, the preferred treatment scenario may be the treatment scenario using the lowest dose of thrombolytic agent, while delivering the (at least minimal acceptable) desired outcome. Or, the preferred treatment scenario may be the treatment scenario requiring the least amount of time to reach a certain outcome. Of course, other criteria for selecting the preferred treatment scenario may be applied without departing from the scope ofthe present teachings.

[0040] The selected or recommended preferred treatment scenario may be approved by the user (e.g., the treating physician) and performed on the patient 150. In an embodiment, progress of the treatment may be monitored, e.g., by the processor 120, and the results of the monitoring may be provided to the predictive computational model module 133, which updates the predictive computational model accordingly. For example, the vital signs from the patient data may improve at a faster or slower rate than anticipated, requiring adjustments to the preferred treatment scenario.

[0041] Predicting the outcome metrics and modeling the treatment scenarios may include the type and location of endovascular devices to be used for drug delivery in the intended treatment scenarios. In a basic embodiment, information about treatment devices may be provided as input from the treating physician via the user interface 122. The optimization algorithm used for treatment selection may compare results from treatment scenarios with different input in the same patient. Given enough time and computational resources, predictive results may be computed for many treatment scenarios in the same patient in an effort to find the optimal one. These treatment scenarios may be generated randomly, within a predetermined solution space, e.g., Monte Carlo simulation, or by using a statistical experimental design. The results may be used to further optimize the treatment plan for the pulmonary embolism using the preferred treatment scenario, for example, through response surface modeling, as would be apparent to one skilled in the art.

[0042] FIG. 2 is an example of multiple pulmonary emboli (clot burden) in lungs of a patient for which a preferred treatment scenario is to be determined, according to a representative embodiment. Referring to FIG. 2, bronchi 210 are shown in lungs 200 of the patient 150 with three pulmonary emboli (clots), including first embolism 221 in secondary bronchi 211, second embolism 222 in tertiary bronchi 212, and third embolism 223 in secondary bronchi 216. FIG 2 also shows various illustrative positions within the bronchi 210 where a distal end of a catheter (not shown) may be placed for performing catheter directed thrombolysis (CDT) of the pulmonary emboli. In particular, position A is in the secondary bronchi 211 near the first embolism 221, position B is in the tertiary bronchi 212 near the second embolism 222, position C is in the trachea 213, position D is in a primary bronchi 214 adjacent to position A, position E isin a secondary bronchi 215 adjacent to position B, and position F is in the secondary bronchi 216 near the third embolism 223.

[0043] In different treatment scenarios, corresponding treatment options are considered. For example, for each location of the catheter as depicted in FIG. 2, the predictive computational model may be used to calculate the outcome metrics for a certain dosing rate and duration. Table 1 shows an example of a summary of the results for different treatment scenarios corresponding to the positions A-F, where two different thrombolytic dosage rates are applied at position F (indicated as Fl and F2). For purposes of discussion, Outcome Metric 1 is increase of perfused lung volume, Outcome Metric 2 is reduction of pulmonary hypertension, and Outcome Metric 3 is reduction of right heart pressure.Table 1

[0044] Based on patient-specific conditions of the patient 150 in the example depicted in FIG. 2 and Table 1, the preferred treatment scenario may be selected. For example, for the patient 150, it may be assumed that a target improvement of Outcome Metric 1 is at least -30 percent, while the amount of thrombolytic dose is to be minimal. Therefore, only positions C, Fl and F2 may be considered based on the Outcome Metric 1. Of these three positions, position Fl uses the smallest thrombolytic dose amount. Therefore, the treatment scenario is selected that includes positioning the distal end of the catheter at position Fl and using the corresponding thrombolytic dose criteria.

[0045] The treatment scenarios may also consist of multi-site thrombolysis, where thrombolysisis performed either consecutively or simultaneously at different positions for one treatment scenario. For example, as shown in Table 2, a first treatment scenario for catheter directed thrombolysis may be performed by placing the catheter in position F near the third embolism 223, followed by moving the catheter to position B near the second embolism 222. A second treatment scenario may be performed by placing the catheter in position A near the first embolism 221, followed by moving the catheter to position B near the second embolism 222.Table 2

[0046] The predictive computational model may be used to predict the improvement over time of dissolving / breaking up the third embolism 223 at position F followed by the second embolism 222 at position B, and to calculate the duration required to dissolve the third and second embolisms 223 and 222 in that order at a certain dose of a certain thrombolytic agent. Likewise, the predictive computational model may be used to predict the improvement over time of dissolving / breaking up the first embolism 221 at position A followed by the second embolism 222 at position B, and to calculate the duration required to dissolve the first and second embolisms 221 and 222 in that order at a certain dose of a certain thrombolytic agent.

[0047] FIG. 3 is a graph showing an example of a visualization (display) of outcome metrics of treatment scenarios involving multiple pulmonary emboli for which a preferred treatment scenario is to be determined, according to a representative embodiment. Referring to FIG. 3, graph 300 shows the improvement of Outcome Metric 1 over time, where the target improvement is assumed to be at least 25 percent and minimal duration, for purpose of illustration. Trace 310 shows the predicted improvement of Outcome Metric 1 according to the first treatment scenario (positions F / B) and trace 320 shows the predicted improvement of Outcome Metric 1 according to the second treatment scenario (positions A / B). As can be seen, both of the traces 310 and 320 meet the 25 percent target improvement of Outcome Metric 1, while trace 320 depicts the shorter duration. Therefore, in the depicted example, the treatmentscenario involving moving the catheter from position A to position B to perform the thrombolysis would be selected.

[0048] Other treatment scenarios may include reversing the order in which the two emboli are treated, or treating both emboli simultaneously with two catheters. In yet another treatment scenario, a single catheter may be placed at position C to perform thrombolysis of the first, second and third emboli 221, 222 and 223 substantially simultaneously.

[0049] FIG. 4 is a flow diagram showing a method of determining a preferred treatment of a pulmonary embolism in a patient using a thrombolytic agent depending on characteristics of the patient, according to a representative embodiment. The method may be implemented at least in part using instructions stored in memory 130 and executable by the processor 120 in the system 100, for example.

[0050] Referring to FIG. 4, imaging data of pulmonary vasculature of the patient is received in block S411. The imaging data is acquired by a medical imaging device, and may be received directly from the medical imaging device, e.g., during patient examinations, or may be received from a database of previously acquired images. The medical imaging device may be any type of compatible imaging or sensing, such as CT, MRI, MRA, X-ray, ultrasound imaging, or scintigraphy, for example.

[0051] In block S412, patient data is received from one or more patient databases, such as an EHR database, for example. The patient data may include one or more vital signs and one or more elements of medical history of the patient, for example.

[0052] In block S413, a patient specific vasculature model of the pulmonary vasculature is created or generated using the imaging data from block S411. The patient specific vasculature model shows the location of the pulmonary embolism within the pulmonary vasculature of the patient.

[0053] In block S414, a predictive computational model of blood flow through the pulmonary vasculature is provided and / or generated using the patient specific vasculature model from block S413 and the patient data from block S412. The predictive computational model includes model parameters.

[0054] In block S415, outcome metrics regarding treatment of the pulmonary embolism are predicted by extending the predictive computational model with emboli treatment models fordifferent treatment scenarios. The predicted outcome metrics indicate breakup of the pulmonary embolism and / or dissolution of the pulmonary embolism within the pulmonary vasculature.

[0055] In block S416, a preferred treatment scenario is selected from the different treatment scenarios based on the predicted outcome metrics from the corresponding emboli treatment models. The preferred treatment scenario may be selected by the user or automatically by a treatment selection optimization algorithm based on various criteria to reach a desired outcome. Selecting the preferred treatment scenario may include determining, for example, which treatment scenario uses the lowest dose of the thrombolytic agent to deliver the desired outcome, or determining which treatment scenario requires the shortest amount of time to deliver the desired outcome.

[0056] In an embodiment, the optimization algorithm may select the preferred treatment scenario from the different treatment scenarios through multi- objective optimization. Using linear scalarization, for example, three different outcome metrics may be considered, including perfused lung volume, pulmonary pressure, and administered volume of thrombolytic agent. The outcome metrics are scored on a range of 0 to 100 with 100 being the ideal target outcome, i.e., total perfusion, ideal pressure and a minimum amount of thrombolytic agent known or expected not to have adverse effects on the patient. Weights may be assigned to these scores such that their weighted sum may be maximized, and the preferred treatment scenario is the one determined to have the maximum weighted sum. For example, using respective weights of 0.2, 0.4 and 0.4, the weighted sum of respective scores 70, 50 and 80 from a particular treatment scenario becomes 0.2*70+0.4*50+0.4*80 = 66, which is compared to weighted sums of the other treatment scenarios to find the greatest weighted sum.

[0057] In block S417, treatment of the pulmonary embolism is performed using the preferred treatment scenario. The preferred treatment scenario may include the location where the treatment is to be applied, the type of thrombolytic agent to be used, the dosage of the thrombolytic agent, and the treatment time, for example. In an embodiment, the application of the preferred treatment scenario may be monitored, and feedback from the monitoring is provided to the predictive computational model, which is updated accordingly, as discussed below. The predictive computational model may be updated using a simple machine learning algorithm, such as a linear regression to fit a parameter, for example, to adapt and optimizetreatment plan by fine tuning parameters, such as diffusion rate and clot dissolving speed. For example, the dissipation rate of the clot to determine treatment time and dose may be based on measurements of the clot dissolving or measurements of the defined and predicted outcome metrics.

[0058] Optionally, following the prediction of outcome metrics in block S415, additional treatment scenarios may be generated in block S418 to further optimize the outcome. The additional treatment scenarios may be generated based on the predicted outcome metrics of the different treatment scenarios. For example, based on N preferred treatment scenarios found, additional treatment scenarios may be defined in between adjacent pairs of the N preferred treatment scenarios. The process returns to block S415, such that additional outcome metrics regarding the treatment of the pulmonary embolism are generated by extending the predictive computational model with emboli treatment models of the additional treatment scenarios for different treatment scenarios, respectively. The preferred treatment scenario may then be selected from the additional treatment scenarios in block S415 based on the predicted additional outcome metrics from the corresponding emboli treatment models.

[0059] Further, optionally, the method may include monitoring the progress of the treatment of the patient according to the preferred treatment scenario in block S419 during the treatment of the pulmonary embolism. For example, the progression of the actual breakup and / or dissolution of the pulmonary embolism may be measured during the treatment. The results of the monitoring (e.g., measurements) are provided to block S414 where the predictive computational model of the blood flow through the pulmonary vasculature is updated accordingly. The outcome metrics are predicted in block S415 using the updated predictive computational model for different treatment scenarios, and another preferred treatment scenario is selected from the different treatment scenarios in block S416. The current preferred treatment scenario may then be adapted based on this preferred treatment scenario (which is essentially an adapted version of the initial preferred treatment scenario). That is, the predicted outcome metrics regarding treatment of the pulmonary embolism are updated by respectively applying the emboli treatment models of different treatment scenarios to the updated predictive computational model in block S415, an adapted preferred treatment scenario is selected from the different treatment scenarios based on the updated predicted outcome metrics in block S416, and the adapted preferred treatmentscenario is implemented for treatment of the pulmonary embolism in block S417.

[0060] In accordance with various embodiments of the present disclosure, the methods described herein may be implemented using a hardware computer system that executes software programs stored on non-transitory storage mediums. Further, in an exemplary, non-limited embodiment, implementations can include distributed processing, component / object distributed processing, and parallel processing. Virtual computer system processing may implement one or more of the methods or functionalities as described herein, and a processor described herein may be used to support a virtual processing environment.

[0061] Although evaluating quality of an ultrasound imaging system has been described with reference to exemplary embodiments, it is understood that the words that have been used are words of description and illustration, rather than words of limitation. Changes may be made within the purview of the appended claims, as presently stated and as amended, without departing from the scope and spirit of the embodiments. Also, although evaluating quality of an ultrasound imaging system has been described with reference to particular means, materials and embodiments, it is not intended to be limited to the particulars disclosed; rather evaluating quality of an ultrasound imaging system extends to all functionally equivalent structures, methods, and uses such as are within the scope of the appended claims.

[0062] The illustrations of the embodiments described herein are intended to provide a general understanding of the structure of the various embodiments. The illustrations are not intended to serve as a complete description of all of the elements and features of the disclosure described herein. Many other embodiments may be apparent to those of skill in the art upon reviewing the disclosure. Other embodiments may be utilized and derived from the disclosure, such that structural and logical substitutions and changes may be made without departing from the scope of the disclosure. Additionally, the illustrations are merely representational and may not be drawn to scale. Certain proportions within the illustrations may be exaggerated, while other proportions may be minimized. Accordingly, the disclosure and the figures are to be regarded as illustrative rather than restrictive.

[0063] One or more embodiments of the disclosure may be referred to herein, individually and / or collectively, by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any particular invention or inventive concept.Moreover, although specific embodiments have been illustrated and described herein, it should be appreciated that any subsequent arrangement designed to achieve the same or similar purpose may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all subsequent adaptations or variations of various embodiments. Combinations of the above embodiments, and other embodiments not specifically described herein, will be apparent to those of skill in the art upon reviewing the description.

[0064] The Abstract of the Disclosure is provided to comply with 37 C.F.R. § 1.72(b) and is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, various features may be grouped together or described in a single embodiment for the purpose of streamlining the disclosure. This disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter may be directed to less than all of the features of any of the disclosed embodiments. Thus, the following claims are incorporated into the Detailed Description, with each claim standing on its own as defining separately claimed subject matter.

[0065] The preceding description of the disclosed embodiments is provided to enable any person skilled in the art to practice the concepts described in the present disclosure. As such, the above disclosed subject matter is to be considered illustrative, and not restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other embodiments which fall within the true spirit and scope of the present disclosure. Thus, to the maximum extent allowed by law, the scope of the present disclosure is to be determined by the broadest permissible interpretation of the following claims and their equivalents and shall not be restricted or limited by the foregoing detailed description. 1

Claims

CLAIMS:

1. A method for determining a treatment for a pulmonary embolism in a patient, the method comprising: obtaining imaging data of the pulmonary embolism within a pulmonary vasculature of the patient; generating a patient specific vasculature model of the pulmonary vasculature based on the imaging data, wherein the patient specific vasculature model includes at least one of a location of the pulmonary embolism within the pulmonary vasculature or a representation of the pulmonary embolism within the pulmonary vasculature; generating a predictive computational model of blood flow through the pulmonary vasculature using the patient specific vasculature model and the patient data; extending the predictive computation model by applying emboli treatment models for different emboli treatment scenarios to the predictive computation model; predicting outcome metrics regarding treatment of the pulmonary embolism using the extended predictive computation model; and selecting a treatment scenario from the different emboli treatment scenarios based on the predicted outcome metrics for performing the treatment of the pulmonary embolism.

2. The method of claim 1 , wherein the predicted outcome metrics indicate at least one of breakup of the pulmonary embolism within the pulmonary vasculature or dissolution of the pulmonary embolism within the pulmonary vasculature.

3. The method of claim 1, further comprising: generating additional treatment scenarios based on the predicted outcome metrics; predicting additional outcome metrics regarding the treatment of the pulmonary embolism by applying emboli treatment models of the additional treatment scenarios to the predictive computational model; and selecting the treatment scenario from the additional treatment scenarios based on the predicted additional outcome metrics.

4. The method of claim 1, wherein the parameters of each emboli treatment model include at least one of a type of the thrombolytic agent, a dose of the thrombolytic agent, a rate of delivery of the thrombolytic agent, a duration of delivery of the thrombolytic agent, or a location of delivery of the thrombolytic agent.

5. The method of claim 1, wherein the predicted outcome metrics comprise at least one of increase of perfused lung volume, increase of amount of oxygenation, reduction of right ventricular dilation, reduction of pulmonary hypertension, reduction of right heart pressure, reduction of diffusion capacity of lungs for carbon monoxide (CO), or reduction of clot burden.

6. The method of claim 1, further comprising: measuring progression of at least one of breakup of the pulmonary embolism during the treatment of the pulmonary embolism or dissolution of the pulmonary embolism during the treatment of the pulmonary embolism; updating model parameters of the predictive computational model based on the measured progression; and adapting the selected treatment scenario based on the updated model parameters.

7. The method of claim 1 , wherein the predictive computational model predicts at least one of concentration of the thrombolytic agent in the pulmonary vasculature, flow simulation tracking of the thrombolytic agent, speed of thrombolysis, speed of dissolution of the pulmonary embolism, or speed of break-up of the pulmonary embolism.

8. The method of claim 1, wherein generating the patient specific vasculature model comprises segmenting the imaging data.

9. The method of claim 1, further comprising: obtaining patient data of the patient, the patient data including at least one vital sign and at least one element of medical history of the patient; andgenerating the predictive computational model of blood flow through the pulmonary vasculature based on the patient data.

10. The method of claim 1, wherein each emboli treatment model includes parameters affecting dynamics of embolism behavior in response to the thrombolytic agent, and the method further comprising: estimating, using a parameter estimation machine learning algorithm, the parameters affecting the dynamics of embolism behavior for each emboli treatment model based on clot properties.

11. The method of claim 10, wherein the parameter estimation machine learning algorithm comprises a linear regression of a dissolution time constant indicating how fast the pulmonary embolism dissolves when exposed to a certain concentration of the thrombolytic agent.

12. The method of claim 1, wherein selecting the treatment scenario comprises determining which of the different emboli treatment scenarios uses a lowest dose of the thrombolytic agent to deliver a desired outcome.

13. The method of claim 1, wherein selecting the treatment scenario comprises determining which of the different emboli treatment scenarios requires a shortest amount of time to deliver a desired outcome.

14. The method of claim 1, wherein selecting the treatment scenario comprises determining which of the different treatment scenarios optimizes a weighted score of the outcome metrics.

15. A system for determining a treatment for a pulmonary embolism in a patient, the system comprising: a processor in communication with memory, the processor configured to:obtain imaging data of the pulmonary embolism within a pulmonary vasculature of the patient; generate a patient specific vasculature model of the pulmonary vasculature using the imaging data, wherein the patient specific vasculature model includes at least one of a location of the pulmonary embolism within the pulmonary vasculature or a representation of the pulmonary embolism within the pulmonary vasculature; generate a predictive computational model of blood flow through the pulmonary vasculature using the patient specific vasculature model; extend the predictive computation model by applying emboli treatment models for different emboli treatment scenarios to the predictive computation model; predict outcome metrics regarding treatment of the pulmonary embolism using the extended predictive computation model; and select a treatment scenario from the different emboli treatment scenarios based on the predicted outcome metrics for performing the treatment of the pulmonary embolism.

16. The system of claim 15, wherein the imaging data comprises computerized tomography (CT) data, magnetic resonance imaging (MRI) data, magnetic resonance angiography (MRA) data, ultrasound data, or scintigraphy data.

17. The system of claim 15, wherein the processor is further configured to: generate additional treatment scenarios based on the predicted outcome metrics; predict additional outcome metrics regarding the treatment of the pulmonary embolism by applying emboli treatment models of the additional treatment scenarios to the predictive computational model; and select the treatment scenario from the additional treatment scenarios based on the predicted additional outcome metrics.

18. The system of claim 15, wherein the parameters of each emboli treatment model include at least a type of the thrombolytic agent, a dose of the thrombolytic agent, a rate ofdelivery of the thrombolytic agent, a duration of delivery of the thrombolytic agent; and a location of delivery of the thrombolytic agent.

19. The system of claim 15, wherein the predicted outcome metrics comprise at least one of increase of perfused lung volume, increase of amount of oxygenation, reduction of right ventricular dilation, reduction of pulmonary hypertension, reduction of right heart pressure, reduction of diffusion capacity of lungs for carbon monoxide (CO), or reduction of clot burden.

20. A non-transitory computer readable medium having stored instructions for determining a treatment of a pulmonary embolism in a patient, the instructions, when executed by a processor, cause the processor to: obtain imaging data of the pulmonary embolism within a pulmonary vasculature of the patient; generate a patient specific vasculature model of the pulmonary vasculature using the imaging data, wherein the patient specific vasculature model includes at least one of a location of the pulmonary embolism within the pulmonary vasculature or a representation of the pulmonary embolism within the pulmonary vasculature; generate a predictive computational model of blood flow through the pulmonary vasculature using the patient specific vasculature model; extend the predictive computation model by applying emboli treatment models for different emboli treatment scenarios to the predictive computation model; predict outcome metrics regarding treatment of the pulmonary embolism using the extended predictive computation model; and select a treatment scenario from the different treatment scenarios based on the predicted outcome metrics for performing the treatment of the pulmonary embolism.

Images