Identifying medical device for procedure depending on tissue properites

Abstract

A system for selecting a device for performing a medical procedure on a patient includes a processor and memory. The processor is configured to obtain anatomical information of the patient and an imaging feature of tissue in a region of interest of the patient; determine current tissue properties in the region of interest based on the imaging feature; generate a patient-specific computational model of the region of interest based on the anatomical information and the current tissue properties; select candidate devices each associated with a device-specific computational model and a device-tissue interaction model; for each candidate device, generate a patient-specific procedure outcome simulation model by merging the patient-specific computational model and the device-specific computational model for the candidate device, and predict, using the patient-specific procedure outcome simulation model, a procedure outcome; and select the device for performing the medical procedure based on the predicted procedure outcome for each candidate devices.

Description

IDENTIFYING MEDICAE DEVICEFOR PROCEDURE DEPENDING ON TISSUE PROPERITESBACKGROUND

[0001] When a medical procedure is required for a patient, such as surgery or a minimally invasive intervention, choices are made regarding an appropriate plan, including which procedure and devices to use for the patient to obtain the best outcome. Such determinations are currently made based primarily on experience and education of the treating physician, which is a subjective approach.

[0002] Software support tools for recommending and selecting best suited procedures and treatment devices for patients would provide a more objective approach, but such tools are not currently available. Such software support tools would have to rely on knowledge of patientspecific tissue properties (e.g., stiffness), device physics of various devices, and the relevant device-tissue interaction mechanisms.SUMMARY

[0003] In a representative embodiment, a method is provided for selecting a medical device for performing a medical procedure on a patient. The method includes: obtaining anatomical information of the patient and patient imaging data including at least one imaging feature of tissue in a region of interest of the patient; determining one or more current tissue properties in the region of interest based on the at least one imaging feature of the tissue; generating a patientspecific computational model of the region of interest based on the anatomical information and the one or more current tissue properties; selecting a plurality of candidate medical devices for performing the medical procedure, each candidate medical device associated with a devicespecific computational model and a device-tissue interaction model; for each candidate medical device of the selected plurality of candidate medical devices: generating a patient-specific procedure outcome simulation model by merging the patient-specific computational model and the device-specific computational model associated with the candidate medical device, and predicting, using the patient-specific procedure outcome simulation model for the candidatemedical device, a procedure outcome based on an interaction between the one or more current tissue properties and one or more physical properties of the candidate medical device; and selecting at least one candidate medical device of the plurality of candidate medical devices for performing the medical procedure based on the predicted procedure outcome for each of the plurality of candidate medical devices.

[0004] In another representative embodiment, a system for selecting a medical device for performing a medical procedure on a patient. The system includes a processor in communication with memory. The processor is configured to: obtain anatomical information of the patient and patient imaging data including at least one imaging feature of tissue in a region of interest of the patient; determine one or more current tissue properties in the region of interest based on the at least one imaging feature of the tissue; generate a patient-specific computational model of the region of interest based on the anatomical information and the one or more current tissue properties; select a plurality of candidate medical devices for performing the medical procedure, wherein each candidate medical device is associated with a device-specific computational model and a device-tissue interaction model; for each candidate medical device of the selected plurality of candidate medical devices: generate a patient-specific procedure outcome simulation model by merging the patient-specific computational model and the device-specific computational model associated with the candidate medical device, and predict, using the patient-specific procedure outcome simulation model for the candidate medical device, a procedure outcome based on an interaction between the one or more current tissue properties and one or more physical properties of the candidate medical device; and select at least one candidate medical device of the plurality of candidate medical devices for performing the medical procedure based on the predicted procedure outcome for each of the plurality of candidate medical devices.

[0005] In another representative embodiment, a non-transitory computer readable medium has stored instructions for selecting a medical device for performing a medical procedure on a patient. The instructions, when executed by a processor, cause the processor to: obtain anatomical information of the patient and patient imaging data including at least one imaging feature of tissue in a region of interest of the patient; determine one or more current tissue properties in the region of interest based on the at least one imaging feature of the tissue; generate a patient-specific computational model of the region of interest based on the anatomicalinformation and the one or more current tissue properties; select a plurality of candidate medical devices for performing the medical procedure, wherein each candidate medical device is associated with a device-specific computational model and a device-tissue interaction model; for each candidate medical device of the selected plurality of candidate medical devices: generate a patient-specific procedure outcome simulation model by merging the patient-specific computational model and the device-specific computational model associated with the candidate medical device, and predict, using the patient-specific procedure outcome simulation model for the candidate medical device, a procedure outcome based on an interaction between the one or more current tissue properties and one or more physical properties of the candidate medical device; and select at least one candidate medical device of the plurality of candidate medical devices for performing the medical procedure based on the predicted procedure outcome for each of the plurality of candidate medical devices.

[0006] In another representative embodiment, a method is provided for identifying a medical device to be used for a procedure on a patient. The includes receiving patient imaging data acquired by a medical imaging device providing at least one imaging feature of tissue in a region of interest of the patient; receiving patient data including anatomical information of the patient; determining current properties of the tissue in the region of interest of the patient by accessing a first database that stores tissue properties correlated with structural imaging features of tissues from images of the tissues, respectively, determining a most similar structural imaging feature of the structural imaging features of tissues in the first database as compared to the at least one imaging feature of the tissue in the patient imaging data, and identifying tissue properties correlated with the most similar structural imaging feature as the current properties of the tissue; creating a patient-specific computational model of the region of interest combining the anatomical information of the patient and the current properties of the tissue; selecting a subset of devices from devices stored in a second database as candidate devices, where the second database stores physical properties of the devices, device-specific computational models of the devices, and corresponding device-tissue interaction models of the devices in association with the devices, respectively; creating patient-specific procedure outcome simulation models by merging the patient-specific computational model of the region of interest and each of the device-specific computational models of the selected candidate devices to provide mergedcomputational models, and connecting the merged computational models to the corresponding device-tissue interaction, respectively; predicting outcomes of the procedure on the patient using the candidate devices based on determined interactions between the current properties of the tissue and the physical properties of the candidate devices, respectively, using the patientspecific procedure outcome simulation models; and selecting at least one candidate device to be the medical device for performing the procedure on the patient based on the predicted outcomes of the procedure.

[0007] In another representative embodiment, a system for identifying a medical device to be used for a procedure on a patient. 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 patient imaging data acquired by a medical imaging device providing at least one imaging feature of tissue in a region of interest of the patient; receive patient data including anatomical information of the patient; determine current properties of the tissue in the region of interest of the patient by determining a most similar structural imaging feature of stored structural imaging features of tissues from images of the tissues, respectively, as compared to the at least one imaging feature of the tissue in the patient imaging data, and identifying stored tissue properties correlated with the most similar structural imaging feature as the current properties of the tissue; create a patient-specific computational model of the region of interest combining the anatomical information of the patient and the current properties of the tissue; select a subset of the devices from stored devices as candidate devices, where the stored devices are stored in association with corresponding physical properties, device-specific computational models, and device-tissue interaction models, respectively; create patient-specific procedure outcome simulation models by merging the patient-specific computational model and each of the device-specific computational models of the selected candidate devices to provide merged computational models, and connecting the merged computational models to the corresponding device-tissue interaction models, respectively; predict outcomes of the procedure on the patient using the candidate devices based on determined interactions between the current properties of the tissue and the physical properties of the candidate devices, respectively, using the patient-specific procedure outcome simulation models; and select at least one candidate device to be the medical device for performing theprocedure on the patient based on the predicted outcomes of the procedure.

[0008] In another representative embodiment, a non-transitory computer readable medium stores instructions for identifying a medical device to be used for a procedure on a patient. When executed by a processor, the instructions cause the processor to receive patient imaging data acquired by a medical imaging device providing at least one imaging feature of tissue in a region of interest of the patient; receive patient data including anatomical information of the patient; determine current properties of the tissue in the region of interest of the patient by determining a most similar structural imaging feature of stored structural imaging features of tissues from images of the tissues, respectively, as compared to the at least one imaging feature of the tissue in the patient imaging data, and identifying stored tissue properties correlated with the most similar structural imaging feature as the current properties of the tissue; create a patient-specific computational model of the region of interest combining the anatomical information of the patient and the current properties of the tissue; select a subset of the devices from stored devices as candidate devices, where the stored devices are stored in association with corresponding physical properties, device-specific computational models, and device-tissue interaction models, respectively; create patient-specific procedure outcome simulation models by merging the patient-specific computational model and each of the device-specific computational models of the selected candidate devices to provide merged computational models, and connecting the merged computational models to the corresponding device-tissue interaction models, respectively; predict outcomes of the procedure on the patient using the candidate devices based on determined interactions between the current properties of the tissue and the physical properties of the candidate devices, respectively, using the patient-specific procedure outcome simulation models; and select at least one candidate device to be the medical device for performing the procedure on the patient based on the predicted outcomes of the procedure.BRIEF DESCRIPTION OF THE DRAWINGS

[0009] 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 likeelements.

[0010] FIG. 1 is a simplified block diagram of a system for identifying a medical device for a procedure depending on tissue properties of the patient, according to a representative embodiment.

[0011] FIG. 2 is a flow diagram showing a method of identifying a medical device for a procedure depending on tissue properties of the patient, according to a representative embodiment.DETAILED DESCRIPTION

[0012] 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. The defined 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.

[0013] 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.

[0014] 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 notpreclude 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.

[0015] 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.

[0016] 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 disclosed herein 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.

[0017] Generally, the various embodiments described herein provide an objective, software based system and method for automatically determining and recommending a medical device for a medical procedure on a patient depending on tissue properties of the patient and device properties of the medical device. The tissue properties of the patient may be determined using imaging data from medical images of the patient, where the tissue properties are correlated with structural imaging features of the tissues provided by the imaging data. Candidate devices are identified from a database of devices based at least in part on anatomical information of the patient and the current properties of the tissue. A patient-specific computational model and a device-specific computational model of each candidate device are merged to provide mergedcomputational models, and relevant device-tissue interaction models are added to the merged computational models to generate patient-specific procedure outcome simulation models, respectively. Outcomes of the procedure on the patient are predicted for the candidate devices based on determined interactions between the current properties of the tissue and the physical properties of the candidate devices, respectively, using the patient-specific procedure outcome simulation models. One of the candidate devices is selected as the medical device for the procedure based on the predicted outcomes. In addition, a candidate device may be selected based on its ability to reach specific locations for most accurate device delivery and deployment.

[0018] FIG. 1 is a simplified block diagram of a system for determining a medical device for a medical procedure depending on tissue properties of the patient, according to a representative embodiment.

[0019] Referring to FIG. 1, system 100 includes a workstation 105 for implementing and / or managing the processes described herein with regard to determining a medical device for a medical procedure depending on tissue properties of the patient and device properties of the medical device. The medical procedures may include various treatments, therapies, surgeries, and interventions, as well as drug deliveries. 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) to obtain medical imaging data from images of a region of interest 155 of a patient (subject) 150. The medical imaging system 140 may be configured to provide any type of compatible imaging or sensing, such as magnetic resonance imaging (MRI), X-ray imaging, computerized tomography (CT) imaging, ultrasound imaging, intervascular ultrasound (IVUS) imaging, optical coherence tomography, optical shape sensing, dielectric tissue sensing, and optical tissue sensing, for example.

[0020] 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 performing an evaluation of the patient 150 using ultrasound images acquired by the medical imaging system 140. The medical images may be provided from the medical imaging system 140 in real-time or near real-time during an imaging or the scanning procedure, or may be retrieved from storagefollowing the scanning procedure. For purposes of illustration, the memory 130 is shown to include software modules, each of which includes the instructions, executable by the processor 120, corresponding to an associated capability of the system 100.

[0021] 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, hard-wired 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 cloudbased or other multi-site 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.

[0022] 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. Asused 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.

[0023] 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.

[0024] 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., neural 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, forexample. These machine learning algorithms cannot be performed in the human mind.

[0025] 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.

[0026] The display 124 may be a monitor such as a computer monitor, a television, a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid-state display, or a cathode ray tube (CRT) 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.

[0027] Referring to the memory 130, the various modules store sets of data and instructions executable by the processor 120 to identify and / or recommend a medical device for performing a procedure depending on tissue properties of the patient and device properties of the medical device, as mentioned above. Medical image module 131 of the memory 130 is configured to obtain and process imaging data of tissue in the region of interest 155 of the patient 150 acquired by the medical imaging system 140. The imaging data provides at least one imaging feature of the tissue in the region of interest 155. The at least one imaging feature may be a structural imaging feature indicating structure-property correlations detectable from the imaging data. Forexample, properties of a clot shown in the vasculature of the patient 150, such as density, fibrous richness, red blood cell richness, and the like, may be identifiable by texture and shade of the clot as captured by the imaging data. The medical image 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.

[0028] 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.

[0029] Tissue properties module 132 is configured to automatically create or generate a patientspecific computational model of the region of interest 155 by linking structural imaging features in the imaging data with tissue properties of the tissue. The tissue properties module 132 accesses a previously populated tissue properties (first) database 133. The tissue properties database 133 stores tissue properties correlated to structural imaging features of tissues (i.e., structure-property correlations) from historic images. The tissue properties may be precalculated or measured, directly or indirectly. Examples of types of tissue for which properties may be identified include blood vessels, thrombi with different ages / chronicities, clots, calcifications, and lesions. The structural imaging features indicate various conditions of the tissue in the region of interest 155, such as constituents of thrombi, quantity and distribution of the thrombi, and a range of the associated properties, for example. Of course, other types of tissues and / or other conditions indicated by the structural imaging features may be addressed without departing from the scope of the present teachings. The tissue properties database 133 may be updated and extended continually with newly obtained patient scans and tissue properties.

[0030] In an embodiment, the tissue properties module 132 may include a tissue properties machine learning model for determining the tissue properties. The tissue properties machine learning model may be implemented as any suitable type of trainable machine learning model, such as a convolutional neural network (CNN), an artificial neural network (ANN), a visiontransformer, or a U-net model, for example. The tissue properties machine learning model may be trained in a supervised fashion using historic images of the tissues and either measured properties or synthetic data, i.e., precalculated tissue properties of the tissues using physics-based tissue property models to correlate the structural imaging features from the images of the tissues with the precalculated tissue properties. The synthetic data can be created by constructing detailed computational models of the tissue, e.g., including all constituents in various compositions. Using known properties of the separate constituents and their responses captured by physics-based mathematical models, the behavior and properties of the combined tissue can be calculated (e.g., through multi-scale approaches). Additionally, the image characteristics of the combined constituents for the different imaging modalities can be calculated using physicsbased mathematical models.

[0031] Using the tissue properties from the tissue properties database 133, the tissue properties machine learning model of the tissue properties module 132 determines current properties of the tissue in the region of interest 155 of the patient 150. That is, the tissue properties machine learning model determines a most similar structural imaging feature of the structural imaging features of tissues in the tissue properties database 133 as compared to the at least one imaging feature of the tissue in the imaging data received from the medical image module 131. The most similar structural imaging feature may be determined by comparing a combination of features that can be extracted from the imaging data, such as relative brightness of the tissue in the image, visible structural features, non-image patient-specific data such as age, sex, and diet, for example. In an embodiment, a tissue properties machine learning algorithm is used to create the tissue properties machine learning model that captures the data in the tissue properties database 133, so that data may be extracted from the tissue properties machine learning model after it has been trained on the data from the tissue properties database 133. The tissue properties machine learning model may be updated or re-trained when the tissue properties database 133 is further populated with additional data. Generally, a machine learning algorithm may be a procedure that runs on a dataset to recognize patterns and rules, and a machine learning model is the output of the machine learning algorithm. A machine learning model may act like a program that can be run on data to make predictions.

[0032] The tissue properties module 132 then determines the tissue properties correlated with thedetermined most similar structural imaging feature in the tissue properties database 133 as the current properties of the tissue in the region of interest 155. Determining the current properties of the tissue in the region of interest 155 may include interpolating between the correlated tissue properties, for example. The tissue properties module 132 then creates or generates the patientspecific computational model of the region of interest 155 by combining anatomical information of the patient 150, e.g., retrieved from the database 112, and the current properties of the tissue as determined from the tissue properties machine learning model. The anatomical information of the patient 150 and the current properties of the tissue may be combined by creating a geometric model capturing all relevant features of the region of interest 155, assigning parameterized mathematical models describing the response of each of the relevant features to certain stimuli to that feature, and assigning the current properties to each of the relevant features by defining parameters of the parameterized mathematical models. For example, the geometry may include a thickness of a tissue layer, the parameters may include tissue permeability, tissue strength, tissue stiffness, tissue density, etc., the stimuli may include mechanical pressure for example exerted by a catheter on the vessel wall, and the response may be deformation or damage of the tissue. The anatomical information may include vasculature and other anatomical data. The patient-specific computational model may be a physics-based computational model or a machine learning model, A physics-based patient-specific computational model applies predetermined physical relationships to input data, and thus does not require training using historic data in order to obtain predictive results.

[0033] Device properties module 134 is configured to enable selection of one or more candidate devices from among multiple medical devices that may be used for the medical procedure. The device properties module 134 accesses a previously populated device properties (second) database 135. The device properties database 135 stores devices in association with corresponding physical properties of the devices, device-specific computational models of the devices, and relevant device-tissue interaction models, respectively. The device properties may be precalculated or measured, directly or indirectly. The device-specific computational models of the devices may be physics-based computational models that apply predetermined physical relationships, as discussed above, or may be machine learning models. Properties used within the physics-based computational models (e.g., stiffness), for example, may come from precalculated,measured, or machine learning models. The device-tissue interaction models are specific to the devices, and may be mathematical descriptions of relevant interactions, such as mechanical contact or thermal / electrical conductance, discussed further below.

[0034] When the device-specific computational models are machine learning models of the devices, they may be implemented as any suitable type of trainable machine learning algorithm, such as a CNN, an ANN, a vision transformer, or a U-net model, for example. The devicespecific machine learning models may be trained in a supervised fashion using measured properties characterizing the devices and manually annotated outcomes of medical procedures using the devices under various conditions to correlate the measured properties with conditions in which the devices were used. Alternatively or in addition, the device-specific machine learning models may be trained using annotated synthetic data that is created using results of known physics-based computational models of the devices. The physics-based computational models may be used to create the synthetic data in response to various stimuli and / or inputs. The synthetic data may then be used to train the device-specific machine learning models, the use of which speeds up calculations as compared to the physics-based computational models.

[0035] Using the device-specific computational models and the physical properties of the devices from the device properties database 135, the device properties module 134 identifies a subset of the stored devices to be the candidate devices for the medical procedure. That is, the device properties module 134 determines which of the stored devices are intended for the type of medical procedure. A further reduction of the set of candidate devices may be accomplished through manual intervention by the user or by querying a database containing historic procedures involving the candidate devices, and the corresponding outcomes and distinguishing features of these procedures, e.g., patient specific information. By matching the current case with those in the database, success rates of specific devices for similar procedures may be obtained and devices with lower success rates may be removed from the set of candidate devices.

[0036] In an embodiment, the device properties module 134 may score each candidate device in the set of candidate devices based on relative desirability of the predicted outcomes of the medical procedure using the candidate device. The scoring may include determining uncertainty levels of the predicted outcomes of the medical procedure using each of the candidate devices. In this case, the scores may be displayed with the candidate devices on the display 124. In anembodiment, the device properties module 134 may make the final selection of the set of candidate devices automatically based on the scores. The automatically selected candidate devices may still be displayed on the display 124 for final approval by the user. Of course, the user may override the automatic selection and choose another one of the candidate devices, which may be scored lower but is desirable to the user for other reasons.

[0037] Procedure outcome simulation module 136 is configured to predict outcomes of the medical procedure on the patient 150 using the candidate devices from the device properties module 134. In particular, the procedure outcome simulation module 136 merges the patientspecific computational model of the region of interest 155 from the tissue properties module 132 with each of the device-specific computational models associated with the selected candidate devices from the device properties module 134 to provide merged computational models corresponding to the selected candidate devices.

[0038] The procedure outcome simulation module 136 then adds the relevant device-tissue interaction models to the merged computational models to create patient-specific procedure outcome simulation models, respectively, corresponding to the selected candidate devices. The device-tissue interaction models may be the same for many combinations of devices and tissues, but are made specific through the parameters that are dependent on geometry, material, environment, and the like. The device-tissue interaction models may be stored in a database, such as the device properties database 135, in association with the different devices, as discussed above. The device-tissue interaction models may include at least one of a mechanical model (e.g., contact model), an electrical model, a thermal model, a magnetic model, an optical model, or an acoustic model, for example.

[0039] The procedure outcome simulation module 136 predicts outcomes of the medical procedure on the patient 150 using the candidate devices based on determined interactions between the current properties of the tissue and the physical properties of the candidate devices, respectively, using the patient-specific procedure outcome simulation models. Each patientspecific procedure outcome simulation model receives the current properties of the tissue, the physical properties of the candidate device, and the device-tissue interaction models as input, and outputs the predicted result of the medical procedure in terms of desired outcome metrics. The outcome metrics may be quantitative, such that specific values may be used to determine thesuccess of a certain procedure, or qualitative, such that the optimal procedure may be identified between multiple options.

[0040] The procedure outcome simulation module 136 selects the candidate device that has the best predicted outcome as the device identified for the medical procedure. The predicted outcomes of the procedure from the patient-specific procedure outcome simulation models may include any relevant physical or physiological change created by the treatment, such as deformations of the candidate devices, amounts of clot removed, damage to tissue, patency of a vessel, change in electric conductance of tissue, and / or least amount of tissue damage depending on specific procedure. The selected candidate device may be displayed on the display 124 for the user to confirm the selection. Alternatively, the procedure outcome simulation module 136 selects the candidate device may rank the candidate devices according to desirability of the outcomes, and display the candidate devices in the ranked order on the display 124. The user then makes the final selection of the candidate device to be used for the medical procedure on the patient 150 aided by the displayed candidate devices.

[0041] This combination results in a learning-on-the-fly, patient-specific, device recommendation tool. In addition, it can be based on continually updated outcome results and may increase knowledge on how to design devices for diseased tissue instead of healthy tissue. The link between tissue properties and medical image features is made through computational modeling, computational models of devices, and device-tissue interaction mechanisms, as well as the hybrid modelling combined with the databases, integrated into the objective device recommendation tool.

[0042] FIG. 2 is a flow diagram showing a method of identifying a medical device for a procedure depending on tissue properties of the patient and device properties of the medical device, 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.

[0043] Referring to FIG. 2, imaging data of the patient is received or obtained in block S211. The imaging data is acquired by a medical imaging device, and provides at least one imaging feature of tissue in a region of interest of the patient. The imaging data may be obtained directly from the medical imaging device, e.g., during patient examinations, or may be obtained from adatabase of previously acquired images. The medical imaging device may be any type of compatible imaging or sensing, such as MRI, X-ray, CT, ultrasound, IVUS, optical coherence tomography, optical shape sensing, dielectric tissue sensing, and optical tissue sensing, for example.

[0044] In block S212, patient data is received from one or more patient databases, such as an EHR database, for example. The patient data may include anatomical information of the patient, such as vasculature data, blood pressure, age, sex, ethnicity, heart rate, and cholesterol level, for example. The anatomical information also may include previously obtained imaging data that can be used as a reference.

[0045] In block S213, current properties of the tissue in the region of interest of the patient are determined. This determination includes accessing a first database that stores tissue properties correlated with structural imaging features of tissues from images of the tissues, respectively. A most similar structural imaging feature in the first database is determined by comparing the at least one imaging feature of the tissue in the patient imaging data to the structural imaging features of tissues stored in the first database. Then, tissue properties correlated with the most similar structural imaging feature are identified as the current properties of the tissue in the patient imaging data. The first database may be constructed by determining precalculated tissue properties of the tissues from tissue property models using physics-based models to correlate the structural imaging features from the images of the tissues with the precalculated tissue properties, and constructing the first database using a tissue properties machine learning model that is trained using the images of the tissues and the precalculated tissue properties of the tissues from the tissue property models to correlate the structural imaging features from the images of the tissues with the precalculated tissue properties.

[0046] In block S214, a patient-specific computational model of the region of interest is created. The patient-specific computational model combines the anatomical information of the patient from block S212 and the current properties of the tissue from block S213. The patient-specific computational model may be a physics-based computational model, for example.

[0047] In block S215, a subset of devices is selected as candidate devices from among devices stored in a second database. The second database stores device-specific computational models of the devices and corresponding physical properties of the devices in association with the devicesand relevant device-tissue interaction models, respectively. The device-specific computational models of the devices may be physics-based computational models, for example.

[0048] In block S216, patient-specific procedure outcome simulation models are created by merging the patient-specific computational model and each of the device-specific computational models of the selected candidate devices, and adding the corresponding device-tissue interaction models to the merged models. That is, the patient-specific computational model and each of the device-specific computational models may be connected mathematically to the device-tissue interaction models corresponding to the candidate devices. Depending on the specific domains in which these models apply, the merging may entail the coupling of the patient-specific computational model and the device-specific computational models by means of a staggered or fully coupled approach (e.g., thermal and structural).

[0049] In block S217, outcomes of the procedure on the patient are predicted for the candidate devices based on determined interactions between the current properties of the tissue and the physical properties of the candidate devices, respectively, using the patient-specific procedure outcome simulation models.

[0050] In block S218, one or more candidate devices are selected to be the medical device for performing the procedure on the patient based on the predicted outcomes of the procedure. The one or more candidate devices may be selected automatically (e.g., by the processor 120) by comparing the outcomes using all of the candidate devices to a predetermined success threshold, and selecting those candidate devices that exceed the success threshold. In an embodiment, the outcomes may be scored by level of success (e.g., determined relative to the success threshold). The selected candidate devices may be displayed on a display according to the corresponding scores, and the user may then choose which of the one or more selected candidate device to be use for the procedure (which may or may not be the highest scoring candidate device). In an embodiment, the user may be provided with insight on criteria used for the recommendation and / or scoring of the candidate devices, and may be given the option to adapt the criteria. For example, the user may assign different weights to different outcome metrics used for scoring. Alternatively, the highest scoring candidate device may simply be selected automatically (e.g., by the processor 120) as the medical device, subject to final approval by the user. The procedure is then performed on the patient using the selected medical device.

[0051] In an embodiment, the method may be repeated using updated information received during the procedure, particularly information regarding the patient that affects the properties of the tissue in the region of interest. Changes may affect the patient specific computational model, for example, and ultimately the patient-specific therapy outcome simulation models used to predict outcomes of the procedure using different medical devices. This require determination of the optimal process and / or recommended device to be updated. For example, if the procedure involves stent placement in a vessel, the patency of the vessel may increase during pre-dilation more than predicted. Therefore, repeating the method may result in suggestion of a larger diameter stent. Additionally, other imaging modalities may be used during subsequent procedures, in which case the corresponding imaging data may be used to update the tissue properties before repeating the method.Example 1

[0052] A first example of identifying a medical device for a medical procedure depending on tissue properties of the patient involves a medical procedure for treating a pulmonary emboly. The pulmonary emboly is imaged using medical imaging, such as ultrasound imaging, for example. Based on geometry and internal structure of the pulmonary emboly observed in the imaging data, the current properties of the pulmonary emboly are determined through interpolation of data available in the tissue properties database. A patient-specific computational model of the pulmonary emboly is constructed using the imaging data as input for the patient geometry with the determined tissue properties assigned, such as elasticity, fracture strength and viscosity, for example.

[0053] Candidate devices, which may possibly be used for the procedure, and corresponding physical properties of the candidate devices are retrieved from a device properties database of devices. Device-specific computational models of the candidate devices are created. When any one candidate device may be used in different ways to apply procedure, multiple device-specific computational models of that candidate device will be provided, i.e., one for each procedure option.

[0054] The patient-specific computational model is combined with each of the device-specific computational models, and appropriate device-tissue interaction models are assigned to each ofthe combinations to create patient-specific procedure outcome simulation models. Simulations may then be performed with each of the patient-specific procedure outcome simulation models to predict outcomes for the corresponding procedure options for the pulmonary emboly using the corresponding devices. This may be done in a quantified manner, but in order to select the optimal procedure and corresponding device, a qualitative ranking is sufficient. The predicted outcomes may be scored and displayed to the user (e.g., physician), and an optimal device and (optionally) procedure may be suggested. Alternatively, a list of possible devices and procedures may be presented, along with scoring, such that the user is able to make his / her own decision in selecting the preferred device for the procedure or select from available inventory in the hospital / lab.

[0055] Possible devices for procedure of the pulmonary emboly include a catheter directed lysis, an aspiration catheter, and a stent retriever, for example. Depending on mechanical stiffness, size and / or location of the pulmonary emboly in the patient, one of the procedures will be more successful than the others in removing the pulmonary emboly. Also, adding specific drug loading to stents, for example, may be included to prevent future problems at the same location, such as restenosis and further pulmonary emboly formation. The drug loading stents may be considered as part of the device-tissue interaction models. Additionally, the device-specific computational model may provide a risk assessment for breakup of the pulmonary emboly and distal embolization.Example 2

[0056] A second example of identifying a medical device for a medical procedure depending on tissue properties of the patient involves a medical procedure for revascularization of a vessel using a stent. Revascularization may be required in response to severe stenosis. A lesion site may be imaged using medical imaging, such as a CT scan, for example. The composition and structure of the lesion site, as well as the material properties, are determined by the tissue property module from the combined data of the imaging and the tissue property database. The composition and the material properties are linked, along with their interaction characteristics, in that the composition is morphology describing amount, orientation and distribution of separate constituents of a tissue, e.g., collagen fibers, and each of the constituents has material properties(mechanical, thermal, electrical, etc.). A patient-specific computational model of the lesion site is created using the geometric data from the medical imaging and the tissue properties obtained from leveraging the tissue property database.

[0057] Candidate devices (candidate stents), which may possibly be used for the procedure, and corresponding physical properties of the candidate stents are retrieved from a device properties database of devices. Device-specific computational models of the candidate stents are created. Therefore, several scenarios may be evaluated, such as deployment of various candidate stents at the lesion site. For each stent, different therapy options may be evaluated as well. For example, pre-dilation and / or post-dilation with various different balloons at various pressures may be evaluated.

[0058] The patient-specific computational model of the lesion site is combined with each of the device-specific computational models of the stents, and appropriate device-tissue interaction models are assigned to each of the combinations to create patient-specific procedure outcome simulation models. Simulations may then be performed with each of the patient-specific procedure outcome simulation models to predict outcomes for the corresponding procedure options using the corresponding stents.

[0059] Another scenario is when the lesion site is severely calcified and vessel preparation is required. In this case, device-specific computational models of candidate vessel preparation devices are created for comparison, e.g., for use in an intravascular lithotripsy procedure. The candidate vessel preparation devices may include scoring balloons, rotational atherectomy devices, and orbital atherectomy devices, for example. Based on the preferred outcome metric, for example maximal flow, the optimal therapy and devices are suggested.

[0060] Other applications may incorporate parametrized biomechanical models of humans, e.g., based on Non-Uniform Rational Basis (NURB) templates, which allow quantification of in-situ loading conditions of in-body devices. The biomechanical models contain vasculature and other relevant anatomical and physical properties information to assess loading conditions, such as bones, muscles, and fat, for example. According to an embodiment, the template biomechanical model is adjusted based on the medical imaging data to be patient specific. In addition to calculating the short term outcome of a procedure, for example the amount of patency achieved after a vessel stenting procedure, the load on the deployed stent may now be assessed by 1simulating natural movement of the patient using the biomechanical model with the deployed stent in the vessel. This may, for example, lead to insight that for a particular patient, a particular stent has a risk of kinking during certain movements by the patient, such as stair climbing, for example.

[0061] Also, additional factors may be incorporated in the procedure recommendations. For example, in some patients, the positioning of their limbs during the procedure may impact the recommendation of which device to use. For example, femoral veins may have impingement points where the vein is compressed due to other surrounding anatomy (e.g., bone, nerve, artery). Certain positions of the patients’ limbs may create more or less impingement, and therefore alter the ability for certain devices (e.g., navigation catheters) to reach the target location. In this case, the patient-specific computational model may include patient positioning to create different scenarios of the patient positioning, used to create the patient specific therapy outcome simulation models. The patient specific therapy outcome simulation models may then output a list of recommended devices and corresponding patient limb positions.

[0062] 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.

[0063] 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.

[0064] 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.

[0065] 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.

[0066] 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.

[0067] The preceding description of the disclosed embodiments is provided to enable any personskilled 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.

Claims

CLAIMS:

1. A method for selecting a medical device for performing a medical procedure on a patient, the method comprising: obtaining anatomical information of the patient and patient imaging data including at least one imaging feature of tissue in a region of interest of the patient; determining one or more current tissue properties in the region of interest based on the at least one imaging feature of the tissue; generating a patient-specific computational model of the region of interest based on the anatomical information and the one or more current tissue properties; selecting a plurality of candidate medical devices for performing the medical procedure, wherein each candidate medical device is associated with a device-specific computational model and a device-tissue interaction model; for each candidate medical device of the selected plurality of candidate medical devices: generating a patient-specific procedure outcome simulation model by merging the patient-specific computational model and the device-specific computational model associated with the candidate medical device, and predicting, using the patient-specific procedure outcome simulation model for the candidate medical device, a procedure outcome based on an interaction between the one or more current tissue properties and one or more physical properties of the candidate medical device; and selecting at least one candidate medical device of the plurality of candidate medical devices for performing the medical procedure based on the predicted procedure outcome for each of the plurality of candidate medical devices.

2. The method of claim 1 , wherein determining the one or more current tissue properties comprises: accessing a first database that stores tissue properties correlated with structural imaging features of tissues, determining at least one structural imaging feature of the structural imaging features that is most similar to the at least one imaging feature in the patient imaging data, andidentifying at least one tissue property correlated with the at least one structural imaging feature in the first database.

3. The method of claim 2, further comprising constructing the first database by: determining precalculated tissue properties of the tissues using tissue property models comprising physics-based models, training a tissue properties machine learning model based on images of the tissues and the precalculated tissue properties of the tissues, and correlating the structural imaging features with the precalculated tissue properties using the tissue properties machine learning model.

4. The method of claim 1, wherein selecting the plurality of candidate medical devices comprises: accessing a second database that stores medical devices, wherein each medical device is associated with physical properties of the medical device, a device-specific computational model, and a device-tissue interaction model, and selecting a subset of the stored medical devices that are intended for a type of the medical procedure as the plurality of candidate medical devices.

5. The method of claim 4, wherein the device-specific computational model comprises a machine learning model trained based on at least one of measured data characterizing the associated medical device or synthetic data characterizing the associated medical device, the synthetic data generated using a physics-based model.

6. The method of claim 1, further comprising: scoring the selected at least one candidate medical device based on the at least one predicted procedure outcome of the selected at least one candidate medical device, and display the scored at least one candidate medical device.

7. The method of claim 6, wherein scoring the selected at least one candidate medical device includes determining uncertainty levels of the at least one predicted procedure outcome.

8. The method of claim 1, wherein at least one of the patient-specific computational model and the device-specific computational model is a physics-based model.

9. The method of claim 1, wherein the plurality of candidate medical devices are selected manually by a user.

10. The method of claim 1, wherein the plurality of candidate medical devices are selected automatically based on the medical procedure, the anatomical information of the patient, and the one or more current tissue properties.

11. The method of claim 1, wherein the device-tissue interaction model includes at least one of a mechanical model, an electrical model, a thermal model, a magnetic model, an optical model, or an acoustic model.

12. A system for selecting a medical device for performing a medical procedure on a patient, the system comprising: a processor in communication with memory, the processor configured to: obtain anatomical information of the patient and patient imaging data including at least one imaging feature of tissue in a region of interest of the patient; determine one or more current tissue properties in the region of interest based on the at least one imaging feature of the tissue; generate a patient-specific computational model of the region of interest based on the anatomical information and the one or more current tissue properties; select a plurality of candidate medical devices for performing the medical procedure, wherein each candidate medical device is associated with a device-specific computational model and a device-tissue interaction model;for each candidate medical device of the selected plurality of candidate medical devices: generate a patient-specific procedure outcome simulation model by merging the patient-specific computational model and the device-specific computational model associated with the candidate medical device, and predict, using the patient-specific procedure outcome simulation model for the candidate medical device, a procedure outcome based on an interaction between the one or more current tissue properties and one or more physical properties of the candidate medical device; and select at least one candidate medical device of the plurality of candidate medical devices for performing the medical procedure based on the predicted procedure outcome for each of the plurality of candidate medical devices.

13. The system of claim 12, wherein to determine the one or more current tissue properties, the processor is further configured to: access a first database that stores tissue properties correlated with structural imaging features of tissues, determine at least one structural imaging feature of the structural imaging features that is most similar to the at least one imaging feature in the patient imaging data, and identify at least one tissue property correlated with the at least one structural imaging feature in the first database.

14. The system of claim 13, wherein the processor is further configured to construct the first database by: determining precalculated tissue properties of the tissues using tissue property models comprising physics-based models, training a tissue properties machine learning model based on images of the tissues and the precalculated tissue properties of the tissues, and correlating the structural imaging features with the precalculated tissue properties using the tissue properties machine learning model.

15. The system of claim 12, wherein to select the plurality of candidate medical devices, the processor is further configured to: access a second database that stores medical devices, wherein each medical device is associated with physical properties of the medical device, a device-specific computational model, and a device-tissue interaction model, and select a subset of the stored medical devices that are intended for a type of the medical procedure as the plurality of candidate medical devices.

16. The system of claim 15, wherein the device-specific computational model comprises a machine learning model trained based on at least one of measured data characterizing the associated medical device or synthetic data characterizing the associated medical device, the synthetic data generated using a physics-based model.

17. The system of claim 12, wherein the processor is further configured to: score the selected at least one candidate device based on the at least one predicted procedure outcome of the selected at least one candidate device; and display the scored at least one candidate devices.

18. The system of claim 12, wherein the predicted procedure outcome from the patientspecific procedure outcome simulation model comprises at least one of deformations of the candidate devices, amounts of clot removed, damage to tissue, patency of a vessel, change in electric conductance of tissue, or least amount of tissue damage depending on specific procedure.

19. A non-transitory computer readable medium having stored instructions for selecting a medical device for performing a medical procedure on a patient, the instructions, when executed by a processor, cause the processor to: obtain anatomical information of the patient and patient imaging data including at least one imaging feature of tissue in a region of interest of the patient;determine one or more current tissue properties in the region of interest based on the at least one imaging feature of the tissue; generate a patient-specific computational model of the region of interest based on the anatomical information and the one or more current tissue properties; select a plurality of candidate medical devices for performing the medical procedure, wherein each candidate medical device is associated with a device-specific computational model and a device-tissue interaction model; for each candidate medical device of the selected plurality of candidate medical devices: generate a patient-specific procedure outcome simulation model by merging the patient-specific computational model and the device-specific computational model associated with the candidate medical device, and predict, using the patient-specific procedure outcome simulation model for the candidate medical device, a procedure outcome based on an interaction between the one or more current tissue properties and one or more physical properties of the candidate medical device; and select at least one candidate medical device of the plurality of candidate medical devices for performing the medical procedure based on the predicted procedure outcome for each of the plurality of candidate medical devices.

20. The non-transitory computer readable medium of claim 19, wherein the instructions, when executed by the processor, further cause the processor to: access a first database that stores tissue properties correlated with structural imaging features of tissues, determine at least one structural imaging feature of the structural imaging features that is most similar to the at least one imaging feature in the patient imaging data, and identify at least one tissue property correlated with the at least one structural imaging feature in the first database as the one or more current tissue properties

Images