Systems and methods for vascular image coregistration - Patents.com

Abstract

A neural network is trained to evaluate patient hemodynamic data using a plurality of extravascular image data sets and a plurality of intravascular image data sets, each of which is co-registered with a corresponding extravascular image data set. A plurality of hemodynamic data sets are provided, each of which is co-registered with a corresponding extravascular image data set. The neural network learns which hemodynamic data is expected for a given intravascular image data set. An intravascular imaging operation is then performed in which an intravascular imaging element is moved within the patient's blood vessel to generate one or more intravascular images. The neural network uses its training to predict hemodynamic values ​​corresponding to the one or more intravascular images from the intravascular imaging operation, and the one or more intravascular images are output in combination with the predicted hemodynamic values.

Description

[Technical field]

[0001] FIELD OF THE DISCLOSURE The present disclosure relates to medical imaging and systems and methods for medical imaging. More particularly, the present disclosure relates to systems and methods for vascular imaging, including intravascular and extravascular imaging and co-registration. [Background technology]

[0002] A wide variety of medical imaging systems and methods have been developed for medical applications, such as for use in imaging vascular anatomical structures. Some of these systems and methods include intravascular and extravascular imaging modalities for imaging vascular structures. These systems and methods may include a variety of configurations and operate or be used according to any one of a variety of methods. Each of the known vascular imaging systems and methods has certain advantages and disadvantages. Thus, there is a continuing need to provide alternative systems and methods for vascular imaging and evaluation, as well as imaging coregistration. Summary of the Invention

[0003] The present disclosure provides alternative medical imaging systems and methods. One example includes a method for evaluating patient hemodynamic data. The method includes training a neural network, followed by subsequently acquiring intravascular images of the patient, and using the trained neural network to evaluate the corresponding hemodynamic data. Training the neural network includes providing a plurality of extravascular image datasets to the neural network, and providing a plurality of intravascular image datasets to the neural network, each intravascular image dataset including intravascular image data illustrating a portion of a blood vessel from a start location to an end location, each intravascular image dataset being co-registered with a corresponding extravascular image dataset of the plurality of extravascular image datasets. Training the neural network also includes providing a plurality of hemodynamic datasets to the neural network, each hemodynamic dataset being co-registered with a corresponding extravascular image dataset of the plurality of extravascular image datasets. The neural network uses the provided intravascular image data sets and the provided hemodynamic data sets, each co-registered with a corresponding extravascular image data set, to learn what hemodynamic data is expected for a given intravascular image data set, thereby creating a trained neural network. Using the trained neural network with a subsequent patient includes performing an intravascular imaging operation (event) in which the intravascular imaging element is moved from a start position to an end position within the patient's blood vessel to generate one or more intravascular images. The trained neural network uses its training to predict hemodynamic values ​​corresponding to one or more intravascular images from the intravascular imaging operation, and the one or more intravascular images are output in combination with the predicted hemodynamic values.

[0004] Alternatively or additionally, at least some of the multiple intravascular image data sets provided in the course of training the neural network may include intravascular ultrasound data.

[0005] Alternatively or additionally, at least some of the multiple intravascular image data sets provided in the course of training the neural network may include optical coherence tomography data.

[0006] Alternatively or additionally, at least some of the multiple extravascular image data sets provided during training of the neural network may include fluoroscopic image data. Alternatively or additionally, at least some of the multiple extravascular image data sets provided during training of the neural network may include angiographic image data.

[0007] Alternatively or additionally, the angiographic data may include two-dimensional angiographic image data. Alternatively or additionally, the angiographic data may include three-dimensional angiographic image data. Alternatively or additionally, the angiographic data may include 3D CTA (three-dimensional computed tomography angiography).

[0008] Alternatively or additionally, at least some of the multiple hemodynamic data sets provided in the course of training the neural network may include blood pressure data obtained with any hyperemic or non-hypemic index.

[0009] Alternatively or additionally, at least some of the multiple intravascular image data sets and at least some of the corresponding hemodynamic data sets may be co-registered using their corresponding points in 2D or 3D space on the corresponding extravascular image data sets.

[0010] Alternatively or additionally, the neural network may include an ensemble of neural networks. Alternatively or additionally, the neural network may include a CNN (Convolutional Neural Network) with a Transformer.

[0011] Alternatively or additionally, the neural network may include a multi-layer neural network. Alternatively or additionally, the multi-layer neural network may include a hemodynamic term in the loss function.

[0012] Alternatively or additionally, at least some of the multiple intravascular image data sets provided in the course of training the neural network may include quantitative data such as lumen boundary, vessel boundary, side branch boundary, blood speckle density, and cardiac cycle parameters, which may be used in training the neural network.

[0013] Alternatively or additionally, one or more intravascular images from the intravascular imaging operation include anatomical landmarks, and the predicted hemodynamic values ​​include predicted blood pressure values ​​proximate the anatomical landmarks.

[0014] Alternatively or additionally, outputting the one or more intravascular images in combination with the predicted hemodynamic values ​​may include displaying the one or more intravascular images and the predicted hemodynamic values ​​on a graphical user interface of the signal processing unit.

[0015] Alternatively or additionally, displaying one or more intravascular images and the predicted hemodynamic values ​​on a graphical user interface of the signal processing unit may include displaying a representation of the complete and coregistrated predicted hemodynamic values ​​together with the intravascular images.

[0016] Alternatively or additionally, displaying one or more intravascular images and the predicted hemodynamic values ​​on a graphical user interface of the signal processing unit may include displaying a fully tri-registered display of the predicted hemodynamic values ​​together with the intravascular images and corresponding extravascular images.

[0017] Another example includes a method for processing image data. The method includes providing a plurality of intravascular image data sets to a neural network, each intravascular image data set including intravascular image data showing a portion of a blood vessel co-registered with an extravascular image from a corresponding extravascular image data set from a start location to an end location. A plurality of hemodynamic data sets are provided to the neural network, each hemodynamic data set including hemodynamic data from a corresponding portion of the blood vessel co-registered with a corresponding extravascular image from a corresponding extravascular image data set from a start location to an end location, as represented by one of the plurality of intravascular image data sets. The neural network using the provided intravascular image data sets and the corresponding provided hemodynamic data sets from the co-registration of each data set to the same extravascular image learns what hemodynamic data is expected for a given intravascular image data set, thereby training the neural network. An intravascular imaging operation is performed on a new patient, in which an imaging element is moved within the blood vessel from a start location to an end location to generate one or more intravascular images. The neural network uses its training to predict hemodynamic values ​​corresponding to one or more intravascular images from the intravascular imaging operation, and the one or more intravascular images are output in combination with the predicted hemodynamic values.

[0018] Alternatively or additionally, at least some of the plurality of intravascular image data sets may include intravascular ultrasound data. Alternatively or additionally, at least some of the plurality of intravascular image data sets may include optical coherence tomography data.

[0019] Alternatively or additionally, at least some of the plurality of extravascular image data sets may include fluoroscopic image data. Alternatively or additionally, at least some of the plurality of extravascular image data sets may include angiographic image data.

[0020] Alternatively or additionally, at least some of the plurality of hemodynamic data sets may include blood pressure data obtained with any hyperemic or non-hypemic index. Another example includes a method for processing patient image data. The method includes acquiring intravascular image data from an intravascular imaging device, the acquisition including an imaging operation during a moving procedure in which an imaging element is moved from a start position to an end position within a blood vessel, the intravascular image data including one or more intravascular images. The one or more intravascular images are input to a trained neural network to determine a predicted blood pressure measurement value for each of the one or more intravascular images. A series of blood pressure values ​​within the blood vessel corresponding to the intravascular location of each of the one or more extravascular images is calculated, and a blood pressure ratio is calculated based on the series of blood pressure values.

[0021] Alternatively or additionally, the method may further include outputting the intravascular image data and the calculated blood pressure corresponding to the points within the blood vessel. Alternatively or additionally, the method may further include acquiring extravascular image data including one or more extravascular images, and co-registering the intravascular image data with the extravascular image data to determine an intravascular location of each of the one or more extravascular images.

[0022] Alternatively or additionally, the method may further include outputting co-registered extravascular image data in combination with the intravascular image data and the calculated blood pressure points corresponding to the points within the blood vessel.

[0023] Alternatively or additionally, acquiring the extravascular image data may include acquiring extravascular image data corresponding to the blood vessel from the start location to the end location. Alternatively or additionally, the intravascular image data may include intravascular ultrasound data.

[0024] Alternatively or additionally, the intravascular image data may include optical coherence tomography data. Alternatively or additionally, the extravascular image data may include fluoroscopic image data. Alternatively or additionally, the extravascular image data set may include angiographic image data.

[0025] Another example includes a method for processing image data. The method includes encoding physical features from a plurality of IVUS frames generated during an IVUS pullback run. Physiology resting index (PRI) pullback data is acquired. Angiography image data is acquired and co-registered with the PRI pullback data. The IVUS frames are co-registered with the angiography image data to co-register the PRI pullback data with the IVUS frames. The co-registered IVUS frames, angiography image data, and PRI pullback data are used to train a neural network on how to predict PRI data based on a subsequent IVUS pullback run. A new IVUS pullback run is then performed to provide the neural network with new IVUS pullback run data including a plurality of IVUS frames so that the neural network can calculate a predicted PRI value for each IVUS frame.

[0026] Alternatively or additionally, the method may further include co-registering the new IVUS pullback run data with the corresponding angiography run. The above summary of some embodiments is not intended to describe each disclosed embodiment or every implementation of the present disclosure. The following figures and detailed description more particularly exemplify these embodiments.

[0027] The present disclosure may be more fully understood from consideration of the following detailed description in conjunction with the accompanying drawings, in which: [Brief description of the drawings]

[0028] [Figure 1] Schematic diagram of training and using a neural network to predict hemodynamic values ​​based on intravascular image data. [Figure 2A] 1 is a flow diagram illustrating an exemplary method for evaluating hemodynamic data of a patient. [Figure 2B] 2B is a flow diagram illustrating an example method for training a neural network as part of the method of FIG. 2A. [Figure 2C] 2B is a flow diagram illustrating an example method for using a trained neural network as part of the method of FIG. 2A. [Diagram 3] 4 is a flow diagram illustrating an example method for processing image data. [Figure 4] 4 is a flow diagram illustrating an exemplary method for processing patient image data. [Diagram 5] 4 is a flow diagram illustrating an example method for processing image data. [Figure 6] Schematic diagram of an exemplary model. [Figure 7] Schematic diagram of an exemplary model. [Figure 8] Schematic diagram of an exemplary model. [Figure 9] 1 is a schematic diagram of an exemplary system for use in vascular imaging coregistration. [Figure 10] 1 is a schematic diagram of an exemplary intravascular imaging catheter shown in partial cross-section. [Figure 11] 11 is a schematic diagram of a distal portion of the exemplary intravascular imaging catheter of FIG. 10 shown in cross-section. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0029] While the present disclosure is amenable to various modifications and alternative forms, details thereof have been shown by way of example in the drawings and will be described in detail. It is to be understood, however, that the intention is not to limit the invention to the particular embodiments described. On the contrary, the invention is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure.

[0030] For the following defined terms, these definitions shall be applied, unless a different definition is given in the claims or elsewhere in this specification. All numerical values ​​are assumed to be modified herein by the term "about," whether or not expressly indicated. The term "about" generally refers to a range of numbers that one of ordinary skill in the art would consider equivalent to the recited value (e.g., having the same function or result). In many instances, the term "about" can include numbers that are rounded to the nearest significant figure.

[0031] The recitation of numerical ranges by endpoints includes all numbers within that range (e.g., 1 to 5 includes 1, 1.5, 2, 2.75, 3, 3.80, 4, and 5). As used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the content clearly dictates otherwise. As used in this specification and the appended claims, the term "or" is generally used in its sense including "or" unless the content clearly dictates otherwise.

[0032] It should be noted that references herein to "one embodiment," "some embodiments," "other embodiments," etc., indicate that the described embodiment may include one or more particular features, structures, or characteristics. However, such a description does not necessarily mean that all embodiments include the particular feature, structure, or characteristic. In addition, if a particular feature, structure, or characteristic is described in connection with one embodiment, it should be understood that such feature, structure, or characteristic may also be used in connection with other embodiments, whether or not explicitly described, unless otherwise stated.

[0033] The following detailed description should be read with reference to the drawings, in which like elements in different drawings are numbered the same. The drawings, which are not necessarily to scale, depict illustrative embodiments and are not intended to limit the scope of the invention.

[0034] A number of different medical imaging modalities may be used to evaluate or treat blood vessels. Two general types of imaging modalities include extravascular imaging modalities and intravascular imaging modalities. This disclosure relates to the use and co-registration of these modalities.

[0035] Extravascular imaging modalities, such as various forms of radiological imaging, provide extravascular image data of a portion of a blood vessel. Some examples include angiographic or fluoroscopic imaging modalities, such as 2D angiography / fluoroscopy, 3D angiography / fluoroscopy, or computed tomography angiography / fluoroscopy. Angiography typically involves rendering a radiographic image of one or more blood vessels, often using a radiopaque contrast agent. Angiographic images can also be viewed in real time by fluoroscopy. In general, fluoroscopy uses less radiation than angiography and is often used to guide medical devices, including radiopaque markers, in or through blood vessels. Extravascular image data of blood vessels can provide useful information regarding the location or positioning of blood vessels, anatomical structures, or devices within blood vessels or anatomical structures. For example, extravascular image data (e.g., angiograms) can provide a comprehensive overall image or a series of images or videos of the vessel(s) of interest, and can provide a "roadmap" with good temporal resolution for general assessment of the vessel(s) or navigation of a device within the vessel.

[0036] Intravascular imaging modalities provide intravascular image data of a portion of a blood vessel. Some examples of intravascular imaging modalities include intravascular ultrasound (IVUS) and optical coherence tomography (OCT). These modalities typically involve imaging the blood vessel itself using an intravascular probe equipped with an imaging element placed within the blood vessel. Several types of device systems are designed to track through the vascular structure to provide intravascular image data. These can include, but are not limited to, intravascular ultrasound (IVUS) devices and optical coherence tomography (OCT) devices (e.g., catheters, guidewires, etc.). In operation, an intravascular probe equipped with an imaging element is moved along the blood vessel in the area where imaging is desired. As the probe passes through the area of ​​interest, a set of intravascular image data is obtained that corresponds to a series of "slices" or cross sections of the blood vessel, lumen, and surrounding tissue. These devices may include radiopaque materials or markers. Such markers are typically positioned near the distal tip or near or on the probe. Thus, the approximate location of the imaging probe or imaging element can be identified by observing the procedure in either the fluoroscopic or angiographic image(s). Typically, such imaging devices are connected to a dedicated processing unit or control module, including processing hardware and software, as well as a display. The raw image data is received by the console, processed to render an image containing features of interest, and rendered on a display device. Intravascular image data of a blood vessel can provide useful information about the blood vessel that is different from, or in addition to, the information provided by extravascular image data. For example, intravascular image data can provide data regarding the cross-section of the lumen, the thickness of deposits on the vessel wall, the diameter of the non-diseased portion of the blood vessel, the length of the diseased segment, the composition of deposits or plaque on the vessel wall, an assessment of plaque load, or an assessment of stent deployment.

[0037] These two general types of imaging modalities provide different image data and thus may be complementary to each other. Thus, in certain circumstances, it may be desirable to provide or use both general types of medical imaging modalities to evaluate or treat a vessel. In addition, it may be useful to correlate the location of acquired intravascular image data / images with their location on the vascular roadmap obtained by the extravascular image data / images. It may be useful to align or "register" (e.g., co-register) image data rendered by two different modalities. It may also be useful to display the co-registered extravascular and intravascular image data together, for example, on a common display monitor. Some exemplary embodiments disclosed herein may include or relate to some or all of these aspects.

[0038] According to some embodiments of the present disclosure, exemplary method(s), system(s), device(s), or software are described herein. These examples include image data acquisition equipment and data / image processors and associated software for acquiring and registering (e.g., co-registering) image data rendered by two separate imaging modalities (e.g., extravascular image data and intravascular image data). Additionally or alternatively, the exemplary method(s), system(s), or software may generate an image on a single display that simultaneously provides an extravascular image with position information associated with an imaging probe (e.g., an IVUS or OCT probe) attached to an intravascular device and an intravascular image.

[0039] Hemodynamic data may be useful to ascertain the health of a patient. In some cases, hemodynamic information, such as, but not limited to, blood pressure data, may be useful to ascertain the health of a patient's vascular system. Various systems for acquiring hemodynamic data may be used. These systems for acquiring hemodynamic data may require one or more pullback runs to acquire the data. In some cases, it may be useful to provide hemodynamic data without requiring any additional pullback runs or any other processes or techniques for acquiring blood pressure information and / or other hemodynamic data.

[0040] FIG. 1 provides a schematic diagram of an exemplary system 10 in which a neural network 12 may be trained to provide an assessed hemodynamic value corresponding to a particular intravascular image. The neural network 12 may be any of a variety of different types of neural networks. In some cases, the neural network 12 may represent a single neural network or multiple neural networks. In some cases, the neural network 12 may be manifested, for example, in a cloud-based server. The neural network 12 may represent a CNN (convolutional neural network) having one or more transformers. In some cases, the neural network 12 may include a multi-layer neural network. These are merely examples.

[0041] The neural network 12 may be adapted to learn. In some cases, the neural network 12 may be considered to include AI (artificial intelligence) and, optionally, capable of ML (machine learning). To train the neural network 12, the neural network 12 may be provided with existing data from which the neural network 12 may learn. In some cases, the neural network 12 may be trained on how to associate a particular hemodynamic property or value with a corresponding intravascular image. The neural network 12 may provide multiple intravascular image data sets provided from a variety of different imaging modalities, such as, but not limited to, intravascular ultrasound and optical coherence tomography data, as described with respect to FIGS. 9-11. The neural network 12 may provide multiple extravascular image data sets 16. The extravascular image data sets 16 may include fluoroscopic image data and / or angiographic image data. Examples of angiographic image data include, but are not limited to, 2D (two-dimensional) angiographic data, 3D (three-dimensional) angiographic data, and 3D CTA (three-dimensional computed tomography angiography).

[0042] Each of the multiple extravascular image data sets 16 provided to the neural network 12 may be co-registered with a corresponding one of the multiple intravascular image data sets 14, such as when a particular intravascular image data set 14 corresponds to a particular intravascular image data acquisition session (e.g., imaging pullback run) of a particular portion of a patient's blood vessel from a particular start point to a particular end point, and the corresponding extravascular image data set 16 corresponds to extravascular image data of the same portion of the same blood vessel of the same patient, from the same start point to the same end point. In some cases, the portion of the patient's anatomy represented by a particular intravascular image data set 14 and the portion of the patient's anatomy represented by a particular extravascular image data set 16 may not exactly match, but may overlap. In either operation, each intravascular image data set 14 may be co-registered with the corresponding extravascular image data set 16, as shown in block 18. Methods for co-registering the intravascular image data set 14 and the extravascular image data set 16 are detailed with respect to FIGS. 9-11 and described thereafter.

[0043] The neural network 12 may be provided with pre-existing hemodynamic datasets 20. In some cases, a particular hemodynamic dataset represents hemodynamic data, such as, but not limited to, blood pressure data, for a particular patient. In some cases, each hemodynamic dataset 20 corresponds to one or more blood pressure measurements taken at a particular location within a particular blood vessel of a particular patient. In some cases, the one or more blood pressure measurements correspond to a particular location within a particular blood vessel that matches the anatomical structure represented by a particular extravascular image dataset 16. In other words, as shown in block 22, each of the hemodynamic datasets 20 may be co-registered with a corresponding extravascular image dataset 16.

[0044] It will be appreciated that by co-registering each of the intravascular image data sets 14 with a corresponding one of the extravascular image data sets 16, and by co-registering each of the hemodynamic data sets 20 with a corresponding one of the extravascular image data sets 16, the neural network 12 can ascertain correlations between the intravascular image data, the extravascular image data, and the hemodynamic data. As a result, the neural network 12, by processing several intravascular image data sets 14, several corresponding extravascular image sets 16, and several corresponding hemodynamic data sets 20, and by being given or otherwise determining the co-registration between the intravascular data and the extravascular data, the co-registration between the extravascular data and the hemodynamic data, and thus the co-registration between the intravascular data and the hemodynamic data, can learn how to evaluate or predict hemodynamic data, such as a blood pressure measurement, as a result of what the neural network 12 sees in a particular intravascular image(s).

[0045] At least some of the intravascular image data sets 14, at least some of the extravascular image data sets 16, and at least some of the hemodynamic data sets 20 may represent historical data previously acquired and stored. At least some of the intravascular image data sets 14, at least some of the extravascular image data sets 16, and at least some of the hemodynamic data sets 20 may represent data acquired from volunteers undergoing these imaging processes to contribute useful data for training the neural network 12. At least some of the intravascular image data sets 14, at least some of the extravascular image data sets 16, and at least some of the hemodynamic data sets 20 may represent patient data that may be acquired independently for research purposes as patients undergo intravascular imaging, extravascular imaging, and hemodynamic measurements for any of a variety of different clinical purposes.

[0046] As a result of the training, the neural network 12 may be considered to have evolved into a trained neural network 24. Here, the distinction between the neural network 12 and the trained neural network 24 may not be simply binary, i.e., the neural network 12 turns into a trained neural network 24 once sufficient training is completed. In some cases, the training may continue indefinitely. The neural network considered to be trained may be periodically tested, such as by providing the neural network 24 with endovascular data, while hemodynamic data obtained essentially simultaneously from the same patient, from the same anatomical structure, may be used as a check against the evaluated hemodynamic measurements provided by the trained neural network 24. If the actual hemodynamic measurements are close to the predicted hemodynamic measurements, this may be interpreted as an indication that the trained neural network 24 is indeed well trained. However, if there is a mismatch or even a substantial mismatch between the actual and predicted hemodynamic measurements, this may be interpreted as an indication that the trained neural network 24 may benefit from additional training.

[0047] Once the neural network 12 becomes a trained neural network 24, the trained neural network 24 may be used to provide an estimated hemodynamic value in response to an intravascular pullback run, such as, but not limited to, an IVUS (intravascular ultrasound) pullback run. Performing an intravascular pullback run may provide a source of an intravascular image 26. Feeding the intravascular image 26 to the trained neural network 24 may result in a predicted hemodynamic value 28. Through training, the trained neural network 24 has learned what hemodynamic values ​​28 have historically resulted from a particular set of parameters defining the intravascular image. For example, a particular type and size of blockage in a blood vessel has historically resulted in a particular change in blood pressure measurements. Once the trained neural network 24 has determined the estimated hemodynamic value, the intravascular image and the corresponding predicted hemodynamic value may be output on any available screen, as shown in block 30. In some cases, for example, the output of the intravascular images and corresponding predicted hemodynamic values ​​may be a computer, such as, but not limited to, via the computer system / subsystem 130 described with respect to FIG.

[0048] Figures 2A, 2B, and 2C are flow diagrams that, in combination, provide an exemplary method 32 for evaluating hemodynamic data of a patient. Figures 2B and 2C provide details not outlined in Figure 2A. Method 32 includes training a neural network (such as neural network 12), as shown in block 34, and using the trained neural network (such as trained neural network 24) with a subsequent patient, as shown in block 26.

[0049] In some cases, the neural network may include an ensemble of neural networks. The neural network may include a CNN (convolutional neural network) with a transformer. In some cases, the neural network may include a multi-layer neural network. The multi-layer neural network may include, for example, a hemodynamic term in a loss function.

[0050] 2B shows details regarding a method 34 for training a neural network. As shown in block 34a, a plurality of extravascular image data sets are provided to the neural network. As shown in block 34b, a plurality of intravascular image data sets are provided to the neural network, each of the intravascular image data sets including intravascular image data showing a portion of a blood vessel from a start location to an end location, and each of the intravascular image data sets is co-registered with a corresponding one of the plurality of extravascular image data sets. At least some of the plurality of intravascular image data sets provided in the course of training the neural network include intravascular ultrasound data. At least some of the plurality of intravascular image data sets provided in the course of training the neural network include optical coherence tomography data.

[0051] As shown in block 34c, a plurality of hemodynamic data sets are provided to the neural network, and each hemodynamic data set is co-registered with a corresponding extravascular image data set of the plurality of extravascular image data sets. As shown in block 34d, the neural network uses the provided plurality of intravascular image data sets and the provided plurality of hemodynamic data sets, each co-registered with a corresponding extravascular image data set, to learn which hemodynamic data is expected for a given intravascular image data set, thereby creating a trained neural network. In some cases, at least some of the plurality of hemodynamic data sets provided in the course of training the neural network consist of blood pressure data obtained with any hyperemic or non-hypemic index.

[0052] In some cases, at least some of the extravascular image data sets provided in the course of training the neural network include fluoroscopic image data. At least some of the extravascular image data sets provided in the course of training the neural network may include angiographic image data. The angiographic data may include, for example, two-dimensional angiographic image data and / or three-dimensional angiographic image data. In some cases, at least some of the angiographic data may include 3D CTA (three-dimensional computed tomography angiography).

[0053] In some cases, at least some of the multiple intravascular image data sets and at least some of the corresponding hemodynamic data sets may be co-registered using their corresponding points in 2D or 3D space on the corresponding extravascular image data sets. In some cases, at least some of the multiple intravascular image data sets provided in the course of training the neural network include quantitative data such as lumen boundary, vessel boundary, side branch boundary, blood speckle density, and cardiac cycle parameters, and the quantitative data is used in training the neural network.

[0054] 2C shows details regarding a method 36 for using a trained neural network (such as trained neural network 24) with a subsequent patient. As shown in block 36a, an intravascular imaging operation is performed in which an intravascular imaging element is moved from a start position to an end position within a patient's vessel to generate one or more intravascular images. As shown in block 36b, the trained neural network uses its training to predict hemodynamic values ​​corresponding to one or more intravascular images from the intravascular imaging operation. As shown in block 36c, the one or more intravascular images are output in combination with the predicted hemodynamic values.

[0055] In some cases, one or more intravascular images from the intravascular imaging operation include anatomical landmarks, and the predicted hemodynamic values ​​include predicted blood pressure values ​​proximate the anatomical landmarks. In some cases, the multiple intravascular image data sets (used to train the neural network) may include indications of important arterial locations, such as proximal fiducials, minimum lumen, and distal fiducials, and one or more intravascular images from the intravascular imaging operation include these important locations. In some cases, the predicted blood pressure values ​​include predicted blood pressure values ​​proximate the important locations.

[0056] In some cases, outputting the one or more intravascular images in combination with the predicted hemodynamic values ​​may include displaying the one or more intravascular images and the predicted hemodynamic values ​​on a graphical user interface of the signal processing unit. Displaying the one or more intravascular images and the predicted hemodynamic values ​​on a graphical user interface of the signal processing unit may include displaying a fully co-registered representation of the predicted hemodynamic values ​​with the intravascular images. In some cases, displaying the one or more intravascular images and the predicted hemodynamic values ​​on a graphical user interface of the signal processing unit may include displaying a fully tri-registered representation of the predicted hemodynamic values ​​with the intravascular images and the corresponding extravascular images.

[0057] 3 is a flow diagram illustrating an exemplary method 38 for processing image data. The method 38 includes providing a plurality of intravascular image data sets to a neural network (such as neural network 12), each intravascular image data set including intravascular image data illustrating a portion of a blood vessel co-registered with an extravascular image from a corresponding extravascular image data set from a start location to an end location, as shown in block 40. At least some of the plurality of intravascular image data sets may include intravascular ultrasound data. At least some of the plurality of intravascular image data sets may include optical coherence tomography data. At least some of the plurality of extravascular image data sets may include fluoroscopy image data. At least some of the plurality of extravascular image data sets may include angiography image data.

[0058] A plurality of hemodynamic data sets are provided to the neural network, each hemodynamic data set including hemodynamic data from a corresponding portion of a blood vessel co-registered with a corresponding extravascular image from a corresponding extravascular image data set from a start location to an end location as represented by one of the plurality of intravascular image data sets, as shown in block 42. At least some of the plurality of hemodynamic data sets may include blood pressure data obtained with any hyperemic or non-hypemic index. As shown in block 44, the neural network uses the provided intravascular image data sets and the corresponding provided hemodynamic data sets to learn what hemodynamic data is expected for a given intravascular image data set from the co-registration of each data set to the same extravascular image, thereby training the neural network.

[0059] The method 38 includes performing an intravascular imaging operation on a new patient in which an imaging element is moved from a start position to an end position within a blood vessel to generate one or more intravascular images, as shown in block 46. The neural network uses its training to predict hemodynamic values ​​corresponding to the one or more intravascular images from the intravascular imaging operation, as shown in block 48. The one or more intravascular images are output in combination with the predicted hemodynamic values, as shown in block 50.

[0060] 4 is a flow diagram illustrating an exemplary method 52 for processing patient image data. The method 52 includes an imaging operation in the course of a moving procedure in which an imaging element is moved from a start position to an end position within a blood vessel, as shown in block 54, in which acquiring intravascular image data from an intravascular imaging device includes one or more intravascular images. As shown in block 56, the one or more intravascular images are input to a trained neural network (such as trained neural network 24) to determine a predicted blood pressure measurement value for each of the one or more intravascular images. As shown in block 58, a series of blood pressure values ​​within the blood vessel corresponding to the intravascular location of each of the one or more extravascular images is calculated. As shown in block 60, a blood pressure ratio is calculated based on the series of blood pressure values.

[0061] In some cases, the method 52 may further include outputting the intravascular image data and the calculated blood pressure points corresponding to the points within the blood vessel, as shown in block 62. In some cases, the method 52 may further include acquiring extravascular image data including one or more extravascular images, and co-registering the intravascular image data with the extravascular image data to determine an intravascular location of each of the one or more extravascular images, as shown in block 64. For example, acquiring the extravascular image data may include acquiring extravascular image data corresponding to the blood vessel from a start location to an end location. In some cases, the method 52 may further include outputting the co-registered extravascular image data in combination with the intravascular image data and the calculated blood pressure points corresponding to the points within the blood vessel, as shown in block 66.

[0062] In some cases, the intravascular image data includes intravascular ultrasound data. In some cases, the intravascular image data includes optical coherence tomography data. The extravascular image data may include fluoroscopy image data, for example, or angiography image data.

[0063] 5 is a flow diagram illustrating an exemplary method 68 for processing image data. The method 68 includes encoding physical features from an IVUS frame from an IVUS pullback run generating a plurality of IVUS frames, as shown in block 70. Physiology Resting Index (PRI) pullback data is collected, as shown in block 72. Image data from an angiographic acquisition is collected, as shown in block 74. The angiographic image is co-registered with the PRI pullback data, as shown in block 76. The IVUS frame is co-registered with the angiographic image data to co-register the PRI pullback data with the IVUS frame, as shown in block 78. The co-registered IVUS frame, angiographic image data, and PRI pullback data are used to train a neural network to predict PRI data based on a subsequent IVUS pullback run, as shown in block 80. The new IVUS pullback run data including a plurality of IVUS frames is then provided to the neural network to calculate a predicted PRI measurement for each IVUS frame, as shown in block 82. In some cases, the method 68 may further include co-registering the new IVUS pullback run data with the corresponding angiography run, as shown in block 84 .

[0064] 6-8 provide schematic diagrams of exemplary models that may be used in training the neural network 12. FIG. 6 is a schematic diagram of a model 86 that may be implemented within the neural network 12. The model 86 includes several inputs 86a, including but not limited to lumen boundary, vessel boundary, side branches, and blood speckle density. The inputs 86a are provided to a neural network block 86c via Nx1 86b. The neural network 86c outputs an iFR prediction 86d. The model 86 uses a loss function 86e. The model 86 integrates a PRI hemodynamic model as an additional term in the loss function to increase the accuracy of the PRI prediction unit. The model 86 receives inputs as feature vectors, such as derived lumen boundary, vessel boundary, side branches, blood speckle density, and cardiac cycle. The input feature vectors represent the variables of the hemodynamic PRI equation.

[0065] 7 is a schematic diagram of a model 88 that may be implemented within the neural network 12. An IVUS (intravascular ultrasound) image 88a is provided to a CNN block 88b. The embedded patches are provided to a transformer block 88c. From there, the signal is passed to an MLP head 88e, resulting in an IFR prediction 88f. The model 88 processes the IVUS image directly using CNN and / or ViT to predict PRI values.

[0066] 8 shows a schematic of model 90, which is a combination of models 86 and 88. The outputs from models 86 and 88 are provided to an averaging block 92. The output from averaging block 92 is a final PRI 94. Model 90 provides a specific, accurate, efficient, real-time AI (Artificial Intelligence) model.

[0067] 9 is a schematic diagram of an exemplary system 102 that may be used in connection with performing embodiments of the present disclosure by acquiring and co-registering extravascular image data (e.g., angiogram / fluoroscopy) and intravascular image data (e.g., IVUS or OCT images). The system 102 may include an extravascular imaging system / subsystem 104 (e.g., an angiogram / fluoroscopy system) for acquiring / generating the extravascular image data. The system 102 may also include an intravascular imaging system / subsystem 106 (e.g., IVUS or OCT) for acquiring / generating the intravascular image data. The system 102 may include a computer system / subsystem 130 including one or more controllers or processors, memory and / or software configured to execute a method for vascular imaging registration of acquired extravascular image data and acquired intravascular image data.

[0068] The extravascular image data may be radiographic image data acquired by an angiography / fluoroscopy system 104. Such angiography / fluoroscopy systems are generally well known in the art. The angiography / fluoroscopy system 104 may include an angiography table 110 that may be positioned to provide sufficient space for positioning an angiography / fluoroscopy unit C-arm 114 in an operating position relative to a patient 100 on the angiography table 110. The raw radiographic image data acquired by the angiography / fluoroscopy C-arm 114 may be passed to an extravascular data input port 118 via a transmission cable 116. The input port 118 may be a separate component or may be integrated into or part of a computer system / subsystem 130. The angiography / fluoroscopy input port 118 may include a processor that converts the raw radiographic image data received thereby into extravascular image data (e.g., angiography / fluoroscopy image data), for example in the form of live video, DICOM, or a series of individual images. The extravascular image data may be initially stored in a memory in the input port 118 or may be stored in the computer 130. If the input port 118 is a separate component from the computer 130, the extravascular image data may be transferred to the computer 130 via the cable 117 and entered into an input port in the computer 130. In some alternatives, communication between devices or processors may be performed via wireless communication rather than cables.

[0069] The intravascular image data may be, for example, IVUS data or OCT data acquired by an intravascular imaging system / subsystem 106 (e.g., an IVUS or OCT system). Such IVUS and OCT systems are generally known in the art. The intravascular subsystem 106 may include an intravascular imaging device such as an imaging catheter 120, e.g., an IVUS or OCT catheter. The imaging device 120 is configured to be inserted into the patient 100 such that its distal end, including a diagnostic assembly or probe 122 (e.g., an IVUS or OCT probe), is in the vicinity of a desired imaging location of a blood vessel. A radiopaque material or marker 123 located on or near the probe 122 may provide an indication of the current location of the probe 122 in a radiographic image.

[0070] As an example, for IVUS intravascular image data, the diagnostic probe 122 generates ultrasound waves and receives ultrasound echoes representative of an area proximate to the diagnostic probe 122. The probe 122 or catheter 120 can convert the ultrasound echoes into corresponding signals, such as electrical or optical signals. The corresponding signals are transmitted along the length of the imaging catheter 120 to a proximal connector 124. The proximal connector 124 of the catheter 120 is communicatively coupled to a processing unit or control module 126. IVUS versions of the probe 122 come in a variety of configurations, including single and multiple transducer element arrays. It should be understood that in the context of IVUS, the transducers may be considered imaging elements. In the case of multiple transducer element arrays, the array of transducers may be arranged linearly along the longitudinal axis of the imaging catheter 120, curvilinearly around the longitudinal axis of the catheter 120, circumferentially around the longitudinal axis, etc.

[0071] An example of an IVUS intravascular imaging catheter 120 is shown in Figures 10 and 11. The imaging catheter 120 may include an elongate shaft 170 having a proximal end portion 172 and a distal end portion 174. A proximal hub or connector 124 may be coupled to or otherwise disposed adjacent to the proximal end portion 172. A tip member 176 may be coupled to or otherwise disposed adjacent to the distal end portion 174. The tip member 176 may include a guidewire lumen, an atraumatic distal tip, one or more radiopaque markers, or other features. An imaging assembly 177 may be disposed within the shaft 170. In general, the imaging assembly 177 (which may include an imaging probe 122 including imaging elements 182) may be used to capture / generate images of a blood vessel. In some cases, the medical device may include devices or features similar to those disclosed in U.S. Patent Application Publication Nos. 2012 / 0059241 and 2017 / 0164925, the entire disclosures of which are incorporated herein by reference. In at least some cases, the medical device 120 may be similar to or include similar features to the OPTICROSS™ imaging catheter available from BOSTON SCIENTIFIC (Marlborough, Mass.).

[0072] 11, the imaging assembly 177 may include a drive cable or shaft 178 and an imaging probe 122 or transducer 182 including a housing 180 and an imaging element. The imaging probe 122 or housing 180 may be coupled to the drive cable 178. The transducer 182 may be rotatable or axially movable relative to the shaft 170. For example, the drive cable 178 may be rotated or moved to rotate or move the transducer 182. The probe 122 or housing 180 may include or be made of, for example, a radiopaque material or marker 123, which may provide an indication of the current position of the probe 122 in a radiographic image.

[0073] Referring back to FIG. 9, as another example, the device 120 may be an OCT catheter used to collect OCT intravascular data. The OCT catheter 120 may include a diagnostic probe 122 that generates or propagates a light beam that is directed at the tissue, and a portion of this light that reflects off subsurface features is collected to represent the area proximate to the diagnostic probe 122. In OCT, the diagnostic probe 122 includes an optical imaging device for light delivery and collection. It should be understood that in the context of OCT, the optical imaging device in the probe 122 may be considered an imaging element. Using a technique called interferometry, the optical path length of the received photons can be recorded and most photons that are scattered multiple times before detection can be removed. Thus, OCT can build an image of a thick sample by removing background signals while collecting light that is directly reflected from the surface of the object. The probe 122 or catheter 120 may transmit optical or light signals along the shaft, or may convert the light signals into corresponding signals, such as electrical or optical signals, that can be transmitted along the length of the imaging catheter 120 to the proximal connector 124. The proximal connector 124 of the catheter 120 is communicatively coupled to a processing unit or control module 126. The probe 122 or housing 180 may include or be made of a radiopaque material or marker 123, which may provide an indication of the current location of the probe 122 in a radiographic image.

[0074] Raw intravascular image data (e.g., raw IVUS or OCT data) may be acquired by the imaging catheter 120 and passed to the control module 126, for example, via the connector 124. The control module 126 may be a separate component or may be integrated into or part of the computer system / subsystem 130. The control module 126 may include a processor that converts, or is configured to convert, the raw intravascular image data received via the catheter 120 into intravascular image data (e.g., IVUS or OCT image data), for example in the form of live video, DICOM, or a series of individual images. The intravascular image data may include cross-sectional images of a vessel segment. In addition, the intravascular image data may include longitudinal cross-sectional images corresponding to slices of the vessel taken along the length of the vessel. The control module 126 may be considered an input port for the computer system / subsystem 130 or may be considered to be connected to an input port of the computer 130, for example, via a cable 119 or a wireless connection. The intravascular image data may be initially stored in memory within the control module 126, or may be stored in memory within the computer system / subsystem 130. If the control module 126 is a separate component from the computer system / subsystem 130, the intravascular image data may be transferred to the computer 130, for example, via cable 119 and into an input port within the computer 130. Alternatively, communication between devices or processors may be performed via wireless communication rather than cable 119.

[0075] The control module 126 may also include one or more components that may be configured to operate the imaging device 120 or control the collection of intravascular image data. For example, in the case of an IVUS system, the control module 126 may include one or more of a processor, memory, a pulse generator, a motor drive unit, or a display. As another example, in the case of an OCT system, the control module 126 may include one or more of a processor, memory, a light source, an interferometer, an optical system, a motor drive unit, or a display. In some cases, the control module 126 may be or include a motor drive unit configured to control the motion of the imaging catheter 120. Such a motor drive unit may control the rotation or movement of the imaging catheter 120 or its components. In some cases, the control module 126 or the motor drive unit may include an automated movement system that may be configured to move the imaging catheter 120 within a controlled / measured object in the patient 100. Such an automated movement system may be used such that during a movement procedure, the imaging catheter 120 (including the imaging element) is moved within the blood vessel from a start position to an end position at a constant or known speed. (e.g., imaging catheter 120 is moved at a particular speed for a known amount of time). In other embodiments, the movement may be performed manually. The movement procedure may be, for example, a "pull-back" procedure (catheter 120 is pulled through the blood vessel) or a "push-through" procedure (catheter 120 is pushed through the blood vessel). Control module 126 may also be comprised of or may include hardware and software configured to control intravascular imaging and data collection. For example, control module 126 may include control features to turn on / off imaging or data collection from / to catheter 120.

[0076] The computer system / subsystem 130 may include one or more controllers or processors, one or more memories, one or more input ports, one or more output ports, and / or one or more user interfaces. The computer 130 is configured to acquire or obtain intravascular image data from or through the intravascular imaging system / subsystem 106 (e.g., IVUS or OCT) and extravascular image data from or through the extravascular imaging system / subsystem 104 (e.g., angiography / fluoroscopy system). The computer 130 or its components may include software and hardware designed to be integrated into a standard catheterization procedure and to automatically acquire both extravascular image data (e.g., angiography / fluoroscopy) and intravascular image data (e.g., IVUS or OCT) via image or video acquisition.

[0077] The computer system / subsystem 130 or components thereof may include software or hardware configured to execute a method for vascular imaging coregistration of acquired extravascular image data and acquired intravascular image data. In that context, the computer 130 may include computer readable instructions or software for executing a method for vascular imaging coregistration as disclosed herein. For example, in some respects, the computer may include a processor or memory including software including program code that causes the computer to execute a method for vascular imaging coregistration as disclosed herein. For example, the computer / computing device may include a processor or memory including instructions executable by the processor to execute a method for vascular imaging coregistration as disclosed herein. In that context, it should also be understood that computer readable media having program code stored thereon in a non-transitory state for use by the computer / computing device 130 is also disclosed herein, the program code causing the computing device 130 to execute a method for vascular imaging coregistration as disclosed herein. Additionally, the computer / computing device 130 may be part of or include a system for intravascular imaging registration including one or more input ports for receiving image data, one or more output ports, and a controller in communication with the input ports and the output ports, the controller configured to perform a method for intravascular imaging registration as disclosed herein.

[0078] The computer system / subsystem 130 may also include software and hardware configured to render or display imaging, including, for example, extravascular imaging or intravascular imaging derived from the received image data or the co-registration method. In some cases, the computer 130 or software may be configured to render both extravascular and intravascular imaging on a single display. In this regard, the system may include a display 150 configured to simultaneously display extravascular and intravascular image data rendered by the computer 130. The display 150 may be part of the computer system 130 or may be a separate component that communicates with the computer system 130, for example, via an output port on the computer 130 and a transmission cable 121. However, in some other cases, communication via the output port may be wireless rather than via a cable. In some cases, the computer 130 or display 150 may be configured to simultaneously provide angiograms, IVUS transverse cross-sectional views, and IVUS longitudinal cross-sectional views, all of which may or may not be co-registered simultaneously. In another example, the display may be configured to simultaneously provide an angiogram, an OCT cross section view, and an OCT longitudinal section view, which may or may not be simultaneously co-registered.

[0079] The computer system / subsystem 130 may also include one or more additional output ports for transferring data to other devices. For example, the computer may include an output port for transferring data to a data archive or memory 131. The computer system / subsystem 130 may also include a user interface, which may include software and hardware configured to allow an operator to use or interact with the system.

[0080] The components of the system 102 may be used in concert during a vascular imaging method or procedure involving the collection of extravascular and intravascular image data during a mobile procedure. In the context of performing such a procedure and acquiring the necessary image data, an exemplary method for intravascular imaging registration may be performed or carried out.

[0081] For example, a patient 100 may be positioned on a table 110 for extravascular imaging of a portion of a blood vessel of interest. The patient 100 or the table may be arranged or adjusted to provide a desired view of the blood vessel of interest in preparation for collection of the extravascular image data. In addition, an intravascular imaging catheter 120 may be introduced into the portion of the blood vessel of interest in preparation for a transfer procedure to collect intravascular image data. The intravascular imaging catheter 120 may be navigated and positioned within the blood vessel (often under fluoroscopy) such that the imaging element is located at a desired starting position for the transfer procedure. A guide catheter may be used to assist with navigation. Once in the proper position, the transfer procedure may be performed or implemented. The necessary extravascular and intravascular image data may be obtained before or during the transfer procedure. In this context, or as part of this process, an exemplary method for vascular imaging co-registration or registration may be performed or implemented.

[0082] Further details regarding co-registering intravascular image data with extravascular image data can be found in U.S. patent application Ser. No. 63 / 157,427, filed March 5, 2021, which is incorporated by reference in its entirety into this specification.

[0083] In some cases, the hemodynamic data may include blood pressure data. As an example, fractional flow reserve (FFR) data may be obtained that compares blood pressure measured in the aorta to blood pressure measured elsewhere, such as in the coronary arteries. If there is no blockage or other obstruction that impedes blood flow through the coronary arteries, the blood pressure measured in the coronary arteries is expected to be the same as the blood pressure measured at the aorta. The FFR may be considered to be the ratio of the two blood pressure values. If the ratio is less than one, this means that the blood pressure in the currently examined coronary artery is lower than the aortic pressure. This may indicate a blockage or other obstruction to blood flow in that particular coronary artery. In some cases, hemodynamic data, such as FFR (fractional flow reserve) data, may be co-registered with extravascular image data, such as angiography data. Intravascular image data, such as IVUS (intravascular ultrasound), may be co-registered with the same extravascular image data to obtain both hemodynamic and intravascular image data for each location of interest in the extravascular image data.

[0084] It will be understood that the present disclosure is in many respects merely illustrative. Changes may be made in details, particularly in matters of shape, size, and arrangement of steps, without exceeding the scope of the present disclosure. This may include, to the extent appropriate, using any of the features of one exemplary embodiment in other embodiments. The scope of the invention is, of course, defined in the language in which the appended claims are expressed.

Claims

1. training a neural network, the training of the neural network comprising: providing a plurality of extravascular image data sets to said neural network; providing a plurality of intravascular image data sets to the neural network, each intravascular image data set including intravascular image data illustrating a portion of a blood vessel from a start location to an end location, each intravascular image data set being co-registered with a corresponding extravascular image data set of the plurality of extravascular image data sets; providing a plurality of hemodynamic data sets to the neural network, each hemodynamic data set being co-registered with a corresponding extravascular image data set of the plurality of extravascular image data sets; the neural network using the provided plurality of intravascular image data sets and the provided plurality of hemodynamic data sets, each co-registered with the corresponding extravascular image data set, to learn which hemodynamic data are expected for a given intravascular image data set, thereby creating a trained neural network; The method comprises using the trained neural network with a subsequent patient, the using the trained neural network with a subsequent patient comprising: performing an intravascular imaging operation in which an intravascular imaging element is moved from a start position to an end position within the patient's blood vessel to generate one or more intravascular images; predicting, by the trained neural network, a hemodynamic value corresponding to the one or more intravascular images from the intravascular imaging operation using its training; and outputting the one or more intravascular images in combination with the predicted hemodynamic values; 16. A method for evaluating patient hemodynamic data comprising:

2. 2. The method of claim 1, wherein at least some of the plurality of hemodynamic data sets provided in the course of training the neural network consist of blood pressure data acquired with any hyperemic or non-hypemic index.

3. 3. The method of claim 1, wherein at least some of the plurality of intravascular image data sets and at least some of the corresponding hemodynamic data sets are co-registered using their corresponding points in 2D or 3D space on the corresponding extravascular image data sets.

4. 4. The method according to claim 1, wherein the neural network comprises one or more of an ensemble of neural networks, a CNN (Convolutional Neural Network) with a Transformer, or a multi-layer neural network.

5. At least some of the intravascular image data sets provided during training of the neural network include quantitative data such as lumen boundary, vessel boundary, side branch boundary, blood speckle density, and cardiac cycle parameters; The quantitative data is used in training the neural network. The method according to any one of claims 1 to 4.

6. the one or more intravascular images from the intravascular imaging operation include anatomical landmarks; the predicted hemodynamic values ​​include predicted blood pressure values ​​proximate the anatomical landmarks. The method according to any one of claims 1 to 5.

7. 7. The method of claim 1, wherein outputting the one or more intravascular images in combination with the predicted hemodynamic values ​​comprises displaying the one or more intravascular images and the predicted hemodynamic values ​​on a graphical user interface of a signal processing unit.

8. 8. The method of claim 7, wherein displaying the one or more intravascular images and the predicted hemodynamic values ​​on a graphical user interface of a signal processing unit comprises displaying a representation of the fully co-registered predicted hemodynamic values ​​together with the intravascular images.

9. 8. The method of claim 7, wherein displaying the one or more intravascular images and the predicted hemodynamic values ​​on a graphical user interface of a signal processing unit comprises displaying a fully tri-registered representation of the predicted hemodynamic values ​​together with the intravascular images and corresponding extravascular images.

10. providing a plurality of intravascular image data sets to a neural network, each intravascular image data set including intravascular image data illustrating a portion of a blood vessel co-registered with an extravascular image from a corresponding extravascular image data set from a start location to an end location; providing a plurality of hemodynamic data sets to the neural network, each hemodynamic data set including hemodynamic data from a corresponding portion of the blood vessel, as represented by one of the plurality of intravascular image data sets, from a start location to an end location, co-registered with a corresponding extravascular image from the corresponding extravascular image data set; said neural network using the provided intravascular image data set and the corresponding provided hemodynamic data set from co-registration of each data set to the same extravascular image to learn which hemodynamic data is expected for a given intravascular image data set, thereby training said neural network; performing an intravascular imaging operation on the new patient, in which the imaging element is moved within the blood vessel from a start position to an end position to generate one or more intravascular images; the neural network using its training to predict hemodynamic values ​​corresponding to the one or more intravascular images from the intravascular imaging operation; outputting the one or more intravascular images in combination with the predicted hemodynamic values. A method for processing image data.

11. acquiring intravascular image data from an intravascular imaging device, the acquiring including an imaging operation during a moving procedure in which the intravascular imaging element is moved from a start position to an end position within a blood vessel, the intravascular image data including one or more intravascular images; inputting the one or more intravascular images into a trained neural network to determine a predicted blood pressure measurement for each of the one or more intravascular images; calculating a set of blood pressure values ​​within the blood vessel corresponding to an intravascular location of each of the one or more extravascular images; calculating a blood pressure ratio based on the series of blood pressure values. A method for processing patient image data.

12. The intravascular image data; The calculated blood pressure corresponding to the point in the vessel and The method of claim 11 , further comprising outputting:

13. acquiring extravascular image data including one or more extravascular images; co-registering the intravascular image data with the extravascular image data to determine an intravascular location of each of the one or more extravascular images; 13. The method of claim 11 or 12, further comprising:

14. 14. The method of claim 13, further comprising outputting the co-registered extravascular image data in combination with the intravascular image data and calculated blood pressure points corresponding to the points within the blood vessel.

15. The method of any one of claims 11 to 14, wherein acquiring extravascular image data comprises acquiring extravascular image data corresponding to the blood vessel from the start location to the end location.

Images