Providing guidance for angiography sequence imaging

Abstract

The subject matter of the present disclosure relates to a computer-implemented method of providing guidance for angiography sequence imaging. The computer-implemented method includes receiving a plurality of angiographic images of a region of interest during angiographic sequence imaging, where each of the plurality of angiographic images is associated with a viewing angle of view of a coronary artery structure in the region of interest; identifying one or more segments of a coronary artery structure in each of the plurality of angiographic images; and providing an indication that one or more of the identified one or more coronary artery segments require one or more additional angiography images associated with different viewing angles.

Description

Field of the Invention

[0001] The present invention relates to a computer-implemented method for providing guidance for angiographic sequence imaging, a computer-implemented method for providing guidance for percutaneous coronary intervention, a transient or non-transient computer-readable storage medium, and a system. Background Art

[0002] During angiographic sequence imaging of the 3D structure of the coronary arteries, medical professionals need to observe each relevant coronary artery segment from at least two different X-ray views. Without obtaining at least two different X-ray views, it is difficult to correctly identify segments of the coronary artery structure that are not distinguishable from each 2D projection, such as stenoses. This is because some stenoses are highly isotropic and therefore appear clearly in 2D from a specific perspective, but are almost invisible from other perspectives. Therefore, a lesion may be visible from one orientation of the segment, but not from another orientation of the segment. In such cases, a single image may provide a false-negative diagnosis of certain stenoses. Therefore, it is difficult to disambiguate coronary artery segments that require invasive intravascular treatment (such as percutaneous coronary intervention).

[0003] The object of the present invention is to improve the prior art. Summary of the Invention

[0004] According to a first aspect of the present invention, a computer-implemented method for providing guidance for sequential angiographic imaging is provided, the computer-implemented method comprising: receiving a plurality of angiographic images of a region of interest during sequential angiographic imaging, wherein each angiographic image in the plurality of angiographic images is associated with a viewing perspective of coronary artery structures in the region of interest; identifying in each angiographic image in the plurality of angiographic images a left-hand or right-hand coronary artery tree having a different arrangement of segments and identifying one or more segments of the identified coronary artery tree; and providing an indication that one or more of the identified one or more coronary artery segments requires one or more additional angiographic images associated with a different viewing perspective, the different viewing perspective having clinical relevance for the identified one or more segments, the clinical relevance supplementing the viewing perspective in the plurality of angiographic images.

[0005] Thus, if during identification of a segment of interest in available angiographic images it is found that the angiographic images have too limited clinical relevance for that particular segment, an indication can be provided that guides the clinician to capture additional angiographic images at different viewing perspectives that supplement the clinical relevance of the original images for the identified segment.

[0006] In particular, for a segment of interest comprising, for example, a stenosis, lesion, or occlusion, this protects accurate identification of such a stenosis, lesion, or occlusion in situations where the available angiographic images are of too limited clinical relevance for that particular segment of interest. This may be due (but not necessarily due) to the identification step revealing that the segment of interest is visible in angiographic images acquired from only a single viewing angle or from multiple viewing angles that are not sufficiently different.

[0007] However, in an embodiment, the clinical relevance of the viewing angle is determined by one or more parameters selected from the group consisting of: clutter of the coronary artery segment and foreshortening of the coronary artery segment. Thus, in the identification step, the clutter and foreshortening of the segment of interest in the available angiographic images are determined, and this information is used to determine an indication of the need to acquire additional images from viewing angles having complementary clinical relevance.

[0008] As used herein, "clutter" refers to the obstruction of a coronary artery segment due to the presence of different structures (in this case, other blood vessels) within the detector's field of view. "Foreshortening" refers to the reduction in length of a coronary artery segment that occurs when the coronary artery segment extends at an angle to the imaging plane.

[0009] In an embodiment, the viewing angle comprises one or more rotation angles of the X-ray detector when capturing corresponding angiographic images of the plurality of angiographic images, or angiographic view classifications.

[0010] The X-ray detector may be an X-ray detector from a C-arm device.

[0011] In an embodiment, the computer-implemented method may further include determining the viewing angle associated with each of the angiographic images by applying each of the angiographic images to a neural network model, the neural network model being trained to determine the viewing angle of the angiographic images; or determining the angiographic view classification associated with each of the angiographic images using metadata associated with each of the angiographic images when the viewing angle includes one or more rotation angles of the X-ray detector when capturing the corresponding angiographic image in the plurality of angiographic images, wherein the metadata describes the one or more angles of the X-ray detector.

[0012] In either case, the workload on the clinician is reduced. In the case of using a neural network, the viewing angle is determined even if metadata is not available. The availability of metadata means that the neural network does not need to be trained and is more computationally efficient.

[0013] In an embodiment, identifying one or more segments of the coronary artery structure in each angiographic image comprises retrieving the coronary artery segments associated with the viewing angle from a database that maps viewing angles to coronary artery segments.

[0014] Retrieving the coronary artery segments from the database is a computationally efficient way to obtain the coronary artery segments.

[0015] In an embodiment, identifying one or more segments of a coronary artery structure in each angiographic image includes applying each angiographic image to a neural network model trained to identify one or more coronary artery segments from angiographic images. A well-trained neural network obviates the need for reliable identification of viewing angles.

[0016] In an embodiment, the computer-implemented method may further include: determining, for each of the one or more segments, a number of different viewing angles associated with each of the one or more identified segments of the coronary artery structure in the plurality of angiographic images; and comparing the determined number of different viewing angles associated with each of the one or more coronary artery segments to a threshold number of viewing angles, wherein providing the indication that the one or more coronary artery segments require one or more additional angiographic images associated with different viewing angles includes identifying the one or more coronary artery segments for which the number of different viewing angles is below the threshold number. For example, guidance is provided to ensure that a physician has access to at least two viewing angles for a vessel segment of interest that includes a stenosis. In other words, the threshold number may be two.

[0017] In an embodiment, a neural network is used to identify either the left or right coronary artery tree from each angiographic image. Once the coronary tree has been identified, it is easier to identify the coronary segments of interest because the left-hand and right-hand trees have different arrangements of segments. This is most beneficial when segment visibility is defined by acquisition angle (as opposed to being evaluated by the network).

[0018] If you know the angle and use the guides to determine which segments are well visible, then one piece of information you need from the image is whether it is the right or left tree being imaged.

[0019] In an embodiment, providing the indication comprises displaying a map of the coronary artery structure, wherein the map comprises the identified one or more coronary artery segments requiring one or more additional angiographic images associated with a different viewing perspective than the remaining one or more coronary artery segments.

[0020] In an embodiment, displaying the identified one or more coronary artery segments requiring one or more additional angiographic images associated with a different viewing angle than the remaining one or more coronary artery segments includes displaying the identified one or more coronary artery segments requiring the additional angiographic images associated with the different viewing angle in a different color than the other coronary artery segments. Color coding the segments in the graph is intuitive for quick and easy interpretation by a clinician.

[0021] In an embodiment, the map of the coronary artery structure comprises at least one of a graphical map and a textual map.

[0022] According to one aspect, a computer-implemented method for providing guidance for percutaneous coronary intervention is provided, the computer-implemented method comprising: guiding angiographic sequence imaging according to the computer-implemented method of any preceding aspect or embodiment; receiving an image of a region of interest during the percutaneous coronary intervention; and displaying on a display the image of the region of interest and an indication of one or more identified coronary artery segments requiring one or more angiographic images associated with different viewing angles.

[0023] In this way, for example, a clinician performing an intervention can understand in real time whether a segment is a suitable candidate for balloon placement.

[0024] In an embodiment, the computer-implemented method further comprises determining, in the received image, a coronary artery segment location of the interventional tool during the percutaneous coronary intervention, wherein providing an indication of the identified one or more coronary artery segments requiring one or more additional angiographic images associated with different viewing angles comprises providing an indication that the identified coronary artery segment where the interventional tool is located requires one or more additional angiographic images associated with different viewing angles in response to determining that the interventional tool is located in one of the identified one or more coronary artery segments requiring one or more additional angiographic images associated with different viewing angles.

[0025] In an embodiment, the computer-implemented method further comprises aligning the image of the region of interest received during the percutaneous coronary intervention with one of the multiple angiographic images of the region of interest received during angiographic sequence imaging; wherein determining the coronary artery segment position of the interventional tool during the percutaneous coronary intervention based on the image of the region of interest received during the percutaneous coronary intervention is based on aligning the image of the region of interest received during the percutaneous coronary intervention with one of the multiple angiographic images of the region of interest received during angiographic sequence imaging.

[0026] According to an aspect, there is provided a transitory or non-transitory computer-readable storage medium storing instructions which, when executed by a processor, cause the processor to perform a computer-implemented method according to any preceding claim.

[0027] According to one aspect, a system is provided, comprising: a storage device including a non-transitory computer-readable storage medium of the aforementioned aspects stored thereon; at least one processor configured to execute instructions from the non-transitory computer-readable storage medium; and a display configured to: display an indication of one or more identified coronary artery segments requiring one or more additional angiographic images associated with different viewing angles, and / or display a received image of a region of interest with the indication of one or more identified coronary artery segments requiring one or more additional angiographic images associated with different viewing angles.

[0028] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Embodiments of the invention may best be understood with reference to the accompanying drawings, in which:

[0030] Figure 1 shows a schematic cross-sectional view of a C-arm device;

[0031] Figure 2 A block diagram of a system for executing a method according to an embodiment of the present invention is shown;

[0032] Figure 3 A flowchart illustrating steps involved in a computer-implemented method for providing guidance for angiographic sequence imaging and a computer-implemented method for providing guidance for percutaneous coronary intervention according to an embodiment of the present invention;

[0033] Figure 3A More details are shown from Figure 3 Display 310;

[0034] Figure 4 A schematic diagram is shown, which illustrates the Figure 3 corresponding well-visible and foreshortened coronary artery segments of angiographic images captured during angiographic sequence imaging;

[0035] Figure 5 A schematic diagram illustrating the left and right coronary artery trees is shown;

[0036] Figure 6 Shows a summary from Figure 3A flowchart of a computer-implemented method for providing guidance for angiographic sequence imaging; and

[0037] Figure 7 Shows a summary from Figure 3 Flowchart of a computer-implemented method for providing guidance for percutaneous coronary intervention. DETAILED DESCRIPTION

[0038] At least some of the example embodiments described herein can be constructed using dedicated, specialized hardware in part or in whole. Terms such as parts, modules or units used herein can include but are not limited to hardware devices, such as circuits in the form of discrete or integrated components, field programmable gate arrays (FPGAs) or application specific integrated circuits (ASICs), which perform certain tasks or provide associated functions. In some embodiments, the elements described can be configured to reside on a tangible, persistent, addressable storage medium, and can be configured to execute on one or more processors. In some embodiments, by way of example, these functional elements can include parts, such as software components, object-oriented software components, class components and task components, processes, functions, attributes, processes, subroutines, program code segmentation, drivers, firmware, microcodes, circuits, data, databases, data structures, tables, arrays and variables. Although example embodiments have been described with reference to the parts, modules and units discussed herein, such functional elements can be combined into fewer elements or divided into additional elements. Various combinations of optional features have been described herein, and it should be understood that the features described can be combined in any suitable combination. In particular, the features of any one example embodiment can be appropriately combined with the features of any other embodiment, unless such a combination is mutually exclusive. Throughout the specification, the term "comprise" or "comprising" means including the specified part(s) but does not exclude the existence of other parts.

[0039] The methods described herein may be computer-implemented methods. In particular, the methods may include at least a computer-implemented method for generating a composite video and a computer-implemented method for training one or more machine learning algorithms. A computer implementing these methods may include a storage device, such as a memory, and a processor. The computer may be a hardware computer, and thus the storage device and processor may be a hardware storage device and a hardware processor, respectively.

[0040] The computer-implemented method may be provided as instructions stored on a transient or non-transient computer-readable medium. The computer-readable medium may be stored in a storage device of a computer. When the instructions are executed by a processor, the instructions cause the processor to perform any method steps described herein.

[0041] Angiographic imaging is a diagnostic medical imaging technique that utilizes X-rays to observe coronary artery structures, such as the coronary artery tree or arteries. An angiographic image is a 2D X-ray image of the coronary artery structure, including multiple coronary artery segments. During angiographic imaging, medical professionals aim to image the coronary artery structure from multiple viewing angles in order to obtain an angiogram having a view of each of the coronary artery segments of the coronary artery structure. If only one viewing angle of the coronary artery structure is obtained, information present in dimensions orthogonal to the imaging plane is not obtained. For example, if a coronary artery segment extends orthogonally to the imaging plane, a dangerous narrowing (i.e., stenosis) of the coronary artery segment will not be observable in a single viewing angle of the coronary artery structure.

[0042] Once identified, endovascular procedures can be used to treat the stenosis. For example, percutaneous coronary intervention (PCI) involves inserting a stent and / or balloon over a guidewire into the patient's coronary artery structure to widen and support the narrowed coronary artery segment. During PCI, medical professionals typically do not use contrast injections. Instead, alternative imaging techniques are used to obtain images in which the interventional tools are visible.

[0043] To achieve sequential angiographic imaging, a contrast agent that is opaque to X-rays is first injected into the patient, and then multiple angiographic images are acquired using an X-ray detecting medical device (such as a C-arm device).

[0044] refer to Figure 1 The C-arm device 100 generally includes an X-ray source 140 and an X-ray detector 150, which are arranged at either end of an arc-shaped arm 130. The source 140 and the detector 150 are arranged opposite each other, thereby forming a line of sight between the source 140 and the detector 150, so that signals emitted by the source 140 can be detected by the detector 150. During imaging, the patient is positioned on the operating table surface between the source 140 and the detector 150 of the C-arm 130, so that the line of sight impinges on the patient's body. For a given position of the line of sight relative to the patient's body, the C-arm 130 obtains an image having a specific viewing angle of the patient's body.

[0045] The C-arm 130 is connected to a base structure 110, such as a stand, by a support arm 120. The C-arm 130 is movable relative to the base structure 110 by at least a rotational motion. The C-arm 130 is movable relative to the operating table surface and the patient thereon by translational and rotational motion. With respect to translational motion, the C-arm can move 130 in horizontal and vertical planes. With respect to rotational motion, the C-arm 130 can move by orbital rotation 160 (i.e., rotation within the plane of the C-arm) about the geometric center of the arc of the C-arm. Additionally, the C-arm can move by angular rotation 170 about the axis of the support arm to provide a propeller-like rotation of the C-arm.

[0046] Thus, the C-arm 130 can be repositioned to obtain multiple angiograms of the coronary artery structures, wherein each angiogram is associated with a different viewing perspective relative to the patient. For example, for a particular region of interest, such as a particular translational position of the patient's body, the C-arm 130 can be repositioned by orbital and / or angular rotations. Thus, each angiographic image is associated with a viewing perspective that includes one or more of the translational position, orbital rotation (i.e., orbital angle) 160, and angular rotation (i.e., angular angle) 170 of the C-arm 130. The translational component can be used to position the heart at the C-arm isocenter. Therefore, the C-arm angle is more important in identifying which segments are visible.

[0047] The metadata for each angiography image includes the viewing angle information described above. The angiography and corresponding metadata may be stored at the C-arm device 100 and / or at a remote server communicatively linked to the C-arm device 100 .

[0048] Angiographic view classification corresponds to the classification of views according to orbit (rotation) and / or angulation (i.e., the angular position of the C-arm achievable by roll and propeller movement, respectively). Coronary artery segments have different visibility levels at different viewing angles. Clinically relevant views for specific segments of interest provide excellent visibility of these specific coronary artery segments.

[0049] In particular, clinically relevant viewing angles are associated with minimal clutter and / or foreshortening of the imaged coronary artery segment of interest, thereby allowing for appropriate diagnosis of, for example, vessel stenosis.

[0050] Typically, angiographic view classifications are classified as a right anterior oblique (RAO) view, a left anterior oblique (LAO) view, or an anteroposterior (AP) view. These view classifications refer to the angulation direction (propeller movement) of the C-arm 130 relative to the patient. For example, a RAO view corresponds to an angulation of the C-arm 130 such that the patient's right hand side is within the detector's field of view. Conversely, a LAO view corresponds to an angulation of the C-arm 130 such that the patient's left hand side is within the detector's field of view. An AP view corresponds to an angulation of the C-arm 130 such that the detector is perpendicular to the patient.

[0051] Each of the RAO, LAO, and AP views can be further classified as cranial or caudal. These view classifications refer to the direction of orbital rotation (roll movement) of the C-arm 130 relative to the patient. The cranial view classification corresponds to orbital rotation of the C-arm 130 toward the patient's head. Conversely, the caudal view classification corresponds to orbital rotation of the C-arm 130 toward the patient's feet.

[0052] The methods disclosed herein can be performed by Figure 2The illustrated system 200 performs the following operations: The system 200 includes a storage device 210 comprising a non-transitory computer-readable storage medium, a processor 220, and a display 230.

[0053] Also refer to Figure 2 The system is configured to receive a plurality of angiographic images. For example, the system 200 is communicatively linked to a server, which is communicatively linked to the C-arm device 100. The system 200 may receive angiograms from the server via a wireless connection (such as Bluetooth or Wi-Fi) or through a physical connection (such as a cable). Alternatively, the system may receive angiograms from a storage device directly connected to the system.

[0054] Also refer to Figure 2 The system display 230 is configured to display an indication of the identified one or more coronary artery segments for which one or more additional angiographic images associated with different viewing angles are required, and / or to display the received image of the region of interest together with an indication of the identified coronary artery segments for which one or more additional angiographic images associated with different viewing angles are required.

[0055] In particular, the viewing perspective of the additional angiographic images can supplement the viewing perspective of the original angiographic images in terms of clinical relevance. For example, the additional angiographic images can visualize the identified coronary artery segments with less foreshortening and / or less clutter. The system display 230 can also be configured to display the one or more angiographic images along with the received images and indications of regions of interest.

[0056] Figure 3 An overview illustrating two computer-implemented methods is shown. The first computer-implemented method is a method for providing guidance for angiographic sequence imaging. The second computer-implemented method is a method for providing guidance for percutaneous coronary intervention.

[0057] refer to Figure 3 A method for providing guidance during a diagnostic procedure uses a C-arm to capture a plurality of angiographic images 300 during angiographic image sequencing. A viewing angle 302 of a coronary artery structure in a region of interest of the angiographic image is determined.

[0058] As described above, the viewing angle includes one or more rotation angles of the X-ray detector when capturing corresponding angiography images in the plurality of angiography images, or angiography view classification.

[0059] When determining the viewing angle 302, the method may include determining the viewing angle 302 associated with each of the angiographic images 300 by applying each angiographic image to a neural network model trained to determine the viewing angle for angiographic images. In other embodiments, when the viewing angle includes one or more rotation angles of an X-ray detector when capturing a corresponding angiographic image in the plurality of angiographic images, the method may include using metadata associated with each of the angiographic images to determine an angiographic view classification associated with each of the angiographic images 300. The metadata describes the one or more angles of the X-ray detector when capturing the associated angiographic image.

[0060] In other embodiments, the view classification may be determined by applying the angiographic image to a neural network trained to determine the view classification based on features in the angiographic image. The neural network may be a first neural network.

[0061] The method also includes identifying one or more segments 304 (or visible segments) of the coronary artery structure in each of the plurality of angiographic images 300 .

[0062] In some embodiments, this step includes retrieving the coronary artery structure associated with the viewing angle from a database that maps coronary artery structures to viewing angles. The mapping can be based on medical guidelines. Each angiographic image can be applied to a neural network classifier trained to identify, for example, left or right coronary artery structures from the angiographic image. Using the coronary artery structure, a specific segment or segments can be retrieved more accurately. The neural network classifier can be a third neural network. The neural network classifier can be a convolutional neural network.

[0063] In other embodiments, this step includes applying each angiographic image to a neural network model trained to identify one or more coronary artery segments directly from the angiographic image. In this manner, there is no need to retrieve the segments from a database. The neural network can be a second neural network, which can be a convolutional neural network. The neural network can be trained using angiographic images labeled with any coronary artery segments visible therein.

[0064] By "visible" it is meant that the segments are shown in a way that does not obscure the segments. For example, the segments are not shown with any foreshortening.

[0065] Brief Reference Figure 4, segment 400 is shown. An orthogonal projection 402 of the segment as shown and a lesion 404 can be seen on the projection. Such an orthogonal projection 402 is considered satisfactory because there is no foreshortening of segment 400. In other words, in the orthogonal projection, the segment is well visible and, without the clutter as in this schematic representation, can be considered to have high clinical relevance for segment 400.

[0066] Figure 4 Also shown in FIG. 4 is a longitudinal projection 406, in which the segment is shown coaxially in the angiogram. In other words, the detector is oriented to coincide with the longitudinal axis of the segment. The longitudinal projection 406 shows a foreshortened segment in which the lesion is not visible. In other words, the segment is not well visible in the presence of foreshortening.

[0067] As in this example, an angiographic image showing a segment with significant foreshortening may be considered to be of insufficient clinical relevance for the clinical task at hand (e.g., determining the severity of a stenosis). In such cases, it may be necessary to acquire additional angiographic images from viewing angles that supplement the original images in terms of clinical relevance. In this particular example, a viewing angle is selected for the additional angiographic images that shows the segment of interest with little or no foreshortening.

[0068] You can refer to Figure 5 The coronary artery structure is best understood, Figure 5 The right coronary artery structure RCA or tree 410 and the left coronary artery structure LCA or tree 412 are shown. Both trees RCA 410, LCA 412 include an arrangement of multiple segments. The arrangement of the segments differs between the trees. The right tree 410 includes segments 1 to 4 and 16 to 16c. The left tree 412 includes segments labeled 5 to 14b. By way of example, Figure 5 The arrangement of the coronary artery segments according to the reference American Heart Association classification is depicted.

[0069] like Figure 5 As shown, because the tree extends three-dimensionally, some orientations of the detector will mean that the segment is anywhere from orthogonal to the longitudinal direction of the segment to the longitudinal axis of the segment.

[0070] Also refer to Figure 3, the method may further include: determining, for each of the one or more segments, a number of different viewing angles associated with each of the one or more identified segments of the coronary artery structure in the plurality of angiographic images; and comparing the determined number of different viewing angles associated with each of the one or more coronary artery segments with a threshold number of viewing angles. In some embodiments, the threshold number of viewing angles may be 2. In other words, the method may check to see if there are two different viewing angles for each segment. A clinical recommendation is to ensure that each segment has been viewed from at least two different viewing angles to ensure that a significant risk of stenosis features is not missed. The different viewing angles may be substantially different. For example, the different viewing angles may be viewing angles that show the segments substantially orthogonally to each other.

[0071] The method may include providing an indication that one or more of the identified one or more coronary artery segments require one or more additional angiographic images associated with different viewing angles having complementary clinical relevance. This may be accomplished by displaying a map on the display 310. The display 310 may correspond to a display from Figure 2 Display 230. Figure 3A Shown from Figure 3 An enlarged view of display 310 is shown.

[0072] The diagram may include a diagram showing the coronary artery structure (left coronary artery tree 412 and right coronary artery tree 410) on the display and a textual diagram 308 of the coronary artery structure. The textual diagram 308 may be a table. The table may include two columns. The first column includes the segment number, e.g., Figure 5 The second column may include a description or name or label of the viewing angle of the captured angiogram in which the segment is visible. The textual graph 308 may be color-coded. In other embodiments, the graphical graph may also be color-coded. The color coding may indicate multiple views of the segment. The color coding may be implemented by color-coding the segment number in the first column and the viewing angle label in the second column.

[0073] In one example, the color coding may include: red, where no clinically relevant angiographic images showing the segmentation were captured; yellow, orange, or amber, where there is an angiographic image showing the segmentation, however the clinical relevance of the viewing angle is questionable; and green, where the number of angiographic images showing the segmentation at different orientations is equal to or greater than a threshold.

[0074] In this way, a segment indicated in green means that the available angiographic images are of sufficient clinical relevance for the segment of interest, and no additional images need to be acquired for the clinical task at hand. On the other hand, for segments indicated in yellow or red, additional images with complementary clinical relevance may be required. Optionally, the system proposes viewing perspectives with complementary clinical relevance, or alternatively, the physician can rely on established clinical guidelines to select viewing perspectives with a reasonable likelihood of complementing the already available views.

[0075] Moreover, as described above, displaying the identified one or more coronary artery segments requiring one or more additional angiographic images associated with a different viewing angle than the remaining one or more coronary artery segments includes displaying the identified one or more coronary artery segments requiring the additional angiographic images associated with the different viewing angle in a different color than the other coronary artery segments.

[0076] In other embodiments, providing the indication may be proactive in the sense of proactively alerting the clinician to capture different views of any segment where the number of different clinically relevant views falls below a threshold number.

[0077] In a second method, a plurality of fluoroscopic images 320 are captured during a percutaneous coronary intervention procedure.

[0078] The method may include determining a segmented coronary artery location of an interventional tool during a percutaneous coronary intervention in a received image. The interventional tool may be a deflated balloon. This may first involve balloon segmentation 322, which may be performed using an object recognition model. For example, the object recognition model may be a "You Only Look Once" (YOLO) algorithm or a retinal algorithm.

[0079] Fluoroscopic images do not show blood vessels because contrast agents are not used during the procedure, unlike diagnostic procedures that use contrast agents. To determine the segmented position of the balloon, the fluoroscopic image can be superimposed on the angiogram having the same viewing angle. This superposition is achieved using a correlation algorithm 326. Next, the segmented coronary artery position of the balloon is determined using one or more of the same methods described above for the diagnostic method. In other words, a segmented position method 328 is used to determine the segmented position of the interventional tool (e.g., balloon).

[0080] In this manner, determining a coronary artery segment position of an interventional tool during percutaneous coronary intervention is based on aligning an image of a region of interest received during percutaneous coronary intervention with one of a plurality of angiographic images of the region of interest received during angiographic sequence imaging.

[0081] Display 330 may be present during the interventional procedure. Display 330 may be the same display as display 310 in some embodiments and / or may be the same display as display 310 in some embodiments. Figure 2 The display 330 may be the same as the display 230 used for the diagnostic procedure. The display 330 may display a fluoroscopic image and a diagram (from a diagnostic procedure) side by side. In this manner, the method may include displaying on the display 330 an image of a region of interest (fluoroscopic image) and an indication of one or more identified coronary artery segments requiring one or more angiographic images associated with different viewing angles. This method of displaying indications is passive in the sense that the clinician can self-remember the suitability of the segment for balloon deployment.

[0082] In other embodiments, the indication can be proactively displayed. In other words, in response to determining that the interventional tool is located in one of the one or more identified coronary artery segments that requires one or more additional angiographic images associated with different viewing angles, the method can include providing an indication that the identified coronary artery segment in which the interventional tool is located requires one or more additional angiographic images associated with different viewing angles. This can be achieved by outputting a warning when the balloon has reached a steady-state position in a segment for which too few angiographic images at different viewing angles were captured during the diagnostic phase.

[0083] You can refer to Figure 6 and Figure 7 Summarize the aforementioned methods.

[0084] refer to Figure 6 A computer-implemented method for providing guidance for sequential angiographic imaging according to one or more embodiments is provided. The computer-implemented method includes: receiving S100 a plurality of angiographic images of a region of interest during sequential angiographic imaging, wherein each of the plurality of angiographic images is associated with a viewing perspective of coronary artery structures in the region of interest; identifying S102 a left-hand or right-hand coronary artery tree having a different arrangement of segments in each of the plurality of angiographic images, and identifying one or more segments of the identified coronary artery tree; and providing S104 an indication that one or more of the identified one or more coronary artery segments requires one or more additional angiographic images associated with a different viewing perspective, the different viewing perspective having clinical relevance for the identified one or more segments that supplements the viewing perspectives in the plurality of angiographic images.

[0085] refer to Figure 7 , provides a computer-implemented method for providing guidance for percutaneous coronary intervention. The computer-implemented method comprises: Figure 6A computer-implemented method of an associated embodiment directs S200 angiographic sequence imaging; receives S202 an image of a region of interest during a percutaneous coronary intervention; and displays S204 on a display the image of the region of interest and an indication of one or more identified coronary artery segments requiring one or more angiographic images associated with different viewing perspectives.

[0086] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive; the invention is not limited to the disclosed embodiments.

[0087] By studying the drawings, the disclosure and the appended claims, those skilled in the art can understand and implement other variations of the disclosed embodiments when practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. A single processor or other unit may implement the functions of several items recited in the claims. Although specific measures are recited in mutually different dependent claims, this does not indicate that a combination of these measures cannot be used to advantage. Any reference signs in the claims should not be interpreted as limiting the scope.

Claims

1. A computer-implemented method for providing guidance for angiographic sequence imaging, the computer-implemented method comprising: receiving (S100) a plurality of angiographic images (300) of a region of interest during angiographic sequence imaging, wherein each angiographic image in the plurality of angiographic images is associated with a viewing angle of a coronary artery structure in the region of interest; identifying (S102) a left-hand or right-hand coronary artery tree having a different arrangement of segments in each of the plurality of angiographic images, and identifying one or more segments of the segments of the identified coronary artery tree; and An indication is provided (S104) that one or more of the identified one or more coronary artery segments require one or more additional angiographic images associated with different viewing angles, the different viewing angles having clinical relevance for the identified one or more segments, the clinical relevance supplementing the viewing angles in the plurality of angiographic images.

2. The computer-implemented method of claim 1 , wherein: The viewing angles include one or more rotation angles of the X-ray detector (150) when capturing corresponding angiographic images among the plurality of angiographic images (300), or angiographic view classifications.

3. The computer-implemented method according to any preceding claim, further comprising: determining the viewing angle associated with each of the angiographic images by applying each of the angiographic images to a neural network model, the neural network model being trained to determine the viewing angle for angiographic images; or When the viewing angle includes one or more rotation angles of the X-ray detector when capturing corresponding angiographic images in the multiple angiographic images, an angiographic view classification associated with each angiographic image in the angiographic images is determined using metadata associated with each angiographic image in the angiographic images, wherein the metadata describes the one or more angles of the X-ray detector.

4. A computer-implemented method according to any preceding claim, wherein: Identifying one or more segments of the identified coronary artery tree in each angiographic image includes: The coronary artery segment associated with the viewing angle is retrieved from a database that maps coronary artery segments to viewing angles.

5. The computer-implemented method according to any one of claims 1 to 3, wherein: Identifying one or more segments of the coronary artery tree in each angiographic image includes: Each angiographic image is applied to a neural network model trained to identify one or more coronary artery segments from the angiographic image.

6. The computer-implemented method of any preceding claim, further comprising: determining, for each of the one or more segments, a number of different viewing angles associated with each of the identified one or more segments of the coronary artery structure in the plurality of angiographic images; as well as comparing the determined number of different viewing angles associated with each of the one or more coronary artery segments to a threshold number of viewing angles, Wherein providing the indication of the one or more coronary artery segments requiring one or more additional angiographic images associated with different viewing angles comprises identifying the one or more coronary artery segments for which the number of different viewing angles is below the threshold number.

7. A computer-implemented method according to any preceding claim, wherein: The clinical relevance of the viewing angle is determined by one or more parameters selected from the group consisting of: clutter of a coronary artery segment, and foreshortening of a coronary artery segment.

8. A computer-implemented method according to any preceding claim, wherein: Providing the indication includes displaying a map of the coronary artery structure, wherein the map includes the identified one or more coronary artery segments requiring one or more additional angiographic images associated with a different viewing perspective than the remaining one or more coronary artery segments.

9. The computer-implemented method of claim 8, wherein: Displaying the identified one or more coronary artery segments requiring one or more additional angiographic images associated with a different viewing angle than the remaining one or more coronary artery segments includes displaying the identified one or more coronary artery segments requiring the additional angiographic images associated with the different viewing angle in a different color than other coronary artery segments.

10. The computer-implemented method according to any one of claims 7 to 9, wherein: The map of the coronary artery structure includes at least one of: a graphical map, and a textual map (308).

11. A computer-implemented method for providing guidance for percutaneous coronary intervention, the computer-implemented method comprising: guiding (S200) angiographic sequence imaging according to a computer-implemented method according to any preceding claim; receiving ( S202 ) an image of the region of interest during percutaneous coronary intervention; The image of the region of interest and an indication of the identified one or more coronary artery segments requiring one or more angiographic images associated with different viewing angles are displayed (S204) on a display (230).

12. The computer-implemented method of claim 11 , further comprising: determining, in the received image, a coronary artery segment location of an interventional tool during said percutaneous coronary intervention, Wherein providing the indication of the identified one or more coronary artery segments requiring one or more additional angiographic images associated with different viewing angles comprises: In response to determining that the interventional tool is located in one of the one or more identified coronary artery segments that requires one or more additional angiographic images associated with a different viewing angle, providing an indication that the identified coronary artery segment in which the interventional tool is located requires one or more additional angiographic images associated with a different viewing angle.

13. The computer-implemented method of claim 12, further comprising: aligning the image of the region of interest received during the percutaneous coronary intervention with an angiographic image of a plurality of angiographic images of the region of interest received during angiographic sequence imaging; Wherein, determining the coronary artery segment position of the interventional tool during the percutaneous coronary intervention based on the image of the region of interest received during the percutaneous coronary intervention is based on: aligning the image of the region of interest received during the percutaneous coronary intervention with one of the multiple angiographic images of the region of interest received during angiographic sequence imaging.

14. A transitory or non-transitory computer-readable storage medium storing instructions which, when executed by a processor, cause the processor to perform the computer-implemented method according to any preceding claim.

15. A system comprising: a storage device (210) comprising the non-transitory computer-readable storage medium of claim 14 stored thereon; at least one processor (220) configured to execute the instructions from the non-transitory computer-readable storage medium; and A display (230) configured to: displaying an indication of the identified one or more coronary artery segments requiring one or more additional angiographic images associated with different viewing angles, and / or The received image of the region of interest is displayed along with the indication of the identified coronary artery segment requiring one or more additional angiographic images associated with the different viewing angles.

Images