Vascular diagnosis device and method

Abstract

Concepts for vascular diagnosis are presented that include generating a composite view of a field of view of a patient's anatomy, the composite view including diagnostic data. More specifically, the method includes: obtaining angiography data of a vascular system of a patient; processing the angiography data to generate semantic angiography data; processing the semantic angiography data to determine one or more velocity profiles according to the one or more locations; determining one or more characteristics based on the one or more velocity profiles according to the one or more locations; generating diagnostic data corresponding to the one or more locations; and generating a composite view including the diagnostic data.

Description

Technical Field

[0001] The present invention relates to a blood vessel diagnosis device and method. Background Art

[0002] Vascular diagnostic devices are used to diagnose vascular health conditions. Existing methods have utilized some flow audible characteristics as diagnostic materials in vascular diseases.

[0003] For decades, noninvasive spectral Doppler waveform analysis has been used as one of the primary diagnostic tools for vascular disease. Current devices and methods for vascular diagnosis utilize duplex Doppler ultrasound. Doppler ultrasound allows for the visualization of blood flow waveforms, which allows for a more quantitative and comprehensive assessment.

[0004] Despite this, ultrasound has significant limitations. Some blood vessels are difficult to visualize correctly with ultrasound, particularly when they are located too deep in the body or too close to bone (e.g., in the popliteal region).

[0005] Furthermore, the use of ultrasound in the context of intravascular interventional X-rays requires the sonographer to be present in a catheterization laboratory, which can be problematic for several reasons (e.g., lack of available technicians, disruption to workflow, and sonographer reluctance to practice in an ionizing environment). Summary of the Invention

[0006] The invention is defined by the claims.

[0007] According to an example of one aspect of the present invention, a vascular diagnostic system is provided, which includes at least one processor, and the at least one processor is configured to: obtain angiographic data of a patient's vascular system, the angiographic data including a field of view of the patient's vascular system; process the angiographic data to generate semantic angiographic data, the semantic angiographic data including information about the presence of anatomical features in the field of view and the location at which the anatomical features exist in the field of view; process the semantic angiographic data to determine one or more velocity curves based on one or more locations, wherein the velocity curve includes data on blood velocity relative to time at a specific location in the field of view; determine one or more characteristics based on the one or more velocity curves based on the one or more locations; generate diagnostic data corresponding to the one or more locations based on the one or more characteristics and the semantic angiographic data; and generate a composite view including the diagnostic data.

[0008] The proposed embodiments enable the generation of a composite view showing diagnostic data according to one or more locations in a field of view. The diagnostic data may include data or characteristics corresponding to multiple velocity profiles representing different locations in the field of view. In addition, the diagnostic data may include diagnostic indications regarding conditions present within the field of view. The diagnostic data may be generated taking into account semantic angiographic data that provides semantic information regarding the location and properties of blood vessels that may be present in the field of view, and further taking into account one or more diagnostic rules for specific locations within the field of view.

[0009] The resulting composite view provides automated vascular assessment across the entire X-ray field of view, overcoming many of the shortcomings of existing techniques.

[0010] The method of the present invention alleviates some or all of the problems mentioned with the use of ultrasound (eg, sonographer availability, issues with deep vessels, or workflow constraints).

[0011] The proposed concept makes measurement much simpler, as conventional ultrasound requires not only reasonably accessible blood vessels but also precise alignment of the ultrasound beam with the vessel. Without this alignment, velocity cannot be accurately measured. This is not a problem with X-ray-based measurement techniques.

[0012] In contrast to what is currently possible with ultrasound, the proposed concept analyzes not only one spatial location (e.g., a given vessel segment), but all sizable vessels within the field of view. Thus, the composite view generated according to the present invention allows providing the user with a more complete and useful picture.

[0013] The disclosed concept does not require any manual interaction to generate diagnostic data across the field of view. Therefore, the present invention is much faster than any known diagnostic technology.

[0014] The present invention enables direct comparison of blood vessels with surrounding vessels, and these comparisons can be used to derive additional diagnostic descriptors (eg, peak velocity ratio).

[0015] The present invention provides the ability to integrate local diagnostic elements together to produce a fully fledged diagnostic map across the entire field of view.

[0016] In an embodiment, the diagnostic data corresponding to the one or more locations is generated by applying one or more diagnostic rules at each of the specific locations in the one or more locations, wherein each of the one or more diagnostic rules includes the following to determine a diagnostic indication as to whether a condition exists at the specific location: comparing the one or more characteristics with one or more reference characteristics; and comparing the specific location with one or more reference locations.

[0017] Thus, one or more diagnostic rules can be applied to a specific location within the field of view to determine whether the location and the characteristic at the location correspond to a reference location and reference characteristic, respectively. If the location corresponds to the reference location and the characteristic corresponds to the reference characteristic, then it can be determined that a condition may exist at the specific location within the field of view. In embodiments, a diagnostic indication may have an associated confidence value that indicates the system's confidence that the diagnostic indication exists. Such diagnostic rules are known in the art.

[0018] In an embodiment, comparing the one or more characteristics with one or more reference characteristics comprises generating a characteristic value based on the characteristic at the specific location, and comparing the characteristic value with one or more reference characteristic values ​​or ranges.

[0019] For example, a blood flow value at a location may be determined and compared to a reference blood flow value or range of blood flow values ​​to determine whether a condition exists at that particular location within the field of view.

[0020] In an embodiment, the processor is configured to obtain one or more further patient characteristics, and wherein the diagnostic rule further comprises comparing the further patient characteristics with one or more further reference characteristics.

[0021] For example, characteristics may include aspects of a patient's medical history or condition that may affect the determination of whether a condition is present at a particular location when the characteristics at that location are considered against a reference characteristic. For example, if a patient takes a particular medication, or has a family history that indicates susceptibility to a particular condition, this may affect the expected characteristics at one or more locations, and the diagnostic indication (i.e., the determination of whether a condition is present at a particular location) may be adjusted accordingly.

[0022] In an embodiment, the one or more characteristics include a degree of stenosis at a particular location.

[0023] In an embodiment, generating diagnostic data corresponding to the one or more locations includes evaluating one or more characteristics corresponding to locations other than the specific location.

[0024] Thus, for each identified vessel, a list of "similar" surrounding vessels can be previously observed or detected or known and identified. These surrounding vessels can be used as comparison points to maintain a given diagnosis.

[0025] Unlike existing methods, in the present invention, diagnostic data is generated for multiple points in the field of view simultaneously, thus being able to provide a more accurate diagnosis by evaluating the property(s) at other locations rather than just at the object location.

[0026] In an embodiment, one or more of the one or more diagnostic rules are modifiable or selectable by a user, resulting in a modified diagnostic indication as to whether a condition exists at the particular location.

[0027] Thus, the user's (operator's) preferences and experience can be factored into the diagnostic instructions.

[0028] In an embodiment, the at least one processor is configured to generate the following, so as to enable extraction of at least one semantic vessel from the vessel segmentation map, thereby enabling processing of the angiography data to generate semantic angiography data, the semantic angiography data comprising information about the presence of anatomical features in the field of view and the locations at which anatomical features are present in the field of view: the vessel segmentation map comprising information about which portions of the field of view include vessels; and one or more labels comprising identification of specific vessels present in the field of view and associated locations of the specific vessels.

[0029] This may provide a convenient method for generating semantic angiographic data.

[0030] Furthermore, the vessels can be semantically segmented, which the present invention enables to be indexed within a table of diagnostic rules. This would not be possible if the vessels were not semantically segmented.

[0031] In an embodiment, the characteristic comprises one or more of: flow direction, phasicity, or curvilinearity.

[0032] The determination of one or more characteristics or descriptors may be critical in vascular diagnosis.

[0033] Flow direction includes determining whether the velocity is oriented from a proximal portion to a distal portion of the vessel.

[0034] Phasicity refers to the phase characteristics of the velocity curve. Velocity curves are typically characterized as single-phase, two-phase, or three-phase. Phasicity can be derived by measuring the behavior of the curve crossing the zero velocity axis.

[0035] Monophasic refers to blood flow or velocity remaining positive and essentially never crossing the zero velocity axis during the cardiac cycle. In the biphasic case, two periods can be observed during the cardiac cycle: a positive velocity period and a negative velocity period. In the triphasic case, two positive velocity periods and one negative velocity period constitute the structure of the flow curve along the cardiac cycle.

[0036] Pulsatility refers to the variation in blood flow or velocity along the cardiac cycle. For example, it can be expressed as the ratio of the difference between the maximum and minimum velocities observed at a given vascular location along the cardiac cycle to the average velocity observed under the same conditions (same location, same time interval). The higher the pulsatility, the greater the variation in blood velocity along the cardiac cycle. The lower the pulsatility, the closer the velocity curve appears to a constant-valued function. A pulsatility of zero indicates an absolutely constant velocity profile along the cardiac cycle.

[0037] Curve characteristics means any other characteristic of the curve, which may include shape, amplitude, slope, or any other characteristic estimated globally on the curve or locally (e.g., during a particular portion of the cardiac cycle). For example, characteristics may include: a characteristic of systole (the top portion of the curve), a characteristic of diastole (the bottom portion of the curve), a characteristic comparing characteristics of systole and diastole, or a characteristic of the gap between either systole and diastole.

[0038] In an embodiment, the curve characteristic comprises one or more of: an indication of blood flow resistance, or an upstroke characteristic.

[0039] The blood flow resistance indicator is a feature of the velocity curve that indicates the presence of blood flow resistance within the connected vasculature somewhere in the patient's body. This resistance can result in reduced blood flow within a specific vessel in the field of view. The cause of blood flow resistance can be outside the field of view, such as in arterioles or capillaries. Blood flow resistance can be a restriction that increases blood flow resistance, thereby resulting in lower blood flow than expected. Distal resistance affects the entire upstream connected vasculature.

[0040] Resistance indications may include: a high-resistance curve (identified by a sharp systolic upstroke, a rapid downstroke); a low-resistance curve (identified by a prolonged downstroke in late systole, with continuous forward flow throughout diastole, without an end-systolic notch) (which is monophasic); or a moderate-resistance curve (identified by a mixture of high-resistance and low-resistance characteristics).

[0041] The upstroke is a curve feature associated with the onset of systole. Upstroke characteristics can include the rate of rise (e.g., rapid rise or prolonged rise). In the case of foot analysis, this upstroke can be called pedal acceleration time, which can be a good indicator for assessing lower extremity arterial perfusion.

[0042] In an embodiment, the at least one processor is configured to process the angiographic data to compensate for motion present in generating the angiographic data, thereby resulting in the generation of motion-compensated semantic angiographic data, and optionally wherein the present motion includes one or more of: patient movement; organ movement; and examination table movement.

[0043] Thus, motion artifacts may be reduced and a higher quality composite view may be produced.

[0044] Thus, the most common causes of motion artifacts can be overcome.

[0045] Because the temporal analysis involved in velocity curve estimation requires a clean removal of background elements, motion compensation is applied to the input angiographic data to eliminate possible patient, organ, or table motion, or a combination of these. Rigid or elastic motion compensation can be considered. Computer vision or learning techniques, or combinations thereof, are possible approaches. The resulting vector field is used to register the angiographic data with the semantic data. This produces semantic digital subtraction angiographic data, in which all data are temporally aligned and the background is suppressed.

[0046] In an embodiment, the system further comprises a user interface, and wherein the at least one processor is configured to display the composite view on a display, and optionally wherein the user interface is configured to receive input to allow the user to modify or manipulate the composite view on the user interface.

[0047] Displaying the composite view allows the clinician to review the composite view and supports the clinician in determining a diagnosis.

[0048] Thus, the user can further tailor the final diagnostic overview in the form of a composite view according to how he evaluates the observed characteristics. Thus, tailored deviations from the guide lines can be introduced. Likewise, the rule database used to generate the diagnosis can be modified according to local preferences or beliefs.

[0049] In an embodiment, the one or more characteristics include pulsatility of blood flow, and the composite view includes a blood pulsatility map corresponding to the field of view.

[0050] The blood pulsatility graph shows blood pulsatility at multiple locations within the field of view.

[0051] In an embodiment, the one or more characteristics include phasicity of blood flow, and the composite view includes a blood phasicity map corresponding to the field of view. In an embodiment, the one or more characteristics include pulsatility of blood flow and phasicity of blood flow, and the composite view includes a pulsatility map and / or a blood phasicity map for the field of view. In an embodiment, the composite view can be adjusted between a blood phase map and a blood pulsatility map, and vice versa.

[0052] According to another aspect, a computer-implemented vascular diagnostic method is provided, comprising the steps of obtaining angiographic data of a patient's vascular system, the angiographic data comprising a field of view of the patient's vascular system; processing the angiographic data to generate semantic angiographic data, the semantic angiographic data comprising information about the presence of anatomical features in the field of view and the locations at which anatomical features exist in the field of view; processing the semantic angiographic data to determine one or more velocity curves based on one or more locations, wherein the velocity curves comprise data of blood velocity relative to time at specific locations in the field of view; determining one or more characteristics based on the one or more velocity curves based on the one or more locations; generating diagnostic data corresponding to the one or more locations based on the one or more characteristics and the semantic angiographic data; and generating a composite view comprising the diagnostic data.

[0053] It will be appreciated that the present invention provides a method for generating vascular diagnostic images and / or data that can be used for vascular diagnosis. Therefore, according to another aspect, a computer-implemented method for generating vascular diagnostic images and / or data is provided, comprising the steps of: obtaining angiographic data of a patient's vascular system, the angiographic data comprising a field of view of the patient's vascular system; processing the angiographic data to generate semantic angiographic data, the semantic angiographic data comprising information about the presence of anatomical features in the field of view and the locations at which the anatomical features are present in the field of view; processing the semantic angiographic data to determine one or more velocity curves according to one or more locations, wherein the velocity curves comprise data about blood flow velocity relative to time at specific locations in the field of view; determining one or more characteristics based on the one or more velocity curves according to the one or more locations; generating diagnostic data corresponding to the one or more locations based on the one or more characteristics and the semantic angiographic data; and generating a composite view comprising the diagnostic data.

[0054] According to another aspect, a computer program product is provided comprising computer program code means which, when executed on a computing device having a processing system, causes the processing system to perform all the steps of the method disclosed herein.

[0055] In an embodiment, two or more sets of angiographic data are acquired about a patient's vascular system, wherein a first set is collected about the patient at a first X-ray angle and at least a second set is collected about the patient at a second, different X-ray angle. In another embodiment, the angular difference between the first X-ray angle and the at least second X-ray angle is 30 degrees or greater. The angle can be measured relative to the patient's center of mass or a central location within the body or portion of the anatomical structure being examined, or more conventionally, in the reference frame of the imaging system plus the examination table.

[0056] Therefore, depth can be represented more accurately. As a projection imaging modality, X-rays can suffer from foreshortening (i.e., discrepancies between true length and projected length). This has a direct impact on velocity measurements. In many cases, vessels are well aligned with the projection plane, and there is very little foreshortening. However, one option to overcome potential foreshortening is to use two angiograms taken at different angles (typically more than 30 degrees apart) and reconstruct depth from these two angles. To determine the velocity profile for each vessel, the projection with the least foreshortening is used. This is sometimes referred to as 3D vessel modeling. Two or more adjacent fields of view can be stitched together to create a larger field of view. This can be done using both anatomical maps (semantic angiographic data) and velocity profiles associated with the same or similar time periods. Actual distances along the vessel path can then be measured on this 3D vessel modeling, and foreshortening can be corrected accordingly. However, when using several angiograms taken at different angles, velocity profiles can also be estimated from those angiograms. Velocity profiles or derived characteristics from those different angiograms can then be combined or selected. For example, it is possible to select the velocity curve or related characteristic corresponding to the angiogram with the smallest amount of foreshortening at a given location on the map. Likewise, when different angiograms are available that are contiguously placed together across a wider field of view, the corresponding velocity curves or related characteristics can be combined to create a diagnostic composite view over the extended field of view.

[0057] In the case of an intravascular intervention, several angiograms can also be considered, wherein at least one of these angiograms corresponds to a time interval before the intervention (which can typically be a balloon dilation or stent implantation procedure), and wherein at least one of these angiograms corresponds to a time interval after the intervention. In this case, it is possible to create a diagnostic composite view based on characteristics extracted from the velocity curves of at least two angiograms. In this case, the diagnostic composite view may be different in the sense that it will reflect differences in the diagnostic assessment depending on the effect of the intervention. For example, it may reflect to what extent the pulsatility or flow has been restored after the balloon or stent has been deployed at the location under consideration.

[0058] In an embodiment, the system generates angiographic data and associated semantic angiographic data related to the same field of view at two different time periods. The time periods can be one or more days apart. For example, first semantic angiographic data can be generated in a first time period, and second angiographic data can be generated in a second time period, which can be, for example, a week or a month later. Thus, as an example, a clinician can then compare a pair of angiograms of the same vascular field of view before and after treatment to monitor how the condition may have changed during the period between the first and second time periods. In an embodiment, the diagnostic view can be adjusted to show images related to different time periods.

[0059] In an embodiment, multiple fields of view are combined together to create a larger composite view.

[0060] 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

[0061] For a better understanding of the invention and in order to show more clearly how it may be put into practice, reference will now be made, by way of example only, to the accompanying drawings in which:

[0062] Figure 1 is a simplified block diagram of the proposed embodiment 10;

[0063] Figure 2 A number of speed curves are shown;

[0064] Figure 3 showing a comparative view of velocity profiles from a first position and a second position;

[0065] Figure 4 is a simplified flow chart of the proposed vascular diagnosis method 40;

[0066] Figure 5 illustrates an example of a computer 50 in which one or more portions of the embodiments may be employed; and

[0067] Figure 6 A possible diagnostic view 61 is shown as well as an unprocessed angiographic image 60 . DETAILED DESCRIPTION

[0068] The present invention will be described with reference to the accompanying drawings.

[0069] It should be understood that the detailed description and specific examples, while indicating exemplary embodiments of the apparatus, system, and method, are intended only for illustrative purposes and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the apparatus, system, and method of the present invention will be better understood from the following description, appended claims, and accompanying drawings.

[0070] By studying the drawings, the disclosure, and the appended claims, those skilled in the art can understand and effect variations of the disclosed embodiments in 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.

[0071] It should be understood that the drawings are merely schematic and not drawn to scale. It should also be understood that the same reference numerals are used throughout the drawings to indicate the same or similar parts.

[0072] By way of example only, the illustrative embodiments may be used in many different types of clinical, medical, or subject-related environments, such as hospitals, doctors' offices, medical research facilities, patient rooms, nursing homes, personal homes, and the like.

[0073] The present invention provides methods and systems for generating composite diagnostic views to assist clinicians. The composite views include anatomical information and diagnostic data. In particular, the generated diagnostic views can include presentations of diagnostic data based on multiple locations within the field of view, which can enable clinicians to make improved diagnoses or assessments. The diagnostic views can also provide one or more diagnostic indications of the presence or absence of a condition at a specific location within the field of view, i.e., the views can indicate both the presence and location of such a condition.

[0074] Diagnostic data from adjacent vessels can be used to generate diagnostic views. This allows for a more comprehensive and complete diagnosis.

[0075] The diagnostic data for each location may include raw diagnostic data (e.g., data that can be directly derived from the velocity profile for each location), or may include a diagnostic indication based on the data. For example, it may be known that in a particular vessel, a particular characteristic may be indicative of a particular condition. Thus, a diagnostic indication may be derived by comparing the characteristics of the raw diagnostic data from multiple locations, taking into account the location in question. For example, if the location matches a reference vessel and the characteristic matches the value or falls within a reference range, a diagnostic indication may be generated to indicate that the condition appears to exist within the field of view. Optionally, the composite view may indicate the characteristic that has been pointed to the diagnosis, and may further indicate the location at which the characteristic was observed. The location indication may be a visual indicator with respect to the field of view and / or a descriptor of the relevant vessel in which the condition has been observed.

[0076] To aid understanding of the proposed concept(s), reference will now be made to Figure 1 An exemplary embodiment of a vascular diagnostic system is described below.

[0077] Figure 1 is a simplified block diagram of the proposed embodiment 10. The system 100 according to the proposed embodiment is configured to obtain (e.g., receive via an input interface) angiographic data 110 of a patient. The angiographic data includes a field of view of the patient, thus covering one or more parts of an anatomical structure or body of the patient.

[0078] The generation of angiography data is well known in the art, and thus a detailed description is omitted.

[0079] System 100 includes a microcontroller and several functional components. The system includes a semantic data component 120; a motion compensation component 130; a velocity profile component 140; a feature extractor 150; a diagnostic component 160; and a composite view generator 170. One or more of these functional components may be combined. The system optionally receives one or more diagnostic rules 180 as input.

[0080] Semantic data component 120 generates semantic angiographic data including information regarding the presence and location of anatomical and biometric features in the field of view. Semantic data component 120 analyzes angiographic data 110 to determine the presence and properties of blood vessels in the field of view. For example, semantic data component 120 generates digital subtraction angiography (DSA) data from angiographic data 110.

[0081] As an example, the semantic data component 120 generates a vessel segmentation map that includes information regarding which portions of the field of view include vessels and one or more labels, each label including an identification of a specific vessel present in the field of view and an associated location of the specific vessel. This information enables extraction of at least one semantic vessel from the vessel segmentation map, thereby enabling processing of angiographic data to generate semantic angiographic data that includes information regarding the presence of anatomical features in the field of view and the locations of the anatomical features present in the field of view.

[0082] Given a target vessel field of view (e.g., peripheral, renal, carotid, neural, etc.), deep learning techniques can generate a vessel segmentation map that generates vessel probabilities at each pixel of angiogram of the target region. Additionally, one or more labels can be associated with each segmented pixel, indicating which vessel(s) the pixel belongs to. A fully trained U-Net (a convolutional neural network developed for biomedical image segmentation) is a typical example of this implementation. Finally, the segmentation network is equivalently trained to detect and quantify stenoses along the analyzed vessel.

[0083] Segmentation maps and label maps are reliable but do not provide a high-level representation. As an improvement, computer vision techniques, such as minimum path techniques fed by these maps, can be employed to provide the desired high-level view as a set of labeled centerlines and borderlines for each identified vessel segment. The presence and severity of stenosis can also modify the vessel centerlines as additional information.

[0084] The motion compensation component 130 is optional and generates motion-compensated semantic angiography data by compensating for one or more of patient motion, organ motion, and table motion.

[0085] Because temporal analysis requires a clean removal of background elements, motion compensation is applied to the input angiogram to eliminate possible patient, organ, or table motion. Rigid or elastic motion compensation can be considered. Computer vision or computer learning techniques, or a combination of both, are alternative possible approaches. The resulting vector field is used to register the angiographic data with the semantic data. This produces a semantic digital subtraction angiogram in which all data are temporally aligned and the background is suppressed, providing motion-compensated angiographic data.

[0086] Motion compensation may be performed at any suitable stage, for example before or after generating semantic angiography data.

[0087] The velocity curve component 140 generates velocity curves for one or more locations in the field of view. Typically, the component generates at least one velocity curve for each blood vessel, but may include generating more than one velocity curve for a blood vessel. Each velocity curve includes data on blood velocity at a specific location relative to time. As an example, a method that can be used to generate multiple velocity curves is discussed in the following scientific article: "Quantification of arterial flow using digital subtraction angiography" by Bonnefous et al. (Med. Phys., Vol. 39, No. 10, October 2012), which is incorporated herein by reference. Additionally or alternatively, velocity curves can be generated using the teachings of "A new algorithm for deriving pulsatile blood flow waveforms tested using simulated dynamic angiographic data" by Seifalian et al. (Neuroradiology, Vol. 31, pp. 263-269, 1989), which is incorporated herein by reference.

[0088] Given a sufficient frame rate (typically 15 fps) and adequate background suppression, the techniques described in the references cited above can be applied to estimate the velocity profile at each point. The integration operation is constrained by vessel coverage and coherent vessel labels. This can be perfectly automated and does not require any manual guidance. For each semantically identified pixel in the image, this yields a velocity profile along the observed cardiac cycle.

[0089] The feature extractor 150 extracts one or more characteristics from one or more velocity curves according to one or more locations. As an example, the feature extractor extracts the flow direction, peak amplitude of the curve, phasicity, and curve characteristics at each location. As an example, the curve characteristic can be an upstroke characteristic, and the peak amplitude can be an indicator of blood flow resistance. The upstroke characteristic refers to the shape, rate of rise, and associated characteristics of the velocity curve when the velocity curve rises above zero (i.e., when blood flow changes direction). In an embodiment, the one or more characteristics include the degree of stenosis at a specific location.

[0090] Diagnostic component 160 generates diagnostic data. In one embodiment, the diagnostic data is generated directly from the velocity profile. The diagnostic data is associated with a specific location and is therefore generated based on one or more characteristics and semantic angiographic data. The latter provides meaningful location information.

[0091] In another embodiment, one or more diagnostic rules 180 are provided as input to the system, and the diagnostic component 160 applies the diagnostic rules to determine whether one or more conditions may exist within the field of view. This is accomplished by comparing one or more characteristics to one or more reference characteristics, and comparing a specific location to one or more reference locations. If a specific characteristic is found at a specific location, it can be determined that a condition exists. Both the location and the characteristic must match the reference location and the value / range for the rule to be satisfied. If the characteristic exists but in the wrong location, or if the characteristic does not exist in a specific location, there is insufficient evidence to indicate that the condition exists. Optionally, the diagnostic rules 180 are provided as part of the system, rather than being provided via a separate input. Optionally, the diagnostic rules 180 are obtained via a wired connection or a wireless connection. In an embodiment, the diagnostic rules can be automatically updated periodically, or can be updated when the diagnostic component requests the latest set of rules.

[0092] The field of medicine is constantly evolving, generating new insights every year. Many of these insights can be formulated for use in the present invention under diagnostic rules. Such insights and examples of how they can be used to support diagnosis can be found in the following article: Kim and al. " Interpretation of peripheral arterial and venous Doppler waveforms: A consensus statement from the Society for Vascular Medicine and Society for Vascular Ultrasound" (Vascular Medicine, 2020, Vol. 25, No. 5, pp. 484-506), which is incorporated herein by reference.

[0093] In an embodiment, applying the diagnostic rule includes generating a characteristic value based on the characteristic at the particular location, and comparing the characteristic value to one or more reference characteristic values ​​or ranges.

[0094] In an embodiment, the diagnostic component 160 also evaluates one or more patient characteristics and compares these one or more patient characteristics with other reference characteristics when generating diagnostic data. This may include, for example, one or more of the following: the patient's medical history, the patient's gender, the patient's current medical condition, or the patient's current medication use. Thus, diagnostic data may be generated in response to the evaluation of other patient characteristics.

[0095] In an embodiment, the diagnostic component 160 generates diagnostic data corresponding to one or more locations by evaluating one or more characteristics corresponding to locations other than the specific location. For example, one or more characteristics of a nearby blood vessel may be evaluated to generate diagnostic data or confirm a diagnostic indication.

[0096] For each vessel, a current consensus determines what constitutes a normal velocity profile and an abnormal velocity profile. This is based on observations of velocity profile descriptors, local anatomy (e.g., presence of stenosis), and possible correlations with surrounding vessels. All of this information can be collected in a diagnostic database addressed by the current anatomical configuration and extracted velocity descriptors. For each vessel, a statement indicating normal / abnormal can be issued, along with an appropriate description, clarifying the reason for the inference.

[0097] The composite view generator 170 generates a composite view 190 based on the semantic angiographic data and the data from the diagnostic component. In one embodiment, this includes overlaying one or more characteristics from one or more velocity curves onto the field of view, thereby providing a composite diagnostic view that provides anatomical information and diagnostic data 192.

[0098] Thus, diagnostic data is collected in one or more views that summarize the clinical vascular situation. Overview maps can be created that indicate which part of the vessel is marked as abnormal. These overview maps can be user-defined and can be interactive (e.g., clicking on a point will open a pop-up window with the measured velocity curve and descriptors, a pop-up window with local vessel characteristics, and a pop-up window with the involved diagnostic rules), thereby comparing the normal situation with the observed situation.

[0099] In an embodiment, system 10 further includes a user interface (not shown), and composite view 190 is displayed on the user interface. In another embodiment, the user interface is configured to receive input to allow the user to modify or manipulate composite view 190 on the user interface. For example, diagnostic data 192 can be turned on or off (i.e., set to be visible or invisible). In another embodiment, one or more diagnostic rules in one or more diagnostic rules 180 can be modified or selected by the user to obtain a modified diagnostic indication regarding whether a condition exists at a particular location.

[0100] In an alternative embodiment, the system is remote from the user interface. For example, the system can be located on a remote server, remote from where the user is working. The system generates a composite view 190 that is displayed on a screen adjacent to the user. The composite view 190 can be transmitted to the screen via any known transmission protocol, such as via Ethernet or via a wireless connection.

[0101] In an embodiment, system 10 generates angiograms of the same vessel field of view before and after a medical procedure. Thus, given a pair of angiograms of the same vessel field of view before and after a procedure, system 10 can also present an aggregated view to provide the physician with a sense of how different descriptors have evolved as a result of the procedure. In this setup, pixel-perfect registration of the angiograms is not necessary: ​​the compositer can leverage semantic vessel segmentation and label maps by providing the average descriptor evolution over a given vessel or vessel portion.

[0102] For further illustration and description, reference will be made to Figure 2 and Figure 3 To describe the working of the present invention.

[0103] Figure 2 Several speed curves are shown.

[0104] Figure 3 A comparative view of the velocity profiles from the first position and the second position is shown.

[0105] refer to Figure 2 , the three curves show how velocity curves can indicate phasicity. The top curve indicates three-phase flow; the middle curve indicates two-phase flow; and the bottom curve indicates single-phase flow. Therefore, phasicity can be determined from the velocity curves and can be a characteristic used in the present invention.

[0106] Figure 3 A comparative view of the velocity profiles from the first and second positions is shown. Figure 3 , the velocity signal on the far side of the occlusion is shown on the left, while the velocity signal on the proximal side of the occlusion is shown on the right. Therefore, the location of the lesion can be determined relative to the location where the velocity curve is generated (e.g., far side or proximal side of the occlusion).

[0107] like Figure 3 The location of the stenosis can be indicated by the shape of the waveform (damping versus rapid upstroke).

[0108] The shape of the velocity curve provides additional insights that can be exploited in the present invention. For example, resistance indicators are described as follows: a high-resistance curve is indicated by a sharp systolic upstroke followed by a rapid downstroke; a low-resistance curve indicates a prolonged downstroke in late systole, with continuous forward flow throughout diastole without a late systolic notch. Such a curve is monophasic; and a medium-resistance curve: a mixture of high-resistance and low-resistance characteristics.

[0109] The upstroke can be used to support a diagnosis. The upstroke (the onset of systole) can be rapid or prolonged. In the case of foot analysis, this can be called pedal acceleration time, which can be a reliable indicator of lower extremity arterial perfusion. In other words, the shape of the curve (particularly the upstroke) can be used to determine the presence of a condition or support a diagnosis.

[0110] By way of further illustration and description, reference will now be made to Figure 4 An exemplary method according to an embodiment is described.

[0111] Figure 4 is a simplified flow chart of the proposed blood vessel diagnosis method 40. The method 40 includes several steps.

[0112] In an obtain angiographic data step 410, angiographic data is obtained. This data may be obtained directly by the system or may be provided to the system as input. The angiographic data includes a field of view.

[0113] In a generate semantic angiography data step 420 , semantic angiography data is generated based on the angiography data.

[0114] In a generate velocity profile(s) step 430 , one or more velocity profiles corresponding to different positions in the field of view are generated.

[0115] In a determine characteristic(s) step 440 , one or more characteristics are generated based on each of the one or more speed profiles.

[0116] In a generate diagnostic data step 450, diagnostic data is generated corresponding to one or more locations for which velocity curves have been generated. The diagnostic data is generated based on one or more characteristics and semantic angiographic data.

[0117] In the generate composite view step 460 , a composite view is generated.

[0118] In a display composite view step 470, the composite view is displayed. This step is optional.

[0119] The method steps may be further understood with reference to the description of the system and the operation of the functional components therein.

[0120] It should be understood that the present invention provides a method for generating vascular diagnostic images and / or data that can be used for vascular diagnosis. Therefore, references to vascular diagnostic methods should be understood as referring to methods for generating vascular diagnostic images and / or data that can be used for vascular diagnosis.

[0121] Figure 5An example of a computer 50 in which one or more parts of the embodiments may be employed is illustrated. The various operations discussed above may utilize the capabilities of the computer 50. For example, one or more parts of a system for providing an object-specific user interface may be incorporated into any element, module, application, and / or component discussed herein. In this regard, it should be understood that the system functional blocks can be run on a single computer or may be distributed across several computers and locations (e.g., connected via the Internet).

[0122] The computer 50 includes, but is not limited to, a PC, a workstation, a laptop, a PDA, a handheld device, a server, a storage device, and the like. Typically, in terms of hardware architecture, the computer 50 may include one or more processors 510, a memory 520, and one or more I / O devices 570 communicatively coupled via a local interface (not shown). The local interface can be, for example, but not limited to, one or more buses or other wired or wireless connections as known in the art. The local interface may have additional elements (e.g., a controller, a buffer (cache memory), a driver, a repeater, and a receiver) to enable communication. Additionally, the local interface may include address, control, and / or data connections to enable appropriate communication between the aforementioned components.

[0123] The processor 510 is a hardware device for executing software that can be stored in the memory 520. The processor 510 can actually be any custom or commercially available processor, central processing unit (CPU), digital signal processor (DSP) or auxiliary processor, etc., associated with the computer 50, and the processor 510 can be a semiconductor-based microprocessor (in the form of a microchip) or a microprocessor.

[0124] The memory 520 can include any one or a combination of volatile memory elements (e.g., random access memory (RAM), such as dynamic random access memory (DRAM), static random access memory (SRAM), etc.) and non-volatile memory elements (e.g., ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic tape, compact disk read-only memory (CD-ROM), magnetic disk, floppy disk, cassette, cartridge, etc.). In addition, the memory 520 can include electronic, magnetic, optical, and / or other types of storage media. Note that the memory 520 can have a distributed architecture in which various components are remote from each other but can be accessed by the processor 510.

[0125] The software in the memory 520 may include one or more separate programs, each of which includes an ordered list of executable instructions for implementing logical functions. According to an exemplary embodiment, the software in the memory 520 includes a suitable operating system (O / S) 550, a compiler 540, source code 530, and one or more application programs 560. As shown, the application programs 560 include numerous functional components for implementing the features and operations of the exemplary embodiment. The application programs 560 of the computer 50 may represent various applications, computing units, logical units, functional units, processes, operations, virtual entities, and / or modules according to exemplary embodiments, but the application programs 560 are not intended to be limiting.

[0126] Operating system 550 controls the execution of other computer programs and provides scheduling, input-output control, file and data management, memory management, and communication control and related services. The inventors contemplate that application program 560 for implementing the exemplary embodiments may be applicable to all commercially available operating systems.

[0127] Application 560 can be a source program, an executable program (object code), a script, or any other entity comprising a set of instructions to be executed. If it is a source program, it is typically translated by a compiler (e.g., compiler 540), an assembler, an interpreter, etc. (which may or may not be included in memory 520) so that it can operate properly in conjunction with O / S 550. In addition, application 560 can be written in an object-oriented programming language with data classes and method classes or a procedural programming language with routines, subroutines, and / or functions (e.g., but not limited to C, C++, C#, Pascal, BASIC, API calls, HTML, XHTML, XML, ASP scripts, JavaScript, FORTRAN, COBOL, Perl, Java, ADA, .NET, etc.).

[0128] I / O devices 570 may include input devices such as, but not limited to, a mouse, keyboard, scanner, microphone, camera, etc. Furthermore, I / O devices 570 may also include output devices such as, but not limited to, a printer, a display, etc. Finally, I / O devices 570 may also include devices that transmit both input and output, such as, but not limited to, a NIC or modulator / demodulator (for accessing remote devices, other files, devices, systems, or networks), a radio frequency (RF) or other transceiver, a telephone interface, a bridge, a router, etc. I / O devices 570 also include components for communicating over various networks (e.g., the Internet or an intranet).

[0129] If the computer 50 is a PC, workstation, smart device, etc., the software in the memory 520 may also include a basic input and output system (BIOS) (omitted for simplicity). The BIOS is a set of basic software routines that initialize and test the hardware at startup, start the O / S 550, and support data transfer between hardware devices. The BIOS is stored in some type of read-only memory (e.g., ROM, PROM, EPROM, EEPROM, etc.) so that it can be executed when the computer 50 is activated.

[0130] When the computer 50 is in operation, the processor 510 is configured to execute software stored in the memory 520, transfer data to and from the memory 520, and generally control the operation of the computer 50 according to the software. The application programs 560 and the O / S 550 are read in whole or in part by the processor 510, possibly cached within the processor 510, and then executed.

[0131] When application 560 is implemented in software, it should be noted that application 560 can be stored on substantially any computer-readable medium for use by or in conjunction with any computer-related system or method. In the context of this document, a computer-readable medium can be an electronic, magnetic, optical, or other physical device or means that can contain or store a computer program for use by or in conjunction with a computer-related system or method.

[0132] Application 560 can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device (e.g., a computer-based system, a system containing a processor, or other system capable of retrieving instructions from and executing instructions on an instruction execution system, apparatus, or device). In the context of this document, a "computer-readable medium" can be any device that can store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium.

[0133] The present invention may be a system, method and / or computer program product.The computer program product may include (one or more) computer-readable storage media having computer-readable program instructions thereon for causing a processor to perform various aspects of the present invention.

[0134] Computer-readable storage media can be a tangible device that can retain and store instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing items. A non-exhaustive list of more specific examples of computer-readable storage media includes the following items: portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), static random access memories (SRAM), portable compact disc read-only memories (CD-ROMs), digital versatile discs (DVDs), memory sticks, floppy disks, mechanically encoded devices (e.g., punch cards or raised structures in grooves on which instructions are recorded) and any suitable combination of the foregoing items. As used herein, "computer-readable storage media" should not be interpreted as transient signals themselves (e.g., radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagated by waveguides or other transmission media (e.g., light pulses by fiber optic cables), or electrical signals transmitted by wires).

[0135] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device, or downloaded to an external computer or external storage device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The network can include copper transmission cables, transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium within the corresponding computing / processing device.

[0136] The computer-readable program instructions for performing the operation of the present invention can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, wherein the one or more programming languages ​​include object-oriented programming languages ​​(such as, Smalltalk, C++, etc.) and conventional procedural programming languages ​​(such as, " C " programming language or similar programming languages). The computer-readable program instructions can be performed completely on the user's computer, partly on the user's computer, performed as an independent software package, partly on the user's computer and partly on a remote computer, or performed completely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any type of network (including local area network (LAN) or wide area network (WAN)), or can be connected to an external computer (such as by using the Internet of an Internet service provider). In certain embodiments, the electronic circuit comprising, for example, a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA) can perform the computer-readable program instructions to personalize the electronic circuit by utilizing the state information of the computer-readable program instructions, so as to perform various aspects of the present invention.

[0137] Various aspects of the present invention are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0138] A single processor or other unit may fulfill the functions of several items recited in the claims.

[0139] The computer program may be stored / distributed on suitable media, such as optical storage media or solid-state media provided together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems.

[0140] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, executed via the processor of the computer or other programmable data processing apparatus, create a module for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that can direct the computer, programmable data processing apparatus, and / or other device to function in a particular manner, such that the computer-readable storage medium having the instructions stored therein comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0141] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable apparatus, or other device to implement the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0142] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functions and operations of the possible implementation methods of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, segment or part of an instruction, and the module, segment or part of the instruction include one or more executable instructions for implementing the specified (one or more) logical functions. In some alternative embodiments, the functions marked in the box may not occur in the order marked in the figure. For example, the two boxes shown in succession can actually be performed substantially simultaneously, or these boxes can sometimes be performed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart illustration and the combination of the boxes in the block diagram and / or flowchart illustration can be implemented by a system based on dedicated hardware that performs the specified function or action or performs a combination of dedicated hardware and computer instructions.

[0143] Figure 6A possible diagnostic view 61 produced by the present invention is illustrated, along with an unprocessed angiographic image 60. The field of view includes the angiographic image and may also include one or more of the following: one or more markers or labels 610 that may indicate information about vessels or features present in the field of view; one or more references to diagnostic data 620 relating to one or more points in time, e.g., a diagnostic view may include an indication of average or maximum flow values ​​at a particular location; and a diagnostic indication 630. Additionally, the diagnostic view 61 may include one or more of shading, coloring, highlighting, and outlining, e.g., to highlight particular vessels or features or to link aspects of the field of view together (e.g., to link vasculature that is related in some way (e.g., two different vessels having characteristics that support a particular diagnostic indication 630)).

[0144] The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0145] If the term "adapted to" is used in the claims or the specification, it should be noted that the term "adapted to" is intended to be equivalent to the term "configured to."

[0146] Any reference signs in the claims should not be construed as limiting the scope.

Claims

1. A vascular diagnostic system comprising: at least one processor configured to: obtaining angiographic data of a patient's vascular system, the angiographic data including a field of view of the patient's vascular system; processing the angiographic data to generate semantic angiographic data, the semantic angiographic data comprising information regarding the presence of anatomical features in the field of view and the locations at which anatomical features are present in the field of view; processing the semantic angiography data to determine one or more velocity curves according to one or more locations, wherein the velocity curves include blood velocity versus time data for specific locations in the field of view; determining one or more characteristics based on the one or more velocity profiles as a function of the one or more locations; generating diagnostic data corresponding to the one or more locations based on the one or more characteristics and the semantic angiographic data; and A composite view including the diagnostic data is generated.

2. The system according to claim 1, wherein: The diagnostic data corresponding to the one or more locations is generated by applying one or more diagnostic rules at each of the specific ones of the one or more locations, wherein each of the one or more diagnostic rules includes the following to determine a diagnostic indication as to whether a condition exists at the specific location: comparing the one or more characteristics to one or more reference characteristics; and The specific location is compared to one or more reference locations.

3. The system according to claim 2, wherein: Comparing the one or more characteristics to one or more reference characteristics includes generating a characteristic value based on the characteristic at the particular location and comparing the characteristic value to one or more reference characteristic values ​​or ranges.

4. A system according to claim 2 or claim 3, wherein: The processor is configured to obtain one or more additional patient characteristics, and wherein, The diagnostic rule further comprises comparing the further patient characteristic with one or more further reference characteristics.

5. The system according to any one of claims 2 to 4, wherein: The one or more characteristics include the degree of stenosis at a particular location.

6. The system according to any one of claims 2 to 5, wherein: Generating the diagnostic data corresponding to the one or more locations includes evaluating one or more characteristics corresponding to locations other than the specific location.

7. A system according to any preceding claim, wherein: One or more of the one or more diagnostic rules are modifiable or selectable by a user to result in a modified diagnostic indication as to whether a condition exists at the particular location.

8. A system according to any preceding claim, wherein: The at least one processor is configured to generate the following to enable extraction of at least one semantic vessel from the vessel segmentation map, thereby enabling processing of the angiographic data to generate semantic angiographic data, the semantic angiographic data comprising information regarding the presence of anatomical features in the field of view and locations at which anatomical features are present in the field of view: the vessel segmentation map, which includes information about which parts of the field of view include blood vessels; and One or more tags including an identification of a specific blood vessel present in the field of view and an associated location of the specific blood vessel.

9. A system according to any preceding claim, wherein: The characteristics include one or more of: flow direction, phase, or curvilinear characteristics.

10. The system according to claim 9, wherein: The curve characteristics include one or more of the following: an indication of blood flow resistance, or an upstroke characteristic.

11. A system according to any preceding claim, wherein: The at least one processor is configured to process the angiographic data to compensate for motion present in generating the angiographic data, thereby resulting in generation of motion-compensated semantic angiographic data, and optionally wherein the present motion comprises one or more of: patient movement; organ movement; and examination table movement.

12. A system according to any preceding claim, further comprising a user interface, and wherein: The at least one processor is configured to display the composite view on a display, and optionally wherein the user interface is configured to receive input to allow the user to modify or manipulate the composite view on the user interface.

13. A system according to any preceding claim, wherein: The one or more characteristics include pulsatility of blood flow, and the composite view includes a blood pulsatility map corresponding to the field of view.

14. A computer-implemented blood vessel diagnosis method comprising the following steps: obtaining angiographic data of a patient's vascular system, the angiographic data including a field of view of the patient's vascular system; processing the angiographic data to generate semantic angiographic data, the semantic angiographic data comprising information regarding the presence of anatomical features in the field of view and the locations at which anatomical features are present in the field of view; processing the semantic angiography data to determine one or more velocity curves according to one or more locations, wherein the velocity curves include blood velocity versus time data for specific locations in the field of view; determining one or more characteristics based on the one or more velocity profiles as a function of the one or more locations; generating diagnostic data corresponding to the one or more locations based on the one or more characteristics and the semantic angiographic data; and A composite view including the diagnostic data is generated.

15. A computer program product comprising computer program code means which, when executed on a computing device having a processing system, causes the processing system to perform all the steps of the method according to claim 14.

Images