Method and apparatus for analyzing diagnostic image data

Abstract

Provided are a method and apparatus for analyzing diagnostic image data, wherein, based on at least one functional parameter, correspondence detection of a vessel of interest is performed between a first diagnostic image and a second diagnostic image by matching one or more values ​​of the functional parameter at specific locations along the vessel of interest in the vascular structure of a patient shown in the first and second diagnostic images, thereby determining a correlation between the locations based on the functional parameter values ​​rather than solely on the vessel geometry.

Description

Technical Field

[0001] The present invention relates to a method, a corresponding apparatus, and a corresponding computer program for analyzing diagnostic image data, in some embodiments multimodal diagnostic image data. In particular, the present invention relates to an improved method and apparatus that allow for more reliable and accurate detection of correspondences for vessels of interest in the vasculature of a patient represented in a plurality of diagnostic images by using functional parameter values. Background Art

[0002] Coronary artery disease is a widespread condition in many societies today. To establish an appropriate treatment plan for each individual patient, it is crucial to obtain as much information as possible about the coronary vasculature. Therefore, accurate assessment of the geometric properties of the vasculature and the dynamics of blood flow through it are particularly relevant with sufficient reliability.

[0003] To this end, a number of different medical measurement modalities are known that can be used to obtain corresponding medical data about these properties. Among these medical measurement modalities are medical imaging modalities (e.g., computed tomography (CT) angiography, invasive angiography, intravascular ultrasound (IVUS) imaging, magnetic resonance (MR) imaging, intracardiac echocardiography (ICE), transesophageal echocardiography (TEE), etc.) and fluid dynamic measurement modalities (e.g., invasive fractional flow reserve (FFR) or instantaneous wave-free ratio (IFR) measurement, ultrasound flow measurement (e.g., Doppler flow measurement), etc.).

[0004] Thus, each of the medical imaging modalities allows for the collection of specific diagnostic image data that reveals specific information about the vasculature. This specific information can vary between different imaging modalities, and even between diagnostic images acquired using the same imaging modality, as acquisition settings such as projection direction, cardiac motion, etc., can alter the visualization of the vasculature in different diagnostic images.

[0005] As such, for an accurate and reliable assessment of the vasculature and therefore of any underlying (coronary) artery disease, it is beneficial to use not only a single diagnostic image but a combination of multiple diagnostic images to retrieve a more complete picture of the vasculature.

[0006] Therefore, methods have been developed in which multiple different diagnostic images are correlated with each other in order to retrieve more information about the coronary arteries. Applications that allow such correlation are, for example, vascular roadmap co-registration, image fusion for different imaging modalities, or motion-compensated vascular modeling.

[0007] Therefore, in order to properly combine the different diagnostic images, a so-called correspondence detection must be performed, during which the same vessel or vessel segment of interest is identified in all diagnostic images and thus co-registered for all diagnostic images. In other words, it is determined which vessel (segment) in the first diagnostic image corresponds to which vessel (segment) in the second diagnostic image.

[0008] However, factors such as changes in projection direction, cardiac motion, the often uncalibrated C-arm geometry, etc., can hinder accurate correspondence detection. As an example, in two or more two-dimensional angiograms acquired from different projection directions, the same vessel (segment) may appear to have such different properties that a correspondence between the vessel (segment) represented in the first diagnostic image and the same vessel (segment) represented in the second diagnostic image can only be established with low accuracy. The problem becomes even more severe in cases where different imaging modalities are used to acquire the diagnostic images. As an example, the co-registration of CT angiograms with invasive angiographic data should be mentioned. Such a registration of CT angiograms to angiographic data can be very challenging due to the ambiguity that may result from cardiac motion and / or unknown relative geometry.

[0009] Therefore, various feature detection schemes have been developed that are said to allow accurate determination of these correspondences. These feature detection schemes are usually based on a combination of many features (such as bifurcation locations, characteristic curves, geometric constraints, etc.). Using these features usually results in the most robust correspondences.

[0010] Despite this, no method has yet been developed that allows establishing accurate and reliable correspondences, in particular between identical blood vessels (segments) represented in different diagnostic images. Summary of the Invention

[0011] It is therefore an object of the present invention to provide a method and a device which enable correspondence detection for one or more vessel segments of a vascular system in a reliable, accurate and efficient manner.

[0012] More particularly, it is an object of the present invention to provide a method and an apparatus for analyzing diagnostic image data that allow combining a plurality of diagnostic images by performing reliable correlation between independently used diagnostic images.

[0013] A further object of the present invention is to provide methods and devices that allow multimodal image visualization and / or multimodal modeling of a patient's vasculature (i.e., one or more blood vessels or vessel segments therein) to be performed in a reliable and accurate manner.

[0014] This object is achieved by a method for analyzing diagnostic image data, the method comprising the steps of obtaining a first diagnostic image and a second diagnostic image of a vessel of interest in a vasculature of a patient, defining at least one determined position for the vessel of interest in the first diagnostic image and defining at least one corresponding determined position for the vessel of interest in the second diagnostic image, determining a first value for at least one functional parameter at the at least one determined position in the first diagnostic image and a second value for the same at least one functional parameter at the corresponding determined position in the second diagnostic image, and associating one or more vessel positions along the vessel of interest represented in the first diagnostic image with one or more vessel positions along the vessel of interest represented in the second diagnostic image based on a comparison of the first value of the at least one functional parameter with the second value of the at least one functional parameter.

[0015] That is to say, the two diagnostic images are co-registered with one another based on the functional parameters that have been determined for at least one specific determined position in the two diagnostic images.

[0016] In this context, the term diagnostic image may specifically refer to an image representing a patient's vasculature. The term vasculature may refer to a vascular tree or a single vessel. The term vasculature may specifically refer to a vessel segment of a vessel of interest. In some embodiments, the diagnostic image may represent the vasculature of one or more vessels of interest, including coronary artery vasculature.

[0017] The first diagnostic image and the second diagnostic image can be obtained using a diagnostic imaging modality. The diagnostic imaging modality can be gated. A gated diagnostic imaging modality typically employs gated reconstruction, in which acquisition of the diagnostic image is performed in parallel with acquisition of data providing information about the cardiac cycle (e.g., electrocardiogram (ECG) data or photoplethysmography (PPG) data). Thus, image acquisition and reconstruction can be gated using selected phase points of the cardiac cycle.

[0018] The term "determined location" may specifically refer to a specific location along the vessel of interest represented in the first diagnostic image and the second diagnostic image, at which a value for a functional parameter may be determined, for example, by actual invasive measurements (e.g., intravascular pullback measurements) and / or non-invasive measurements (e.g., Doppler blood flow measurements) and / or by simulating fluid dynamics through the vessel of interest using a corresponding fluid dynamics model. A plurality of determined locations may be used, at each of which a corresponding value for one or more functional parameters may be determined.

[0019] The term functional parameter may particularly refer to a parameter indicating the dynamic behavior of the vessel of interest, in particular a parameter indicating the fluid dynamics through the vessel of interest. That is, a functional parameter may refer to a parameter such as pressure, flow, vascular resistance, etc., which varies with the vessel of interest.

[0020] The term vessel location may specifically refer to a location along a vessel of interest. A plurality of vessel locations along the length of the vessel of interest may be determined. The vessel locations in the first diagnostic image and the second diagnostic image are associated with each other by comparing a first value and a second value of at least one functional parameter obtained for the determined location in the first diagnostic image and the determined location in the second diagnostic image.

[0021] That is, if a plurality of first values ​​for a particular functional parameter are obtained in a first diagnostic image, and a plurality of second values ​​for the same functional parameter are obtained in a second diagnostic image, these values ​​can be compared with each other. Determined positions where the values ​​correspond to each other are then associated with each other, i.e., assumed to correspond to the same blood vessel position represented in both images.

[0022] Therefore, according to this method, at least one determined location is determined in two diagnostic images. Subsequently, a value of a functional parameter is determined for the at least one determined location. These values, determined for the first diagnostic image and the second diagnostic image, are then compared to establish a correlation. For example, if a value for a specific determined location in the first diagnostic image corresponds to a value for a specific determined location in the second diagnostic image, these determined locations are assumed to correspond to the same vessel location within the vessel of interest that exhibits the same value for the specific functional parameter. This allows for correspondence detection between the first and second diagnostic images, even when the diagnostic images were acquired using different acquisition settings and / or different imaging modalities.

[0023] In some embodiments, obtaining the first diagnostic image and the second diagnostic image includes acquiring the first diagnostic image using first acquisition settings with a first diagnostic imaging modality, and acquiring the second diagnostic image using second acquisition settings with the first diagnostic imaging modality, the second acquisition settings being different from the first acquisition settings.

[0024] In some embodiments, the first diagnostic image and the second diagnostic image may be acquired at different acquisition settings using a specific diagnostic or medical imaging modality (e.g., CT angiography, invasive angiography, IVUS imaging, MR imaging, ICE, TEE, etc.). In one specific embodiment, the first diagnostic image and the second diagnostic image may be acquired at two different acquisition settings using two-dimensional X-ray angiography.

[0025] In this context, the term acquisition settings may specifically refer to the settings of acquisition parameters, such as the radiation duration, projection direction, acquisition timing relative to the cardiac cycle, etc. Such acquisition parameter settings can be adjusted from patient to patient or even from image to image. Thus, a change in the acquisition settings corresponds to a change in one or more acquisition parameters used to perform the corresponding acquisition. Such a change typically results in a change in the representation of the vessel of interest in the diagnostic image.

[0026] Therefore, acquiring two or more diagnostic images using different acquisition settings and subsequently correlating these images with each other allows gathering more information about the vessel or vessel segment of interest.

[0027] In some embodiments, obtaining the first diagnostic image and the second diagnostic image includes acquiring the first diagnostic image via a first diagnostic imaging modality and acquiring the second diagnostic image via a second diagnostic imaging modality, the second diagnostic imaging modality being different from the first diagnostic imaging modality. In some embodiments, the first diagnostic imaging modality corresponds to a non-invasive diagnostic imaging modality and the second diagnostic imaging modality corresponds to an invasive diagnostic imaging modality.

[0028] In some embodiments, different imaging modalities may also be used to acquire the first diagnostic image and the second diagnostic image. As an example, a non-invasive imaging modality (e.g., CT angiography, X-ray angiography, MR imaging, US imaging, etc.) may be used to acquire the first diagnostic image, and an invasive imaging modality (e.g., invasive angiography, IVUS imaging, ICE or TEE imaging, etc.) may be used to acquire the second diagnostic image. In other embodiments, both the first diagnostic image and the second diagnostic image may be acquired using an invasive imaging modality, or both the first diagnostic image and the second diagnostic image may be acquired using a non-invasive imaging modality. It should also be understood that the corresponding acquisition settings may depend specifically on the individual imaging modality used.

[0029] Because each imaging modality allows visualization of different aspects of the vessel of interest, the information gathered using different imaging modalities is greater than that available using a single imaging modality. By using functional parameter values ​​for correlating the first and second diagnostic images, it is possible to detect correspondence between the vessels of interest in each of the first and second diagnostic images, regardless of the different imaging methods used to acquire the first and second diagnostic images. This is because the functional parameters relate to the dynamics of the vessel of interest and are (primarily) independent of its geometric properties (which can be represented differently when using different imaging modalities). In particular, the combination of noninvasive and invasive techniques allows for the acquisition of a wide variety of information about the vessel of interest. This improves the accuracy of vessel assessment, thereby improving the diagnosis of any potential disease.

[0030] In some embodiments, determining the first value and / or the second value of the at least one functional parameter comprises acquiring intravascular measurement data for the vessel of interest, and deriving the first value and the second value of the at least one functional parameter at the at least one determined location based on the intravascular measurement data. In some embodiments, determining the first value and / or the second value of the at least one functional parameter comprises generating a fluid dynamics model for the vessel of interest, and deriving the first value and the second value of the at least one functional parameter at the at least one determined location based on the fluid dynamics model.

[0031] In some embodiments, the functional parameter value can be derived specifically from invasive measurements of the functional parameter. To this end, a catheter or the like with a corresponding measuring device attached thereto can be introduced into the patient's vascular system, and specifically into a vessel of interest. Inside the vessel of interest, the measuring device can be used to acquire intravascular measurement data (e.g., values ​​for one or more of pressure, flow, vascular resistance, etc.) at specific locations along the length of the vessel of interest.

[0032] In some embodiments, a first value of at least one functional parameter may be determined using first intravascular measurement data acquired by a first measurement modality, and a second value of at least one functional parameter may be determined using second intravascular measurement data acquired by a second measurement modality.

[0033] Additionally, in some specific embodiments, the measurement data collected for the vessel of interest in the first diagnostic image and for the vessel of interest in the second diagnostic image may correspond to pullback data (e.g., pressure pullback data). The pullback data may then include a plurality of first functional parameter values, one for each measurement location (i.e., each location at which a pullback measurement was performed in the vessel of interest shown in the first diagnostic image). The pullback data may also include a plurality of second functional parameter values, one for each measurement location in the vessel of interest shown in the second diagnostic image.

[0034] In some embodiments, a fluid dynamics model representing blood flow through a vessel of interest and / or blood flow through multiple vessels in a vasculature can be used to derive functional parameter values ​​based on corresponding fluid flow simulations. The term fluid dynamics model can therefore specifically refer to a model of blood flow through a vessel of interest.

[0035] This fluid dynamics model is generated by simulating the interaction of blood with the vessel wall. Since blood is a fluid and the vessel wall can be considered a corresponding surface with which the fluid interacts, the interaction of blood with the vessel wall can be most accurately defined by considering corresponding boundary conditions that account for the properties of the vessel wall and the blood interacting with it. These properties may include vessel wall composition, vessel wall elasticity and vessel impedance, bifurcations in the vessel, outflow through these bifurcations, blood viscosity, vessel exit resistance at certain locations along the length of the vessel, and so on. The fluid dynamics model can be integrated with a two-dimensional or three-dimensional geometric model to thereby represent the fluid dynamics of the blood at each location in one or more vessels of interest depicted in the geometric model.

[0036] In some embodiments, one (e.g., first) functional parameter value may correspond to a measured value, while another (e.g., second) functional parameter value may correspond to a simulated value simulated using a fluid dynamics model. As an example, the first functional parameter value may be obtained using a pullback measurement (e.g., a pressure (particularly FFR or iFR) pullback measurement, an ultrasound flow measurement (e.g., a Doppler flow measurement), etc.), and the second functional parameter value may be obtained by simulating the corresponding functional parameter using a fluid dynamics model.

[0037] In this context, in some exemplary embodiments, the first diagnostic image may correspond to a CT angiography image and the second diagnostic image may correspond to an invasive angiography image, whereby the first functional parameter value for the first diagnostic CT angiography image corresponds to a simulated iFR value derived from a fluid dynamics model and the second functional parameter value for the second diagnostic invasive angiography image corresponds to a measured FFR or iFR pullback value.

[0038] In some exemplary embodiments, the first diagnostic image may correspond to an IVUS image, and the second diagnostic image may correspond to a CT or invasive angiography image, and the correspondence detection is performed based on first and second functional parameter values ​​(e.g., pressure or flow distribution), which are simulated with the aid of a fluid dynamics model for both the first and second diagnostic images.

[0039] In some exemplary embodiments, two CT or invasive angiography images may be co-registered based on simulated functional parameter values ​​to perform correspondence detection. In some exemplary embodiments, the first diagnostic image may also correspond to a neuro-MR image, and the second diagnostic image may correspond to an ultrasound (US) image, whereby MR-based flow measurements may be used to obtain a first functional parameter value for the first diagnostic image, and Doppler flow measurements may be used to obtain a second functional parameter value for the second diagnostic image.

[0040] In other exemplary embodiments, the first diagnostic image may correspond to a CT image provided with a simulated flow distribution as a first functional parameter value and registered to an intravascular US image provided with Doppler flow measurements as a second functional parameter value.

[0041] In some exemplary embodiments, the first diagnostic image may correspond to a CT image, and the second diagnostic image may be an ICE image or a TEE image, and correspondence detection may be performed by matching a first functional parameter value derived from Doppler flow measurement with a second functional parameter value derived from a simulated flow distribution. Other combinations are also possible.

[0042] In some embodiments, the method further comprises obtaining one or more acquisition parameters used to acquire the first diagnostic image and / or the second diagnostic image, respectively, and associating one or more vessel positions along the vessel of interest represented in the first diagnostic image and the second diagnostic image, respectively, based on the one or more acquisition parameters.

[0043] In some embodiments, acquisition parameters used to acquire the first diagnostic image and the second diagnostic image may be used as further information for performing correspondence detection.

[0044] Acquisition parameters that can be used as such additional information can particularly relate to the projection geometry of the first and second diagnostic images, the cardiac phase, and certain image features. One or more of these acquisition parameters can thus be combined to eliminate ambiguities and / or inaccuracies caused by possible uncertainties when performing correspondence detection.

[0045] For example, knowing the projection geometry allows the orientation of a vessel of interest in a diagnostic image to be determined. Consequently, inherent errors resulting from misidentification of vessels of interest in the first and / or second diagnostic images when performing correspondence detection between the first and second diagnostic images can be reduced because the projection geometry is known. Consequently, it is possible to indicate how the vessel of interest should be represented in the diagnostic image for a particular projection geometry (or other factors that similarly demonstrate an impact on the vessel of interest and its representation in the diagnostic image), thereby enabling accurate correspondence detection.

[0046] As described above, acquisition parameters can be used to eliminate uncertainty regarding vessel identification. As a specific example, an FFR or iFR pullback measurement may result in the acquisition of multiple pressure values, which may be matched to pressure values ​​simulated for the left anterior descending artery (LAD) or to pressure values ​​simulated for the left circumflex artery (LCX). Knowledge of the projection geometry (specifically, the projection angle of one or more invasive angiographic images recorded with the FFR or iFR pullback data) allows for resolution of whether the data should be matched to the LAD or LCX.

[0047] In some embodiments, acquisition parameters can be used as additional information to provide an initial starting point for correspondence detection. As a specific example, knowledge of the projection geometry of one or more invasive angiography images and knowledge of the reconstruction geometry of one or more computed tomography (CT) angiography images can help perform an initial co-registration of image data from invasive angiography and CT angiography, respectively. This initial co-registration can then be used as a starting point for further correspondence detection, which then takes into account (coronary artery) motion and potential miscalibration by matching pressure values ​​from FFR or iFR pullback measurements to corresponding simulated pressure values.

[0048] In some embodiments, additional information (e.g., geometric information about the vessel of interest itself) can also help provide more accurate correspondence detection. In particular, in situations where multiple vessel locations can be matched to a particular functional parameter value, the additional geometric information can allow the vessel location to be uniquely identified. As an example, a pressure value (as a first value) obtained by invasive measurement for a particular vessel location visible in, for example, an invasive angiography image may be matched to two or more simulated pressure values ​​(second values) at two or more vessel locations in a corresponding CT angiography image. That is, the vessel location in the CT angiography image that corresponds to the vessel location in the invasive angiography image is ambiguous. In this case, given that the vessel size can be derived from both the CT angiography image and the invasive angiography image, the invasive angiography image and the CT angiography image at the particular vessel location allow determination of the location in the invasive angiography image where the vessel size best matches the vessel size in the CT angiography image. This best match then allows unique identification of the particular vessel location in the CT angiography image to be matched to the vessel location in the invasive angiography image.

[0049] In some embodiments, associating one or more vessel locations along the vessel of interest represented in the first diagnostic image with one or more vessel locations along the vessel of interest represented in the second diagnostic image includes determining a point-to-point correspondence for the one or more vessel locations along the vessel of interest represented in the first diagnostic image and the second diagnostic image, respectively.

[0050] In some embodiments, the correspondence detection is performed by creating a point-to-point correspondence between the vascular systems shown in the first diagnostic image and the second diagnostic image by matching the first value and the second value of the corresponding functional information with each other. This point-to-point correspondence can then be used for multimodal vascular modeling or multimodal image visualization. In some embodiments, the point-to-point correspondence can be specifically implemented by determining the outflow (particularly the virtual outflow) derived for the first diagnostic image and the second diagnostic image, and continuously matching the peak values ​​of the (virtual) outflow with each other. In some embodiments, the point-to-point correspondence determination is also performed based on additional information about the acquisition parameters as indicated above (e.g., projection geometry, etc.).

[0051] In some embodiments, the first diagnostic image and / or the second diagnostic image are acquired using one or more of: computed tomography (CT) angiography and / or invasive angiography and / or intravascular ultrasound (IVUS) and / or magnetic resonance (MR) imaging and / or intracardiac echocardiography (ICE) and / or transesophageal echocardiography (TEE).

[0052] For development purposes, a wide variety of different (medical) imaging modalities can be envisaged. In addition, a wide variety of functional parameter measurements can also be acquired, for example by IVUS, TEE, ICE, etc.

[0053] In some embodiments, the method further includes: training a classification device using a training data set indicating the correlation between the blood vessels of interest in the first diagnostic image and the second diagnostic image to obtain a classification result, and comparing the first value of the at least one functional parameter with the second value of the at least one functional parameter based on the classification result.

[0054] In some embodiments, matching the functional parameter values ​​derived for the first and second diagnostic images can also be performed using a machine learning algorithm (which can be implemented as a trained classifier or neural network). In particular, the machine learning algorithm (particularly a classifier) ​​can be trained using a training dataset indicating the association between vessels of interest and functional parameter values. In some embodiments, the classifier uses the training results to match the functional parameter values ​​between the first and second diagnostic images, thereby generating a point-to-point correspondence.

[0055] In some embodiments, the method further comprises segmenting the blood vessel of interest represented in the first diagnostic image and the second diagnostic image, respectively, and generating a physiological model of the blood vessel of interest based on the segmentation.

[0056] In some embodiments, the first and second diagnostic images can be used to generate a physiological model of the vessel of interest. That is, when performing correspondence detection, information collected using different acquisition settings and / or different imaging modalities can be used to generate a more comprehensive physiological model of the vessel of interest. To this end, the vessel of interest represented in the first and second diagnostic images can be segmented into multiple segments. Based on this segmentation, a physiological model of the vessel of interest can be generated, comprising a geometric model of the vessel of interest, i.e., a geometric representation of the vessel of interest and / or the entire vasculature. This geometric model can generally be a two-dimensional or three-dimensional model, depending on the information available from the first and second diagnostic images. That is, if the first and / or second diagnostic images allow for the derivation of information in three-dimensional form, the geometric model can be a three-dimensional model, whereas if the first and / or second diagnostic images allow for the derivation of information in two-dimensional form, the geometric model can be a two-dimensional model. In other embodiments, where only two-dimensional information is available, the geometric model can be a quasi-three-dimensional model, where the third dimension is interpolated from the other two dimensions.

[0057] According to another aspect, an apparatus for analyzing diagnostic image data is provided, the apparatus comprising: an input unit configured to obtain a first diagnostic image and a second diagnostic image of a vessel of interest in a vascular system of a patient; a definition unit configured to define at least one determined location for the vessel of interest in the first diagnostic image and at least one corresponding determined location for the vessel of interest in the second diagnostic image; a determination unit configured to determine a first value for at least one functional parameter at the at least one determined location in the first diagnostic image and a second value for the same at least one functional parameter at the corresponding determined location in the second diagnostic image; and an association unit configured to associate one or more vessel locations along the vessel of interest represented in the first diagnostic image with one or more vessel locations along the vessel of interest represented in the second diagnostic image based on a comparison of the first value of the at least one functional parameter with the second value of the at least one functional parameter. In some embodiments, the apparatus further comprises: a modeling unit configured to generate a physiological model of the vessel of interest based on the first diagnostic image and the second diagnostic image.

[0058] In a further aspect, a computer program for controlling an apparatus according to the invention is provided, said computer program being adapted to perform the steps of the method according to the invention when run by a processing unit. In yet another aspect, a computer readable medium having the above-mentioned computer program stored thereon is provided.

[0059] It shall be understood that the method according to claim 1, the apparatus according to claim 12, the computer program according to claim 14 and the computer readable medium according to claim 15 have similar and / or identical preferred embodiments, in particular as defined in the dependent claims.

[0060] It shall be understood that a preferred embodiment of the invention can also be any combination of the dependent claims or the above-described embodiments with the respective independent claim.

[0061] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinabove. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In the following figures:

[0063] Figure 1 An apparatus for analyzing diagnostic image data according to an embodiment is schematically illustrated.

[0064] Figure 2 The correlation between the first diagnostic image and the second diagnostic image according to the embodiment is schematically illustrated.

[0065] Figure 3 Expressed the basis Figure 1 Modification of the device.

[0066] Figure 4 A flow chart of a method for analyzing diagnostic image data according to an embodiment is shown. DETAILED DESCRIPTION

[0067] The illustrations in the drawings are schematically shown. In different drawings, similar or identical elements are provided with the same reference signs.

[0068] Figure 1 An exemplary embodiment of an apparatus 1 for analyzing diagnostic image data is schematically represented. The apparatus 1 comprises an input unit 100 , a definition unit 200 , a determination unit 300 , an association unit 400 , a modeling unit 500 and a display unit 600 .

[0069] The input unit 100 is configured to receive a first diagnostic image 10 and a second diagnostic image 20. In an exemplary embodiment, the first diagnostic image 10 and the second diagnostic image 20 correspond to two-dimensional images acquired using the same imaging modality (i.e., X-ray angiography) using different acquisition settings. In particular, the first diagnostic image 10 is acquired in a different projection direction than the second diagnostic image 20. It should be understood that although the first diagnostic image 10 and the second diagnostic image 20 are acquired according to the same imaging modality, the first diagnostic image 10 and the second diagnostic image 20 are acquired according to the same imaging modality. Figure 1In a particular embodiment of the apparatus 1 , the apparatus 1 is configured to receive two diagnostic images acquired by the same imaging modality, but the apparatus 1 may also be configured to process a first diagnostic image 10 acquired using a first imaging modality and a second diagnostic image 20 acquired using a second imaging modality.

[0070] exist Figure 1 In an exemplary embodiment of the present invention, the input unit 100 is further configured to receive data 30 indicating corresponding acquisition settings for acquiring the first diagnostic image 10 and the second diagnostic image 20. Figure 1 In the exemplary embodiment of , the input unit 100 is further configured to obtain acquisition parameters from the data 30. In other embodiments, the definition unit 200, the determination unit 300 and / or the association unit 400 may alternatively or additionally be configured to retrieve the acquisition parameters.

[0071] The input unit 100 is further configured to provide the first diagnostic image 10, the second diagnostic image 20 and the derived acquisition parameters to the definition unit 200. The definition unit 200 is configured to receive the first diagnostic image 10 and the second diagnostic image 20 and define at least one determined position for the corresponding blood vessels of interest shown in the first diagnostic image 10 and the second diagnostic image 20. Figure 1 In a specific embodiment, the definition unit 200 defines three determined positions along the longitudinal axis of the vessel of interest in the first diagnostic image 10 and defines three corresponding determined positions along the longitudinal axis of the vessel of interest in the second diagnostic image 20. It should be understood that in other embodiments, the definition unit 200 may define more or fewer determined positions for the vessel of interest. The definition unit 200 then provides data indicating the defined determined positions, along with the first diagnostic image 10 and the second diagnostic image 20, to the determination unit 300.

[0072] The determination unit 300 is configured to receive the first diagnostic image 10 and the second diagnostic image 20 and data indicating the defined determination position from the definition unit 200. In addition, the determination unit 300 is configured to receive the intravascular measurement data 40. Figure 1 In a particular embodiment, the intravascular measurement data 40 corresponds to pressure pullback data acquired by slowly pulling a pressure wire back through the vessel of interest.

[0073] The determination unit 300 is further configured to determine a corresponding value of at least one functional parameter at a corresponding determined position based on the intravascular measurement data 40. Figure 1In an exemplary embodiment of the present invention, the determining unit 300 is configured to obtain a first pressure value for a first determined position, a first pressure value for a second determined position, and a first pressure value for a third determined position from the first diagnostic image 10. Another determining unit 300 is configured to obtain a second pressure value for a first corresponding determined position, a second pressure value for a second corresponding determined position, and a second pressure value for the third determined position from the second diagnostic image 20.

[0074] The determination unit 300 then provides data indicating the first pressure values ​​and the second pressure values ​​respectively obtained from the first diagnostic image 10 and the second diagnostic image 20 at three corresponding determined positions together with the first diagnostic image 10, the second diagnostic image 20 (and optionally the acquisition parameters) to the correlation unit 400.

[0075] The correlation unit 400 is configured to receive data indicating a first pressure value and a second pressure value, a first diagnostic image 10 and a second diagnostic image 20 (and optionally also acquisition parameters). The correlation unit 400 then compares the first pressure value and the second pressure value to each other in order to determine a correlation between a first plurality of vessel positions along the longitudinal axis of a vessel of interest represented in the first diagnostic image 10 and a second plurality of vessel positions along the longitudinal axis of the same vessel of interest represented in the second diagnostic image 20. Figure 1 In a specific embodiment of the present invention, the correlation unit 400 pays special attention to the pressure distribution derived from the first pressure value and the second pressure value, and matches the pressure distribution determined for the first pressure value to the pressure distribution determined for the second pressure value. By doing so, the correlation unit 400 can establish a point-to-point correspondence between the blood vessels of interest shown in the first diagnostic image 10 and the blood vessels of interest shown in the second diagnostic image 20. That is, for each blood vessel position of the blood vessel of interest in the first diagnostic image 10, the corresponding blood vessel position of the blood vessel of interest in the second diagnostic image 20 is determined. Figure 1 In a specific embodiment of the present invention, the derivation of the point-to-point correspondence is further supported by information about acquisition parameters.

[0076] When registering the blood vessels of interest in the first diagnostic image 10 with the blood vessels of interest in the second diagnostic image 20, the registered multiple images are provided to the modeling unit 500. The modeling unit 500 segments the blood vessels of interest in the first diagnostic image 10 and the second diagnostic image 20, and generates a physiological model of the blood vessels of interest. Figure 1 In a particular embodiment of the invention, the physiological model comprises in particular a geometric model allowing the geometry of the vessel of interest to be derived. In some embodiments, the physiological model may also comprise a fluid dynamics model.

[0077] The modeling unit 500 is further configured to provide the generated model (optionally together with the first diagnostic image 10 and the second diagnostic image 20 ) to a display unit 600 , which includes a screen 601 and a user interface 602 , when the model is generated.

[0078] The display unit 600 is configured to generate a graphical representation of the physiological model and present this graphical representation to a user, optionally together with one or both of the first diagnostic image 10 and the second diagnostic image 20 . In some embodiments, the user can interact with the model via the user interface 602 .

[0079] Figure 2 A method for associating vessels of interest represented in a first diagnostic image 10 and a second diagnostic image 20 is shown. Figure 2 In a particular embodiment of the present invention, the first diagnostic image 10 and the second diagnostic image 20 correspond to coronary angiograms acquired using different projection directions.

[0080] In accordance with Figure 2 In an exemplary embodiment of the invention, a fluid dynamics model is generated based on the first diagnostic image 10 and the second diagnostic image 20. The fluid dynamics model is then used to simulate functional parameters for at least the determined positions 11, 12, 13, 21, 22, and 23 along the vessel of interest. Figure 2 In a specific embodiment of the present invention, a fluid dynamics model is used to derive virtual outflow through the vessels of interest at the determined positions 11, 12, and 13 for the diagnostic image 10, and virtual outflow through the vessels of interest at the determined positions 21, 22, and 23 for the diagnostic image 20. Subsequently, the correlation unit 400 performs matching on the peaks of the virtual outflow through the vessels of interest, thereby providing a point-to-point reference between the at least two images.

[0081] Figure 3 The apparatus 1' is schematically shown. The apparatus 1' is based on Figure 1 1 . Components identical to those in apparatus 1 are referenced with the same reference numerals in apparatus 1 ′. In other words, apparatus 1 ′ also includes an input unit 100, a definition unit 200, a determination unit 300, a modeling unit 500, and a display unit 600. Apparatus 1 ′ also includes an association unit 400 ′, which includes a classification device 401.

[0082] In order to avoid repetition, only the differences between the apparatus 1 and the apparatus 1' are described in detail below. That is, the input unit 100, the definition unit 200 and the determination unit 300, as well as the modeling unit 500 and the display unit 600 are configured with respect to Figure 1 Just as described.

[0083] In accordance with Figure 3 In a specific embodiment of the present invention, the input unit 100 receives the first imaging modality (in Figure 2 In the specific case of the apparatus 1 ', the first imaging modality corresponds to X-ray angiography. In addition, the input unit 100 receives a first diagnostic image 10' acquired using a second imaging modality (in this specific case, the second imaging modality corresponds to magnetic resonance imaging). It should be understood that although the apparatus 1 ' is configured to receive (and process) first diagnostic images 10' and second diagnostic images 20' acquired using two different imaging modalities, the apparatus 1 ' can also receive and process first diagnostic images 10 and second diagnostic images 20 acquired using one specific imaging modality.

[0084] As about Figure 1 The first diagnostic image 10' and the second diagnostic image 20' are processed as described. Figure 1 The device 1 and the Figure 3 The difference between the apparatus 1' is the association unit 400'. Figure 1 In contrast to the embodiment of Figure 2 The correlation unit 400′ comprises a classification device 401. The classification device 401 is trained by means of a training data set 50 (which is typically provided to the classification device 401 before correlation) having a correspondence between at least one functional parameter along the vessels of interest represented in the first diagnostic image 10 and the second diagnostic image 20.

[0085] In accordance with Figure 3 In a specific embodiment of the present invention, the classification device receives a first diagnostic image 10 and a second diagnostic image 20, and classifies the two diagnostic images so as to establish a point-to-point correspondence. When the first diagnostic image 10 is registered to the second diagnostic image 20, the registered diagnostic images are provided to the modeling unit 500, and the modeling unit 500 is as described in relation to Figure 1 Proceed as described.

[0086] Figure 4 A method 1000 for analyzing diagnostic image data executed by apparatus 1 is schematically shown. In step S101, input unit 100 receives a first diagnostic image 10 and a second diagnostic image 20. In step S102, input unit 100 also receives data 30 indicating acquisition settings used to acquire first diagnostic image 10 and second diagnostic image 20. In step S103, input unit 100 derives relevant acquisition parameters from data 30 and provides first diagnostic image 10 and second diagnostic image 20 together with the acquisition parameters derived from data 30 to definition unit 200.

[0087] In step S201, the definition unit 200 receives the first diagnostic image 10 and the second diagnostic image 20 together with the acquisition parameters. In step S202, the definition unit 200 defines at least one determined position for the corresponding blood vessels of interest shown in the first diagnostic image 10 and the second diagnostic image 20. Figure 4 In a specific embodiment of the present invention, the definition unit 200 again defines three determined positions along the vessel of interest in the first diagnostic image 10 and three corresponding determined positions along the vessel of interest in the second diagnostic image 20. The definition unit 200 then provides the first diagnostic image 10 and the second diagnostic image 20 and data indicating the defined determined positions to the determination unit 300.

[0088] In step S301, the determination unit 300 receives the first diagnostic image 10, the second diagnostic image 20, and data indicating a determined position from the determination unit 300, and also receives intravascular measurement data 40 indicating at least one functional parameter. In step S302, the determination unit 300 derives a corresponding value of at least one functional parameter at a corresponding determined position based on the intravascular measurement data 40. Figure 4 In an exemplary embodiment of the present invention, the determining unit 300 specifically derives a first pressure value for a first determined position, a first pressure value for a second determined position, and a first pressure value for a third determined position from the first diagnostic image 10, and derives a second pressure value for a first corresponding determined position, a second pressure value for a second corresponding determined position, and a second pressure value for a third corresponding determined position from the second diagnostic image 20.

[0089] In step S303, the determination unit 300 provides the first diagnostic image 10, the second diagnostic image 20 (and optionally also the acquisition parameters as indicated by the data 30) together with the data indicating the first pressure values ​​and the second pressure values ​​at three corresponding determined positions obtained from the first diagnostic image 10 and the second diagnostic image 20 to the association unit 400.

[0090] In step S401, the correlation unit 400 receives the first diagnostic image 10 and the second diagnostic image 20 together with data indicating the first and second pressure values ​​(and optionally, acquisition parameters). In step S402, the correlation unit 400 compares the first and second pressure values ​​with each other, and in step S403, determines the association between a first plurality of vessel positions along a vessel of interest represented in the first diagnostic image 10 and a second plurality of vessel positions along the same vessel of interest represented in the second diagnostic image 20, thereby performing vessel registration of the vessel of interest. The correlation unit 400 then provides the registered multiple images to the modeling unit 500.

[0091] In step S501, the modeling unit 500 receives a plurality of registered images, and in step S502, the modeling unit 500 segments a blood vessel of interest in the first diagnostic image 10 and the second diagnostic image 20. In step S503, the modeling unit 500 generates a physiological model of the blood vessel of interest and provides the generated model (optionally together with the first diagnostic image 10 and the second diagnostic image 20) to the display unit 600.

[0092] In step S601, the display unit 600 then generates a graphical representation of the physiological model, which optionally includes the first diagnostic image 10 and / or the second diagnostic image 20. In step S602, the display unit 600 then displays the graphical representation to the user, by means of which the user can interact with the displayed information.

[0093] Although the first diagnostic image and the second diagnostic image are acquired using X-ray angiography with different acquisition settings in the above embodiments, it should be understood that the first diagnostic image and the second diagnostic image may also be acquired using different imaging modalities (e.g., invasive angiography, neuro MR imaging, US imaging, CT imaging, ICE imaging, TEE imaging, etc.).

[0094] Although the functional parameter value corresponds to the pressure value in the above embodiment, other functional (dynamic) parameter values ​​may also be used in other embodiments, such as flow rate, vascular resistance, etc.

[0095] Those skilled in the art will be able to understand and implement other variations to the disclosed embodiments in practicing the claimed invention by studying the drawings, the disclosure, and the claims.

[0096] In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality.

[0097] A single unit or device may fulfill the functions of several items recited in the claims. 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.

[0098] The processes performed by one or more units or devices, such as defining at least one determined location, determining a first value and a second value of at least one functional parameter, associating one or more blood vessel locations, generating a fluid dynamics model, and deriving the first value and the second value of at least one functional parameter based on the fluid dynamics model, generating a physiological model, etc., can be performed by any other number of units or devices. These processes (particularly controlling the device to analyze diagnostic image data according to a control method executed by a corresponding device controller) can be implemented as program code elements of a computer program and / or dedicated hardware.

[0099] The computer program may be stored / distributed on suitable media, such as optical storage media or solid-state media supplied 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 telecommunication systems.

[0100] Any reference signs in the claims should not be construed as limiting the scope.

[0101] The present invention relates to a method for analyzing diagnostic image data, the method comprising: obtaining a first diagnostic image and a second diagnostic image of a vessel of interest in a vasculature of a patient, defining at least one determined location for the vessel of interest in the first diagnostic image and defining at least one corresponding determined location for the vessel of interest in the second diagnostic image, determining a first value for at least one functional parameter at the at least one determined location in the first diagnostic image and a second value for the same at least one functional parameter at the corresponding determined location in the second diagnostic image, and associating one or more vessel locations along the vessel of interest represented in the first diagnostic image with one or more vessel locations along the vessel of interest represented in the second diagnostic image based on a comparison of the first value of the at least one functional parameter with the second value of the at least one functional parameter.

Claims

1. A method for analyzing diagnostic image data, comprising: obtaining a first diagnostic image and a second diagnostic image of a vessel of interest in the patient's vasculature, defining at least one determined position for the vessel of interest in the first diagnostic image and defining at least one corresponding determined position for the vessel of interest in the second diagnostic image, determining a first value for at least one functional parameter at the at least one determined location of the first diagnostic image and a second value for the same at least one functional parameter at the corresponding determined location of the second diagnostic image, One or more vessel locations along the vessel of interest represented in the first diagnostic image are associated with one or more vessel locations along the vessel of interest represented in the second diagnostic image based on a comparison of the first value of the at least one functional parameter with the second value of the at least one functional parameter.

2. The method according to claim 1, wherein Obtaining the first diagnostic image and the second diagnostic image includes: acquiring the first diagnostic image using a first acquisition setting with a first diagnostic imaging modality, and The second diagnostic image is acquired by the first diagnostic imaging modality using second acquisition settings that are different from the first acquisition settings.

3. The method according to claim 1, wherein Obtaining the first diagnostic image and the second diagnostic image includes: acquiring the first diagnostic image by a first diagnostic imaging modality, and The second diagnostic image is acquired by a second diagnostic imaging modality that is different from the first diagnostic imaging modality.

4. The method according to claim 3, wherein: The first diagnostic imaging modality corresponds to a non-invasive diagnostic imaging modality, and the second diagnostic imaging modality corresponds to an invasive diagnostic imaging modality.

5. The method according to claim 1, wherein Determining the first value and / or the second value of the at least one functional parameter comprises: acquiring intravascular measurement data for the vessel of interest, and The first value and the second value of the at least one functional parameter at the at least one determined position are derived based on the intravascular measurement data.

6. The method according to claim 1, wherein Determining the first value and / or the second value of the at least one functional parameter comprises: generating a fluid dynamics model for the vessel of interest, and The first value and the second value of the at least one functional parameter at the at least one determined location are derived based on the fluid dynamics model.

7. The method according to claim 1, further comprising: obtaining one or more acquisition parameters for acquiring the first diagnostic image and / or the second diagnostic image, respectively, and One or more vessel locations along the vessel of interest represented in the first and second diagnostic images, respectively, are associated based on the one or more acquisition parameters.

8. The method according to claim 1, wherein Associating one or more vessel locations along the vessel of interest represented in the first diagnostic image with one or more vessel locations along the vessel of interest represented in the second diagnostic image includes determining a point-to-point correspondence for the one or more vessel locations along the vessel of interest represented in the first and second diagnostic images, respectively.

9. The method according to claim 1, wherein The first diagnostic image and / or the second diagnostic image are acquired using one or more of: computed tomography angiography and / or invasive angiography and / or intravascular ultrasound imaging and / or magnetic resonance imaging and / or intracardiac echocardiography and / or transesophageal echocardiography.

10. The method according to claim 1, further comprising: training a classification device using a training data set indicating correlation between blood vessels of interest in the first diagnostic image and the second diagnostic image to obtain a classification result, and The first value of the at least one functional parameter is compared with the second value of the at least one functional parameter based on the classification result.

11. The method according to claim 1 , further comprising: segmenting the blood vessels of interest represented in the first diagnostic image and the second diagnostic image, respectively, and A physiological model of the vessel of interest is generated based on the segmentation.

12. An apparatus for analyzing diagnostic image data, comprising: an input unit configured to obtain a first diagnostic image and a second diagnostic image of a vessel of interest in a vasculature of a patient; a defining unit configured to define at least one determined position for the vessel of interest in the first diagnostic image and to define at least one corresponding determined position for the vessel of interest in the second diagnostic image; a determining unit configured to determine a first value for at least one functional parameter at the at least one determined location of the first diagnostic image and a second value for the same at least one functional parameter at the corresponding determined location of the second diagnostic image; a correlating unit configured to correlate one or more vessel positions along the vessel of interest represented in the first diagnostic image with one or more vessel positions along the vessel of interest represented in the second diagnostic image based on a comparison of the first value of the at least one functional parameter with the second value of the at least one functional parameter.

13. The apparatus according to claim 12, further comprising: A modeling unit is configured to generate a physiological model of the blood vessel of interest based on the first diagnostic image and the second diagnostic image.

14. A computer program product comprising a computer program adapted to perform the method according to any one of claims 1 to 11 for controlling an apparatus according to claim 12 or 13 when the computer program is run by a processing unit.

15. A computer-readable medium having stored thereon the computer program according to claim 14.

Images