System and method for invasive diagnostic planning

Abstract

A method for performing an invasive diagnostic test prior to a procedure is provided. Such a method includes retrieving an image including at least a portion of a blood vessel, and extracting cross-sectional profiles from the image at different locations along the blood vessel. The method then advances to generate a hemodynamic model based on the image and at least in part based on the cross-sectional profile. The hemodynamic model models blood flow at each of the different locations from which the cross-sectional profile has been extracted. The method then extracts a determination of plaque features from the image and generates or retrieves an initial treatment plan based at least in part on the hemodynamic model and the determined plaque features. The method then determines that the defined invasive diagnostic test may change the initial treatment plan based on the hemodynamic model and the determination of plaque characteristics.

Description

Technical Field

[0001] The present disclosure generally relates to systems and methods for invasive diagnostic planning. Specifically, the present disclosure relates to using CT-guided modeling to determine whether the use of invasive diagnostic devices is likely to add value and to support invasive diagnostic device selection for percutaneous coronary intervention (PCI). Background Art

[0002] Coronary interventions, such as percutaneous coronary intervention (PCI), are often planned based on imaging. Such imaging, which can be cardiac CT imaging, is often used as the first-line test for coronary artery disease (CAD), and an increasing number of patients with prior CT examinations are routinely scheduled for diagnostic and interventional laboratory procedures.

[0003] Spectral CT and spectral CT angiography allow for better coronary artery assessment due to the material separation between the contrast agent and calcified lesions. In addition, such spectral CT imaging allows for better robustness to imaging artifacts such as calcium halos. Based on the improved material separation, high-risk plaque characteristics such as positive remodeling, low-attenuation plaques, punctate calcifications, and napkin patterns can be visualized.

[0004] However, to plan a procedure, the medical team typically initially gathers all diagnostic information and then creates a surgical plan. Consequently, modern procedures enable the determination of whether to perform invasive diagnostic functions and imaging measurements without first determining whether such invasive procedures are necessary or likely to add value. Such procedures may include intravascular ultrasound (IVUS), optical coherence tomography (OCT), angiography-based pressure or flow testing, or guidewire-based pressure or flow testing.

[0005] Thus, there is a need for a system and preoperative method for utilizing imaging, such as CT imaging, to determine and plan appropriate coronary interventions. There is also a need for a system and method that can determine whether CT imaging is sufficient to complete such a plan, or whether additional invasive diagnostic capabilities and imaging measurements, such as IVUS, OCT, pressure / flow, and angiography-based pressure or flow testing, are needed to improve such a plan. Summary of the Invention

[0006] Methods and systems for planning coronary interventions, such as percutaneous coronary intervention (PCI), are provided. Modern interventions are often planned based on spectral CT imaging, which is increasingly used as the first-line test for CAD. However, additional invasive procedures are often used to confirm the diagnosis, and interventions are often planned based on these additional invasive procedures.

[0007] To best utilize available resources and better manage risk to the patient, it is beneficial to determine whether the treatment plan can be based solely on CT data or whether additional invasive diagnostic capabilities and imaging measurements are required. Such more invasive procedures may include intravascular ultrasound (IVUS), optical coherence tomography (OCT), angiography-based pressure or flow testing, or guidewire-based pressure or flow testing.

[0008] Because avoiding unnecessary invasive procedures is beneficial, the systems and methods described herein provide guidance as to whether a treatment plan can be made based on a CT image or CT angiography (CTA), or as to whether further invasive evaluation would be valuable. The guidance can be based on a determination of how likely it is that additional invasive evaluation will alter the proposed treatment plan.

[0009] Many embodiments rely on spectral CT imaging because such spectral CT imaging has the following advantages: it improves local image contrast by varying the image reconstruction properties on the image according to the underlying tissue, making the visual assessment of coronary artery morphology more accurate. Such spectral CT imaging can then be used to model blood flow in the coronary arteries, which in turn can be used to evaluate whether further information from more invasive diagnostic procedures may change the treatment plan.

[0010] In some embodiments, a method for performing an invasive diagnostic test prior to a procedure is provided, comprising: retrieving at least one image comprising at least a portion of a blood vessel (typically a coronary artery); and extracting from the at least one image a plurality of cross-sectional profiles at different locations along the blood vessel.

[0011] The method then proceeds to generate a hemodynamic model based on the at least one image and at least in part on the cross-sectional profile.Such a hemodynamic model models the blood flow at each of the different locations for which the cross-sectional profile has been extracted.

[0012] The method then extracts a determination of plaque characteristics from the at least one image and generates or retrieves an initial treatment plan based at least in part on the hemodynamic model and the determined plaque characteristics.

[0013] The method then determines, based on the hemodynamic model and determination of plaque characteristics, that a defined invasive diagnostic test may alter the initial treatment plan.

[0014] In some embodiments, determining that the defined invasive diagnostic test is likely to alter the initial treatment plan is performed by an AI-based algorithm trained on historical patient case data and corresponding risk profiles.

[0015] In some embodiments, the method includes generating a recommendation to perform a defined invasive diagnostic test.

[0016] In some embodiments, the defined invasive diagnostic test is one of a plurality of potential invasive diagnostic tests.The defined invasive diagnostic test is then the test of the plurality of potential invasive diagnostic tests determined to be most likely to change the diagnosis or change the surgical plan for the procedure.

[0017] In some such embodiments, the plurality of potentially invasive diagnostic tests includes at least one of: intravascular ultrasound (IVUS), optical coherence tomography (OCT), angiography-based pressure or flow testing, and guidewire-based pressure or flow testing.

[0018] In some embodiments, determining that the defined invasive diagnostic test is likely to alter the initial treatment plan is performed by modeling the performance of the defined invasive diagnostic test in the hemodynamic model.

[0019] In some embodiments, the at least one image is a CT image, and the cross-sectional profile extracted from the image is perpendicular to a local centerline extracted from a corresponding CT image. In some such embodiments, the CT image is a contrast-based image, and the method further comprises generating a binary image mask from the contrast-based image, skeletonizing the corresponding CT image, and deriving at least one local centerline from the skeletonized image.

[0020] In some embodiments, the hemodynamic model determines blood pressure, blood flow, and shear stress at a location corresponding to each cross-sectional profile.

[0021] In some embodiments, the CT image is a spectral CT image, and the determining of plaque characteristics includes determining a type and a corresponding morphological pattern of plaque at each cross-sectional profile.

[0022] In some such embodiments, the depth of the calcification at each cross-sectional profile is determined based on the distance of the calcification from the centerline.The centerline then corresponds to the center of the corresponding lumen at the cross-sectional profile.

[0023] In some embodiments, the method proceeds to display to the user a map of plaque at each cross-sectional profile or a map of high-risk features in the hemodynamic model.

[0024] In some embodiments, the method determines a risk of plaque rupture based on the plaque characteristics. In such embodiments, an initial treatment plan is based at least in part on the risk of plaque rupture.

[0025] In some embodiments, the method determines that a defined invasive diagnostic test is likely to change the initial treatment plan by determining a percentage likelihood that the defined invasive test will change the initial treatment plan and comparing the determined likelihood to a threshold percentage likelihood.

[0026] In some embodiments, the method includes modeling the implementation of potential invasive diagnostic tests in the context of a hemodynamic model. For each potential invasive diagnostic test, the method then generates a probability that the corresponding diagnostic test will change the initial treatment plan. The defined invasive diagnostic test is then one of a plurality of potential invasive diagnostic tests.

[0027] In some such embodiments, the method further comprises displaying to the user the likelihood associated with each of the potential diagnostic tests.

[0028] In some embodiments, generating the likelihood is performed by an AI-based algorithm trained on historical patient case data and corresponding risk profiles. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a schematic diagram of a system according to one embodiment of the present disclosure.

[0030] Figure 2 A method for invasive diagnostic testing according to the present disclosure is illustrated. DETAILED DESCRIPTION

[0031] The description of the illustrative embodiments according to the principles of the present invention is intended to be read in conjunction with the accompanying drawings, which are considered part of the entire written description. In the description of the embodiments of the invention disclosed herein, any reference to direction or orientation is intended solely for ease of description and is not intended to limit the scope of the invention in any way. Relative terms such as "lower," "upper," "horizontal," "vertical," "above," "below," "upward," "downward," "top," and "bottom" and their derivatives (e.g., "horizontally," "downwardly," "upwardly," etc.) should be interpreted as referring to the orientation as then described or as shown in the drawings discussed. These relative terms are for ease of description only and do not require that the device be constructed or operated in a particular orientation unless expressly indicated as such. Unless expressly stated otherwise, terms such as "attach," "attach," "connect," "couple," "interconnect," and similar terms refer to relationships in which structures are fixed or attached to each other directly or indirectly through intermediate structures, as well as both removable and rigid attachments or relationships. Furthermore, the features and benefits of the invention are illustrated by reference to the illustrated embodiments. Therefore, the invention should obviously not be limited to such exemplary embodiments illustrating some possible non-limiting feature combinations that may exist alone or in other feature combinations; the scope of the invention is defined by the appended claims.

[0032] This disclosure describes one or more best modes currently contemplated for practicing the present invention. This description is not intended to be taken in a limiting sense, but rather provides examples of the present invention presented for illustrative purposes only, with reference to the accompanying drawings, to suggest advantages and configurations of the present invention to those skilled in the art. Like reference numerals designate similar or similar components throughout the various views of the drawings.

[0033] It is important to note that the disclosed embodiments are merely examples of the many advantageous uses of the innovative teachings herein. In general, statements made in the specification of this application do not necessarily limit any of the various claimed disclosures. Furthermore, some statements may apply to some inventive features but not to others. In general, unless otherwise indicated, singular elements may be plural, and vice versa, without loss of generality.

[0034] A preoperative method for planning surgical procedures based on CT imaging is described. The method involves extracting cross-sectional profiles at different locations along the coronary arteries and generating a hemodynamic model based on the CT images. This hemodynamic model models blood flow at the different locations where the cross-sectional profiles were extracted.

[0035] Typically, if a patient is scheduled for a coronary intervention, such as percutaneous coronary intervention (PCI), the methods described herein can be applied to plan the underlying procedure or intervention. In doing so, the hemodynamic model can be used to determine whether the information derived from the CT imaging is sufficient for planning the intervention, or whether additional information would be valuable. Such a determination can be based on determining how likely it is that additional information available through invasive diagnostic testing would change the diagnosis or surgical plan of the procedure.

[0036] In some embodiments, pre-intervention imaging can take forms other than CT, such as the above-mentioned spectral CT imaging. In medical imaging other than CT (such as magnetic resonance imaging (MRI) or positron emission tomography (PET)), different methods can be used to process images, and the resulting images or image data can take different forms. In this disclosure, embodiments are discussed based on CT imaging. However, it should be understood that the methods and systems described herein can also be used in the context of other imaging modalities.

[0037] Figure 1 FIG. 1 is a schematic diagram of a system 100 according to an embodiment of the present disclosure. As shown in the figure, the system 100 generally includes a processing device 110 and an imaging device 120 .

[0038] The processing device 110 can apply processing routines to images or measurement data, such as projection data, received from the imaging device 120. The processing device 110 can include a memory 113 and a processor circuit 111. The memory 113 can store a plurality of instructions. The processor circuit 111 can be coupled to the memory 113 and can be configured to execute the instructions. The instructions stored in the memory 113 can include processing routines and data associated with the processing routines, such as machine learning algorithms and various filters used to process images. Although all data is described as being stored in the memory 113, it should be understood that in some embodiments, some data may be stored in a database, which itself may be stored in the memory or in a separate system.

[0039] The processing device 110 may also include an input 115 and an output 117. The input 115 may receive information, such as images or measurement data, from the imaging device 120. The output 117 may output information, such as processed images, to a user or user interface device. The output 117 may similarly output determinations generated by the methods described below, such as recommendations and risk determinations, as well as the likelihood that a given test may change the diagnosis or treatment. The output may include a monitor or display that may display additional information or a model that is updated in real time.

[0040] In some embodiments, processing device 110 may be directly associated with imaging device 120. In alternative embodiments, processing device 110 may be distinct from imaging device 120 such that it receives image or measurement data through network 311 or other interface at input 115 for processing.

[0041] In some embodiments, imaging device 120 may include image data processing equipment and a spectral or conventional CT scanning unit for generating CT projection data when scanning an object (e.g., a patient). Furthermore, imaging device 120 may be configured for coronary CT angiography. This allows imaging to be performed using contrast, and image timing may be configured to track fluid flow in the blood vessels.

[0042] In addition to conventional and spectral CT images, the method can rely on multi-spectral image results, photon counting CT images or dark field CT images.

[0043] While a system comprising an imaging device 120 and a processing device 110 is shown, it should be understood that the method can be implemented directly on the processing device, such as in the context of images received at input 115 via network 311. The methods described herein relate to processing images as part of evaluating and planning a potential intervention, typically in the context of a procedure such as stent implantation. As mentioned above, imaging is typically performed prior to such a procedure. In this manner, previously generated imaging can be retrieved via input 115 and evaluated prior to or in lieu of obtaining a new image.

[0044] Figure 2 A method for implementing an invasive diagnostic test according to the present disclosure is illustrated. As shown, in implementing the method, the described system 100 can first retrieve (200) at least one image from the imaging device 120 at the input portion 115. The image includes at least a portion of the patient's coronary arteries. The retrieved image is typically obtained by CT imaging, such as a conventional CT scan or non-invasive coronary CT angiography, which can be used to evaluate plaque in the coronary arteries. Such CT imaging can be spectral CT imaging, which provides additional information, as described above. When referring to images, it should be understood that more than one image can be relied upon, and the CT image can be a three-dimensional image constructed from a large number of scans.

[0045] Once such imaging is retrieved (at 200), the method proceeds to segmenting the coronary arteries (210) to support analysis. This may include finding the centerline and lumen outline of the coronary arteries (220). This may be done, for example, using spectral reconstruction using intensity thresholds established in the mono-energy CT image, or using an iodine-based image to create a binary image mask. Skeletonization may then be applied to derive the centerline, such that after skeletonization of the corresponding CT image, at least one local centerline may be extracted therefrom.

[0046] At each centerline location, a hypothetical healthy vessel diameter may be estimated from the nearest non-diseased proximal and distal locations. The method may then create or extract (230) a plurality of cross-sectional profiles or slices corresponding to different locations along the coronary artery from the image. Such cross-sectional profiles are typically perpendicular to the local centerline direction previously extracted from the corresponding CT image (found at 220). In some embodiments, photon counting CT may be used for this procedure due to its higher accuracy.

[0047] Once the cross-sectional profiles have been created or extracted (at 230), the method proceeds to generating a hemodynamic model (240). Such a model is based on the image itself as well as the segmentation (at 210) and the derived cross-sectional profiles (at 230). The hemodynamic model models the blood flow at each of the different locations for which the cross-sectional profiles have been created or extracted. In some embodiments, in addition to the underlying blood flow, the hemodynamic model models the blood pressure and shear stress at the location corresponding to each cross-sectional profile (extracted at 230).

[0048] Separately, the method returns to segmentation (at 210) and extracts from the at least one image (retrieved at 200) the determination of the blob features in the segments identified by the segmentation (250). In some embodiments, the blob features may be identified and processed at locations corresponding to each of the derived cross-sectional profiles (at 230).

[0049] The identified plaque characteristics (250) may include identification of the longitudinal location of the plaque in the artery and identification of the location and classification of the plaque. For example, the plaque may be classified as soft, mixed, or calcified. Such determination may be based on spectral CT image intensity, where spectral CT images are used. Additionally, such determination may be based on known typical morphological patterns of plaque, such as the napkin ring sign.

[0050] In some embodiments, the calcification depth of the plaque can be similarly estimated by considering the plaque characteristics (250) in the context of the centerline and lumen contours of the coronary artery (identified at 220). Thus, for example, the determination of whether the calcification is in the intima layer or the media layer can be estimated based on the distance of the calcification from the center of the lumen. Thus, the determination of the plaque characteristics (at 250) can be a combination of determining the type of plaque and the corresponding morphological pattern at each cross-sectional contour.

[0051] In some embodiments, calcium content quantification can be based on CAN = non-calcified / CAL = low or mixed calcification level / CAH = highly calcified.

[0052] High-risk plaque (HRP) features can also be identified. Such high-risk features may include LA = low-attenuation plaque <30 HU / NR = napkin ring sign (low-attenuation core surrounded by a rim of higher attenuation and <130 HU) / PR = positive remodeling (remodeling idx > 1.1 = CSA increased by 10%) / SC = punctate calcification (calcified lesions between 1-3 mm and >130 HU)

[0053] Other patterns may also be identifiable. For example, plaques can be classified as DC = dense calcification (substantial calcification with negligible other plaque components) / FM = mixed fibrous calcification (a mixture of calcified foci and fibrous components) / FP = fibrous plaque (fiber only with negligible other plaque components).

[0054] Other features of interest may include thrombosis / peripheral coronary inflammation (eg, via pFAI).

[0055] Once plaque characteristics are identified (at 250), such plaque characteristics can be used to identify rupture risk (260), which in turn can be used to guide treatment. Once plaque characteristics are fully evaluated (at 250, 260) and cross-sectional profiles are extracted (at 230) and utilized in the context of a hemodynamic model (at 240), the results can be combined to generate a patient classification for the patient (265).

[0056] In some embodiments, these findings can be presented to the user independently on a cross-sectional basis (at 270), such as using color coding on the tortuosity or multi-planar reformatting of the vessel. The presentation to the user can be in the context of a risk profile map or other presentation of high-risk features. Thus, the method can display a map of plaque at each cross-sectional profile or a map of high-risk features in the hemodynamic model.

[0057] Once the hemodynamic model is generated (at 240) and the plaque characteristics have been identified (at 250), an initial treatment plan is generated or retrieved (280) based at least in part on the hemodynamic model and the plaque characteristics. Such a treatment plan can be manually generated, thereby provided by a clinician using the described method, or can be automatically generated by the method. In some embodiments, the treatment plan can be independently generated and provided by a clinician, regardless of whether the clinician generating the treatment plan is using the method.

[0058] Once the initial treatment plan is generated or retrieved (at 280), the method proceeds to determine (290) whether one or more invasive diagnostic tests are likely to change the initial treatment plan that has been generated or retrieved (at 280) based on the hemodynamic model and the determination of the plaque characteristics. If an invasive test is unlikely to provide additional information that will change the course of action proposed by the clinician or recommended by the method, the value of such a test can be minimal. Therefore, even if such a test is likely to provide additional information, if such information is unlikely to change the treatment plan, or in some cases, the diagnosis, such a test should be avoided. In this way, the method can determine whether an invasive diagnostic test provides sufficient value to justify the cost, time, effort and / or risk associated with such a test.

[0059] As part of determining (at 290) whether one or more invasive diagnostic tests are likely to change the initial treatment plan, the method can independently evaluate each of a plurality of potential invasive diagnostic tests. Each such test can be, for example, intravascular ultrasound (IVUS), optical coherence tomography (OCT), angiographic-based pressure or flow test, or guidewire-based pressure or flow test. In some embodiments, determining (at 290) can include, for each such test, an evaluation of whether such test is likely to change the initial treatment plan. In some embodiments, the method can also evaluate a single type of test performed with different test parameters.

[0060] Once each potentially invasive diagnostic test is evaluated, each such test may be assigned a likelihood that the diagnosis and treatment plan (such as the initial treatment plan) would be altered if the corresponding diagnostic test were performed as a subsequent evaluation.

[0061] In some embodiments, a list of potential invasive diagnostic tests and the corresponding likelihood that such tests will change the diagnosis and treatment plan can be presented (295) to the user. In other embodiments, the method can alternatively select a defined invasive diagnostic test from a plurality of potential tests, wherein the defined test is the test most likely to change the initial treatment plan. Such likelihood can be defined in terms of a percentage likelihood that the corresponding invasive test will change the initial treatment plan, or can be presented in a specific other manner. In such embodiments, a threshold value for measuring likelihood can be provided. For example, a threshold percentage likelihood can be provided. In this way, the likelihood assigned to a particular test can be compared to a threshold value to determine whether to recommend the corresponding test or any one of the plurality of potential invasive diagnostic tests.

[0062] In some embodiments, the determination of whether one or more invasive diagnostic tests are likely to change the initial treatment plan (at 290) is based on an AI-based algorithm, such as a convolutional neural network (CNN). Such a CNN can be trained based on historical patient case data and a corresponding risk profile. In such embodiments, the determination can be based on a risk profile generated for the patient (at 270). Such historical patient case data can also include documentation regarding the corresponding initial diagnosis and treatment plan, any additional invasive diagnostic measurements collected during treatment, and final treatment documentation.

[0063] In some embodiments, the AI-based algorithm may be provided with guidelines and other literature associated with patient care. Such guidelines may be used to determine whether information that may be obtained from one or more invasive diagnostic tests is likely to change the initial diagnosis or treatment plan.

[0064] It should be understood that although the methods described herein utilize CNN, other machine learning techniques may also be used. For example, general neural networks such as random forests, shallow predictors (support vector machines or SVMs and Gaussian processes or GPs) or more advanced architectures such as recurrent neural networks (RNNs) and transformer models may also be used.

[0065] The method can be used in CT systems and imaging workstations as well as PACS viewers dedicated to coronary artery analysis using CCTA scans.

[0066] In some embodiments, determining (at 290) that a defined invasive diagnostic test may alter the initial treatment plan is performed by modeling the performance of the defined invasive diagnostic test in the context of a hemodynamic model. In some embodiments, where multiple potential invasive diagnostic tests are considered, each such test may be modeled in the context of the hemodynamic model.

[0067] In some embodiments, the method can generate a recommendation to perform an invasive diagnostic test. In such an embodiment, it can be determined (at 290) that the defined invasive diagnostic test is likely to change the initial treatment plan. As such, the method can proceed to recommending (300) the defined invasive diagnostic test. During practice, a clinician utilizing the method can then proceed to perform the recommended invasive test (310) and create a final treatment plan (320). In the event that the method determines that the invasive diagnostic test is unlikely to change the initial treatment plan (at 280), the initial treatment plan can be finalized (at 330) as the final treatment plan (at 320).

[0068] In some embodiments, the determination (at 290) is based on specified factors understood from the literature. For example, if certain portions have three or more high-risk plaque characteristics as determined based on plaque characterization (at 250), the method may not recommend invasive physiological measurements and may instead recommend medical treatment or direct stenting if the CT-based fractional flow reserve analysis (CT-FFR) is less than 0.8.

[0069] Alternatively, the method can recommend invasive FFR in cases where the segment has less than 3 high-risk plaque features and the CT-FFR is close to the cutoff point.

[0070] In cases where structures are further from the vessel lumen, the method can recommend IVUS over OCT. In cases where indications of collaterals are found, the method can indicate that angiography-based FFR or instantaneous wave-free ratio (iFR) should not be used, and instead recommend guideline-based measurements. In cases where tandem lesions are identified, the method can recommend iFR over FFR.

[0071] While the method is described herein with respect to the coronary arteries, it will be appreciated that similar methods can be used with respect to the pulmonary arteries in the context of peripheral arterial disease, as well as with respect to the carotid arteries or cerebral vessels (eg, the circle of Williams).

[0072] The method according to the present disclosure can be implemented on a computer as a computer-implemented method, or implemented in dedicated hardware, or implemented in a combination of the two. The executable code for the method according to the present disclosure can be stored on a computer program product. Examples of computer program products include memory devices, optical storage devices, integrated circuits, servers, online software, etc. Preferably, the computer program product may include non-transient program code stored on a computer-readable medium, which is used to perform the method according to the present disclosure when the program product is executed on a computer. In an embodiment, the computer program may include computer program code suitable for performing all steps of the method according to the present disclosure when the computer program is run on a computer. The computer program may be embodied on a computer-readable medium.

[0073] While the present disclosure has been described at length and with a certain particularity with respect to several described embodiments, it is not intended that it should be limited to any such details or embodiments or any particular embodiment, but rather should be interpreted with reference to the appended claims so as to provide the broadest possible interpretation of such claims in light of the prior art and so effectively encompass the intended scope of the present disclosure.

[0074] All examples and conditional language recorded herein are intended to be used for teaching purposes, to help the reader understand the principles of the present disclosure and the concept that the inventors have contributed to promote this area, and should be interpreted as not being limited to such specific examples and conditions of recording. In addition, all statements of the principles, aspects and embodiments of the present disclosure and their specific examples are intended to cover both their structure and function equivalents. In addition, such equivalents are intended to include currently known equivalents and equivalents developed in the future, i.e., any element of the performance identical function of development, and no matter how the structure.

Claims

1. A method for performing an invasive diagnostic test prior to a procedure, comprising: retrieving at least one image, the image including at least a portion of the blood vessel; extracting a plurality of cross-sectional profiles at different locations along the blood vessel from the at least one image; generating a hemodynamic model based on the at least one image and at least in part on the cross-sectional profile, the hemodynamic model modeling blood flow at each of the different locations for which the cross-sectional profile has been extracted; extracting a determination of plaque characteristics from the at least one image; generating or retrieving an initial treatment plan based at least in part on the hemodynamic model and the determined plaque characteristics; Determining a defined invasive diagnostic test based on the hemodynamic model and the determination of plaque characteristics may alter the initial treatment plan.

2. The method according to claim 1, wherein Determining whether the defined invasive diagnostic test may alter the initial treatment plan is performed by an AI-based algorithm trained on historical patient case data and corresponding risk profiles.

3. The method according to claim 1, wherein The blood vessel is a coronary artery.

4. The method according to claim 1, wherein The defined invasive diagnostic test is a potential invasive diagnostic test of a plurality of potential invasive diagnostic tests, and wherein the defined invasive diagnostic test is the test of the plurality of potential invasive diagnostic tests determined to be most likely to change the diagnosis or alter the surgical plan for the procedure.

5. The method according to claim 4, wherein The plurality of potentially invasive diagnostic tests includes at least one of: intravascular ultrasound (IVUS), optical coherence tomography (OCT), angiography-based pressure or flow testing, and guidewire-based pressure or flow testing.

6. The method according to claim 1, wherein Determining that the defined invasive diagnostic test may alter the initial treatment plan is performed by modeling performance of the defined invasive diagnostic test in the hemodynamic model.

7. The method according to claim 1, wherein The at least one image is a CT image, and wherein the cross-sectional profile extracted from the at least one image is perpendicular to a local centerline extracted from a corresponding CT image.

8. The method according to claim 7, wherein: The CT image is a contrast-based image, the method further comprising generating a binary image mask based on the contrast-based image, skeletonizing the corresponding CT image, and deriving at least one local centerline from the skeletonized image.

9. The method according to claim 7, wherein: The hemodynamic model determines blood pressure, blood flow, and shear stress at a location corresponding to each cross-sectional profile.

10. The method according to claim 7, wherein: The CT image is a spectral CT image, and wherein the determining of plaque characteristics includes determining a type and a corresponding morphological pattern of plaque at each cross-sectional profile.

11. The method of claim 10, further comprising determining a depth of the calcification based on a distance of the calcification from the centerline at each cross-sectional profile, wherein The centerline corresponds to the center of the corresponding lumen at the cross-sectional profile. 12 . The method of claim 10 , further comprising displaying a map of plaque at each cross-sectional profile or a map of high-risk features in the hemodynamic model.

13. The method according to claim 1, further comprising determining the risk of plaque rupture based on the plaque characteristics, wherein: The initial treatment plan is based at least in part on the risk of plaque rupture.

14. The method according to claim 1, wherein Determining that a defined invasive diagnostic test is likely to change the initial treatment plan is performed by determining a percentage likelihood that the defined invasive test will change the initial treatment plan and comparing the determined likelihood to a threshold percentage likelihood.

15. The method according to claim 1, further comprising: modeling implementation of multiple potential invasive diagnostic tests within the context of the hemodynamic model; And for each potential invasive diagnostic test, generating a likelihood that the corresponding diagnostic test will change the initial treatment plan, wherein the defined invasive diagnostic test is one of the plurality of potential invasive diagnostic tests.

16. The method of claim 15, further comprising displaying a probability associated with each of the potential diagnostic tests.

17. The method according to claim 15, wherein: The generation of the likelihood is performed by an AI-based algorithm trained on historical patient case data and corresponding risk profiles.

18. A system for planning a process, comprising: a memory for storing a plurality of instructions; a processor circuit coupled to the memory and configured to execute the instructions to: retrieving at least one image, the image including at least a portion of the blood vessel; extracting a plurality of cross-sectional profiles at different locations along the blood vessel from the at least one image; generating a hemodynamic model based on the at least one image and at least in part on the cross-sectional profile, the hemodynamic model modeling blood flow at each of the different locations for which the cross-sectional profile has been extracted; extracting a determination of plaque characteristics from the at least one image; generating or retrieving an initial treatment plan based at least in part on the hemodynamic model and the determined plaque characteristics; as well as Determining a defined invasive diagnostic test based on the hemodynamic model and the determination of the plaque characteristics may alter the initial treatment plan.

19. The system according to claim 18, wherein The blood vessel is a coronary artery, and wherein determining that the defined invasive diagnostic test is likely to alter the initial treatment plan is performed by an AI-based algorithm trained on historical patient case data and corresponding risk profiles.

20. The system of claim 18, wherein: The defined invasive diagnostic test is a potential invasive diagnostic test among a plurality of potential invasive diagnostic tests, and wherein determining that the defined invasive diagnostic test may change the initial treatment plan is performed by modeling the implementation of each potential invasive diagnostic test among the plurality of potential invasive diagnostic tests in the context of the hemodynamic model; and for each potential invasive diagnostic test, generating a likelihood that the corresponding diagnostic test will change the initial treatment plan.

Images