Method, device, equipment, and medium for determining FFR based on multimodal medical images

Abstract

The present invention provides a method, device, equipment and medium for determining FFR based on multimodal medical images, the method includes: acquiring an intravascular image including a vascular segment of interest (S210); acquiring an extravascular image including a vascular segment of interest, the vascular segment of interest being at least partially overlapped with the vascular segment of interest (S220); performing registration on the intravascular image and the extravascular image to obtain a registration result (S230); and determining a target fractional flow reserve based on the intravascular image and the extravascular image according to the registration result (S240). The FFR determination method of the present invention optimizes the calculation of fractional flow reserve by integrating advantageous information of the intravascular image and the extravascular image according to the registration result between the intravascular image and the extravascular image, and obtains a fractional flow reserve that combines completeness and local accuracy of the vascular segment based on the multimodal medical images, thereby improving the accuracy and stability of the fractional flow reserve calculation.

Description

[Technical Field]

[0001] The present invention relates to the field of medical instruments for intravascular intervention imaging, and in particular to a method, apparatus, device and medium for determining FFR based on multimodal medical images. [Background technology]

[0002] Coronary artery disease has become the most common and fatal disease in the world. Currently, percutaneous coronary intervention (PCI) is one of the effective treatment methods for coronary artery disease.

[0003] Fractional flow reserve (FFR) measures the pressure difference between the distal and proximal ends of a coronary artery stenosis, effectively reflecting the impact of stenotic lesions on the blood supply function of the blood vessel and assessing whether ischemia will occur in the myocardium supplied by the coronary artery. Currently, FFR has become the gold standard for diagnosing, guiding, and evaluating PCI treatment in clinical practice.

[0004] However, conventional FFR requires measuring blood pressure via a pressure guidewire, which is a complex and time-consuming procedure, and the required surgical consumables (FFR guidewires) are expensive. Furthermore, side effects from injecting dilating drugs into blood vessels can cause discomfort to patients, and the guidewire intervention process is prone to damage to the patient's blood vessels. These factors have limited the widespread adoption of FFR measurement using the pressure guidewire method.

[0005] In addition, conventional methods for calculating FFR using images generally involve obtaining images of the exterior or interior of blood vessels based on vascular imaging techniques, such as X-ray contrast imaging, computed tomography (CT) imaging, optical coherence tomography (OCT) imaging, and intravascular ultrasound (IVUS) imaging techniques, and then obtaining information about the vessel lumen, and then calculating the fractional flow reserve using methods such as fluid dynamics analysis, stress analysis, and vascular tissue analysis.

[0006] However, because the length of the blood vessel imaged when an intraluminal image is acquired is limited, it may not be possible to completely cover the entire diseased blood vessel, resulting in an incomplete blood vessel segment represented by the fractional flow reserve calculated based on the intraluminal image. Furthermore, the observation range of the branching vessel in the intraluminal image is very short, making it difficult to accurately identify the branching vessel's branching flow relative to the blood flow. Furthermore, the intraluminal image cannot reflect the overall spatial information of the blood vessel, especially its curvature, making it prone to calculation errors. Compared to the intraluminal image, the extravascular image can better represent the overall spatial information of the examined blood vessel segment. Therefore, the blood vessel segment represented by the fractional flow reserve calculated based on the extravascular image is relatively complete, but the local accuracy is often weaker than that of the intraluminal image. Summary of the Invention

[0007] In view of the above-mentioned problems of the prior art, an object of the present invention is to provide a method, device, equipment, and medium for determining FFR based on multimodal medical images, which can improve the accuracy and stability of fractional flow reserve calculation.

[0008] In order to solve the above problem, the present invention provides: acquiring an intraluminal image including a vessel segment of interest; acquiring an external vessel image including a vessel segment under examination, the vessel segment under examination and the vessel segment of interest at least partially overlapping; obtaining a registration result by performing registration between the intravascular image and the external vascular image; and determining a target fractional flow reserve based on multimodal medical images based on the intravascular image and the extravascular image using the registration result.

[0009] Furthermore, obtaining a registration result by performing registration on the intravascular image and the extravascular image includes: obtaining first feature information in the intraluminal image of the vessel segment of interest, the first feature information including inner lumen information of the vessel segment of interest; acquiring second feature information in the external vascular image, the second feature information including external lumen information of the subject vascular segment; and performing registration based on the first feature information and the second feature information to obtain a registration result.

[0010] Furthermore, determining a target fractional flow reserve based on a multimodal medical image based on the intravascular image and the extravascular image using the registration result includes: determining a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image; determining a second pullback curve corresponding to the fractional flow reserve of the examined vessel segment based on the external vascular image; and determining a target fractional flow reserve based on the multi-modal medical image based on the first pullback curve and the second pullback curve according to the registration result.

[0011] Preferably, determining a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image includes: obtaining a blood flow velocity in the examined vessel segment; determining a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image and the blood flow velocity.

[0012] Preferably, determining a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image includes: obtaining first branch vessel information of the vessel segment of interest, the first branch vessel information including branch opening information obtained based on the vessel intraluminal image and branch information obtained based on the vessel external image; determining a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image and the first branch vessel information.

[0013] Preferably, determining the fractional flow reserve of the examined vessel segment and its corresponding second pullback curve based on the external vascular image includes: obtaining a blood flow velocity in the examined vessel segment; determining the fractional flow reserve of the examined vessel segment and its corresponding second pullback curve based on the external vessel image and the blood flow velocity.

[0014] Preferably, determining the fractional flow reserve of the examined vessel segment and its corresponding second pullback curve based on the external vascular image includes: acquiring second branch vessel information of the examined blood vessel segment, the second branch vessel information including branch opening information obtained based on the blood vessel intraluminal image and branch information obtained based on the blood vessel external image; determining the fractional flow reserve of the examined vessel segment and its corresponding second pullback curve based on the external vessel image and the second branch vessel information.

[0015] Furthermore, determining a target fractional flow reserve based on a multimodal medical image based on the first pullback curve and the second pullback curve using the registration result includes: determining a first array of fractional flow reserve values ​​corresponding to an array of first vascular positions of the vascular segment of interest in the intraluminal image based on the first pullback curve; determining a second array of fractional flow reserves corresponding to an array of second vascular positions of the examined vascular segment in the external vascular image based on the second pullback curve, wherein the array of second vascular positions and the array of first vascular positions at least partially overlap; fusing the sequence of the first fractional flow reserve and the sequence of the second fractional flow reserve based on the registration result to obtain a sequence of a target fractional flow reserve; determining a target fractional flow reserve based on the multi-modal medical image based on the array of target fractional flow reserves.

[0016] Furthermore, fusing the sequence of the first fractional flow reserve and the sequence of the second fractional flow reserve based on the registration result to obtain a sequence of a target fractional flow reserve, calculating an array of first difference values ​​based on the array of first fractional flow reserve values, and a value in the array of first difference values ​​is a reduction value relative to a fractional flow reserve value at a position preceding a corresponding position in the array of first fractional flow reserve values; calculating a second difference value array based on the second fractional flow reserve array, and a value in the second difference value array is a reduction value of the fractional flow reserve at a corresponding position in the second fractional flow reserve array relative to the fractional flow reserve at a previous position; Merging the first difference value array and the second difference value array according to the registration result to obtain a target difference value array; determining an array of the target fractional flow reserve values ​​based on the array of the target difference values.

[0017] Preferably, determining a target fractional flow reserve based on a multimodal medical image based on the intravascular image and the extravascular image using the registration result includes: obtaining first feature information of the vascular segment of interest in the vascular intraluminal image, the first feature information including inner lumen information of the vascular segment of interest; acquiring second feature information in the external vascular image, the second feature information including external lumen information of the subject vascular segment; Calculating a target fractional flow reserve based on the multimodal medical image based on the first feature information and the second feature information using the registration result.

[0018] Preferably, determining a target fractional flow reserve based on a multimodal medical image based on the intravascular image and the extravascular image using the registration result includes: performing image fusion between the intravascular image and the external vascular image based on the registration result to obtain a fusion image; obtaining fused feature information in the fused image, the fused feature information including fused lumen information of the vessel segment under test; Calculating a target fractional flow reserve based on the multimodal medical image based on the fusion feature information.

[0019] Another aspect of the present invention is an intraluminal image acquisition module for acquiring an intraluminal image including a vessel segment of interest; an extravascular image acquisition module for acquiring an extravascular image including a vessel segment under examination, wherein the vessel segment under examination and the vessel segment of interest at least partially overlap; a registration module for performing registration on the intravascular image and the extravascular image to obtain a registration result; and a fractional flow reserve determination module for determining a target fractional flow reserve based on multimodal medical images based on the intravascular image and the extravascular image using the registration result.

[0020] Another aspect of the present invention provides an electronic device including a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to realize the above-described method for determining an FFR based on multimodal medical images.

[0021] Another aspect of the present invention provides a computer-readable storage medium having stored thereon at least one instruction or at least one program, the at least one instruction or at least one program being loaded and executed by a processor to implement the above-described method for determining FFR based on multi-modal medical images.

[0022] According to the above technical means, the present invention has the following effects.

[0023] According to the method for determining FFR based on multi-modal medical images of the present invention, the intravascular image and the extravascular image are registered, and the calculation of fractional flow reserve is optimized by integrating the advantageous information of the intravascular image and the extravascular image according to the registration result, thereby obtaining a fractional flow reserve that combines completeness of the vascular segment based on the multi-modal medical images with local accuracy, thereby improving the accuracy and stability of the fractional flow reserve calculation. [Brief explanation of the drawings]

[0024] In order to more clearly explain the technical solutions of the present invention, the following briefly introduces the drawings that need to be used in the description of the embodiments or prior art. Obviously, the following drawings are only some embodiments of the present invention, and those skilled in the art can further obtain other drawings based on these drawings without expending inventive efforts.

[0025] [Figure 1] FIG. 1 is a diagram illustrating an implementation environment according to one embodiment of the present invention. [Figure 2] FIG. 2 is a flowchart of a method for determining FFR based on multimodal medical images according to one embodiment of the present invention. [Figure 3] FIG. 3 is a flowchart of a method for determining FFR based on multimodal medical images according to another embodiment of the present invention. [Figure 4] FIG. 4 is a diagram illustrating determining a target fractional flow reserve sequence according to one embodiment of the present invention. [Figure 5A] FIG. 5A is a diagram illustrating a first pullback curve according to an embodiment of the present invention. [Figure 5B] FIG. 5B is a diagram illustrating a second pullback curve according to an embodiment of the present invention. [Figure 5C] FIG. 5C is a diagram illustrating a target pullback curve according to one embodiment of the present invention. [Figure 6] FIG. 6 is a flowchart of a method for determining FFR based on multimodal medical images according to another embodiment of the present invention. [Figure 7] FIG. 7 is a flowchart of a method for determining FFR based on multimodal medical images according to another embodiment of the present invention. [Figure 8] FIG. 8 is a structural schematic diagram of an apparatus for determining FFR based on multi-modal medical images according to an embodiment of the present invention. [Figure 9] FIG. 9 is a structural schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0026] In order to allow those skilled in the art to better understand the technical solutions of the present invention, the technical solutions of the embodiments of the present invention will be described below clearly and fully with reference to the drawings of the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of the embodiments. Any other embodiments obtained by those skilled in the art based on the embodiments of the present invention without expending inventive efforts also fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc. in the present specification and claims, as well as in the drawings, are used to distinguish between similar objects and need not be used to describe a particular order or chronological order. Such terms, when used, are interchangeable where appropriate, and it should be understood that the embodiments of the present invention described herein may be practiced in orders other than those illustrated or described herein. Furthermore, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusions, such as processes, methods, apparatus, products, or devices of a series of steps or units, and need not be limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to those processes, methods, products, or devices. 1 of the specification, a diagram illustrating an implementation environment according to one embodiment of the present invention is shown. As shown in FIG. 1, the implementation environment may include at least one medical scanning device 110 and a computer device 120, and the computer device 120 and each medical scanning device 110 may be directly or indirectly connected via wired or wireless communication, although the embodiment of the present invention is not limited thereto.

[0028] Here, the computing device 120 may be, but is not limited to, various types of servers, personal computers, laptops, smartphones, tablet computers, and portable wearable devices. The server may be an independent server, a server group consisting of multiple servers, or a distributed system. It may also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0029] The medical scanning device 110 may use an imaging technique such as OCT imaging or IVUS imaging to obtain an intravascular image including a vascular segment of interest, or may use an imaging technique such as X-ray contrast imaging or CT imaging to obtain an extravascular image including a target vascular segment (where the target vascular segment and the target vascular segment of interest overlap at least partially).

[0030] The computing device 120 can acquire the intravascular image and the extravascular image captured by the medical scanning device 110 and determine a target fractional flow reserve based on the multi-modal medical image according to the method provided by the embodiment of the present invention, so that doctors can be promptly guided to investigate and take measures. By optimizing the calculation of the fractional flow reserve based on the multi-modal medical image, a target fractional flow reserve can be obtained that combines completeness of the vascular segment and local accuracy, and its accuracy and stability are both higher than those calculated based on a single medical image.

[0031] Specifically, the FFR determination method based on multimodal medical images provided by the embodiments of the present invention may be applied to a situation where fractional flow reserve is calculated based on external and endoluminal images of coronary arteries such as the left circumflex artery, the left anterior descending artery, and the right coronary artery.

[0032] It should be noted that Figure 1 is only an example, and those skilled in the art will appreciate that although only one medical scanning device 110 is shown in Figure 1, this is not intended to limit embodiments of the present invention and may include more or fewer medical scanning devices 110 than are shown.

[0033] Referring to Figure 2 of the specification, a flow chart of a method for determining FFR based on multi-modal medical images according to an embodiment of the present invention is shown, which may be implemented in the computer device 120 in Figure 1. Specifically, as shown in Figure 2, the method may include the following steps:

[0034] S210: An intraluminal image including a vessel segment of interest is acquired.

[0035] In an embodiment of the present invention, the vascular segment of interest may be a segment of a blood vessel that has an abnormality compared to a normal blood vessel, and the image of the vascular lumen may be obtained by directly acquiring an image including only the separated vascular segment of interest, or by selecting an image corresponding to the vascular segment of interest from the vascular lumen image of the blood vessel, but this embodiment is not limited thereto. If the imaging quality of some of the vascular lumen images is poor, only some of the vascular lumen images with good imaging quality may be selected for further processing, and the vascular segment in the some of the vascular lumen images with good imaging quality may be used as the vascular segment of interest.

[0036] In an embodiment of the present invention, the intravascular lumen image may be one type of intravascular lumen image or may include multiple types of intravascular lumen images, and the source of the intravascular lumen image may be directly imported related data, may be acquired through real-time connection from another resource library, or may be acquired by searching a stored image database based on information such as a user's name, but the embodiment of the present invention is not limited thereto. Specifically, the intravascular lumen image may be an OCT image, an IVUS image, etc.

[0037] S220: Acquire an external vessel image including a vessel segment under examination, the vessel segment under examination and the vessel segment of interest at least partially overlapping.

[0038] In an embodiment of the present invention, the external vascular image may be obtained by directly acquiring an image including only the separated vascular segment of the inspection target, or by selecting an image corresponding to the vascular segment of the inspection target from the external vascular image of the blood vessel, but the embodiment of the present invention is not limited thereto. If the imaging quality of some of the external vascular images is poor, only some external images with good imaging quality may be selected for further processing, and the vascular segment in the some external images with good imaging quality may be determined as the vascular segment of interest.

[0039] In an embodiment of the present invention, the extravascular image may be one type of extravascular image or may include multiple types of extravascular images, and the source of the extravascular image may be directly imported related data, may be obtained by connecting to another resource library in real time, or may be obtained by searching a stored image database based on information such as a user's name, but the embodiment of the present invention is not limited thereto. Specifically, the extravascular image may be an X-ray image, a CT image, etc.

[0040] In some embodiments of the present invention, the examined vessel segment may include the vessel segment of interest, for example, the entire vessel in which the vessel segment of interest is located, or the examined vessel segment may include only a portion of the vessel segment of interest, for example, only a portion of the proximal, middle, or distal end of the vessel segment of interest, although the present invention is not limited thereto.

[0041] In actual use, since the blood vessels displayed in the external vascular image are often complete, the vascular segment of interest generally corresponds to a partial vascular segment of the vascular segment under examination. If the vascular segment of interest exceeds the range of the vascular segment under examination, the vascular segment of interest can be cut according to actual conditions to obtain the fractional flow reserve based on the multi-modal medical image corresponding to the vascular segment under examination, or the vascular segment under examination can be extended by the vascular segment of interest to obtain the fractional flow reserve based on the multi-modal medical image corresponding to the extended vascular segment.

[0042] S230: Registration is performed on the intravascular image and the extravascular image to obtain a registration result.

[0043] In an embodiment of the present invention, registration may be performed based on characteristic information of the intravascular image and characteristic information of the extravascular image to obtain a correspondence relationship between the vascular segment of interest and the vascular segment to be inspected.

[0044] In an embodiment of the present invention, performing registration on the intravascular image and the extravascular image to obtain a registration result includes: obtaining first feature information in the intraluminal image of the vessel segment of interest, the first feature information including inner lumen information of the vessel segment of interest; acquiring second feature information in the external vascular image, the second feature information including external lumen information of the examined blood vessel segment; The method may include performing registration based on the first feature information and the second feature information to obtain a registration result.

[0045] Specifically, image processing may be performed on the vascular intraluminal image and the vascular extraluminal image, respectively, to obtain corresponding first feature information and second feature information. Here, the internal lumen information may include the vascular inner diameter and the vascular inner length at each location within the blood vessel. The vascular inner diameter refers to the diameter of the blood vessel obtained based on the vascular intraluminal image, and the vascular inner length is the length along the vascular axis from a certain location on the lumen within the blood vessel to the proximal end point of the blood vessel segment of interest. The external lumen information may include the vascular outer diameter and the vascular outer length at each location outside the blood vessel. The vascular outer diameter refers to the diameter of the blood vessel obtained based on the vascular extraluminal image, and the vascular outer length is the length along the vascular axis from a certain location on the extravascular lumen to the proximal end point of the blood vessel segment to be examined.

[0046] Preferably, the first feature information may further include branch orifice information, histological information, or vascular plaque information of the vessel segment of interest. The second feature information may further include branch information, stress information, or the like of the vessel segment to be inspected. Here, the branch orifice information may include an internal branch vessel number (the number including information on the number of the vessel branch to which the branch belongs) and position information of the internal branch vessel with respect to the vessel segment of interest. The branch information may include an external branch vessel number (the number including information on the number of the vessel branch to which the branch belongs) and position information of the external branch vessel with respect to the vessel segment to be inspected.

[0047] It should be noted that embodiments of the present invention may use various image processing methods in the prior art to perform image processing on the vascular intraluminal image and the vascular external image to obtain corresponding first feature information and second feature information. Different feature information may be obtained by different image processing methods, and embodiments of the present invention are not limited thereto. For example, various lumen segmentation methods in the prior art, such as lumen segmentation methods based on artificial intelligence, may be used to perform lumen segmentation on the vascular intraluminal image and the vascular external image to obtain corresponding external lumen information and internal lumen information, respectively. Various branch identification methods in the prior art (e.g., branch identification methods based on artificial intelligence, etc.) may be used to perform branch identification on the vascular intraluminal image and the vascular external image to obtain corresponding branch opening information and branch information, respectively.

[0048] Specifically, when performing registration, a primary registration may be performed on the first feature information and the second feature information to obtain third feature information, and then a secondary registration may be performed on the first feature information and the third feature information to obtain a registration result. Here, the third feature information may include external lumen information of a first target vascular segment corresponding to the vascular segment of interest in the vascular external image, and the registration result may be a correspondence relationship between the first feature information and the third feature information. Note that in this embodiment of the present invention, the vascular segment of interest is located inside the blood vessel, and the first target vascular segment refers to a vascular segment located outside the blood vessel corresponding to the vascular segment of interest.

[0049] In this embodiment, the order of the steps of acquiring the first characteristic information of the vessel segment of interest and acquiring the second characteristic information of the vessel segment to be examined can be interchangeable, and the steps may be performed simultaneously. The embodiment of the present invention does not limit the order of acquiring the first characteristic information of the vessel segment of interest and the second characteristic information of the vessel segment to be examined.

[0050] In some possible embodiments, the intravascular image and the extravascular image may be registered using other registration methods known in the art, although embodiments of the present invention are not limited thereto.

[0051] S240: According to the registration result, a target fractional flow reserve based on multimodal medical images is determined based on the intravascular image and the extravascular image.

[0052] In an embodiment of the present invention, the target fractional flow reserve may be a fractional flow reserve corresponding to the examined blood vessel segment, or may be a fractional flow reserve corresponding to an extended blood vessel segment obtained by extending the examined blood vessel segment using the blood vessel segment of interest. The target fractional flow reserve can represent the entire blood vessel segment, has relatively good local accuracy, and its accuracy and stability are both higher than those calculated from a single medical image, so that it can help doctors better evaluate the blood supply function of blood vessels and accurately determine the narrowed areas of blood vessels.

[0053] In an embodiment of the present invention, referring to FIG. 3 of the specification, determining a target fractional flow reserve based on multimodal medical images based on the intravascular image and the extravascular image according to the registration result can include the following steps:

[0054] S2411: Determine a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image.

[0055] Here, the first pullback curve is a relationship curve between the vascular position and the fractional flow reserve in the vascular segment of interest. In embodiments of the present invention, the fractional flow reserve may be calculated using various methods for determining the fractional flow reserve based on a vascular intraluminal image in the prior art to obtain the first pullback curve, but the embodiments of the present invention are not limited thereto. For example, the first pullback curve may be obtained by acquiring characteristic information, such as internal lumen information and branch orifice information, of the vascular segment of interest from the vascular intraluminal image, reconstructing a lumen model of the first blood vessel, and performing a fluid dynamics analysis based on a normal blood flow velocity to calculate the fractional flow reserve, where the normal blood flow velocity may be predetermined.

[0056] In one possible embodiment, determining a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image includes: obtaining a blood flow velocity in the examined vessel segment; determining a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image and the blood flow velocity.

[0057] Specifically, the blood flow velocity of the examined blood vessel segment may be calculated based on the external blood vessel image. The specific calculation method is conventional, and will not be further described in the present embodiment. For example, the blood flow velocity of the examined blood vessel segment may be measured using angiography. For example, the flow velocity of contrast agent in the examined blood vessel segment may be measured as the blood flow velocity of the examined blood vessel segment. Alternatively, the average blood flow velocity when the examined blood vessel segment is filled with contrast agent may be calculated based on the arrangement of the angiographic images of the examined blood vessel segment. In some possible embodiments, the blood flow velocity of the examined blood vessel segment may also be obtained using other conventional blood flow velocity calculation methods. The present embodiment is not limited thereto.

[0058] Specifically, after obtaining the blood flow velocity of the blood vessel segment to be examined, the calculation process for calculating the fractional flow reserve based on the vascular intraluminal image using the blood flow velocity is optimized, thereby enabling to obtain a more accurate fractional flow reserve and first pullback curve.

[0059] In another possible embodiment, determining a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image includes: obtaining first branch vessel information of the vessel segment of interest, the first branch vessel information including branch opening information obtained based on the vessel intraluminal image and branch information obtained based on the vessel external image; determining a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image and the first branch vessel information.

[0060] Specifically, various branch identification methods (e.g., artificial intelligence-based branch identification methods) used in the prior art may be used to perform branch identification on the intraluminal image to obtain branch opening information for the vascular segment of interest, and branch identification may be performed on the external vascular image to obtain branch information for the vascular segment of interest. Furthermore, the registration information may be used to determine branch information for the vascular segment of interest among the vascular segments of interest. After obtaining first branch vessel information for the vascular segment of interest, the calculation process for calculating fractional flow reserve based on the vascular intraluminal image using the first branch vessel information may be optimized to obtain more accurate fractional flow reserve and a first pullback curve. For example, the process for reconstructing a lumen model of the first blood vessel may be optimized using the first branch vessel information.

[0061] In another possible embodiment, a calculation process for calculating the fractional flow reserve based on the endoluminal image may be simultaneously optimized using the blood flow velocity of the examined vessel segment and first branch vessel information of the vessel segment of interest, thereby obtaining more accurate fractional flow reserve and a first pullback curve. For example, a process for reconstructing a lumen model of a first vessel may be optimized using the first branch vessel information, and a fluid dynamics analysis may be performed based on the blood flow velocity of the examined vessel segment to calculate the fractional flow reserve and obtain the first pullback curve.

[0062] S2412: Determine a second pullback curve corresponding to the fractional flow reserve of the vessel segment under test based on the external vessel image.

[0063] Here, the second pullback curve is a relationship curve between the vascular position and the fractional flow reserve in the examined vascular segment. In embodiments of the present invention, the fractional flow reserve may be calculated using various methods for determining the fractional flow reserve based on an external vascular image in the prior art to obtain the second pullback curve. However, the present invention is not limited thereto. For example, characteristic information, such as external lumen information and branch information, of the examined vascular segment may be obtained from the external vascular image, and a lumen model of the second blood vessel may be reconstructed. A fluid dynamics analysis may be performed based on a normal blood flow velocity to calculate the fractional flow reserve, thereby obtaining the second pullback curve. The normal blood flow velocity may be predetermined.

[0064] In one possible embodiment, determining a second pullback curve corresponding to the fractional flow reserve of the examined vessel segment based on the external vessel image includes: obtaining a blood flow velocity in the examined vessel segment; and determining a fractional flow reserve of the examined vessel segment and a corresponding second pullback curve based on the external vessel image and the blood flow velocity.

[0065] Specifically, the method for determining the blood flow velocity of the examined blood vessel segment is similar to step S2411, and the embodiment of the present invention will not be described further here. After obtaining the blood flow velocity of the examined blood vessel segment, the calculation process for calculating the fractional flow reserve based on the blood flow velocity and the external vascular image can be optimized to obtain more accurate fractional flow reserve and second pullback curve.

[0066] In another possible embodiment, determining a second pullback curve corresponding to the fractional flow reserve of the examined vessel segment based on the external vascular image includes: acquiring second branch vessel information of the examined blood vessel segment, the second branch vessel information including branch opening information obtained based on the blood vessel intraluminal image and branch information obtained based on the blood vessel external image; and determining a fractional flow reserve of the target vessel segment and a corresponding second pullback curve based on the external vessel image and the second branch vessel information.

[0067] Specifically, branch identification may be performed on the external vascular image using various branch identification methods (e.g., artificial intelligence-based branch identification methods) in the prior art to obtain branch information for the target vascular segment, and branch identification may be performed on the internal vascular image to obtain branch orifice information for the target vascular segment. Furthermore, the branch orifice information of the target vascular segment among the target vascular segments may be determined as the branch orifice information for the target vascular segment using the registration information. After obtaining second branch vessel information for the target vascular segment, a calculation process for calculating fractional flow reserve based on the external vascular image using the second branch vessel information may be optimized to obtain a more accurate fractional flow reserve and second pullback curve. For example, the process for reconstructing a second vascular lumen model using the second branch vessel information may be optimized.

[0068] In another possible embodiment, a calculation process for calculating the fractional flow reserve based on the vascular external image using the blood flow velocity of the examined vascular segment and information on a second branch vessel of the examined vascular segment may be simultaneously optimized to obtain a more accurate fractional flow reserve and a second pullback curve. For example, a process for reconstructing a second vascular lumen model using information on the second branch vessel may be optimized to perform a fluid dynamics analysis based on the blood flow velocity of the examined vascular segment, thereby calculating the fractional flow reserve and obtaining the second pullback curve.

[0069] S2413: According to the registration result, a target fractional flow reserve based on the multimodal medical image is determined based on the first pullback curve and the second pullback curve.

[0070] Since the fractional flow reserve calculated based on the intraluminal image has good local accuracy and the fractional flow reserve calculated based on the extraluminal image can represent a complete vascular segment, it is possible to obtain a target fractional flow reserve that combines completeness of the vascular segment with local accuracy by fusing the fractional flow reserve calculated based on the intraluminal image and the fractional flow reserve calculated based on the extraluminal image.

[0071] In an embodiment of the present invention, determining a target fractional flow reserve based on a multi-modal medical image based on the first pullback curve and the second pullback curve according to the registration result includes: determining a first array of fractional flow reserve values ​​corresponding to an array of first vascular positions of the vascular segment of interest in the intraluminal image based on the first pullback curve; determining a second array of fractional flow reserves corresponding to an array of second vascular positions of the examined vascular segment in the external vascular image based on the second pullback curve, wherein the second array of vascular positions and the first array of vascular positions at least partially overlap; merging the sequence of the first fractional flow reserve with the sequence of the second fractional flow reserve based on the registration result to obtain a sequence of a target fractional flow reserve; and determining a target fractional flow reserve based on the multi-modal medical image based on the array of target fractional flow reserves.

[0072] In actual use, the external vascular image may be uniformly sampled from the proximal end of the target vascular segment toward the external lumen of the target vascular segment to obtain a second array of vascular positions of the target vascular segment, and the fractional flow reserve of the target vascular segment corresponding to each vascular position in the second array of vascular positions may be determined based on the second pullback curve to obtain the second array of fractional flow reserves. Then, a subarray of vascular positions in a first target vascular segment corresponding to the target vascular segment of interest is determined from the second array of vascular positions, and the subarray of vascular positions is treated as a subarray of the first array of vascular positions. A portion of the target vascular segment of interest beyond the target vascular segment of interest is uniformly sampled at the same sampling interval to obtain the first array of vascular positions. Furthermore, the fractional flow reserve of the target vascular segment of interest corresponding to each vascular position in the first array of vascular positions is determined based on the first pullback curve using the registration result to obtain the first array of fractional flow reserves.

[0073] In the sampling process, in one preferred embodiment, the proximal end point of the examined vessel segment is the first sampling position, the distal end point of the examined vessel segment is the last sampling position, and the proximal and distal end points of the vessel segment of interest are also included in the array of second vessel positions. However, the above preferred embodiment is not limited to the sampling positions. In actual use, the array of second vessel positions may include one or more of the proximal and distal end points of the examined vessel segment and the proximal and distal end points of the vessel segment of interest, or may not include any one of them. The embodiments of the present invention are not limited thereto.

[0074] Specifically, fusing the sequence of the first fractional flow reserve and the sequence of the second fractional flow reserve based on the registration result to obtain a sequence of a target fractional flow reserve is performed by: calculating an array of first difference values ​​based on the array of first fractional flow reserve values, and a value in the array of first difference values ​​is a reduction value of the fractional flow reserve value at a corresponding position in the array of first fractional flow reserve values ​​relative to the fractional flow reserve value at an immediately preceding position; calculating an array of second difference values ​​based on the array of second fractional flow reserve values, and a value in the array of second difference values ​​is a reduction value of the fractional flow reserve value at a corresponding position in the array of second fractional flow reserve values ​​relative to the fractional flow reserve value at a position immediately before the corresponding position; According to the registration result, performing merging of the first difference value array and the second difference value array to obtain a target difference value array; determining an array of the target fractional flow reserve values ​​based on the array of the target difference values.

[0075] In actual use, the vessel segment to be inspected and the vessel segment of interest will at least partially overlap, so in actual use, there may be several cases as follows:

[0076] In the first case, the vessel segment of interest is a part of the vessel segment to be inspected, and in this case, fusing the first difference value array and the second difference value array based on the registration result to obtain a target difference value array may include determining a target sub-array in the second difference value array corresponding to the first difference value array based on the registration result, and replacing the target sub-array in the second difference value array with the first difference value array to obtain the target difference value array.

[0077] For example, referring to FIG. 4 of the specification, assuming that the sequence of first fractional flow reserve values ​​determined based on the first pullback curve is {1, 0.99, 0.98, 0.97} and the sequence of second fractional flow reserve values ​​determined based on the second pullback curve is {1, 0.98, 0.96, 0.94, 0.92, 0.90, 0.88, 0.86, 0.84, 0.82, 0.80}, in the first step, by calculation, it can be obtained that the sequence of first difference values ​​is {0, 0.01, 0.01, 0.01} and the sequence of second difference values ​​is {0, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02}.

[0078] In the second step, based on the registration result, it can be determined that the target sub-array of the second difference value array corresponding to the first difference value array is the sub-array consisting of the third array value to the sixth array value, {0.02, 0.02, 0.02, 0.02}. Then, the target sub-array can be replaced with the first difference value array to obtain the target difference value array {0, 0.02, 0, 0.01, 0.01, 0.01, 0.02, 0.02, 0.02, 0.02, 0.02}.

[0079] In a second case, the vascular segment to be inspected includes only a portion of the vascular segment at the proximal or distal end of the vascular segment of interest, and in this case, fusing the first difference value array and the second difference value array based on the registration result to obtain the target difference value array may include determining a first sub-array from the first difference value array corresponding to the second difference value array and a second sub-array from the second difference value array corresponding to the first difference value array based on the registration result, and replacing the second sub-array from the second difference value array with the first sub-array to obtain the target difference value array.

[0080] Preferably, after replacing the second subarray of the second difference value array with the first subarray, a difference value array other than the first subarray of the first difference value array may be supplemented to the difference value array obtained by the replacement, thereby finally obtaining the target difference value array.

[0081] For example, the first difference value array is calculated as {0, 0.01, 0.01, 0.01}, the second difference value array is calculated as {0, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02}, and the first subarray corresponding to the second difference value array, among the first difference value array determined by the registration result, is a subarray {0.01, 0.02, 0.02} consisting of the third array value and the fourth array value. .01}, and the second subarray of the second difference value array corresponding to the first difference value array is a subarray {0, 0.02} consisting of the first array value to the second array value, then the second subarray of the second difference value array may be replaced with the first subarray to obtain a target difference value array {0.01, 0.01, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02}.

[0082] Preferably, the array of difference values ​​other than the first subarray {0, 0.01} from the first array of difference values ​​may be further supplemented to the array of difference values ​​obtained by replacement, to finally obtain the array of target difference values ​​{0, 0.01, 0.01, 0.01, 0.01, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02}.

[0083] In a third case, the vascular segment to be inspected is a part of the vascular segment of interest, and in this case, fusing the first difference value array and the second difference value array based on the registration result to obtain a target difference value array may include determining a target sub-array from the first difference value array corresponding to the second difference value array based on the registration result, and replacing the target sub-array from the first difference value array with the second difference value array to obtain the target difference value array.

[0084] In a fourth case, the vascular segment to be inspected is the same vascular segment as the vascular segment of interest, and in this case, fusing the first difference value array and the second difference value array based on the registration result to obtain a target difference value array may include calculating an average or weighted average value for two difference values ​​that correspond in positions in the first difference value array and the second difference value array to obtain a target difference value corresponding to that position, and finally obtaining the target difference value array.

[0085] For example, assuming that the calculated array of first difference values ​​is {0, 0.01, 0.01, 0.01} and the array of second difference values ​​is {0, 0.02, 0.02, 0.02}, the average of two difference values ​​that correspond in position in the first difference value array and the second difference value array may be calculated to obtain the target difference value array {0, 0.015, 0.015, 0.015}.

[0086] In some possible embodiments, in the first to third cases, the target difference value corresponding to each position may be obtained by calculating an average value or a weighted average value for the portion where the positions in the first difference value array and the second difference value array correspond to each other, but the embodiments of the present invention are not limited thereto.

[0087] In actual use, determining the array of target fractional flow reserve values ​​based on the array of target difference values ​​may include subtracting a sum of array values ​​before (including) the current position in the array of target difference values ​​from the fractional flow reserve value at a first position in the array of second fractional flow reserve values ​​to obtain the fractional flow reserve value corresponding to the current position, and finally obtaining the array of target fractional flow reserve values.

[0088] For example, if the array of target difference values ​​is {0, 0.02, 0, 0.01, 0.01, 0.01, 0.02, 0.02, 0.02, 0.02, 0.02}, the fractional flow reserve at the first position is 1-0=1, the fractional flow reserve at the second position is 1-0-0.02=0.98, the fractional flow reserve at the third position is 1-0-0.02-0=0.98, the fractional flow reserve at the fourth position is 1-0-0.02-0-0.01=0.97, and the rest can be inferred from this, and finally, the array of target fractional flow reserve values ​​can be obtained as {1, 0.98, 0.98, 0.97, 0.96, 0.95, 0.93, 0.91, 0.89, 0.87, 0.85}.

[0089] Specifically, determining a target fractional flow reserve based on a multimodal medical image based on the array of target fractional flow reserves includes: performing curve fitting using the array of target fractional flow reserves to obtain a target pullback curve based on the multimodal medical image, the target pullback curve being a relationship curve between the vascular position and the fractional flow reserve in the second target vascular segment; The method may further include setting the target fractional flow reserve to a value corresponding to a distal end point of the second target blood vessel segment on the target pullback curve.

[0090] Here, the second target vessel segment is related to the target fractional flow reserve array. For example, if the vessel segment of interest is a part of the vessel segment under test, the second target vessel segment is the vessel segment under test. If the vessel segment under test is a vessel segment including only a part of the proximal or distal end of the vessel segment of interest, if data beyond the range of the vessel segment of interest is discarded (i.e., when calculating the target fractional flow reserve array, the difference value array other than the first subarray of the first difference value array is not added to the resulting difference value array), the second target vessel segment is the vessel segment under test. If data beyond the range of the vessel segment of interest is added (i.e., when calculating the target fractional flow reserve array, the difference value array other than the first subarray of the first difference value array is added to the resulting difference value array), the second target vessel segment is the vessel segment obtained by expanding the vessel segment under test using the vessel segment of interest. When the inspection target vascular segment is a part of the vascular segment of interest, the second target vascular segment is the vascular segment of interest. When the inspection target vascular segment and the vascular segment of interest are the same vascular segment, the second target vascular segment is the inspection target vascular segment.

[0091] In actual use, when performing curve fitting, if the target fractional flow reserve array does not include the fractional flow reserve corresponding to the proximal end point of the second target vascular segment (which is 1), it can be first added to the target fractional flow reserve array to ensure that the fractional flow reserve corresponding to the proximal end point of the second target vascular segment is 1 throughout, and then curve fitting can be performed.

[0092] In actual use, when sampling vascular positions, if the distal end point of the vascular segment to be inspected is the last vascular position in the sequence of second vascular positions and the distal end point of the vascular segment of interest is the last vascular position in the sequence of first vascular positions, then the fractional flow reserve corresponding to the distal end point of the vascular segment to be inspected or the distal end point of the vascular segment of interest in the sequence of target fractional flow reserves can be directly used as the target fractional flow reserve based on the multi-modal medical image.

[0093] For example, assuming that a first pullback curve of a vessel segment of interest determined based on an intravascular image is as shown in FIG. 5A and a second pullback curve of a vessel segment of interest determined based on an extravascular image is as shown in FIG. 5B, a sequence of first fractional flow reserves determined based on the first pullback curve is {0.99, 0.98, 0.97, 0.965, 0.96, 0.955, 0.95, 0.93, 0.91, 0.89, 0.87, 0.85}, and a sequence of second fractional flow reserves determined based on the second pullback curve is {0.98, 0.96, 0.94, 0.92, 0.9, 0.86, 0.82, 0.78, 0.77, 0.76}. ,0.75,0.74,0.73,0.71,0.69,0.67,0.65,0.63,0.61,0.59}. Using the above method, a target fractional flow reserve sequence {0.99,0.98,0.97,0.965,0.96,0.955,0.95,0.93,0.91,0.89,0.87,0.85,0.84,0.82,0.8,0.78,0.76,0.74,0.72,0.7} can be obtained. The final target pullback curve based on the multi-modal medical image obtained by fitting is shown in Figure 5C. This target pullback curve can not only represent the complete blood vessel segment, but also has relatively high local accuracy.

[0094] Here, the most important factor is the fractional flow reserve corresponding to the last point on the target pullback curve based on the multimodal medical image (i.e., the distal end point of the second target vascular segment). This is the criterion for evaluating the blood supply status of the entire blood vessel and the coronary artery. If the fractional flow reserve is greater than 0.8, it indicates sufficient blood flow to the myocardium; otherwise, it indicates insufficient blood flow to the myocardium. As shown in Figure 5C, the target fractional flow reserve is 0.7, indicating insufficient blood flow to the myocardium.

[0095] In this embodiment of the present invention, a first pullback curve determined based on an intravascular image and a second pullback curve determined based on an external vascular image are combined to obtain a target pullback curve and target fractional flow reserve based on multi-modal medical images. This not only allows for complete representation of the vascular segment, but also has relatively high local accuracy, and its accuracy and stability are higher than those of fractional flow reserve calculated based on a single medical image, allowing for more accurate assessment of myocardial ischemia and determination of vascular stenosis.

[0096] In one possible embodiment, referring to FIG. 6 of the specification, determining a target fractional flow reserve based on a multimodal medical image based on the intravascular image and the extravascular image according to the registration result includes: S2421: acquiring first feature information including inner lumen information of the blood vessel segment of interest in the blood vessel intraluminal image; S2422: acquiring second feature information including external lumen information of the test vessel segment in the blood vessel external image; S2423: Calculating a target fractional flow reserve based on the multimodal medical image based on the first feature information and the second feature information using the registration result.

[0097] Specifically, the first feature information may further include branch opening information, histological information, vascular plaque information, etc. of the vessel segment of interest, and the second feature information may further include branch information, stress information, etc. The method of obtaining the first feature information and the second feature information is similar to S230, and the embodiment of the present invention will not be further described here.

[0098] Preferably, a first vascular lumen model is reconstructed based on the first feature information, a second vascular lumen model is reconstructed based on the second feature information, and then the first vascular lumen model and the second vascular lumen model are merged according to the registration result to obtain a target lumen model, and a fluid dynamics analysis is performed based on the blood flow velocity of the examined vascular segment to calculate a fractional flow reserve, and a target pullback curve and a target fractional flow reserve are obtained based on the corresponding multi-modal medical image. Here, the method for determining the blood flow velocity of the examined vascular segment is similar to step S2411, and the embodiment of the present invention will not be further described here.

[0099] Preferably, a third vascular lumen model is reconstructed based on the first feature information and the second feature information according to the registration result, and a fluid dynamics analysis is performed based on the blood flow velocity of the examined vascular segment to calculate a fractional flow reserve, and a target pullback curve and a target fractional flow reserve are obtained based on the corresponding multi-modal medical image. Here, the method for determining the blood flow velocity of the examined vascular segment is similar to S2411, and the embodiment of the present invention will not be further described here.

[0100] In another possible embodiment, referring to FIG. 7 of the specification, determining a target fractional flow reserve based on a multimodal medical image based on the intravascular image and the extravascular image according to the registration result includes: S2431: Performing image fusion between the intravascular image and the external vascular image based on the registration result to obtain a fusion image; S2432: Obtaining fusion feature information including fusion lumen information of the vessel segment of the test subject in the fusion image; S2433: Calculating a target fractional flow reserve based on the multi-modal medical image based on the fusion feature information.

[0101] Specifically, the fused lumen information may include a blood vessel diameter and a blood vessel length at each point of the blood vessel, where the blood vessel diameter refers to the blood vessel diameter obtained based on the fused image, and the blood vessel length refers to the length along the blood vessel axis from a certain point on the blood vessel to the proximal end point of the blood vessel in the fused image.

[0102] Preferably, the fusion feature information may further include fusion branch information, histological information, vascular plaque information, etc. The method of obtaining the fusion feature information is similar to step S230, and the embodiment of the present invention will not be further described here.

[0103] Specifically, a fourth vascular lumen model may be reconstructed based on the fused feature information, and a fluid dynamics analysis may be performed based on the blood flow velocity of the examined vascular segment to calculate the fractional flow reserve, and a target pullback curve and a target fractional flow reserve may be obtained based on the corresponding multi-modal medical image. Here, the method for determining the blood flow velocity of the examined vascular segment is similar to step S2411, and the embodiment of the present invention will not be described further here.

[0104] As described above, the method for determining FFR based on multi-modal medical images according to the embodiment of the present invention performs registration on the intravascular image and the extravascular image. The registration results are used to integrate the advantageous information of the intravascular image and the extravascular image, thereby optimizing the calculation of fractional flow reserve. This results in a fractional flow reserve that combines completeness of the vascular segment based on multi-modal medical images with local accuracy, thereby improving the accuracy and stability of the fractional flow reserve calculation.

[0105] Furthermore, by obtaining a single fractional flow reserve value through fusion calculation based on multiple medical images, the problem of selection and unification that occurs when different fractional flow reserve values ​​are calculated for the same blood vessel based on different medical images can be further resolved. The multi-modal medical image-based FFR determination method of the present invention selects various medical images and utilizes the advantageous information expressed by blood vessels to calculate the fractional flow reserve value, and the accuracy and stability of the calculated fractional flow reserve value are both higher than those calculated based on a single medical image.

[0106] Please refer to Figure 8 of the specification, which shows the structure of an FFR determination device 800 based on multi-modal medical images according to one embodiment of the present invention. As shown in Figure 8, the device 800 includes: an intraluminal image acquisition module 810 for acquiring an intraluminal image including a vessel segment of interest; an extravascular image acquisition module 820 for acquiring an extravascular image including a vessel segment under examination, wherein the vessel segment under examination and the vessel segment of interest at least partially overlap; a registration module 830 for performing registration between the intravascular image and the extravascular image to obtain a registration result; The method may further include a fractional flow reserve determination module 840 for determining a target fractional flow reserve based on multi-modal medical images based on the intravascular image and the extravascular image using the registration result.

[0107] It should be noted that the device according to the above embodiments is described by only using the division of each of the above functional modules as an example to realize its functions. In actual use, the above functions can be completed by allocating them to different functional modules as needed, that is, by dividing the internal structure of the device into different functional modules, all or part of the above functions can be achieved. Furthermore, the device provided by the above embodiments belongs to the same concept as the corresponding method embodiments, and the specific implementation details thereof can be referred to the corresponding method embodiments, and will not be further described here.

[0108] An embodiment of the present invention further provides an electronic device, the electronic device comprising a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, the at least one instruction or the at least one program being loaded and executed by the processor, thereby realizing the method for determining FFR based on multi-modal medical images according to the method embodiment as described above.

[0109] The memory can be used to store software programs and modules, and the processor executes the software programs and modules stored in the memory to perform various functional applications and data processing. The memory can mainly include a storage program area capable of storing an operating system, application programs required for functions, etc., and a storage data area capable of storing data created in accordance with the use of the device. The memory can also include high-speed random access memory, and can further include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Correspondingly, the memory can further include a memory controller to provide access to the memory by the processor.

[0110] In a specific embodiment, FIG. 9 illustrates a hardware structural diagram of an electronic device for implementing a method for determining an FFR based on multimodal medical images according to an embodiment of the present invention. The electronic device may be a computer terminal, a mobile terminal, or a device thereof, and the electronic device may constitute or include an apparatus for determining an FFR based on multimodal medical images according to an embodiment of the present invention. As illustrated in FIG. 9 , the electronic device 900 may include components such as one or more computer-readable storage media memory 910, one or more processing cores processor 920, an input unit 930, a display unit 940, a radio frequency (RF) circuit 950, a wireless fidelity (WiFi) module 960, and a power supply 970. Those skilled in the art will appreciate that the configuration of the electronic device illustrated in FIG. 9 does not constitute a limitation on the electronic device 900, and that the electronic device may include more or fewer components than those illustrated, may combine certain components, or may have different component arrangements.

[0111] The memory 910 may be configured to store software programs and modules. The processor 920 executes the software programs and modules stored in the memory 910 and accesses data stored in the memory 910 to execute various functional applications and data processing. The memory 910 may primarily include a program storage area capable of storing an operating system, an application program required for at least one function, and a data storage area capable of storing data generated in accordance with the use of the electronic device. The memory 910 may also include a high-speed random access memory, or may further include nonvolatile memory such as a hard disk, memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 910 may further include a memory controller to provide access to the memory 910 by the processor 920.

[0112] The processor 920 is the control center of the electronic device 900, connecting each part of the entire electronic device via various interfaces and lines, and performing various functions and data processing of the electronic device 900 by operating or executing software programs and / or modules stored in the memory 910 and calling up data stored in the memory 910, thereby supervising the entire electronic device 900. The processor 920 may be a central processing unit, or may be another general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or the like. The general-purpose processor may be a microprocessor, or any conventional processor, or the like.

[0113] Input unit 930 may be configured to receive input numeric or character information and generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. Specifically, input unit 930 may include a touch-sensitive surface 931 and other input devices 932. Specifically, touch-sensitive surface 931 may include, but is not limited to, a touchpad or touch panel, and other input devices 932 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control buttons, switch buttons, etc.), a trackball, a mouse, a joystick, etc.

[0114] The display unit 940 may be used to display information input by a user, information provided to a user, and various graphical user interfaces of the electronic device, which may be composed of figures, text, icons, videos, or any combination thereof. The display unit 940 may include a display panel 941, preferably in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc.

[0115] The RF circuitry 950 may be used to receive and transmit signals during message transmission or phone calls, particularly to receive downlink messages from a base station, which are then processed by one or more processors 920, and transmit uplink data to the base station. Typically, the RF circuitry 950 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a subscriber identity module (SIM) card, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc. The RF circuitry 950 may also communicate with a network or other devices via wireless communication. The wireless communication may use any one of the communication standards or protocols, including, but not limited to, Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0116] WiFi is a short-range wireless transmission technology, and electronic device 900 can provide users with wireless broadband Internet access by enabling them to send and receive emails, browse web pages, and access streaming media via WiFi module 960. While FIG. 9 shows WiFi module 960, it is not a required component of electronic device 900, and it may be omitted as needed without changing the essence of the invention.

[0117] The electronic device 900 further includes a power supply 970 (e.g., a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the processor 920 via a power management system, which may realize functions such as charge / discharge management and power consumption management. The power supply 970 may further include optional components such as one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0118] Although not shown, the electronic device 900 may include a Bluetooth module or the like, but this will not be discussed further here.

[0119] An embodiment of the present invention further provides a computer-readable storage medium, which may be installed in an electronic device for storing at least one instruction or at least one program relating to a method for determining FFR based on multi-modal medical images, the at least one instruction or the at least one program being loaded and executed by the processor to realize the method for determining FFR based on multi-modal medical images provided in the above method embodiment.

[0120] Preferably, in an embodiment of the present invention, the above-mentioned storage medium may include, but is not limited to, various media capable of storing program code, such as a U disk, a read-only memory (ROM), a random access memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.

[0121] An embodiment of the present invention further provides a computer program product or a computer program, the computer program product or the computer program including computer instructions stored in a computer-readable storage medium, wherein a processor of a computing device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, thereby causing the computing device to perform the method for determining FFR based on multi-modal medical images provided in the various preferred embodiments above.

[0122] The order of the above-described embodiments of the present invention is for illustrative purposes only and does not represent the merits or demerits of the embodiments. The above describes specific embodiments of the present invention. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than the examples and still achieve desirable results. Also, processes depicted in the figures do not necessarily achieve desirable results in the particular order or sequential order shown. In some embodiments, multitasking and parallel processing may also be performed or may be advantageous.

[0123] Each embodiment in this specification is described in a stepwise manner, and the same or similar parts may be referred to in each embodiment, and each embodiment will be described focusing on the differences from other embodiments. In particular, the device embodiments are basically similar to the method embodiments, so they will be briefly described, and for related parts, please refer to the description of the method embodiments.

[0124] Those skilled in the art can understand that all or part of the steps in the above embodiments may be implemented in hardware, or may be instructed to be implemented in relevant hardware by a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disk, etc.

[0125] The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for determining FFR based on multimodal medical images, the method being performed by a device for determining FFR based on multimodal medical images, the device including a vascular intraluminal image acquisition module, a vascular extraluminal image acquisition module, a registration module, and a fractional flow reserve determination module, the method comprising: acquiring, by the intraluminal image acquisition module, an intraluminal image including a vessel segment of interest; acquiring, by the external vessel image acquisition module, an external vessel image including a vessel segment under examination, wherein the vessel segment under examination and the vessel segment of interest at least partially overlap; obtaining a registration result by performing registration on the intravascular image and the external vascular image by the registration module; determining, by the fractional flow reserve determination module, a target fractional flow reserve based on multimodal medical images based on the intravascular image and the extravascular image according to the registration result; determining the target fractional flow reserve includes: determining, by the fractional flow reserve determination module, a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image; determining, by the fractional flow reserve determination module, a second pullback curve corresponding to the fractional flow reserve of the examined vessel segment based on the external vascular image; and determining the target fractional flow reserve based on the first pullback curve and the second pullback curve by the fractional flow reserve determination module.

2. Obtaining the registration result by performing the registration includes: obtaining, by the registration module, first feature information in the vascular intraluminal image, the first feature information including interior lumen information of the vascular segment of interest; obtaining second feature information in the external vascular image by the registration module, the second feature information including external lumen information of the examined vascular segment; The method of claim 1 , further comprising: performing, by the registration module, the registration based on the first feature information and the second feature information to obtain the registration result.

3. Determining the first pullback curve comprises: obtaining a blood flow velocity of the examined vessel segment by the fractional flow reserve determination module; The method of claim 1 , further comprising: determining, by the fractional flow reserve determination module, the first pullback curve based on the intravascular image and the blood flow velocity.

4. Determining the first pullback curve comprises: The fractional flow reserve determination module obtains first branch vessel information of the vessel segment of interest, the first branch vessel information including branch opening information obtained based on the vessel intraluminal image and branch information obtained based on the vessel extraluminal image; and determining, by the fractional flow reserve determination module, the first pullback curve based on the intraluminal image and the first branch vessel information.

5. Determining the second pullback curve comprises: obtaining a blood flow velocity of the examined vessel segment by the fractional flow reserve determination module; The method of claim 1 , further comprising: determining, by the fractional flow reserve determining module, the second pullback curve based on the extravascular image and the blood flow velocity.

6. Determining the second pullback curve comprises: obtaining second branch vessel information of the test vessel segment by the fractional flow reserve determination module, the second branch vessel information including branch opening information obtained based on the vascular intraluminal image and branch information obtained based on the vascular extraluminal image; and determining, by the fractional flow reserve determination module, the second pullback curve based on the extravascular image and the second branch vessel information.

7. determining the target fractional flow reserve includes: determining, by the fractional flow reserve determination module, a sequence of first fractional flow reserve values ​​corresponding to a sequence of first vascular positions of the vascular segment of interest in the intraluminal image based on the first pullback curve; determining, by the fractional flow reserve determination module, a second fractional flow reserve sequence corresponding to a second vascular position sequence of the examined vascular segment in the external vascular image based on the second pullback curve, wherein the second vascular position sequence and the first vascular position sequence at least partially overlap; the fractional flow reserve determination module combines the first fractional flow reserve sequence and the second fractional flow reserve sequence according to the registration result to obtain a target fractional flow reserve sequence; The method of claim 1 , further comprising: determining, by the fractional flow reserve determination module, the target fractional flow reserve based on an array of target fractional flow reserves.

8. obtaining the target fractional flow reserve sequence, the fractional flow reserve determination module calculates a first difference value array based on the first fractional flow reserve array, and a value in the first difference value array is a reduction value of the fractional flow reserve at a corresponding position in the first fractional flow reserve array relative to the fractional flow reserve at a position immediately before the corresponding position; calculating, by the fractional flow reserve determination module, a second difference value array based on the second fractional flow reserve array, and a value in the second difference value array is a reduction value of the fractional flow reserve at a corresponding position in the second fractional flow reserve array relative to the fractional flow reserve at a position immediately before the corresponding position; The fractional flow reserve determining module combines the first difference value sequence and the second difference value sequence according to the registration result to obtain a target difference value sequence; The method of claim 7 , further comprising: determining, by the fractional flow reserve determination module, the array of target fractional flow reserve values ​​based on the array of target difference values.

9. determining the target fractional flow reserve includes: acquiring, by the fractional flow reserve determination module, first feature information in the intraluminal image, the first feature information including inner lumen information of the vascular segment of interest; obtaining second feature information in the external vascular image by the fractional flow reserve determination module, the second feature information including external lumen information of the examined vascular segment; 2. The method of claim 1, further comprising: calculating, by the fractional flow reserve determination module, the target fractional flow reserve based on the first characteristic information and the second characteristic information.

10. determining the target fractional flow reserve includes: the fractional flow reserve determination module performs image fusion between the intravascular image and the extravascular image based on the registration result to obtain a fusion image; obtaining fusion feature information, including fusion lumen information of the examined vessel segment in the fusion image, by the fractional flow reserve determination module; The method of claim 1 , further comprising: calculating, by the fractional flow reserve determination module, the target fractional flow reserve based on the fused feature information.

11. 1. An apparatus for determining FFR based on multimodal medical images, comprising: an intraluminal image acquisition module for acquiring an intraluminal image including a vessel segment of interest; an extravascular image acquisition module for acquiring an extravascular image including a vessel segment under examination, wherein the vessel segment under examination and the vessel segment of interest at least partially overlap; a registration module for performing registration on the intravascular image and the external vascular image to obtain a registration result; a fractional flow reserve determination module for determining a target fractional flow reserve based on a multimodal medical image based on the intravascular image and the extravascular image according to the registration result; determining the target fractional flow reserve includes: determining a first pullback curve corresponding to the fractional flow reserve of the vessel segment of interest based on the intraluminal image; determining a second pullback curve corresponding to the fractional flow reserve of the examined vessel segment based on the external vascular image; determining the target fractional flow reserve based on the first pullback curve and the second pullback curve.

12. 11. An electronic device comprising a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and wherein the at least one instruction or the at least one program is loaded and executed by the processor to realize the method for determining FFR based on multimodal medical images according to any one of claims 1 to 10.

13. 11. A computer-readable storage medium having stored thereon at least one instruction or at least one program, the at least one instruction or at least one program being loaded and executed by a processor to implement the method for determining FFR based on multimodal medical images according to any one of claims 1 to 10.

Images