Registration method and device of extravascular image and intravascular image, storage medium and electronic equipment

Abstract

The invention discloses an extravascular image and intravascular image registration method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring a first lumen feature point set of an intravascular image corresponding to a target blood vessel segment, and acquiring a second lumen feature point set of an extravascular image corresponding to the target blood vessel segment; determining a first feature sequence corresponding to the first lumen feature point set; determining the shortened blood vessel length of the target blood vessel section in the extravascular image; determining a plurality of first local feature point sets in the second lumen feature point set based on the length of the shortened blood vessel, and determining second feature sequences respectively corresponding to the plurality of first local feature point sets; and performing blood vessel registration on the intravascular image and the extravascular image based on the second feature sequence and the first feature sequence corresponding to the plurality of first local feature point sets to obtain a registration result. According to the invention, the blood vessel registration under the shortening condition is realized, the blood vessel registration precision is improved, the collection quality requirement on the blood vessel image is reduced, and the collection requirement on the blood vessel image is reduced.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a registration method, device, storage medium and electronic equipment for extravascular image and intravascular image. Background Art

[0002] With the rapid development of medical imaging technology, evaluating the degree of coronary artery stenosis and plaque stability through medical imaging analysis and guiding percutaneous coronary intervention surgery are very critical links in clinical treatment.

[0003] Coronary angiography (CAG) is currently the most commonly used extraluminal imaging mode. It uses contrast agents and X-rays to image the coronary arteries. It can present the overall anatomical structure of the coronary arteries and assist in determining the exact location and extent of the lesions. However, it can only perform a two-dimensional assessment of the lumen size, cannot provide information such as plaque morphology and atherosclerotic load, and is difficult to clearly display lesions in the vascular wall. As the current mainstream intraluminal imaging technology, intravascular ultrasound (IVUS) can not only observe the morphology of the lumen and plaques, but also determine the nature of the lesions based on echo characteristics, and is convenient for quantitative determination of the size of the lumen and plaques and the degree of lumen stenosis. Its penetration is much higher than that of OCT. However, it faces the challenge of doctors finding it difficult to locate the ideal stent edge landing area defined by IVUS on CAG images. Therefore, combining multimodal image registration is of great significance to the development of clinical diagnosis and treatment technology.

[0004] In the process of implementing the present invention, it was found that there are at least the following technical problems in the prior art: the current vascular registration process has high requirements on the image quality of vascular images, and the vascular images to be registered are required to be free from problems such as vascular shortening, and it is impossible to accurately register vascular images with problems such as vascular shortening. Summary of the invention

[0005] The present invention provides a registration method, device, storage medium and electronic equipment for extravascular image and intravascular image, so as to realize the registration of intravascular image and extravascular image and improve the accuracy of vascular registration.

[0006] According to one aspect of the present invention, a registration method for an extravascular image and an intravascular image is provided, comprising:

[0007] Acquire a first lumen feature point set of an intravascular image corresponding to a target blood vessel segment, and acquire a second lumen feature point set of an extravascular image corresponding to the target blood vessel segment;

[0008] Determining a first feature sequence corresponding to the first lumen feature point set;

[0009] determining a shortened blood vessel length of the target blood vessel segment in the extravascular image;

[0010] Based on the shortened blood vessel length, determining a plurality of first local feature point sets in the second lumen feature point set, and determining second feature sequences respectively corresponding to the plurality of first local feature point sets;

[0011] Based on the second feature sequences and the first feature sequences respectively corresponding to the multiple first local feature point sets, blood vessel registration is performed on the intravascular image and the extravascular image to obtain a registration result.

[0012] Optionally, the first feature sequence includes an identifier corresponding to the first feature point in the first lumen feature point set and blood vessel diameter information;

[0013] Alternatively, the first feature sequence is a multidimensional feature sequence, which includes multidimensional feature data corresponding to the first feature point in the first lumen feature point set, and the multidimensional feature data is obtained by feature extraction based on the identifier corresponding to the first feature point and the blood vessel diameter information.

[0014] Optionally, the performing blood vessel registration on the intravascular image and the extravascular image based on the second feature sequence and the first feature sequence respectively corresponding to the multiple first local feature point sets includes:

[0015] Based on matching the second feature sequences respectively corresponding to the plurality of first local feature point sets with the first feature sequence, determining the matching degree data respectively corresponding to the plurality of first local feature point sets;

[0016] The matching degree data respectively corresponding to the plurality of first local feature point sets are compared to determine a target local feature point set as the registration result.

[0017] Optionally, determining the shortened blood vessel length of the target blood vessel segment in the extravascular image includes:

[0018] Obtaining the blood vessel length corresponding to the first lumen feature point set;

[0019] The shortened vessel length of the target vessel segment in the extravascular image is determined based on the vessel length and a preset shortening parameter; the shortened vessel length is one or more.

[0020] Optionally, the method further includes:

[0021] For each of the plurality of shortened blood vessel lengths, determining a plurality of first local feature point sets corresponding to the shortened blood vessel length in a second lumen feature point set of the extravascular image, and determining second feature sequences respectively corresponding to the plurality of first local feature point sets;

[0022] Based on the second feature sequences and the first feature sequences respectively corresponding to the plurality of first local feature point sets, blood vessel registration is performed on the intravascular image and the extravascular image to obtain a registration result corresponding to the length of the shortened blood vessel;

[0023] A target registration result is determined based on the registration results respectively corresponding to the lengths of the plurality of shortened blood vessels.

[0024] Optionally, the registration result corresponding to the shortened blood vessel length includes a target local feature point set corresponding to the shortened blood vessel length;

[0025] The determining of the target registration result based on the registration results respectively corresponding to the lengths of the plurality of shortened blood vessels comprises:

[0026] The matching degree data of the target local feature point set corresponding to at least one of the shortened blood vessel lengths are compared to determine a target registration point set as the target registration result.

[0027] Optionally, the method further includes:

[0028] Determining a third feature sequence corresponding to the second lumen feature point set;

[0029] Based on the third feature sequence and the first feature sequence, performing vascular registration on the intravascular image and the extravascular image to obtain a registration segment point set in the extravascular image;

[0030] Based on the shortened blood vessel length, a plurality of second local feature point sets are determined in the registration segment point set, and fourth feature sequences respectively corresponding to the plurality of second local feature point sets are determined;

[0031] Based on the fourth feature sequences and the first feature sequence respectively corresponding to the plurality of second local feature point sets, blood vessel registration is performed on the intravascular image and the extravascular image to obtain a registration result.

[0032] According to another aspect of the present invention, there is provided a registration device for an extravascular image and an intravascular image, comprising:

[0033] A feature point set acquisition module, used to acquire a first lumen feature point set of an intravascular image corresponding to a target blood vessel segment, and to acquire a second lumen feature point set of an extravascular image corresponding to the target blood vessel segment;

[0034] A feature sequence determination module, used to determine a first feature sequence corresponding to the first lumen feature point set;

[0035] A shortened blood vessel length determination module, used to determine the shortened blood vessel length corresponding to the target blood vessel in the extravascular image;

[0036] A registration module is used to determine multiple first local feature point sets in the second lumen feature point set of the extravascular image based on the length of the shortened blood vessel, and determine second feature sequences corresponding to the multiple first local feature point sets respectively; based on the second feature sequences and the first feature sequences corresponding to the multiple first local feature point sets respectively, perform blood vessel registration on the intravascular image and the extravascular image to obtain a registration result.

[0037] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0038] at least one processor; and

[0039] a memory communicatively connected to the at least one processor; wherein,

[0040] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for aligning the extravascular image and the intravascular image described in any embodiment of the present invention.

[0041] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for aligning extravascular images with intravascular images described in any embodiment of the present invention when executed.

[0042] The technical solution of the embodiment of the present invention, taking into account the presence of vascular shortening in the target vascular segment in the extravascular image, determines the shortened vascular length of the target vascular segment in the extravascular image, and determines multiple first local feature point sets corresponding to the shortened vascular lengths in the second lumen feature point set corresponding to the extravascular image; obtains the second feature sequences of the multiple first local feature point sets and the first feature sequence of the first lumen feature point set corresponding to the intravascular image, the first feature sequence and the second feature sequence being feature sequences of unequal lengths, and obtains the registration result by aligning the first feature sequence and the multiple second feature sequences, thereby achieving vascular registration in the case of shortening, improving vascular registration accuracy, and reducing the requirements for the acquisition quality of vascular images, as well as the requirements for the acquisition of vascular images.

[0043] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 It is a flow chart of a registration method of an extravascular image and an intravascular image provided by the first embodiment of the present invention;

[0046] Figure 2 is a schematic diagram of the structure of a blood vessel branch provided in Embodiment 1 of the present invention;

[0047] Figure 3 is a schematic diagram of blood vessel registration provided by Embodiment 1 of the present invention;

[0048] Figure 4 is a flow chart of a registration method for an extravascular image and an intravascular image provided by a second embodiment of the present invention;

[0049] Figure 5 is a flow chart of a registration method for an extravascular image and an intravascular image provided by Embodiment 3 of the present invention;

[0050] Figure 6 It is a structural schematic diagram of a registration device for an extravascular image and an intravascular image provided by a fourth embodiment of the present invention;

[0051] Figure 7 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0053] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0054] Embodiment 1

[0055] Figure 1 This is a flow chart of a registration method for an extravascular image and an intravascular image provided by the first embodiment of the present invention. This embodiment can be applied to the case where the intravascular image and the extravascular image are registered with each other under the condition of considering the shortening of the blood vessels. The method can be executed by a registration device for the extravascular image and the intravascular image. The registration device for the extravascular image and the intravascular image can be implemented in the form of hardware and / or software. The registration device for the extravascular image and the intravascular image can be configured in electronic devices such as mobile phones, tablet computers, computers or servers. Figure 1 As shown, the method includes:

[0056] S110 , obtaining a first lumen feature point set of an intravascular image corresponding to a target blood vessel segment, and obtaining a second lumen feature point set of an extravascular image corresponding to the target blood vessel segment.

[0057] Among them, the target vascular segment refers to the vascular segment of interest, and the intravascular image can be an intravascular ultrasound image of the target vascular segment, and the intravascular ultrasound image is composed of an image sequence. For example, the intravascular image can be an IVUS image. In an embodiment of the present invention, the intravascular image corresponding to the target vascular segment is obtained, and the intravascular image corresponding to the target vascular segment is segmented to obtain a first lumen segmentation result. The implementation method of lumen segmentation of the intravascular image is not limited here. Taking each frame of the image sequence as a sampling point, the first lumen segmentation result is sampled to obtain a first lumen feature point set. The first lumen feature point set includes multiple first feature points, and the first feature points are respectively provided with identifiers. The identifier of the first feature point can be the serial number of the first feature point, and the serial number of the first feature point can be arranged in order from the proximal end to the distal end of the multiple first feature points.

[0058] The extravascular image may be a coronary angiography image of the target vascular segment. In an embodiment of the present invention, the extravascular image corresponding to the target vascular segment is acquired, and the lumen segmentation is performed on the extravascular image corresponding to the target vascular segment to obtain a second lumen segmentation result. The vascular diameter of the extravascular image corresponding to the target vascular segment is sampled and processed to obtain a plurality of second feature points, and the plurality of second feature points form a second lumen feature point set. For example, the vascular diameter of the extravascular image may be sampled and processed based on a preset sampling rate, or the vascular diameter of the extravascular image may be uniformly sampled and processed based on a preset number of feature points. The second feature points are respectively provided with identifiers, and the identifiers of the second feature points may be serial numbers of the second feature points, and the serial numbers of the second feature points may be arranged in an orderly manner from the proximal end to the distal end of the plurality of second feature points.

[0059] In some embodiments, optionally, the method further includes: resampling the first feature points in the first lumen feature point set and / or the second feature points in the second lumen feature point set based on the same sampling rate.

[0060] Since the average physical length of adjacent sampling points in the first lumen feature point set may be inconsistent with the average physical length of adjacent sampling points in the second lumen feature point set, it is necessary to resample the first feature point in the first lumen feature point set and / or the second feature point in the second lumen feature point set so that the sampling rate between adjacent sampling points in the first lumen feature point set is consistent with the sampling rate between adjacent sampling points in the second lumen feature point set. The resampling method includes but is not limited to the nearest neighbor interpolation method, the bilinear interpolation method, the cubic spline interpolation method, etc., which are not limited here.

[0061] Optionally, a target sampling rate (i.e., the same sampling rate for resampling) is selected from the first sampling rate corresponding to the first lumen feature point set and the second sampling rate corresponding to the second lumen feature point set, and the first feature point in the first lumen feature point set or the second feature point in the second lumen feature point set is resampled based on the target sampling rate. Wherein, the target sampling rate (Spacing) may be the smaller sampling rate of the first sampling rate and the second sampling rate. Exemplarily, if the target sampling rate is the first sampling rate, the second feature point in the second lumen feature point set is resampled based on the first sampling rate; if the target sampling rate is the second sampling rate, the first feature point in the first lumen feature point set is resampled based on the second sampling rate. Optionally, a third sampling rate may be pre-set, and the first feature point in the first lumen feature point set and the second feature point in the second lumen feature point set are resampled based on the pre-set third sampling rate. The third sampling rate may be greater than the first sampling rate, and the third sampling rate may be greater than the second sampling rate.

[0062] Optionally, after resampling, the identifier of the first feature point in the first lumen feature point set is adaptively updated, and the identifier of the first feature point is determined based on the position of the first feature point in the target blood vessel segment; and / or, the identifier of the second feature point in the second lumen feature point set is adaptively updated, and the identifier of the second feature point is determined based on the position of the first feature point in the target blood vessel segment.

[0063] S120: Determine a first feature sequence corresponding to the first lumen feature point set.

[0064] The first feature sequence includes feature information of multiple first feature points in the first lumen feature point set. Optionally, the first feature sequence includes an identifier and blood vessel diameter information corresponding to the first feature point in the first lumen feature point set; wherein the blood vessel diameter information may be the diameter information at the blood vessel position where the first feature point is located, which may be extracted from the intravascular image. Accordingly, the first feature sequence is a two-dimensional feature sequence, including an identifier sequence and a blood vessel diameter sequence.

[0065] Optionally, the first feature sequence is a multidimensional feature sequence, and the first feature sequence includes multidimensional feature data corresponding to the first feature point in the first lumen feature point set, and the multidimensional feature data is obtained by feature extraction based on the identifier and vascular diameter information corresponding to the first feature point. For example, the multidimensional feature data of the first feature point includes one or more of the identifier of the first feature point, vascular diameter information, vascular diameter gradient feature, and vascular diameter event feature, and accordingly, the first feature sequence includes one or more of the identifier sequence of the first feature point, vascular diameter sequence, vascular diameter gradient feature sequence, and vascular diameter event feature; or the first feature sequence can be understood as a sequence formed by a multidimensional data group of multiple first feature points.

[0066] Optionally, the identifiers and blood vessel diameter information corresponding to the multiple first feature points in the first lumen feature point set form a first initial feature sequence, and by performing feature extraction on the first initial feature sequence, a multidimensional feature sequence corresponding to the first lumen feature point set is obtained as the first feature sequence.

[0067] Optionally, before extracting features from the first initial feature sequence, the method further includes: normalizing and smoothing the blood vessel diameter information in the first initial feature sequence. The normalization method includes, but is not limited to, Min-Max normalization, Z-score normalization, logarithmic normalization, standard deviation normalization, etc., which are not limited here. The smoothing method includes, but is not limited to, moving average method, exponential smoothing method, polynomial smoothing method, low-pass filter smoothing method, Kalman filter smoothing method, etc., which are not limited here.

[0068] Optionally, multiple first feature points in the first lumen feature point set are sorted based on the identifier. For each first feature point, determine a neighborhood of a preset length of the first feature point; determine the vascular diameter gradient feature of the first feature point based on the vascular diameter information of multiple neighborhood feature points in the neighborhood. The preset length can be understood as the number of first feature points, for example, the preset length is 50, and the corresponding number of domain feature points is 50. The first feature point is located at the center of the domain, and the neighborhood feature point is located before or after the first feature point. For each feature point in the domain, calculate the vascular diameter gradient data of the feature point, and the vascular diameter gradient data corresponding to the multiple feature points in the neighborhood form the vascular diameter gradient feature of the first feature point. The multiple feature points in the neighborhood include the first feature point and the neighborhood feature points of the first feature point.

[0069] Furthermore, the blood vessel diameter gradient feature of the first feature point is determined based on the blood vessel diameter information of multiple neighborhood feature points in the neighborhood. Blood vessel diameter gradient data of any feature point in the neighborhood:

[0070]

[0071] Among them, ΔR i is the gradient feature of the blood vessel diameter of the i-th feature point in the neighborhood, R i Represents the blood vessel diameter information of the i-th neighborhood feature point, R i-1 Represents the blood vessel diameter information of the i-1th feature point in the neighborhood, R i+1 Indicates the blood vessel diameter information of the i+1th feature point in the neighborhood. Since the first and last first feature points in the neighborhood have only one adjacent feature point, for the preset length l, the dimension of the blood vessel diameter gradient feature is l-2.

[0072] Optionally, the feature extraction of the first initial feature sequence includes: obtaining a first branch feature point set of the intravascular image; the first branch feature point set includes branch feature points corresponding to each branch blood vessel in the intravascular image; for a first feature point corresponding to the branch feature point in the first lumen feature point set, processing the blood vessel diameter information of the first feature point based on preset processing parameters to obtain the processed blood vessel diameter information of the first feature point.

[0073] The first branch feature point set is used to describe the branch position information of the intravascular image sequence. In an embodiment of the present invention, the vascular branches of the intravascular image are segmented to obtain a branch segmentation result, and the midpoint of multiple first feature points of the same vascular branch in the position area corresponding to the first lumen feature point set in the branch segmentation result is used as a branch feature point. Exemplarily, a certain vascular branch corresponds to the first feature points 100-110 in the first lumen feature point set, and accordingly, the branch feature point corresponding to the vascular branch can be 105. The target vascular segment may include multiple vascular branches, and the branch feature points corresponding to the multiple vascular branches form the first branch feature point set. It should be noted that when the first lumen feature point set is resampled, the branch feature points in the first branch feature point set need to be updated according to the identifier of the first feature point in the resampled first lumen feature point set.

[0074] For the first feature point corresponding to the branch feature point in the first lumen feature point set, the vascular diameter information of the first feature point is processed based on the preset processing parameters to obtain the processed vascular diameter information of the first feature point. Specifically, the processing formula of the vascular diameter information is as follows: R'=R*a; wherein R' represents the processed vascular diameter information of the first feature point, R is the vascular diameter information of the first feature point, and a is a preset processing parameter, which can be 0.01. It can be understood that, except for the first feature point corresponding to the branch feature point, the vascular diameter information of other first feature points remains unchanged.

[0075] Optionally, the feature extraction of the first initial feature sequence also includes: obtaining a vascular diameter sequence formed by the vascular diameter information of the multiple first feature points in the first lumen feature point set, the vascular diameter information of the first feature point including at least one of the vascular diameter information after processing and the vascular diameter information before processing; for each of the first feature points, determining an event interval corresponding to the first feature point in the vascular diameter sequence, the event type of each of the first feature points in the event interval being consistent; and determining the vascular diameter event feature of the first feature point based on the event interval corresponding to the first feature point.

[0076] The blood vessel diameter event may include an uphill event and a downhill event. The uphill event may be understood as an event in which the blood vessel diameter information continues to increase, and the downhill event may be understood as an event in which the blood vessel diameter information continues to decrease. The event interval may be understood as an interval with a consistent event type, and the event interval includes multiple first feature points of the same time type. The event interval includes an uphill interval in which the change trend of the blood vessel diameter information increases monotonically, and a downhill interval in which the change trend of the blood vessel diameter information decreases monotonically.

[0077] A vascular diameter sequence formed by vascular diameter information of multiple first feature points in the first lumen feature point set is obtained, wherein the vascular diameter sequence includes vascular diameter information of multiple first feature points in the first lumen feature point set before processing; or, the vascular diameter sequence includes vascular diameter information of multiple first feature points in the first lumen feature point set after processing.

[0078] For each first feature point, determine the event interval corresponding to the first feature point in the vascular diameter sequence, obtain the vascular diameter information of the first feature point and the vascular diameter information of the adjacent first feature point, compare the vascular diameter information of the first feature point and the vascular diameter information of the adjacent first feature point, and determine the event type based on the comparison result. For example, for the first feature point i, the vascular diameter information of the first feature point i+1 is greater than the vascular diameter information of the first feature point i, indicating that the event type is uphill; the vascular diameter information of the first feature point i+1 is less than the vascular diameter information of the first feature point i, indicating that the event type is downhill. The vascular diameter information of the first feature point i+1 is equal to the vascular diameter information of the first feature point i, indicating that the event type is non-downhill and non-uphill. Similarly, the vascular diameter information of the first feature point i-1 is compared with the first feature point i to determine the event type. Taking the event type of uphill as an example, the first feature point i+1 is added to the event interval of the first feature point i, and the blood vessel diameter information of the first feature point i+1 and the first feature point i+2 are continued to be compared to determine the event type. When the event type is uphill, the first feature point i+2 is added to the event interval of the first feature point i, and so on, until the event type changes, stop searching, and get the event interval corresponding to the first feature point i.

[0079] The vascular diameter event feature of the first feature point is determined based on the event interval, event = {upslope, downslope}, where upslope indicates the event feature when the event type is rising, and downslope indicates the event feature when the event type is falling. If the vascular diameter information in the event interval corresponding to the first feature point decreases monotonically, the vascular diameter event feature of the first feature point is event = {0, I i}; If the blood vessel diameter information in the event interval corresponding to the first feature point increases monotonically, the blood vessel diameter event feature of the first feature point is event = {I i ,0},I i represents the characteristic value of the i-th first feature point in the event interval. If the blood vessel diameter information remains unchanged in the event interval corresponding to the first feature point, the event feature of the first feature point is event = {0, 0}. Specifically, the calculation formula of the characteristic value of the first feature point in the event interval is as follows:

[0080] Among them, I irepresents the characteristic value of the first characteristic point i in the event interval, t i represents the blood vessel diameter information after or before processing of the i-th first feature point, t i Indicates the identifier of the i-th first feature point, t s and t e represents the event interval of the i-th first feature point (t s , t e )’s lower limit feature point identification and upper limit feature point identification.

[0081] It can be understood that the first feature sequence includes l+2-dimensional feature data corresponding to each first feature point, specifically including: one-dimensional identification of the first sampling point, one-dimensional blood vessel diameter information, two-dimensional blood vessel diameter event characteristics and l-2-dimensional blood vessel diameter gradient characteristics.

[0082] S130: Determine the shortened blood vessel length of the target blood vessel segment in the extravascular image.

[0083] In this embodiment, in theory, the physical lengths of the target blood vessel segments corresponding to the intravascular image and the extravascular image are consistent, that is, L 内 =L 外 , where for intravascular images, the physical length of the target vessel segment can be determined based on the number of image frames and the average physical length in the intravascular image, i.e., L 外 =Spacing*M, where M is the number of first feature points in the first lumen feature point set corresponding to the intravascular image, and Spacing can be the physical length between adjacent sampling points corresponding to the target sampling rate.

[0084] Considering that the target blood vessel segment in the extravascular image has a shortened blood vessel, the blood vessel lengths corresponding to the target blood vessel segment in the extravascular image and the intravascular image are inconsistent. The shortened blood vessel length of the target blood vessel segment in the extravascular image is determined. The shortened blood vessel length can be understood as the blood vessel length of the target blood vessel segment in the extravascular image after shortening, and can be determined based on the blood vessel length corresponding to the target blood vessel segment in the intravascular image and the preset shortening parameter of the extravascular image.

[0085] Optionally, determining the shortened vessel length of the target vessel segment in the extravascular image includes: obtaining the vessel length corresponding to the first lumen feature point set; and determining the shortened vessel length of the target vessel segment in the extravascular image based on the vessel length and a preset shortening parameter.

[0086] The blood vessel length corresponding to the first lumen feature point set can be understood as the number of first feature points in the first lumen feature point set. The physical length L of the target blood vessel segment can be determined by the blood vessel length corresponding to the first lumen feature point set and the average physical length between the first feature points in the intravascular image.内 The shortening value of the target blood vessel segment in the extravascular image can be determined by the physical length of the target blood vessel segment and the preset shortening parameter. For example, the shortening value of the target blood vessel segment in the extravascular image can be determined based on the product of the physical length of the target blood vessel segment and the preset shortening parameter. The physical length of the target blood vessel segment after shortening in the extravascular image can be determined by the difference between the physical length of the target blood vessel segment and the shortening value of the target blood vessel segment in the extravascular image. The shortened blood vessel length of the target blood vessel segment in the extravascular image is determined based on the average physical length between the physical length of the target blood vessel segment after shortening and the second characteristic point in the extravascular image. The shortened blood vessel length can be understood as the number of characteristic points of the target blood vessel segment corresponding to the intravascular image corresponding to the first characteristic point when shortened.

[0087] Optionally, the shortened vessel length of the target vessel segment in the extravascular image may be characterized based on the following formula: (L 内 -p) / Spacing, where the shortening value p = L 内 *a, a is the preset shortening parameter.

[0088] S140. Based on the shortened blood vessel length, determine a plurality of first local feature point sets in the second lumen feature point set, and determine second feature sequences corresponding to the plurality of first local feature point sets respectively.

[0089] Taking the first second feature point in the second lumen feature point set as the starting point, traverse the second lumen feature point set based on the preset step size and the shortened blood vessel length, and determine multiple first local feature point sets corresponding to the shortened blood vessel length. Exemplarily, taking the shortened blood vessel length as n and the preset step size as s as an example, taking the first second feature point in the second lumen feature point set as the starting point, it is determined that the first first local feature point set that satisfies the shortened blood vessel length includes the 1st second feature point to the nth second feature point; the second first local feature point set includes the s+1th second feature point to the s+nth second feature point; the third first local feature point set includes the 2s+1th second feature point to the 2s+nth second feature point, and so on.

[0090] For each first local feature point set, including multiple second feature points respectively, a second feature sequence of each first local feature point set is determined. Optionally, the second feature sequence may include the identification and blood vessel diameter information corresponding to the second feature point in the first local feature point set. Optionally, the second feature sequence is a multidimensional feature sequence, and the second feature sequence includes multidimensional feature data corresponding to the second feature point in the first local feature point set, and the multidimensional feature data is obtained by feature extraction based on the identification and blood vessel diameter information corresponding to the second feature point. For example, the multidimensional feature data of the second feature point includes one or more of the identification of the second feature point, blood vessel diameter information, blood vessel diameter gradient feature and blood vessel diameter event feature, and accordingly, the second feature sequence includes one or more of the identification sequence, blood vessel diameter sequence, blood vessel diameter gradient feature sequence and blood vessel diameter event feature of the second feature point.

[0091] Optionally, the identifiers and blood vessel diameter information corresponding to the plurality of second feature points in the first local feature point set form a second initial feature sequence, and by performing feature extraction on the second initial feature sequence, a multidimensional feature sequence corresponding to the first local feature point set is obtained as the second feature sequence.

[0092] Optionally, extracting features from the second initial feature sequence includes: for each second feature point, determining a neighborhood of a preset length of the second feature point; and determining a blood vessel diameter gradient feature of the second feature point based on blood vessel diameter information of a plurality of neighborhood feature points in the neighborhood. Detailed description is omitted here.

[0093] Optionally, the feature extraction of the second initial feature sequence includes: obtaining a second branch feature point set of the extravascular image; the second branch feature point set includes branch feature points corresponding to each branch blood vessel in the extravascular image; for the second feature point corresponding to the branch feature point in the second lumen feature point set, processing the blood vessel diameter information of the second feature point based on preset processing parameters to obtain the processed blood vessel diameter information of the second feature point. The processed blood vessel diameter information is R'=R*a, which will not be repeated here.

[0094] For example, Figure 2 is a schematic diagram of the structure of the blood vessel branch provided in the first embodiment of the present invention, such as Figure 2 As shown, points A and B are the intersection points of the blood vessel branch and the trunk, point C is the intersection point of the branch diameter and the trunk, 100, 105 and 110 are the first feature points corresponding to points A, B and C on the blood vessel branch in the first lumen feature point set, and 105 is the midpoint, and 105 is used as the branch feature point.

[0095] Optionally, extracting features from the second initial feature sequence further includes: obtaining a vascular diameter sequence formed by the vascular diameter information of the plurality of second feature points in the second lumen feature point set, the vascular diameter information of the second feature points including at least one of the vascular diameter information after processing and the vascular diameter information before processing; for each of the second feature points, determining an event interval corresponding to the second feature point in the vascular diameter sequence, wherein the event type of each of the second feature points in the event interval is consistent; and determining the vascular diameter event feature of the second feature point based on the event interval corresponding to the second feature point. No further details are given here.

[0096] It can be understood that the multi-dimensional feature data of the same second feature point in different first local feature point sets can be reused without repeated calculation.

[0097] S150 , performing blood vessel registration on the intravascular image and the extravascular image based on the second feature sequences and the first feature sequences respectively corresponding to the multiple first local feature point sets to obtain a registration result.

[0098] In this embodiment, the higher the similarity between the second feature sequence and the first feature sequence, the higher the matching degree between the first local feature point set and the first lumen feature point set. The similarity between the second feature sequence corresponding to each first local feature point set and the first feature sequence can be determined based on a preset sequence matching algorithm. Based on the similarity between the second feature sequences corresponding to multiple first local feature point sets and the first feature sequence, the first local feature point set corresponding to the highest similarity is determined to determine the registration result, which can include the first local feature point set corresponding to the highest similarity.

[0099] Among them, the pre-set sequence matching algorithms include but are not limited to Euclidean distance algorithm, cosine similarity algorithm, mutual information algorithm, Hausdorff distance algorithm, Pearson similarity coefficient algorithm, Manhattan distance algorithm and dynamic kernel correlation algorithm.

[0100] Optionally, the vascular registration of the intravascular image and the extravascular image based on the second feature sequence and the first feature sequence respectively corresponding to the multiple first local feature point sets includes: matching the second feature sequences corresponding to the multiple first local feature point sets with the first feature sequence to determine the matching degree data respectively corresponding to the multiple first local feature point sets; comparing the matching degree data respectively corresponding to the multiple first local feature point sets to determine the target local feature point set as the registration result.

[0101] Optionally, the pre-set sequence matching algorithm can be a DTW (Dynamic Time Warping) algorithm. The second feature sequence of the first local feature point set and the first feature sequence are matched by the DTW algorithm to find the shortest path of the corresponding sequence in each dimension, calculate the score, and finally obtain the optimal matching path of the second feature sequence and the first feature sequence through weighted calculation, and output the matching degree data. The matching degree data characterizes the similarity between the second feature sequence and the first feature sequence. The higher the matching degree data, the higher the matching degree between the first local feature point set and the first lumen feature point set.

[0102] By comparing the matching degree data respectively corresponding to the plurality of first local feature point sets, the first local feature point set corresponding to the maximum matching degree data is determined as the target local feature point set as the registration result.

[0103] For example, see Figure 3 , Figure 3 1 is a schematic diagram of blood vessel registration provided by Embodiment 1 of the present invention. One or more second feature points in the target local feature point set corresponding to the extravascular image correspond to one or more frames of the image sequence in the intravascular image.

[0104] The technical solution of this embodiment, taking into account the presence of vascular shortening in the target vascular segment in the extravascular image, determines the shortened vascular length of the target vascular segment in the extravascular image, and determines multiple first local feature point sets corresponding to the shortened vascular lengths in the second lumen feature point set corresponding to the extravascular image; obtains the second feature sequences of the multiple first local feature point sets and the first feature sequence of the first lumen feature point set corresponding to the intravascular image, the first feature sequence and the second feature sequence being feature sequences of unequal lengths, and obtains the registration result by aligning the first feature sequence and the multiple second feature sequences, thereby achieving vascular registration in the case of shortening, improving vascular registration accuracy, and reducing the requirements for the acquisition quality of vascular images, as well as the requirements for the acquisition of vascular images.

[0105] Embodiment 2

[0106] Figure 4 This is a flow chart of a registration method for an extravascular image and an intravascular image provided by the second embodiment of the present invention, which is optimized on the basis of the above embodiment and provides a process for vascular registration of intravascular images and extravascular images for multiple shortened blood vessel lengths. Figure 2 As shown, the method includes:

[0107] S210 , obtaining a first lumen feature point set of an intravascular image corresponding to a target blood vessel segment, and obtaining a second lumen feature point set of an extravascular image corresponding to the target blood vessel segment.

[0108] S220: Determine a first feature sequence corresponding to the first lumen feature point set.

[0109] S230: Determine the shortened blood vessel length of the target blood vessel segment in the extravascular image.

[0110] S240. For each of the multiple shortened blood vessel lengths, determine multiple first local feature point sets corresponding to the shortened blood vessel length in the second lumen feature point set of the extravascular image, and determine second feature sequences corresponding to the multiple first local feature point sets, respectively.

[0111] S250 , performing blood vessel registration on the intravascular image and the extravascular image based on the second feature sequences and the first feature sequences respectively corresponding to the multiple first local feature point sets, to obtain a registration result corresponding to the shortened blood vessel length.

[0112] S260: Determine a target registration result based on the registration results corresponding to the lengths of the plurality of shortened blood vessels.

[0113] In this embodiment, there are multiple shortened blood vessel lengths, and a method for determining the multiple shortened blood vessel lengths may include: obtaining the blood vessel length corresponding to the first lumen feature point set; determining a shortening value range based on the blood vessel length and a preset shortening parameter, determining at least one shortening value in the shortening value range, and determining a shortening blood vessel length based on each shortening value to obtain at least one shortening blood vessel length.

[0114] Specifically, the physical length L of the target blood vessel segment can be determined by the blood vessel length corresponding to the first lumen feature point set and the average physical length between the first feature points in the intravascular image. 内 The upper limit P of the shortening value of the target blood vessel segment in the extravascular image can be determined by the physical length of the target blood vessel segment and the preset shortening parameter. For example, the upper limit P of the shortening value of the target blood vessel segment in the extravascular image can be determined based on the product of the physical length of the target blood vessel segment and the preset shortening parameter. Accordingly, the shortening value range is (0, P). At least one shortening value p is determined in the shortening value range. For example, multiple shortening values ​​p can be obtained by random sampling, or multiple shortening values ​​p can be determined based on preset value intervals.

[0115] For each at least one shortening value p, the physical length of the target blood vessel segment after shortening in the extravascular image can be determined by the difference between the physical length of the target blood vessel segment and at least one shortening value p, and the shortened blood vessel length of the target blood vessel segment in the extravascular image is determined based on the physical length of the target blood vessel segment after shortening and the average physical length between the second feature point in the extravascular image.

[0116] In the case where there are multiple shortened vessel lengths, the multiple shortened vessel lengths are traversed, and for each shortened vessel length, multiple first local feature point sets corresponding to the shortened vessel length are determined respectively, and second feature sequences corresponding to the multiple first local feature point sets are determined respectively, and registration is performed based on the second feature sequences corresponding to the multiple first local feature point sets and the first feature sequence to obtain a registration result corresponding to the shortened vessel length, and the registration result corresponding to the shortened vessel length includes a target local feature point set corresponding to the shortened vessel length.

[0117] In the above registration process, the matching degree data corresponding to the target local feature point set corresponding to each shortened blood vessel length can be obtained, and the matching degree data of the target local feature point set corresponding to at least one of the shortened blood vessel lengths can be compared to determine the target registration point set as the target registration result. Specifically, the target local feature point set corresponding to the maximum matching degree data is determined as the target registration point set as the target registration result.

[0118] The technical solution of this embodiment determines multiple shortened blood vessel lengths and performs blood vessel registration for different shortened blood vessel lengths, thereby avoiding the situation where a single shortened blood vessel length is inaccurately determined, and improving the accuracy of blood vessel registration. In the target local feature point sets corresponding to multiple shortened blood vessel lengths, by comparing the matching degree data of the target local feature point sets corresponding to the multiple shortened blood vessel lengths, the target local feature point set with the maximum matching degree data is determined as the target registration point set, thereby improving the accuracy of the target registration point set.

[0119] Embodiment 3

[0120] Figure 5 This is a flow chart of a registration method for an extravascular image and an intravascular image provided by the third embodiment of the present invention. The above embodiment is optimized and the vascular registration process is divided into two stages. The first stage determines the registration segment point set corresponding to the extravascular image. In the second stage, the first lumen feature point set of the intravascular image is used to perform registration in the registration segment point set to determine the target registration result. In the first stage, the vascular shortening is not considered, but in the second stage, the vascular shortening is considered. See Figure 5 , the method specifically comprises:

[0121] S310, obtaining a first lumen feature point set of an intravascular image corresponding to a target blood vessel segment, and obtaining a second lumen feature point set of an extravascular image corresponding to the target blood vessel segment.

[0122] S320, determining a first feature sequence corresponding to the first lumen feature point set; and determining a third feature sequence corresponding to the second lumen feature point set.

[0123] S330: Based on the third feature sequence and the first feature sequence, perform vascular registration on the intravascular image and the extravascular image to obtain a registration segment point set in the extravascular image.

[0124] S340: Determine the shortened blood vessel length of the target blood vessel segment in the extravascular image.

[0125] S350 , based on the shortened blood vessel length, determine a plurality of second local feature point sets in the registration segment point set, and determine fourth feature sequences corresponding to the plurality of second local feature point sets respectively.

[0126] S360: Perform blood vessel registration on the intravascular image and the extravascular image based on the fourth feature sequences and the first feature sequence respectively corresponding to the plurality of second local feature point sets to obtain a registration result.

[0127] The third feature sequence includes the identifiers and blood vessel diameter information of multiple second feature points in the second lumen feature point set. Alternatively, the third feature sequence includes multi-dimensional feature data of multiple second feature points in the second lumen feature point set. The method for determining the multi-dimensional feature data of the second feature points is not described in detail here.

[0128] Optionally, the first feature sequence and the third feature sequence may be registered by a pre-trained registration model. Specifically, the first feature sequence and the third feature sequence are input into a pre-set registration model to output a registration segment point set. Without considering vascular shortening, the vascular segment corresponding to the registration segment point set in the extravascular image matches the target vascular segment in the intravascular image.

[0129] Optionally, based on a preset sliding window, slide on the second lumen feature point set to obtain multiple local feature point sets corresponding to the window area, any of the local feature point sets corresponding to the window area includes multiple second feature points in the window area; determine the local feature sequences corresponding to the multiple local feature point sets; the second feature sequence corresponding to the second lumen feature point set includes the local feature sequences corresponding to the multiple local feature point sets. Match the local feature sequences corresponding to the multiple local feature point sets with the first multidimensional feature sequence to determine the matching degree data corresponding to the multiple local feature point sets; determine the registration segment point set based on the matching degree data corresponding to the multiple local feature point sets.

[0130] Optionally, the registration segment point set is a local point set of the second lumen feature point set. By registering the third feature sequence with the first feature sequence in the first stage, the registration segment point set is determined, the number of second feature points in the registration segment point set is simplified, and the data volume of the second stage registration process is reduced.

[0131] Based on the shortened blood vessel length, multiple second local feature point sets are determined in the registration segment point set. Specifically, the first second feature point in the registration segment point set is used as the starting point, and multiple second local feature point sets are determined based on a preset step length. Feature extraction is performed on each second local feature point set to obtain a fourth feature series of each second local feature point set. The fourth feature series includes the identifiers and blood vessel diameter information of multiple second feature points in the second local feature point set. Alternatively, the fourth feature series includes multi-dimensional feature data of multiple second feature points in the second local feature point set. The method for determining the multi-dimensional feature data of the second feature points is not described in detail here.

[0132] The registration result is obtained by registering the fourth feature sequence and the first feature sequence respectively corresponding to the plurality of second local feature point sets.

[0133] In some embodiments, there are multiple shortened blood vessel lengths. For each shortened blood vessel length, multiple second local feature point sets corresponding to the shortened blood vessel length are determined in the registration segment point set, and fourth feature sequences corresponding to the multiple second local feature point sets are determined. Based on the fourth feature sequences corresponding to the multiple second local feature point sets and the first feature sequence, the intravascular image and the extravascular image are registered with each other to obtain a registration result corresponding to the shortened blood vessel length. A target registration result is determined based on the registration results corresponding to the multiple shortened blood vessel lengths.

[0134] In the technical solution of this embodiment, it can be understood that the number of the second local feature point set is smaller than the number of the first local feature point set, which reduces the amount of data in the second stage and improves the registration efficiency.

[0135] Embodiment 4

[0136] Figure 6 FIG. 4 is a schematic diagram of a device for registering an extravascular image with an intravascular image provided by a fourth embodiment of the present invention. Figure 6 As shown, the device comprises:

[0137] The feature point set acquisition module 410 is used to acquire a first lumen feature point set of an intravascular image corresponding to a target blood vessel segment, and to acquire a second lumen feature point set of an extravascular image corresponding to the target blood vessel segment;

[0138] A feature sequence determination module 420, configured to determine a first feature sequence corresponding to the first lumen feature point set;

[0139] A shortened blood vessel length determination module 430, configured to determine a shortened blood vessel length corresponding to the target blood vessel in the extravascular image;

[0140] The registration module 440 is used to determine multiple first local feature point sets in the second lumen feature point set of the extravascular image based on the length of the shortened blood vessel, and determine second feature sequences corresponding to the multiple first local feature point sets respectively; based on the second feature sequences and the first feature sequences corresponding to the multiple first local feature point sets respectively, perform blood vessel registration on the intravascular image and the extravascular image to obtain a registration result.

[0141] Based on the above embodiment, optionally, the first feature sequence includes an identifier corresponding to the first feature point in the first lumen feature point set and blood vessel diameter information;

[0142] Alternatively, the first feature sequence is a multidimensional feature sequence, which includes multidimensional feature data corresponding to the first feature point in the first lumen feature point set, and the multidimensional feature data is obtained by feature extraction based on the identifier corresponding to the first feature point and the blood vessel diameter information.

[0143] Optionally, the registration module 440 is used to: determine the matching degree data corresponding to the multiple first local feature point sets based on matching the second feature sequences corresponding to the multiple first local feature point sets with the first feature sequences; and determine the target local feature point set as the registration result by comparing the matching degree data corresponding to the multiple first local feature point sets.

[0144] Based on the above embodiment, optionally, the shortened vessel length determination module 430 is used to: obtain the vessel length corresponding to the first lumen feature point set; determine the shortened vessel length of the target vessel segment in the extravascular image based on the vessel length and a preset shortening parameter; the shortened vessel length is one or more.

[0145] Optionally, the registration module 440 is also used to: for each of the multiple shortened blood vessel lengths, determine multiple first local feature point sets corresponding to the shortened blood vessel length in the second lumen feature point set of the extravascular image, and determine second feature sequences corresponding to the multiple first local feature point sets respectively; perform vascular registration on the intravascular image and the extravascular image based on the second feature sequences and the first feature sequences corresponding to the multiple first local feature point sets respectively, to obtain a registration result corresponding to the shortened blood vessel length; and determine a target registration result based on the registration results corresponding to the multiple shortened blood vessel lengths respectively.

[0146] Optionally, the registration result corresponding to the shortened blood vessel length includes a target local feature point set corresponding to the shortened blood vessel length;

[0147] Optionally, the registration module 440 is further configured to compare the matching degree data of the target local feature point set corresponding to at least one of the shortened blood vessel lengths, and determine a target registration point set as the target registration result.

[0148] On the basis of the above embodiment, optionally, the registration module 440 is also used to: determine a third feature sequence corresponding to the second lumen feature point set; perform vascular registration on the intravascular image and the extravascular image based on the third feature sequence and the first feature sequence to obtain a registration segment point set in the extravascular image; determine multiple second local feature point sets in the registration segment point set based on the shortened blood vessel length, and determine fourth feature sequences corresponding to the multiple second local feature point sets respectively; perform vascular registration on the intravascular image and the extravascular image based on the fourth feature sequences corresponding to the multiple second local feature point sets and the first feature sequence to obtain a registration result.

[0149] The extravascular image and intravascular image registration device provided in the embodiment of the present invention can execute the extravascular image and intravascular image registration method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0150] Embodiment 5

[0151] Figure 7 1 is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0152] like Figure 7As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0153] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0154] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a registration method for an extravascular image and an intravascular image.

[0155] In some embodiments, the registration method of the extravascular image and the intravascular image can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the registration method of the extravascular image and the intravascular image described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the registration method of the extravascular image and the intravascular image by any other appropriate means (for example, by means of firmware).

[0156] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0157] The computer program for implementing the registration method of the extravascular image and the intravascular image of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or the block diagram are implemented. The computer program can be executed completely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or completely on a remote machine or server.

[0158] Embodiment 6

[0159] Embodiment 6 of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute a registration method for an extravascular image and an intravascular image, the method comprising:

[0160] Acquire a first lumen feature point set of an intravascular image corresponding to a target blood vessel segment, and acquire a second lumen feature point set of an extravascular image corresponding to the target blood vessel segment; determine a first feature sequence corresponding to the first lumen feature point set; determine the shortened blood vessel length of the target blood vessel segment in the extravascular image; based on the shortened blood vessel length, determine a plurality of first local feature point sets in the second lumen feature point set, and determine second feature sequences corresponding to the plurality of first local feature point sets respectively; perform vascular registration on the intravascular image and the extravascular image based on the second feature sequences corresponding to the plurality of first local feature point sets and the first feature sequence respectively, to obtain a registration result.

[0161] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0162] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0163] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0164] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0165] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0166] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A registration method for an extravascular image and an intravascular image, characterized in that: include: Acquire a first lumen feature point set of an intravascular image corresponding to a target blood vessel segment, and acquire a second lumen feature point set of an extravascular image corresponding to the target blood vessel segment; Determining a first feature sequence corresponding to the first lumen feature point set; determining a shortened blood vessel length of the target blood vessel segment in the extravascular image; Based on the shortened blood vessel length, determining a plurality of first local feature point sets in the second lumen feature point set, and determining second feature sequences respectively corresponding to the plurality of first local feature point sets; Based on the second feature sequences and the first feature sequences respectively corresponding to the multiple first local feature point sets, blood vessel registration is performed on the intravascular image and the extravascular image to obtain a registration result.

2. The method according to claim 1, characterized in that The first feature sequence includes an identifier corresponding to the first feature point in the first lumen feature point set and blood vessel diameter information; Alternatively, the first feature sequence is a multidimensional feature sequence, which includes multidimensional feature data corresponding to the first feature point in the first lumen feature point set, and the multidimensional feature data is obtained by feature extraction based on the identifier corresponding to the first feature point and the blood vessel diameter information.

3. The method according to claim 1, characterized in that The performing blood vessel registration on the intravascular image and the extravascular image based on the second feature sequence and the first feature sequence respectively corresponding to the plurality of first local feature point sets comprises: Based on matching the second feature sequences respectively corresponding to the plurality of first local feature point sets with the first feature sequence, determining the matching degree data respectively corresponding to the plurality of first local feature point sets; The matching degree data respectively corresponding to the plurality of first local feature point sets are compared to determine a target local feature point set as the registration result.

4. The method according to claim 1, characterized in that: The determining of the shortened blood vessel length of the target blood vessel segment in the extravascular image comprises: Obtaining the blood vessel length corresponding to the first lumen feature point set; The shortened vessel length of the target vessel segment in the extravascular image is determined based on the vessel length and a preset shortening parameter; the shortened vessel length is one or more.

5. The method according to claim 4, characterized in that The method further comprises: For each of the plurality of shortened blood vessel lengths, determining a plurality of first local feature point sets corresponding to the shortened blood vessel length in a second lumen feature point set of the extravascular image, and determining second feature sequences respectively corresponding to the plurality of first local feature point sets; Based on the second feature sequences and the first feature sequences respectively corresponding to the plurality of first local feature point sets, blood vessel registration is performed on the intravascular image and the extravascular image to obtain a registration result corresponding to the length of the shortened blood vessel; A target registration result is determined based on the registration results respectively corresponding to the lengths of the plurality of shortened blood vessels.

6. The method according to claim 5, characterized in that The registration result corresponding to the shortened blood vessel length includes a target local feature point set corresponding to the shortened blood vessel length; The determining of the target registration result based on the registration results respectively corresponding to the lengths of the plurality of shortened blood vessels comprises: The matching degree data of the target local feature point set corresponding to at least one of the shortened blood vessel lengths are compared to determine a target registration point set as the target registration result.

7. The method according to claim 1, characterized in that The method further comprises: Determining a third feature sequence corresponding to the second lumen feature point set; Based on the third feature sequence and the first feature sequence, performing vascular registration on the intravascular image and the extravascular image to obtain a registration segment point set in the extravascular image; Based on the shortened blood vessel length, a plurality of second local feature point sets are determined in the registration segment point set, and fourth feature sequences respectively corresponding to the plurality of second local feature point sets are determined; Based on the fourth feature sequences and the first feature sequence respectively corresponding to the plurality of second local feature point sets, blood vessel registration is performed on the intravascular image and the extravascular image to obtain a registration result.

8. A registration device for an extravascular image and an intravascular image, characterized in that: include: A feature point set acquisition module, used to acquire a first lumen feature point set of an intravascular image corresponding to a target blood vessel segment, and to acquire a second lumen feature point set of an extravascular image corresponding to the target blood vessel segment; A feature sequence determination module, used to determine a first feature sequence corresponding to the first lumen feature point set; A shortened blood vessel length determination module, used to determine the shortened blood vessel length corresponding to the target blood vessel in the extravascular image; A registration module is used to determine multiple first local feature point sets in the second lumen feature point set of the extravascular image based on the length of the shortened blood vessel, and determine second feature sequences corresponding to the multiple first local feature point sets respectively; based on the second feature sequences and the first feature sequences corresponding to the multiple first local feature point sets respectively, perform blood vessel registration on the intravascular image and the extravascular image to obtain a registration result.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for registering the extravascular image and the intravascular image as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the registration method of the extravascular image and the intravascular image according to any one of claims 1 to 7 when executed.

Images