A collateral circulation status assessment method, device, storage medium and electronic device

Abstract

The present application discloses a collateral circulation status assessment method, device, storage medium, and electronic device, wherein the method comprises: acquiring multiple target images containing a region of interest, each target image including collateral vessel features of the normal side and the affected side; extracting the collateral vessel features of each target image to obtain a vascular mask image corresponding to each target image, each vascular mask image including the grayscale features of the collateral vessels of the normal side and the affected side; determining the filling degree of the affected side based on the grayscale value of the normal side and the grayscale value of the affected side in the same vascular mask image to obtain a plurality of filling degrees; and assessing the collateral circulation status based on at least each of the filling degrees to obtain an assessment result of the collateral circulation status. The collateral circulation status assessment method of the present application can make the assessment result more accurate, shorten the assessment time, and increase efficiency.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a collateral circulation status assessment method, device, storage medium, and electronic device. Background Art

[0002] Acute ischemic stroke, the leading cause of disability and second leading cause of death worldwide, has become the leading cause of mortality in my country, accounting for approximately 80% of all strokes. With the continuous advancement of endovascular treatment technology, establishing personalized assessment and treatment plans for specific patients to improve their clinical outcomes and prognosis has become an urgent issue.

[0003] Cerebral collateral circulation refers to compensatory blood flow through other vessels when the blood supply area is ischemic due to cerebral vascular stenosis or occlusion. Good collateral circulation is closely related to the surgical process of removing intravascular thrombi and predicting disease progression. Effective collateral circulation can stabilize cerebral blood flow in the infarcted area, extend the treatment window, and improve the long-term outcome of reperfusion therapy.

[0004] Several collateral assessment methods are currently available, including those based on invasive imaging techniques, such as digital subtraction angiography (DSA), and noninvasive imaging techniques, such as computed tomography angiography (CTA) and computed tomography perfusion (CTP). Noninvasive imaging techniques are recommended for patients classified as Category IA candidates for endovascular treatment during the initial imaging examination. However, currently, noninvasive collateral assessment methods based on these techniques are inaccurate or require a long evaluation time, making them unsuitable for patients in the acute phase.

[0005] Therefore, there is an urgent need for a method to assess the status of collateral circulation, so that the assessment of brain collateral circulation can be more accurate and timely. Summary of the Invention

[0006] In view of this, the present invention provides a collateral circulation status assessment method, device, storage medium and electronic device, the main purpose of which is to solve the problem of inaccurate collateral circulation status assessment at present.

[0007] To solve the above problems, the present application provides a collateral circulation status assessment method, comprising:

[0008] Acquire multiple target images containing a region of interest, each of the target images including collateral vessel features of a normal side and an affected side;

[0009] Extracting collateral vessel features of each target image to obtain a vessel mask image corresponding to each target image, wherein each vessel mask image includes grayscale features of collateral vessels on the normal side and the affected side;

[0010] determining the filling degree of the affected side in the corresponding vascular mask image based on the grayscale value of the normal side and the grayscale value of the affected side in the same vascular mask image, so as to obtain a plurality of filling degrees;

[0011] The collateral circulation state is evaluated at least based on each of the filling degrees to obtain an evaluation result of the collateral circulation state.

[0012] Optionally, acquiring multiple target images including the region of interest specifically includes:

[0013] Performing CT perfusion imaging scans based on a predetermined number of scans to obtain scan images corresponding to each number of scans;

[0014] Preprocessing each of the scanned images to obtain a first image corresponding to each of the scanned images;

[0015] A blood vessel enhancement process is performed on each of the first images to obtain each of the target images with enhanced features of the side branch vessels.

[0016] Optionally, extracting collateral vessel features of each target image to obtain a vessel mask image corresponding to each target image specifically includes:

[0017] Using a maximum intensity projection algorithm to process each of the target images, respectively, to obtain processed target images;

[0018] The processed target images are processed by non-local mean filtering to obtain the blood vessel mask images.

[0019] Optionally, the determining the filling degree of the affected side based on the grayscale value of the normal side and the grayscale value of the affected side in the same vascular mask image to obtain a plurality of filling degrees includes:

[0020] Matching each of the vascular mask images with a standard blood supply area zoning template image to determine a first target blood supply area on the normal side and a second target blood supply area corresponding to the first target blood supply area in each of the vascular mask images; the second target blood supply area is the blood supply area on the affected side;

[0021] Based on the grayscale value of the first target blood supply area on the normal side in each of the vascular mask images and the grayscale value of the second target blood supply area, the filling degree of the second target blood supply area is determined to obtain the multiple filling degrees corresponding to each of the vascular mask images.

[0022] Optionally, the evaluating the collateral circulation state based at least on each of the filling degrees to obtain an evaluation result of the collateral circulation state specifically includes:

[0023] determining a target filling degree based on each of the filling degrees;

[0024] The collateral circulation state is evaluated at least based on the target filling degree to obtain an evaluation result of the collateral circulation state.

[0025] Optionally, the collateral circulation status assessment method further includes:

[0026] determining a delay time of filling of the collateral vessels on the affected side based on the grayscale value of the collateral vessels on the normal side and the grayscale value of the collateral vessels on the affected side in each of the vascular mask images;

[0027] The collateral circulation state is evaluated based on the delay time to obtain an evaluation result of the collateral circulation state.

[0028] Optionally, determining the delay time of filling of the collateral vessels on the affected side based on the grayscale value of the collateral vessels on the normal side and the grayscale value of the collateral vessels on the affected side in each of the vascular mask images specifically includes:

[0029] determining at least one first vascular mask image whose filling degree meets a first preset condition based on the grayscale value of the collateral vessels on the normal side in each of the vascular mask images;

[0030] determining, based on the grayscale values of the collateral vessels on the affected side in each of the vascular mask images, at least one second vascular mask image whose filling degree meets a second preset condition;

[0031] The delay time is determined based on the scanning time corresponding to each of the first blood vessel mask images and the scanning time corresponding to each of the second blood vessel mask images.

[0032] To solve the above technical problems, the present application provides a collateral circulation status assessment device, comprising:

[0033] The acquisition module acquires multiple target images containing the region of interest, each of which includes collateral vessel features of the normal side and the affected side.

[0034] an extraction module, extracting collateral vessel features of each target image, and obtaining a vessel mask image corresponding to each target image, wherein each vessel mask image includes grayscale features of collateral vessels on the normal side and the affected side;

[0035] an acquisition module, configured to determine the filling degree of the affected side based on the grayscale value of the normal side and the grayscale value of the affected side in the same blood vessel mask image, so as to obtain a plurality of filling degrees;

[0036] An evaluation module is configured to evaluate the collateral circulation status based at least on the respective filling degrees to obtain an evaluation result of the collateral circulation status.

[0037] In order to solve the above technical problems, the present application provides a storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of any of the above-mentioned collateral circulation status assessment methods.

[0038] To solve the above technical problems, the present application provides an electronic device, which includes at least a memory and a processor, wherein a computer program is stored on the memory, and the processor implements the steps of any of the above-mentioned collateral circulation status assessment methods when executing the computer program on the memory.

[0039] This application performs CT perfusion imaging based on a predetermined number of scans to obtain scan data (CTP data for each phase) corresponding to each scan number. The assessment method in this application differs from any previous collateral assessment method in that it determines the collateral circulation filling degree and, based on the filling degree, determines whether the collateral circulation is in a good or poor state. This method can make the assessment results more accurate, shorten the assessment time, and increase efficiency. This lays the foundation for subsequently providing these assessment results to clinicians as a reference.

[0040] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0042] Figure 1 This is a flow chart of a collateral circulation status assessment method according to an embodiment of the present application;

[0043] Figure 2 This is a flowchart of a collateral circulation status assessment method according to another embodiment of the present application. DETAILED DESCRIPTION

[0044] Various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0045] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but merely as an example of an embodiment. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.

[0046] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0047] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0048] It should also be understood that although the present application has been described with reference to certain specific examples, those skilled in the art will readily be able to implement many other equivalent forms of the present application.

[0049] The above and other aspects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings.

[0050] Specific embodiments of the present application will be described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments described are merely examples of the present application and may be implemented in a variety of ways. Familiar and / or repetitive functions and structures are not described in detail to avoid obscuring the present application with unnecessary or redundant details. Therefore, the specific structural and functional details described herein are not intended to be limiting, but rather serve merely as a basis and representative basis for the claims to teach those skilled in the art to variously utilize the present application with substantially any suitable detailed structure.

[0051] This specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may all refer to one or more of the same or different embodiments according to the present application.

[0052] The present application embodiment provides a method for evaluating the state of collateral circulation, which can be applied to the evaluation of the state of brain collateral circulation. Figure 1 As shown, the evaluation method in this embodiment includes the following steps:

[0053] Step S101, acquiring a plurality of target images including a region of interest, wherein each target image includes collateral vessel features of a normal side and an affected side;

[0054] In this step, before acquiring multiple target images, multiple scans can be performed based on CT perfusion imaging to obtain scan data corresponding to each scan, that is, to obtain several groups / periods of CTP data, thereby obtaining several groups / periods of scan images. After acquiring the scanned images, the scanned data can be processed to obtain target images. For example, SPM12 software can be used to correct the anterior and posterior commissures of the brain, perform skull stripping, align to MNI space, and pre-process each scanned image using multi-scale smoothing filtering to obtain a first image corresponding to each scanned image. A Hessian matrix-related vascular enhancement algorithm can be used to perform vascular enhancement processing on each first image to obtain each target image with enhanced collateral vessel features. After obtaining the target images, the flow characteristics of the contrast agent in the blood vessels can be further utilized to further use a matrix completion algorithm to separate the calcified background for image extraction to obtain the final target images, which include collateral vessel features on both the normal side and the affected side.

[0055] Step S102, extracting collateral vessel features of each target image to obtain a vessel mask image corresponding to each target image, wherein each vessel mask image includes grayscale features of collateral vessels on the normal side and the affected side;

[0056] In this step, each target image is processed along the axial direction using a maximum intensity projection algorithm to facilitate presentation of vascular morphology and grayscale distribution on the image, thereby obtaining a corresponding vascular mask image. The above steps are repeated for each scan data / each scan data phase in a predetermined number of CTP data phases to obtain a corresponding vascular mask image. Each vascular mask image includes the grayscale characteristics of collateral vessels on the normal side and the affected side.

[0057] Step S103, determining the filling degree of the affected side in the corresponding vascular mask image based on the grayscale value of the normal side and the grayscale value of the affected side in the same vascular mask image, to obtain a plurality of filling degrees;

[0058] The normal side and the affected side in this step are obtained by comparing the difference in the mean grayscale values of the blood vessels in each arterial vascular partition. The side with the lower grayscale mean is the affected side, and the other side is the normal side. In this step, the filling degree specifically refers to the percentage of the grayscale value of the blood flow in the affected side blood vessels to the grayscale value of the blood flow in the normal side blood vessels.

[0059] Step S104: evaluating the collateral circulation status at least based on the respective filling degrees to obtain an evaluation result of the collateral circulation status.

[0060] In this step, the collateral circulation status is evaluated based on the filling degree. For example, when the filling degree is greater than a preset value, it indicates that the collateral circulation status is good, and when the filling degree is less than the preset value, it indicates that the collateral circulation status is poor.

[0061] The method in this embodiment performs CT perfusion imaging scans based on a predetermined number of scans to obtain scan data corresponding to each scan number (CTP data of each phase), and then determines the fullness of the collateral circulation. Based on the fullness, the collateral circulation state is determined to be in a good state or a poor state, which can make the evaluation results more accurate, shorten the evaluation time, and increase the efficiency.

[0062] On the basis of the above embodiments, in order to make the assessment of collateral circulation status more accurate, another embodiment of the present application provides a method for assessing collateral circulation status, such as Figure 2 As shown, the following steps are included:

[0063] Step S201, performing CT perfusion imaging scans based on a predetermined number of scans to obtain scan images corresponding to each number of scans;

[0064] During implementation, the number of scans can be set based on actual needs. For example, setting the number of scans to 19 will yield 19 phases of CTP scan data / scanned images. When acquiring scanned images, the scanning protocols of different hospitals and equipment can be further combined to obtain scanned images corresponding to each scan number. The predetermined number of scans can cover the entire cycle of CT perfusion imaging. CT perfusion imaging involves continuous CT scanning of the region of interest (ROI) to obtain a time-density curve for the ROI. The entire scan cycle can be determined based on the ROI time-density curve. For example, in the assessment of cerebral collateral vessels, by acquiring data from a complete CT perfusion imaging cycle and reconstructing images to obtain the grayscale features of the vessels on the normal and affected sides at different phases, the degree of vascular filling can be determined. This eliminates the need for manual evaluation and experience to select the arterial phase. Subsequently, data from the venous phase and late venous phase are selected every 8 seconds, improving data accuracy.

[0065] Step S202, preprocessing each of the scanned images to obtain a preprocessed first image;

[0066] In this step, the SPM12 software can be used to perform anterior and posterior brain correction on each of the scanned images, remove the skull, align them to the MNI space, and use multi-scale smoothing filtering to remove interference information to obtain the first pre-processed image.

[0067] Step S203 : performing blood vessel enhancement processing on each of the first images to obtain each of the target images with enhanced features of the collateral vessels.

[0068] In this step, a Hessian matrix-related vascular enhancement algorithm can be used to perform vascular enhancement processing on each first image to obtain each target image with enhanced collateral vessel features. After obtaining the target image, the flow characteristics of the contrast agent in the blood vessel can be further used to further use a matrix completion algorithm to separate the calcified background for image extraction to obtain the final target images, which include collateral vessel features on the normal side and the affected side.

[0069] Step S204: extracting collateral vessel features of each target image to obtain a vessel mask image corresponding to each target image, wherein each vessel mask image includes grayscale features of collateral vessels on the normal side and the affected side;

[0070] During the specific implementation of this step, maximum intensity projection of grayscale can be performed along the axial spatial dimension, and each of the projected target images can be processed using a non-local mean filtering method to obtain each of the vascular mask images, each of which includes grayscale features of the collateral vessels on the normal side and the affected side;

[0071] Step S205 , determining the filling degree of the affected side based on the grayscale value of the normal side and the grayscale value of the affected side in the same blood vessel mask image, to obtain a plurality of filling degrees;

[0072] In this step, each of the vascular mask images is matched with a standard blood supply area zoning template image to determine a first target blood supply area and a second target blood supply area on the normal side in each vascular mask image; the second target blood supply area is the blood supply area on the affected side. Based on the grayscale value of the first target blood supply area on the normal side and the grayscale value of the second target blood supply area corresponding to the first target blood supply area in each vascular mask image, the filling degree of the second target blood supply area is determined to obtain the plurality of filling degrees. The standard blood supply area zoning template can specifically be a cerebral zoning template, which includes templates for standard zoning areas such as the posterior inferior cerebellar artery, superior cerebellar artery, vertebral artery and basilar artery branches, anterior choroidal artery, lenticulostriate artery, anterior cerebral artery, middle cerebral artery, and posterior cerebral artery. That is, the zoning template includes a correspondence between the location information of each blood supply area and the blood supply area name. Of course, the standard blood supply area zoning template can also be a zoning template corresponding to other parts of the body. If the affected side appears in the blood supply area of another artery, the standard blood supply area zoning template is the corresponding blood supply area zoning template.

[0073] During the implementation of this step, the blood supply area can be determined specifically by matching each of the vascular mask images with a predetermined standard blood supply area zoning template image to determine a first target blood supply area on the normal side in each of the vascular mask images and a second target blood supply area on the affected side corresponding to the normal side; the second blood supply area corresponds one-to-one to the first blood supply area; based on the grayscale value of the first target blood supply area on the normal side in each of the vascular mask images and the grayscale value of the second target blood supply area corresponding to the first target blood supply area, the filling degree of the second target blood supply area is determined to obtain the filling degree of the several phases of side branches. This step is explained using the example of the affected side as a cerebral artery. The first target blood supply area can be any of the following blood supply areas: the posterior inferior cerebellar artery, the superior cerebellar artery, the vertebral artery and basilar artery branches, the anterior choroidal artery, the lenticulostriate artery, the anterior cerebral artery, the middle cerebral artery, and the posterior cerebral artery. The second target blood supply area can be any of the following blood supply areas: the posterior inferior cerebellar artery, the superior cerebellar artery, the vertebral artery and basilar artery branches, the anterior choroidal artery, the lenticulostriate artery, the anterior cerebral artery, the middle cerebral artery, and the posterior cerebral artery. When determining the filling degree, the filling degree of the affected side can be determined for a specific group / pair of blood supply areas, or it can be determined simultaneously based on multiple groups / pairs of blood supply areas. For example, if the first target blood supply area is the posterior inferior cerebellar artery and the second target blood supply area is the posterior inferior cerebellar artery, the grayscale value of the normal side's posterior inferior cerebellar artery is then compared with the grayscale value of the affected side's posterior inferior cerebellar artery to determine the filling degree of the affected side's posterior inferior cerebellar artery in each of the vascular mask images, thereby obtaining a number of filling degrees. Similarly, when the first target blood supply area is the posterior inferior cerebellar artery and the superior cerebellar artery, and the second target blood supply area is the posterior inferior cerebellar artery and the superior cerebellar artery, then the grayscale value of the posterior inferior cerebellar artery on the normal side is compared with the grayscale value of the posterior inferior cerebellar artery on the affected side, and the grayscale value of the posterior superior cerebellar artery on the normal side is compared with the grayscale value of the posterior superior cerebellar artery on the affected side to determine the filling degree of the posterior inferior cerebellar artery on the affected side in each of the vascular mask images, and the filling degree of the posterior superior cerebellar artery on the affected side in each of the vascular mask images. Subsequently, the first target filling degree can be determined based on the filling degree of each posterior inferior cerebellar artery, and the second target filling degree can be determined based on the filling degree of each posterior superior cerebellar artery. Finally, the collateral circulation status can be determined based on the first target filling degree and the second target filling degree. The grayscale value of the first target blood supply area and the grayscale value of the second target blood supply area can be the average grayscale value within the corresponding blood supply area, or the grayscale value of a certain point within the corresponding blood supply area. Preferably, the grayscale value of the first target blood supply area and the grayscale value of the second target blood supply area are average grayscale values in the corresponding blood supply areas.

[0074] Since different blood flows will have different grayscale values in the image, the higher the grayscale value, the greater the blood flow. Therefore, in this step, the percentage of the grayscale value of the second target blood supply area on the affected side to the grayscale value of the first target blood supply area on the normal side can be determined, and the fullness of the blood supply area on the affected side relative to the normal side can be determined based on the percentage, so that the determination of the fullness is more accurate.

[0075] Step S206, determining a delay time of filling of the collateral vessels on the affected side based on the grayscale value of the collateral vessels on the normal side and the grayscale value of the collateral vessels on the affected side in each of the vascular mask images;

[0076] During the specific implementation of this step, based on the grayscale values of the collateral vessels on the normal side in each of the vascular mask images, at least one first vascular mask image is determined whose filling degree meets a first preset condition; based on the grayscale values of the collateral vessels on the affected side in each of the vascular mask images, at least one second vascular mask image is determined whose filling degree meets a second preset condition; and based on the scan time corresponding to each first vascular mask image and the scan time corresponding to each second vascular mask image, a delay time is determined, where the delay time is equal to the difference between the scan time corresponding to the second vascular mask image and the scan time corresponding to the first vascular mask image. The delay time (Time delay) can also be specifically expressed as: Time delay = |P lm -P rm |*T x . T x The time interval is determined by the P_ lm 、P_ rm The time difference between them is determined, P lm is the phase number of a first blood vessel mask image whose filling degree meets the first preset condition, P rm is the period of a second blood vessel mask image whose filling degree meets the second preset condition. x is an equal time interval. In the actual data scanning process, the time intervals of adjacent periods may also be different. The above formula is T x In this embodiment, the grayscale value of the first target blood supply area and the grayscale value of the second target blood supply area may be the average grayscale value of the arterial blood vessels.

[0077] Step S207 , evaluating the collateral circulation state based on the filling degree and the delay time to obtain an evaluation result of the collateral circulation state.

[0078] During the specific implementation of this step, a target filling degree is first determined based on each of the filling degrees. The target filling degree may include an average filling degree calculated based on each of the filling degrees, or a filling degree that satisfies a preset condition. Specifically, an average value may be calculated based on each of the filling degrees and used as the target filling degree. Alternatively, at least one filling degree may be selected from each of the filling degrees by calculating the variance, thereby eliminating filling degrees with large errors. This allows for more reasonable and accurate determination of the target filling degree, laying the foundation for subsequent accurate assessment of collateral circulation status based on the target filling degree. After determining the target filling degree, a predetermined mapping relationship between filling degrees and scores is used to determine the score corresponding to the target filling degree, obtaining a first score. Similarly, a predetermined mapping relationship between delay time and scores is used to determine the score corresponding to the delay time, obtaining a second score. Finally, the first and second scores are weighted to determine the target score. The collateral circulation status is determined based on the score interval corresponding to the target score, i.e., different score intervals correspond to different collateral circulation statuses.

[0079] In this embodiment, by determining the filling degree of each second target blood supply area (the blood supply area on the affected side) in each vascular mask image, the target filling degree of each second target blood supply area can be determined more comprehensively and accurately, thereby making the subsequent assessment of collateral circulation status based on the target filling degree more accurate. Furthermore, by determining the delay time of the blood supply area based on the grayscale values of the affected and normal blood supply areas in each vascular mask image, and assessing the collateral circulation status based on the delay time and filling degree, the final assessment results can be more accurate.

[0080] Two collateral status assessment methods based on non-invasive imaging techniques have been proposed in the related art. One method compares the filling extent of collateral vessels on the affected and normal sides in single-phase CTA images to generate a collateral score. The other method utilizes the patient's arterial, venous, and late venous phase data, not only comparing the filling extent of the affected and normal sides but also providing the timing of delayed filling of the affected collateral. This scoring scheme effectively avoids the disadvantage of single-phase CTA data in underestimating collateral circulation. However, three-phase CTA data acquisition requires high equipment and technician requirements, and the scanning time is relatively long, making it unsuitable for patients in the acute phase. In some embodiments, the first-phase CTP data corresponding to the peak of arterial blood flow is selected as the arterial phase based on the time-density curve, and the venous and late venous phase data are then selected at 8-second intervals. However, since the scanning interval between each phase of CTP data is fixed, selecting the arterial phase data based on the perfusion curve and then directly selecting the venous and late venous phase data at fixed time intervals can lead to inaccurate data selection. The collateral status assessment method proposed in the above-mentioned embodiments of this application utilizes complete CTP data, eliminating the complex and time-consuming process of manually selecting arterial, venous, and late venous phase data from CTP data, thereby improving the accuracy and efficiency of collateral status assessment. Furthermore, complete CTP data contains comprehensive hemodynamic information and is clinically easier to obtain than triple-phase CTA data. It also provides richer temporal information, which is significantly enhanced compared to single-phase CTA data.

[0081] Another embodiment of the present application provides a collateral circulation status assessment device, comprising:

[0082] The acquisition module acquires multiple target images containing the region of interest, each of which includes collateral vessel features of the normal side and the affected side.

[0083] an extraction module, extracting collateral vessel features of each target image, and obtaining a vessel mask image corresponding to each target image, wherein each vessel mask image includes grayscale features of collateral vessels on the normal side and the affected side;

[0084] an acquisition module, configured to determine the filling degree of the affected side based on the grayscale value of the normal side and the grayscale value of the affected side in the same blood vessel mask image, so as to obtain a plurality of filling degrees;

[0085] An evaluation module is configured to evaluate the collateral circulation status based at least on the respective filling degrees to obtain an evaluation result of the collateral circulation status.

[0086] In this embodiment, the collateral circulation status assessment device also includes an acquisition module for acquiring images of each cerebral blood vessel. The acquisition module is specifically used to: perform CT perfusion imaging scans based on a predetermined number of scans to obtain scan images corresponding to each scan number; preprocess each of the scan images to obtain a preprocessed first image; and use a blood vessel enhancement algorithm to perform blood vessel enhancement processing on the preprocessed first image to obtain a feature-enhanced target image.

[0087] The extraction module is specifically used to: extract each target image respectively using a maximum density projection algorithm; and process each target image using a non-local mean filtering method to obtain each blood vessel mask image.

[0088] The acquisition module is specifically used to: determine the filling degree of the affected side based on the grayscale value of the normal side and the grayscale value of the affected side in the same vascular mask image, so as to obtain a plurality of filling degrees, and includes: matching each of the vascular mask images with a standard blood supply area zoning template image to determine the first target blood supply area and the second target blood supply area on the normal side in each of the vascular mask images; the second target blood supply area is the blood supply area on the affected side; based on the grayscale value of the first target blood supply area on the normal side in each of the vascular mask images and the grayscale value of the second target blood supply area corresponding to the first target blood supply area, determine the filling degree of the second target blood supply area to obtain the plurality of filling degrees.

[0089] The evaluation module is specifically used to: evaluate the collateral circulation status based on at least each of the filling degrees to obtain an evaluation result of the collateral circulation status, specifically including: determining a target filling degree based on each of the filling degrees, the target filling degree including: an average filling degree calculated based on each of the filling degrees, or a filling degree that meets preset conditions; evaluate the collateral circulation status based on at least the target filling degree to obtain an evaluation result of the collateral circulation status.

[0090] Specifically, the evaluation module is specifically used to: determine the delay time of the second target blood supply area based on the grayscale value of the first target blood supply area and the grayscale value of the second target blood supply area in each of the vascular mask images; the evaluation of the collateral circulation state based on at least each of the filling degrees to obtain the evaluation result of the collateral circulation state specifically includes: evaluating the collateral circulation state based on each of the filling degrees and the delay time to obtain the evaluation result of the collateral circulation state.

[0091] During the specific implementation process, the evaluation module is used to determine the delay time of the second target blood supply area based on the grayscale value of the first target blood supply area and the grayscale value of the second target blood supply area in each of the vascular mask images, specifically including: determining at least one first vascular mask image whose filling degree meets the first preset condition based on the grayscale value of the normal-side collateral blood vessels in each of the vascular mask images; determining at least one second vascular mask image whose filling degree meets the second preset condition based on the grayscale value of the affected-side collateral blood vessels in each of the vascular mask images; and determining the delay time based on the scanning time corresponding to each of the first vascular mask images and the scanning time corresponding to each of the second vascular mask images.

[0092] The method in this embodiment performs CT perfusion imaging scans based on a predetermined number of scans to obtain scan data corresponding to each scan number (CTP data of each phase), and then determines the filling degree and delay time of the collateral circulation. Based on the filling degree and delay time, the collateral circulation state is determined to be in a good state or a poor state, which can make the evaluation results more accurate, shorten the evaluation time, and increase the efficiency.

[0093] Another embodiment of the present application provides a storage medium storing a computer program. When the computer program is executed by a processor, the following method steps are implemented:

[0094] Step 1: Acquire multiple target images containing the region of interest, each of which includes collateral vessel features of the normal side and the affected side.

[0095] Step 2: extracting collateral vessel features of each target image to obtain a vessel mask image corresponding to each target image, wherein each vessel mask image includes grayscale features of collateral vessels on the normal side and the affected side;

[0096] Step 3: determining the filling degree of the affected side based on the grayscale value of the normal side and the grayscale value of the affected side in the same blood vessel mask image to obtain a plurality of filling degrees;

[0097] Step 4: Evaluate the collateral circulation status based on at least each of the filling degrees to obtain an evaluation result of the collateral circulation status.

[0098] The specific implementation process of the above method steps can be found in the above embodiments of any collateral circulation status assessment method, and this embodiment will not be repeated here.

[0099] The method in this embodiment performs CT perfusion imaging scans based on a predetermined number of scans to obtain scan data corresponding to each scan number (CTP data of each phase), and then determines the fullness of the collateral circulation. Based on the fullness, the collateral circulation state is determined to be in a good state or a poor state, which can make the evaluation results more accurate, shorten the evaluation time, and increase the efficiency.

[0100] Another embodiment of the present application provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the following method steps when executing the computer program in the memory:

[0101] Step 1: Acquire multiple target images containing a region of interest, each of the target images including collateral vessel features of the normal side and the affected side;

[0102] Step 2: extracting collateral vessel features of each target image to obtain a vessel mask image corresponding to each target image, wherein each vessel mask image includes grayscale features of collateral vessels on the normal side and the affected side;

[0103] Step 3: determining the filling degree of the affected side based on the grayscale value of the normal side and the grayscale value of the affected side in the same blood vessel mask image, so as to obtain a plurality of filling degrees;

[0104] Step 4: evaluating the collateral circulation status based at least on the fullness of each of the above-mentioned degrees, and obtaining an evaluation result of the collateral circulation status.

[0105] The specific implementation process of the above method steps can be found in the embodiment of the collateral circulation status assessment method described above, and will not be repeated in this embodiment.

[0106] The method in this embodiment performs CT perfusion imaging scans based on a predetermined number of scans to obtain scan data corresponding to each scan number (CTP data of each phase), and then determines the fullness of the collateral circulation. Based on the fullness, the collateral circulation state is determined to be in a good state or a poor state, which can make the evaluation results more accurate, shorten the evaluation time, and increase the efficiency.

[0107] The above embodiments are merely exemplary embodiments of the present application and are not intended to limit the scope of the present application. The scope of protection of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and scope of protection of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the scope of protection of the present application.

Claims

1. A collateral circulation status assessment method, characterized in that: include: Acquire multiple target images containing a region of interest, each of the target images including collateral vessel features of a normal side and an affected side; Extracting collateral vessel features of each target image to obtain a vessel mask image corresponding to each target image, wherein each vessel mask image includes grayscale features of collateral vessels on the normal side and the affected side; Determining the filling degree of the affected side based on the grayscale value of the normal side and the grayscale value of the affected side in the same blood vessel mask image to obtain a plurality of filling degrees; At least evaluating the collateral circulation state based on each of the filling degrees to obtain an evaluation result of the collateral circulation state; The determination of the collateral circulation status assessment result specifically includes: determining a delay time of filling of the collateral vessels on the affected side based on the grayscale value of the collateral vessels on the normal side and the grayscale value of the collateral vessels on the affected side in each of the vascular mask images; evaluating the collateral circulation state based on the delay time to obtain an evaluation result of the collateral circulation state; The determining of the delayed time of filling of the collateral vessels on the affected side based on the grayscale value of the collateral vessels on the normal side and the grayscale value of the collateral vessels on the affected side in each of the vascular mask images specifically includes: Determining at least one first vascular mask image whose filling degree meets a first preset condition based on the grayscale value of the normal-side collateral vessels in each of the vascular mask images; determining, based on the grayscale values of the collateral vessels on the affected side in each of the vascular mask images, at least one second vascular mask image whose filling degree meets a second preset condition; determining a delay time based on a scan time corresponding to each of the first blood vessel mask images and a scan time corresponding to each of the second blood vessel mask images; The delay time (Time delay) is specifically expressed as: Time delay = |P lm -P rm |*T x； Among them, T x is an equal time interval, which is determined by the P specified in the data scanning plan. _lm 、P _rm The time difference between them is determined, P lm is the phase number of a first blood vessel mask image whose filling degree meets the first preset condition, P rm is the phase number of a second blood vessel mask image whose filling degree meets the second preset condition.

2. The method according to claim 1, wherein The acquiring of multiple target images including the region of interest specifically includes: Performing CT perfusion imaging scans based on a predetermined number of scans to obtain scan images corresponding to each number of scans; Preprocessing each of the scanned images to obtain a first image corresponding to each of the scanned images; A blood vessel enhancement process is performed on each of the first images to obtain each of the target images with enhanced features of the side branch vessels.

3. The method according to claim 1, wherein Extracting the collateral vessel features of each target image to obtain a vessel mask image corresponding to each target image specifically includes: Using a maximum intensity projection algorithm to process each of the target images, respectively, to obtain processed target images; The processed target images are processed by non-local mean filtering to obtain the blood vessel mask images.

4. The method according to claim 1, wherein The method of determining the filling degree of the affected side based on the grayscale value of the normal side and the grayscale value of the affected side in the same blood vessel mask image to obtain a plurality of filling degrees includes: Matching each of the vascular mask images with a standard blood supply area zoning template image to determine a first target blood supply area on the normal side and a second target blood supply area corresponding to the first target blood supply area in each of the vascular mask images, where the second target blood supply area is the blood supply area on the affected side; Based on the grayscale value of the first target blood supply area on the normal side in each of the vascular mask images and the grayscale value of the second target blood supply area, the filling degree of the second target blood supply area is determined to obtain the multiple filling degrees corresponding to each of the vascular mask images.

5. The method according to claim 1, wherein the evaluating the collateral circulation status based on at least each of the filling degrees to obtain the evaluation result of the collateral circulation status specifically comprises: determining a target filling degree based on each of the filling degrees; The target filling degree includes: an average filling degree calculated based on the filling degrees, or a filling degree that meets a preset condition; The collateral circulation state is evaluated at least based on the target filling degree to obtain an evaluation result of the collateral circulation state.

6. A collateral circulation status assessment device, characterized in that: include: An acquisition module is configured to acquire a plurality of target images including a region of interest, wherein each target image includes collateral vessel features of a normal side and an affected side; an extraction module, extracting collateral vessel features of each target image, and obtaining a vessel mask image corresponding to each target image, wherein each vessel mask image includes grayscale features of collateral vessels on the normal side and the affected side; an acquisition module, configured to determine the filling degree of the affected side based on the grayscale value of the normal side and the grayscale value of the affected side in the same blood vessel mask image, so as to obtain a plurality of filling degrees; an evaluation module, configured to evaluate the collateral circulation status based at least on the respective filling degrees, and obtain an evaluation result of the collateral circulation status; The evaluation module is further configured to determine a delay time of filling of the collateral vessels on the affected side based on the grayscale value of the collateral vessels on the normal side and the grayscale value of the collateral vessels on the affected side in each of the vascular mask images; evaluating the collateral circulation state based on the delay time to obtain an evaluation result of the collateral circulation state; The evaluation module is further configured to: determine at least one first vascular mask image whose filling degree meets a first preset condition based on the grayscale value of the normal-side collateral vessels in each of the vascular mask images; determining, based on the grayscale values of the collateral vessels on the affected side in each of the vascular mask images, at least one second vascular mask image whose filling degree meets a second preset condition; determining a delay time based on a scan time corresponding to each of the first blood vessel mask images and a scan time corresponding to each of the second blood vessel mask images; The delay time (Time delay) is specifically expressed as: Time delay = |P lm -P rm |*T x； Among them, T x is an equal time interval, which is determined by the P specified in the data scanning plan. _lm 、P _rm The time difference between them is determined, P lm is the phase number of a first blood vessel mask image whose filling degree meets the first preset condition, P rm is the phase number of a second blood vessel mask image whose filling degree meets the second preset condition.

7. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the collateral circulation status assessment method according to any one of claims 1 to 5 are implemented.

8. An electronic device, characterized in that: The method comprises at least a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the target object detection method according to any one of claims 1 to 5 when executing the computer program in the memory.

Images