Method for determining values of collateral circulation indicators based on single-phase CTA

Abstract

This invention discloses a method for determining collateral circulation indicators based on single-phase CTA, including acquiring single-phase CTA images and DWI images; preprocessing the images to obtain first images at different levels; registering and identifying the blood-supplying brain tissue regions in the first images at different levels to obtain second images at different levels; identifying the ischemic foci area as the vascular aggregation area based on the DWI images, and mapping the vascular aggregation area to the second images at different levels to obtain third images at different levels; calculating the ratio of the area of ​​the vascular aggregation circle to the area of ​​the healthy side vascular circle in the third images at different levels; calculating the mean value based on the ratio and the number of third images, and determining it as the collateral circulation indicator value of the single-phase CTA image to obtain an intuitive and accurate assessment result. This method can be applied to the field of collateral circulation assessment in acute ischemic stroke based on single-phase CTA.

Description

Technical Field

[0001] This invention relates to the field of collateral circulation assessment based on single-phase CTA, and in particular to a method for determining the numerical value of collateral circulation index based on single-phase CTA. Background Technology

[0002] Currently, there is increasing emphasis on the assessment of collateral circulation in acute ischemic stroke using CTA images. However, rapid assessment and interpretation of collateral circulation in acute ischemic stroke based on single-phase CTA remains a significant challenge due to the complexity of the images, which often requires considerable time for novice assessors to understand. Furthermore, current assessments of collateral circulation in acute ischemic stroke based on single-phase CTA are not accurate enough. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method for determining collateral circulation index values ​​based on single-phase CTA, so as to obtain intuitive and more accurate assessment results of collateral circulation in acute ischemic stroke based on single-phase CTA.

[0004] A first aspect of the present invention provides a method for determining the value of collateral circulation index based on single-phase CTA, comprising: acquiring single-phase CTA images and DWI images; preprocessing the single-phase CTA images to obtain first images at different levels, wherein the first images at different levels are characterized as images projected onto the single-phase CTA images in the coronal plane at different distances; registering the first images at different levels with a preset brain template image and identifying the blood-supplying brain tissue region to obtain second images at different levels; identifying the ischemic foci range as the vascular aggregation range based on the DWI images, and mapping the vascular aggregation range to the second images at different levels to obtain third images at different levels; calculating the ratio of the area of ​​the vascular aggregation range to the area of ​​the healthy side vascular aggregation range in the third images at different levels; calculating and processing the average value based on the ratio and the number of third images, and determining the average value as the collateral circulation index value of the single-phase CTA image.

[0005] According to some embodiments of the present invention, the preprocessing of the single-temporal CTA image to obtain a first image at different levels includes: projecting the single-temporal CTA image in the coronal plane to obtain a projection map; obtaining intersection points by intersecting different horizontal lines with the contour lines in the projection map; obtaining two intersection points of the same horizontal line and the contour lines, and calculating the intersection distance between the two intersection points; comparing the intersection distances corresponding to different horizontal lines, and selecting the horizontal line corresponding to the smallest intersection distance as the target horizontal line; and removing the image below the target horizontal line in the projection map to obtain the first image.

[0006] According to some embodiments of the present invention, the process of registering the first image at different levels and identifying the blood-supplying brain tissue region based on a preset brain template image to obtain a second image at different levels includes: calculating the rigid transformation value between the brain template image and the first image; and obtaining the second image by applying the rigid transformation value to the brain mask of the brain template.

[0007] According to some embodiments of the present invention, the process of registering the first image at different levels and identifying the blood-supplying brain tissue region based on a preset brain template image to obtain the second image at different levels includes: removing the skull image from the second image through a neural network.

[0008] According to some embodiments of the present invention, the step of registering the first image at different levels based on a preset brain template image and identifying the blood supply brain tissue region to obtain the second image at different levels further includes: performing filtering processing on the second image at different scales.

[0009] Another aspect of the present invention provides a device for assessing collateral circulation in acute ischemic stroke based on single-phase CTA, comprising: a first module for acquiring single-phase CTA images and DWI images; a second module for preprocessing the single-phase CTA images to obtain first images at different levels, wherein the first images at different levels are characterized as images projected onto the single-phase CTA images in the coronal plane at different distances; a third module for registering the first images at different levels with a preset brain template image and identifying the blood-supplying brain tissue region to obtain second images at different levels; a fourth module for identifying the ischemic foci range as the vascular aggregation range based on the DWI image, and mapping the vascular aggregation range to the second images at different levels to obtain third images at different levels; a fifth module for calculating the ratio of the area of ​​the vascular aggregation range to the area of ​​the healthy side vascular aggregation range in the third images at different levels; and a sixth module for calculating and processing the average value based on the ratio and the number of third images, and determining the average value as the collateral circulation index value of the single-phase CTA image. The second module includes: a projection module for projecting the single-phase CTA image onto the coronal plane to obtain a projection map; an intersection module for obtaining intersection points by intersecting the contour lines in the projection map with different horizontal lines; a first calculation module for obtaining two intersection points of the same horizontal line and the contour line, and calculating the intersection distance between the two intersection points; a comparison module for comparing the intersection distances corresponding to different horizontal lines, and selecting the horizontal line corresponding to the smallest intersection distance as the target horizontal line; and a removal module for removing the image below the target horizontal line in the projection map to obtain a first image. The third module includes: a second calculation module for calculating the rigid transformation value between the brain template image and the first image; and a transformation module for applying the rigid transformation value to the brain mask of the brain template to perform a rigid transformation to obtain a second image. The third module includes: a skull removal module for removing the skull image from the second image using a neural network. The third module also includes: a processing module for performing filtering processing on the second image at different scales.

[0010] Another aspect of the present invention provides an electronic device, including a processor and a memory; the memory is used to store a program; the processor executes the program to implement the method for determining the value of the side circulation index based on single-phase CTA as described above.

[0011] The electronic device according to embodiments of the present invention has at least the same beneficial effects as the method for determining the side circulation index value based on single-phase CTA described above.

[0012] Another aspect of the present invention provides a computer-readable storage medium storing a program that is executed by a processor to implement the method for determining the value of the side circulation index based on single-phase CTA as described above.

[0013] The computer-readable storage medium according to embodiments of the present invention has at least the same beneficial effects as the above-described method for determining the numerical value of the side circulation index based on single-phase CTA.

[0014] Another aspect of the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the method for determining the value of the side circulation index based on single-phase CTA as described above.

[0015] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the method for determining the side circulation index value based on single-phase CTA as described above.

[0016] In embodiments of the present invention, single-phase CTA images and DWI images are acquired. The single-phase CTA images are preprocessed to obtain first images at different levels. The first images at different levels are characterized as images projected onto the single-phase CTA images in the coronal plane at different distances, thereby maintaining the three-dimensional evaluation of the CTA images as much as possible in a multi-layered manner. Based on a preset brain template image, the first images at different levels are registered and the blood-supplying brain tissue regions are identified to obtain second images at different levels. The ischemic foci are identified as the vascular aggregation range based on the DWI images, and the vascular aggregation range is mapped to the second images at different levels to obtain third images at different levels. The ratio of the area of ​​the vascular aggregation range to the area of ​​the healthy side vascular aggregation range is calculated for the third images at different levels. The mean value is calculated based on the ratio and the number of third images, and the mean value is determined as the collateral circulation index value of the single-phase CTA images. Finally, the ratio of the vascular aggregation range to the vascular aggregation circle range is obtained. Combined with the number of multi-layer third images, the final mean value is obtained, maintaining the three-dimensional analysis of CTA images. This enables a more accurate assessment of collateral circulation in acute ischemic stroke based on single-phase CTA images, and outputs the final collateral circulation index values ​​to obtain a more intuitive assessment result. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the method for determining the numerical value of the side circulation index based on single-phase CTA, provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0020] Cerebral collateral circulation refers to the ability of blood to reach the ischemic area through bypass vessels or newly formed blood vessels when the main arteries supplying the brain (one or more) are narrowed or blocked. This allows for varying degrees of perfusion compensation and protection of ischemic tissue, and is one of the important predictive indicators for clinical efficacy and long-term prognosis in patients with ischemic stroke. Currently, there are numerous methods and devices for assessing collateral circulation, often relying primarily on qualitative assessment. However, this is limited by individual assessor consistency bias and depends heavily on the assessor's subjective judgment. CTA has become an important tool for assessing collateral circulation in recent years, with multi-phase CTA providing better evaluation, but it also has limitations. Single-phase CTA is more widely used, with relatively fewer restrictions on qualifications and conditions, and offers many qualitative methods and devices for assessing collateral circulation. However, a simple and effective quantitative collateral circulation assessment protocol based on single-phase CTA urgently needs to be developed.

[0021] Currently, multi-phase CTA can acquire CTA images at multiple time points (arterial phase, venous phase, and late venous phase). To meet the temporal resolution and whole-brain coverage requirements of multi-phase CTA, the CT scanner detector needs to have a certain width. High-displacement CT equipment is mainly distributed in large comprehensive hospitals, while ordinary hospitals use low-displacement CT equipment, which is sufficient for general CT scan diagnosis and does not require costly replacement. Therefore, improving the assessment of collateral circulation in AIS using sCTA still warrants further investigation. While multi-phase CTA can better assess collateral circulation, the radiation dose increases with the number of scanning phases. In patients with poor cardiac function, poor filling of the pia mater collaterals can affect interpretation. Single-phase CTA is widely used for collateral circulation assessment, with source images and MIP (maximum intensity projection) images being the most commonly used. MIP images are relatively more frequently used; they utilize the projection of all pixels with the highest density in the line of sight direction from the volumetric data for assessment, reducing the image from three-dimensional to two-dimensional. This can cause overlap of blood vessels and bones, obscuring some blood vessels and causing assessment errors.

[0022] Therefore, a method for determining the numerical value of the collateral circulation index based on single-phase CTA is proposed to more intuitively evaluate single-phase CTA images.

[0023] refer to Figure 1 , Figure 1 The flowchart of the method for determining the numerical value of the side circulation index based on single-phase CTA provided in the embodiments of the present invention includes at least the following steps S110-S160:

[0024] Step S110: Acquire single-phase CTA images and DWI images.

[0025] Step S120: Preprocess the single-phase CTA image to obtain first images at different levels. The first images at different levels are characterized as images projected onto the single-phase CTA image at different distances in the coronal plane.

[0026] Specifically, single-phase CTA images and DWI images are acquired. For example, a CT scanner and contrast agent can be used to acquire single-phase CTA images. Because single-phase CTA images are three-dimensional, they are projected at different distances in the coronal plane to obtain two-dimensional images, i.e., the first images. Specifically, the CTA images contained in the Dicom standard format are first read. In the acquired CTA images, the skull is projected in the coronal plane to obtain the left and right contour lines of the human body in the medical image. Compared to the current method of directly using the projection of all pixels with the highest density in the line-of-sight direction from the volumetric data for evaluation, projecting single-phase CTA images at different distances in the coronal plane to obtain multiple first images preserves the three-dimensional vascular layer assessment, resulting in more accurate results.

[0027] Furthermore, step S120 also includes: projecting a single-phase CTA image onto the coronal plane to obtain a projection image; obtaining intersection points by intersecting different horizontal lines with the contour lines in the projection image; obtaining two intersection points of the same horizontal line and the contour line, and calculating the intersection distance between the two intersection points; comparing the intersection distances corresponding to different horizontal lines, and selecting the horizontal line corresponding to the smallest intersection distance as the target horizontal line; and removing the image below the target horizontal line in the projection image to obtain the first image.

[0028] Specifically, many factors can influence the assessment of collateral circulation in single-phase CTA images. For example, human or machine factors can cause deviations in the height and shooting range of the single-phase CTA image during its capture. Therefore, to improve the accuracy of single-phase CTA image data processing, preprocessing is necessary. This involves projecting the single-phase CTA image onto the coronal plane to obtain a projection image. Intersection points are obtained by finding the intersections of different horizontal lines with the contour lines in the projection image. The distance between the intersection points of different horizontal lines and the contour lines is then calculated, and the horizontal line with the smallest intersection distance is selected as the target horizontal line. Understanding this, the smallest intersection distance indicates the horizontal line is located at the neck position. Therefore, the image below the target horizontal line in the projection image is removed to obtain the first image. Since the initial CTA image is a frontal view of the human body including the head, and subsequent processing only targets the head, it is necessary to determine the neck position and retain the image above the neck while cropping the image below the neck to avoid the influence of other blood vessels below the neck.

[0029] Step S130: Based on the preset brain template image, register the first image at different levels and identify the blood supply brain tissue region to obtain the second image at different levels.

[0030] Specifically, during the acquisition of single-phase CTA images, human or machine factors may cause angular deviations in the final images. Therefore, to improve the accuracy of CTA image data processing, second images at different levels are obtained by registering first images based on a preset brain template image and identifying the blood-supplying brain tissue region. It is understood that the preset brain template image is a standard brain template image obtained based on prior knowledge. More specifically, step S130 also includes the following steps: calculating the rigid transformation value between the brain template image and the first image: applying the rigid transformation value to the brain mask of the brain template to perform a rigid transformation to obtain the second image. A flexible network registration method is selected. ROI annotation is performed on the cranial medical images to be registered; the annotation method is not limited. The specific steps for identifying the blood-supplying brain tissue include: inputting the annotated cranial medical images into a trained CNN network model; accurately registering the input medical image data based on the standard brain region structure map stored in the CNN network; and identifying the MCA blood-supplying brain tissue region after registration. During the registration process, structural features of the cranial medical images can be abstracted through multi-level feature extraction. Furthermore, the second image also includes skull images; if these are not removed, it will affect the accuracy of subsequent CTA image evaluation. Therefore, the skull images in the second image are removed using a neural network, exemplarily a UNet++ neural network or a 3D-UNet neural network. The second image is then filtered at different scales; for example, the Hessian algorithm is used to filter and obtain enhanced vessel signals of different diameters. It should be noted that the filtering process is for vessel segmentation and extraction. The resulting second image is more visually appealing, improving the accuracy of subsequent evaluation.

[0031] Step S140: Identify the ischemic lesion range based on the DWI image as the vascular aggregation range, and map the vascular aggregation range to second images at different levels to obtain third images at different levels;

[0032] Specifically, by acquiring signal regions in DWI images, a mapping relationship is constructed between these signal regions and the blood-supplying brain tissue regions in the second image. Blood-supplying brain tissue regions corresponding to signal regions exceeding a preset value are selected as the vascular aggregation zone range. This vascular aggregation zone range is then drawn and mapped to second images at different levels, resulting in third images at different levels. In other words, combining the mapping results of DWI images and the MCA blood-supplying brain tissue regions yields third images at different levels. Furthermore, this process also includes removing third images where the vascular aggregation zone range is 0. Therefore, the final third image obtained is one containing the vascular aggregation zone range.

[0033] Step S150: Calculate the ratio of the area of ​​the vascular cluster to the area of ​​the healthy side vascular cluster in the third image at different levels.

[0034] Step S160: Calculate and process the mean value based on the ratio and the number of third images, and determine the mean value as the collateral circulation index value of the single-phase CTA image.

[0035] Specifically, after obtaining the third image showing the extent of vascular clusters, the area of ​​the multi-layered vascular cluster region is delineated based on the segmented image. The ratio is obtained by comparing the area of ​​the vascular cluster region with the area of ​​the contralateral vascular cluster region. The ratio for each layer is obtained and the mean is calculated by combining the number of third images. This mean is used as the quantified collateral scoring result, thus providing a more intuitive and accurate assessment of collateral circulation in acute ischemic stroke based on single-phase CTA images. To improve the accuracy of the collateral circulation index values ​​in the final single-phase CTA images, and to enhance generalization ability and robustness, a consistency and correlation comparison test was conducted with the commonly used and well-performing ASPECTS collateral circulation score to calibrate the reliability of the proposed quantitative assessment results.

[0036] The method for determining collateral circulation indices based on single-phase CTA can currently be used for quantitative assessment of collateral circulation in acute ischemic stroke (AIS). Single-phase CTA is widely used in the assessment of collateral circulation in AIS. However, source images and maximum intensity projection (MIP) images are more commonly used. MIP images are relatively more frequently used. They are projected using all pixel values ​​with the highest density in the line of sight of the volumetric data for assessment. This reduces the image from three-dimensional to two-dimensional, which causes overlap of blood vessels and bones, obscuring some blood vessels and easily leading to assessment errors. While multi-phase CTA can obtain CTA images at multiple time points (arterial phase, venous phase, late venous phase), in order to meet the requirements of temporal resolution and whole-brain coverage for multi-phase CTA, the CT scanner detector needs to have a certain width. Currently, high-capacity CT scanners are mainly distributed in large general hospitals and are not widely available. Furthermore, while multi-phase CTA can better assess collateral circulation, the radiation dose increases with each scanning phase. For patients with poor cardiac function, poor pia mater collateral filling can affect the interpretation of multi-phase CTA images. Therefore, this invention employs a multi-task network deep learning model on single-phase CTA images of acute ischemic stroke to segment cerebral vessels in the region of interest. Based on the segmented and labeled vessel images, the areas of concentrated vascular clusters are delineated. The final quantitative score of collateral circulation in acute ischemic stroke is determined by averaging the ratio of the delineated areas on the healthy and affected sides across multiple layers. Unlike previous qualitative and quantitative scoring methods for collateral circulation, the collateral circulation index determination method based on single-phase CTA transforms the complex and cumbersome single-phase CTA collateral circulation scoring scheme into a concrete numerical assessment. It takes into account the spatial distribution characteristics of collateral circulation and directly assesses collateral vessels within the vessel aggregation area, improving generalization ability and robustness. By performing multi-level quantitative assessment of single-phase CTA based on the range of vessel aggregation, maintaining three-dimensional vascular level assessment, it also reduces the time consumed by complex image post-processing steps. For the assessment of collateral circulation in patients with acute ischemic stroke, reducing time costs is a prerequisite for treatment; and it is also user-friendly for less experienced image interpreters.

[0037] A device for assessing collateral circulation in acute ischemic stroke based on single-phase CTA is also disclosed, comprising:

[0038] The first module is used to acquire single-phase CTA images and DWI images;

[0039] The second module is used to preprocess single-phase CTA images to obtain first images at different levels. The first images at different levels are characterized as images projected onto the single-phase CTA images at different distances in the coronal plane.

[0040] The third module is used to register the first image at different levels based on the preset brain template image and identify the blood supply brain tissue area to obtain the second image at different levels.

[0041] The fourth module is used to identify the ischemic lesion range based on the DWI image as the vascular aggregation range, and to map the vascular aggregation range to the second image at different levels to obtain the third image at different levels.

[0042] The fifth module is used to calculate the ratio of the area of ​​the vascular cluster to the area of ​​the vascular cluster on the healthy side for the third image at different levels.

[0043] The sixth module is used to calculate and process the mean value based on the ratio and the number of third images, and to determine the mean value as the collateral circulation index value of the single-phase CTA image.

[0044] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform actions such as... Figure 1 The method.

[0045] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0046] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0047] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0048] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0049] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0050] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0051] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0052] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0053] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for determining the numerical value of the side circulation index based on single-phase CTA, characterized in that, include: Acquire single-phase CTA and DWI images; The single-phase CTA image is preprocessed to obtain first images at different levels. The first images at different levels are characterized as images projected onto the single-phase CTA image at different distances in the coronal plane. Based on a preset brain template image, the first image at different levels is registered and the blood supply brain tissue region is identified to obtain the second image at different levels. The ischemic lesion range is identified based on the DWI image as the vascular aggregation range, and the vascular aggregation range is mapped to the second image at different levels to obtain the third image at different levels. The ratio of the area of ​​the vascular cluster to the area of ​​the vascular cluster on the healthy side is calculated for the third image at different levels. The mean value is calculated based on the ratio and the number of the third images, and the mean value is determined as the collateral circulation index value of the single-phase CTA image.

2. The method for determining the numerical value of the side circulation index based on single-phase CTA according to claim 1, characterized in that, The preprocessing of the single-phase CTA image to obtain first images at different levels includes: The single-phase CTA image is projected onto the coronal plane to obtain a projection image; Intersection points are obtained by intersecting different horizontal lines with the outline lines in the projection drawing; Find two intersection points of the same horizontal line and the outline, and calculate the distance between the two intersection points; Compare the intersection distances corresponding to different horizontal lines, and select the horizontal line with the smallest intersection distance as the target horizontal line; The first image is obtained by removing the image below the target horizontal line in the projection image.

3. The method for determining the numerical value of the side circulation index based on single-phase CTA according to claim 1, characterized in that, The process involves registering the first image at different levels with a preset brain template image and identifying the blood-supplying brain tissue region to obtain second images at different levels, including: Calculate the rigid transformation value between the brain template image and the first image: The second image is obtained by applying rigid transformation values ​​to the brain mask of the brain template.

4. The method for determining the numerical value of the side circulation index based on single-phase CTA according to claim 3, characterized in that, The process involves registering the first image at different levels with a preset brain template image and identifying the blood-supplying brain tissue region to obtain second images at different levels, including: The skull image in the second image is removed using a neural network.

5. The method for determining the numerical value of the side circulation index based on single-phase CTA according to claim 1, characterized in that, The method of registering the first image at different levels and identifying the blood-supplying brain tissue region based on a preset brain template image to obtain second images at different levels also includes: The second image is then filtered at different scales.

6. A processing apparatus for single-phase CTA image data, characterized in that, include: The first module is used to acquire single-phase CTA images and DWI images; The second module is used to preprocess the single-phase CTA image to obtain first images at different levels. The first images at different levels are characterized as images projected onto the single-phase CTA image at different distances in the coronal plane direction. The third module is used to register the first image at different levels based on a preset brain template image and identify the blood supply brain tissue region to obtain the second image at different levels. The fourth module is used to identify the ischemic lesion range based on the DWI image as the vascular aggregation range, and to map the vascular aggregation range to the second image at different levels to obtain the third image at different levels; The fifth module is used to calculate the ratio of the area of ​​the vascular cluster to the area of ​​the vascular cluster on the healthy side for the third image at different levels. The sixth module is used to calculate and process the mean value based on the ratio and the number of the third images, and to determine the mean value as the side circulation index value of the single-phase CTA image.

7. An electronic device, characterized in that, Including the processor and memory; The memory is used to store a program; the processor executes the program to implement the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The storage medium stores a program that is executed by a processor to implement the method as described in any one of claims 1 to 5.

Images