Method for determining morphological parameters of a region of interest and related product

Abstract

The application relates to a method for determining morphological parameters of a region of interest and a related product. The method comprises: performing center line extraction processing on a plurality of first regions of interest in an acquired original image to determine center lines corresponding to the plurality of first regions of interest, performing straightening processing on each two of the center lines respectively, and determining a target straightened image from at least one obtained straightened image, mapping the target straightened image to the original image, and determining morphological parameters corresponding to a second region of interest that overlaps with the plurality of first regions of interest in the original image according to a mapping relationship. The method can realize automatic measurement of an aneurysm without manual measurement, the measurement result is more accurate, and the measurement speed can be improved.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a method for determining morphological parameters of a region of interest and related products. Background Technology

[0002] Intracranial aneurysms are abnormal bulges in intracranial arteries caused by congenital abnormalities or acquired damage to the vessel wall, gradually expanding under hemodynamic load and other factors. Intracranial aneurysms have a high prevalence in the population; many adults currently have them. Rupture of an intracranial aneurysm results in high mortality and disability rates. Therefore, assessing the risk of rupture is crucial, and a key aspect of this is the morphological evaluation of the aneurysm.

[0003] Currently, aneurysm morphological parameters are measured by reconstructing aneurysm images using three-dimensional digital subtraction angiography and manually measuring relevant morphological parameters within the images. However, existing techniques suffer from inaccurate measurement results when determining aneurysm morphological parameters. Summary of the Invention

[0004] Therefore, it is necessary to provide a method and related products for determining the morphological parameters of the region of interest that can accurately measure the morphological parameters of an aneurysm, addressing the aforementioned technical problems.

[0005] Firstly, this application provides a method for determining the morphological parameters of a region of interest. The method includes:

[0006] Centerline extraction is performed on multiple first regions of interest in the acquired original image to determine the centerlines corresponding to the multiple first regions of interest; the original image also includes second regions of interest that overlap with the multiple first regions of interest;

[0007] Straighten each pair of center lines separately, and determine the target straightened image from at least one obtained straightened image;

[0008] The target straightened image is mapped onto the original image, and the morphological parameters corresponding to the second region of interest are determined in the original image.

[0009] In one embodiment, determining the target straightened image corresponding to the original image from at least one obtained straightened image includes:

[0010] Obtain the segmented image corresponding to the straightened image; the segmented image includes a first region of interest and a second region of interest.

[0011] The target straightened image is determined based on the volume of the second region of interest in the segmented image.

[0012] In one embodiment, the morphological parameters of the region of interest include at least one of the following: volume of the second region of interest, longest diameter, neck width, major axis, width, and height.

[0013] In one embodiment, if the morphological parameters of the region of interest include the neck width; mapping the straightened target image onto the original image, and determining the morphological parameters corresponding to the second region of interest in the original image, includes:

[0014] Traverse the segmented image to determine the set of boundary points between the second region of interest and the first region of interest;

[0015] Based on the set of boundary points, determine the target interface between the second region of interest and the first region of interest;

[0016] The target straightened image is mapped onto the original image to obtain the target mapping relationship; the target mapping relationship is used to indicate the correspondence between the pixels of the target straightened image and the pixels of the original image;

[0017] Based on the target interface and target mapping relationship, the neck width corresponding to the second region of interest in the original image is determined; the neck width is used to characterize the maximum width at the junction of the first and second regions of interest on the target interface.

[0018] In one embodiment, determining the neck width corresponding to the second region of interest in the original image based on the target interface and target mapping relationship includes:

[0019] Obtain the coordinates of each boundary point in the target interface based on the straightened target image;

[0020] Based on the coordinates of each boundary point in the target interface and the target mapping relationship, the neck width corresponding to the second region of interest in the original image is determined.

[0021] In one embodiment, determining the target interface between the second region of interest and the first region of interest based on the set of boundary points includes:

[0022] Based on the set of boundary points, determine the initial boundary interface corresponding to the set of boundary points; the initial boundary interface is parallel to one coordinate axis of the coordinate system where the target straightened image is located, and the distance from each point in the set of boundary points to the initial boundary interface is within a preset range;

[0023] Calculate the distance between each point in the boundary point set and the second region of interest in the segmented image, and determine the target boundary based on the obtained multiple distance values.

[0024] In one embodiment, determining the target interface based on multiple obtained distance values ​​includes:

[0025] Find the target distance value among multiple obtained distance values;

[0026] The planar movement range is determined based on the target distance value and the preset movement threshold.

[0027] Within the planar movement range, the initial interface is moved. If the area of ​​the target region of interest is minimized, the target region of interest is taken as the target interface. The target region of interest is the area formed by the initial interface, the first region of interest, and the second region of interest in the segmented image.

[0028] In one embodiment, the morphological parameters of the region of interest further include the major axis, width, and height corresponding to the second region of interest; mapping the straightened image of the target onto the original image, and determining the morphological parameters corresponding to the second region of interest in the original image, further includes:

[0029] The coordinates of points in the second region of interest in the segmented image are obtained based on the target straightened image;

[0030] Based on the coordinates of the points in the second region of interest in the segmented image, the coordinates of each boundary point in the target interface, and the target mapping relationship, the major axis, width, and height of the second region of interest in the original image are determined.

[0031] Secondly, this application also provides an apparatus for measuring morphological parameters of a region of interest. The apparatus includes:

[0032] The centerline extraction module is used to extract centerlines from multiple first regions of interest in the acquired original image and determine the centerlines corresponding to the multiple first regions of interest; wherein, the original image also includes second regions of interest that overlap with the multiple first regions of interest;

[0033] The straightening module is used to straighten each pair of center lines separately, and to determine the target straightened image corresponding to the original image from at least one obtained straightened image;

[0034] The mapping module is used to map the target straightened image onto the original image and determine the morphological parameters corresponding to the second region of interest in the original image.

[0035] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method in any of the embodiments of the first aspect described above.

[0036] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

[0037] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

[0038] The method and related products for determining the morphological parameters of the aforementioned regions of interest (ROIs) involve extracting centerlines from multiple first ROIs in the acquired original image, determining the centerlines corresponding to each ROI, straightening every two centerlines, identifying a target straightened image from at least one straightened image, mapping the target straightened image onto the original image, and determining the morphological parameters of second ROIs that overlap with the multiple first ROIs in the original image based on the mapping relationship. This enables automated measurement of aneurysms without manual intervention, resulting in more accurate measurements and increased measurement speed. Furthermore, analyzing only the aneurysm-bearing vessels further reduces computational load and improves measurement speed. Attached Figure Description

[0039] Figure 1 This is an internal structural diagram of a computer device in one embodiment;

[0040] Figure 2 This is a flowchart illustrating a method for determining the morphological parameters of a region of interest in one embodiment.

[0041] Figure 2-a This is a schematic diagram of image straightening in one embodiment;

[0042] Figure 3 This is a flowchart illustrating a method for determining the morphological parameters of a region of interest in another embodiment;

[0043] Figure 4 This is a flowchart illustrating a method for determining the morphological parameters of a region of interest in another embodiment;

[0044] Figure 5 This is a flowchart illustrating a method for determining the morphological parameters of a region of interest in another embodiment;

[0045] Figure 6 This is a flowchart illustrating a method for determining the morphological parameters of a region of interest in another embodiment;

[0046] Figure 7This is a flowchart illustrating a method for determining the morphological parameters of a region of interest in another embodiment;

[0047] Figure 8 This is a flowchart illustrating a method for determining the morphological parameters of a region of interest in another embodiment;

[0048] Figure 8-a This is a schematic diagram of morphological parameters in one embodiment;

[0049] Figure 9 This is a structural block diagram of a device for determining the morphological parameters of a region of interest in one embodiment. Detailed Implementation

[0050] 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.

[0051] Intracranial aneurysms are abnormal bulges formed by the gradual dilation of intracranial arterial walls due to local damage caused by congenital abnormalities or acquired factors, under hemodynamic load and other influences. The prevalence of intracranial aneurysms is high, ranging from 0.4% to 6% of adults. Rupture of an intracranial aneurysm results in high mortality and disability rates. Therefore, assessing the risk of rupture is crucial, and a key aspect is morphological evaluation. Currently, the gold standard for aneurysm morphological parameters is based on 3D-DSA (three-dimensional digital subtraction angiography) reconstruction, with morphological parameters measured manually from the reconstructed image. However, limitations exist in the measurement results due to factors such as optimal view selection, and the entire process is time-consuming, labor-intensive, and not entirely accurate.

[0052] Based on this, the method for determining the morphological parameters of the region of interest provided in the embodiments of this application can be applied to, for example... Figure 1The computer device shown can be a terminal. The computer device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it performs centerline extraction processing on multiple first regions of interest in the acquired original image, determines the centerlines corresponding to the multiple first regions of interest, straightens every two centerlines, and determines a target straightened image from at least one obtained straightened image; it maps the target straightened image onto the original image and determines the morphological parameters corresponding to a second region of interest in the original image. The display screen of the computer device can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs or touchpads set on the casing of the computer device, or external keyboards, touchpads or mice, etc.

[0053] It should be noted that the method for determining the region of interest provided in this application can be executed by a computed tomography (CT) imaging device or an magnetic resonance imaging (MRI) device. This CT or MRI device can be implemented as part or all of a computer device through software, hardware, or a combination of both. In the following method embodiments, the execution subject is always described using a computer device as an example.

[0054] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0055] In one embodiment, such as Figure 2 As shown, a method for determining the morphological parameters of a region of interest is provided, which can be applied to... Figure 1 Taking a computer device as an example, the explanation includes the following steps:

[0056] S202, perform centerline extraction processing on multiple first regions of interest in the acquired original image to determine the centerlines corresponding to the multiple first regions of interest; wherein, the original image also includes second regions of interest that overlap with the multiple first regions of interest.

[0057] The original image is obtained by capturing the target area of ​​the object using a CT or MR imaging device. The first region of interest is the area of ​​the carrier vessel of the aneurysm. The second region of interest is the area of ​​the aneurysm. The target location can include the head, legs, etc., and is not limited thereto.

[0058] Specifically, the original image can be input into a pre-defined aneurysm detection model, which outputs the aneurysm's location information within the original image. Based on this location information, a portion of the aneurysm can be extracted from the original image. The aneurysm's location information may include the coordinates of its center point, its length, width, and height. The extracted aneurysm portion may include the aneurysm region and the overlapping carrier vessel region.

[0059] Based on the image of the extracted aneurysm portion, the center line can be manually marked by the operator in the first region of interest (ROI) within the image of the extracted aneurysm portion. Alternatively, a traversal algorithm can be used to iterate through each point in the image of the extracted aneurysm portion to extract the center lines of multiple second ROIs (i.e., the carrier vessel of the aneurysm).

[0060] S204, straighten each pair of center lines separately, and determine the target straightened image from at least one obtained straightened image.

[0061] Specifically, the curvature of each pair of center lines can be calculated using the curvature calculation formula. For each center line, sampling points need to be set based on the curvature of each point on the center line; the greater the curvature, the more sampling points are set. For each sampling point, the direction vector of each sampling point is calculated. This can be done by subtracting the values ​​of adjacent sampling points; for sampling points at both ends, the vector of each sampling point can be obtained by calculating the difference between the sampling point and its adjacent points. Based on each sampling point and its direction vector, the normal plane corresponding to each sampling point can be determined. Based on the coordinates of each point on the normal plane corresponding to each sampling point, the corresponding coordinates in the original image are found, and the coordinates in the original image are interpolated using a preset resampling algorithm. This yields the points on the normal plane corresponding to each sampling point that correspond to the points on the normal plane in the original image, thus forming the target normal planes of the original image. The world coordinates of each point on the target normal plane are recorded. By superimposing the target normal planes along the Z-axis and aligning the sampling points, the straightened image corresponding to each pair of center lines can be obtained, such as... Figure 2-a As shown. Based on multiple straightened images, the image with the largest aneurysm volume among the multiple straightened images can be used as the target straightened image.

[0062] S206, map the straightened target image onto the original image, and determine the morphological parameters corresponding to the second region of interest in the original image.

[0063] Specifically, the coordinates of each point in the determined target straightened image are mapped to the original image to obtain the mapping relationship between the coordinates. Based on the coordinates of the aneurysm in the target straightened image, the coordinate information of the aneurysm in the original image can be determined using the mapping relationship, and then the corresponding morphological parameters of the aneurysm can be calculated.

[0064] Furthermore, in the process of determining morphological parameters, it is also necessary to determine the aneurysm neck plane based on the interface between the first region of interest and the second region of interest in the straightened image, and then determine the relevant morphological parameters based on the aneurysm neck plane.

[0065] Optionally, the morphological parameters of the region of interest include at least one of the following: volume, longest diameter, neck width, major axis, width, and height of the second region of interest.

[0066] The longest diameter can be determined based on the maximum distance between any two voxel points on the aneurysm surface. The neck width can be determined based on the maximum distance between any two voxel points on the aneurysm neck plane boundary. The major diameter is determined based on the maximum distance from a voxel point on the aneurysm surface to the center point of the neck plane. The width is determined based on the maximum distance between any two voxel points on the aneurysm surface that are perpendicular to the major diameter. The height is determined based on the maximum vertical distance from a voxel point on the aneurysm surface to the neck plane.

[0067] In the aforementioned method for determining the morphological parameters of regions of interest, centerline extraction is performed on multiple first regions of interest in the acquired original image to determine the corresponding centerlines. Each pair of centerlines is then straightened, and a target straightened image is determined from at least one straightened image. This target straightened image is mapped onto the original image, and the morphological parameters corresponding to second regions of interest overlapping with the multiple first regions of interest are determined in the original image based on the mapping relationship. This method enables automated measurement of aneurysms without manual intervention, resulting in more accurate measurements and increased measurement speed. Analyzing only the aneurysm-bearing vessels further reduces computational load and improves measurement speed. Simultaneously, straightening the vessels and calculating morphological parameters based on the straightened vessels makes the morphological parameters more accurate and robust.

[0068] The above embodiments illustrate a method for determining morphological parameters of a region of interest. The most crucial aspect of this method is acquiring a straightened image. Since each pair of blood vessels will produce a straightened image, determining the target straightened image is particularly critical. An embodiment will be used to illustrate this. In one embodiment, such as... Figure 3 As shown, determining the target straightened image corresponding to the original image from at least one obtained straightened image includes:

[0069] S302, Obtain the segmented image corresponding to the straightened image; the segmented image includes a first region of interest and a second region of interest.

[0070] Specifically, each straightened image can be input into a preset segmentation neural network model to obtain a corresponding segmented image including a first region of interest and a second region of interest. This segmented image can be a ternary mask image; pixel 0 represents the background, pixel 1 represents the second region of interest, and pixel 2 represents the first region of interest.

[0071] S303, determine the target straightened image based on the volume of the second region of interest in the segmented image.

[0072] Specifically, based on each segmented image, the straightened image corresponding to the segmented image with the largest second region of interest is selected as the target straightened image.

[0073] In this embodiment, a segmented image corresponding to the straightened image is obtained. The segmented image includes a first region of interest and a second region of interest. The target straightened image is determined based on the volume of the second region of interest in the segmented image. The straightened image with the most information points can be determined as the target segmented image so as to obtain more accurate morphological parameters in subsequent calculations.

[0074] The above embodiments illustrate how to determine the target straightened image. Now, an embodiment will be used to illustrate how to determine morphological parameters. In one embodiment, such as... Figure 4 As shown, if the morphological parameters of the region of interest include the neck width; the target straightened image is mapped onto the original image, and the morphological parameters corresponding to the second region of interest are determined in the original image, including:

[0075] S402, traverse the segmented image and determine the set of boundary points between the second region of interest and the first region of interest.

[0076] S404, Based on the set of boundary points, determine the target interface between the second region of interest and the first region of interest.

[0077] S406, Map the target straightened image to the original image to obtain the target mapping relationship; the target mapping relationship is used to indicate the correspondence between the pixels of the target straightened image and the pixels of the original image.

[0078] S408, determine the neck width corresponding to the second region of interest in the original image based on the target interface and the target mapping relationship; the neck width is used to characterize the maximum width at the junction of the first region of interest and the second region of interest on the target interface.

[0079] Specifically, if the pixel of the second region of interest (ROI) is 1 and the pixel of the background is 0, the pixels of the ROI in the segmented image are traversed. If the pixel of the neighborhood is 2, then this pixel is determined as the boundary point set P of the ROI and the first ROI. Based on the boundary point set P and a preset planar formula, the target interface is determined. The target straightened image is mapped onto the original image to obtain the correspondence between the pixels of the target straightened image and the pixels of the original image. Based on the target mapping relationship, the position coordinates of the target interface in the straightened image in the original image can be determined. And based on the target interface corresponding to the second ROI in the original image, the maximum distance between any two voxel points on the boundary of the target interface is determined, which is the neck width. The target interface can be the neck plane.

[0080] In this embodiment, by traversing the segmented image, the set of boundary points between the second region of interest (ROI) and the first ROI is determined. Based on the boundary point set, the target interface between the second ROI and the first ROI is determined. The straightened target image is then mapped onto the original image to obtain the target mapping relationship. Based on the target interface and the target mapping relationship, the neck width corresponding to the second ROI in the original image is determined. This allows for the accurate determination of the morphological parameter neck width based on the correspondence between the straightened target image and the original image.

[0081] Furthermore, in one embodiment, such as Figure 5As shown, based on the target interface and target mapping relationship, the width of the tumor neck corresponding to the second region of interest in the original image is determined, including:

[0082] S502, obtain the coordinates of each boundary point in the target interface based on the straightened target image.

[0083] Specifically, since the target interface is obtained based on the target straightened image, the coordinates of the target interface can be directly determined based on the coordinates of each pixel in the target straightened image.

[0084] S504. Based on the coordinates of each boundary point in the target interface and the target mapping relationship, determine the neck width corresponding to the second region of interest in the original image.

[0085] Specifically, once the coordinates of each boundary point in the target interface and the target mapping relationship are determined, the coordinates of each pixel point of the corresponding target interface in the original image can be determined. Then, the maximum distance between any two pixels on the target interface boundary is taken as the neck width.

[0086] In this embodiment, the coordinates of each boundary point in the target interface are obtained based on the straightened target image. Based on the coordinates of each boundary point in the target interface and the target mapping relationship, the neck width corresponding to the second region of interest in the original image is determined. The neck width, a morphological parameter of the original image, is then determined based on the straightened image. Straightening the blood vessel and calculating its morphological parameters based on the straightened vessel makes the morphological parameters more accurate and robust.

[0087] The above embodiments illustrate how to determine the neck width. When determining the neck width, it is necessary to first determine the target interface. An embodiment will now be used to illustrate how to determine the target interface. In one embodiment, such as... Figure 6 As shown, based on the set of boundary points, the target interface between the second region of interest and the first region of interest is determined, including:

[0088] S602, Based on the set of boundary points, determine the initial boundary interface corresponding to the set of boundary points; the initial boundary interface is parallel to one coordinate axis of the coordinate system where the target straightened image is located, and the distance from each point in the set of boundary points to the initial boundary interface is within a preset range.

[0089] S604, calculate the distance between each point in the boundary point set and the second region of interest in the segmented image, and determine the target boundary based on the obtained multiple distance values.

[0090] Specifically, the initial interface plane0 can be determined based on the boundary point set P and a preset plane formula. This initial interface must be parallel to the z-axis of the coordinate system in the target straightened image, and the sum of the distances from the boundary point set P to this plane must be less than a preset range. The preset plane formula can be a three-dimensional plane formula; for example, Ax + By + Cz + D = 0, where x, y, and z are the coordinates of points on the plane, and A, B, C, and D are parameters to be determined. Because they are parallel to the z-axis, the formula can be simplified to Ax + By + D = 0. The distances from the boundary point set to each point in the second region of interest (ROI) in the segmented image are calculated. Among these distances, the maximum distance d from the initial interface to the second ROI is determined. The initial interface is moved back and forth within the range of 0-0.2d along a direction perpendicular to it. When the initial interface intersects both the first and second ROIs, and the area of ​​the intersecting plane is minimized, this intersecting interface is the desired target interface.

[0091] Furthermore, in one embodiment, such as Figure 7 As shown, the target interface is determined based on multiple distance values ​​obtained, including:

[0092] S702, find the target distance value among the obtained multiple distance values;

[0093] S704, Determine the planar movement range based on the target distance value and the preset movement threshold;

[0094] S706, move the initial interface within the planar movement range. If the area of ​​the target region of interest is minimized, the target region of interest is taken as the target interface. The target region of interest is the area formed by the initial interface, the first region of interest, and the second region of interest in the segmented image.

[0095] The target distance value is a distance value determined according to a preset rule. For example, the preset rule is to use the maximum distance value among multiple distance values ​​as the target distance value.

[0096] Specifically, a target distance value is selected from multiple distance values ​​according to a preset rule. The target distance value can be used as the upper limit of the planar movement range, i.e., the maximum value of the preset distance threshold, with 0 as the lower limit. Alternatively, the target distance value ± the preset movement threshold can be used, and the calculated result is taken as the planar movement range; no restrictions are imposed here. Within the planar movement range, the initial interface is moved. If the area of ​​the target region of interest is minimized, the target region of interest is taken as the target interface; where the target region of interest is the area formed by the initial interface, the first region of interest, and the second region of interest in the segmented image.

[0097] In this embodiment, an initial boundary interface is determined based on the boundary point set. The distance between each point in the boundary point set and the second region of interest in the segmented image is calculated, and the target boundary interface is determined based on the obtained multiple distance values. After determining the maximum range of movement of the initial boundary interface, the target boundary interface can be further determined. That is, the determined target boundary interface will not exceed the preset error range, resulting in a more accurate target boundary interface, which further provides a basis for subsequently determining accurate morphological parameters.

[0098] The above embodiments illustrate how to determine the target interface. Now, an embodiment will be used to further illustrate how to determine other morphological parameters. In one embodiment, such as... Figure 8 As shown, if the morphological parameters of the region of interest also include the major axis, width, and height corresponding to the second region of interest; mapping the straightened image of the target onto the original image, and determining the morphological parameters corresponding to the second region of interest in the original image, further includes:

[0099] S802, obtain the coordinates of the points in the second region of interest in the segmented image based on the straightened target image.

[0100] S804, based on the coordinates of the points in the second region of interest in the segmented image, the coordinates of each boundary point in the target interface, and the target mapping relationship, determine the major axis, width, and height of the second region of interest in the original image.

[0101] Specifically, since the image segmentation is based on the target straightened image, the coordinates of the points in the second region of interest (ROI) of the segmented image are the same as the coordinates of the points in the second ROI of the target straightened image. Based on the coordinates of the points in the second ROI of the segmented image, the coordinates of each boundary point in the target interface, and the target mapping relationship, the coordinates of the points in the second ROI of the original image and the coordinates of each boundary point in the target interface are determined. The maximum distance from a point in the second ROI to the center point of the target interface is taken as the major axis. The maximum distance between any two points in the second ROI perpendicular to the major axis is taken as the width. The maximum perpendicular distance from a point in the second ROI to the target interface is taken as the height. (See also...) Figure 8-a .

[0102] Optionally, the morphological parameters also include the longest diameter, which can be mapped from the second region of interest in the target straightening image to the second region of interest in the original image, and the maximum distance between any two points of various second regions of interest in the original image is taken as the longest diameter.

[0103] In this embodiment, the coordinates of points in the second region of interest (ROI) in the segmented image are obtained based on the target straightened image. Then, based on the coordinates of the ROI points, the coordinates of each boundary point in the target interface, and the target mapping relationship, the major axis, width, and height of the ROI in the original image are determined. This allows for accurate determination of different morphological parameters based on the target straightened image.

[0104] To facilitate understanding by those skilled in the art, a method for determining the morphological parameters of a region of interest is further described below with reference to an embodiment. In one embodiment, the method for determining the morphological parameters of a region of interest includes:

[0105] S10, perform centerline extraction processing on multiple first regions of interest in the acquired original image to determine the centerlines corresponding to the multiple first regions of interest; wherein, the original image also includes second regions of interest that overlap with the multiple first regions of interest.

[0106] S20, straighten each pair of center lines separately.

[0107] S30, Obtain the segmented image corresponding to the straightened image; the segmented image includes a first region of interest and a second region of interest.

[0108] S40, determine the target straightened image based on the volume of the second region of interest in the segmented image.

[0109] S50: Traverse the segmented image and determine the set of boundary points between the second region of interest and the first region of interest.

[0110] S60, Based on the set of boundary points, determine the initial boundary interface corresponding to the set of boundary points; the initial boundary interface is parallel to one coordinate axis of the coordinate system where the target straightened image is located, and the distance from each point in the set of boundary points to the initial boundary interface is within a preset range.

[0111] S70, calculate the distance between each point in the boundary point set and the second region of interest in the segmented image.

[0112] S80: Find the target distance value among the multiple obtained distance values, and determine the planar movement range based on the target distance value and the preset movement threshold.

[0113] S90, move the initial interface within the planar movement range. If the area of ​​the target region of interest is minimized, the target region of interest is taken as the target interface. The target region of interest is the area formed by the initial interface, the first region of interest, and the second region of interest in the segmented image.

[0114] S100, map the target straightened image onto the original image to obtain the target mapping relationship; the target mapping relationship is used to indicate the correspondence between the pixels of the target straightened image and the pixels of the original image.

[0115] S110, obtain the coordinates of each boundary point in the target interface based on the straightened target image.

[0116] S120, based on the coordinates of each boundary point in the target interface and the target mapping relationship, determine the neck width corresponding to the second region of interest in the original image; the neck width is used to characterize the maximum width at the boundary between the first region of interest and the second region of interest on the target interface.

[0117] S130: Obtain the coordinates of the points in the second region of interest in the segmented image based on the straightened target image.

[0118] S140, based on the coordinates of the points in the second region of interest in the segmented image, the coordinates of each boundary point in the target interface, and the target mapping relationship, determine the major axis, width, and height of the second region of interest in the original image.

[0119] In this embodiment, by extracting centerlines from multiple first regions of interest (ROIs) in the acquired original image, centerlines corresponding to these ROIs are determined. Each pair of centerlines is then straightened, and a target straightened image is identified from at least one straightened image. This target straightened image is mapped onto the original image, and morphological parameters corresponding to second regions of interest that overlap with the multiple ROIs are determined in the original image based on the mapping relationship. This enables automated aneurysm measurement without manual intervention, resulting in more accurate measurements and increased measurement speed. Analyzing only the aneurysm-bearing vessels further reduces computational load and improves measurement speed. Simultaneously, straightening the vessels and calculating morphological parameters based on the straightened vessels makes the morphological parameters more accurate and robust.

[0120] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0121] Based on the same inventive concept, this application also provides an apparatus for determining the morphological parameters of a region of interest (ROI) to implement the method for determining morphological parameters of a ROI as described above. The solution provided by this apparatus is similar to the solution described in the above method. Therefore, the specific limitations in the embodiments of the apparatus for determining morphological parameters of one or more ROIs provided below can be found in the limitations of the method for determining morphological parameters of a ROI described above, and will not be repeated here.

[0122] In one embodiment, such as Figure 9 As shown, an apparatus for determining morphological parameters of a region of interest is provided, comprising:

[0123] The centerline extraction module 901 is used to perform centerline extraction processing on multiple first regions of interest in the acquired original image to determine the centerlines corresponding to the multiple first regions of interest; wherein, the original image also includes second regions of interest that overlap with the multiple first regions of interest;

[0124] The straightening module 902 is used to straighten each pair of center lines in each center line separately, and to determine the target straightened image corresponding to the original image from at least one obtained straightened image;

[0125] The mapping module 903 is used to map the target straightened image onto the original image and determine the morphological parameters corresponding to the second region of interest in the original image.

[0126] Optionally, the morphological parameters of the region of interest include at least one of the following: volume, longest diameter, neck width, major axis, width, and height of the second region of interest.

[0127] The apparatus for determining the morphological parameters of the region of interest provided in this embodiment can execute the above-described method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.

[0128] In one embodiment, the straightening module includes:

[0129] The acquisition unit is used to acquire the segmented image corresponding to the straightened image; the segmented image includes a first region of interest and a second region of interest.

[0130] The first determining unit is used to determine the target straightened image based on the volume of the second region of interest in the segmented image.

[0131] In one embodiment, if the morphological parameters of the region of interest include the neck width, the mapping module includes:

[0132] The traversal unit is used to traverse the segmented image and determine the set of boundary points between the second region of interest and the first region of interest.

[0133] The second determining unit is used to determine the target interface between the second region of interest and the first region of interest based on the set of boundary points;

[0134] The mapping unit is used to map the target straightened image onto the original image to obtain the target mapping relationship; the target mapping relationship is used to indicate the correspondence between the pixels of the target straightened image and the pixels of the original image;

[0135] The third determining unit is used to determine the neck width corresponding to the second region of interest in the original image based on the target interface and the target mapping relationship; the neck width is used to characterize the maximum width at the junction of the first region of interest and the second region of interest on the target interface.

[0136] In one embodiment, the third determining unit is specifically used to obtain the coordinates of each boundary point in the target interface based on the target straightened image; and to determine the neck width corresponding to the second region of interest in the original image based on the coordinates of each boundary point in the target interface and the target mapping relationship.

[0137] In one embodiment, the second determining unit is specifically used to determine the initial interface corresponding to the boundary point set based on the boundary point set; the initial interface is parallel to one coordinate axis of the coordinate system where the target straightened image is located, and the distance from each point in the boundary point set to the initial interface is within a preset range; calculate the distance between each point in the boundary point set and the second region of interest in the segmented image, and determine the target interface based on the obtained multiple distance values.

[0138] In one embodiment, the second determining unit is specifically used to find the target distance value among the multiple distance values ​​obtained; determine the planar movement range according to the target distance value and a preset movement threshold; move the initial interface within the planar movement range; and if the area of ​​the target region of interest is the smallest, take the target region of interest as the target interface; wherein, the target region of interest is the region formed by the initial interface and the first region of interest and the second region of interest in the segmented image.

[0139] In one embodiment, if the morphological parameters of the region of interest further include the major axis, width, and height corresponding to the second region of interest, the mapping module further includes:

[0140] The second acquisition module is used to acquire the coordinates of points in the second region of interest in the segmented image based on the target straightened image;

[0141] The second mapping module is used to determine the major axis, width, and height of the second region of interest in the original image based on the coordinates of the points in the second region of interest in the segmented image, the coordinates of each boundary point in the target interface, and the target mapping relationship.

[0142] The apparatus for determining the morphological parameters of the region of interest provided in this embodiment can execute the above-described method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.

[0143] Each module in the device for determining the morphological parameters of the aforementioned region of interest can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0144] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method in any of the above embodiments.

[0145] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method in any of the above embodiments.

[0146] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method in any of the above embodiments.

[0147] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0148] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0149] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0150] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining morphological parameters of a region of interest, characterized in that, The method includes: Centerline extraction is performed on multiple first regions of interest in the acquired original image to determine the centerlines corresponding to the multiple first regions of interest; wherein, the original image also includes second regions of interest that overlap with the multiple first regions of interest; Each pair of center lines is straightened, and a target straightened image is determined from at least one obtained straightened image. Traverse the segmented image corresponding to the straightened image, determine the set of boundary points between the second region of interest and the first region of interest, determine the initial interface corresponding to the boundary point set based on the boundary point set, calculate the distance between each point in the boundary point set and the second region of interest in the segmented image, determine the target interface based on the obtained multiple distance values, map the target straightened image onto the original image, and determine the morphological parameters corresponding to the second region of interest in the original image based on the target interface. The initial interface is parallel to one coordinate axis of the coordinate system where the target straightened image is located, and the distance from each point in the set of intersection points to the initial interface is within a preset range.

2. The method according to claim 1, characterized in that, Determining the target straightened image corresponding to the original image from at least one obtained straightened image includes: Obtain the segmented image corresponding to the straightened image; the segmented image includes the first region of interest and the second region of interest; The target straightened image is determined based on the volume of the second region of interest in the segmented image.

3. The method according to claim 2, characterized in that, The morphological parameters of the region of interest include at least one of the following: volume, longest diameter, neck width, major axis, width, and height of the second region of interest.

4. The method according to claim 3, characterized in that, If the morphological parameters of the region of interest include the neck width; the step of mapping the straightened image of the target onto the original image, and determining the morphological parameters corresponding to the second region of interest in the original image based on the target interface, includes: The target straightened image is mapped onto the original image to obtain a target mapping relationship; the target mapping relationship is used to indicate the correspondence between the pixels of the target straightened image and the pixels of the original image; Based on the target interface and the target mapping relationship, the neck width corresponding to the second region of interest in the original image is determined; the neck width is used to characterize the maximum width at the boundary between the first region of interest and the second region of interest on the target interface.

5. The method according to claim 4, characterized in that, The step of determining the neck width corresponding to the second region of interest in the original image based on the target interface and the target mapping relationship includes: Based on the straightened image of the target, obtain the coordinates of each boundary point in the target interface; Based on the coordinates of each boundary point in the target interface and the target mapping relationship, the neck width corresponding to the second region of interest in the original image is determined.

6. The method according to claim 1, characterized in that, Determining the target interface based on multiple obtained distance values ​​includes: Find the target distance value among the obtained multiple distance values; The planar movement range is determined based on the target distance value and the preset movement threshold. The initial interface is moved within the plane movement range. If the area of ​​the target region of interest is minimized, the target region of interest is taken as the target interface. The target region of interest is the area formed by the initial interface, the first region of interest, and the second region of interest in the segmented image.

7. The method according to claim 5, characterized in that, If the morphological parameters of the region of interest further include the major axis, width, and height corresponding to the second region of interest; the step of mapping the straightened image of the target onto the original image, and determining the morphological parameters corresponding to the second region of interest in the original image based on the target interface, further includes: Based on the target straightened image, obtain the coordinates of the points in the second region of interest in the segmented image; Based on the coordinates of the points in the second region of interest in the segmented image, the coordinates of each boundary point in the target interface, and the target mapping relationship, the major axis, width, and height of the second region of interest in the original image are determined.

8. The method according to claim 6, characterized in that, The target distance value is a distance value determined according to a preset rule.

9. A device for determining morphological parameters of a region of interest, characterized in that, The device includes: The centerline extraction module is used to perform centerline extraction processing on multiple first regions of interest in the acquired original image to determine the centerlines corresponding to the multiple first regions of interest; wherein, the original image also includes second regions of interest that overlap with the multiple first regions of interest; The straightening module is used to straighten each pair of center lines in each of the center lines, and to determine the target straightened image corresponding to the original image from at least one obtained straightened image; The mapping module is used to traverse the segmented image corresponding to the straightened image, determine the set of boundary points between the second region of interest and the first region of interest, determine the initial interface corresponding to the boundary point set based on the boundary point set, calculate the distance between each point in the boundary point set and the second region of interest in the segmented image, determine the target interface based on the obtained multiple distance values, map the target straightened image to the original image, and determine the morphological parameters corresponding to the second region of interest in the original image based on the target interface. The initial interface is parallel to one coordinate axis of the coordinate system where the target straightened image is located, and the distance from each point in the set of intersection points to the initial interface is within a preset range.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8.

Images