Method for detecting aortic dissection rupture position, electronic device and storage medium

Abstract

This invention provides a method, electronic device, and storage medium for detecting the location of aortic dissection ruptures. Based on an image of the aorta to be detected and its true and false lumen mask images, a first search starting layer is determined according to a first search rule. Then, based on the first search starting layer and the true and false lumen mask images, the location of the aortic dissection rupture is calculated according to a second search rule. The method, electronic device, and storage medium provided by this invention can improve the detection efficiency and accuracy of aortic dissection rupture locations. Furthermore, the algorithm is simple, efficient, and has strong generalization ability, achieving fully automated detection of aortic dissection rupture locations, and is easy to implement. In addition, the method provided by this invention can determine a second search starting layer and the aortic arch location according to a third search rule, and calculate the rupture initiation location of the aortic dissection according to the second search rule, further improving accuracy.

Description

Technical Field

[0001] This invention relates to the field of medical image processing technology, and in particular to a method, electronic device and storage medium for detecting the location of aortic dissection rupture. Background Technology

[0002] Aortic dissection is a high-risk aortic vascular disease with a high mortality rate. Its pathological feature is a partial tear in the inner wall of the aorta, through which blood enters and divides the vessel into a true lumen and a false lumen. Therefore, identifying the location of the tear is a decisive factor for the success of vascular repair, especially for patients scheduled for endovascular stent grafting.

[0003] There are two main existing methods for locating aortic dissection ruptures: one relies on manual marking by doctors based on CTA images, which requires a certain level of experience and skill from the doctor and is relatively inefficient. The other is a computer-automated detection method for aortic dissection rupture locations. While this method can significantly reduce diagnostic time and allow for rapid selection of appropriate surgical options for timely treatment, each method has its own limitations based on its underlying principles, which are listed below:

[0004] 1. Existing detection methods have weak generalization ability and cannot determine the starting position of the breach, resulting in low detection efficiency.

[0005] 2. The addition of methods other than images has increased the uncertainty of the detection results, affecting the accuracy of location detection.

[0006] Therefore, how to provide a method for detecting the location of aortic dissection rupture with strong generalization ability, so as to improve the detection efficiency and accuracy of aortic dissection rupture location, is one of the technical problems that urgently need to be solved by those skilled in the art.

[0007] It should be noted that the information disclosed in the background section of this invention is intended only to enhance the understanding of the general background of this invention, and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0008] The purpose of this invention is to address the aforementioned deficiencies in the prior art by providing a method, electronic device, and storage medium for detecting the location of aortic dissection ruptures, thereby improving the detection efficiency and accuracy of aortic dissection rupture locations.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a method for detecting the location of an aortic dissection rupture, comprising:

[0010] Based on the aortic image to be detected and the true and false lumen mask images of the aortic image, the first search starting layer is determined according to the first search rule;

[0011] Based on the first search starting layer and the true and false cavity mask images, the location of the aortic dissection rupture is calculated according to the second search rule.

[0012] Optionally, calculating the location of the aortic dissection rupture further includes:

[0013] Based on the aortic image and the true and false lumen mask images, the second search starting layer and the location of the aortic arch are determined according to the third search rule;

[0014] Based on the second search starting layer and the location of the aortic arch, the initiation position of the aortic dissection is calculated according to the fourth search rule.

[0015] Optionally, determining the second search starting layer according to the aortic image and the true / false lumen mask image, and following a third search rule, includes:

[0016] Based on the false lumen region in the true and false lumen mask image, calculate the length of the false lumen region along the aortic extension direction;

[0017] Based on the true and false cavity mask images and the length, the position of the false cavity region at the first preset length ratio is calculated by traversing along the head to the lower limb direction;

[0018] The cross-section of the aortic image at that location is used as the second search starting layer.

[0019] Optionally, determining the aortic arch location based on the aortic image and the true / false lumen mask image according to a third search rule includes:

[0020] Starting from the second search starting layer, traverse layer by layer along the lower limb towards the head, and obtain the area of ​​the aortic image in each cross section based on the true and false cavity mask images;

[0021] Based on the area of ​​each cross-section, select the cross-section with the largest area in the aortic image;

[0022] The aortic arch is located in the N layers above and below the largest cross-section of the aortic image; N is a first preset threshold and is a positive integer.

[0023] Optionally, the step of calculating the initiation location of the aortic dissection tear according to the second search initiation layer and the aortic arch location, and in accordance with the fourth search rule, includes:

[0024] Step A1: Obtain the maximum connected region area and center coordinates of the false cavity region in the second search starting layer; and use the center coordinates as the seed point, and use the second search starting layer as the first current search layer;

[0025] Step A2: Based on the pixel values ​​of the seed points and the preset adjustment factor, the segmentation result of the false lumen region in the next search layer is obtained by the adaptive region growing method; and based on the segmentation result, the maximum connected region area and center coordinates of the false lumen region in the next search layer are obtained; wherein, the next search layer is the cross-section of the aortic image that is adjacent to the first current search layer and close to the head direction;

[0026] Step A3: Determine whether the first preset search termination condition is met. If yes, proceed to step A4. If no, use the center coordinates of the next search layer as the seed point, use the next search layer as the first current search layer, and proceed to step A2. The first preset search termination condition includes the ratio of the maximum connected region area of ​​the next search layer to the maximum connected region area of ​​the first current search layer exceeding the second preset threshold and the next search layer being located at the aortic arch.

[0027] Step A4: Calculate the starting position of the aortic dissection rupture based on the coordinates of the seed point.

[0028] Optionally, before obtaining the segmentation result of the pseudo-cavity region in the next search layer using an adaptive region growing method based on the pixel value of the seed point and a preset adjustment factor, the method further includes:

[0029] Based on the true and false lumen mask images, the false lumen ROI image is extracted from the aortic image;

[0030] The step of obtaining the maximum connected region area and center coordinates of the pseudo-cavity region in the second search starting layer includes:

[0031] Based on the pseudo-cavity ROI image, obtain the maximum connected region area and center coordinates of the pseudo-cavity region in the second search starting layer.

[0032] Optionally, the step of obtaining the segmentation result of the pseudo-cavity region in the next search layer using an adaptive region growing method based on the pixel value of the seed point and a preset adjustment factor includes:

[0033] Calculate the low threshold pixel value and the high threshold pixel value based on the pixel value of the seed point and the adjustment factor;

[0034] Based on the low threshold pixel value and the high threshold pixel value, an adaptive region growing method is used to obtain the segmentation result of the pseudo-cavity region in the next search layer.

[0035] Optionally,

[0036] The step of calculating the low-threshold pixel value and the high-threshold pixel value based on the pixel value of the seed point and the adjustment factor includes calculating the high-threshold pixel value and the low-threshold pixel value respectively using the following formulas:

[0037]

[0038]

[0039] In the formula, The low threshold pixel value, The high threshold pixel value, The pixel value of the seed point. The regulating factor is mentioned above.

[0040] Optionally, determining the first search starting layer according to the aortic image to be detected and the true and false lumen mask images of the aortic image, according to the first search rule, includes:

[0041] Based on the true and false lumen mask images, calculate the length of the false lumen region along the aortic extension direction;

[0042] Based on the true and false cavity mask images and the length, the position of the false cavity region at the second preset length ratio is calculated;

[0043] The cross-section of the aortic image at that location is determined as the first search starting layer.

[0044] Optionally, calculating the location of the aortic dissection tear based on the first search starting layer and the true / false lumen mask image, according to the second search rule, includes:

[0045] Step B1: Obtain the maximum connected component of the false cavity, the center coordinates of the false cavity, the maximum connected component of the true cavity, and the center coordinates of the true cavity in the first search starting layer, respectively; and use the center coordinates of the false cavity as the seed point of the false cavity and the center coordinates of the true cavity as the seed point of the true cavity, and use the first search starting layer as the second current search layer;

[0046] Step B2: Based on the false lumen seed point and the true lumen seed point, take the second current search layer as the starting search layer, and search layer by layer along the lower limb towards the head and the head towards the lower limb, until the false lumen region is reached in the starting cross section and the ending cross section of the aortic image, and obtain the maximum connected region of the false lumen and the maximum connected region of the true lumen in each search layer.

[0047] Step B3: Determine whether the maximum connected region of the false lumen and the maximum connected region of the true lumen in each search layer are the same connected region. If so, determine the position of the aortic dissection in the middle of the rupture in the search layer according to the center coordinates of the false lumen and the center coordinates of the true lumen in the search layer, and according to the preset dissection rupture position calculation rules.

[0048] Step B4: Merge the midpoints of the ruptures in each search layer to obtain the midpoint of the rupture in the aortic dissection.

[0049] Optionally, the step of searching layer by layer from the lower limb toward the head, based on the false cavity seed point and the true cavity seed point, using the second current search layer as the starting search layer, includes:

[0050] B211: Using an adaptive region growing method, based on the pixel values ​​of the false lumen seed points and a preset adjustment factor, the false lumen segmentation result of the false lumen region in the next head search layer is obtained. Based on the false lumen segmentation result, the maximum connected component of the false lumen region and the coordinates of the false lumen center in the next head search layer are obtained. Based on the pixel values ​​of the true lumen seed points and a preset adjustment factor, the true lumen segmentation result of the true lumen region in the next head search layer is obtained. Based on the true lumen segmentation result, the maximum connected component of the true lumen region and the coordinates of the true lumen center in the next head search layer are obtained. Wherein, the next head search layer is a cross-section of the aortic image adjacent to the second current search layer and close to the head direction.

[0051] B212: Determine whether the next head search layer is the starting cross section where the false cavity region is located. If yes, stop the search; if no, use the false cavity center coordinates of the next head search layer as the false cavity seed point, use the true cavity center coordinates of the next head search layer as the true cavity seed point, use the next head search layer as the second current search layer, and execute step B211.

[0052] Optionally, the step of searching layer by layer from the head to the lower limbs based on the false cavity seed point and the true cavity seed point, using the second current search layer as the starting search layer, includes:

[0053] B221: Using an adaptive region growing method, based on the pixel values ​​of the false lumen seed points and a preset adjustment factor, the false lumen segmentation result of the false lumen region in the next lower limb search layer is obtained. Based on the false lumen segmentation result, the maximum connected component and the center coordinates of the false lumen region in the next lower limb search layer are obtained. Based on the pixel values ​​of the true lumen seed points and a preset adjustment factor, the true lumen segmentation result of the true lumen region in the next lower limb search layer is obtained. Based on the true lumen segmentation result, the maximum connected component and the center coordinates of the true lumen region in the next lower limb search layer are obtained. The next lower limb search layer is a cross-section of the aortic image adjacent to the second current search layer and close to the lower limb direction.

[0054] B222: Determine whether the search layer for the lower limb is the termination cross section where the false cavity region is located. If yes, stop the search; if no, use the center coordinates of the false cavity of the search layer for the lower limb as the seed point of the false cavity, use the center coordinates of the true cavity of the search layer for the lower limb as the seed point of the true cavity, use the search layer for the lower limb as the second current search layer, and execute step B221.

[0055] Optionally, before obtaining the maximum connected component of the false cavity region, the coordinates of the center of the false cavity, the maximum connected component of the true cavity region, and the coordinates of the center of the true cavity in the first search starting layer, the method further includes:

[0056] Based on the true and false lumen mask images, the false lumen ROI image and the true lumen ROI image are extracted from the aortic image;

[0057] The step of obtaining the maximum connected component of the false cavity, the coordinates of the center of the false cavity, the maximum connected component of the true cavity, and the coordinates of the center of the true cavity in the first search starting layer includes:

[0058] Based on the false cavity ROI image, obtain the maximum connected component and center coordinates of the false cavity region in the first search starting layer;

[0059] Based on the true cavity ROI image, obtain the maximum connected region of the true cavity and the coordinates of the true cavity center in the first search starting layer.

[0060] Optionally, before determining the first search starting layer according to the first search rule based on the aortic image to be detected and the true and false lumen mask images of the aortic image, the method further includes:

[0061] The true and false lumen mask images are obtained based on the pixel values ​​of the pixels in the true lumen region and the false lumen region in the aortic image.

[0062] To achieve the second objective of the present invention, the present invention also provides an electronic device, the electronic device including a processor and a memory, the memory storing a computer program, which, when executed by the processor, implements the aortic dissection rupture location detection method described in any of the above claims.

[0063] To achieve the third objective of the present invention, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for detecting the location of aortic dissection rupture as described in any of the preceding claims.

[0064] Compared with the prior art, the present invention provides a method, electronic device and storage medium for detecting the location of aortic dissection rupture, which has the following beneficial effects:

[0065] The method for detecting the location of aortic dissection rupture provided by this invention determines a first search starting layer according to a first search rule based on an image of the aorta to be detected and a mask image of the true and false lumens of the aorta. This configuration allows the method to determine the first search starting layer based on the false lumen region using the mask image, thereby significantly narrowing the search range and improving the detection efficiency of aortic dissection rupture location. Furthermore, the method calculates the rupture location of the aortic dissection according to a second search rule based on the first search starting layer and the mask image of the true and false lumens. Since the search range is determined based on the false lumen region, the detection accuracy of aortic dissection rupture location is improved. The algorithm is simple and efficient, achieving fully automatic detection of aortic dissection rupture location and is easy to implement.

[0066] Furthermore, the method for detecting the location of aortic dissection rupture provided by the present invention further includes determining the second search starting layer and the aortic arch location according to the aortic image and the true and false lumen mask image, according to a third search rule. With this configuration, for the case where the starting location of a type B aortic dissection rupture is generally on the aortic arch, but the false lumen region in the true and false lumen mask image may not cover the aortic arch location, the method for detecting the location of aortic dissection provided by the present invention can compensate for the potential deficiency of obtaining the middle position of the aortic rupture but failing to obtain the starting position of the aortic rupture when determining the first search starting layer according to the first search rule and the true and false lumen mask image, and calculating the rupture location of the aortic dissection according to the second search rule. The method for detecting the location of aortic dissection rupture provided by the present invention calculates the starting location of the aortic dissection rupture according to the second search initiation layer and the location of the aortic arch, and in accordance with the fourth search rule. Since the starting location of a type B aortic dissection rupture is generally on the aortic arch, the accuracy of detecting the location of the aortic dissection rupture can be improved.

[0067] Furthermore, the method for detecting the location of aortic dissection rupture provided by this invention employs adaptive region growing to perform morphological connected domain attribute analysis and calculation layer by layer, thereby realizing fully automatic detection of aortic dissection rupture location. The algorithm is simple, efficient, and easy to implement, and this invention implements an end-to-end algorithm flow.

[0068] Since the electronic device and storage medium provided by this invention and the method for detecting the location of aortic dissection rupture provided by this invention belong to the same inventive concept, they have at least the same beneficial effects, and will not be described in detail here. Attached Figure Description

[0069] Figure 1 A flowchart illustrating a method for detecting the location of an aortic dissection tear according to an embodiment of the present invention;

[0070] Figure 2 A flowchart illustrating the main detection of the starting position of the breach according to one embodiment of the present invention;

[0071] Figure 3 A cross-sectional schematic diagram of the aorta after processing using the aortic dissection rupture location detection method provided by this invention;

[0072] Figure 4 for Figure 2 Flowchart of a method for determining the second search starting layer in one embodiment of step S210;

[0073] Figure 5(a) is a three-dimensional schematic diagram of the second search starting layer of an aortic image using the aortic dissection rupture location detection method provided by the present invention;

[0074] Figure 5(b) is a schematic cross-sectional view of the second search starting layer in Figure 5(a);

[0075] Figure 6 for Figure 2 Flowchart of a method for determining the location of the aortic arch in one embodiment of step S210;

[0076] Figure 7 for Figure 2 A flowchart illustrating the process of calculating the starting position of the aortic dissection rupture according to the fourth search rule in step S220.

[0077] Figure 8 for Figure 7 A flowchart illustrating the process of obtaining the segmentation result of the false cavity region in the next search layer in one embodiment of step A2;

[0078] Figure 9 A schematic diagram showing the calculation results of the starting position of aortic dissection rupture using the aortic dissection rupture location detection method provided by this invention;

[0079] Figure 10 for Figure 1 A flowchart illustrating a method for determining the first search starting layer in one embodiment of step S110.

[0080] Figure 11(a) is a three-dimensional schematic diagram of the first search starting layer of an aortic image using the aortic dissection rupture location detection method provided by the present invention;

[0081] Figure 11(b) is a cross-sectional schematic diagram of the first search starting layer in Figure 11(a);

[0082] Figure 12 for Figure 1 In step S120, a flowchart is shown in which the location of the aortic dissection rupture is predicted according to the second search rule; Figure 13(a) is a schematic diagram of the prediction result of the location of one intermediate rupture of the aortic dissection using the aortic dissection rupture location detection method provided by the present invention.

[0083] Figure 13(b) is a schematic diagram of the prediction result of another intermediate tear location of aortic dissection using the aortic dissection tear location detection method provided by the present invention;

[0084] Figure 13(c) is a schematic diagram of the prediction result of another intermediate rupture location of aortic dissection using the aortic dissection rupture location detection method provided by the present invention.

[0085] Figure 13(d) is a schematic diagram of the prediction result of the intermediate rupture location of aortic dissection using the aortic dissection rupture location detection method provided by the present invention;

[0086] The reference numerals in the attached figures are explained as follows:

[0087] 110 - True voice, 120 - False voice. Detailed Implementation

[0088] To make the objectives, advantages, and features of the present invention clearer, the following detailed description, in conjunction with the accompanying drawings, provides a more comprehensive overview of the method for detecting the location of aortic dissection rupture, the electronic device, and the storage medium proposed in this invention. It should be noted that the drawings are all in a very simplified form and use non-precise scales, intended only to facilitate and clearly illustrate the embodiments of the present invention. It should be understood that the accompanying drawings do not necessarily show the specific structure of the invention to scale, and the illustrative features used to explain certain principles of the invention in the accompanying drawings are also drawn in a slightly simplified manner. Specific design features of the invention disclosed herein, including, for example, specific dimensions, orientations, positions, and shapes, will be determined in part by the specific application and usage environment. Furthermore, in the embodiments described below, the same reference numerals are sometimes used across different drawings to denote the same parts or parts having the same function, omitting repeated descriptions. In this specification, similar reference numerals and letters are used to denote similar items; therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0089] Where appropriate, these terms may be replaced. Similarly, if the methods described herein comprise a series of steps, and the order of these steps presented herein is not necessarily the only possible order in which these steps can be performed, and some of the described steps may be omitted and / or some other steps not described herein may be added to the method.

[0090] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0091] As understood by those skilled in the art, aortic dissection is caused by a tear in the aortic intima due to various reasons, allowing blood to enter the aortic wall through the primary tear (rupture), causing the vessel wall to separate and forming a true and false "double lumen". In addition to the primary tear, re-tears in aortic dissection are increasingly being recognized, as the size and number of re-tears directly affect the blood perfusion of the false lumen, and thus relate to the prognosis and treatment outcomes of patients with aortic dissection. Compared to the primary tear, re-tears have more complex local anatomy, more variable locations, and are more difficult to detect clinically.

[0092] Based on this, the core idea of ​​the present invention is to provide a method, electronic device and storage medium for detecting the location of aortic dissection rupture. The method for detecting the location of aortic dissection rupture provided by the present invention uses the results of the true and false cavity segmentation mask as the initial input to automatically detect the location of the aortic dissection rupture in the aortic image, which can improve the detection efficiency and accuracy of the aortic rupture location.

[0093] To achieve the above-mentioned goals, one embodiment of the present invention provides a method for detecting the location of aortic dissection rupture. Please refer to [link to relevant documentation]. Figure 1 , Figure 1 This is a flowchart illustrating the method for detecting the location of aortic dissection rupture provided in this embodiment. From... Figure 1 As can be seen, the method for detecting the location of aortic dissection rupture provided in this embodiment includes:

[0094] Step S110: Based on the aortic image to be detected and the true and false lumen mask images of the aortic image, determine the first search starting layer according to the first search rule;

[0095] Step S120: Based on the first search starting layer and the true and false lumen mask images, calculate the location of the aortic dissection rupture according to the second search rule.

[0096] The method for detecting the location of aortic dissection rupture provided by this invention determines a first search starting layer according to a first search rule based on the aortic image to be detected and the true and false lumen mask images of the aortic image. This configuration allows the method to determine the first search starting layer based on the false lumen region of the true and false lumen mask images, thereby significantly narrowing the search range and improving the detection efficiency of aortic dissection rupture location. Furthermore, the method calculates the rupture location of the aortic dissection according to a second search rule based on the first search starting layer and the true and false lumen mask images. Since the search range is determined based on the false lumen region, the detection accuracy of aortic dissection rupture location is improved. The algorithm is simple and efficient, achieving fully automatic detection of aortic dissection rupture location and is easy to implement.

[0097] Furthermore, such as Figure 2 As shown, Figure 2 This is a schematic flowchart illustrating the detection of the initiation position of a tear according to an embodiment of the present invention. Figure 2 It can be seen that calculating the location of the aortic dissection tear also includes:

[0098] Step S210: Based on the aortic image and the true and false lumen mask images, determine the second search starting layer and the location of the aortic arch according to the third search rule;

[0099] Step S220: Based on the second search starting layer and the location of the aortic arch, calculate the starting position of the aortic dissection according to the fourth search rule.

[0100] The method for detecting the location of aortic dissection rupture provided by this invention determines the second search starting layer and the aortic arch position according to a third search rule based on the aortic image and the true / false lumen mask image. This configuration is advantageous because the starting position of a type B aortic dissection rupture is generally on the aortic arch. However, in cases where the false lumen region in the true / false lumen mask image may not cover the aortic arch position, the method for detecting the location of aortic dissection provided by this invention can compensate for the potential deficiency in step S120, which only obtains the intermediate position of the aortic rupture and may not be able to obtain the starting position of the aortic rupture. Furthermore, the method for detecting the location of aortic dissection rupture provided by this invention calculates the starting position of the aortic dissection rupture according to a fourth search rule based on the second search starting layer and the aortic arch position. Since the starting position of a type B aortic dissection rupture is generally on the aortic arch, this method can improve the accuracy of aortic dissection rupture location detection.

[0101] For ease of understanding and description, this invention uses aortic CTA (computed tomography angiography) images as an example to illustrate the method for detecting the location of aortic dissection rupture. However, as those skilled in the art will understand, in this invention, the aortic image (i.e., aortic vascular image) can also be an MRA (magnetic resonance angiography) image, or other medical images. The aortic image can be acquired using an image acquisition device, such as CT or MRI imaging equipment, or obtained through internet searches, or by scanning with a scanning device. The size of the aortic image can be set according to specific circumstances, and this invention does not impose any limitations on this.

[0102] Preferably, in one preferred embodiment, before step S110, which determines the first search starting layer according to a first search rule based on the aortic image to be detected and the true and false lumen mask images of the aortic image, the method further includes:

[0103] The true and false lumen mask images are obtained based on the pixel values ​​of the pixels in the true lumen region and the false lumen region in the aortic image.

[0104] Specifically, preferably, an adaptive region growing method can be used to obtain the connected components of the true lumen region and the false lumen region based on the pixel values ​​of each pixel in the aortic image. Then, the true and false lumen mask image is obtained based on the connected components of the true lumen region and the false lumen region. For example, based on the pixel value range of each region in the aortic image, the pixel value of the false lumen region is labeled as 2, and the pixel value of the true lumen region is labeled as 1. The specific labeled values ​​of the false lumen region and the standard values ​​of the true lumen region are merely illustrative examples and are not limitations of the present invention. Furthermore, the present invention does not limit the method of obtaining the true and false lumen mask image; it can be obtained manually or automatically through an algorithm. The method of obtaining the true and false lumen mask image will not be elaborated here. It should be particularly noted that the true and false lumen mask image is obtained based on the aortic image, that is, the true and false lumen mask image corresponds one-to-one with the aortic image.

[0105] Furthermore, the method for detecting the location of aortic dissection rupture in this embodiment of the invention can be applied to the electronic device in this embodiment of the invention. The electronic device can be a personal computer, a mobile terminal, etc., and the mobile terminal can be a mobile phone, a tablet computer, or other hardware device with various operating systems.

[0106] Furthermore, although the above description outlines the sequence of calculating the aortic dissection tear location using steps S110 and S120 (collectively referred to as Step B for ease of description), and further calculating the tear initiation location using steps S210 and S220 (collectively referred to as Step A for ease of description), as those skilled in the art will understand, Step B and Step A are two completely independent steps without any sequential dependency. That is, the present invention does not limit the execution order of Step B and Step A. In one embodiment, Step B is executed first to detect the aortic dissection tear location, and then Step A is executed to detect the tear initiation location near the aortic arch. In another embodiment, Step A can be executed first to detect the tear initiation location near the aortic arch, and then Step B can be executed to detect the aortic dissection tear location. Even more importantly, if the performance of the electronic equipment allows, Step B and Step A can be executed in parallel. Preferably, before performing steps B and A, in one embodiment, the method for detecting the location of the aortic dissection tear further includes:

[0107] The aortic image is truncated, and its pixel values ​​are scaled to a preset pixel threshold range. Specifically, based on the aortic image, the maximum and minimum pixel values ​​(CT values) of the aortic region are analyzed, and then the pixel values ​​of the aortic image are scaled to a preset range using linear scaling. See [link to relevant documentation]. Figure 3 , Figure 3 A cross-sectional schematic diagram of the aorta after being truncated using the aortic dissection rupture location detection method provided by this invention. Figure 3 In this context, the Hu values ​​of the aortic image are scaled to a Hu value range of [0, 600]. Figure 3 As can be seen, the aortic image after truncation is not only clearer, which is beneficial for doctors to observe and analyze; but also, through linearization, the amount of data in the aortic image can be reasonably reduced, thereby speeding up the efficiency of subsequent data processing.

[0108] Specifically, in one embodiment, please refer to Figure 4 , Figure 4 for Figure 2 A flowchart illustrating a method for determining the location of the aortic arch in one embodiment of step S210. From... Figure 4 As can be seen, in step S210, determining the second search starting layer according to the aortic image and the true / false lumen mask image, and following the third search rule, includes:

[0109] Step A011: Calculate the length of the false lumen region along the aortic extension direction based on the false lumen region in the true and false lumen mask image;

[0110] Step A012: Based on the true and false cavity mask images and the length, traverse along the head to the lower limb direction to calculate the position of the false cavity region at the first preset length ratio;

[0111] Step A013: Determine the cross-section of the aortic image at this location as the second search starting layer.

[0112] Specifically, for aortic CTA (computed tomography angiography) images, based on its imaging principle, the aortic image is a cross-sectional image (slice) created by continuously sampling the aorta and surrounding tissues of the scanned object using a computer, and then sequentially combining these slices. Therefore, based on the false lumen region (e.g., the region marked with a pixel value of 2) in the true and false lumen mask image, the minimum cross-sectional image (starting slice or initial cross-section, such as the 300th slice) and the maximum cross-sectional image (ending slice or termination cross-section, such as the 500th slice) of the false lumen region can be obtained. Thus, the length of the false lumen region along the aortic extension direction can be calculated based on the difference between the starting slice and the maximum slice. Furthermore, since the starting location of a type B aortic dissection tear is generally on the aortic arch, the search can proceed from the head down the limbs, and the cross-sectional image (starting search slice) at the location of the first preset length ratio of the false lumen region can be used as the second search starting layer. Specifically, in one embodiment, referring to Figures 5(a) and 5(b), Figures 5(a) and 5(b) are respectively three-dimensional and cross-sectional schematic diagrams of the second search starting layer of an aortic image using the aortic dissection rupture location detection method provided by the present invention. In Figure 5(a), the first preset length ratio is 1 / 4. That is, the second search starting layer is taken as 1 / 4 of the false lumen range starting from the direction of the human head, so as to detect the starting position of the aortic dissection rupture. The location of the center of the cross in Figure 5(a) is the location of the second search starting layer.

[0113] With this configuration, the method for detecting the location of aortic dissection rupture provided by the present invention can determine the second search starting layer based on the false lumen region using its true and false lumen mask images, which can greatly reduce the search range and improve the detection efficiency and accuracy of aortic dissection rupture location.

[0114] Preferably, in one embodiment, please refer to Figure 6 , Figure 6 for Figure 2 A flowchart illustrating a method for determining the location of the aortic arch in one embodiment of step S210. From... Figure 6 As can be seen, in step S210, determining the aortic arch location according to the third search rule based on the aortic image and the true / false lumen mask image includes:

[0115] Step A021: Starting from the second search starting layer, traverse layer by layer along the lower limb towards the head, and obtain the area of ​​the aortic image in each cross section based on the true and false cavity mask images;

[0116] Step A022: Based on the area of ​​each cross-section, select the cross-section with the largest area in the aortic image;

[0117] Step A023: Determine the location of the aortic arch in the N layers above and below the largest cross-section of the aortic image; N is a first preset threshold and N is a positive integer.

[0118] Specifically, since the aortic arch has the largest cross-section in the entire aorta, each cross-section is first traversed using the true and false lumen mask images to find the cross-section with the largest area. Based on the anatomical characteristics of the aorta, the aortic arch is located in the layers above and below the largest cross-section. Preferably, referring to Figure 5(a), the first preset threshold N is set to 10, meaning that the aortic arch is considered to be located within the 10 layers above and below the largest cross-section. Obviously, this is only an exemplary description and not a limitation of the invention. In other embodiments, the first preset threshold N can also be 8 or 12, etc., depending on actual needs, which will not be elaborated further.

[0119] With this configuration, the aortic dissection tear location detection method provided by the present invention addresses the situation where the starting location of a type B aortic dissection tear is generally on the aortic arch, but the false lumen region in the true and false lumen mask image may not cover the aortic arch location. The method can calculate the tear location starting position of the aortic dissection according to the second search starting layer and the aortic arch location, following the fourth search rule. Since the starting location of a type B aortic dissection tear is generally on the aortic arch, this improves the accuracy of aortic dissection tear location detection.

[0120] Preferably, in one embodiment, see Figure 7 , Figure 7 for Figure 2 A flowchart illustrating the process of calculating the initiation location of the aortic dissection according to the fourth search rule in step S220. From... Figure 7 As can be seen, in step S220, the step of calculating the initiation position of the aortic dissection according to the second search starting layer and the aortic arch position, and in accordance with the fourth search rule, includes:

[0121] Step A1: Obtain the maximum connected region area and center coordinates of the false cavity region in the second search starting layer; and use the center coordinates as the seed point, and use the second search starting layer as the first current search layer.

[0122] Specifically, the connected components of the pseudo-cavity region (e.g., the pixel marked as 2 in the real and pseudo-cavity mask image) of the second search starting layer are extracted, and then a method of taking the largest connected component is performed to prevent isolated pixels from affecting subsequent calculations. Then, the center coordinates (x, y) of the largest connected component are calculated based on its contour as the seed point of the next layer.

[0123] Preferably, in one embodiment, the area of ​​the pseudo-cavity connected region in the second search starting layer can be stored simultaneously to avoid repeated calculations in step A3, thereby reducing the amount of computation and improving detection efficiency.

[0124] With this configuration, the method for detecting the location of aortic dissection rupture provided by this invention can automatically acquire seed points without manual interaction, thus laying the foundation for fully automated detection of aortic dissection rupture location.

[0125] Step A2: Based on the pixel value of the seed point and the preset adjustment factor, obtain the segmentation result of the false lumen region in the next search layer using the adaptive region growing method; and based on the segmentation result, obtain the maximum connected region area and center coordinates of the false lumen region in the next search layer; wherein, the next search layer is a cross-section of the aortic image that is adjacent to the first current search layer and close to the head direction.

[0126] Specifically, in one preferred embodiment, please refer to Figure 8 , Figure 8 for Figure 7 A flowchart illustrating one implementation method for obtaining the segmentation result of the pseudo-cavity region in the next search layer in step A2. From... Figure 8 As can be seen, step A2, which describes obtaining the segmentation result of the pseudo-cavity region in the next search layer based on the pixel value of the seed point and a preset adjustment factor using an adaptive region growing method, includes:

[0127] A21: Calculate the low threshold pixel value and the high threshold pixel value based on the pixel value of the seed point and the adjustment factor.

[0128] Preferably, the high threshold pixel value and the low threshold pixel value are calculated using the following formulas respectively:

[0129]

[0130]

[0131] In the formula, The low threshold pixel value, The high threshold pixel value, The pixel value of the seed point. The adjustment factor is mentioned above. As those skilled in the art will understand, the present invention is not limited. The specific value should be set reasonably according to actual needs. The value of is preferably between 0.1 and 0.3, and more preferably, It can be set to 0.2.

[0132] A22: Based on the low threshold pixel value and the high threshold pixel value, an adaptive region growing method is used to obtain the segmentation result of the pseudo-cavity region in the next search layer.

[0133] Preferably, in one embodiment, the area of ​​the connected domain in the pseudo-cavity region of the next search layer can be calculated simultaneously to avoid repeated calculations in step A3, thereby reducing the amount of computation and improving detection efficiency.

[0134] Step A3: Determine whether the first preset search termination condition is met. If yes, proceed to step A4; otherwise, use the center coordinates of the next search layer as the seed point, use the next search layer as the first current search layer, and proceed to step A2. The first preset search termination condition includes the ratio of the maximum connected region area of ​​the next search layer to the maximum connected region area of ​​the first current search layer exceeding a second preset threshold and the next search layer being located at the aortic arch.

[0135] Therefore, the method for detecting the location of aortic dissection rupture provided by this invention calculates the center coordinates of the false lumen connected region of the current layer as the seed point for the next layer by starting from the second search starting layer and moving towards the head layer by layer based on the region growth segmentation results. The area of ​​the false lumen connected region of the current layer is calculated and recorded. Adaptive region growth can obtain the false lumen segmentation result for each cross-section. Furthermore, based on the principle that the true lumen region and the false lumen region are separate and not connected due to the presence of the vascular intima patch; only when a rupture exists and the intima patch is incomplete will the true lumen region and the false lumen region connect. This invention can determine whether a rupture exists in a layer by analyzing the area value of the false lumen segmentation result for each cross-section. For details, please refer to [link to relevant documentation]. Figure 9 , Figure 9 This diagram illustrates the calculation results of the aortic dissection tear location initiation position using the aortic dissection tear location detection method provided by this invention. Figure 9 In this context, the second preset threshold is set to 2. This means that the judgment is based on the ratio of the pseudo-lumen area of ​​the next layer to the current layer. If the area ratio is greater than 2 and the aortic arch is located, the starting point of the aortic dissection tear is considered to have been found. (Compare Figure 5(b) and...) Figure 9 It is clear that the true lumen 110 and the false lumen 120 of the aorta in Figure 5(b) are not connected, meaning there is no tear there; while Figure 9 In this diagram, the true lumen 110 and the false lumen 120 are connected and located near the aortic arch, indicating that the starting point of the aortic dissection rupture has been found. Specifically, as those skilled in the art will understand, the value of the aforementioned second preset threshold is merely illustrative and not a limitation of the invention. The invention does not limit the specific value of the second preset threshold; in practical applications, it should be reasonably selected according to the specific circumstances.

[0136] Step A4: Calculate the starting position of the aortic dissection rupture based on the coordinates of the seed point.

[0137] With this configuration, the aortic dissection rupture location detection method provided by the present invention achieves fully automatic aortic dissection rupture location detection by performing morphological connected domain attribute analysis and calculation layer by layer through adaptive region growing. The algorithm is simple, efficient, and has high generalization ability.

[0138] Preferably, in one exemplary embodiment, before step A2, which involves obtaining the segmentation result of the pseudo-cavity region in the next search layer using an adaptive region growing method based on the pixel value of the seed point and a preset adjustment factor, the method further includes:

[0139] A02: Based on the true and false lumen mask images, extract the false lumen ROI (region of interest) image from the aortic image.

[0140] Accordingly, obtaining the maximum connected region area and center coordinates of the false cavity region in the second search starting layer includes: obtaining the maximum connected region area and center coordinates of the false cavity region in the second search starting layer based on the false cavity ROI image.

[0141] As understood by those skilled in the art, if the false lumen region of the true and false lumen mask image can cover the aortic arch location or the aortic dissection tear location is completely located within the false lumen region, step B can also detect the starting location of the aortic dissection tear near the aortic arch. However, for ease of distinction, the tear location detected in step B will be referred to as the intermediate tear location below.

[0142] Preferably, in one exemplary embodiment, please refer to Figure 10 , Figure 10 for Figure 1 A flowchart illustrating a method for determining the first search starting layer in one embodiment of step S110. From Figure 10 As can be seen, in step S110, determining the first search starting layer according to the first search rule based on the aortic image to be detected and the true and false lumen mask images of the aortic image includes:

[0143] Step B01: Calculate the length of the false lumen region along the aortic extension direction based on the true and false lumen mask images;

[0144] Step B02: Based on the true and false cavity mask images and the length, calculate the position of the false cavity region at the second preset length ratio;

[0145] Step B03: Determine the cross-section of the aortic image at this location as the first search starting layer.

[0146] Since the method for obtaining the first search starting layer is similar to the basic principle of obtaining the second search starting layer described above, it will not be repeated here. However, it should be noted that, as those skilled in the art will understand, the present invention does not limit the specific values ​​of the first preset length ratio and the second preset length ratio; the specific values ​​in this article are merely illustrative examples. Furthermore, the value of the second preset length ratio can be the same as or different from the first preset length ratio, and the present invention does not impose any restrictions on this. Specifically, in one preferred embodiment, referring to Figures 11(a) and 11(b), Figures 11(a) and 11(b) are cross-sectional and three-dimensional schematic diagrams of the first search starting layer of an aortic image using the aortic dissection rupture location detection method provided by the present invention. In Figure 11(a), the first preset length ratio is 1 / 2. That is, the second search starting layer is taken at 1 / 2 of the false lumen range, so as to detect the middle position of the aortic dissection rupture. In Figure 11(a), the position of the center of the cross is the position of the first search starting layer.

[0147] With this configuration, the aortic dissection location detection method provided by the present invention determines the first search starting layer based on the false lumen region using its true and false lumen mask images, thereby greatly narrowing the search range and improving the detection efficiency of aortic dissection tear location.

[0148] Preferably, in one exemplary embodiment, see Figure 12 , Figure 12 for Figure 1 A flowchart illustrating the process of predicting the location of the aortic dissection rupture according to the second search rule in step S120. From... Figure 12 As can be seen, in step 120, the step of calculating the location of the aortic dissection tear according to the second search rule based on the first search starting layer and the true and false lumen mask images includes:

[0149] Step B1: Obtain the maximum connected component of the false cavity, the center coordinates of the false cavity, the maximum connected component of the true cavity, and the center coordinates of the true cavity in the first search starting layer, respectively; and use the center coordinates of the false cavity as the seed point of the false cavity and the center coordinates of the true cavity as the seed point of the true cavity, and use the first search starting layer as the second current search layer.

[0150] Step B2: Based on the false lumen seed point and the true lumen seed point, using the second current search layer as the starting search layer, search layer by layer along the lower limb towards the head and the head towards the lower limb, until the false lumen region is reached at the starting cross section and the ending cross section of the aortic image, and obtain the maximum connected region of the false lumen and the maximum connected region of the true lumen for each search layer.

[0151] Specifically, in one preferred embodiment, the layer-by-layer search along the lower limbs toward the head includes:

[0152] B211: Using an adaptive region growing method, based on the pixel values ​​of the false lumen seed points and a preset adjustment factor, the false lumen segmentation result of the false lumen region in the next head search layer is obtained. Based on the false lumen segmentation result, the maximum connected component and the center coordinates of the false lumen region in the next head search layer are obtained. Based on the pixel values ​​of the true lumen seed points and a preset adjustment factor, the true lumen segmentation result of the true lumen region in the next head search layer is obtained. Based on the true lumen segmentation result, the maximum connected component and the center coordinates of the true lumen region in the next head search layer are obtained. Wherein, the next head search layer is a cross-section of the aortic image adjacent to the second current search layer and close to the head direction.

[0153] B212: Determine whether the next head search layer is the starting cross section where the false cavity region is located. If yes, stop the search; if no, use the false cavity center coordinates of the next head search layer as the false cavity seed point, use the true cavity center coordinates of the next head search layer as the true cavity seed point, use the next head search layer as the second current search layer, and execute step B211.

[0154] In particular, since the basic principle of obtaining the pseudo-cavity segmentation result of the pseudo-cavity region in the next head search layer by means of the adaptive region growing method in step B211, based on the pixel value of the pseudo-cavity seed point and the preset adjustment factor, is the same as the basic principle of obtaining the segmentation result of the pseudo-cavity region in the next search layer by means of the adaptive region growing method based on the pixel value of the seed point and the preset adjustment factor in step A2, it will not be explained in detail here.

[0155] Further, in one preferred embodiment, the layer-by-layer search along the head to the lower limbs includes:

[0156] B221: Using an adaptive region growing method, based on the pixel values ​​of the false lumen seed points and a preset adjustment factor, the false lumen segmentation result of the false lumen region in the next lower limb search layer is obtained. Based on the false lumen segmentation result, the maximum connected component and the center coordinates of the false lumen region in the next lower limb search layer are obtained. Based on the pixel values ​​of the true lumen seed points and a preset adjustment factor, the true lumen segmentation result of the true lumen region in the next lower limb search layer is obtained. Based on the true lumen segmentation result, the maximum connected component and the center coordinates of the true lumen region in the next lower limb search layer are obtained. The next lower limb search layer is a cross-section of the aortic image adjacent to the second current search layer and close to the lower limb direction.

[0157] B222: Determine whether the search layer for the lower limb is the termination cross section where the false cavity region is located. If yes, stop the search; if no, use the center coordinates of the false cavity of the search layer for the lower limb as the seed point of the false cavity, use the center coordinates of the true cavity of the search layer for the lower limb as the seed point of the true cavity, use the search layer for the lower limb as the second current search layer, and execute step B221.

[0158] Since the principle of searching layer by layer towards the lower limbs is the same as that of searching along the head, please refer to the relevant explanations of steps B211-B212 above. They will not be repeated here.

[0159] As those skilled in the art will understand, after step B1, the present invention does not limit the order of the layer-by-layer search along the lower limbs towards the head and the layer-by-layer search along the head towards the lower limbs. In one embodiment, the search can begin from the first search starting layer, proceeding layer by layer along the lower limbs towards the head until the starting cross-section where the false cavity region is located is reached; then, the search proceeds layer by layer along the head towards the lower limbs until the ending cross-section where the false cavity region is located is reached. In another embodiment, the search can begin from the first search starting layer, proceeding layer by layer along the head towards the lower limbs until the ending cross-section where the false cavity region is located is reached, and then, the search proceeds layer by layer along the lower limbs towards the head until the starting cross-section where the false cavity region is located is reached. Obviously, if the performance of the electronic device allows, the layer-by-layer search along the lower limbs towards the head and the layer-by-layer search along the head towards the lower limbs can be performed simultaneously.

[0160] Step B3: Determine whether the maximum connected region of the false lumen and the maximum connected region of the true lumen in each search layer are the same connected region. If so, determine the position of the aortic dissection in the middle of the rupture in the search layer according to the center coordinates of the false lumen and the center coordinates of the true lumen of the search layer, and according to the preset dissection rupture position calculation rules.

[0161] Specifically, the preset dissection rupture location calculation rule includes using the center of the false lumen or / the coordinates of the true lumen center as the midpoint of the rupture location of the aortic dissection in the search layer.

[0162] Step B4: Merge the midpoints of the ruptures in each search layer to obtain the midpoint of the rupture in the aortic dissection.

[0163] Please refer to Figures 13(a), 13(b), 13(c), and 13(d), which are schematic diagrams showing the prediction results of the intermediate rupture location at different cross-sections (slices) of aortic dissection using the aortic dissection rupture location detection method provided by this invention.

[0164] Comparing Figure 11(b) with Figures 13(a), 13(b), 13(c), and 13(d), it is clear that the true lumen 110 and the false lumen 120 of the aortic vessel in Figure 11(b) are not connected, meaning there is no tear there. However, in Figures 13(a), 13(b), 13(c), and 13(d), the true lumen 110 and the false lumen 120 are connected, indicating that the starting location of the aortic dissection tear has been found.

[0165] With this configuration, the aortic dissection location detection method provided by the present invention calculates the aortic dissection tear location according to the first search starting layer and the true and false lumen mask images, and according to the second search rule. Since the search range is determined according to the false lumen region, it can improve the detection accuracy of the aortic dissection tear location. The algorithm is simple and efficient, realizes fully automatic aortic dissection tear location detection, and is easy to implement.

[0166] In summary, the method for detecting the location of aortic dissection rupture provided by this invention is based on the principle that the segmentation results of the true lumen and the false lumen are independent connected domains, but if a rupture exists, the segmentation results will be merged into a single connected domain. The method determines layer by layer whether there are two true lumen connected domains and two false lumen connected domains generated by the adaptive region growth. If so, it indicates that the intima is intact and there is no rupture. If the result is only one connected domain, it indicates that there is a rupture in this cross-section, and the location of the rupture can be considered by selecting the center point coordinates of one of the regions. Specifically, as described above, the method for detecting the location of aortic dissection rupture provided by the present invention first determines the range of the false lumen in the z-direction (along the direction of aortic vessel extension) based on the input true and false lumen mask image when detecting the middle position of the aortic dissection rupture. The cross-section of the false lumen range at 1 / 2 is taken as the starting layer cross-section for the search. Then, the search is performed layer by layer along the direction from the lower limb to the head and along the direction from the head to the lower limb. First, the connected regions marked as 1 (true lumen) and 2 (false lumen) on the starting layer cross-section are extracted respectively. The maximum connected region is taken for each connected region of 1 and each connected region of 2 to prevent the influence of isolated pixels. Then, the center coordinates (x, y) of the maximum connected region of the true lumen and the false lumen are calculated based on the contour of the maximum connected region of the true lumen and the false lumen as the seed points of the true lumen region and the false lumen region of the next head search layer / the next lower limb search layer. Then, adaptive region growth is performed in stages based on the two seed points. Finally, the true and false lumen results generated in stages are merged together. Repeat this process, traversing layer by layer in both directions, until the maximum (terminating cross section) and minimum (starting cross section) range of the false lumen region in the z-direction are reached in the true and false lumen mask images. Finally, the predicted rupture locations in the two directions are merged, thus detecting all intermediate rupture locations of the aortic dissection rupture.

[0167] Preferably, before obtaining the maximum connected component of the false cavity, the center coordinates of the false cavity, the maximum connected component of the true cavity, and the center coordinates of the true cavity in step B1, the method further includes:

[0168] Based on the true and false lumen mask images, the false lumen ROI image and the true lumen ROI image are extracted from the aortic image.

[0169] Accordingly, step B1, which involves obtaining the maximum connected component of the false cavity, the coordinates of the center of the false cavity, the maximum connected component of the true cavity, and the coordinates of the center of the true cavity in the first search starting layer, includes:

[0170] Based on the false cavity ROI image, obtain the maximum connected component and center coordinates of the false cavity region in the first search starting layer;

[0171] Based on the true cavity ROI image, obtain the maximum connected region of the true cavity and the coordinates of the true cavity center in the first search starting layer.

[0172] Another embodiment of the present invention provides an electronic device, the electronic device including a processor and a memory, the memory storing a computer program, which, when executed by the processor, implements the method for detecting the location of aortic dissection rupture as described in any of the above embodiments.

[0173] Another embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps of the method for detecting the location of aortic dissection rupture as described in any of the above embodiments.

[0174] Since the electronic device and storage medium provided by this invention belong to the same inventive concept as the method for detecting the location of aortic dissection rupture provided by this invention, the specific implementation methods and beneficial effects are described in a relatively brief manner. For details, please refer to the methods for detecting the location of aortic dissection rupture provided in the above-mentioned embodiments, which will not be described in detail here.

[0175] The readable storage medium of embodiments of the present invention can be any combination of one or more computer-readable media. The readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable computer hard disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device.

[0176] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0177] It should be noted that computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0178] The method, electronic device, and storage medium for detecting the location of aortic dissection ruptures provided by this invention can improve the detection efficiency and accuracy of aortic dissection rupture locations. The algorithm is simple and efficient, realizing fully automatic detection of aortic dissection rupture locations, and is easy to implement. Furthermore, the method for detecting the location of aortic dissection ruptures provided by this invention uses adaptive region growing to perform morphological connected component attribute analysis and calculation layer by layer, realizing fully automatic detection of aortic dissection rupture locations. The algorithm is simple, efficient, and easy to implement, and this invention realizes an end-to-end algorithm flow.

[0179] It should be noted that the systems and methods disclosed in the embodiments herein can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments herein. In this regard, each block in a flowchart or block diagram may represent a module, program, or part of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system to perform the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0180] In addition, the functional modules in the various embodiments of this article can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0181] In the description of this specification, the 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 present 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. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0182] In summary, the above embodiments have provided a detailed description of the different configurations of the aortic dissection rupture location detection method, electronic device, and storage medium proposed in this invention. Of course, the above description is only a description of the preferred embodiments of this invention and is not intended to limit the scope of this invention in any way. This invention includes, but is not limited to, the configurations listed in the above embodiments. Those skilled in the art can draw inferences from the above embodiments. Any changes or modifications made by those skilled in the art based on the above disclosure are within the scope of protection of the claims.

Claims

1. A method for detecting the location of an aortic dissection tear, characterized in that, include: Based on the mask images of the true and false lumens, calculate the length of the false lumen region along the direction of aortic extension; Based on the true and false cavity mask images and the length, the position of the false cavity region at the second preset length ratio is calculated; The cross-section of the aorta image to be detected at this location is determined as the first search starting layer; Based on the first search starting layer and the true and false cavity mask images, the location of the aortic dissection rupture is calculated according to the second search rule; Calculating the location of the aortic dissection tear includes the following steps: Step B1: Obtain the maximum connected component of the false cavity, the center coordinates of the false cavity, the maximum connected component of the true cavity, and the center coordinates of the true cavity in the first search starting layer, respectively; and use the center coordinates of the false cavity as the seed point of the false cavity and the center coordinates of the true cavity as the seed point of the true cavity, and use the first search starting layer as the second current search layer; Step B2: Based on the false lumen seed point and the true lumen seed point, take the second current search layer as the starting search layer, and search layer by layer along the lower limb towards the head and the head towards the lower limb, until the false lumen region is reached in the starting cross section and the ending cross section of the aortic image, and obtain the maximum connected region of the false lumen and the maximum connected region of the true lumen in each search layer. Step B3: Determine whether the maximum connected region of the false lumen and the maximum connected region of the true lumen in each search layer are the same connected region. If so, determine the position of the aortic dissection in the middle of the rupture in the search layer according to the center coordinates of the false lumen and the center coordinates of the true lumen of the search layer, and according to the preset dissection rupture position calculation rules. Step B4: Merge the midpoints of the ruptures in each search layer to obtain the midpoint of the rupture in the aortic dissection.

2. The method for detecting the location of aortic dissection rupture according to claim 1, characterized in that, The calculation of the location of the aortic dissection tear also includes: Based on the aortic image and the true and false lumen mask images, the second search starting layer and the location of the aortic arch are determined according to the third search rule; Based on the second search starting layer and the location of the aortic arch, the initiation position of the aortic dissection is calculated according to the fourth search rule.

3. The method for detecting the location of aortic dissection rupture according to claim 2, characterized in that, The step of determining the second search starting layer according to the aortic image and the true and false lumen mask images, and in accordance with the third search rule, includes: Based on the false lumen region in the true and false lumen mask image, calculate the length of the false lumen region along the aortic extension direction; Based on the true and false cavity mask images and the length, the position of the false cavity region at the first preset length ratio is calculated by traversing along the head to the lower limb direction; The cross-section of the aortic image at that location is used as the second search starting layer.

4. The method for detecting the location of aortic dissection rupture according to claim 2, characterized in that, The step of determining the aortic arch location based on the aortic image and the true / false lumen mask image, according to a third search rule, includes: Starting from the second search starting layer, traverse layer by layer along the lower limb towards the head, and obtain the area of ​​the aortic image in each cross section based on the true and false cavity mask images; Based on the area of ​​each cross-section, select the cross-section with the largest area in the aortic image; The aortic arch is located in the N layers above and below the largest cross-section of the aortic image; N is a first preset threshold and is a positive integer.

5. The method for detecting the location of aortic dissection rupture according to claim 2, characterized in that, The step of calculating the initiation location of the aortic dissection tear according to the second search initiation layer and the location of the aortic arch, and in accordance with the fourth search rule, includes: Step A1: Obtain the maximum connected region area and center coordinates of the false cavity region in the second search starting layer; and use the center coordinates as the seed point, and use the second search starting layer as the first current search layer; Step A2: Based on the pixel values ​​of the seed points and the preset adjustment factor, the segmentation result of the false lumen region in the next search layer is obtained by the adaptive region growing method; and based on the segmentation result, the maximum connected region area and center coordinates of the false lumen region in the next search layer are obtained; wherein, the next search layer is the cross-section of the aortic image that is adjacent to the first current search layer and close to the head direction; Step A3: Determine whether the first preset search termination condition is met. If yes, proceed to step A4. If no, use the center coordinates of the next search layer as the seed point, use the next search layer as the first current search layer, and proceed to step A2. The first preset search termination condition includes the ratio of the maximum connected region area of ​​the next search layer to the maximum connected region area of ​​the first current search layer exceeding the second preset threshold and the next search layer being located at the aortic arch. Step A4: Calculate the starting position of the aortic dissection rupture based on the coordinates of the seed point.

6. The method for detecting the location of aortic dissection rupture according to claim 5, characterized in that, Before obtaining the segmentation result of the pseudo-cavity region in the next search layer using an adaptive region growing method based on the pixel value of the seed point and a preset adjustment factor, the method further includes: Based on the true and false lumen mask images, the false lumen ROI image is extracted from the aortic image; The step of obtaining the maximum connected region area and center coordinates of the pseudo-cavity region in the second search starting layer includes: Based on the pseudo-cavity ROI image, obtain the maximum connected region area and center coordinates of the pseudo-cavity region in the second search starting layer.

7. The method for detecting the location of aortic dissection rupture according to claim 6, characterized in that, The step of obtaining the segmentation result of the pseudo-cavity region in the next search layer using an adaptive region growing method based on the pixel value of the seed point and a preset adjustment factor includes: Calculate the low threshold pixel value and the high threshold pixel value based on the pixel value of the seed point and the adjustment factor; Based on the low threshold pixel value and the high threshold pixel value, an adaptive region growing method is used to obtain the segmentation result of the pseudo-cavity region in the next search layer.

8. The method for detecting the location of aortic dissection rupture according to claim 7, characterized in that, The step of calculating the low threshold pixel value and the high threshold pixel value based on the pixel value of the seed point and the adjustment factor includes calculating the high threshold pixel value and the low threshold pixel value respectively using the following formulas: In the formula, The low threshold pixel value, The high threshold pixel value, The pixel value of the seed point. The regulating factor is mentioned above.

9. The method for detecting the location of aortic dissection rupture according to claim 1, characterized in that, The step of searching layer by layer from the lower limb toward the head, based on the false cavity seed point and the true cavity seed point, using the second current search layer as the starting search layer, includes: B211: Using an adaptive region growing method, based on the pixel values ​​of the false lumen seed points and a preset adjustment factor, the false lumen segmentation result of the false lumen region in the next head search layer is obtained. Based on the false lumen segmentation result, the maximum connected component of the false lumen region and the coordinates of the false lumen center in the next head search layer are obtained. Based on the pixel values ​​of the true lumen seed points and a preset adjustment factor, the true lumen segmentation result of the true lumen region in the next head search layer is obtained. Based on the true lumen segmentation result, the maximum connected component of the true lumen region and the coordinates of the true lumen center in the next head search layer are obtained. Wherein, the next head search layer is a cross-section of the aortic image adjacent to the second current search layer and close to the head direction. B212: Determine whether the next head search layer is the starting cross section where the false cavity region is located. If yes, stop the search; if no, use the false cavity center coordinates of the next head search layer as the false cavity seed point, use the true cavity center coordinates of the next head search layer as the true cavity seed point, use the next head search layer as the second current search layer, and execute step B211.

10. The method for detecting the location of aortic dissection rupture according to claim 1, characterized in that, The step of searching layer by layer from the head to the lower limbs based on the false cavity seed point and the true cavity seed point, using the second current search layer as the starting search layer, includes: B221: Using an adaptive region growing method, based on the pixel values ​​of the false lumen seed points and a preset adjustment factor, the false lumen segmentation result of the false lumen region in the next lower limb search layer is obtained. Based on the false lumen segmentation result, the maximum connected component and the center coordinates of the false lumen region in the next lower limb search layer are obtained. Based on the pixel values ​​of the true lumen seed points and a preset adjustment factor, the true lumen segmentation result of the true lumen region in the next lower limb search layer is obtained. Based on the true lumen segmentation result, the maximum connected component and the center coordinates of the true lumen region in the next lower limb search layer are obtained. The next lower limb search layer is a cross-section of the aortic image adjacent to the second current search layer and close to the lower limb direction. B222: Determine whether the search layer for the lower limb is the termination cross section where the false cavity region is located. If yes, stop the search; if no, use the center coordinates of the false cavity of the search layer for the lower limb as the seed point of the false cavity, use the center coordinates of the true cavity of the search layer for the lower limb as the seed point of the true cavity, use the search layer for the lower limb as the second current search layer, and execute step B221.

11. The method for detecting the location of aortic dissection rupture according to claim 1, characterized in that, Before obtaining the maximum connected component of the false cavity, the coordinates of the center of the false cavity, the maximum connected component of the true cavity, and the coordinates of the center of the true cavity in the first search starting layer, respectively, the method further includes: Based on the true and false lumen mask images, the false lumen ROI image and the true lumen ROI image are extracted from the aortic image; The step of obtaining the maximum connected component of the false cavity, the coordinates of the center of the false cavity, the maximum connected component of the true cavity, and the coordinates of the center of the true cavity in the first search starting layer includes: Based on the false cavity ROI image, obtain the maximum connected component and center coordinates of the false cavity region in the first search starting layer; Based on the true cavity ROI image, obtain the maximum connected region of the true cavity and the coordinates of the true cavity center in the first search starting layer.

12. The method for detecting the location of aortic dissection rupture according to any one of claims 1-11, characterized in that, The detection method further includes: The true and false lumen mask images are obtained based on the pixel values ​​of the pixels in the true lumen region and the false lumen region in the aortic image.

13. An electronic device, characterized in that, The method includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the method for detecting the location of aortic dissection rupture as described in any one of claims 1 to 12.

14. A computer-readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, implements the method for detecting the location of aortic dissection rupture as described in any one of claims 1 to 12.

Images