Curvature-based aneurysm neck automatic segmentation method, device and system

Automatically segmentation of the aneurysm neck plane based on the curvature principle based on DICOM data, solving the problem of inaccurate measurement in the prior art, achieving rapid and accurate automatic positioning of the aneurysm neck plane, and improving the accuracy and reliability of treatment .

CN119006484APending Publication Date: 2024-11-22NORTH SICHUAN MEDICAL COLLEGE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411068123.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The existing aneurysm neck plane measurement methods cannot be fully automated and have low accuracy, making it difficult to accurately locate the treatment.

Method used

Based on DICOM medical imaging data, the aneurysm neck plane is automatically segmented through the curvature principle, and the vascular model is established using DICOM data, the center line is calculated, the segmentation plane is positioned, and the point with the largest curvature is selected, and the optimal plane is determined by random sampling.

Benefits of technology

It realizes rapid and accurate automatic positioning of the neck plane of aneurysm, improves the efficiency and repeatability of morphological parameter calculations, and reduces treatment errors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119006484A_ABST
    Figure CN119006484A_ABST
Patent Text Reader

Abstract

The invention designs a curvature-based aneurysm neck automatic segmentation method, device and system, and the method comprises the steps: building a blood vessel model of an aneurysm and an aneurysm-carrying artery based on DICOM medical image data, and obtaining the blood vessel center lines of the aneurysm and the aneurysm-carrying artery; obtaining a first central point, a second central point, a first fulcrum and a second fulcrum for positioning, and establishing a first segmentation plane, a second segmentation plane and a third segmentation plane for limiting; calculating the curvature of a point between the second segmentation plane and the third segmentation plane according to a curvature principle, and screening out tumor neck feature points according to a distance weighting function; and randomly sampling the tumor neck feature points by using a random sampling method to obtain three sampling points, and establishing a tumor neck plane according to the three sampling points. Calculation and measurement are carried out on the basis of computer graphics, and the tumor neck plane is automatically divided, so that the accuracy and repeatability of morphological parameter calculation are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of medical image processing technology, and in particular to a method, device and system for automatically segmenting an aneurysm neck based on curvature. Background Art

[0002] Aneurysms are a pathological vascular dilation disease that seriously endangers human health. They often have no obvious characteristics when they occur, and the onset is rapid. According to the latest surveys and studies, the incidence rate among adults is 3%-5%. The disease mainly occurs in people aged 40-60 years old, and the incidence rate in women is higher than that in men. When an aneurysm ruptures, it often causes subarachnoid hemorrhage, leaving the patient with serious sequelae or even death. From the perspective of the overall treatment level of aneurysms, the treatment level varies greatly in regions with different economic development levels. It can be seen that the timely prevention and treatment of unruptured aneurysms can greatly reduce the risk of future disease in aneurysm carriers.

[0003] Among the existing technologies, the treatment techniques for unruptured aneurysms mainly include clipping and interventional surgery. Both of these technologies require the location of the aneurysm neck and related data to determine the specific and appropriate surgical method during preoperative preparation. As for the current neck division method, most of them use computer manual measurement, which has a slow measurement speed, large randomness in the measurement results, and unsatisfactory accuracy. The improvement of aneurysm neck plane positioning is mainly the improvement of traditional measurement methods or measurement methods. It is impossible to achieve fully automatic measurement of the aneurysm neck plane, and its accuracy is difficult to guarantee.

[0004] Therefore, there is a need for an automatic method for measuring and calculating the aneurysm neck plane, which can quickly and accurately measure the aneurysm neck plane. Summary of the invention

[0005] Based on this, it is necessary to provide a method for automatic segmentation of aneurysm neck based on curvature to address the above technical problems.

[0006] The present invention provides a method for automatically segmenting an aneurysm neck based on curvature, comprising:

[0007] Based on DICOM medical imaging data, the parent artery and aneurysm images are segmented to establish the relevant vascular model and obtain the centerline of the aneurysm and parent artery;

[0008] Optionally, the intracranial tumor-bearing artery image is segmented from the three-dimensional DICOM data of CTA or MRA by using grayscale contrast, and the arterial region where the aneurysm is located is limited and selected;

[0009] Furthermore, a three-dimensional surface model of the tumor-bearing artery is established by obtaining the image data, and the center line of the tumor-bearing artery is calculated.

[0010] Positioning points for positioning the splitting plane are obtained, wherein the positioning points include a first center point, a second center point, a first fulcrum, and a second fulcrum.

[0011] Optionally, obtaining positioning points for positioning segmentation, the first center point, the second center point, the first fulcrum, and the second fulcrum, specifically includes:

[0012] The center lines of the parent artery and the aneurysm are obtained, and the intersection of the center line of the parent artery and the center line of the aneurysm is defined as the first center point, and the end point of the aneurysm close to the dome of the aneurysm is defined as the second center point. A point on each side of the center line of the first center point is defined as the first fulcrum and the second fulcrum respectively.

[0013] The second normal vector is combined with the first center point to obtain a second segmentation plane, and the third segmentation plane is obtained by combining the second center point.

[0014] Obtaining a limiting plane for limiting the tumor neck site, specifically including a first segmentation plane established through the first center point, the second center point and the first fulcrum, a second segmentation plane established through the first center point, the second center point, the first fulcrum and the second fulcrum, and a third segmentation plane;

[0015] Optionally, obtaining a segmentation plane for limiting the tumor neck site specifically includes:

[0016] A first vector is established by the first center point and the second center point, and a second vector is established with the first center point, the first fulcrum and the second fulcrum respectively. The angles of the first vector and the two vectors are compared, and the vector on the side with the larger angle is defined as the fulcrum where the second vector is located as the first fulcrum, and the fulcrum on the other side is the third vector located as the second fulcrum.

[0017] The vector that is perpendicular to both the first vector and the second vector is defined as a first normal vector, and the first center point, the second center point, and the support point where the second vector is located are combined to obtain a first segmentation plane.

[0018] The first support point and the second support point form a fourth vector, and combined with the first normal vector, a second normal vector perpendicular to the fourth vector and the first normal vector is obtained.

[0019] The method of obtaining a plurality of first candidate point sets specifically includes rotating and intersecting the first segmentation plane with the parent artery and the aneurysm to obtain a plurality of intersection points as the first candidate point sets.

[0020] Optionally, obtaining a first candidate point set specifically includes:

[0021] The second normal vector is the rotation axis, and the first segmentation plane is rotated along this axis. Each time the intersection of the rotation plane and the tumor-bearing artery and the aneurysm model is used as a set of first candidate point sets, and a total rotation of 360° is performed to finally obtain multiple sets of first candidate point sets.

[0022] The multiple sets of second candidate point sets are obtained, specifically including: establishing an inter-plane vector field through the second segmentation plane and the third segmentation plane, screening the first candidate point set, and obtaining a second candidate point set located between the vector fields.

[0023] The second candidate point set is obtained, specifically including:

[0024] All points in the first candidate point set are respectively constructed as vector fields perpendicular to the second segmentation plane and the third segmentation plane, and points with opposite directions of two vectors are selected as the second candidate point set.

[0025] Furthermore, the curvature of each group of points in the second candidate point set is calculated respectively, and ten points with the largest curvature in each group of points are selected.

[0026] Furthermore, a measurement point between the first center point and the second center point, one quarter of the way close to the first center point, is obtained; and combined with the second center point, the distances from the ten points with the largest curvature in each group to the measurement point and the second center point are measured.

[0027] Obtaining the tumor neck feature points specifically includes, based on the curvature principle, calculating the ten points with the largest curvature in the second candidate point set, and selecting the tumor neck feature points according to the distance weighted function.

[0028] Optionally, obtaining the tumor neck feature point specifically includes:

[0029] The curvature of each group of points in the second candidate point set is calculated respectively, and the ten points with the largest curvature in each group of points are selected.

[0030] A measurement point is obtained between the first center point and the second center point, which is one quarter of the way close to the first center point. Combined with the second center point, the distances from the ten points with the largest curvature in each group to the measurement point and the second center point are measured.

[0031] A distance weighted function equation is established through the two types of distances to obtain the shortest point of the two types of distances, that is, to obtain the optimal point of the tumor neck curvature in each group, that is, the tumor neck characteristic point;

[0032] Further, obtaining the tumor neck plane specifically includes:

[0033] A random sampling method including but not limited to RANSAC and LSC is used to sample the curvature points, and a total of three feature points are extracted.

[0034] A tumor neck plane is obtained through the three sampled tumor neck feature points, and the plane minimizes the sum of the distances from all tumor neck feature points to the plane.

[0035] The present application provides a device for automatically segmenting an aneurysm neck based on control points, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method for automatically segmenting an aneurysm neck based on control points as described in the present application.

[0036] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for automatically segmenting an aneurysm neck based on curvature described in the present application are implemented.

[0037] The present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the method for automatically segmenting an aneurysm neck based on curvature described in the present application.

[0038] The method for automatic segmentation of aneurysm neck based on curvature in this application has at least the following effects:

[0039] The present application locates the first segmentation plane, the second segmentation plane and the third segmentation plane intersecting the aneurysm and the parent artery by combining the first center point, the second center point, the first fulcrum point and the second fulcrum point to limit the range of the feature point of the neck. The first segmentation plane is rotated, and the curvature is used to obtain the optimal curvature point in each group of intersection points as the feature point of the neck. The sampling method is used to obtain the best neck plane, and the automatic positioning measurement of the neck plane of the aneurysm is realized. The present application locates the neck plane by the feature point of the neck, and controls the result error caused by the morphology of the aneurysm.

[0040] The present application utilizes computer graphics to automatically divide the tumor neck plane, thereby improving the efficiency and repeatability of morphological parameter calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flow chart of a method for automatically segmenting an aneurysm neck based on curvature in one embodiment of the present application;

[0042] Figure 2 A schematic diagram of a process of obtaining a first center point, a second center point, a first fulcrum, and a second fulcrum in one embodiment of the present application;

[0043] Figure 3 A schematic diagram of a process of obtaining a first segmentation plane, a second segmentation plane, and a third segmentation plane in an embodiment of the present application;

[0044] Figure 4A schematic diagram of a process of obtaining a first segmentation plane, a second segmentation plane, and a third segmentation plane in an embodiment of the present application;

[0045] Figure 5 A schematic diagram of a process for obtaining a first candidate point set and a second candidate point set in an embodiment of the present application;

[0046] Figure 6 This is a schematic diagram of a process of obtaining a first candidate point set in an embodiment of the present application;

[0047] Figure 7 This is a schematic diagram of a process of obtaining a second candidate point set in an embodiment of the present application;

[0048] Figure 8 This is a schematic diagram of the process of aneurysm neck feature points in one embodiment of the present application;

[0049] Fig. 9 It is a schematic diagram of the process and effect of the aneurysm neck feature points and the aneurysm neck plane in one embodiment of the present application;

[0050] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0051] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0052] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following is a clear and complete description of the technical solutions in the embodiments of this specification in conjunction with the drawings in the embodiments of this specification. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments of this specification, other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

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

[0054] It should be understood that when an element (such as a layer, film, region, or substrate) is described as being "on" another element, the element may be directly on the other element, or there may be intermediate elements. Moreover, in the specification and claims, when an element is described as being "connected" to another element, the element may be "directly connected" to the other element, or "connected" to the other element through a third element.

[0055] See also Figure 1 The present application provides a method for automatically segmenting an aneurysm neck based on curvature, comprising steps S100 to S600. Among them:

[0056] Step S100, based on DICOM medical image data, segment the parent artery and aneurysm images to establish a relevant blood vessel model, and obtain the centerline of the aneurysm and the parent artery;

[0057] Step S200, obtaining positioning points for positioning the splitting plane, wherein the positioning points include a first center point, a second center point, a first fulcrum, and a second fulcrum;

[0058] Step S300, obtaining a limiting plane for limiting the tumor neck site, specifically including a first segmentation plane established through the first center point, the second center point and the first fulcrum, a second segmentation plane established through the first center point, the second center point, the first fulcrum and the second fulcrum, and a third segmentation plane;

[0059] Step S400, obtaining multiple groups of first candidate point sets and multiple groups of second candidate point sets, specifically including rotating the first segmentation plane to intersect the parent artery and the aneurysm, obtaining multiple groups of intersection points as the first candidate point sets, establishing an inter-plane vector field through the second segmentation plane and the third segmentation plane, screening the first candidate point sets, and obtaining a second candidate point set located between the vector fields;

[0060] Step S500, obtaining the tumor neck feature points, specifically including, based on the curvature principle, calculating the ten points with the largest curvature in the second candidate point set, and selecting the tumor neck feature points according to the distance weighted function;

[0061] Step S600, using a random sampling method including but not limited to RANSAC and LSC random sampling methods, sampling the curvature points, and extracting three feature points in total. Obtaining the tumor neck plane through the three sampled tumor neck feature points.

[0062] In this embodiment, the first center point refers to the center line of the tumor-bearing artery and the aneurysm, the center line of the tumor-bearing artery and the center line of the aneurysm intersect, the second intersection refers to the end point of the aneurysm close to the dome of the tumor, and the first fulcrum and the second fulcrum refer to a point on each of the center lines on both sides of the first center point. A first vector is established by the first center point and the second center point, and the first center point and the first fulcrum and the second fulcrum are respectively used to establish a second vector, and the angles of the first vector and the two vectors are compared, and the vector on the side with a larger angle is defined as the fulcrum where the second vector is located as the first fulcrum, and the fulcrum where the third vector is located on the other side is the second fulcrum.

[0063] In some embodiments, the sub-steps and extended steps of each step of the method for automatic segmentation of aneurysm neck based on control points are further described. It includes (1) image reading and surface reconstruction; (2) obtaining aneurysm positioning points; (3) obtaining aneurysm limiting plane; (4) obtaining a first candidate point set and a second candidate point set; (5) obtaining aneurysm neck feature points; (6) obtaining aneurysm neck plane. Among them, (1) corresponds to step S100; (2) obtaining aneurysm neck positioning points corresponds to step S200; (3) obtaining a limiting plane corresponds to step S300; (4) obtaining a first candidate point set and a second candidate point set corresponds to step S400; (5) obtaining aneurysm neck feature points corresponds to step S500; (6) obtaining aneurysm neck plane corresponds to step S600.

[0064] (1) Image reading and surface reconstruction.

[0065] Read vascular images, including but not limited to three-dimensional image sequences of DSA, CTA, and MRA. Use thresholding, level set, or artificial intelligence segmentation models (such as 3D UNet) to segment the image sequence, and then use the marching cubes algorithm to reconstruct its surface to obtain a vascular model based on the aneurysm and the parent artery. Calculate the voronoi diagram of the vascular model, and use the maximum sphere diameter algorithm and fast marching method to obtain the vascular centerline from the entrance to the exit.

[0066] See also Figure 2 , (2) Obtain the aneurysm location point,

[0067] The center lines of the parent artery and the aneurysm are obtained, and the intersection of the center line of the parent artery and the center line of the aneurysm is defined as the first center point, and the end point of the aneurysm close to the dome of the aneurysm is defined as the second center point. A point on each side of the center line of the first center point is defined as the first fulcrum and the second fulcrum respectively.

[0068] See also Figure 3 and Figure 4 (3) obtaining the aneurysm limiting plane as a sub-step of step S300, specifically comprising:

[0069] Step S310, obtain a first vector through the first center point and the second center point, respectively establish two vectors with the first fulcrum and the second fulcrum, compare the angles of the first vector and the two vectors, and define the vector on the side with a larger angle as the second vector, and the other side as the third vector;

[0070] Step S320, a perpendicular vector between the first vector and the second vector is defined as a first normal vector, and a first segmentation plane is obtained by combining the first center point, the second center point, and the support point where the second vector is located;

[0071] Step S330, the first fulcrum and the second fulcrum form a fourth vector, and combined with the first normal vector, obtain a second normal vector perpendicular to the fourth vector and the first normal vector;

[0072] Step S340: The second normal vector is combined with the first center point to obtain a second segmentation plane, and the second center point is combined to obtain a third segmentation plane.

[0073] See also Figure 5 , Figure 6 and Figure 7 , (4) obtaining the first candidate point set and the second candidate point set as sub-steps of step S400, specifically including:

[0074] Step S410, the second normal vector is used as the rotation axis, and the first segmentation plane is rotated along the axis. Each time, the intersection of the rotation plane, the parent artery and the aneurysm model is used as a set of first candidate point sets, and the rotation is 360° in total, and finally multiple sets of first candidate point sets are obtained;

[0075] Step S420, constructing vector fields perpendicular to the second segmentation plane and the third segmentation plane for all points in the first candidate point set, and selecting points with opposite directions of two vectors as the second candidate point set;

[0076] Step S430, combining each group of second candidate point sets with the second normal vector, and using the cross product formula to divide each group of second candidate point sets into two groups according to the position of the point sets on the left or right side of the second normal vector, so that all the obtained optimized second tumor neck point sets are arranged in group order according to the plane rotation direction.

[0077] See also Figure 8 and Fig. 9 , (5) Obtain tumor neck feature points

[0078] Step S510, performing curvature analysis on each group of points in the second candidate point set, and selecting ten points with the largest curvature in each group of points;

[0079] Step S520, obtaining a measurement point between the first center point and the second center point, which is one quarter of the distance on one side of the first center point, and combining the second center point, measuring the distances from the ten points with the largest curvature in each group to the measurement point and the second center point;

[0080] Step S530: establishing a distance weighted function equation through two types of distances to obtain the optimal point of the tumor neck curvature in each group, that is, the tumor neck feature point.

[0081] (6) Obtain the tumor neck plane.

[0082] A random sampling method including but not limited to RANSAC and LSC is used to sample the curvature points, and a total of three feature points are extracted; a tumor neck plane is obtained through the three sampled tumor neck feature points, and the plane minimizes the total distance from all tumor neck feature points to the plane.

[0083] The embodiments of the present application use computational graphics algorithms to automatically divide the aneurysm neck plane, thereby improving the repeatability of morphological parameter calculations. For doctors, the learning threshold and workload of aneurysm morphological assessment are reduced; for hospitals, the capacity to receive and treat patients is indirectly improved; for patients, more reliable assessment methods can provide more reliable diagnostic results, thereby reducing the risk of aneurysm rupture and the risk of excessive intervention to a certain extent.

[0084] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0085] In one embodiment, a device for automatically segmenting an aneurysm neck based on curvature is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0086] Step S100, based on DICOM medical image data, segment the parent artery and aneurysm images to establish a relevant blood vessel model, and obtain the centerline of the aneurysm and the parent artery;

[0087] Step S200, obtaining positioning points for positioning the splitting plane, wherein the positioning points include a first center point, a second center point, a first fulcrum, and a second fulcrum;

[0088] Step S300, obtaining a limiting plane for limiting the tumor neck site, specifically including a first segmentation plane established through the first center point, the second center point and the first fulcrum, a second segmentation plane established through the first center point, the second center point, the first fulcrum and the second fulcrum, and a third segmentation plane;

[0089] Step S400, obtaining multiple groups of first candidate point sets and multiple groups of second candidate point sets, specifically including rotating the first segmentation plane to intersect the parent artery and the aneurysm, obtaining multiple groups of intersection points as the first candidate point sets, establishing an inter-plane vector field through the second segmentation plane and the third segmentation plane, screening the first candidate point sets, and obtaining a second candidate point set located between the vector fields;

[0090] Step S500, obtaining the tumor neck feature points, specifically including, based on the curvature principle, calculating the ten points with the largest curvature in the second candidate point set, and selecting the tumor neck feature points according to the distance weighted function;

[0091] Step S600, using a random sampling method including but not limited to RANSAC and LSC random sampling methods, sampling the curvature points, and extracting three feature points in total. Obtaining the tumor neck plane through the three sampled tumor neck feature points.

[0092] In one embodiment, a system for automatically segmenting an aneurysm neck based on curvature is provided, and when the system executes a computer program, the following steps are implemented:

[0093] Step S100, based on DICOM medical image data, segment the parent artery and aneurysm images to establish a relevant blood vessel model, and obtain the centerline of the aneurysm and the parent artery;

[0094] Step S200, obtaining positioning points for positioning the splitting plane, wherein the positioning points include a first center point, a second center point, a first fulcrum, and a second fulcrum;

[0095] Step S300, obtaining a limiting plane for limiting the tumor neck site, specifically including a first segmentation plane established through the first center point, the second center point and the first fulcrum, a second segmentation plane established through the first center point, the second center point, the first fulcrum and the second fulcrum, and a third segmentation plane;

[0096] Step S400, obtaining multiple groups of first candidate point sets and multiple groups of second candidate point sets, specifically including rotating the first segmentation plane to intersect the parent artery and the aneurysm, obtaining multiple groups of intersection points as the first candidate point sets, establishing an inter-plane vector field through the second segmentation plane and the third segmentation plane, screening the first candidate point sets, and obtaining a second candidate point set located between the vector fields;

[0097] Step S500, obtaining the tumor neck feature points, specifically including, based on the curvature principle, calculating the ten points with the largest curvature in the second candidate point set, and selecting the tumor neck feature points according to the distance weighted function;

[0098] Step S600, using a random sampling method including but not limited to RANSAC and LSC random sampling methods, sampling the curvature points, and extracting three feature points in total. Obtaining the tumor neck plane through the three sampled tumor neck feature points.

[0099] In one embodiment, the device, system, etc. for automatically segmenting the neck of an aneurysm based on curvature may use a computer device, which may be a terminal, and includes a structure diagram as shown in FIG. Fig.10 The device, electronic device, non-volatile computer storage medium and method provided in the embodiments of this specification correspond to each other, and therefore, the device, electronic device and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding device, electronic device and non-volatile computer storage medium will not be described in detail here.

[0100] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many improvements to method flows today can be regarded as direct improvements to hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming themselves, without asking chip manufacturers to design and produce "logic compiler" software to implement it. It is similar to the software compiler used in program development, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that it is easy to obtain a hardware circuit that implements the logical method flow by simply performing some logic programming on the method flow using the above-mentioned hardware description languages ​​and programming it into an integrated circuit.

[0101] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0102] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0103] For the convenience of description, the above device is described by being divided into various units according to their functions and described separately. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware. It should be understood by those skilled in the art that this specification embodiment can be provided as a method, system, or computer program product. Therefore, this specification embodiment can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification embodiment can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0105] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0107] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory. The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0108] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0109] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0110] The specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0111] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0112] The above is only an embodiment of this specification and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for automatic segmentation of aneurysm neck based on curvature, characterized in that: include: Based on DICOM medical imaging data, the parent artery and aneurysm images are segmented to establish the relevant vascular model and obtain the centerline of the aneurysm and parent artery; Obtaining positioning points for positioning the splitting plane, the positioning points comprising a first center point, a second center point, a first fulcrum, and a second fulcrum; Obtaining a limiting plane for limiting the tumor neck site, specifically including a first segmentation plane established through the first center point, the second center point and the first fulcrum, a second segmentation plane established through the first center point, the second center point, the first fulcrum and the second fulcrum, and a third segmentation plane; Obtaining multiple groups of first candidate point sets and multiple groups of second candidate point sets, specifically including rotating the first segmentation plane to intersect the parent artery and the aneurysm to obtain multiple groups of intersection points as the first candidate point sets, establishing an inter-plane vector field through the second segmentation plane and the third segmentation plane, screening the first candidate point set, and obtaining a second candidate point set located between the vector fields; Obtaining the tumor neck feature points specifically includes, based on the curvature principle, calculating the ten points with the largest curvature in the second candidate point set, and selecting the tumor neck feature points according to the distance weighted function.

2. The method according to claim 1, characterized in that Obtaining positioning points for positioning segmentation, the first center point, the second center point, the first fulcrum, and the second fulcrum, specifically includes: The center lines of the parent artery and the aneurysm are obtained, and the intersection of the center line of the parent artery and the center line of the aneurysm is defined as the first center point, and the end point of the aneurysm close to the dome of the aneurysm is defined as the second center point. A point on each side of the center line of the first center point is defined as the first fulcrum and the second fulcrum respectively.

3. The method according to claim 1, characterized in that Obtaining the segmentation plane for limiting the tumor neck site, specifically including: A first vector is established by the first center point and the second center point, two vectors are established with the first center point, the first fulcrum and the second fulcrum respectively, the angles of the first vector and the two vectors are compared, and the vector on the side with the larger angle is defined as the fulcrum where the second vector is located as the first fulcrum, and the fulcrum where the third vector is located on the other side is defined as the second fulcrum; The vector perpendicular to both the first vector and the second vector is defined as a first normal vector, and a first segmentation plane is obtained by combining the first center point, the second center point and the support point where the second vector is located; The first support point and the second support point form a fourth vector, and combined with the first normal vector, a second normal vector perpendicular to the fourth vector and the first normal vector is obtained; The second normal vector is combined with the first center point to obtain a second segmentation plane, and the third segmentation plane is obtained by combining the second center point.

4. The method according to claim 1, characterized in that Obtain the first candidate point set, including: The second normal vector is the rotation axis, and the first segmentation plane is rotated along this axis. Each time the intersection of the rotation plane and the tumor-bearing artery and the aneurysm model is used as a set of first candidate point sets, and a total rotation of 360° is performed to finally obtain multiple sets of first candidate point sets.

5. The method according to claim 1, characterized in that The second candidate point set is obtained, specifically including: All points in the first candidate point set are respectively constructed as vector fields perpendicular to the second segmentation plane and the third segmentation plane, and points with opposite directions of two vectors are selected as the second candidate point set.

6. The method according to claim 5, characterized in that The optimized second candidate point set is obtained. The optimization process includes: Each group of second candidate point sets is combined with the second normal vector, and each group of second candidate point sets is divided into two groups according to the position of the point set at the second normal vector, on the left or right side, using the cross product formula, so as to facilitate the subsequent unilateral curvature calculation point selection, so that all the obtained optimized second tumor neck point sets are arranged in group order according to the plane rotation direction, even if the feature points can eventually be connected by straight lines to form a complete tumor neck segmentation line, there is no cross connection between the feature points.

7. The method according to claim 1, characterized in that Obtaining the tumor neck feature point specifically includes: Perform curvature analysis on each group of points in the second candidate point set, and select the ten points with the largest curvature in each group of points; Obtain a measurement point between the first center point and the second center point, which is one quarter of the distance on one side of the first center point. Combined with the second center point, measure the distances from the ten points with the largest curvature in each group to the measurement point and the second center point. A distance weighted function equation is established through the two types of distances to obtain the shortest point of the two types of distances, that is, the optimal point of the tumor neck curvature in each group, that is, the tumor neck characteristic point.

8. The method according to claim 1, characterized in that Obtaining the tumor neck plane specifically includes: A random sampling method including but not limited to RANSAC and LSC is used to sample the curvature points, and a total of three feature points are extracted; A tumor neck plane is obtained through the three sampled tumor neck feature points, and the plane minimizes the sum of the distances from all tumor neck feature points to the plane.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the steps of the method for automatically segmenting an aneurysm neck based on curvature as described in any one of claims 1 to 8.

10. A processor, characterized in that: The processor is used to run a program, wherein the processor is used to execute the steps of the method for automatic segmentation of an aneurysm neck based on curvature as described in any one of claims 1 to 8 when the program is running.

11. A measurement system, comprising a measurement device for automatic segmentation of an aneurysm neck, characterized in that: The system device is used to execute the steps of the method for automatic segmentation of aneurysm neck based on curvature as described in any one of claims 1 to 8.