Method, system and electronic device for planning puncture and catheterization path for spontaneous cerebral hemorrhage

Abstract

The invention discloses a spontaneous cerebral hemorrhage puncture and catheterization path planning method, system and electronic equipment, and relates to the technical field of puncture and catheterization path planning. The method comprises the following steps: obtaining a cranial CT image of a target user; preprocessing the cranial CT image, and inputting the preprocessed cranial CT image into a skull hematoma segmentation model to obtain an intracranial hematoma area and a skull area of ​​the target user; determining a puncture opening area and a target area according to the intracranial hematoma area and the skull area of ​​the target user; performing ellipsoid fitting on the intracranial hematoma area of ​​the target user to obtain an intracranial hematoma ellipsoid, and searching for a puncture opening point and a target point in the puncture opening area and the target point area, so that the angle between a straight line passing through the puncture opening point and the target point and the major axis of the intracranial hematoma ellipsoid is minimized, thereby realizing automatic, efficient and accurate planning of the spontaneous cerebral hemorrhage puncture and catheterization path.

Description

Technical Field

[0001] The present invention relates to the technical field of puncture and catheterization path planning, and in particular to a method, system and electronic equipment for spontaneous cerebral hemorrhage puncture and catheterization path planning based on a neural network. Background Art

[0002] Intracranial hematoma caused by spontaneous cerebral hemorrhage has the characteristics of high mortality, high disability rate and high morbidity rate in clinical practice. Puncture and catheter drainage is a relatively minimally invasive surgical treatment for intracranial hematoma. It is simple, short in operation time, and less traumatic, and can effectively alleviate the space-occupying effect of intracranial hematoma. However, the effect of this surgical treatment method depends on the accuracy of the puncture and catheter placement. The key to the formulation of the puncture and catheterization path lies in the location of the puncture opening point and the target point. The location of the traditional puncture opening point and the target point needs to be determined by a neurosurgeon with certain experience, which is subjective, and has low accuracy and repeatability. Summary of the invention

[0003] The purpose of the present invention is to provide a spontaneous cerebral hemorrhage puncture catheterization path planning method, system and electronic equipment, which can efficiently and accurately perform intracranial hematoma puncture catheterization path planning.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] In a first aspect, the present invention provides a method for planning a puncture and catheterization path for spontaneous cerebral hemorrhage, comprising:

[0006] Acquire a cranial CT image of a target user; the cranial CT image includes a plurality of cranial images;

[0007] Preprocessing the cranial CT image, and inputting the preprocessed cranial CT image into a skull hematoma segmentation model to obtain an intracranial hematoma region and a skull region of a target user; wherein the skull hematoma segmentation model is determined based on a neural network;

[0008] Determining a puncture opening area and a target area according to the intracranial hematoma area and the skull area of ​​the target user;

[0009] An ellipsoid is fitted on the intracranial hematoma area of ​​the target user to obtain an intracranial hematoma ellipsoid, and a puncture opening point and a target point are found in the puncture opening area and the target point area, so that the angle between the straight line passing through the puncture opening point and the target point and the long axis of the intracranial hematoma ellipsoid is minimized, thereby realizing the puncture and catheterization path planning for spontaneous cerebral hemorrhage.

[0010] In a second aspect, the present invention provides a spontaneous cerebral hemorrhage puncture and catheterization path planning system, comprising:

[0011] A cranial CT image acquisition module is used to acquire a cranial CT image of a target user; the cranial CT image includes a plurality of cranial images;

[0012] An intracranial hematoma region and skull region determination module, used to preprocess the cranial CT image and input the preprocessed cranial CT image into a skull hematoma segmentation model to obtain the intracranial hematoma region and skull region of the target user; wherein the skull hematoma segmentation model is determined based on a neural network;

[0013] A puncture opening area and target area determination module, used to determine the puncture opening area and target area according to the intracranial hematoma area and the skull area of ​​the target user;

[0014] The puncture opening point and target point determination module is used to perform ellipsoid fitting on the intracranial hematoma area of ​​the target user to obtain the intracranial hematoma ellipsoid, and to search for the puncture opening point and the target point in the puncture opening area and the target point area so that the angle between the straight line passing through the puncture opening point and the target point and the long axis of the intracranial hematoma ellipsoid is minimized, thereby realizing the puncture and catheterization path planning for spontaneous cerebral hemorrhage.

[0015] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the spontaneous cerebral hemorrhage puncture and catheterization path planning method according to the first aspect.

[0016] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0017] The present invention firstly divides the intracranial hematoma area and the skull area of ​​the target user efficiently and accurately through a neural network; then, according to the intracranial hematoma area and the skull area of ​​the target user, determines the puncture opening area and the target area; finally, performs ellipsoid fitting on the intracranial hematoma area of ​​the target user to obtain the intracranial hematoma ellipsoid, and searches for the puncture opening point and the target point in the puncture opening area and the target point area, so that the angle between the straight line passing through the puncture opening point and the target point and the long axis of the intracranial hematoma ellipsoid is minimized, thereby realizing automatic planning of the puncture and catheterization path for spontaneous cerebral hemorrhage and reducing brain damage at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1A flow chart of a spontaneous cerebral hemorrhage puncture and catheterization path planning method provided in an embodiment of the present invention;

[0020] Figure 2 This is a structural diagram of a spontaneous cerebral hemorrhage puncture and catheterization path planning system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] Embodiment 1

[0024] The present embodiment provides a method for puncture and catheterization path planning for spontaneous cerebral hemorrhage, which mainly includes preprocessing, segmentation of intracranial hematoma area and skull area, positioning of puncture opening area and target area, and puncture and catheterization path planning. Among them, preprocessing mainly includes image registration and regularization to ensure that all images are in the same orientation and highlight important related areas; puncture and catheterization path planning mainly includes combining the puncture opening area and the target area to find the longest straight line passing through the intracranial hematoma to achieve spontaneous cerebral hemorrhage puncture and catheterization path planning.

[0025] like Figure 1 As shown, this embodiment provides a method for puncture and catheterization path planning for spontaneous cerebral hemorrhage, including:

[0026] Step 101: Acquire a cranial CT image of a target user; the cranial CT image includes a plurality of cranial images.

[0027] Step 102: preprocess the cranial CT image, and input the preprocessed cranial CT image into a skull hematoma segmentation model to obtain the intracranial hematoma area and skull area of ​​the target user; wherein the skull hematoma segmentation model is determined based on a neural network.

[0028] Step 103: Determine the puncture opening area and the target area according to the intracranial hematoma area and the skull area of ​​the target user.

[0029] Step 104: Perform ellipsoid fitting on the intracranial hematoma area of ​​the target user to obtain an intracranial hematoma ellipsoid, and search for a puncture opening point and a target point in the puncture opening area and the target point area, so that the angle between the straight line passing through the puncture opening point and the target point and the long axis of the intracranial hematoma ellipsoid is minimized, thereby realizing spontaneous cerebral hemorrhage puncture and catheterization path planning.

[0030] In the embodiment of the present invention, an ellipsoid fitting algorithm of the least square method may be used to perform ellipsoid fitting on the intracranial hematoma region of the target user to obtain an intracranial hematoma ellipsoid.

[0031] As an optional implementation manner, the preprocessing of the cranial CT image described in this embodiment specifically includes:

[0032] Image registration and regularization processing are performed on each of the cranial brain images to obtain a preprocessed cranial brain CT image.

[0033] Since the scanned brain CT images may be in different areas of the image and have different orientations, it is necessary to adjust all brain images to the same position and orientation through image registration.

[0034] Furthermore, this embodiment adjusts the position and direction of the brain image to the same template through rigid registration.

[0035] As an optional implementation, the neural network described in this embodiment is a semantic segmentation network, preferably a U-Net network.

[0036] The characteristic of U-Net is that it has a symmetrical structure, which consists of a symmetrical encoder and decoder. The encoder is responsible for gradually downsampling the input image and extracting high-level features. The decoder gradually restores the encoder output through upsampling operations, and finally obtains a segmentation result of the same size as the input image.

[0037] Furthermore, the process of determining the skull hematoma segmentation model is as follows:

[0038] A skull hematoma segmentation model is determined based on multiple sample data and a U-Net network; wherein the sample data includes input data and corresponding label data; the input data is a preprocessed skull image of a sample user; and the label data is an intracranial hematoma region image and a skull region image corresponding to the preprocessed skull image of the sample user.

[0039] As an optional implementation manner, before executing step 103, the method described in this embodiment further includes:

[0040] A 3D connectivity analysis is performed on all the intracranial hematoma regions of the target user to determine all connected domains, and the largest connected domain is determined as the final intracranial hematoma region of the target user.

[0041] Because there may be multiple intracranial hematoma areas in the brain, but small intracranial hematoma areas generally do not require surgical treatment. Therefore, it is necessary to carry out connected domain analysis on the intracranial hematoma area segmentation result. Different from the general 2D situation, the present embodiment needs to analyze 3D connectivity, so when analyzing 3D connectivity, it is necessary to consider the connectivity of adjacent 26 pixels, that is to say, if a voxel point is identified as intracranial hematoma, and among the adjacent 26 voxel points around it, if there is also a voxel point that is also identified as intracranial hematoma, then these two voxel points just belong to the same intracranial hematoma. After obtaining all connected domains, retain a connected region with the largest volume therein as the final intracranial hematoma region.

[0042] Step 103 described in this embodiment specifically includes:

[0043] (1) The surface area of ​​the lower third of the target user's final intracranial hematoma area is determined as the target area; (2) The puncture opening area is determined based on the target user's skull area, the first condition and the second condition; wherein the first condition is that the puncture opening point needs to be on the skull above the frontal sinus; the second condition is that the puncture opening point needs to avoid the midline of the brain, and the puncture opening point and the final intracranial hematoma area are located on the same side.

[0044] Furthermore, the puncture opening area is determined according to the target user's skull area, the first condition and the second condition, specifically including: first, according to the preprocessed brain CT image, the background area, nasal cavity area and frontal sinus area of ​​the skull are determined; secondly, using a 2D connected domain analysis method, within the frontal sinus area, the point closest to the top of the brain is determined as the highest point of the frontal sinus; according to the target user's skull area, the first condition, the second condition and the highest point of the frontal sinus, the puncture opening area is determined; wherein the puncture opening area is the intersection area of ​​the skull area with the highest point of the frontal sinus and the skull area that meets the first condition and the second condition.

[0045] As an optional implementation manner, step 104 described in this embodiment specifically includes:

[0046] The puncture opening point and the target point are found in the puncture opening area and the target point area, so that the angle between the straight line passing through the puncture opening point and the target point and the long axis of the intracranial hematoma ellipsoid is as small as possible, and the distance through which the straight line passes through the normal area of ​​the brain is as short as possible, thereby realizing the puncture and catheterization path planning for spontaneous cerebral hemorrhage.

[0047] Among them, the above multi-objective function is solved by using optimization algorithms such as particle swarm, so as to obtain the optimal puncture opening point and the optimal target point, thereby realizing the puncture and catheterization path planning for spontaneous cerebral hemorrhage. The above multi-objective function is a function that the angle between the straight line and the long axis of the intracranial hematoma ellipsoid is as small as possible, and the distance through which the straight line passes through the normal brain area is as short as possible.

[0048] The method described in this embodiment was used to test 50 brain CT images, and the doctor satisfaction with the planned puncture and catheterization paths reached 90%, indicating that the present invention can effectively realize the automatic planning of puncture and catheterization paths for spontaneous cerebral hemorrhage.

[0049] Embodiment 2

[0050] In order to execute the method corresponding to the above-mentioned embodiment 1 and realize the corresponding functions and technical effects, a spontaneous cerebral hemorrhage puncture and catheterization path planning system is provided below.

[0051] like Figure 2 As shown, this embodiment provides a spontaneous cerebral hemorrhage puncture catheterization path planning system, including:

[0052] The cranial CT image acquisition module 201 is used to acquire the cranial CT image of the target user; the cranial CT image includes a plurality of cranial images.

[0053] The intracranial hematoma area and skull area determination module 202 is used to preprocess the brain CT image and input the preprocessed brain CT image into the skull hematoma segmentation model to obtain the intracranial hematoma area and skull area of ​​the target user; wherein the skull hematoma segmentation model is determined based on a neural network.

[0054] The puncture opening area and target area determination module 203 is used to determine the puncture opening area and the target area according to the intracranial hematoma area and the skull area of ​​the target user.

[0055] The puncture opening point and target point determination module 204 is used to perform ellipsoid fitting on the intracranial hematoma area of ​​the target user to obtain the intracranial hematoma ellipsoid, and to search for the puncture opening point and the target point in the puncture opening area and the target point area, so that the angle between the straight line passing through the puncture opening point and the target point and the long axis of the intracranial hematoma ellipsoid is minimized, thereby realizing the puncture and catheterization path planning for spontaneous cerebral hemorrhage.

[0056] Embodiment 3

[0057] An embodiment of the present invention provides an electronic device including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the spontaneous cerebral hemorrhage puncture and catheterization path planning method of embodiment one.

[0058] Optionally, the above-mentioned electronic device may be a server.

[0059] In addition, an embodiment of the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the spontaneous cerebral hemorrhage puncture and catheterization path planning method of embodiment 1.

[0060] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0061] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A spontaneous cerebral hemorrhage puncture catheterization path planning method, characterized in that: include: Acquire a cranial CT image of a target user; the cranial CT image includes a plurality of cranial images; The cranial CT image is preprocessed, and the preprocessed cranial CT image is input into a skull hematoma segmentation model to obtain an intracranial hematoma region and a skull region of a target user; wherein the skull hematoma segmentation model is determined based on a neural network; and the skull hematoma segmentation model is determined as follows: Determine a skull hematoma segmentation model according to a plurality of sample data and a neural network; wherein the sample data includes input data and corresponding label data; the input data is a preprocessed skull image of a sample user; the label data is an intracranial hematoma region image and a skull region image corresponding to the preprocessed skull image of the sample user; Determining a puncture opening area and a target area according to the intracranial hematoma area and the skull area of ​​the target user; Ellipsoid fitting is performed on the intracranial hematoma area of ​​the target user to obtain an intracranial hematoma ellipsoid, and a puncture opening point and a target point are searched in the puncture opening area and the target point area, so that the angle between the straight line passing through the puncture opening point and the target point and the long axis of the intracranial hematoma ellipsoid is minimized, thereby realizing spontaneous cerebral hemorrhage puncture catheterization path planning; Preprocessing the brain CT image specifically includes: Performing image registration and regularization processing on each of the cranial brain images to obtain a preprocessed cranial brain CT image; Before executing the step of determining the puncture opening area and the target area according to the intracranial hematoma area and the skull area of ​​the target user, the method further includes: A 3D connectivity analysis is performed on all the intracranial hematoma regions of the target user to determine all connected domains, and the largest connected domain is determined as the final intracranial hematoma region of the target user.

2. A spontaneous cerebral hemorrhage puncture and catheterization path planning method according to claim 1, characterized in that: The preprocessed brain CT image is input into the skull hematoma segmentation model to obtain the target user's intracranial hematoma area and skull area, including: The preprocessed brain images are sequentially input into the skull hematoma segmentation model to obtain the intracranial hematoma area image and the skull area image corresponding to each preprocessed brain image, and the intracranial hematoma area image and the skull area image corresponding to each preprocessed brain image are summarized to obtain the intracranial hematoma area and the skull area of ​​the target user.

3. A spontaneous cerebral hemorrhage puncture and catheterization path planning method according to claim 1, characterized in that: The neural network is a U-Net network.

4. A spontaneous cerebral hemorrhage puncture and catheterization path planning method according to claim 1, characterized in that: According to the intracranial hematoma area and the skull area of ​​the target user, the puncture opening area and the target area are determined, specifically including: The lower third of the surface area of ​​the target user's final intracranial hematoma area is determined as the target area; The puncture opening area is determined based on the target user's skull area, the first condition and the second condition; wherein, the first condition is that the puncture opening point needs to be on the skull above the frontal sinus; the second condition is that the puncture opening point needs to avoid the midline of the brain, and the puncture opening point and the final intracranial hematoma area are located on the same side.

5. A spontaneous cerebral hemorrhage puncture and catheterization path planning method according to claim 1, characterized in that: Searching for a puncture opening point and a target point in the puncture opening area and the target point area so that the angle between the straight line passing through the puncture opening point and the target point and the long axis of the intracranial hematoma ellipsoid is minimized, thereby realizing spontaneous cerebral hemorrhage puncture catheterization path planning, specifically includes: The puncture opening point and the target point are found in the puncture opening area and the target point area, so that the angle between the straight line passing through the puncture opening point and the target point and the long axis of the intracranial hematoma ellipsoid is as small as possible, and the distance through which the straight line passes through the normal area of ​​the brain is as short as possible, thereby realizing the puncture and catheterization path planning for spontaneous cerebral hemorrhage.

6. A spontaneous cerebral hemorrhage puncture catheterization path planning system, characterized in that: include: A cranial CT image acquisition module is used to acquire a cranial CT image of a target user; the cranial CT image includes a plurality of cranial images; The intracranial hematoma region and skull region determination module is used to preprocess the cranial CT image and input the preprocessed cranial CT image into the skull hematoma segmentation model to obtain the intracranial hematoma region and skull region of the target user; wherein the skull hematoma segmentation model is determined based on a neural network; the determination process of the skull hematoma segmentation model is as follows: Determine a skull hematoma segmentation model according to a plurality of sample data and a neural network; wherein the sample data includes input data and corresponding label data; the input data is a preprocessed skull image of a sample user; the label data is an intracranial hematoma region image and a skull region image corresponding to the preprocessed skull image of the sample user; A puncture opening area and target area determination module, used to determine the puncture opening area and target area according to the intracranial hematoma area and the skull area of ​​the target user; The puncture opening point and target point determination module is used to perform ellipsoid fitting on the intracranial hematoma area of ​​the target user to obtain the intracranial hematoma ellipsoid, and to search for the puncture opening point and the target point in the puncture opening area and the target point area, so that the angle between the straight line passing through the puncture opening point and the target point and the long axis of the intracranial hematoma ellipsoid is minimized, thereby realizing the puncture and catheterization path planning for spontaneous cerebral hemorrhage; The intracranial hematoma region and skull region determination module is further used to perform image registration and regularization processing on each of the cranial brain images to obtain a preprocessed cranial brain CT image; The puncture opening area and target area determination module is also used to perform 3D connectivity analysis on all the intracranial hematoma areas of the target user, determine all connected domains, and determine the largest connected domain as the final intracranial hematoma area of ​​the target user.

7. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the spontaneous cerebral hemorrhage puncture and catheterization path planning method according to any one of claims 1 to 5.

Images