A system and method for predicting the prognosis of craniocerebral trauma based on a three-dimensional model

Abstract

The present application discloses a system and method for predicting the prognosis of craniocerebral trauma based on a three-dimensional model, which belongs to the field of medical care systems. The present application obtains a feature sequence reflecting the quality of craniocerebral healing based on a three-dimensional model of the patient's craniocerebral, obtains data reflecting the quality of craniocerebral healing through data processing, evaluates the quality of healing based on the acquired feature sequence reflecting the quality of craniocerebral healing, accurately obtains features reflecting the quality of craniocerebral healing, accurately analyzes the features of the quality of craniocerebral healing, quickly and accurately discovers abnormal recovery, improves the accuracy of craniocerebral trauma recovery prediction, and solves the problem of low accuracy of craniocerebral trauma recovery prediction in the prior art.

Description

Technical Field

[0001] The present application belongs to the field of medical care systems, and more specifically, is a system and method for predicting the prognosis of craniocerebral trauma based on a three-dimensional model. Background Art

[0002] Craniocerebral trauma refers to the damage to the soft tissue and dura mater of the head caused by external forces. This kind of injury may be caused by collision, fall, accident, etc., which usually leads to damage to the scalp, skull, dura mater, arachnoid and other structures, and may cause brain tissue contusion, bleeding and other problems. The severity of craniocerebral trauma varies from individual to individual, and may cause different degrees of neurological dysfunction, or even endanger life. The symptoms of craniocerebral trauma depend on the site and severity of the injury, and may include headache, nausea and vomiting, loss of consciousness, limb weakness, speech disorders, etc. Measures for the treatment of craniocerebral trauma include surgical treatment, neuroprotective agents, intracranial pressure-reducing drugs, etc., which aim to directly solve the structural abnormalities or functional disorders caused by craniocerebral injury and improve symptoms by removing the cause. After craniocerebral trauma surgery, it is necessary to predict and analyze the patient's recovery effect, and then a craniocerebral trauma prognosis prediction and analysis system is needed;

[0003] In the process of predicting and analyzing the patient's recovery effect, the existing technology usually only analyzes the wound healing through the recovery of the wound surface. The feature sequence extracted to reflect the quality of craniocerebral healing is not specific. The shape of the wound surface and the uniformity of wound healing are not considered when analyzing the wound healing. This leads to low accuracy in predicting the recovery of craniocerebral trauma. Most of the existing technologies have the above problems.

[0004] In order to solve the problems raised by the background technology, the present application designs a system and method for predicting and analyzing the prognosis of craniocerebral trauma based on a three-dimensional model. Summary of the invention

[0005] In order to address the deficiencies in the prior art mentioned in the background technology, the present application proposes a system and method for predicting the prognosis of craniocerebral trauma based on a three-dimensional model. A feature sequence reflecting the quality of craniocerebral healing is obtained based on the three-dimensional model of the patient's craniocerebral brain, data reflecting the quality of craniocerebral healing is obtained through data processing, the healing quality is evaluated based on the acquired feature sequence reflecting the quality of craniocerebral healing, the healing risk is evaluated based on the evaluated healing quality, and a healing warning is performed based on the healing risk assessment result. The features reflecting the quality of craniocerebral healing are accurately obtained, the features of the quality of craniocerebral healing are accurately analyzed, and abnormal recovery situations are quickly and accurately discovered, thereby improving the accuracy of prediction of craniocerebral trauma recovery.

[0006] To achieve the above objectives, this application provides the following technical solutions:

[0007] In a first aspect, the present application provides a method for predicting and analyzing the prognosis of craniocerebral trauma based on a three-dimensional model, which specifically comprises the following steps:

[0008] Step 1: Obtain the prognosis and healing images of craniocerebral treatment, construct a three-dimensional model of the patient's craniocerebral brain, and intuitively reflect the patient's craniocerebral rehabilitation status;

[0009] Step 2: obtaining a feature sequence reflecting the quality of craniocerebral healing based on the patient's craniocerebral three-dimensional model, and performing data processing to obtain data reflecting the quality of craniocerebral healing;

[0010] Step 3, evaluating the healing quality based on the acquired characteristic sequence reflecting the healing quality of the craniocerebral area;

[0011] Step 4: Perform a healing risk assessment based on the assessed healing quality, and perform a healing warning based on the healing risk assessment result.

[0012] As a preferred technical solution of the method for predicting and analyzing the prognosis of craniocerebral trauma based on a three-dimensional model, the specific content of step 1 is:

[0013] Step 11: Obtain the prognosis and healing images of craniocerebral treatment through medical imaging equipment, and obtain the previously constructed three-dimensional model of the patient's craniocerebral brain. The three-dimensional model of the patient's craniocerebral brain is constructed by medical staff before the patient's surgery through model construction;

[0014] Step 12. Based on the segmented prognosis healing image of cranial and brain treatment, use three-dimensional reconstruction software to map the prognosis healing image of cranial and brain treatment into the patient's cranial and brain three-dimensional model. It should be noted here that how to construct the patient's cranial and brain three-dimensional model through model construction is a conventional technical means of three-dimensional construction in the prior art, which can be achieved through existing medical three-dimensional construction software. At the same time, this is not the main point of the invention of this application. Here, only a brief description of the construction method of the three-dimensional model is given, so it will not be described in detail here.

[0015] As a preferred technical solution of the method for predicting and analyzing the prognosis of craniocerebral trauma based on a three-dimensional model, the step 2 of obtaining a feature sequence reflecting the quality of craniocerebral healing based on the three-dimensional model of the patient's craniocerebral includes the following specific steps:

[0016] Step 21, obtaining a three-dimensional model image of the patient's brain before surgery, a three-dimensional model image after surgery, and a three-dimensional model image during this examination;

[0017] Step 22: Obtain the three-dimensional contour of the brain tissue area removed during the operation by overlapping and comparing the three-dimensional model image before the operation with the three-dimensional model image after the operation. The corresponding process usually includes the following steps:

[0018] Step 221, image registration: the three-dimensional model images before and after the operation need to be registered so that they can be accurately aligned;

[0019] Step 222, image segmentation: the registered image needs to be segmented to extract the brain tissue area;

[0020] Step 223, 3D contour extraction: After the brain tissue area is segmented, the 3D contour shape information can be obtained by extracting its surface contour;

[0021] Step 23, obtaining the three-dimensional contour of the restored area where the brain tissue is removed and the pixel value of the restored area through the three-dimensional model image after the operation and the three-dimensional model image during the current examination;

[0022] Step 24: The collected three-dimensional contour of the removed brain tissue region, the three-dimensional contour of the restored region, and the pixel values ​​of the restored region are used to form a feature sequence.

[0023] As a preferred technical solution of the method for predicting and analyzing the prognosis of craniocerebral trauma based on a three-dimensional model, step 3 includes the following specific contents:

[0024] Step 31, obtaining the three-dimensional contour of the removed brain tissue area, the three-dimensional contour of the restored area, and the pixel value of the restored area;

[0025] Step 32, performing healing shape quality assessment based on the three-dimensional contour of the removed brain tissue area and the three-dimensional contour of the restored area; Step 32 includes the following specific contents: obtaining the three-dimensional contour of the removed brain tissue area and the three-dimensional contour of the restored area, obtaining the volume of the restored area and the distance data of each point restored in the contour of the removed brain tissue area, and importing the volume of the restored area and the distance data of each point restored in the contour of the removed brain tissue area into the healing shape quality assessment formula to calculate the healing shape quality, wherein the healing shape quality assessment formula is: , where Kz is the healing shape quality, a is the recovery speed ratio, exp() is the exponential power of the natural constant e, Vc is the volume of the recovery area, Vm is the volume of the removed brain tissue area, dm is the average value of the current cycle recovery, n is the number of regional contour points, zi is the distance data of the i-th brain tissue area contour point recovery, z is the average distance data of the removed brain tissue area contour point recovery, in this formula, the former evaluates the abnormality of the recovery speed by the volume ratio of the restored brain tissue, and the latter evaluates the abnormality of the quality of the recovery by the uniformity of the recovery of each point;

[0026] Step 33: Perform healing pixel quality assessment based on the pixel values ​​of the restored area, wherein the healing pixel quality assessment formula is: , where xw is the average pixel value of the restored area, xn is the average pixel value of the normal brain tissue, and Kx is the healing pixel quality;

[0027] Step 34: Obtain the calculated healing shape quality and healing pixel quality to evaluate the healing quality, wherein the healing quality evaluation method is: weight the healing shape quality and the healing pixel quality respectively and then add them to obtain the healing quality.

[0028] As a preferred technical solution of the method for predicting and analyzing the prognosis of craniocerebral trauma based on a three-dimensional model, step 4 includes the following specific contents:

[0029] The calculated healing quality is obtained, and the inverse of the calculated healing quality is compared with the healing risk standard. If the inverse of the healing quality is greater than or equal to the healing risk standard, it indicates that the healing is dangerous and a healing warning is issued; if the inverse of the healing quality is less than the healing risk standard, it indicates that the healing is normal and no healing warning is issued.

[0030] In a second aspect, the present application provides a craniocerebral trauma prognosis prediction and analysis system based on a three-dimensional model, which is implemented based on the above-mentioned craniocerebral trauma prognosis prediction and analysis method based on a three-dimensional model, and specifically includes a data acquisition module, a feature extraction module, a healing quality assessment module, a healing risk assessment module and a healing early warning module;

[0031] The data acquisition module is used to obtain the prognosis and healing images of craniocerebral treatment and construct a three-dimensional model of the patient's craniocerebral;

[0032] The feature extraction module is used to obtain a feature sequence reflecting the quality of craniocerebral healing based on the patient's craniocerebral three-dimensional model;

[0033] The healing quality assessment module is used to assess the healing quality based on the acquired feature sequence reflecting the healing quality of the craniocerebral area;

[0034] The healing risk assessment module is used to perform healing risk assessment based on the assessed healing quality;

[0035] The healing early warning module is used to provide a healing early warning based on the healing risk assessment result.

[0036] In a third aspect, the present application provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0037] The processor executes the above-mentioned three-dimensional model-based craniocerebral trauma prognosis prediction and analysis method by calling the computer program stored in the memory.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer processor, enables the computer processor to execute the above-mentioned three-dimensional model-based craniocerebral trauma prognosis prediction and analysis method.

[0039] Compared with the prior art, the beneficial effects of the present application are as follows: the present application obtains a feature sequence reflecting the quality of cranial and brain healing based on a three-dimensional model of the patient's cranial and brain, obtains data reflecting the quality of cranial and brain healing through data processing, evaluates the healing quality based on the acquired feature sequence reflecting the quality of cranial and brain healing, evaluates the healing risk based on the evaluated healing quality, and performs healing warning based on the healing risk assessment result, accurately obtains features reflecting the quality of cranial and brain healing, accurately analyzes the features of the quality of cranial and brain healing, quickly and accurately discovers abnormal recovery situations, and improves the accuracy of prediction of recovery from craniocerebral trauma. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings;

[0041] Figure 1 This is a schematic diagram of the overall process of the craniocerebral trauma prognosis prediction and analysis method based on a three-dimensional model in this application;

[0042] Figure 2 This is a flow chart of step 2 of the method for predicting the prognosis of craniocerebral trauma based on a three-dimensional model in this application;

[0043] Figure 3 A schematic diagram of three-dimensional contour extraction of a three-dimensional model-based craniocerebral trauma prognosis prediction and analysis method in this application;

[0044] Figure 4 This is a flow chart of step 3 of the method for predicting the prognosis of craniocerebral trauma based on a three-dimensional model in this application;

[0045] Figure 5 This is a schematic diagram of the overall framework of the craniocerebral trauma prognosis prediction and analysis system based on a three-dimensional model in this application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present application and its application or use.

[0047] Example 1

[0048] In order to solve the technical problems raised in the background technology, the present application provides a preferred embodiment: Figure 1-Figure 4 As shown, the prognosis prediction and analysis method of craniocerebral trauma based on a three-dimensional model includes the following specific steps:

[0049] Step 1: Obtain the prognosis and healing images of craniocerebral treatment, construct a three-dimensional model of the patient's craniocerebral brain, and intuitively reflect the patient's craniocerebral rehabilitation status;

[0050] In this embodiment, the specific content of step 1 is:

[0051] Step 11: Obtain the prognosis and healing images of craniocerebral treatment through medical imaging equipment, and obtain the previously constructed three-dimensional model of the patient's craniocerebral brain. The three-dimensional model of the patient's craniocerebral brain is constructed by medical staff before the patient's surgery through model construction;

[0052] Step 12: Based on the segmented prognosis healing image of craniocerebral treatment, the prognosis healing image of craniocerebral treatment is mapped into the patient's craniocerebral 3D model by using 3D reconstruction software. It should be noted that how to construct the patient's craniocerebral 3D model by model construction is a conventional technical means of 3D construction in the prior art, which can be realized by using existing medical 3D construction software. Meanwhile, this is not the gist of the invention of the present application. Here, only a brief description of the construction method of the 3D model is given, so it will not be described in detail.

[0053] At the same time, it should be noted that the following are some of the commonly used medical 3D construction software:

[0054] The first is 3D Slicer software: 3D Slicer is an open source medical image computing platform that can be used to process, view and analyze medical image data, including cranial images;

[0055] The second is FreeSurfer software: FreeSurfer is an open source brain imaging software that can be used to automatically reconstruct the three-dimensional model of the cerebral cortex surface and subcortical structures. Based on MRI image data, it can generate high-precision three-dimensional models of the brain for neuroscience research and clinical applications.

[0056] Step 2: obtaining a feature sequence reflecting the quality of craniocerebral healing based on the patient's craniocerebral three-dimensional model, and performing data processing to obtain data reflecting the quality of craniocerebral healing;

[0057] In this embodiment, if Figure 2 As shown, the step 2 of obtaining a characteristic sequence reflecting the quality of craniocerebral healing based on the patient's craniocerebral three-dimensional model includes the following specific steps:

[0058] Step 21, obtaining a three-dimensional model image of the patient's brain before surgery, a three-dimensional model image after surgery, and a three-dimensional model image during this examination;

[0059] Step 22: Obtain the three-dimensional contour of the brain tissue area removed during the operation by overlapping and comparing the three-dimensional model image before the operation and the three-dimensional model image after the operation. In this embodiment, it should be specifically explained that Figure 3 As shown, the corresponding 3D contour extraction process usually includes the following steps:

[0060] Step 221, image registration: the three-dimensional model images before and after the operation need to be registered so that they can be accurately aligned;

[0061] Step 222, image segmentation: the registered image needs to be segmented to extract the brain tissue area;

[0062] Step 223, 3D contour extraction: After the brain tissue area is segmented, the 3D contour shape information can be obtained by extracting its surface contour;

[0063] Step 23, obtaining the three-dimensional contour of the restored area where the brain tissue is removed and the pixel value of the restored area through the three-dimensional model image after the operation and the three-dimensional model image during the current examination;

[0064] Step 24, the collected three-dimensional contour of the removed brain tissue area, the three-dimensional contour of the restored area, and the pixel values ​​of the restored area are used to form a feature sequence;

[0065] Step 3, evaluating the healing quality based on the acquired characteristic sequence reflecting the healing quality of the craniocerebral area;

[0066] In this embodiment, if Figure 4 As shown, step 3 includes the following specific contents:

[0067] Step 31, obtaining the three-dimensional contour of the removed brain tissue area, the three-dimensional contour of the restored area, and the pixel value of the restored area;

[0068] Step 32, performing healing shape quality assessment based on the three-dimensional contour of the removed brain tissue region and the three-dimensional contour of the restored region; in this embodiment, it should be specifically explained that step 32 includes the following specific contents: obtaining the three-dimensional contour of the removed brain tissue region and the three-dimensional contour of the restored region, obtaining therefrom the volume of the restored region and the distance data of each point restored in the contour of the removed brain tissue region, and importing the volume of the restored region and the distance data of each point restored in the contour of the removed brain tissue region into a healing shape quality assessment formula to calculate the healing shape quality;

[0069] In this embodiment, the healing shape quality evaluation formula is preferably: , where Kz is the healing shape quality, a is the recovery speed ratio, exp() is the exponential power of the natural constant e, Vc is the volume of the recovery area, Vm is the volume of the removed brain tissue area, dm is the average value of the current cycle recovery, n is the number of regional contour points, zi is the distance data of the i-th brain tissue area contour point recovery, z is the average distance data of the removed brain tissue area contour point recovery, in this formula, the former evaluates the abnormality of the recovery speed by the volume ratio of the restored brain tissue, and the latter evaluates the abnormality of the recovery quality by the uniformity of the recovery of each point; other expressions of the healing shape quality evaluation formula are pointed out here: for example, in order to evaluate the uniformity of the recovery of each point, the contour similarity of the removed brain tissue area contour and the restored area three-dimensional contour at the same scale can be used for evaluation, and in order to evaluate the abnormality of the recovery speed, the volume comparison of the brain tissue area contour and the restored area three-dimensional contour can be used for evaluation;

[0070] Step 33: Perform healing pixel quality assessment based on the pixel values ​​of the restored area, wherein the healing pixel quality assessment formula is: , where xw is the average pixel value of the restored area, xn is the average pixel value of the normal brain tissue, and Kx is the quality of the healing pixel. Here, the difference between the pixels of the restored area and the normal area is used to further evaluate the recovery quality of the restored area.

[0071] Step 34, obtaining the calculated healing shape quality and healing pixel quality to evaluate the healing quality, wherein the healing quality evaluation method is: weighting the healing shape quality and the healing pixel quality respectively and then adding them to obtain the healing quality, which is expressed here by the formula, that is, , where Km is the healing mass, , They are the healing shape quality weight and the healing pixel quality weight respectively;

[0072] In this step, the quality of healing is comprehensively analyzed by integrating the shape abnormality of healing restoration and the quality abnormality of healing pixels;

[0073] Step 4: Perform healing risk assessment based on the assessed healing quality, and perform healing warning based on the healing risk assessment result;

[0074] In this embodiment, step 4 includes the following specific contents:

[0075] The calculated healing quality is obtained, and the inverse of the calculated healing quality is compared with the healing risk standard. If the inverse of the healing quality is greater than or equal to the healing risk standard, it indicates that the healing is dangerous and a healing warning is issued; if the inverse of the healing quality is less than the healing risk standard, it indicates that the healing is normal and no healing warning is issued.

[0076] At the same time, it should be pointed out in the present embodiment that the acquisition of the preset parameters in the present embodiment is a conventional technical means in the field, and the preferred method of obtaining the preset parameters (such as the healing risk standard, the healing shape quality weight, the healing pixel quality weight and the recovery speed ratio coefficient, etc.) is as follows: obtaining the characteristic sequences in the prognosis healing image data of several groups of craniocerebral treatments with the same surgical cycle, calculating the healing quality through these parameters and analyzing whether the healing is normal, obtaining the judgment result of whether the healing is complete after the treatment cycle, importing the judgment result of whether the healing is complete after the welding treatment cycle and the calculated healing quality into the fitting software, and outputting the value of the preset parameters that meets the maximum judgment accuracy.

[0077] The advantages of this embodiment over the prior art are as follows: a feature sequence reflecting the quality of cranial and brain healing is obtained based on the patient's three-dimensional model of the cranial and brain, data reflecting the quality of cranial and brain healing is obtained through data processing, the healing quality is evaluated based on the acquired feature sequence reflecting the quality of cranial and brain healing, the healing risk is evaluated based on the evaluated healing quality, and a healing warning is given based on the healing risk assessment result, the features reflecting the quality of cranial and brain healing are accurately obtained, the features of the quality of cranial and brain healing are accurately analyzed, abnormal recovery situations are discovered quickly and accurately, and the accuracy of prediction of recovery from craniocerebral trauma is improved.

[0078] Example 2

[0079] like Figure 5 As shown, this embodiment provides a craniocerebral trauma prognosis prediction and analysis system based on a three-dimensional model, which is implemented based on the above-mentioned craniocerebral trauma prognosis prediction and analysis method based on a three-dimensional model, and specifically includes a data acquisition module, a feature extraction module, a healing quality assessment module, a healing risk assessment module and a healing early warning module; wherein the data acquisition module is used to obtain the prognosis healing image of craniocerebral treatment and construct a three-dimensional model of the patient's craniocerebral; the feature extraction module is used to obtain a feature sequence reflecting the quality of craniocerebral healing based on the three-dimensional model of the patient's craniocerebral; the healing quality assessment module is used to evaluate the healing quality based on the acquired feature sequence reflecting the quality of craniocerebral healing; the healing risk assessment module is used to evaluate the healing risk based on the evaluated healing quality; the healing early warning module is used to give a healing early warning based on the healing risk assessment result; in this embodiment, it should be noted that Figure 5 The arrow in the figure indicates the data transmission direction of the system. The specific steps of the system module in this embodiment have been fully mentioned in the above method embodiment, so they will not be repeated here in detail.

[0080] Example 3

[0081] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0082] The processor executes the above-mentioned three-dimensional model-based craniocerebral trauma prognosis prediction and analysis method by calling the computer program stored in the memory.

[0083] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement the three-dimensional model-based craniocerebral trauma prognosis prediction and analysis method provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0084] Example 4

[0085] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0086] When the computer program is executed on a computer device, the computer device is enabled to execute the above-mentioned three-dimensional model-based craniocerebral trauma prognosis prediction and analysis method.

[0087] For example, the computer readable storage medium can be a read-only memory, a random access memory, a read-only CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0088] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0089] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0090] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A method for predicting and analyzing the prognosis of craniocerebral trauma based on a three-dimensional model, characterized in that: It includes the following specific steps: Step 1: Obtain the prognosis and healing images of craniocerebral treatment, construct a three-dimensional model of the patient's craniocerebral brain, and intuitively reflect the patient's craniocerebral rehabilitation status; Step 2: obtaining a feature sequence reflecting the quality of craniocerebral healing based on the patient's craniocerebral three-dimensional model, and performing data processing to obtain data reflecting the quality of craniocerebral healing; Step 3, evaluating the healing quality based on the acquired characteristic sequence reflecting the healing quality of the craniocerebral area; The step 3 includes the following specific contents: Step 31, obtaining the three-dimensional contour of the removed brain tissue area, the three-dimensional contour of the restored area, and the pixel value of the restored area; Step 32, performing healing shape quality assessment based on the three-dimensional contour of the removed brain tissue area and the three-dimensional contour of the restored area; the step 32 includes the following specific contents: obtaining the three-dimensional contour of the removed brain tissue area and the three-dimensional contour of the restored area, obtaining the volume of the restored area and the distance data of each point restored in the contour of the removed brain tissue area, and importing the volume of the restored area and the distance data of each point restored in the contour of the removed brain tissue area into the healing shape quality assessment formula to calculate the healing shape quality, wherein the healing shape quality assessment formula is: , where Kz is the healing shape quality, a is the recovery speed ratio, exp() is the exponential power of the natural constant e, Vc is the volume of the recovery area, Vm is the volume of the removed brain tissue area, dm is the average value of the current cycle recovery, n is the number of regional contour points, zi is the distance data of the i-th brain tissue area contour point recovery, and z is the average distance data of the removed brain tissue area contour points recovery; Step 33: Perform healing pixel quality assessment based on the pixel values ​​of the restored area, wherein the healing pixel quality assessment formula is: , where xw is the average pixel value of the restored area, xn is the average pixel value of the normal brain tissue, and Kx is the healing pixel quality; Step 34, obtaining the calculated healing shape quality and healing pixel quality to evaluate the healing quality, wherein the healing quality evaluation method is: weighting the healing shape quality and the healing pixel quality respectively and then adding them to obtain the healing quality; Step 4: Perform a healing risk assessment based on the assessed healing quality, and issue a healing warning based on the healing risk assessment result.

2. The method for predicting and analyzing the prognosis of craniocerebral trauma based on a three-dimensional model according to claim 1, characterized in that: The specific content of step 1 is: Step 11, obtaining the prognosis and healing images of craniocerebral treatment through medical imaging equipment, and obtaining the previously constructed three-dimensional model of the patient's craniocerebral; Step 12: Based on the segmented prognosis and healing image of the craniocerebral treatment, the prognosis and healing image of the craniocerebral treatment is mapped into the three-dimensional model of the patient's craniocerebral using three-dimensional reconstruction software.

3. The method for predicting and analyzing the prognosis of craniocerebral trauma based on a three-dimensional model as claimed in claim 2, characterized in that: The step 2 of obtaining a characteristic sequence reflecting the quality of craniocerebral healing based on the patient's craniocerebral three-dimensional model comprises the following specific steps: Step 21, obtaining a three-dimensional model image of the patient's brain before surgery, a three-dimensional model image after surgery, and a three-dimensional model image during this examination; Step 22, obtaining the three-dimensional contour of the brain tissue area removed during the operation by overlapping and comparing the three-dimensional model image before the operation and the three-dimensional model image after the operation; Step 23, obtaining the three-dimensional contour of the restored area where the brain tissue is removed and the pixel value of the restored area through the three-dimensional model image after the operation and the three-dimensional model image during the current examination; Step 24: The collected three-dimensional contour of the removed brain tissue region, the three-dimensional contour of the restored region, and the pixel values ​​of the restored region are used to form a feature sequence.

4. The method for predicting and analyzing the prognosis of craniocerebral trauma based on a three-dimensional model according to claim 1, characterized in that: The step 4 includes the following specific contents: The calculated healing quality is obtained, and the inverse of the calculated healing quality is compared with the healing risk standard. If the inverse of the healing quality is greater than or equal to the healing risk standard, it indicates that the healing is dangerous and a healing warning is issued; if the inverse of the healing quality is less than the healing risk standard, it indicates that the healing is normal and no healing warning is issued.

5. A three-dimensional model-based craniocerebral trauma prognosis prediction and analysis system, which is implemented based on the three-dimensional model-based craniocerebral trauma prognosis prediction and analysis method according to any one of claims 1 to 4, characterized in that: It specifically includes a data acquisition module, a feature extraction module, a healing quality assessment module, a healing risk assessment module and a healing early warning module; The data acquisition module is used to obtain the prognosis and healing images of craniocerebral treatment and construct a three-dimensional model of the patient's craniocerebral; The feature extraction module is used to obtain a feature sequence reflecting the quality of craniocerebral healing based on the patient's craniocerebral three-dimensional model; The healing quality assessment module is used to assess the healing quality based on the acquired feature sequence reflecting the healing quality of the craniocerebral area; The healing risk assessment module is used to perform healing risk assessment based on the assessed healing quality; The healing early warning module is used to provide a healing early warning based on the healing risk assessment result.

6. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the three-dimensional model-based craniocerebral trauma prognosis prediction and analysis method as described in any one of claims 1 to 4 by calling the computer program stored in the memory.

7. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer processor, the computer processor executes the three-dimensional model-based craniocerebral trauma prognosis prediction and analysis method as described in any one of claims 1 to 4.

Images