A neurosurgery navigation system and storage medium based on ray projection

Abstract

The present invention discloses a neurosurgery navigation system based on ray projection, and specifically relates to the technical field of ray projection, including obtaining an area of ​​interest in the surgical area according to an image of the surgical area of ​​a patient before surgery, determining noise information of the area of ​​interest by the difference between pixel values ​​of the area of ​​interest and other areas, analyzing the three-dimensional image of the patient through Blob, extracting connected Blob areas in the area of ​​interest, obtaining regional feature information of the area of ​​interest, and quantifying the complexity of the area of ​​interest, determining the complex area in the surgical area of ​​the patient, obtaining dynamic changes of the complex area in the patient by collecting real-time images in the complex area, determining matching information of the complex area and delay information of real-time imaging, and quantifying potential risks of the complex area in the surgical area of ​​the patient. The present invention helps to identify potential changes in the surgical area and provide timely warnings, thereby improving the safety and accuracy of the operation.

Description

Technical Field

[0001] The present invention relates to the technical field of light projection, and more specifically, to a neurosurgery navigation system and a storage medium based on light projection. Background Art

[0002] During neurosurgery, preoperative images are an important reference for doctors to understand the surgical area of ​​the patient. The images provide doctors with a three-dimensional view of the patient's anatomical structure, which helps to accurately locate the surgical target area. By comparing preoperative images with real-time intraoperative images, neurosurgeons can navigate more accurately and avoid risky areas.

[0003] During the operation, due to factors such as surgical operations and patient tissue deformation, real-time images may differ from preoperative images, making intraoperative navigation more difficult. Traditional surgical navigation systems often rely on preoperative images for marking and planning, but cannot effectively respond to real-time changes that occur during surgery, especially when performing surgery in complex areas. The matching accuracy of preoperative images and the delay of real-time imaging will affect the safety and accuracy of the operation. Therefore, it is not easy to accurately identify dynamic changes in complex areas during surgery and promptly warn of potential risks.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a neurosurgery navigation system and a storage medium based on ray projection to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A neurosurgery navigation system based on ray projection, comprising a region extraction module, a noise processing module, a feature processing module, a complexity assessment module, an image comparison module and a risk assessment module, and signal connections between the modules;

[0008] A region extraction module, used for obtaining a region of interest in the surgical area based on an image of the surgical area of ​​the patient before surgery;

[0009] A noise processing module, used for determining noise information of the region of interest by comparing the difference between the pixel values ​​of the region of interest and other regions;

[0010] A feature processing module is used to analyze the patient's three-dimensional image through Blob, extract the connected Blob area in the region of interest, and obtain the regional feature information of the region of interest;

[0011] A complexity evaluation module is used to quantify the complexity of the region of interest based on the noise information and regional feature information of the region of interest;

[0012] An image comparison module is used to determine the complex area in the patient's surgical area according to the complexity of the area of ​​interest, obtain the dynamic changes of the patient's complex area by collecting real-time images in the complex area, and determine the matching information of the complex area and the delay information of the real-time imaging;

[0013] The risk assessment module is used to comprehensively analyze the matching information of complex areas and the delayed information of real-time imaging, quantify the potential risks of complex areas in the patient's surgical area, and generate early warning signals;

[0014] The noise information of the region of interest is represented by the signal-to-noise ratio deviation coefficient, and the regional characteristic information of the region of interest is represented by the regional performance index;

[0015] The matching information of complex areas is represented by the total similarity coefficient and the dynamic change coefficient, and the delay information of real-time imaging is represented by the delay anomaly coefficient.

[0016] In a preferred embodiment, determining the noise information of the region of interest includes:

[0017] The logic for obtaining the signal-to-noise ratio deviation coefficient is as follows: obtain the pixel value of each pixel point in the region of interest, and mark the pixel value of each pixel point in the region of interest as: GXQ n , where n=1, 2, 3, ..., N, N is a positive integer, and n is the number of each pixel in the region of interest;

[0018] Select the background of the image in the three-dimensional image of the patient, obtain the pixel value of each pixel in the image background, and mark the pixel value of each pixel in the image background as: BJ i , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of each pixel in the image background;

[0019] Calculate the mean and standard deviation of the pixel value of each pixel in the region of interest, and mark the mean and standard deviation of the pixel value of each pixel in the region of interest as: GXQ avg and GXQ std ,in,

[0020] Calculate the mean and standard deviation of the pixel value of each pixel in the image background, and mark the mean and standard deviation of the pixel value of each pixel in the image background as: BJ avg and BJ std ,in,

[0021]

[0022] Calculate the signal-to-noise ratio deviation coefficient using the following formula: Among them, SNR pc is the signal-to-noise ratio deviation coefficient.

[0023] In a preferred embodiment, obtaining the regional characteristic information of the region of interest includes:

[0024] The logic for obtaining the regional performance index is as follows: performing B lob analysis on the region of interest, obtaining B lob regions divided in the region of interest, and classifying different B lob regions, and classifying the B lob regions divided in the region of interest into possible disease-prone regions, disease-prone regions, and normal regions;

[0025] Calculate the regional performance index using the formula: Among them, BX qy is the regional performance index, ZC sl is the number of Blob regions in the normal area of ​​the region of interest, KNB sl BF is the number of Blob regions in the region of interest where the disease may occur. sl is the number of Blob regions in the diseased area of ​​the region of interest.

[0026] In a preferred embodiment, quantifying the complexity of the region of interest includes:

[0027] The signal-to-noise ratio deviation coefficient and the regional performance index are weighted to construct a preoperative region of interest evaluation model and generate a preoperative region of interest evaluation coefficient. The expression of the preoperative region of interest evaluation coefficient is: Among them, pg sq is the preoperative region of interest assessment coefficient, α1 and α2 are the signal-to-noise ratio deviation coefficient and the proportional coefficient of the regional performance index, respectively, and α1 and α2 are both greater than 0.

[0028] In a preferred embodiment, determining a complex area in a surgical area of ​​a patient includes:

[0029] A preoperative region of interest evaluation coefficient threshold is set, the preoperative region of interest evaluation coefficient is compared with the preoperative region of interest evaluation coefficient threshold, the region of interest smaller than the preoperative region of interest evaluation coefficient threshold is obtained, and the region of interest smaller than the preoperative region of interest evaluation coefficient threshold is marked as a complex region.

[0030] In a preferred embodiment, determining the matching information of the complex area includes:

[0031] The acquisition logic of the total similarity coefficient is: obtain the pixel value of each pixel point in the real-time image of the complex area in the monitoring interval, and mark the pixel value of each pixel point in the real-time image of the complex area in the monitoring interval as: SS km , where k = 1, 2, 3, ..., K, K is a positive integer, k is the number of the image collected at different times in the complex area, m = 1, 2, 3, ..., M, M is a positive integer, m is the number of the heavy pixel points of the image at different times in the complex area;

[0032] Obtain the pixel value of each pixel point in the preoperative image of the complex area, and mark the pixel value of each pixel point in the preoperative image of the complex area as: SQ m , calculate the mean and variance of the pixel values ​​of each pixel point in the complex area preoperative image, and mark the mean and variance of the pixel values ​​of each pixel point in the complex area preoperative image as: avg sq and σ sq ;

[0033] Calculate the mean and variance of the pixel values ​​of each pixel point in the real-time image of the complex area, and mark the mean and variance of the pixel values ​​of each pixel point in the real-time image of the complex area as: avg k and σ k ;

[0034] The similarity coefficient between the real-time image of the complex area and the preoperative image at different times is calculated using the following formula: Among them, XS k is the similarity coefficient between the real-time image of the complex area at different times and the preoperative image, cov k is the covariance of the pixel values ​​of each pixel point in the real-time image of the complex area at different times and the preoperative image, C1 and C2 are constants;

[0035] Calculate the total similarity coefficient, the calculation formula is: Among them, XS all is the total similarity coefficient;

[0036] The acquisition logic of the dynamic change coefficient is: according to the pixel value of each pixel point in the real-time image of the complex intraoperative area in the monitoring interval, the time second-order derivative value of the pixel value of each pixel point in the monitoring interval is calculated, and the calculation formula is: in, is the time second-order derivative value of pixel k at different times in the monitoring interval;

[0037] Set the time second derivative threshold and mark the time second derivative threshold as: DS yz, compare the time second-order derivative of each pixel in the real-time image of the complex area within the monitoring interval with the time second-order derivative threshold, obtain the pixel points in the real-time image of the complex area within the monitoring interval that are greater than the time second-order derivative threshold, and re-mark the pixel points in the monitoring interval that are greater than the time second-order derivative threshold as: Wherein, g=1, 2, 3, ..., G, G is a positive integer, and g is the number of the pixel point that is greater than the time second-order derivative threshold in the monitoring interval;

[0038] Calculate the dynamic change coefficient using the following formula: Among them, DT bh is the dynamic change coefficient.

[0039] In a preferred embodiment, the delay information of real-time imaging of complex areas includes:

[0040] The acquisition logic of the delay anomaly coefficient is: obtain the timestamp when the image sensor in the real-time image of the complex area captures the image, and mark the timestamp when the image sensor in the real-time image of the complex area captures the image as: Tc h , where h = 1, 2, 3, ..., H, H is a positive integer, and h is the number of the image captured by the image sensor;

[0041] Get the moment when the image is processed and ready for display and record another timestamp, and record another timestamp when the image is processed and ready for display as: Tp h ;

[0042] Calculate the average delay using the formula: Among them, YC is the average delay;

[0043] Calculate the delay standard deviation using the formula: Among them, YC std is the delay standard deviation;

[0044] Calculate the delay coefficient of variation using the formula: Among them, BY yc is the coefficient of variation of delay;

[0045] Calculate the delay anomaly coefficient, the calculation formula is: Among them, YC yc is the delay anomaly coefficient.

[0046] In a preferred embodiment, the matching information of the complex area and the delay information of the real-time imaging are comprehensively analyzed, including:

[0047] The total similarity coefficient, dynamic change coefficient and delay anomaly coefficient are weighted to construct an early warning evaluation model and generate an early warning evaluation coefficient. The calculation formula of the early warning evaluation coefficient is: Among them, pg yj is the early warning assessment coefficient, β1, β2, and β3 are the proportional coefficients of the total similarity coefficient, the dynamic change coefficient, and the delay anomaly coefficient, respectively. β1, β2, and β3 are all greater than 0.

[0048] In a preferred embodiment, generating an early warning signal includes:

[0049] A warning assessment coefficient threshold is set, and the warning assessment coefficient of the complex area is compared with the warning assessment coefficient threshold. If the warning assessment coefficient of the complex area is less than the warning assessment coefficient threshold, a warning signal is generated, indicating that the complex area may have undergone major changes or instability, reminding the surgical team to pay attention to the potential risks of the area. If the warning assessment coefficient of the complex area is greater than the warning assessment coefficient threshold, no warning signal is generated.

[0050] In a preferred embodiment, a medium has a computer program stored thereon.

[0051] Technical effects and advantages of the present invention:

[0052] The present invention analyzes images of the patient's surgical area before surgery, divides the patient's surgical area into multiple regions of interest in more detail, performs Blob analysis and noise analysis on the regions of interest, evaluates the complexity of the preoperative regions of interest, and marks them. Through the marked regions of interest, potential changes in the surgical area are identified through image comparison and real-time image analysis during the operation, and potential risks are evaluated. Warning signals are generated according to the early warning evaluation system, which helps the surgical team make corresponding decisions in a timely manner, thereby improving the safety and accuracy of the operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0054] Figure 1 The figure is a schematic diagram of the structure of a neurosurgery navigation system based on ray projection according to the present invention. DETAILED DESCRIPTION

[0055] 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.

[0056] Example 1

[0057] Figure 1 A schematic diagram of the structure of a neurosurgery navigation system based on ray projection of the present invention is given, which specifically includes a region extraction module, a noise processing module, a feature processing module, a complexity assessment module, an image comparison module and a risk assessment module, and the modules are signal-connected;

[0058] A region extraction module, used for obtaining a region of interest in the surgical area based on an image of the surgical area of ​​the patient before surgery;

[0059] A noise processing module, used for determining noise information of the region of interest by comparing the difference between the pixel values ​​of the region of interest and other regions;

[0060] A feature processing module is used to analyze the patient's three-dimensional image through Blob, extract the connected Blob area in the region of interest, and obtain the regional feature information of the region of interest;

[0061] A complexity evaluation module is used to quantify the complexity of the region of interest based on the noise information and regional feature information of the region of interest;

[0062] An image comparison module is used to determine the complex area in the patient's surgical area according to the complexity of the area of ​​interest, obtain the dynamic changes of the patient's complex area by collecting real-time images in the complex area, and determine the matching information of the complex area and the delay information of the real-time imaging;

[0063] The risk assessment module is used to comprehensively analyze the matching information of complex areas and the delayed information of real-time imaging, quantify the potential risks of complex areas in the patient's surgical area, and generate early warning signals.

[0064] Using ray projection technology, intraoperative images of the patient’s anatomy are compared and registered with preoperative 3D image data, providing surgeons with precise navigation guidance, including:

[0065] Before surgery, the patient is scanned with medical imaging, such as MRI (magnetic resonance imaging) or CT (computed tomography), to generate high-resolution three-dimensional images, and image processing software is used to perform three-dimensional reconstruction of the patient's surgical area to generate a detailed anatomical structure model;

[0066] The three-dimensional image model generated before surgery is registered with the navigation system. The registration step is to align the coordinate system of the preoperative image with the actual anatomical position of the patient during surgery. According to the surgical plan, the surgical area of ​​interest, such as the location of the tumor or lesion, is selected so that it can be focused on during light projection.

[0067] Affix markers at specific locations on the patient's head or use patient feature points as reference points for the light projection navigation system to accurately align the patient's actual anatomical position during surgery with the 3D imaging data;

[0068] During the operation, the light projection system projects the preoperative 3D model onto the patient's head or the surface of the surgical area through optical projection technology based on the preoperative image data. The light projection navigation system tracks the position changes of the surgical instruments and the patient in real time. The navigation system updates the image in real time to ensure that the surgeon's operation is accurately located in the anatomical area of ​​interest.

[0069] During the operation, the patient may experience slight displacement due to breathing, heartbeat or other factors. The light projection system uses real-time tracking equipment to calibrate and adjust these displacements to ensure that the light projection remains consistent with the patient's actual anatomical structure.

[0070] The region of interest is obtained before surgery, and the methods for obtaining the region of interest include the following:

[0071] Manual marking by doctors: Before neurosurgery, doctors use MRI, CT or other imaging technologies to image the surgical area of ​​the patient. Through these three-dimensional images, doctors can clearly mark the target area of ​​the surgery, such as lesions, tumors, lesions, etc.

[0072] Based on image processing and segmentation algorithms: For MRI, CT and other images, ROI can be obtained through image threshold segmentation technology. Threshold segmentation distinguishes different tissues or structures based on the intensity value of pixels or voxels, or segments the region of interest by detecting edges;

[0073] ROI extraction based on multimodal images: By fusing multiple image modalities (such as preoperative MRI, CT and intraoperative ultrasound), the region of interest can be identified more accurately.

[0074] According to the three-dimensional image of the patient before surgery, the patient's region of interest is identified and extracted, and the patient's three-dimensional image is further analyzed. The noise information of the region of interest is determined by the difference between the pixel value of the region of interest and other regions. The three-dimensional image of the patient is analyzed by B lob, and the connected B lob regions in the region of interest are extracted to obtain the regional feature information of the region of interest. The noise information and regional feature information of the region of interest are represented by the signal-to-noise ratio deviation coefficient and the regional performance index, respectively.

[0075] The logic for obtaining the signal-to-noise ratio deviation coefficient is as follows: obtain the pixel value of each pixel point in the region of interest, and mark the pixel value of each pixel point in the region of interest as: GXQ n , where n=1, 2, 3, ..., N, N is a positive integer, and n is the number of each pixel in the region of interest;

[0076] Select the background of the image in the three-dimensional image of the patient, obtain the pixel value of each pixel in the image background, and mark the pixel value of each pixel in the image background as: BJ i , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of each pixel in the image background;

[0077] Calculate the mean and standard deviation of the pixel value of each pixel in the region of interest, and mark the mean and standard deviation of the pixel value of each pixel in the region of interest as: GXQ avg and GXQ std ,in,

[0078]

[0079] Calculate the mean and standard deviation of the pixel value of each pixel in the image background, and mark the mean and standard deviation of the pixel value of each pixel in the image background as: BJ avg and BJ std ,in,

[0080]

[0081] Calculate the signal-to-noise ratio deviation coefficient using the following formula: Among them, SNR pc is the signal-to-noise ratio deviation coefficient.

[0082] From the formula, we can see that the smaller the signal-to-noise ratio deviation coefficient is, the stronger the random fluctuation in the image is, which may mask or interfere with the detection and analysis of real signals (such as tissue characteristics), and there may be more complex lesions in the region of interest. The reasons for evaluating the complexity of the region of interest by the signal-to-noise ratio deviation coefficient are as follows:

[0083] A high SNR deviation coefficient indicates good image quality and can clearly display tissue structures and lesions, while a low SNR deviation coefficient may indicate that there is a lot of interfering noise in the image. The region of interest (ROI) usually contains complex structures such as blood vessels, tumors or other tissue features. Highly complex areas may be affected by more noise, resulting in a lower SNR deviation coefficient.

[0084] Complex areas may contain a variety of different tissue types and morphological features. This diversity may cause the signal intensity of tissues in these areas to vary greatly, so the corresponding noise level will also be higher, resulting in a lower signal-to-noise ratio. In complex areas, tissue boundaries may be blurred, resulting in large fluctuations in pixel intensity, which in turn affects the stability of the signal and further affects the calculation results of the signal-to-noise ratio deviation coefficient.

[0085] The logic for obtaining the regional performance index is as follows: performing B lob analysis on the region of interest, obtaining B lob regions divided in the region of interest, and classifying different B lob regions, and classifying the B lob regions divided in the region of interest into possible disease-prone regions, disease-prone regions, and normal regions;

[0086] Calculate the regional performance index using the formula: Among them, BX qy is the regional performance index, ZC sl is the number of Blob regions in the normal area of ​​the region of interest, KNB sl BF is the number of Blob regions in the region of interest where the disease may occur. sl is the number of Blob regions in the diseased area of ​​the region of interest.

[0087] It should be noted that the Blob area refers to the connected area formed in the image. These areas are similar in pixel intensity, shape or other features. The connected component analysis algorithm is used to identify all the Blob areas in the image and extract the features of each Blob, such as area, perimeter, shape, center position, etc. According to the features of each Blob area, the type of Blob area is identified. The types of Blob areas include: possible disease area, disease area and normal area. The possible disease area indicates that there may be lesions, and the characteristic value shows abnormality. The disease area indicates a confirmed lesion area, which usually has obvious pathological characteristics. The normal area indicates tissue that is considered to be healthy, and the characteristic value is within the normal range.

[0088] As can be seen from the formula, the smaller the regional performance index, the more extensive the lesions may be in the region of interest, and may indicate increased complexity of the tissue, which may make surgery more difficult and require more precise navigation and planning to avoid damaging surrounding healthy tissue. The reasons why the regional performance index evaluates the complexity of the region of interest are as follows:

[0089] Assessing the number of these areas can help determine a patient's risk level; for example, more diseased areas may indicate a higher risk of disease progression, necessitating a more aggressive treatment strategy.

[0090] By identifying the possible areas of disease, it can help doctors detect potential lesions early.

[0091] Early intervention and treatment are crucial, especially in the management of diseases such as cancer;

[0092] Before surgery, analyzing the number and characteristics of different regions of interest can help surgeons better plan the surgical path, reduce damage to normal tissues, and improve the safety and effectiveness of surgery.

[0093] The signal-to-noise ratio deviation coefficient and the regional performance index are weighted to construct a preoperative region of interest evaluation model and generate a preoperative region of interest evaluation coefficient. The expression of the preoperative region of interest evaluation coefficient is: Among them, pg sq is the preoperative region of interest assessment coefficient, α1 and α2 are the signal-to-noise ratio deviation coefficient and the proportional coefficient of the regional performance index, respectively, and α1 and α2 are both greater than 0.

[0094] A preoperative region of interest evaluation coefficient threshold is set, the preoperative region of interest evaluation coefficient is compared with the preoperative region of interest evaluation coefficient threshold, the region of interest smaller than the preoperative region of interest evaluation coefficient threshold is obtained, and the region of interest smaller than the preoperative region of interest evaluation coefficient threshold is marked as a complex region.

[0095] It should be noted that by analyzing the patient's three-dimensional images before surgery and obtaining the patient's complex areas, it helps to significantly improve the accuracy and safety of the surgery during the operation:

[0096] Mark complex areas before surgery, and quickly align these marks with the images during surgery (image registration) during real-time imaging. This registration can help doctors accurately locate the lesion area and avoid misoperation and damage to healthy tissues.

[0097] Preoperative marking of complex areas helps doctors plan the surgical path in advance and avoid mistakes in complex or high-risk areas. This is especially important in neurosurgery because nerve tissue is very sensitive and small mistakes may lead to serious consequences.

[0098] The information from preoperative marking can be used as part of the intraoperative navigation system to provide real-time feedback on the patient's physical changes and surgical progress during surgery. There is no need to repeatedly identify the area of ​​interest during surgery. Preoperative marking enables the intraoperative image processing system to focus on key areas more quickly and accurately, reducing unnecessary full-image calculations and improving the efficiency of real-time imaging.

[0099] Complex areas help doctors verify the actual lesion condition during surgery, such as whether it is consistent with preoperative images or whether the lesion has expanded, which helps doctors adjust surgical strategies in a timely manner.

[0100] During the operation, navigate to the complex area, compare the real-time image of the complex area with the preoperative image, collect the matching information of the complex area and the delay information of the real-time imaging, represent the matching information of the complex area by the total similarity coefficient and the dynamic change coefficient, and represent the delay information of the real-time imaging by the delay abnormality coefficient.

[0101] The matching information of complex areas reflects the accuracy and safety of the surgical process. It can monitor the dynamic changes of patient tissues in real time, identify potential deviations, and avoid misoperations, including:

[0102] Avoid cutting into the wrong area due to slight displacement of the scalpel or tool, thus reducing damage to healthy tissue;

[0103] Identify dynamic changes in tissues to ensure that the resection or operation area is consistent with the preoperative plan;

[0104] Reduce surgical time and avoid delays due to inaccurate matching;

[0105] Provide timely warnings in emergency situations, ensure surgical safety, and adjust surgical strategies in a timely manner.

[0106] The acquisition logic of the total similarity coefficient is: obtain the pixel value of each pixel point in the real-time image of the complex area in the monitoring interval, and mark the pixel value of each pixel point in the real-time image of the complex area in the monitoring interval as: SS km , where k = 1, 2, 3, ..., K, K is a positive integer, k is the number of the image collected at different times in the complex area, m = 1, 2, 3, ..., M, M is a positive integer, m is the number of the heavy pixel points of the image at different times in the complex area;

[0107] Obtain the pixel value of each pixel point in the preoperative image of the complex area, and mark the pixel value of each pixel point in the preoperative image of the complex area as: SQ m , calculate the mean and variance of the pixel values ​​of each pixel point in the complex area preoperative image, and mark the mean and variance of the pixel values ​​of each pixel point in the complex area preoperative image as: avg sq and σ sq ;

[0108] It should be noted that complex areas may undergo various forms of changes during the monitoring process. For example, external factors such as surgical operations, instrument impacts, and bleeding may cause changes in the pixel values ​​of complex areas. The patient's physiological reactions or pathological changes will also affect the status of these areas. Therefore, it is necessary to analyze the dynamic changes of complex areas over time.

[0109] Calculate the mean and variance of the pixel values ​​of each pixel point in the real-time image of the complex area, and mark the mean and variance of the pixel values ​​of each pixel point in the real-time image of the complex area as: avg k and σ k ;

[0110] The similarity coefficient between the real-time image of the complex area and the preoperative image at different times is calculated using the following formula: Among them, XS kis the similarity coefficient between the real-time image of the complex area at different times and the preoperative image, cov k is the covariance of the pixel values ​​of each pixel point in the real-time image of the complex area at different times and the preoperative image, C1 and C2 are constants;

[0111] It should be noted that C1 and C2 are constants used for stability and to prevent the denominator from being zero, and are set and adjusted by the staff based on actual conditions.

[0112] Calculate the total similarity coefficient, the calculation formula is: Among them, XS all is the total similarity coefficient.

[0113] It can be seen from the formula that the larger the total similarity coefficient is, the higher the pixel similarity between the preoperative and intraoperative images is, which means that the changes between the preoperative and intraoperative images may be smaller, and the surgery can be performed based on the neurosurgical navigation system, and the potential risk is smaller. The total similarity coefficient provides an important feedback indicator for surgical navigation, helping doctors monitor tissue changes during surgery in real time and ensure that the surgery is performed accurately, especially in operations in complex or critical areas.

[0114] The acquisition logic of the dynamic change coefficient is: according to the pixel value of each pixel point in the real-time image of the complex intraoperative area in the monitoring interval, the time second-order derivative value of the pixel value of each pixel point in the monitoring interval is calculated, and the calculation formula is: in, is the time second-order derivative value of pixel k at different times in the monitoring interval;

[0115] Set the time second derivative threshold and mark the time second derivative threshold as: DS yz , compare the time second-order derivative of each pixel in the real-time image of the complex area within the monitoring interval with the time second-order derivative threshold, obtain the pixel points in the real-time image of the complex area within the monitoring interval that are greater than the time second-order derivative threshold, and re-mark the pixel points in the monitoring interval that are greater than the time second-order derivative threshold as: Wherein, g=1, 2, 3, ..., G, G is a positive integer, and g is the number of the pixel point that is greater than the time second-order derivative threshold in the monitoring interval;

[0116] It should be noted that the time second derivative threshold is set by professional staff to measure the acceleration of the change of a pixel value in a short period of time. Professional staff will set this threshold based on the specific application scenario, image characteristics and expected range of change. When the time second derivative of a pixel value exceeds the set threshold, it means that the pixel has undergone a large change and may represent important clinical information, such as the occurrence of lesions, changes in tissue structure or image quality problems.

[0117] Calculate the dynamic change coefficient using the following formula: Among them, DT bh is the dynamic change coefficient.

[0118] It can be seen from the formula that the larger the dynamic change coefficient is, the greater the potential risk is that the complex area may have undergone significant changes during the operation, which may have a significant impact on the surgical results.

[0119] The acquisition logic of the delay anomaly coefficient is: obtain the timestamp when the image sensor in the real-time image of the complex area captures the image, and mark the timestamp when the image sensor in the real-time image of the complex area captures the image as: Tc h , where h = 1, 2, 3, ..., H, H is a positive integer, and h is the number of the image captured by the image sensor;

[0120] Get the moment when the image is processed and ready for display and record another timestamp, and record another timestamp when the image is processed and ready for display as: Tp h ;

[0121] Calculate the average delay using the formula: Among them, YC is the average delay;

[0122] Calculate the delay standard deviation using the formula: Among them, YC std is the delay standard deviation;

[0123] Calculate the delay coefficient of variation using the formula: Among them, BY yc is the coefficient of variation of delay;

[0124] Calculate the delay anomaly coefficient, the calculation formula is: Among them, YC yc is the delay anomaly coefficient.

[0125] It can be seen from the formula that the larger the delay abnormality coefficient, the greater the potential risk of instability or abnormal delay in the image captured by the image sensor, which affects the real-time performance of the surgical process.

[0126] The total similarity coefficient, dynamic change coefficient and delay anomaly coefficient are weighted to construct an early warning evaluation model and generate an early warning evaluation coefficient. The calculation formula of the early warning evaluation coefficient is: Among them, pg yj is the early warning assessment coefficient, β1, β2, and β3 are the proportional coefficients of the total similarity coefficient, the dynamic change coefficient, and the delay anomaly coefficient, respectively. β1, β2, and β3 are all greater than 0.

[0127] A warning assessment coefficient threshold is set, and the warning assessment coefficient of the complex area is compared with the warning assessment coefficient threshold. If the warning assessment coefficient of the complex area is less than the warning assessment coefficient threshold, a warning signal is generated, indicating that the complex area may have undergone major changes or instability, reminding the surgical team to pay attention to the potential risks of the area. If the warning assessment coefficient of the complex area is greater than the warning assessment coefficient threshold, no warning signal is generated.

[0128] Example 2

[0129] A medium stores a computer program and a storage block. When the computer program is run by a processor, a neurosurgery navigation system based on ray projection is executed and the neurosurgery navigation system based on ray projection is stored in the storage block.

[0130] The present invention analyzes images of the patient's surgical area before surgery, divides the patient's surgical area into multiple regions of interest in a more detailed manner, performs B lob analysis and noise analysis on the regions of interest, evaluates the complexity of the preoperative regions of interest, and marks them. Through the marked regions of interest, potential changes in the surgical area are identified and potential risks are evaluated through image comparison and real-time image analysis during the operation, and an early warning signal is generated according to the early warning evaluation system, which helps the surgical team make corresponding decisions in a timely manner, thereby improving the safety and accuracy of the operation.

[0131] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0132] 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 the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the 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. The 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, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). 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.

[0133] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0134] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0136] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0137] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0138] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A neurosurgery navigation system based on ray projection, characterized in that: It includes a region extraction module, a noise processing module, a feature processing module, a complexity assessment module, an image comparison module and a risk assessment module, and the modules are connected by signals; A region extraction module, used for obtaining a region of interest in the surgical area based on an image of the surgical area of ​​the patient before surgery; A noise processing module, used for determining noise information of the region of interest by comparing the difference between the pixel values ​​of the region of interest and other regions; A feature processing module is used to analyze the patient's three-dimensional image through Blob, extract the connected Blob area in the region of interest, and obtain the regional feature information of the region of interest; A complexity evaluation module is used to quantify the complexity of the region of interest based on the noise information and regional feature information of the region of interest; An image comparison module is used to determine the complex area in the patient's surgical area according to the complexity of the area of ​​interest, obtain the dynamic changes of the patient's complex area by collecting real-time images in the complex area, and determine the matching information of the complex area and the delay information of the real-time imaging; The risk assessment module is used to comprehensively analyze the matching information of complex areas and the delayed information of real-time imaging, quantify the potential risks of complex areas in the patient's surgical area, and generate early warning signals; The noise information of the region of interest is represented by the signal-to-noise ratio deviation coefficient, and the regional characteristic information of the region of interest is represented by the regional performance index; The matching information of complex areas is represented by the total similarity coefficient and the dynamic change coefficient, and the delay information of real-time imaging is represented by the delay anomaly coefficient.

2. A neurosurgery navigation system based on ray projection according to claim 1, characterized in that: Determine noise information for the region of interest, including: The logic for obtaining the signal-to-noise ratio deviation coefficient is as follows: obtain the pixel value of each pixel point in the region of interest, and mark the pixel value of each pixel point in the region of interest as: GXQ n , where n=1, 2, 3, ..., N, N is a positive integer, and n is the number of each pixel in the region of interest; Select the background of the image in the three-dimensional image of the patient, obtain the pixel value of each pixel in the image background, and mark the pixel value of each pixel in the image background as: BJ i , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of each pixel in the image background; Calculate the mean and standard deviation of the pixel value of each pixel in the region of interest, and mark the mean and standard deviation of the pixel value of each pixel in the region of interest as: GXQ avg and GXQ std ,in, Calculate the mean and standard deviation of the pixel value of each pixel in the image background, and mark the mean and standard deviation of the pixel value of each pixel in the image background as: BJ avg and BJ std ,in, Calculate the signal-to-noise ratio deviation coefficient using the following formula: Among them, SNR pc is the signal-to-noise ratio deviation coefficient.

3. A neurosurgery navigation system based on ray projection according to claim 2, characterized in that: Get regional characteristic information of the area of ​​interest, including: The logic for obtaining the regional performance index is as follows: performing Blob analysis on the region of interest, obtaining Blob regions divided in the region of interest, and classifying different Blob regions, and classifying the Blob regions divided in the region of interest into possible disease-prone regions, disease-prone regions, and normal regions; Calculate the regional performance index using the formula: Among them, BX qy is the regional performance index, ZC sl is the number of Blob regions in the normal area of ​​the region of interest, KNB sl BF is the number of Blob regions in the region of interest where the disease may occur. sl is the number of Blob regions in the diseased area of ​​the region of interest.

4. A neurosurgery navigation system based on ray projection according to claim 3, characterized in that: Quantify the complexity of the region of interest, including: The signal-to-noise ratio deviation coefficient and the regional performance index are weighted to construct a preoperative region of interest evaluation model and generate a preoperative region of interest evaluation coefficient. The expression of the preoperative region of interest evaluation coefficient is: Among them, pg sq is the preoperative region of interest assessment coefficient, α1 and α2 are the signal-to-noise ratio deviation coefficient and the proportional coefficient of the regional performance index, respectively, and α1 and α2 are both greater than 0.

5. A neurosurgery navigation system based on ray projection according to claim 4, characterized in that: Identify complex areas within the patient's surgical field, including: A preoperative region of interest evaluation coefficient threshold is set, the preoperative region of interest evaluation coefficient is compared with the preoperative region of interest evaluation coefficient threshold, the region of interest smaller than the preoperative region of interest evaluation coefficient threshold is obtained, and the region of interest smaller than the preoperative region of interest evaluation coefficient threshold is marked as a complex region.

6. A neurosurgery navigation system based on ray projection according to claim 5, characterized in that: Determine matching information for complex areas, including: The acquisition logic of the total similarity coefficient is: obtain the pixel value of each pixel point in the real-time image of the complex area in the monitoring interval, and mark the pixel value of each pixel point in the real-time image of the complex area in the monitoring interval as: SS km , where k = 1, 2, 3, ..., K, K is a positive integer, k is the number of the image collected at different times in the complex area, m = 1, 2, 3, ..., M, M is a positive integer, m is the number of the heavy pixel points of the image at different times in the complex area; Obtain the pixel value of each pixel point in the preoperative image of the complex area, and mark the pixel value of each pixel point in the preoperative image of the complex area as: SQ m , calculate the mean and variance of the pixel values ​​of each pixel point in the complex area preoperative image, and mark the mean and variance of the pixel values ​​of each pixel point in the complex area preoperative image as: avg sq and σ sq ; Calculate the mean and variance of the pixel values ​​of each pixel point in the real-time image of the complex area, and mark the mean and variance of the pixel values ​​of each pixel point in the real-time image of the complex area as: avg k and σ k ; The similarity coefficient between the real-time image of the complex area and the preoperative image at different times is calculated using the following formula: Among them, XS k is the similarity coefficient between the real-time image of the complex area at different times and the preoperative image, cov k is the covariance of the pixel values ​​of each pixel point in the real-time image of the complex area at different times and the preoperative image, C1 and C2 are constants; Calculate the total similarity coefficient, the calculation formula is: Among them, XS all is the total similarity coefficient; The logic for obtaining the dynamic change coefficient is: according to the pixel value of each pixel point in the real-time image of the complex intraoperative area in the monitoring interval, the time second-order derivative value of the pixel value of each pixel point in the monitoring interval is calculated, and the calculation formula is: in, is the time second-order derivative value of pixel k at different times in the monitoring interval; Set the time second derivative threshold and mark the time second derivative threshold as: DS yz , compare the time second-order derivative of each pixel in the real-time image of the complex area within the monitoring interval with the time second-order derivative threshold, obtain the pixel points in the real-time image of the complex area within the monitoring interval that are greater than the time second-order derivative threshold, and re-mark the pixel points in the monitoring interval that are greater than the time second-order derivative threshold as: Wherein, g=1, 2, 3, ..., G, G is a positive integer, and g is the number of the pixel point that is greater than the time second-order derivative threshold in the monitoring interval; Calculate the dynamic change coefficient using the following formula: Among them, DT bh is the dynamic change coefficient.

7. A neurosurgery navigation system based on ray projection according to claim 6, characterized in that: Delayed information for real-time imaging of complex areas, including: The acquisition logic of the delay anomaly coefficient is: obtain the timestamp when the image sensor in the real-time image of the complex area captures the image, and mark the timestamp when the image sensor in the real-time image of the complex area captures the image as: Tc h , where h = 1, 2, 3, ..., H, H is a positive integer, and h is the number of the image captured by the image sensor; Get the moment when the image is processed and ready for display and record another timestamp, and record another timestamp when the image is processed and ready for display as: Tp h ; Calculate the average delay using the formula: Among them, YC is the average delay; Calculate the delay standard deviation using the formula: Among them, YC std is the delay standard deviation; Calculate the delay coefficient of variation using the formula: Among them, BY yc is the coefficient of variation of delay; Calculate the delay anomaly coefficient, the calculation formula is: Among them, YC yc is the delay anomaly coefficient.

8. A neurosurgery navigation system based on ray projection according to claim 7, characterized in that: Comprehensively analyze the matching information of complex areas and the delay information of real-time imaging, including: The total similarity coefficient, dynamic change coefficient and delay anomaly coefficient are weighted to construct an early warning evaluation model and generate an early warning evaluation coefficient. The calculation formula of the early warning evaluation coefficient is: Among them, pg yj is the early warning assessment coefficient, β1, β2, and β3 are the proportional coefficients of the total similarity coefficient, the dynamic change coefficient, and the delay anomaly coefficient, respectively. β1, β2, and β3 are all greater than 0.

9. A neurosurgery navigation system based on ray projection according to claim 8, characterized in that: Generate early warning signals, including A warning assessment coefficient threshold is set, and the warning assessment coefficient of the complex area is compared with the warning assessment coefficient threshold. If the warning assessment coefficient of the complex area is less than the warning assessment coefficient threshold, a warning signal is generated, indicating that the complex area may have undergone major changes or instability, reminding the surgical team to pay attention to the potential risks of the area. If the warning assessment coefficient of the complex area is greater than the warning assessment coefficient threshold, no warning signal is generated.

10. A medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a neurosurgery navigation system based on ray projection according to any one of claims 1 to 9 is executed.

Images