Auxiliary three-dimensional imaging system and method for complex chest trauma operation

Abstract

The invention belongs to the technical field of medical image assistance, and particularly relates to an auxiliary stereo imaging system and method for a complex chest trauma operation. By integrating multi-modal image data, real-time three-dimensional space capture, dynamic correction and risk score driven view adjustment, accurate assistance of the thymotomy operation process is achieved, the accuracy and safety of the operation are improved, the operation risk and operation difficulty are remarkably reduced, and the operation efficiency is improved. By acquiring and processing multi-modal image data in real time, a high-precision three-dimensional anatomical structure model containing thymus tissues, a blood vessel network and nerve distribution can be constructed, a visual surgical navigation view is provided for a doctor, meanwhile, a dynamic correction technology is adopted, thymus displacement parameters caused by thoracic cavity respiratory movement of a patient are monitored in real time, and the thoracic cavity of the patient can be accurately and accurately positioned. And on the basis, the real-time three-dimensional space data is dynamically adjusted, so that the spatial synchronization of the image data and the anatomical structure is ensured, and the navigation error caused by respiratory movement is effectively avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical imaging assistance, and particularly relates to a complex chest trauma surgical assistance stereoscopic imaging system and method. Background Art

[0002] With the continuous progress of medical technology, the requirements for the precision of surgical operations are increasing day by day. Especially in complex thymectomy surgeries, traditional surgical navigation methods often rely on two-dimensional imaging data and are difficult to intuitively and real-time reflect the three-dimensional anatomical structure of the surgical area, thus increasing the surgical risk and operation difficulty. Along with the rapid development of three-dimensional imaging technology, its application in the medical field is becoming more and more extensive. Performing surgical navigation based on three-dimensional imaging technology can significantly improve the accuracy and safety of surgeries.

[0003] However, there are still some problems with existing three-dimensional imaging technology in thymectomy surgeries, such as real-time update of image data, precise reconstruction of anatomical structures, and dynamic changes of anatomical structures during the surgical process, etc. These often lead to insufficient real-time performance and accuracy of surgical navigation, and thus affect the surgical effect. In addition, there are some areas blocked by instruments during the surgical process, and the blocked areas may limit the doctor's vision and affect the precision and safety of the surgery. To solve the above problems, the present invention proposes a complex chest trauma surgical assistance stereoscopic imaging method to improve the precision and safety of surgeries. Summary of the Invention

[0004] The purpose of the present invention is to provide a complex chest trauma surgical assistance stereoscopic imaging system and method, which can obtain multi-modal image data of the thymus region in real time, construct a precise three-dimensional anatomical structure model, and dynamically correct the spatial synchronization between the image data and the anatomical structure to generate a stereoscopic navigation view to assist doctors in surgical operations.

[0005] The technical solutions adopted by the present invention are specifically as follows: A complex chest trauma surgical assistance stereoscopic imaging method, comprising: Obtaining multi-modal image data of the thymus region, where the multi-modal image data includes CT images and ultrasound images; Constructing a three-dimensional anatomical structure model containing thymus tissue, blood vessel network, and nerve distribution through image segmentation processing; Real-time capturing visible light images and near-infrared spectral data of the surgical field to generate real-time three-dimensional space data; Collecting real-time displacement parameters of the thymus caused by the patient's thoracic respiratory movement, and dynamically correcting the real-time three-dimensional space data according to the real-time displacement parameters to maintain the spatial synchronization between the image data and the anatomical structure; Overlay the corrected three-dimensional anatomical structure model with the operative field in real time to generate a stereoscopic navigation view, and dynamically adjust the display angle, depth, and transparency of the stereoscopic navigation view according to the risk score of the resection location.

[0006] In a preferred embodiment, after the multi-modal image data acquisition is completed, preprocessing is performed synchronously. The steps of preprocessing include: Perform isotropic sampling on the CT images and uniformly adjust the slice thickness to a preset standard value; Perform dynamic range compression and speckle noise suppression on the ultrasound images, and eliminate speckle noise through anisotropic diffusion filtering; Acquire CT images and ultrasound images at the end of exhalation and peak inhalation phases respectively, and fuse the CT images and ultrasound images to correct respiratory artifacts.

[0007] In a preferred embodiment, the steps of constructing a three-dimensional anatomical structure model including thymic tissue, vascular network, and nerve distribution through image segmentation processing include: Use image feature comparison to process the CT images, and combine with the texture features of the ultrasound images for auxiliary segmentation to extract the contour of the thymic tissue; Identify and label the main blood vessels with a preset diameter through vascular recognition, and combine with ultrasound blood flow imaging to confirm the branching directions of blood vessels and supplement the capillary network; Based on the high-resolution characteristics of the ultrasound images, identify the directions of nerve fibers and generate a nerve distribution map; Perform spatial matching on the segmentation results of each image source, and achieve the fusion of multi-modal image data through respiratory cycle synchronization correction to generate a three-dimensional anatomical structure model of the thymic region.

[0008] In a preferred embodiment, the steps of capturing the visible light image and near-infrared spectrum data of the operative field in real time to generate real-time three-dimensional spatial data include: Use dual-channel synchronous imaging to obtain high-definition visible light images and near-infrared spectrum information of the operative field respectively. Among them, the dual-channel includes a visible light channel and a near-infrared channel. The visible light channel is equipped with a polarization filter, and the near-infrared channel sets a specific wavelength range to enhance the contrast of blood vessel imaging; Perform dynamic threshold segmentation on the near-infrared spectrum information, extract the blood vessel contour, and perform spatial registration in combination with the visible light image to align the blood vessels with the tissue structure; Fuse the registered visible light image and near-infrared spectrum information, and input them into a pre-trained deep learning model to predict the anatomical structure topological relationship of the instrument occlusion area in the operative field and generate real-time three-dimensional spatial data with confidence weights.

[0009] In a preferred embodiment, the step of predicting the anatomical structure topological relationship of the instrument occlusion area in the surgical field and generating real-time three-dimensional spatial data with confidence weights includes: Collect the positions of the instruments in consecutive multi-frame near-infrared spectral information, perform spatial mapping based on the positions of the instruments, and establish the instrument movement trajectories; Predict the potential occlusion areas of the anatomical structures by the instruments at the next moment according to the historical movement trajectories of the instruments and the current breathing phase; Perform hierarchical annotation on the anatomical structures within the potential occlusion areas, determine the corresponding confidence weights according to the occlusion degree, encode the confidence weights as transparency parameters, and then integrate the transparency parameters into the real-time three-dimensional spatial data model.

[0010] In a preferred embodiment, the step of collecting the real-time displacement parameters of the thymus caused by the respiratory movement of the patient's chest includes: Real-time monitor the contraction amplitude and frequency of the intercostal muscle groups through a micro-sensor array pre-deployed in the patient's chest to obtain thymus displacement data; Select respiratory movement feature marker points in the CT images, and combine with the real-time diaphragm displacement data of the ultrasound images to construct a three-dimensional spatial displacement vector field; Collect the real-time displacement data and historical displacement data of the patient under the current breathing cycle and historical breathing cycles, and perform time series analysis to output the predicted deformation parameters of the thymus tissue; Superimpose the three-dimensional spatial displacement vector field and the predicted deformation parameters to generate the real-time displacement parameters of the thymus.

[0011] In a preferred embodiment, the step of dynamically correcting the real-time three-dimensional spatial data based on the real-time displacement parameters to maintain the spatial synchronization between the image data and the anatomical structures includes: Calculate the coordinate compensation amount of the real-time three-dimensional spatial data based on the three-dimensional spatial displacement vector field and the predicted deformation parameters, and adjust the image data frame by frame according to the coordinate compensation amount; Through the synchronous acquisition of the visible light channel and the near-infrared channel, update the three-dimensional coordinates of the chest anatomical structures at a preset update interval within the breathing cycle; Compare the real-time monitoring values fed back by the micro-sensor array with the predicted deformation parameters in real time, output the spatial deviation, and dynamically correct the coordinate compensation amount according to the spatial deviation; When the spatial deviation exceeds the preset threshold, trigger the alarm mechanism and trigger the ultrasound scan for secondary calibration.

[0012] In a preferred embodiment, the step of dynamically adjusting the display angle, depth, and transparency of the stereoscopic navigation view according to the risk score of the resection position includes: Calculate the Euclidean distance between the current resection point and the blood vessel network in the three-dimensional anatomical structure model, and record it as the first conditional parameter; Collect the minimum distance between the current resection point and the nerve fiber bundle, and record it as the second conditional parameter; Perform weighted fusion on the first conditional parameter and the second conditional parameter to generate a risk score; Dynamically adjust the display angle, depth, and transparency of the stereoscopic navigation view according to the risk score; When the risk score is higher than the preset risk threshold, trigger an ultrasound scan for secondary calibration and synchronously update the topological structure of the occluded area; When the risk score is lower than the preset risk threshold, output a risk deviation value, and fine-tune the display parameters of the stereoscopic navigation view according to the risk deviation value.

[0013] The present invention also provides a surgical assistance stereoscopic imaging system for thymectomy, using the above-mentioned complex chest trauma surgical assistance stereoscopic imaging method, including: A data acquisition module for acquiring multi-modal image data in the thymus region, where the multi-modal image data includes CT images and ultrasound images; A model construction module for constructing a three-dimensional anatomical structure model including thymus tissue, blood vessel network, and nerve distribution through image segmentation processing; An operative field capture module for real-time capturing visible light images and near-infrared spectral data of the operative field to generate real-time three-dimensional spatial data; A correction module for collecting real-time displacement parameters of the thymus caused by the patient's thoracic respiratory movement, and dynamically correcting the real-time three-dimensional spatial data according to the real-time displacement parameters to maintain the spatial synchronization between the image data and the anatomical structure; A view adjustment module for overlaying the corrected three-dimensional anatomical structure model with the operative field in real time to generate a stereoscopic navigation view, and dynamically adjusting the display angle, depth, and transparency of the stereoscopic navigation view according to the risk score at the resection position.

[0014] And an electronic device, the electronic device includes: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned complex chest trauma surgical assistance stereoscopic imaging method.

[0015] The technical effects achieved by the present invention are: The present invention realizes precise assistance for the thymectomy surgical process by integrating multi-modal image data, real-time three-dimensional space capture, dynamic correction, and risk score-driven view adjustment. This method not only improves the accuracy and safety of the surgery but also significantly reduces the surgical risk and operation difficulty. By acquiring and processing multi-modal image data in real time, the present invention can construct a high-precision three-dimensional anatomical structure model including thymus tissue, blood vessel network, and nerve distribution, providing an intuitive surgical navigation view for doctors, enabling them to clearly identify anatomical structures during the surgery, and thus making more accurate surgical decisions. The dynamic correction technology is also adopted. By real-time monitoring the thymus displacement parameters caused by the patient's thoracic respiratory movement and dynamically adjusting the real-time three-dimensional space data based on this, the spatial synchronization between the image data and the anatomical structure is ensured, effectively avoiding navigation errors caused by respiratory movement. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic flow chart of the method of the present invention; Figure 2 is a schematic diagram of the system module of the present invention; Figure 3 is a schematic diagram of the electronic device structure of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be made in conjunction with the accompanying drawings of the specification.

[0018] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0019] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in a preferred embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selectively exclusive embodiment from other embodiments.

[0020] Please refer to Figure 1 as shown, the present invention provides a method for assisted stereoscopic imaging of complex chest trauma surgery, including: S1. Acquire multi-modal image data under the thymus region, and the multi-modal image data includes CT images and ultrasound images; In the step S1, before performing thymectomy, multi-modal image data of the thymus region is collected, including computed tomography (CT) images and ultrasound images. CT images can provide high-resolution anatomical structure information, while ultrasound images can show the real-time dynamic conditions of the vascular network and nerve distribution. The combination of the two provides rich information for three-dimensional reconstruction. After the multi-modal image data is collected, preprocessing is performed synchronously. The steps of preprocessing include: Perform isotropic sampling on the CT images and uniformly adjust the slice thickness to a preset standard value; Perform dynamic range compression and speckle noise suppression on the ultrasound images, and eliminate speckle noise through anisotropic diffusion filtering; Collect CT images and ultrasound images at the end of exhalation and the peak phase of inhalation respectively, and fuse the CT images and ultrasound images to correct respiratory artifacts; Specifically, after the multi-modal image data is collected, in order to improve the quality of the image data and provide a more accurate basis for subsequent three-dimensional reconstruction and surgical navigation, first, isotropic sampling is performed on the CT images. In this stage, the slice thickness of the CT images is uniformly adjusted to a preset standard value, such as 1 mm or 2 mm, to ensure uniform resolution in the entire volume data. This processing method helps to perform seamless image browsing and analysis in three-dimensional space, especially for cases that require precise measurement or three-dimensional reconstruction. For ultrasound images, the preprocessing steps include dynamic range compression and speckle noise suppression. The dynamic range of ultrasound images is usually large, which may cause the details of bright and dark areas to not be clearly displayed at the same time. Through dynamic range compression, the contrast of the image can be adjusted to make the boundaries of different tissues more obvious. At the same time, since speckle noise in ultrasound imaging is a common problem, the application of anisotropic diffusion filters can effectively eliminate irregular speckles and improve the clarity of the image. Then, CT images and ultrasound images are collected at two key points of respiration - the end of exhalation and the peak phase of inhalation. This is mainly because respiratory movement may cause small changes in the position of internal organs, generating respiratory artifacts. By comparing images at different respiratory phases and performing fusion processing, the position deviation caused by respiration can be corrected, thus providing more accurate comparison and positioning information.

[0021] S2. Construct a three-dimensional anatomical structure model including thymus tissue, vascular network, and nerve distribution through image segmentation processing; In the step S2, after the multi-modal image data is processed, the processed multi-modal image data will be finely segmented through corresponding image segmentation processing techniques to construct a three-dimensional anatomical structure model including thymus tissue, blood vessel network, and nerve distribution, providing an accurate anatomical reference for thymectomy planning. Among them, the steps of constructing a three-dimensional anatomical structure model including thymus tissue, blood vessel network, and nerve distribution through image segmentation processing include: Process the CT image using image feature comparison and assist in segmentation by combining the texture features of the ultrasound image to extract the contour of the thymus tissue; Automatically label the main blood vessels with a preset diameter through blood vessel recognition, and confirm the direction of blood vessel branches by combining ultrasound blood flow imaging to supplement the capillary network; Based on the high-resolution characteristics of the ultrasound image, identify the direction of nerve fibers and generate a nerve distribution map; Perform spatial matching on the segmentation results of each image source, and through respiratory cycle synchronization correction, realize the fusion of multi-modal image data to generate a three-dimensional anatomical structure model of the thymus region; Specifically, in the process of constructing the three-dimensional anatomical structure model, first, the CT image is processed using image feature comparison technology to enhance the boundary of the thymus tissue, making it more prominent against a high-contrast background. At the same time, by introducing the texture features of the ultrasound image, more accurate segmentation can be assisted, thereby extracting the accurate contour of the thymus tissue and ensuring the initial accuracy of the model. Then, the blood vessel recognition technology is used to automatically label the main blood vessels with a preset diameter, making the main blood vessels show obvious structures in the CT image. Subsequently, by combining the dynamic information of ultrasound blood flow imaging, the direction of blood vessel branches can be traced and confirmed to construct a complete blood vessel network. After identifying the blood vessel structure, by analyzing the ultrasound image, the direction of nerve fibers can be identified to form a map of nerve distribution. Finally, perform spatial matching on the segmentation results of CT, ultrasound, and nerve distribution. This process requires respiratory cycle synchronization correction for different image sources to eliminate the anatomical structure displacement caused by respiratory movement and ensure that each structure can be accurately aligned in three-dimensional space, thereby generating a complete three-dimensional anatomical structure model of the thymus region.

[0022] S3. Real-time capture the visible light image and near-infrared spectrum data of the surgical field to generate real-time three-dimensional space data; In the step S3, during the operation, the visible light image and near-infrared spectrum data of the surgical field will be captured in real time to generate real-time three-dimensional space data. Through near-infrared spectroscopy, the real-time displacement of the thymus caused by thoracic respiratory movement can be traced to maintain the synchronization between the image and the actual anatomical structure. Among them, the steps of real-time capturing the visible light image and near-infrared spectrum data of the surgical field to generate real-time three-dimensional space data include: Dual-channel synchronous imaging is used to obtain high-definition visible light images and near-infrared spectral information of the surgical field. The dual channels include a visible light channel and a near-infrared channel. The visible light channel is equipped with a polarization filter, and the near-infrared channel is set to a specific wavelength range to enhance the contrast of vascular development. Perform dynamic threshold segmentation on near-infrared spectral information, extract blood vessel contours, and combine with visible light images for spatial registration to align blood vessels and tissue structures; The registered visible light image is fused with the near-infrared spectrum information and input into the pre-trained deep learning model to predict the anatomical topological relationship of the instrument-occluded area in the surgical field and generate real-time three-dimensional spatial data with confidence weights. Specifically, during the operation, dual-channel imaging is used to obtain high-definition visible light images and near-infrared spectral information of the surgical field. The visible light channel is equipped with a polarizing filter to reduce the interference of ambient light and enhance the image contrast to make the tissue structure clearer, while the near-infrared channel is set within a specific wavelength range. The purpose of setting the wavelength range is to maximize the absorption of near-infrared light by hemoglobin in the blood vessels, thereby improving the effect of vascular development. Then, the near-infrared spectral information is processed by dynamic threshold segmentation to identify the blood vessel contour, and the segmented blood vessel contour is spatially aligned with the visible light image (such as through feature point matching algorithms) to ensure that the vascular structure is clear. The 3D structure is aligned with other tissue structures in the surgical field to provide an accurate reference for subsequent 3D reconstruction. After the registration is completed, the data integrating visible light image information and near-infrared spectral information is input into the pre-trained deep learning model (specifically through known deep learning frameworks, such as convolutional neural networks, etc., trained and optimized based on existing image data). This can predict the topological relationship of the anatomical structure in the area blocked by the instrument. Through the prediction of the deep learning model, the generated 3D spatial data not only contains the structural information of the surgical field, but also comes with confidence weights. The confidence weights can indicate the accuracy of the deep learning model's predictions, providing real-time decision support for doctors.

[0023] Secondly, the steps of predicting the topological relationship of the anatomical structure in the instrument occlusion area in the surgical field and generating real-time three-dimensional spatial data with confidence weights include: Collect the position of the instrument in multiple frames of continuous near-infrared spectral information, perform spatial mapping based on the position of the instrument, and establish the movement trajectory of the instrument; Based on the historical movement trajectory of the device and the current breathing stage, predict the potential occlusion area of ​​the anatomical structure by the device at the next moment; The anatomical structures in the potential occlusion area are graded and labeled, and the corresponding confidence weights are determined according to the degree of occlusion. The confidence weights are encoded into transparency parameters, and then the transparency parameters are integrated into the real-time 3D spatial data model. In this embodiment, first, multiple frames of near-infrared spectral information are continuously collected. The near-infrared spectral information can accurately capture the position of the instrument in the surgical field and also perform real-time spatial mapping to construct the dynamic movement trajectory of the instrument. Specifically, it is similar to drawing the movement path of the instrument in a virtual space, providing a basis for subsequent prediction and analysis. Then, the historical movement trajectory of the instrument is used to predict its future movement trend. Here, considering the influence of physiological activities such as human breathing, the movement pattern of the instrument at the current breathing stage is analyzed to predict the potential occlusion area that the instrument may cause to the anatomical structure at the next moment, which helps the doctor anticipate potential line-of-sight obstructions in advance and make corresponding operation adjustments. After determining the potential occlusion area, the anatomical structures within the potential occlusion area are classified and labeled. According to the severity of the occlusion, such as complete occlusion, partial occlusion, or only causing light interference, etc., the anatomical structures are assigned different confidence weightings. The confidence weightings can help the doctor quickly identify the severity of the occlusion and prioritize the treatment of important or urgent parts. In this embodiment, the confidence weightings are converted into transparency parameters. The higher the occlusion degree of the area, the higher the transparency. Thus, in the three-dimensional spatial data model, the doctor can observe which areas may disappear behind the instrument and which areas are still visible, enhancing the practicality and intuitiveness of the real-time three-dimensional view.

[0024] S4. Collect the real-time displacement parameters of the thymus caused by the patient's thoracic respiratory movement, and dynamically correct the real-time three-dimensional spatial data according to the real-time displacement parameters to maintain the spatial synchronization between the image data and the anatomical structure; In the step S4, the three-dimensional spatial data is dynamically corrected according to the real-time displacement parameters to eliminate the image drift caused by the patient's respiratory movement, so as to ensure that the image data and the anatomical structure can always be consistent and provide a stable and reliable surgical field navigation for the doctor. Among them, the step of collecting the real-time displacement parameters of the thymus caused by the patient's thoracic respiratory movement includes: By a micro-sensor array pre-deployed in the patient's chest, the contraction amplitude and frequency of the intercostal muscles are monitored in real time to obtain thymus displacement data; Select respiratory movement feature marker points in the CT image, and combine with the real-time diaphragm displacement data of the ultrasound image to construct a three-dimensional spatial displacement vector field; Collect the real-time displacement data and historical displacement data of the patient at the current breathing cycle and historical breathing cycles, and perform time series analysis to output the predicted deformation parameters of the thymus tissue; Superimpose and process the three-dimensional spatial displacement vector field and the predicted deformation parameters to generate the real-time displacement parameters of the thymus; Specifically, when collecting the real-time displacement parameters of the patient's thymus, first deploy a micro-sensor array at the patient's chest cavity to monitor the contraction amplitude and frequency of the intercostal muscle groups in real time, so as to effectively track the minute displacement of the thymus. In order to construct a more accurate three-dimensional space model, characteristic marker points of the respiratory movement are selected in the CT image. The characteristic marker points combined with the real-time diaphragm displacement data provided by the ultrasound image can form a dynamic three-dimensional space displacement vector field to mark the movement trajectory of the thymus during each breath. Then, the displacement data of the patient's current respiratory cycle and several past respiratory cycles are also collected and subjected to time series analysis (such as using time series prediction algorithms such as autoregressive integrated moving average model or long short-term memory network), so as to identify the deformation law of the thymus tissue and output the predicted deformation parameters at different respiratory stages. Finally, the obtained three-dimensional space displacement vector field and the predicted deformation parameters are superimposed (specifically, each coordinate point of the three-dimensional space displacement vector field is multiplied by the predicted deformation parameter point by point and weighted and summed), and the generated real-time displacement parameters can comprehensively display the dynamic changes of the thymus during breathing.

[0025] Secondly, the steps of dynamically correcting the real-time three-dimensional space data according to the real-time displacement parameters to keep the spatial synchronization between the image data and the anatomical structure include: Based on the three-dimensional space displacement vector field and the predicted deformation parameters, calculate the coordinate compensation amount of the real-time three-dimensional space data, and adjust the image data frame by frame according to the coordinate compensation amount; Through the synchronous acquisition of the visible light channel and the near-infrared channel, update the three-dimensional coordinates of the chest anatomical structure at a preset update interval during the respiratory cycle; According to the real-time monitoring value fed back by the micro-sensor array, compare it with the predicted deformation parameters in real time, output the spatial deviation, and dynamically correct the coordinate compensation amount according to the spatial deviation; When the spatial deviation exceeds the preset threshold, trigger the alarm mechanism and trigger the ultrasound scan for secondary calibration; Specifically, when adjusting the real-time three-dimensional space data by using the real-time displacement parameters, first calculate the coordinate compensation amount of each frame of image data based on the three-dimensional space displacement vector field and in combination with the predicted deformation parameters. Among them, the calculation formula of the coordinate compensation amount is: , where represents the coordinate compensation amount, represents the three-dimensional space coordinate point, represents the time parameter (respiratory cycle stage), represents the th three-dimensional space displacement vector field component, represents the weight coefficient of the displacement vector field, represents the total number of displacement vector field components, with a value of 3, corresponding to direction represents a correction coefficient for predicting deformation parameters represents the predicted deformation parameter to compensate for the minute displacement caused by physiological movement. In this way, the multi-modal image data can be adjusted to the position corresponding to the actual anatomical structure, and then synchronously acquired through the visible light channel and the near-infrared channel. The three-dimensional coordinates of the thoracic anatomical structure are updated at a preset update interval within the respiratory cycle, so as to provide more comprehensive and real-time information on anatomical structure changes. Then, the data monitored by the real-time feedback of the micro-sensor array is compared with the predicted deformation parameter. When a spatial deviation is found, it will be immediately output, and the coordinate compensation amount will be dynamically corrected accordingly to ensure that the calibration process can be maintained under rapidly changing physiological conditions. It should be noted that when the spatial deviation exceeds the preset deviation threshold, an alarm mechanism will also be triggered to alert the operator, and at the same time, an ultrasonic scan will be started for secondary calibration to avoid the problem of inaccurate navigation caused by error accumulation.

[0026] S5. Superimpose the corrected three-dimensional anatomical structure model on the surgical field in real time to generate a stereoscopic navigation view, and dynamically adjust the display angle, depth, and transparency of the stereoscopic navigation view according to the risk score of the resection position; In the step S5, the corrected three-dimensional anatomical structure model will be superimposed and displayed on the real-time image of the surgical field to generate a stereoscopic navigation view, and according to the risk score of the resection position, the display angle, depth, and transparency can be dynamically adjusted, enabling the doctor to more intuitively identify high-risk areas and thus make accurate surgical decisions. Among them, the step of dynamically adjusting the display angle, depth, and transparency of the stereoscopic navigation view according to the risk score of the resection position includes: Calculate the Euclidean distance between the current resection point and the blood vessel network in the three-dimensional anatomical structure model and record it as the first conditional parameter; Collect the minimum distance between the current resection point and the nerve fiber bundle and record it as the second conditional parameter; Perform weighted fusion on the first conditional parameter and the second conditional parameter to generate a risk score; Dynamically adjust the display angle, depth, and transparency of the stereoscopic navigation view according to the risk score; When the risk score is higher than the preset risk threshold, trigger an ultrasonic scan for secondary calibration and synchronously update the topological structure of the occluded area; When the risk score is lower than the preset risk threshold, output the risk deviation value and finely adjust the display parameters of the stereoscopic navigation view according to the risk deviation value; Specifically, first, the Euclidean distance between the current resection point and the vascular network in the three-dimensional anatomical structure model will be calculated, that is, in three-dimensional space, the straight-line distance from the resection point to the nearest blood vessel, which quantifies the possible impact degree of the resection operation on the blood vessels and is recorded as the first conditional parameter. To protect the nerve fiber bundle, the minimum distance between the current resection point and the sensitive structure will also be collected and recorded as the second conditional parameter. Then, the first conditional parameter and the second conditional parameter will be weighted and fused to generate the corresponding risk score. According to the risk score, the display parameters of the stereoscopic navigation view will be adjusted in real time. If the risk score exceeds the preset risk threshold, it indicates that the potential threat of the resection operation to the surrounding tissues increases. At this time, an ultrasonic scan will be triggered for secondary calibration, which helps to further confirm the safety of the resection point and synchronously update the topological structure of the occluded area to ensure the accuracy of the navigation information. When the risk score is lower than the preset risk threshold, it indicates that the surgical risk is relatively low. At this time, the risk deviation value (the difference between the risk threshold and the risk score) will be output, and the display parameters of the stereoscopic navigation view will be fine-tuned according to the risk deviation value to ensure that the surgeon can obtain appropriate visual guidance.

[0027] Please refer to Figure 2 , a surgical assistance stereoscopic imaging system for thymectomy, using the above-mentioned complex chest trauma surgical assistance stereoscopic imaging method, including: A data acquisition module for acquiring multi-modal image data in the thymus region, where the multi-modal image data includes CT images and ultrasonic images; A model construction module for constructing a three-dimensional anatomical structure model including thymus tissue, vascular network, and nerve distribution through image segmentation processing; An operative field capture module for capturing the visible light image and near-infrared spectrum data of the operative field in real time to generate real-time three-dimensional space data; A correction module for collecting the real-time displacement parameters of the thymus caused by the patient's thoracic respiratory movement and dynamically correcting the real-time three-dimensional space data according to the real-time displacement parameters to maintain the spatial synchronization between the image data and the anatomical structure; A view adjustment module for superimposing the corrected three-dimensional anatomical structure model and the operative field in real time to generate a stereoscopic navigation view and dynamically adjusting the display angle, depth, and transparency of the stereoscopic navigation view according to the risk score of the resection position.

[0028] Among the above, the data acquisition module can accurately acquire multi-modal image data under the thymus region. The multi-modal image data includes high-precision CT images and real-time ultrasound images, laying a foundation for subsequent model construction. The model construction module constructs a three-dimensional anatomical structure model including thymus tissue, blood vessel network, and nerve distribution through advanced image segmentation processing technology. The operative field capture module is responsible for real-time capturing of visible light images and near-infrared spectral data of the operative field. The visible light images and near-infrared spectral data can generate real-time three-dimensional spatial data after being processed, providing real-time information for dynamic correction during the surgical process. The correction module can collect real-time displacement parameters of the thymus caused by the patient's thoracic respiratory movement, and dynamically correct the real-time three-dimensional spatial data based on the real-time displacement parameters to ensure the spatial synchronization of the image data and the anatomical structure, thereby improving the accuracy and safety of the surgical process. The view adjustment module is responsible for real-time superimposing the corrected three-dimensional anatomical structure model on the operative field to generate a stereoscopic navigation view, and dynamically adjusting the display angle, depth, and transparency of the stereoscopic navigation view according to the risk score of the resection position, enabling the doctor to more intuitively identify high-risk areas and make more accurate surgical decisions.

[0029] Please refer to Figure 3 , an electronic device, the electronic device includes: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the above complex chest trauma surgery assisted stereoscopic imaging method.

[0030] The processor of the above electronic device can be a central processing unit (CPU), a graphics processing unit (GPU), or a digital signal processor (DSP). The memory can include a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash), a hard disk, or a solid-state drive (SSD). And, the computer program stored in the memory can be executed by the processor to implement the above thymectomy surgery assisted stereoscopic imaging method. In addition, the electronic device can also include components such as an arithmetic unit, an input device, an output device, and a network interface. The arithmetic unit can provide computing support for at least one of the central processing unit (CPU), the graphics processing unit (GPU), or the digital signal processor (DSP). The input device, such as a keyboard, a mouse, or a touch screen, is used to receive user input instructions. The output device, such as a display or a printer, is used to display the processing result or print output. The network interface is responsible for the communication connection between the electronic device and other devices to ensure data transmission and sharing.

[0031] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method comprising a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, device, article or method. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, device, article or method comprising such element.

[0032] The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention. The structures, devices and operation methods not specifically described and explained in the present invention are implemented by conventional means in the art without special description and limitation.

Claims

1. A stereoscopic imaging method for assisting complex chest trauma surgery, characterized in that: Including: Obtain multimodal image data under the thymus region, where the multimodal image data includes CT images and ultrasound images; Construct a three-dimensional anatomical structure model including thymus tissue, vascular network, and nerve distribution through image segmentation processing; Real-time capture the visible light image and near-infrared spectral data of the surgical field to generate real-time three-dimensional space data; Collect the real-time displacement parameters of the thymus caused by the patient's thoracic respiratory movement, and dynamically correct the real-time three-dimensional space data based on the real-time displacement parameters to maintain the spatial synchronization of the image data and the anatomical structure; Overlay the corrected three-dimensional anatomical structure model with the surgical field in real time to generate a stereoscopic navigation view, and dynamically adjust the display angle, depth, and transparency of the stereoscopic navigation view according to the risk score of the resection position.

2. The method for assisting three-dimensional imaging in complex chest trauma surgery according to claim 1, wherein: After the multimodal image data is collected, preprocessing is performed synchronously. The steps of preprocessing include: Perform isotropic sampling processing on the CT images, and uniformly adjust the slice thickness to a preset standard value; Perform dynamic range compression and speckle noise suppression on the ultrasound images, and eliminate speckle noise through anisotropic diffusion filtering; Collect CT images and ultrasound images at the end of exhalation and the peak phase of inhalation respectively, and fuse the CT images and ultrasound images to correct respiratory artifacts.

3. A method for assisting three-dimensional imaging in complex chest trauma surgery according to claim 1, characterized in that: The steps of constructing a three-dimensional anatomical structure model including thymus tissue, vascular network, and nerve distribution through image segmentation processing include: Use image feature contrast to process the CT images, and combine the texture features of the ultrasound images for auxiliary segmentation to extract the contour of the thymus tissue; Identify and label the main blood vessels with a preset diameter through vascular recognition, and combine ultrasound blood flow imaging to confirm the direction of blood vessel branches and supplement the capillary network; Based on the high-resolution characteristics of the ultrasound images, identify the direction of nerve fibers and generate a nerve distribution map; Perform spatial matching on the segmentation results of each image source, and achieve the fusion of multimodal image data through respiratory cycle synchronization correction to generate a three-dimensional anatomical structure model of the thymus region.

4. A method for stereoscopic imaging assistance in complex chest trauma surgery according to claim 1, characterized in that: The steps of real-time capturing the visible light image and near-infrared spectral data of the surgical field to generate real-time three-dimensional space data include: Use dual-channel synchronous imaging to respectively obtain the high-definition visible light image and near-infrared spectral information of the surgical field. Among them, the dual-channel includes a visible light channel and a near-infrared channel. The visible light channel is equipped with a polarization filter, and the near-infrared channel sets a specific wavelength range to enhance the contrast of blood vessel imaging; Perform dynamic threshold segmentation on the near-infrared spectral information, extract the blood vessel contour, and perform spatial registration in combination with the visible light image to align the blood vessels and tissue structures; Fuse the registered visible light image and near-infrared spectral information, and input them into a pre-trained deep learning model to predict the anatomical structure topological relationship of the instrument occlusion area in the surgical field, and generate real-time three-dimensional space data with confidence weights.

5. A method for assisting three-dimensional imaging in complex chest trauma surgery according to claim 4, characterized in that: The steps of predicting the anatomical structure topological relationship of the instrument occlusion area in the surgical field and generating real-time three-dimensional space data with confidence weights include: Collect the positions of the instruments in consecutive frames of near-infrared spectral information, and perform spatial mapping based on the positions of the instruments to establish the movement trajectory of the instruments; Predict the potential occlusion area of the instruments on the anatomical structure at the next moment according to the historical movement trajectory of the instruments and the current respiratory phase; Grade and label the anatomical structures within the potential occlusion area, determine the corresponding confidence weight according to the occlusion degree, encode the confidence weight as a transparency parameter, and then integrate the transparency parameter into the real-time three-dimensional spatial data model.

6. A method for assisting three-dimensional imaging in complex chest trauma surgery according to claim 1, characterized in that: The step of collecting the real-time displacement parameters of the thymus caused by the thoracic respiratory movement of the patient includes: By means of a micro sensor array pre-deployed in the patient's chest cavity, the contraction amplitude and frequency of the intercostal muscle groups are monitored in real time to obtain thymus displacement data; Select respiratory movement feature marker points in the CT image, and combine with the real-time diaphragm displacement data of the ultrasonic image to construct a three-dimensional spatial displacement vector field; Collect the real-time displacement data and historical displacement data of the patient under the current respiratory cycle and historical respiratory cycles, and perform time series analysis to output the predicted deformation parameters of the thymus tissue; Superimpose and process the three-dimensional spatial displacement vector field and the predicted deformation parameters to generate the real-time displacement parameters of the thymus.

7. A method for auxiliary three-dimensional imaging of complex chest trauma surgery according to claim 1, characterized in that: The step of dynamically correcting the real-time three-dimensional spatial data according to the real-time displacement parameters to maintain the spatial synchronization between the image data and the anatomical structure includes: Based on the three-dimensional spatial displacement vector field and the predicted deformation parameters, calculate the coordinate compensation amount of the real-time three-dimensional spatial data, and adjust the image data frame by frame according to the coordinate compensation amount; Through the synchronous acquisition of the visible light channel and the near-infrared channel, update the three-dimensional coordinates of the thoracic anatomical structure at a preset update interval within the respiratory cycle; According to the real-time monitoring value feedback by the micro sensor array, compare it with the predicted deformation parameters in real time, output the spatial deviation, and dynamically correct the coordinate compensation amount according to the spatial deviation; When the spatial deviation exceeds the preset threshold, trigger the alarm mechanism and trigger ultrasonic scanning for secondary calibration.

8. A method for assisting three-dimensional imaging in complex chest trauma surgery according to claim 7, characterized in that: The step of dynamically adjusting the display angle, depth and transparency of the stereoscopic navigation view according to the risk score of the resection position includes: Calculate the Euclidean distance between the current resection point and the blood vessel network in the three-dimensional anatomical structure model, and record it as the first conditional parameter; Collect the minimum distance between the current resection point and the nerve fiber bundle, and record it as the second conditional parameter; Perform weighted fusion on the first conditional parameter and the second conditional parameter to generate a risk score; Dynamically adjust the display angle, depth and transparency of the stereoscopic navigation view according to the risk score; When the risk score is higher than the preset risk threshold, trigger ultrasonic scanning for secondary calibration and synchronously update the topological structure of the occlusion area; When the risk score is lower than the preset risk threshold, output the risk deviation value, and finely adjust the display parameters of the stereoscopic navigation view according to the risk deviation value.

9. A surgical assistance stereoscopic imaging system for thymectomy, characterized in that: Using the complex chest trauma surgery-assisted stereoscopic imaging method according to any one of claims 1 to 8, includes: A data acquisition module, used to acquire multi-modal image data in the thymus region, and the multi-modal image data includes CT images and ultrasonic images; A model construction module, used to construct a three-dimensional anatomical structure model including thymus tissue, blood vessel network and nerve distribution through image segmentation processing; An operative field capture module, used to capture the visible light image and near-infrared spectrum data of the operative field in real time to generate real-time three-dimensional spatial data; A calibration module, configured to collect real-time displacement parameters of the thymus caused by the thoracic respiratory movement of a patient, and dynamically calibrate the real-time three-dimensional spatial data according to the real-time displacement parameters to maintain the spatial synchronization between the image data and the anatomical structure; A view adjustment module, configured to overlay the corrected three-dimensional anatomical structure model with the surgical field in real time to generate a stereoscopic navigation view, and dynamically adjust the display angle, depth, and transparency of the stereoscopic navigation view according to the risk score of the resection position.

10. An electronic device, characterized in that: The electronic device includes: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the complex chest trauma surgery-assisted stereoscopic imaging method according to any one of claims 1 to 8.

Images