A preoperative auxiliary planning MRI image laryngeal tumor three-dimensional reconstruction system

Abstract

The present application relates to the technical field of three-dimensional image data processing, and particularly relates to a preoperative auxiliary planning MRI image laryngeal tumor three-dimensional reconstruction system. For each voxel point in the initial three-dimensional model of the larynx, the system constructs a preoperative three-dimensional laryngeal image result through tissue image features. In the intraoperative stage, the expected tissue change characteristics are obtained according to the information of the instrument coordinate trajectory in the three-dimensional laryngeal image structure, and compared with the actual tissue change characteristics embodied by the power feedback data sequence of the electrocautery, so as to determine the abnormal type of the tissue under the coordinate trajectory, and update the labeling in the initial three-dimensional model. The present application can effectively identify the abnormal type of the detailed tissue feature area by comparing the expected tissue change characteristics with the actual tissue change characteristics, and then update and render the three-dimensional model in real time through the labeling method, so as to realize the effective response of the intraoperative characteristics.

Description

Technical Field

[0001] This invention relates to the field of three-dimensional image data processing technology, specifically to a three-dimensional reconstruction system for MRI images of laryngeal tumors for preoperative planning. Background Technology

[0002] Laryngeal cancer is a common malignant tumor of the head and neck, and surgical resection is its main treatment. The core goal of surgery is to completely remove the tumor while preserving, to the greatest extent possible, the vital functions of the larynx, such as voice and respiration. To overcome the limitations of two-dimensional image interpretation, a preoperative planning system based on three-dimensional reconstruction has been proposed. Existing technologies can convert two-dimensional image sequences into three-dimensional geometric models based on two-dimensional magnetic resonance imaging (MRI), visually demonstrating the spatial proximity of the tumor to surrounding organs. However, in existing technologies, because the three-dimensional models constructed from MRI images focus more on macroscopic tissue geometry, they cannot effectively distinguish tissues with similar morphology but vastly different histological characteristics. For example, they cannot differentiate postoperative fibrotic scars from residual microtumor foci on the model. Furthermore, existing three-dimensional models for preoperative auxiliary planning are static, and the surgical navigation information they provide is entirely based on preoperative data. They cannot respond to dynamic processes during surgery, and when the actual surgical situation deviates from the preoperative plan, the three-dimensional model cannot provide effective updates and responses. Summary of the Invention

[0003] To address the technical problems of existing preoperative auxiliary planning 3D laryngeal models failing to accurately identify detailed tissue feature regions and providing effective responses, the present invention aims to provide a preoperative auxiliary planning MRI image 3D reconstruction system for laryngeal tumors. The specific technical solution adopted is as follows:

[0004] This invention proposes a three-dimensional reconstruction system for laryngeal tumors based on MRI images for preoperative planning, the system comprising:

[0005] The preoperative 3D image atlas construction module is used to construct an initial 3D model of the region of interest for laryngeal surgery based on MRI images. For each voxel in the initial 3D model, the tissue image features of each voxel are obtained based on the spatial T2 signal intensity variation characteristics and ADC value variation characteristics. The differences in tissue image features between adjacent voxel points are used as edge weights to construct the preoperative 3D map structure of the larynx.

[0006] The intraoperative information acquisition module is used to acquire, in real time, the coordinate trajectory of the high-frequency electrosurgical tip in the three-dimensional graph structure and the electrosurgical power feedback data sequence based on the surgical navigation system; the voxel points corresponding to the coordinate trajectory in the three-dimensional graph structure constitute a voxel point sequence, and the edge weight sequence corresponding to the voxel point sequence is obtained; the change characteristics of the edge weight sequence are used as the expected tissue change characteristics before surgery; the change characteristics of the electrosurgical power feedback data sequence are used as the actual tissue change characteristics;

[0007] The 3D model-assisted update module is used to compare the expected tissue change characteristics with the actual tissue change characteristics, determine the anomaly type of the tissue under the coordinate trajectory based on the comparison results, and annotate it in the initial 3D model according to the anomaly type.

[0008] Furthermore, the tissue imaging features are two-dimensional features consisting of the T2 signal intensity change rate and the ADC value dispersion in the neighborhood space.

[0009] Furthermore, the rate of change of the T2 signal intensity is the spatial gradient modulus of the voxel point.

[0010] Furthermore, the ADC value dispersion is the standard deviation of the ADC value in the neighborhood space of the voxel point.

[0011] Furthermore, the edge weight is the Euclidean distance between adjacent voxel points representing the tissue image features.

[0012] Furthermore, the expected preoperative tissue change characteristics are the standard deviation of the normalized edge weight sequence.

[0013] Furthermore, the actual tissue change characteristics are the standard deviation of the normalized electrosurgical power feedback data sequence.

[0014] Furthermore, the system also includes an early warning module, used to use the difference between expected tissue change characteristics and actual tissue change characteristics as a deviation index; to obtain the clarity index of the endoscopic video in the surgical navigation system; to obtain the navigation reliability index of the surgical navigation system based on the deviation index and the clarity index; and to feed back an early warning signal based on the navigation reliability index.

[0015] Furthermore, the method for obtaining the navigation reliability index includes:

[0016] The navigation reliability index of the surgical navigation system is obtained by mapping the negative correlation of the deviation index and multiplying it by the clarity index.

[0017] Furthermore, determining the anomaly type of the tissue under the coordinate trajectory based on the comparison results includes:

[0018] If the actual tissue change characteristics are greater than the preset expected tissue change characteristics, and the difference between the expected tissue change characteristics and the actual tissue change characteristics is greater than the preset difference error threshold, then it indicates that the anomaly type of the throat region corresponding to the coordinate trajectory is an unexpected high feedback tissue.

[0019] If the actual tissue change characteristics are less than the preset expected tissue change characteristics, and the difference between the expected tissue change characteristics and the actual tissue change characteristics is greater than the preset difference error threshold, then it indicates that the anomaly type of the throat region corresponding to the coordinate trajectory is an unexpected low-feedback tissue.

[0020] The present invention has the following beneficial effects:

[0021] This invention, based on an initial 3D model, provides a quantitative benchmark derived from the image itself by constructing a graph structure to reflect the tissue characteristics of candidate tissue areas and to enable effective comparison and response during the surgical phase. Then, in the intraoperative information acquisition module, the expected preoperative tissue change characteristics are determined by combining real-time monitoring of the coordinate trajectory in the surgical navigation system with the preoperative candidate 3D graph structure. Furthermore, the actual tissue change characteristics are obtained based on the real-time feedback data sequence of electrosurgical power. Quantifying these two characteristics allows for effective comparison of expected and actual data. Based on the comparison results, the strength of the difference is analyzed, and abstract deviation values ​​are converted into actual anomaly types. These anomaly types are then rendered in real-time into the initial 3D model, achieving model annotation—that is, the model effectively responds to intraoperative electrosurgical feedback. This invention effectively identifies anomaly types in detailed tissue feature areas by comparing expected and actual tissue change characteristics, and then updates and renders the 3D model in real-time using annotation methods, achieving effective response to intraoperative features. Attached Figure Description

[0022] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a block diagram of a three-dimensional reconstruction system for laryngeal tumors based on MRI images, provided as an embodiment of the present invention. Detailed Implementation

[0024] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a three-dimensional reconstruction system for MRI images of laryngeal tumors for preoperative auxiliary planning based on the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0026] The following description, in conjunction with the accompanying drawings, details the specific scheme of a three-dimensional reconstruction system for MRI images of laryngeal tumors for preoperative planning provided by the present invention.

[0027] Please see Figure 1 The diagram illustrates a block diagram of a three-dimensional reconstruction system for MRI images of laryngeal tumors for preoperative planning, provided by an embodiment of the present invention. The system includes: a preoperative three-dimensional image atlas construction module 101, an intraoperative information acquisition module 102, and a three-dimensional model auxiliary update module 103.

[0028] In this embodiment of the invention, the basic three-dimensional modeling method still uses existing technology for acquisition. Specifically, in the preoperative three-dimensional image atlas construction module 101, an initial three-dimensional model of the region of interest for laryngeal surgery needs to be constructed first based on the MRI images. The initial three-dimensional model is the basic processing object in this embodiment of the invention, and subsequent modules can be regarded as further analysis and updates to it.

[0029] In this embodiment of the invention, the method for obtaining the initial three-dimensional model of the region of interest (ROI) for laryngeal surgery includes: acquiring three-dimensional data from T2-weighted imaging sequences and calculating the corresponding apparent diffusion coefficient (ADC) map from the diffusion-weighted imaging sequence data. Subsequently, three-dimensional rigid registration is performed on these two three-dimensional datasets. The purpose of this operation is to eliminate spatial positional deviations caused by minor patient movements during different sequence scans, ensuring that after registration, voxels with the same index coordinates in the two datasets correspond to tissue micro-elements at the same anatomical location. After registration, the operator delineates the three-dimensional ROI related to the current surgery on the T2-weighted images. This ROI should completely encompass the visible tumor, key laryngeal anatomical structures, and the potential surgical scope. It should be noted that the specific image registration methods are well-known techniques to those skilled in the art and will not be elaborated upon here.

[0030] T2 signal intensity is an important parameter in magnetic resonance imaging (MRI) for assessing tissue characteristics, and its intensity changes are closely related to tissue water content and lesion nature. ADC value (apparent diffusion coefficient) is a core parameter in MRI for quantifying the diffusion capacity of water molecules. Therefore, these two parameters can characterize the tissue features of each voxel in the initial three-dimensional model. The preoperative three-dimensional image atlas construction module 101 further considers that changes in these features can reflect the tissue characteristics in space. Therefore, it utilizes the spatial changes in T2 signal intensity and ADC value to obtain the tissue image features of each voxel.

[0031] The preoperative 3D image atlas construction module 101 further treats each voxel in the initial 3D model as a node in a graph. For each node, all spatially adjacent nodes are connected to form edges of the graph. The edge weight of each edge in the graph is the difference in tissue imaging features between adjacent voxels. This edge weight directly and quantitatively describes the magnitude of the difference in comprehensive imaging features that must be crossed when moving from one tissue micro-element to its adjacent tissue micro-element. A larger edge weight means that the instrument is crossing a boundary where tissue properties are drastically changed. This constructs the preoperative 3D laryngeal image structure, which includes not only the geometric features of the tissue region but also the tissue features at each location within the tissue region. As a static data structure, this atlas encapsulates the positions, tissue features, and tissue feature differences between all voxels within the surgical region of interest into a unified object, facilitating processing by subsequent modules in the system.

[0032] Preferably, in this embodiment of the invention, the tissue imaging features are two-dimensional features consisting of the T2 signal intensity change rate and the ADC value dispersion in the neighborhood space. The T2 signal intensity change rate can reflect the degree of spatial variation in the tissue water molecule content of the target voxel point; the ADC value dispersion is used to reflect the spatial non-uniformity of tissue cell density in the local microenvironment of that point. Tumor tissue usually has a different local ADC value dispersion than normal, structurally homogeneous tissue due to dense cell proliferation and disordered arrangement.

[0033] The rate of change of T2 signal intensity is the spatial gradient magnitude of the voxel point. In this embodiment of the invention, the central difference method is used to estimate the rate of change of T2 signal intensity of the target voxel point along the three spatial axes, and then the square root of the sum of squares is calculated to obtain the spatial gradient magnitude. The ADC value dispersion is the standard deviation of the ADC values ​​in the neighborhood space of the voxel point. The standard deviation is a technical feature well known to those skilled in the art, and the specific method for obtaining it will not be described in detail. In this embodiment of the invention, the neighborhood space is set as a 3×3×3 cubic region of the voxel point in space.

[0034] Preferably, in this embodiment of the invention, the edge weight is the Euclidean distance between adjacent voxel points representing tissue image features.

[0035] To ensure the initial 3D model generated during preoperative planning responds effectively during surgery, the real-time motion status of surgical instruments in the surgical navigation system must be analyzed. The intraoperative information acquisition module 102, by fusing and analyzing the real-time spatial position information of surgical instruments with the real-time power feedback signal of the energy device and comparing it with the preoperative 3D laryngeal image structure, can generate comparative feature indicators that provide real-time, quantitative assessment of the consistency between the current surgical procedure and the preoperative image prediction. Therefore, the intraoperative information acquisition module 102 can first acquire the coordinate trajectory of the high-frequency electrosurgical tip in the 3D image structure and the electrosurgical power feedback data sequence in real time according to the surgical navigation system.

[0036] The method for obtaining the coordinate trajectory includes: continuously acquiring the three-dimensional spatial coordinates of the high-frequency electrosurgical tip at a preset fixed frequency through a standard interface connection with the surgical navigation system. These three-dimensional spatial coordinates are obtained based on the surgical navigation system and therefore need to be registered with the coordinate system in the preoperative three-dimensional laryngeal image to obtain the coordinate trajectory. In this embodiment, the preset fixed frequency is set to 30 times per second. In this embodiment, a 1-second time window is used as the time window for acquiring the coordinate trajectory.

[0037] The method for obtaining the electrosurgical power feedback data sequence includes: directly connecting a power feedback acquisition device to the power output port of the high-frequency electrosurgical energy platform host, continuously acquiring the instantaneous output power value of the electrosurgical unit at a set acquisition frequency, and obtaining the electrosurgical power feedback data sequence within the analysis time window. In this embodiment of the invention, the acquisition frequency of the electrosurgical power feedback data sequence is set to 100 times per second, and the coordinate trajectory is acquired using a 1-second analysis time window.

[0038] To achieve type identification of the intraoperative tissue area and real-time response in a 3D model based on intraoperative information, this embodiment of the invention employs a method of comparing expected tissue change characteristics with actual tissue change characteristics. By comparing the expected and actual characteristics, the tissue characteristics of the working area during the real-time intraoperative stage can be determined. Therefore, the intraoperative information acquisition module 102 constructs a voxel sequence from the voxel points corresponding to the coordinate trajectory in the 3D graph structure and obtains the corresponding edge weight sequence, where each element in the edge weight sequence is the edge weight between two adjacent voxels in the voxel sequence. It should be noted that because the coordinate trajectory is continuous, the voxels in the voxel sequence are also continuous, and there is an edge weight between two adjacent voxels in the sequence. The edge weight sequence can directly reflect the expected results before surgery, specifically the difference in expected tissue characteristics traversed by the electrosurgical unit at each step during this small movement. This embodiment of the invention further quantifies the change characteristics of the edge weight sequence to obtain the expected tissue change characteristics before surgery. The preoperative expected tissue change characteristics objectively reflect the degree of fluctuation in tissue image characteristics predicted by the three-dimensional model constructed by preoperative auxiliary planning under a certain working path of the electrosurgical unit. The higher the preoperative expected tissue change characteristics, the more it indicates that the working path has passed through a region with drastic and uneven changes in tissue characteristics; conversely, it indicates that it has passed through a relatively uniform region.

[0039] To achieve an effective comparison with the expected tissue change characteristics before surgery, the intraoperative information acquisition module 102 further uses the change characteristics of the electrosurgical power feedback data sequence as the actual tissue change characteristics. The actual tissue change characteristics objectively reflect the degree of fluctuation in tissue impedance changes embodied in the energy feedback signal along the working path.

[0040] It should be noted that, considering the influence of dimensions during data comparison, this embodiment of the invention requires normalization before acquiring the variation characteristics of the edge weight sequence and the electrosurgical power feedback data sequence. This embodiment employs range standardization for normalization, determining the maximum and minimum values ​​in each dimension, and then performing normalization based on these values ​​to obtain the normalized edge weight sequence and the normalized electrosurgical power feedback data sequence. Normalization preserves the original data distribution while eliminating the influence of dimensions, limiting the data value range to between 0 and 1.

[0041] Based on the information from the aforementioned modules, the 3D model-assisted update module 103 can compare the expected tissue change characteristics with the actual tissue change characteristics. Based on the comparison results, it determines the anomaly type of the tissue under the coordinate trajectory, specifically whether the anomaly type belongs to a high-feedback or low-feedback tissue. The module then labels the anomaly type in the initial 3D model.

[0042] Preferably, in this embodiment of the invention, the system further includes an early warning module, which is used to use the difference between the expected tissue change characteristics and the actual tissue change characteristics as a deviation index. That is, the larger the deviation index, the greater the difference between the expected and the actual, indicating that the surgical navigation system's judgment of the actual candidate tissue is less reliable. Further, the clarity index of the endoscopic video in the surgical navigation system is obtained, and the clarity index is used to further characterize the reliability of the surgical navigation system; a navigation reliability index of the surgical navigation system is obtained based on the deviation index and the clarity index; and an early warning signal is fed back based on the navigation reliability index.

[0043] In this embodiment of the invention, in order to effectively compress the dynamic range of the data and make the deviation coefficient equally sensitive to both small and large original values, this embodiment of the invention selects the logarithmic transformation method to obtain the deviation index, which is expressed by the formula:

[0044] A = |log2(B+a)-log2(C+a)|; where A is the deviation exponent, B is the expected tissue change characteristic, C is the actual tissue change characteristic, and a is the hyperparameter. The hyperparameter is a very small positive constant to prevent logarithmic calculation errors when B and C are both zero, ensuring the numerical stability of the algorithm. In this embodiment, it is set to 0.1.

[0045] The deviation index is a dimensionless, non-negative scalar. Its value directly and robustly quantifies the difference between the expected tissue changes and the actual tissue changes. A deviation index close to zero indicates a high degree of agreement, meaning the surgical procedure matches the preoperative imaging expectations; while a value significantly greater than zero indicates a significant deviation, suggesting the possible encounter with unexpected tissue structures or lesions.

[0046] In this embodiment of the invention, the sharpness index can be obtained by summing the color saturation and gradient of each frame in the endoscopic video. Color saturation is used to detect red screen caused by bleeding, and the gradient sum is used to detect blur caused by delay or defocusing. Therefore, the sum of the normalized color saturation and normalized gradient of each frame is used as the initial sharpness index, and the average initial sharpness index of all frames in the endoscopic video is used as the sharpness index. It should be noted that the methods for obtaining color saturation and gradient sum are well-known to those skilled in the art and will not be elaborated further. Similarly, range standardization can be used for normalization, which will also not be elaborated further.

[0047] Furthermore, in this embodiment of the invention, the deviation index is negatively correlated and then multiplied by the clarity index to obtain the navigation reliability index of the surgical navigation system. That is, the smaller the deviation index and the higher the clarity index, the more likely the surgical procedure under the surgical navigation system is as expected and the procedure is relatively safe. This embodiment of the invention can divide the warning signals into three levels based on the magnitude of the navigation reliability index: safe, alert, and dangerous. Different levels are indicated in the system using different sounds (e.g., sounds of different frequencies and rhythms) and different colored signal lights (e.g., green, yellow, and red). The navigation reliability threshold ranges for the three levels of warning signals can be specifically set according to the actual implementation scenario, which will not be elaborated further in this embodiment of the invention.

[0048] It should be noted that the negative correlation mapping and normalization method in the embodiments of the present invention adopts the exponential function mapping method, which takes the negative number of the deviation exponent as the power of the exponential function with the natural constant as the base, and the output result of the exponential function is the result after negative correlation mapping and normalization.

[0049] Preferably, in this embodiment of the invention, determining the abnormality type of the tissue under the coordinate trajectory based on the comparison results includes:

[0050] If the actual tissue change characteristics are greater than the preset expected tissue change characteristics, and the difference between the expected and actual tissue change characteristics is greater than the preset difference error threshold, it indicates that the instrument path appears as a region with relatively uniform tissue characteristics on the preoperative image, but the power feedback of the high-frequency electrosurgical unit fluctuates drastically. This usually corresponds to cutting into tiny structures with significantly different electrical impedances that are not visible or underestimated on the image, such as small nutrient vessels, nerve bundles, or dense fibrotic scar tissue. Therefore, the abnormal type of the laryngeal region corresponding to the coordinate trajectory is unexpected high-feedback tissue. In this embodiment of the invention, the coordinate trajectory is rendered and marked with a specific highlight color (e.g., blue) in the initial three-dimensional model on the surgical navigation interface. At the same time, the interface will pop up a text prompt "Encountered unexpected high-feedback tissue". Updating the rendering of the three-dimensional model can help the doctor determine the surgical direction.

[0051] If the actual tissue change characteristics are less than the preset expected tissue change characteristics, and the difference between the expected and actual tissue change characteristics is greater than a preset difference error threshold, it indicates that the instrument path is crossing a boundary identified as having drastic tissue characteristic changes on preoperative imaging (e.g., the junction of a tumor and normal muscle), but the power feedback of the high-frequency electrosurgical unit is abnormally stable. This usually corresponds to entering an area with highly homogeneous histological characteristics, such as large areas of necrotic tissue, cystic areas, or liquefaction areas. These areas lack effective impedance changes, and the abnormal type of the laryngeal region corresponding to the coordinate trajectory is unexpected low-feedback tissue. Similarly, a specific highlight color (e.g., purple) can be selected for rendering and marking, and a text prompt will appear: "Tissue feedback is lower than expected, possibly entering a necrotic / cystic area."

[0052] It should be noted that after obtaining the absolute value of the difference between the expected tissue change characteristics and the actual tissue change characteristics, and normalizing the absolute value of the difference, the difference error threshold is set to 0.6. That is, when the absolute value of the difference after normalization is greater than 0.6, it is considered that one feature is much larger than the other feature.

[0053] In summary, this invention, through real-time response to intraoperative information in a 3D model and real-time, categorized, and dynamic color annotation, maps the quantified one-dimensional features back into the 3D model, making them part of the 3D reconstruction model. This invention dynamically supplements the original static model, allowing surgeons to intuitively see the location of abnormal areas and determine the type of abnormality, thus making more accurate judgments and operational adjustments. For example, choosing to avoid blue-marked trajectories to protect blood vessels, or confirming whether purple-marked areas require more thorough cleaning. This invention not only provides risk warnings but also feeds back the energy feedback information acquired in real-time during surgery to the preoperative planning model in an intuitive and interpretable way, achieving a closed loop between preoperative auxiliary planning and intraoperative reality. This greatly enhances the practical value and decision support capabilities of the 3D reconstruction system in complex cases.

[0054] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0055] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A preoperative auxiliary planning MRI image laryngeal tumor three-dimensional reconstruction system, characterized in that, The system comprises: A preoperative three-dimensional image atlas construction module is configured to construct an initial three-dimensional model of a laryngeal surgery region of interest according to MRI images; for each voxel point in the initial three-dimensional model, tissue image features of each voxel point are obtained according to T2 signal intensity variation characteristics and ADC value variation characteristics in space; and a difference in tissue image features between adjacent voxel points is taken as an edge weight value to construct a preoperative laryngeal three-dimensional graph structure; An intraoperative information acquisition module is configured to acquire a coordinate trajectory of a high-frequency electrotome tip in the three-dimensional graph structure and an electrotome power feedback data sequence in real time according to a surgical navigation system; voxel points corresponding to the coordinate trajectory in the three-dimensional graph structure form a voxel point sequence, and an edge weight value sequence corresponding to the voxel point sequence is obtained; variation characteristics of the edge weight value sequence are taken as preoperative expected tissue variation characteristics; and variation characteristics of the electrotome power feedback data sequence are taken as actual tissue variation characteristics; A three-dimensional model assisted updating module is configured to compare the expected tissue variation characteristics and the actual tissue variation characteristics, determine an abnormal type of tissue under the coordinate trajectory according to a comparison result, and label the initial three-dimensional model according to the abnormal type. The tissue image features are two-dimensional features composed of a T2 signal intensity variation rate and an ADC value dispersion degree in a neighborhood space.

2. The preoperative assisted planning MRI image laryngeal tumor three-dimensional reconstruction system according to claim 1, characterized in that, The T2 signal intensity variation rate is a spatial gradient module length of a voxel point.

3. The preoperative assisted planning MRI image laryngeal tumor three-dimensional reconstruction system according to claim 1, characterized in that, The ADC value dispersion degree is a standard deviation of ADC values in a voxel point neighborhood space.

4. The preoperative planning-assisted MRI image laryngeal tumor three-dimensional reconstruction system according to claim 1, characterized in that, The edge weight value is an Euclidean distance of tissue image features between adjacent voxel points.

5. The preoperative planning-assisted MRI image laryngeal tumor three-dimensional reconstruction system according to claim 1, characterized in that, The preoperative expected tissue variation characteristics are a standard deviation of the edge weight value sequence after normalization processing.

6. The preoperative planning-assisted MRI image laryngeal tumor three-dimensional reconstruction system according to claim 1, characterized in that, The actual tissue variation characteristics are a standard deviation of the electrotome power feedback data sequence after normalization.

7. The preoperative planning aided MRI image laryngeal tumor three-dimensional reconstruction system according to claim 1, characterized in that, The system further comprises a warning module configured to take a difference between the expected tissue variation characteristics and the actual tissue variation characteristics as a deviation index, acquire a definition index of an endoscope video in the surgical navigation system, obtain a navigation reliability index of the surgical navigation system according to the deviation index and the definition index, and feed back a warning signal according to the navigation reliability index.

8. The preoperative assisted planning MRI image laryngeal tumor three-dimensional reconstruction system according to claim 7, characterized in that, The method for obtaining the navigation reliability index comprises: Multiplying the deviation index after negative correlation mapping and the definition index to obtain the navigation reliability index of the surgical navigation system.

9. The preoperative planning-assisted MRI image laryngeal tumor three-dimensional reconstruction system according to claim 1, characterized in that, The method for determining the abnormal type of tissue under the coordinate trajectory according to the comparison result comprises: If the actual tissue variation characteristics are greater than a preset expected tissue variation characteristics, and a difference between the expected tissue variation characteristics and the actual tissue variation characteristics is greater than a preset difference error threshold, it is indicated that an abnormal type of a laryngeal region corresponding to the coordinate trajectory is an unexpected high feedback tissue; If the actual tissue variation characteristics are less than a preset expected tissue variation characteristics, and a difference between the expected tissue variation characteristics and the actual tissue variation characteristics is greater than a preset difference error threshold, it is indicated that an abnormal type of a laryngeal region corresponding to the coordinate trajectory is an unexpected low feedback tissue.

Images