VR-based CT room operation virtual training method and system

Abstract

The invention relates to the technical field of data analysis, in particular to a VR-based CT room operation virtual training method and system. The method comprises the following steps: acquiring an equipment model and a patient model in current CT training operation; analyzing a relative position relationship between the equipment model and the patient model at the initial position to obtain an initial abnormal value; analyzing posture changes of a plurality of limb parts of the patient model before and after the limb adjustment operation to obtain a plurality of posture anomaly indexes; according to the initial abnormal value, analyzing the change of an overlapping region between a plurality of limb parts of the patient model and the equipment model in the examination process of the current CT training operation, and obtaining a plurality of position abnormal indexes; and obtaining an operation evaluation result of the current CT training operation according to the plurality of attitude anomaly indexes and the plurality of position anomaly indexes. According to the invention, the evaluation accuracy of the abnormal operation condition of the CT training operation can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a VR-based virtual training method and system for CT room operation. Background Art

[0002] Virtual reality (VR)-based virtual training for CT room operations offers significant advantages. First, it simulates real-world surgical scenarios in a virtual environment, providing a safe and risk-free training platform and avoiding potential risks associated with actual operations. Second, the immersive 3D interactive experience accelerates skill acquisition, shortens the learning curve, and rapidly improves proficiency. Furthermore, real-time feedback and personalized guidance based on operational results (such as AI-assisted assessments), combined with repeatable training and remote collaboration capabilities, can significantly reduce training costs and optimize resource allocation.

[0003] In the existing technology, the degree of operational errors made by trainees during CT training operations is often evaluated by analyzing the depth to which a digital human (representing a patient) penetrates the side wall of the CT equipment. However, this evaluation method considers too few dimensions and is unable to effectively identify operational errors made by trainees during CT training operations, resulting in poor training results in actual CT training operations.

[0004] That is, the existing technology has poor accuracy in evaluating operational abnormalities of VR-based CT training operations. Summary of the Invention

[0005] In order to solve the technical problem of poor accuracy in evaluating operational abnormalities in VR-based CT training operations in the prior art, the present invention aims to provide a VR-based virtual training method and system for CT room operations. The technical solutions adopted are as follows: In a first aspect, an embodiment of the present invention provides a VR-based virtual training method for CT room operations, the method comprising: Acquire a device model and a patient model in a current CT training operation, wherein the device model is used to represent a device for performing a CT examination, and the patient model is used to represent a patient for performing a CT examination; Analyze the relative position relationship between the device model and the patient model at the initial position to obtain an initial abnormal value; analyzing posture changes of multiple limb parts of the patient model before and after a limb adjustment operation to obtain multiple posture abnormality indexes, wherein the limb adjustment operation is used to reduce the depth of the limb parts of the patient model penetrating into the device model; analyzing, based on the initial abnormal values, changes in overlapping areas between multiple limb parts of the patient model and the device model during an examination process of a current CT training operation to obtain multiple position abnormality indices; An operation evaluation result of the current CT training operation is obtained according to the multiple posture abnormality indices and the multiple position abnormality indices.

[0006] In one embodiment, analyzing the relative positional relationship between the device model and the patient model at the initial position to obtain the initial abnormal value includes: Analyzing a deviation between a placement midline of the device model and a model midline of the patient model in an initial position to obtain a deviation angle, wherein the placement midline is a midline of an examination bed of the device model, and the examination bed is used to place the patient model; Calculating the shortest distance between the torso of the patient model in the initial position and the edge of the examination bed to obtain a minimum distance value; The initial abnormal value is obtained according to the deviation angle and the minimum distance value.

[0007] In one embodiment, obtaining the initial abnormal value according to the deviation angle and the minimum distance value includes: Calculating the ratio of the deviation angle to the minimum distance value to obtain a position deviation value; Calculating a ratio of the projected area to the reference area to obtain a space occupation ratio, wherein the projected area is the area of ​​the projection of the patient model within the reference region when the patient model lies flat on the examination bed, the reference area is the total area of ​​the reference region, and the reference region is the plane area corresponding to the examination bed; The product of the position deviation value and the occupancy ratio is calculated to obtain the initial abnormal value.

[0008] In one embodiment, the analyzing of posture changes of multiple limb parts of the patient model before and after the limb adjustment operation to obtain multiple posture abnormality indexes includes: Analyzing a position change of a target part before and after the limb adjustment operation to obtain position change information of the target part, wherein the target part is any one of the multiple limb parts of the patient model; analyzing a change in the depth of the target part penetrating into the device model before and after the limb adjustment operation to obtain depth change information of the target part; A posture abnormality index of the target part is obtained according to the position change information and the depth change information of the target part.

[0009] In one embodiment, analyzing the position change of the target part before and after the limb adjustment operation to obtain the position change information of the target part includes: Analyzing position changes of a plurality of target data points included in the target part before and after the limb adjustment operation to obtain movement distances of the plurality of points of the target part, wherein the position change information of the target part includes the movement distances of the plurality of points of the target part, and the target data point is a data point supporting the limb adjustment operation among the plurality of data points constituting the target part; The analyzing the change in the depth of the target part penetrating into the device model before and after the limb adjustment operation to obtain the depth change information of the target part includes: Analyzing changes in the depths of the multiple target data points penetrating into the device model before and after the limb adjustment operation to obtain multiple depth differences of the target parts, wherein the depth change information of the target parts includes the multiple depth differences of the target parts; Obtaining a posture abnormality index of the target part according to the position change information and the depth change information of the target part includes: Among the multiple depth differences of the target part, determining the largest depth difference as the limit depth difference of the target part; Calculating the sum of the moving distances of multiple points of the target part to obtain a total moving distance of the target part; The limit depth difference and the total moving distance of the target part are calculated to obtain the posture abnormality index of the target part.

[0010] In one embodiment, the initial abnormal values ​​are analyzed based on the overlapped areas of the multiple limb parts of the patient model and the device model during the examination process of the current CT training operation to obtain multiple position abnormality indices, including: Analyzing a change in an area of ​​an overlapping region between a target part and a device model during an examination process of a current CT training operation to obtain an area abnormality value of the target part, wherein the target part is any one of multiple limb parts of the patient model; Analyzing a depth change of an overlapping area between the target part and the device model during an inspection process of a current CT training operation to obtain a depth abnormality value of the target part; A position anomaly index of the target part is obtained according to the initial anomaly value, the area anomaly value of the target part, and the depth anomaly value of the target part.

[0011] In one embodiment, analyzing the change in the area of ​​the overlapping region between the target site and the device model during the inspection process of the current CT training operation to obtain the area abnormality value of the target site includes: Acquire multiple overlapping areas corresponding to the target part, wherein the multiple overlapping areas correspond one-to-one to multiple inspection moments within an inspection time period, the overlapping areas being the areas of overlapping regions between the target part and the device model at the corresponding inspection moments, and the inspection time period being the time period corresponding to the inspection process of the current CT training operation; Analyzing the area difference between two adjacent overlapping areas of the target part within the inspection time period to obtain a plurality of area difference values ​​corresponding to the target part, wherein the area difference value is the difference between the overlapping area corresponding to the target part at the corresponding inspection time and the overlapping area corresponding to the target part at the previous inspection time; Among the multiple area difference values ​​corresponding to the target part, counting the number of the area difference values ​​that are greater than 0 to obtain an area abnormality value of the target part; The analyzing the depth change of the overlapping area between the target part and the device model during the inspection process of the current CT training operation to obtain the depth abnormal value of the target part includes: Acquire multiple overlapping depths corresponding to the target part, wherein the multiple overlapping depths correspond one-to-one to multiple inspection moments within an inspection time period, the overlapping depth being the depth at which the overlapping region between the target part and the device model penetrates into the device model at the corresponding inspection moment, and the inspection time period being the time period corresponding to the inspection process of the current CT training operation; Analyzing the depth difference between two adjacent overlapping depths of the target part within the inspection time period to obtain a plurality of depth difference values ​​corresponding to the target part, wherein the depth difference value is the difference between the depth area corresponding to the target part at the corresponding inspection time and the depth area corresponding to the target part at the previous inspection time; Among the multiple depth differences corresponding to the target part, the largest depth difference is determined as the depth abnormal value of the target part.

[0012] In one embodiment, obtaining an operation evaluation result of the current CT training operation according to the multiple posture abnormality indices and the multiple position abnormality indices includes: Acquire a plurality of posture tolerances, wherein the plurality of posture tolerances correspond one-to-one to a plurality of limb parts of the patient model, and the posture tolerances are used to represent a maximum adjustment degree of the corresponding limb part during a limb adjustment operation; Obtaining a plurality of limb abnormality coefficients according to the plurality of posture tolerances, wherein the sum of the limb abnormality coefficients and the corresponding posture tolerances is 1; Obtaining a plurality of limb abnormality values ​​according to a plurality of limb abnormality coefficients, the plurality of posture abnormality indices, and the plurality of position abnormality indices; calculating a sum of the plurality of limb abnormality values ​​to obtain an operation abnormality value; An operation evaluation result of the current CT training operation is generated according to the operation abnormal value.

[0013] In one embodiment, obtaining a plurality of posture tolerances includes: Counting the total number of multiple target data points included in a target part to obtain the number of movable points of the target part, wherein the target part is any one of multiple limb parts of the patient model, and the target data point is a data point supporting limb adjustment operations among the multiple data points constituting the target part; calculating a ratio of the number of movable points of the target part to the volume of the target part to obtain a first value of the target part; The product of the first value of the target part and the second value of the target part is calculated to obtain the posture tolerance of the target part, wherein the second value of the target part is: the maximum point movement limit distance among the multiple point movement limit distances corresponding to the multiple target data points.

[0014] In a second aspect, another embodiment of the present invention provides a VR-based CT room operation virtual training system, the system comprising: an acquisition module, configured to acquire a device model and a patient model in a current CT training operation, wherein the device model is used to represent a device for performing a CT examination, and the patient model is used to represent a patient for performing a CT examination; An initial analysis module is used to analyze the relative position relationship between the device model and the patient model at the initial position to obtain an initial abnormal value; a posture analysis module, configured to analyze posture changes of multiple limb parts of the patient model before and after a limb adjustment operation to obtain multiple posture abnormality indices, wherein the limb adjustment operation is configured to reduce the depth of penetration of the limb parts of the patient model into the device model; a position analysis module, configured to analyze, based on the initial abnormal values, changes in overlapping areas between multiple limb parts of the patient model and the device model during the examination process of the current CT training operation, to obtain multiple position abnormality indices; The operation evaluation module is used to obtain an operation evaluation result of the current CT training operation according to the multiple posture abnormality indices and the multiple position abnormality indices.

[0015] In a third aspect, another embodiment of the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method described in the first aspect when executed by the processor.

[0016] In a fourth aspect, another embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0017] The present invention has the following beneficial effects: The present invention obtains the device model and patient model in the current CT training operation, and analyzes the relative positional relationship between the device model and the patient model in the initial position to evaluate the positional deviation of the patient model in the placement stage, and then analyzes the posture changes of multiple limb parts of the patient model before and after the limb adjustment operation to adapt to the situation where the patient's limbs can be adjusted in a certain range, effectively distinguishes the severity of the patient model's deep penetration into the device model, and completes an accurate evaluation of the degree of posture abnormality of the patient model in the limb adjustment stage; further analyzes the changes in the overlapping areas between multiple limb parts of the patient model and the device model during the inspection process of the current CT training operation to determine the degree of conflict between each limb part of the patient model and the device model when the operation is abnormal, and then comprehensively and accurately evaluates the severity of the positional conflict that may occur between the patient model and the device model during the inspection, and performs an operational evaluation of the current CT training operation accordingly, which can improve the accuracy of the evaluation of operational abnormalities in CT training operations based on VR. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0019] Figure 1 A schematic flow chart of a VR-based virtual training method for CT room operations provided by one embodiment of the present invention; Figure 2 A schematic diagram of the structure of a VR-based CT room operation virtual training system provided by one embodiment of the present invention; Figure 3 The present invention provides a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] To further illustrate the technical means and effectiveness of the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a VR-based virtual training method and system for CT room operations proposed by the present invention. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0021] Unless defined otherwise, 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 belongs.

[0022] The following describes in detail a VR-based CT room operation virtual training method and system provided by the present invention with reference to the accompanying drawings.

[0023] This invention proposes a VR-based virtual training method for CT room operation. Figure 1 , which shows a flow chart of a VR-based CT room operation virtual training method provided by one embodiment of the present invention, the method comprising the following steps: Step S1: Acquire the device model and patient model in the current CT training operation.

[0024] The device model is used to represent the device for performing CT examination, and the patient model is used to represent the patient for performing CT examination.

[0025] The target user performs multiple CT training operations in a three-dimensional virtual scene constructed based on VR technology (such as a virtual CT examination room). The current CT training operation is the CT training operation corresponding to the current moment among the multiple CT training operations. The target user is any user who performs CT training operations (such as a medical student).

[0026] The device model is specifically a virtual model of a CT examination instrument fixedly placed in the aforementioned three-dimensional virtual scene. The device model includes an examination bed for placing a patient model and an annular inspection device for performing CT examinations (for emitting X-rays and receiving X-rays that pass through the patient's body and converting them into electrical signals). The examination bed can move along the axis of the annular inspection device. After the target user places the patient model on the examination bed and adjusts its position (the patient model is in its initial position), the examination bed moves along the axis of the annular inspection device and penetrates the inner area enclosed by the annular inspection device until it reaches a predetermined position. The annular inspection device is then activated. After a certain period of time (e.g., 2 minutes) of X-ray transmission and reception processing, the annular inspection device is deactivated, and the examination bed moves back along the axis of the annular inspection device to its initial position, thus completing a CT training operation. During each CT training operation, the target user needs to place the patient model on the examination bed and adjust the patient model's position (e.g., from lying on its side to lying flat on its back) so that the patient model can successfully complete the aforementioned CT examination process and minimize interference with the device model (e.g., to avoid partial overlap between the patient model and the device model).

[0027] It should be understood that when the examination bed is in the predetermined position, the part to be examined (such as the chest part) of the patient model on the examination bed is located in the inner area enclosed by the annular examination piece.

[0028] Step S2: Analyze the relative position relationship between the device model and the patient model at the initial position to obtain an initial abnormal value.

[0029] In this step, the relative positional relationship between the device model and the patient model in the initial position is analyzed to determine the initial state of the patient model after being placed on the examination bed by the target user. The rationality (or abnormality) of the interaction between the patient model and the device model based on the initial state (referring to the process of performing the above-mentioned CT examination) is then analyzed, thereby completing the static position analysis of the patient model and providing a reference for the subsequent dynamic position analysis of the patient model (referring to the analysis of changes in the overlapping areas between multiple limb parts of the patient model and the device model during the examination process of the current CT training operation in subsequent steps).

[0030] Furthermore, the analyzing the relative positional relationship between the device model and the patient model at the initial position to obtain the initial abnormal value includes: Analyzing a deviation between a placement midline of the device model and a model midline of the patient model in an initial position to obtain a deviation angle, wherein the placement midline is a midline of an examination bed of the device model, and the examination bed is used to place the patient model; Calculating the shortest distance between the torso of the patient model in the initial position and the edge of the examination bed to obtain a minimum distance value; The initial abnormal value is obtained according to the deviation angle and the minimum distance value.

[0031] In the present invention, the model midline of the patient model in the initial position may be understood as the midline of the spine of the patient model in the initial position.

[0032] Based on the above settings, the relative position relationship between the device model and the patient model in the initial position is comprehensively considered from the perspectives of angle and distance to obtain a more accurate initial abnormality value.

[0033] Among them, the larger the deviation angle, the more serious the degree to which the model centerline of the patient model in the initial position deviates from the placement centerline of the device model, the more likely the placement position of the patient model is abnormal, and the higher the initial abnormal value; vice versa.

[0034] Similarly, the smaller the minimum distance value is, the closer the torso of the patient model in the initial position is to the edge of the examination bed, the greater the probability that the limbs of the patient model in the initial position will cross the edge of the examination bed and interfere with the annular inspection piece, the more likely the placement of the patient model is abnormal, and the higher the initial abnormality value; vice versa.

[0035] Furthermore, obtaining the initial abnormal value according to the deviation angle and the minimum distance value includes: Calculating the ratio of the deviation angle to the minimum distance value to obtain a position deviation value; Calculating a ratio of the projected area to the reference area to obtain a space occupation ratio, wherein the projected area is the area of ​​the projection of the patient model within the reference region when the patient model lies flat on the examination bed, the reference area is the total area of ​​the reference region, and the reference region is the plane area corresponding to the examination bed; The product of the position deviation value and the occupancy ratio is calculated to obtain the initial abnormal value.

[0036] In the above setup, the space occupancy ratio is calculated to quantify the corresponding space occupancy of the patient model after it is placed on the examination bed. Combined with the volume of the patient model and the angular deviation and minimum distance obtained from the previous analysis, the relative positional relationship between the device model and the patient model in the initial position is accurately evaluated, making the calculated initial abnormal value more accurate and reliable.

[0037] Among them, the higher the occupancy ratio, the larger the volume of the patient model appears, the larger the space it occupies when lying flat on the examination bed, the smaller the range of adjustment when the examination bed moves subsequently, the more likely the placement position is abnormal, and the higher the initial abnormal value.

[0038] For example, if the current CT training operation is set as the jth CT training operation among multiple CT training operations performed by the target user, the initial abnormal value of the jth CT training operation is It can be expressed as: in, represents the occupancy ratio corresponding to the j-th CT training operation, represents the deviation angle corresponding to the j-th CT training operation, represents the minimum distance value corresponding to the j-th CT training operation.

[0039] Step S3: Analyze the posture changes of multiple limb parts of the patient model before and after the limb adjustment operation to obtain multiple posture abnormality indexes.

[0040] The limb adjustment operation is used to reduce the depth of the limb part of the patient model penetrating into the device model.

[0041] The limbs of the patient model have a certain ability to adjust their positions to simulate the situation where the limbs of the human body (such as limbs) can be flexibly adjusted within a certain range. After the target user places the patient model on the examination bed, the patient model moves to a predetermined position along with the examination bed. The target user can perform limb adjustment operations to retract the limbs of the patient model near the torso of the patient model when the limbs of the patient model collide with the device model, so as to reduce the degree of interference (i.e., collision) between the limbs of the patient model and the annular inspection part of the device model (i.e., reduce the depth and area of ​​penetration of the limbs of the patient model into the device model).

[0042] In the above setting, by analyzing the posture changes of multiple limb parts of the patient model before and after the limb adjustment operation, the severity of the patient model's deep penetration into the device model is effectively distinguished, and the degree of abnormal posture of the patient model in the limb adjustment stage is accurately assessed, making the final output operation evaluation results more accurate.

[0043] Furthermore, the analysis of posture changes of multiple limb parts of the patient model before and after the limb adjustment operation to obtain multiple posture abnormality indexes includes: Analyzing a position change of a target part before and after the limb adjustment operation to obtain position change information of the target part, wherein the target part is any one of the multiple limb parts of the patient model; analyzing a change in the depth of the target part penetrating into the device model before and after the limb adjustment operation to obtain depth change information of the target part; A posture abnormality index of the target part is obtained according to the position change information and the depth change information of the target part.

[0044] In the above setting, the position changes and penetration depth changes of each limb part before and after the limb adjustment operation are analyzed to accurately quantify the degree of posture abnormality of the patient model during the limb adjustment stage.

[0045] Furthermore, analyzing the position change of the target part before and after the limb adjustment operation to obtain the position change information of the target part includes: Analyze the position changes of multiple target data points included in the target part before and after the limb adjustment operation to obtain the movement distances of multiple points of the target part, wherein the position change information of the target part includes the movement distances of multiple points of the target part, and the target data point is a data point that supports the limb adjustment operation among the multiple data points constituting the target part.

[0046] In the above process, by analyzing the position changes of multiple target data points included in the target part before and after the limb adjustment operation, the position changes of the target part before and after the limb adjustment operation are comprehensively evaluated from the fine-grained dimension of the data points, so that the position change information of the target part obtained is more accurate.

[0047] Among them, the multiple point movement distances of the target part correspond one-to-one to the multiple target data points included in the target part, and the point movement distance is the distance between the point position of the corresponding target data point before the limb adjustment operation and the point position after the limb adjustment operation. The point position of the target data point can be understood as the position of the projection point of the target data point projected on the plane corresponding to the reference area.

[0048] The data points that support limb adjustment operations among the multiple data points of the target part can be understood as: "Adaptive Movable Points" among the multiple data points of the target part, whose positions can be automatically adjusted according to real-time input (such as user operations, physical engine calculations, and environmental data).

[0049] The analyzing the change in the depth of the target part penetrating into the device model before and after the limb adjustment operation to obtain the depth change information of the target part includes: The depth changes of the multiple target data points penetrating into the device model before and after the limb adjustment operation are analyzed to obtain multiple depth differences of the target parts, wherein the depth change information of the target parts includes the multiple depth differences of the target parts.

[0050] In the above process, by analyzing the depth changes of multiple target data points included in the target part before and after the limb adjustment operation, the depth changes of the target part before and after the limb adjustment operation are comprehensively evaluated from the fine-grained dimension of the data points, so that the depth change information of the target part obtained is more accurate.

[0051] The depth differences of the target part correspond to the target data points included in the target part, and the depth differences are the depths of the corresponding target data points penetrating into the device model after the limb adjustment operation. The depth of penetration into the device model The depth of the target data point penetrating into the device model can be understood as the closest distance between the projection point of the target data point in the plane corresponding to the reference area and the device boundary area. The device boundary area can be understood as the projection area of ​​the inner wall of the annular inspection part in the plane corresponding to the reference area.

[0052] Obtaining a posture abnormality index of the target part according to the position change information and the depth change information of the target part includes: Among the multiple depth differences of the target part, determining the largest depth difference as the limit depth difference of the target part; Calculating the sum of the moving distances of multiple points of the target part to obtain a total moving distance of the target part; The limit depth difference and the total moving distance of the target part are calculated to obtain the posture abnormality index of the target part.

[0053] For example, if the current CT training operation is set as the jth CT training operation among multiple CT training operations performed by the target user, the posture abnormality index of the kth limb part among the multiple limb parts of the patient model is It can be expressed as: in, is the limit depth difference of the kth limb part, is the point movement distance of the p-th target data point in the k-th limb part, is the total number of target data points included in the k-th limb part, It can be understood as the total moving distance of the kth limb part.

[0054] In the application, after determining the posture abnormality index of each limb part of the patient model based on the above process, the maximum and minimum normalization method can be used to normalize the multiple posture abnormality indices (the normalized value range is (0,1)) to eliminate numerical differences, facilitate subsequent use, and further improve the accuracy of the final operation evaluation results.

[0055] Step S4: Analyze the changes in the overlapping areas between the multiple limb parts of the patient model and the device model during the examination process of the current CT training operation according to the initial abnormal values, and obtain multiple position abnormality indices.

[0056] It should be emphasized that the analysis of the changes in the overlapping areas between the multiple limb parts of the patient model and the device model during the examination process of the current CT training operation is carried out after the limb adjustment operations of the multiple limb parts of the patient model are completed.

[0057] Among them, the examination process can be understood as the process from the moment when the limb adjustment operations of multiple limb parts of the patient model are completed to the moment when the examination bed moves to the predetermined position (or, from the moment when the limb adjustment operations of multiple limb parts of the patient model are completed to the predetermined time period, which can be 2 minutes).

[0058] Only static position analysis of the patient model cannot effectively evaluate the severity of the collision between the patient model and the equipment model under the current placement operation. Based on the above settings, by analyzing the dynamic position of the patient model during the examination process, the severity of the collision between the patient model and the equipment model under the current placement operation can be effectively evaluated, so as to output more accurate operation evaluation results.

[0059] Furthermore, the initial abnormal values ​​are used to analyze the changes in the overlapping areas between the multiple limb parts of the patient model and the device model during the examination process of the current CT training operation to obtain multiple position abnormality indices, including: Analyzing a change in an area of ​​an overlapping region between a target part and a device model during an examination process of a current CT training operation to obtain an area abnormality value of the target part, wherein the target part is any one of multiple limb parts of the patient model; Analyzing a depth change of an overlapping area between the target part and the device model during an inspection process of a current CT training operation to obtain a depth abnormality value of the target part; A position anomaly index of the target part is obtained according to the initial anomaly value, the area anomaly value of the target part, and the depth anomaly value of the target part.

[0060] During the inspection process, the factors that affect the degree of collision between the patient model and the device model (that is, the degree of model overlap) mainly include: the initial position of the patient model before entering the enclosed area of ​​the annular inspection piece of the device model (represented by the initial outlier), the area of ​​the overlapping area between the patient model and the annular inspection piece (represented by the area outlier), and the depth of the overlapping area between the patient model and the annular inspection piece within the annular inspection piece (represented by the depth outlier).

[0061] Among them, the more drastic the area change, the larger the corresponding area anomaly value, the more severe the collision between the patient model and the device model, and the larger the position anomaly index finally calculated, and vice versa.

[0062] Similarly, the more drastic the depth change, the larger the corresponding depth anomaly value, the more severe the collision between the patient model and the device model, and the larger the final calculated position anomaly index, and vice versa.

[0063] The larger the initial outlier value, the more unreasonable the initial position of the patient model, the more severe the collision between the patient model and the device model, and the larger the final calculated position anomaly index, and vice versa.

[0064] Based on this, in the above process, the position abnormality index of the corresponding limb part is determined by comprehensively considering the three main factors that affect the collision degree, which can more accurately evaluate the collision degree between the corresponding limb part and the device model.

[0065] It should be noted that the larger the position abnormality index of a certain limb part, the more unreasonable the placement of the patient model in that limb part in the current CT training operation. That is, while outputting the overall evaluation results of the current CT training operation, the rationality of the placement of each limb part can be evaluated based on the position abnormality index of each limb part and improvement suggestions can be given to help the target user identify operation problems and correct them more quickly.

[0066] For example, if the current CT training operation is set as the jth CT training operation among multiple CT training operations performed by the target user, the position abnormality index of the kth limb part among the multiple limb parts of the patient model is It can be expressed as: in, represents the initial outlier value of the j-th CT training operation, represents the area abnormality of the k-th limb part, represents the depth outlier of the k-th limb part.

[0067] Specifically, analyzing the area change of the overlapping region between the target part and the device model during the inspection process of the current CT training operation to obtain the area abnormality value of the target part includes: Acquire multiple overlapping areas corresponding to the target part, wherein the multiple overlapping areas correspond one-to-one to multiple inspection moments within an inspection time period, the overlapping areas being the areas of overlapping regions between the target part and the device model at the corresponding inspection moments, and the inspection time period being the time period corresponding to the inspection process of the current CT training operation; Analyzing the area difference between two adjacent overlapping areas of the target part within the inspection time period to obtain a plurality of area difference values ​​corresponding to the target part, wherein the area difference value is the difference between the overlapping area corresponding to the target part at the corresponding inspection time and the overlapping area corresponding to the target part at the previous inspection time; Among the multiple area difference values ​​corresponding to the target part, counting the number of the area difference values ​​that are greater than 0 to obtain an area abnormality value of the target part; The analyzing the depth change of the overlapping area between the target part and the device model during the inspection process of the current CT training operation to obtain the depth abnormal value of the target part includes: Acquire multiple overlapping depths corresponding to the target part, wherein the multiple overlapping depths correspond one-to-one to multiple inspection moments within an inspection time period, the overlapping depth being the depth at which the overlapping region between the target part and the device model penetrates into the device model at the corresponding inspection moment, and the inspection time period being the time period corresponding to the inspection process of the current CT training operation; Analyzing the depth difference between two adjacent overlapping depths of the target part within the inspection time period to obtain a plurality of depth difference values ​​corresponding to the target part, wherein the depth difference value is the difference between the depth area corresponding to the target part at the corresponding inspection time and the depth area corresponding to the target part at the previous inspection time; Among the multiple depth differences corresponding to the target part, the largest depth difference is determined as the depth abnormal value of the target part.

[0068] Multiple inspection moments within the inspection time period are equidistantly spaced in the time domain. For example, if the total duration of the inspection time period is set to 2 minutes and the time interval between two adjacent inspection moments is 1 second, the total number of multiple inspection moments in the inspection time period is 120.

[0069] In the above process, by counting the number of area difference values ​​greater than 0 among the multiple area difference values ​​corresponding to the target part, that is, counting the moments when the overlapping area increases, the threshold setting error that may be introduced by the threshold comparison method is avoided, and the area abnormality value of the target part can be quantified more accurately and conveniently.

[0070] Accordingly, by analyzing the depth difference between two adjacent overlapping depths in the multiple overlapping depths corresponding to the target part within the inspection time period, and determining the maximum depth difference as the depth outlier of the target part, the numerical interference introduced by the extreme value can be avoided, so as to accurately represent the degree of depth mutation in the overlapping process of the patient model and the device model through the maximum depth difference, that is, to obtain a more accurate depth outlier.

[0071] Step S5: Obtain an operation evaluation result of the current CT training operation according to the multiple posture abnormality indices and the multiple position abnormality indices.

[0072] In the above process, the abnormal posture and position of multiple limb parts of the comprehensive patient model during the examination process can comprehensively complete the evaluation of the current CT training operation from multiple angles, making the final output operation evaluation results more accurate and effective.

[0073] The step of obtaining an operation evaluation result of the current CT training operation according to the multiple posture abnormality indices and the multiple position abnormality indices includes: Acquire a plurality of posture tolerances, wherein the plurality of posture tolerances correspond one-to-one to a plurality of limb parts of the patient model, and the posture tolerances are used to represent a maximum adjustment degree of the corresponding limb part during a limb adjustment operation; Obtaining a plurality of limb abnormality coefficients according to the plurality of posture tolerances, wherein the sum of the limb abnormality coefficients and the corresponding posture tolerances is 1; Obtaining a plurality of limb abnormality values ​​according to a plurality of limb abnormality coefficients, the plurality of posture abnormality indices, and the plurality of position abnormality indices; calculating a sum of the plurality of limb abnormality values ​​to obtain an operation abnormality value; An operation evaluation result of the current CT training operation is generated according to the operation abnormal value.

[0074] The operation abnormality value is used to indicate the degree of operation abnormality of the current CT training operation. A larger value indicates a higher degree of operation abnormality of the current CT training operation, and vice versa.

[0075] For example, if the current CT training operation is set as the jth CT training operation among the multiple CT training operations performed by the target user, the limb abnormality value of the kth limb part among the multiple limb parts of the patient model is It can be expressed as: in, represents the limb abnormality coefficient of the kth limb part, It represents the position abnormality index of the k-th limb part after normalization (processed by the maximum and minimum normalization method, the normalized value range is (0, 1)). Normalized posture abnormality index of the k-th limb part.

[0076] The maximum adjustment degree of different limb parts during limb adjustment operations is different. Therefore, in the above process, posture tolerance is introduced to distinguish the maximum adjustment degree of different limb parts during limb adjustment operations, so that the limb abnormality value calculated for each limb part is more accurate.

[0077] Specifically, the step of obtaining multiple posture tolerances includes: Counting the total number of multiple target data points included in a target part to obtain the number of movable points of the target part, wherein the target part is any one of multiple limb parts of the patient model, and the target data point is a data point supporting limb adjustment operations among the multiple data points constituting the target part; calculating a ratio of the number of movable points of the target part to the volume of the target part to obtain a first value of the target part; The product of the first value of the target part and the second value of the target part is calculated to obtain the posture tolerance of the target part, wherein the second value of the target part is: the maximum point movement limit distance among the multiple point movement limit distances corresponding to the multiple target data points.

[0078] The larger the volume of a limb part, the easier it is for the limb part to collide with the device model, and the more difficult it is to adjust the position of the limb part, and vice versa.

[0079] The more movable points a limb has, the greater the maximum moving distance of the largest point among multiple target data points, indicating that the flexibility of the limb is higher and the position adjustment of the limb is easier, and vice versa.

[0080] For example, if the current CT training operation is set as the jth CT training operation among multiple CT training operations performed by the target user, the posture tolerance of the kth limb part among the multiple limb parts of the patient model is It can be expressed as: in, represents the second value of the k-th limb part, represents the volume of the kth limb part, Indicates the number of movable points of the k-th limb.

[0081] In some embodiments, the process of generating the operation evaluation result of the current CT training operation according to the operation abnormal value may be: Normalizing the abnormal operation value to obtain an abnormal operation normalized value; The operation sequence corresponding to the current CT training operation, the identity of the operating user (that is, the identity of the target user, such as the name and age of the target user), the normalized value of the operation abnormality, the multiple posture abnormality indices, and the multiple position abnormality indices are summarized to generate the operation evaluation result.

[0082] In the application, each CT training operation of the target user and its corresponding normalized abnormality value can be recorded during multiple CT training operations and displayed in a table so that the target user and other users (for example, when the target user is a medical student, the other user can be a teaching teacher) can observe the training status of the target user.

[0083] In addition, during each CT training operation, the overlapping areas of the device model and the patient model can be highlighted to help the target user quickly find the areas where the patient is injured during the current CT training operation, so that the target user can correct unreasonable actions in a timely manner in subsequent operations.

[0084] In general, the present invention obtains the device model and patient model in the current CT training operation, and analyzes the relative positional relationship between the device model and the patient model in the initial position to evaluate the degree of positional deviation of the patient model in the placement stage, and then analyzes the posture changes of multiple limb parts of the patient model before and after the limb adjustment operation to adapt to the situation where the patient's limbs can be adjusted in a certain range, effectively distinguish the severity of the depth of penetration of the patient model into the device model, and complete an accurate assessment of the degree of posture abnormality of the patient model in the limb adjustment stage; further analyzes the changes in the overlapping areas between multiple limb parts of the patient model and the device model during the inspection process of the current CT training operation to determine the degree of conflict between each limb part of the patient model and the device model when the operation is abnormal, and then comprehensively and accurately assess the severity of the positional conflict that may occur between the patient model and the device model during the inspection, and conducts an operational evaluation of the current CT training operation based on this, which can improve the accuracy of the assessment of operational abnormalities in CT training operations based on VR.

[0085] This invention proposes a VR-based CT room operation virtual training system, please refer to Figure 2, which shows a structural diagram of a VR-based CT room operation virtual training system 200 provided by one embodiment of the present invention, the system includes: An acquisition module 201 is configured to acquire a device model and a patient model in a current CT training operation, wherein the device model is used to represent a device for performing a CT examination, and the patient model is used to represent a patient for performing a CT examination; An initial analysis module 202 is used to analyze the relative position relationship between the device model and the patient model in the initial position to obtain an initial abnormal value; a posture analysis module 203 for analyzing posture changes of multiple limb parts of the patient model before and after a limb adjustment operation to obtain multiple posture abnormality indices, wherein the limb adjustment operation is used to reduce the depth of penetration of the limb parts of the patient model into the device model; a position analysis module 204 for analyzing, based on the initial abnormal values, changes in overlapping areas between the multiple limb parts of the patient model and the device model during the examination process of the current CT training operation to obtain multiple position abnormality indices; The operation evaluation module 205 is configured to obtain an operation evaluation result of the current CT training operation according to the multiple posture abnormality indices and the multiple position abnormality indices.

[0086] It should be noted that the system provided in the above embodiment is merely an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, the VR-based CT room operation virtual training system and the VR-based CT room operation virtual training method embodiment provided in the above embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0087] The embodiment of the present invention also provides an electronic device. Figure 3 , the electronic device may include a processor 301, a memory 302, and a program 3021 stored in the memory 302 and executable on the processor 301.

[0088] When the program 3021 is executed by the processor 301, it can achieve Figure 1 Any steps in the corresponding method embodiments and achieving the same beneficial effects will not be repeated here.

[0089] Those skilled in the art will appreciate that all or part of the steps of implementing the above-described embodiment method may be accomplished through hardware associated with program instructions, and the program may be stored in a readable medium.

[0090] The embodiment of the present invention further provides a readable storage medium, wherein the readable storage medium stores a computer program, and when the computer program is executed by a processor, the above Figure 1 Any steps in the corresponding method embodiments can achieve the same technical effects and will not be described again here to avoid repetition.

[0091] The computer-readable storage medium of the embodiments of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component.

[0092] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0093] The program code contained on the storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0094] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0095] An embodiment of the present invention further provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a VR-based CT room operation virtual training method provided in the above embodiment.

[0096] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0097] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A VR-based virtual training method for CT room operation, characterized in that: The method comprises: Acquire a device model and a patient model in a current CT training operation, wherein the device model is used to represent a device for performing a CT examination, and the patient model is used to represent a patient for performing a CT examination; Analyze the relative position relationship between the device model and the patient model at the initial position to obtain an initial abnormal value; analyzing posture changes of multiple limb parts of the patient model before and after a limb adjustment operation to obtain multiple posture abnormality indexes, wherein the limb adjustment operation is used to reduce the depth of the limb parts of the patient model penetrating into the device model; analyzing, based on the initial abnormal values, changes in overlapping areas between the multiple limb parts of the patient model and the device model during the examination process of the current CT training operation to obtain multiple position abnormality indices; An operation evaluation result of the current CT training operation is obtained according to the multiple posture abnormality indices and the multiple position abnormality indices.

2. The VR-based CT room operation virtual training method according to claim 1 is characterized in that: The analyzing the relative position relationship between the device model and the patient model at the initial position to obtain the initial abnormal value includes: Analyzing a deviation between a placement midline of the device model and a model midline of the patient model in an initial position to obtain a deviation angle, wherein the placement midline is a midline of an examination bed of the device model, and the examination bed is used to place the patient model; Calculating the shortest distance between the torso of the patient model in the initial position and the edge of the examination bed to obtain a minimum distance value; The initial abnormal value is obtained according to the deviation angle and the minimum distance value.

3. The VR-based CT room operation virtual training method according to claim 2, characterized in that: The obtaining of the initial abnormal value according to the deviation angle and the minimum distance value includes: Calculating the ratio of the deviation angle to the minimum distance value to obtain a position deviation value; Calculating a ratio of the projected area to the reference area to obtain a space occupation ratio, wherein the projected area is the area of ​​the projection of the patient model within the reference region when the patient model lies flat on the examination bed, the reference area is the total area of ​​the reference region, and the reference region is the plane area corresponding to the examination bed; The product of the position deviation value and the occupancy ratio is calculated to obtain the initial abnormal value.

4. The VR-based CT room operation virtual training method according to claim 1, characterized in that: The analysis of posture changes of multiple limbs of the patient model before and after the limb adjustment operation to obtain multiple posture abnormality indexes includes: Analyzing a position change of a target part before and after the limb adjustment operation to obtain position change information of the target part, wherein the target part is any one of the multiple limb parts of the patient model; analyzing a change in the depth of the target part penetrating into the device model before and after the limb adjustment operation to obtain depth change information of the target part; A posture abnormality index of the target part is obtained according to the position change information and the depth change information of the target part.

5. The VR-based CT room operation virtual training method according to claim 4 is characterized in that: The analyzing the position change of the target part before and after the limb adjustment operation to obtain the position change information of the target part includes: Analyzing position changes of a plurality of target data points included in the target part before and after the limb adjustment operation to obtain movement distances of the plurality of points of the target part, wherein the position change information of the target part includes the movement distances of the plurality of points of the target part, and the target data point is a data point supporting the limb adjustment operation among the plurality of data points constituting the target part; The analyzing the change in the depth of the target part penetrating into the device model before and after the limb adjustment operation to obtain the depth change information of the target part includes: Analyzing changes in the depths of the multiple target data points penetrating into the device model before and after the limb adjustment operation to obtain multiple depth differences of the target parts, wherein the depth change information of the target parts includes the multiple depth differences of the target parts; Obtaining a posture abnormality index of the target part according to the position change information and the depth change information of the target part includes: Among the multiple depth differences of the target part, determining the largest depth difference as the limit depth difference of the target part; Calculating the sum of the moving distances of multiple points of the target part to obtain a total moving distance of the target part; The limit depth difference and the total moving distance of the target part are calculated to obtain the posture abnormality index of the target part.

6. The VR-based CT room operation virtual training method according to claim 1, characterized in that: The method further comprises analyzing, based on the initial abnormal values, changes in overlapping areas between the multiple limb parts of the patient model and the device model during the examination process of the current CT training operation to obtain multiple position abnormality indices, including: Analyzing a change in an area of ​​an overlapping region between a target part and a device model during an examination process of a current CT training operation to obtain an area abnormality value of the target part, wherein the target part is any one of multiple limb parts of the patient model; Analyzing a depth change of an overlapping area between the target part and the device model during an inspection process of a current CT training operation to obtain a depth abnormality value of the target part; A position anomaly index of the target part is obtained according to the initial anomaly value, the area anomaly value of the target part, and the depth anomaly value of the target part.

7. The VR-based CT room operation virtual training method according to claim 6, characterized in that: The analyzing the area change of the overlapping region between the target part and the device model during the inspection process of the current CT training operation to obtain the area abnormality value of the target part includes: Acquire multiple overlapping areas corresponding to the target part, wherein the multiple overlapping areas correspond one-to-one to multiple inspection moments within an inspection time period, the overlapping areas being the areas of overlapping regions between the target part and the device model at the corresponding inspection moments, and the inspection time period being the time period corresponding to the inspection process of the current CT training operation; Analyzing the area difference between two adjacent overlapping areas of the target part within the inspection time period to obtain a plurality of area difference values ​​corresponding to the target part, wherein the area difference value is the difference between the overlapping area corresponding to the target part at the corresponding inspection time and the overlapping area corresponding to the target part at the previous inspection time; Among the multiple area difference values ​​corresponding to the target part, counting the number of the area difference values ​​that are greater than 0 to obtain an area abnormality value of the target part; The analyzing the depth change of the overlapping area between the target part and the device model during the inspection process of the current CT training operation to obtain the depth abnormal value of the target part includes: Acquire multiple overlapping depths corresponding to the target part, wherein the multiple overlapping depths correspond one-to-one to multiple inspection moments within an inspection time period, the overlapping depth being the depth at which the overlapping region between the target part and the device model penetrates into the device model at the corresponding inspection moment, and the inspection time period being the time period corresponding to the inspection process of the current CT training operation; Analyzing the depth difference between two adjacent overlapping depths of the target part within the inspection time period to obtain a plurality of depth difference values ​​corresponding to the target part, wherein the depth difference value is the difference between the depth area corresponding to the target part at the corresponding inspection time and the depth area corresponding to the target part at the previous inspection time; Among the multiple depth differences corresponding to the target part, the largest depth difference is determined as the depth abnormal value of the target part.

8. The VR-based CT room operation virtual training method according to claim 1, characterized in that: Obtaining an operation evaluation result of the current CT training operation according to the multiple posture abnormality indices and the multiple position abnormality indices includes: Acquire a plurality of posture tolerances, wherein the plurality of posture tolerances correspond one-to-one to a plurality of limb parts of the patient model, and the posture tolerances are used to represent a maximum adjustment degree of the corresponding limb part during a limb adjustment operation; Obtaining a plurality of limb abnormality coefficients according to the plurality of posture tolerances, wherein the sum of the limb abnormality coefficients and the corresponding posture tolerances is 1; Obtaining a plurality of limb abnormality values ​​according to a plurality of limb abnormality coefficients, the plurality of posture abnormality indices, and the plurality of position abnormality indices; calculating a sum of the plurality of limb abnormality values ​​to obtain an operation abnormality value; An operation evaluation result of the current CT training operation is generated according to the operation abnormal value.

9. The VR-based CT room operation virtual training method according to claim 8, characterized in that: The acquiring of multiple posture tolerances includes: Counting the total number of multiple target data points included in a target part to obtain the number of movable points of the target part, wherein the target part is any one of multiple limb parts of the patient model, and the target data point is a data point supporting limb adjustment operations among the multiple data points constituting the target part; calculating a ratio of the number of movable points of the target part to the volume of the target part to obtain a first value of the target part; The product of the first value of the target part and the second value of the target part is calculated to obtain the posture tolerance of the target part, wherein the second value of the target part is: the maximum point movement limit distance among the multiple point movement limit distances corresponding to the multiple target data points.

10. A VR-based CT room operation virtual training system, characterized in that: The system comprises: an acquisition module, configured to acquire a device model and a patient model in a current CT training operation, wherein the device model is used to represent a device for performing a CT examination, and the patient model is used to represent a patient for performing a CT examination; An initial analysis module is used to analyze the relative position relationship between the device model and the patient model at the initial position to obtain an initial abnormal value; a posture analysis module, configured to analyze posture changes of multiple limb parts of the patient model before and after a limb adjustment operation to obtain multiple posture abnormality indices, wherein the limb adjustment operation is configured to reduce the depth of penetration of the limb parts of the patient model into the device model; a position analysis module, configured to analyze, based on the initial abnormal values, changes in overlapping areas between multiple limb parts of the patient model and the device model during the examination process of the current CT training operation, to obtain multiple position abnormality indices; The operation evaluation module is used to obtain an operation evaluation result of the current CT training operation according to the multiple posture abnormality indices and the multiple position abnormality indices.

Images