Background
The Virtual Intelligent (VI) medical platform is a medical platform constructed based on holographic technologies such as virtual reality, augmented reality, mixed reality and the like, artificial intelligence, big data and the like, is used for assisting and guiding invasive, minimally invasive and noninvasive clinical diagnosis and treatment processes, and can be applied to the fields including but not limited to surgery, internal medicine, radiotherapy department, interventional department and the like.
Radiation therapy is one of the main approaches for malignant tumor treatment. However, tumors, normal tissues and organs, and radiation used in radiotherapy in the human body are invisible to the naked eye. Modern images, such as CT, MRI, PET-CT, become the "eyes" of medical workers, and 3D virtual reconstruction and display of patients and tumors can be performed. The treatment planning system integrates image data and treatment equipment information into a whole, and achieves the functions of 3D image reconstruction, target area sketching, irradiation field setting, dose calculation, scheme evaluation and the like. The treatment planning system can display the relative positions of the parts of the treatment equipment in a 3D mode, but in the actual treatment implementation process, the parts still cannot be implemented due to collision among the equipment, planning adjustment is needed again, more work is brought to medical staff, and the patient is not changed when the medical staff occupy the machine of the treatment room equipment.
Currently, two virtual simulated image display three-dimensional spatial positions are provided by treatment planning systems: firstly, beam's Eye View (BEV), which is a position relation between a radiation source position and a target area and a jeopardizing organ viewed by a 3D simulation observer along the central axis direction of the radiation source, and also a spatial position relation between equipment and a tumor is viewed along the Beam direction; and a Room view (REV) is a spatial positional relationship between the components of the therapeutic apparatus and between the device and the patient, as viewed by a simulated observer standing at a location within the treatment Room. The two above simulations show that a physicist can be aided in initially evaluating the likelihood of treatment plan delivery. And the two images are displayed through the traditional electronic screen, and the viewpoint is selected by operating the mouse.
Further, the existing technical solutions have the following drawbacks: (1) The current planned evaluation concerns whether the target area and the physical dose distribution meet clinical requirements, so that the occurrence of collisions between devices or between device patients in the treatment delivery cannot be accurately evaluated; (2) The BEV and REV simulation images are viewed through a traditional electronic screen, are not intuitive, and cannot simulate a treatment plan in a full view angle manner in a radiotherapy environment; (3) The gesture of sliding the mouse wheel and dragging is not in line with the natural motion language of the human body.
Disclosure of Invention
Aiming at the defects in the prior art, the embodiment of the application aims to provide a radiotherapy plan simulation method, equipment and storage medium based on a virtual intelligent medical platform.
In order to achieve the above object, in a first aspect, an embodiment of the present application provides a radiotherapy plan simulation method based on a virtual intelligent medical platform, including:
a plan reading step: acquiring a patient DICOM RT data object from a hospital, and analyzing the patient DICOM RT data object to generate a plan file;
and a data conversion step: three-dimensional reconstruction is carried out on the patient DICOM RT data object by using a Python language and a 3DSlicer software tool to obtain a three-dimensional model file, and format conversion is carried out on the three-dimensional model file to generate a display file for holographic display; the three-dimensional model file comprises a three-dimensional human body surface model, a three-dimensional radiation field model, a three-dimensional dose distribution model and a three-dimensional structure model, and the display file comprises an OBJ file or an STL file;
planning simulation step: loading and displaying the plan file and the display file, and simulating the radiotherapy process of the real accelerator; the radiotherapy process comprises the steps of showing the relation between the field and the target area endangered organ, the rotation condition of the treatment machine head, the shape of the field, the condition of whether collision influence exists between a patient and the accelerator machine head, the position of the zero-degree field, the position relation between the zero-degree field beam and the target area and the execution process of the current treatment plan.
As a specific embodiment of the present application, the plan reading step specifically includes:
establishing communication connection with DICOM network of hospital and providing C-Stroe network service;
receiving the patient DICOM RT data object via a DICOM protocol;
the patient DICOM RT data object is parsed to generate the plan file, which includes a Json file for describing data information.
As a specific embodiment of the present application, the plan simulation step specifically includes:
determining a target position of the virtual accelerator in a mode of scanning a space scene or in a mode of gesture recognition;
loading and displaying the plan file and the display file;
selecting a virtual accelerator model corresponding to an accelerator required by the DICOM RT data object of the patient from the plan file, and combining the target position and a gesture operation adjustment position to finish positioning of the virtual accelerator model, wherein the gesture operation adjustment position is obtained by adjusting the initial position and the angle of the virtual accelerator through gestures;
and simulating the radiotherapy process of the real accelerator according to the positioned virtual accelerator model, the loaded three-dimensional model file and the treatment information contained in the plan file.
Further, the plan simulation step further includes:
controlling the transparency and the display condition of the virtual machine model to achieve the effect of observing the internal organs at risk, the target area position and the CT section information of the human body;
by body movement, walking or gesturing to observe the simulated execution of the radiotherapy plan from different angles.
Further, the method further comprises:
and a data recording step: and acquiring annotation records of medical staff on the radiotherapy process, and uploading the records to a server for storage.
In a second aspect, an embodiment of the present application provides a radiotherapy plan simulation device based on a virtual intelligent medical platform, including a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, where the memory is configured to store a computer program, the computer program includes program instructions, and the processor is configured to invoke the program instructions to perform the method of the first aspect.
In a third aspect, embodiments of the present application provide a computer readable storage medium storing a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of the first aspect described above.
According to the embodiment of the application, the Python language and the 3DSlicer software tool are utilized to analyze and process the radiotherapy plan information, and the analyzed file is converted and loaded and displayed to the simulation equipment (such as holographic glasses), so that the implementation condition of the treatment plan can be simulated in an omnibearing manner, the possible problems in the implementation of the treatment plan are predicted, the situation that a patient cannot implement treatment after being positioned in a treatment room is avoided, the occupation of the treatment room equipment is avoided, the readjustment of the treatment plan is avoided, the workload of medical staff is reduced, and the inconvenience and pain of the patient are also reduced.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, a flowchart of a radiotherapy plan simulation method based on a virtual intelligent medical platform according to an embodiment of the present application is shown. It should be noted that the embodiment of the method is described in terms of a simulation device, which may be holographic glasses or an AR/VR terminal. The holographic glasses will be described below. As shown, the simulation method may include the steps of:
s101, planning and reading: patient DICOM RT data objects from a hospital are acquired and parsed to generate a planning file.
Specifically, step S101 includes:
establishing communication connection with DICOM network of hospital and providing C-Stroe network service;
receiving the patient DICOM RT data object;
the patient DICOM RT data object is parsed to generate the plan file, which includes a Json file for describing data information.
S102, a data conversion step: and performing three-dimensional reconstruction on the patient DICOM RT data object by using a Python language and a 3DSlicer software tool to obtain a three-dimensional model file, and performing format conversion on the three-dimensional model file to generate a display file for holographic display.
Specifically, a Python language and a 3DSlicer software tool are used for three-dimensional reconstruction of a patient DICOM RT data object, and the reconstructed three-dimensional model file comprises: a three-dimensional body surface model, a three-dimensional portal model, a three-dimensional dose distribution model and a three-dimensional structure model. And carrying out format conversion on the three-dimensional model file to generate an OBJ or STL file which can be used for holographic display.
S103, plan simulation step: and loading and displaying the plan file and the display file, and simulating the radiotherapy process of the real accelerator.
Specifically, step S103 includes:
(1) Determining the target position of the virtual accelerator by utilizing a mode of scanning a space scene by holographic glasses or a gesture recognition mode; for example, the holographic glasses scan the space scene by using the technologies of space recognition, object recognition and the like, determine the target position of the virtual accelerator, and complete the process of planning, simulating and initializing the scene; or by identifying, dragging, etc. the target location of the virtual accelerator.
(2) Loading and displaying the planning file and the display file on the holographic glasses; for example, a Json file for describing data information, an OBJ or STL file for holographic display, is loaded and displayed in the holographic glasses.
(3) Selecting a virtual accelerator model corresponding to an accelerator required by a patient DICOM RT data object from the plan file, and combining a target position of the virtual accelerator and a gesture operation adjustment position to finish positioning of the virtual accelerator model, wherein the gesture operation adjustment position is obtained by adjusting the initial position and angle of the virtual accelerator through gestures; for example, the plan file (Json file) contains accelerator model information, and the virtual accelerator model required for plan simulation is selected by the model information, and then loaded into the determined target position, thereby completing the positioning of the virtual accelerator model.
(4) Simulating a radiotherapy process of a real accelerator according to the positioned virtual accelerator model, the loaded three-dimensional model file and treatment information contained in the planning file, wherein the radiotherapy process comprises a process of showing the rotation condition of a treatment machine head, the shape of a radiation field, whether collision influence exists between a patient and the accelerator machine head, the position of a zero-degree radiation field, the position relationship between a zero-degree radiation field beam and a target area, the relationship between the radiation field and the target area endangered organs and the execution process of a current treatment plan.
For example, the virtual accelerator position, the three-dimensional body surface model, and the virtual accelerator model are automatically matched to the accelerator treatment couch. Meanwhile, the transparency of the virtual machine model and whether the virtual machine model is displayed or not can be controlled, so that the effects of observing the endangered organs, the target area position, CT section information and the like in the human body are achieved. After the positioning is finished, the running process of the real accelerator can be dynamically simulated by reading RT Plan information in the DICOM RT data object of the patient, wherein the running process comprises the rotation of the treatment machine head and the shape of the radiation field, and whether collision influence exists between the patient and the accelerator machine head or not is visually checked. The virtual model can simulate the shape of the field, and can observe the position of the field at zero degree, the position relation between the beam at zero degree and the target area, the shape of the field, the relation between the field and the target area endangered organ, and the executing process of the current treatment plan. In addition, the radiotherapy process can be observed from different angles through body movement, rotation or gesture operation.
S104, a data recording step: and acquiring annotation records of medical staff on the radiotherapy process, and uploading the records to a server for storage.
Specifically, in the automatic simulation process, a doctor can make annotation records on the conditions of the simulation process including the operation condition of the machine head, the irradiation condition of the field beam, analysis of the simulation result and the like, and upload the annotation records to a server for storage.
According to the radiotherapy plan simulation method, the Python language and the 3DSlicer software tool are utilized to analyze and process radiotherapy plan information, and the analyzed file is converted and loaded and displayed to simulation equipment (such as holographic glasses), so that the implementation condition of a treatment plan can be simulated in an omnibearing manner, the possible problems in the implementation of the treatment plan are predicted, the situation that a patient cannot implement treatment after being positioned in a treatment room is avoided, the equipment of the treatment room is avoided being occupied, the readjustment of the treatment plan is avoided, the workload of medical staff is reduced, and inconvenience and pain of the patient are also reduced.
Further, in the present embodiment, in the plan simulation process, a gesture recognition or voice recognition manner is adopted to interact with the holographic glasses, so as to replace a sliding mouse or dragging mouse in the treatment plan simulation in the prior art, so that the simulation method in the present embodiment is more in line with the natural motion language of the human body.
Based on the same inventive concept, the embodiment of the application provides radiotherapy plan simulation equipment based on a virtual intelligent medical platform. As shown in fig. 2, the simulation apparatus 100 may include: one or more processors 101, one or more input devices 102, one or more output devices 103, and a memory 104, the processors 101, input devices 102, output devices 103, and memory 104 being interconnected by a bus 105. The memory 104 is used for storing a computer program comprising program instructions, said processor 101 being configured for invoking said program instructions for performing the method of the above-described embodiment of a virtual intelligent medical platform based radiotherapy plan simulation method.
It should be appreciated that in embodiments of the present application, the processor 101 may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device 102 may include a keyboard or the like, and the output device 103 may include a display (LCD or the like), a speaker or the like.
The memory 104 may include read only memory and random access memory and provides instructions and data to the processor 101. A portion of the memory 104 may also include non-volatile random access memory. For example, the memory 104 may also store information of device type.
In a specific implementation, the processor 101, the input device 102, and the output device 103 described in the embodiments of the present application may execute the implementation described in the embodiments of the radiotherapy plan simulation method based on the virtual intelligent medical platform provided in the embodiments of the present application, which is not described herein again.
It should be noted that, in the embodiment of the present application, the specific workflow and related details of the server refer to the foregoing method embodiment, and are not described herein again.
Further, an embodiment of the present application also provides a readable storage medium storing a computer program, the computer program including program instructions that when executed by a processor implement: the radiotherapy plan simulation method based on the virtual intelligent medical platform.
The computer readable storage medium may be an internal storage unit of the system according to any of the foregoing embodiments, for example, a hard disk or a memory of the system. The computer readable storage medium may also be an external storage device of the system, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the system. Further, the computer readable storage medium may also include both internal storage units and external storage devices of the system. The computer readable storage medium is used to store the computer program and other programs and data required by the system. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.