Visualization system and visualization method for medical data
By constructing a decoupled system consisting of a rendering object module, a rendering scene controller module, and a rendering strategy module, the problem that medical data visualization technology cannot adapt to multiple types of data is solved, and flexible, stable, and scalable medical data visualization is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUABORON NEUTRON TECH (HANGZHOU) CO LTD
- Filing Date
- 2026-01-08
- Publication Date
- 2026-05-12
AI Technical Summary
Existing medical data visualization technologies cannot simultaneously adapt to the visualization needs of various types of medical data in different medical scenarios.
A medical data visualization system is provided, including a rendering object module, a rendering scene controller module, and a rendering strategy module. The rendering object module encapsulates medical data, the rendering scene controller module manages the scene and camera, and the rendering strategy module defines specific algorithms, thereby decoupling the three modules and supporting the visualization needs of different types of medical data.
It has achieved adaptation to different medical data types and varied rendering requirements, improving the system's stability, maintainability, flexibility and scalability, and can meet the visualization needs of various types of medical data in various medical scenarios.
Smart Images
Figure CN122024979A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of medical data processing technology, specifically to a medical data visualization system and visualization method. Background Technology
[0002] In related technologies, the visualization of medical data is mainly achieved using mature open-source toolkits such as The Visualization Toolkit (VTK). However, this is primarily aimed at visualizing medical imaging data. Medical data not only includes imaging data but also encompasses various non-imaging data types, which also require visualization and analysis. However, current medical data visualization technologies are not well-suited to meeting the visualization needs of diverse medical data across various medical scenarios. Summary of the Invention
[0003] This invention provides a medical data visualization system and method to address the problem that medical data visualization technology cannot simultaneously support the visualization needs of multiple different types of medical data in various medical scenarios.
[0004] In a first aspect, the present invention provides a medical data visualization system, comprising: a rendering object module, a rendering scene controller module, and a rendering strategy module; The rendering object module is used to acquire multiple medical data to be rendered and encapsulate them respectively to obtain multiple rendering objects; The rendering strategy module is used to predefine multiple rendering strategies, with each rendering strategy corresponding to a specific rendering algorithm. The rendering scene controller module is used to manage one or more rendering scene controllers, which are used to render the rendering object using the corresponding rendering strategy.
[0005] In a second aspect, the present invention provides a method for visualizing medical data, applied to the visualization system described in the first aspect or any corresponding embodiment thereof, the visualization method comprising: Acquire multiple target medical data to be rendered; The target medical data is encapsulated into rendering objects respectively; Select the corresponding target rendering scene controller from a plurality of pre-built rendering scene controllers, render the target medical data according to the target rendering strategy corresponding to each target medical data, and display it in the rendering window corresponding to the target rendering scene controller; The target rendering strategy is a specific drawing algorithm.
[0006] Thirdly, the present invention provides a medical data visualization device, applied to the visualization system described in the first aspect or any corresponding embodiment thereof, the device comprising: The data acquisition module is used to acquire multiple target medical data to be rendered; An encapsulation module is used to encapsulate the target medical data into rendering objects respectively; The rendering module is used to select the corresponding target rendering scene controller from a plurality of pre-built rendering scene controllers, render the target medical data according to the target rendering strategy corresponding to each target medical data, and display it in the rendering window corresponding to the target rendering scene controller; The target rendering strategy is a specific drawing algorithm.
[0007] Fourthly, the present invention provides an electronic device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the medical data visualization method of the second aspect above or any corresponding embodiment thereof.
[0008] Fifthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the medical data visualization method of the second aspect or any corresponding embodiment described above.
[0009] In a sixth aspect, the present invention provides a computer program product, including computer instructions for causing a computer to execute the medical data visualization method of the second aspect or any corresponding embodiment described above.
[0010] In this embodiment of the invention, medical data is encapsulated by a rendering object module, the scene controller module manages the scene and camera, and the rendering strategy module defines specific algorithms, thus achieving decoupling among the three components. The rendering object can dynamically select a rendering strategy to support the visualization needs of different types of medical data. The system is stable, maintainable, flexible, and scalable. Therefore, it can handle different types of medical data and varied rendering requirements, and is thus adaptable to the visualization needs of various types of medical data in different medical scenarios. Attached Figure Description
[0011] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0012] Figure 1 This is a schematic block diagram of a medical data visualization system according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the elements of a visualization system according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the VTK pipeline for the aspect rendering strategy according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the VTK pipeline for volume rendering strategy according to an embodiment of the present invention; Figure 5 This is a schematic diagram of medical image data rendering according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the VTK pipeline for surface rendering strategy according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the segmented structure data rendering according to an embodiment of the present invention; Figure 8 This is a schematic diagram of the VTK pipeline for point cloud rendering according to an embodiment of the present invention; Figure 9 This is a schematic diagram of the VTK pipeline for contour rendering strategy according to an embodiment of the present invention; Figure 10 This is a schematic diagram of isodose lines rendered according to an embodiment of the present invention; Figure 11 This is a schematic diagram of sagittal plane rendering of dose bands / dose cloud maps according to an embodiment of the present invention; Figure 12 This is a flowchart illustrating a method for visualizing medical data according to an embodiment of the present invention; Figure 13 This is a schematic diagram of the rendering module call according to an embodiment of the present invention; Figure 14 This is a structural block diagram of a medical data visualization device according to an embodiment of the present invention; Figure 15 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0013] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0014] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.
[0015] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.
[0016] This embodiment provides a medical data visualization system, which is implemented based on the Visualization Toolkit (VTK), such as... Figure 1 As shown, the visualization system includes: a rendering object module 101, a rendering scene controller module 102, and a rendering strategy module 103; The rendering object module 101 is used to acquire multiple medical data to be rendered and encapsulate them respectively to obtain multiple rendering objects.
[0017] Specifically, a RenderObject is a unified encapsulated entity of the data to be rendered, which includes, but is not limited to, vtkImageData (image data) and vtkPolyData (polygon data). The RenderObject module decouples the underlying data from its specific presentation in the scene, enabling centralized management of rendering resources. In addition to encapsulating the raw data itself, the RenderObject also contains display attribute information (also known as visualization attribute information) related to that data, such as color, transparency, and pseudo-color mapping parameters. In this embodiment, all types of medical data to be rendered are encapsulated through a unified RenderObject interface. The RenderObject must be combined with a corresponding rendering strategy to ultimately achieve its visual display in the scene.
[0018] Medical data can be data from boron neutron capture therapy, medical data required for patient management and services, or medical data required for clinical decision support, disease risk prediction, and other scenarios.
[0019] The rendering strategy module 103 is used to predefine multiple rendering strategies, each corresponding to a specific rendering algorithm. The core of the RenderStrategy module is managing a specific type of vtkActor. The vtkActor is a key component of the rendering strategy, used to establish a connection between the rendering scene controller and the rendering object. In the visualization pipeline, it interfaces upwards with the rendering scene controller and downwards with the data in the rendering object. Each rendering strategy is responsible for building and maintaining its corresponding visualization rendering pipeline. External applications can dynamically specify or switch rendering strategies for any rendering object, thereby achieving flexible control over the data presentation format.
[0020] The rendering scene controller module 102 manages one or more rendering scene controllers, which are used to render the rendering object using the corresponding rendering strategy. Specifically, the rendering scene controller is a wrapper component for the VTK rendering context (including, for example, the renderer (vtkRenderer), render camera (RenderCamera), checkerboard strategy, and orientation indicator). External applications can choose to instantiate a two-dimensional (2D) or three-dimensional (3D) rendering scene controller. The system will automatically configure the corresponding geometric constraints and camera model according to the selection. This mechanism ensures the flexibility of the underlying rendering environment. In this embodiment, any type of rendering object (i.e., encapsulated medical data) can be bound to a rendering strategy compatible with its data type and rendered and displayed in an optional rendering scene controller.
[0021] Medical data can be medical-related data, including imaging data, structural data (including geometric model data, contour data, etc.), dosage data, and text data. While a rendered object must be combined with a rendering strategy to be ultimately displayed, the rendering algorithm can be flexibly configured and switched at runtime based on the rendering strategy. That is, it allows for dynamic loading and switching of rendering algorithms (such as facet rendering, volume rendering, and surface rendering) for different medical data, thereby achieving a system expansion mechanism that conforms to the open / closed principle.
[0022] In this embodiment, the rendering strategy module can be used to predefine and construct a variety of different rendering strategies. When rendering medical data to be rendered, the corresponding rendering strategy can be selected according to the rendering needs of the medical data, and the rendering can be carried out in the corresponding rendering scene controller. Ultimately, different types of medical data can be visualized.
[0023] In other words, this embodiment extends the rendering workflow organization of The Visualization Toolkit (VTK) based on related technologies, introducing a dynamic switching mechanism for rendering algorithms for different types of data. This enables the combined display of multiple data types within the same visualization scene. Furthermore, it improves rendering flexibility and overall operational efficiency in complex medical data visualization scenarios. In this embodiment, the rendering object module encapsulates medical data, the rendering scene controller module manages the scene and camera, and the rendering strategy module defines specific algorithms, achieving decoupling between the three. The rendering object can dynamically select rendering strategies to support the visualization needs of different types of medical data. The system possesses stability, maintainability, flexibility, and scalability. Therefore, it can handle different types of medical data and varied rendering requirements, thus adapting to the visualization needs of various types of medical data in different medical scenarios.
[0024] Specifically, when encapsulating medical data, its display attributes (i.e., visualization attributes) can be encapsulated along with it. The display attributes of medical data include at least one of the following: color, transparency, visibility, pseudocolor mapping parameters, and transformation matrix. In other words, the rendering object module is responsible for the complete encapsulation of the medical data itself and its display attributes.
[0025] In addition, such as Figure 2 As shown, the visualization system provided in this embodiment offers a unified external interface ( Figure 2 The IRenderHandler in the software meets the requirements of high cohesion and low coupling in software design.
[0026] In some alternative implementations, the plurality of medical data to be rendered differ in at least one of the following: resolution, source, and data structure.
[0027] In other words, the visualization system provided in this embodiment can realize the combined display of medical data with different resolutions, different sources, and different visualization needs (achieved through different rendering strategies).
[0028] When the visualization system provided in this embodiment is used to visualize boron neutron capture therapy data, for example, when integrated into a BNCT treatment planning system (BNCT-TPS), it allows physicians or physicists to efficiently complete all plan evaluations within a single system without relying on external tools. Specifically, the visualization method provided in this embodiment directly serves the complex BNCT treatment plan optimization process by accurately presenting various boron neutron capture therapy data (such as BNCT target structure data, normal tissue structure data, and neutron-dose distribution data). The visualization function supports physicians in performing multi-dimensional dose assessments, effectively assisting in optimizing target conformity and protecting organs at risk, significantly improving clinical evaluation efficiency, shortening the complex review time of BNCT plans, and increasing the efficiency of treatment delivery.
[0029] In some optional implementations, the rendering strategy module is also used to define one or more of the rendering strategies.
[0030] In other words, the medical data visualization system provided in this embodiment supports the expansion of rendering strategies, so that rendering strategies can be added at any time according to the visualization needs of medical data.
[0031] Specifically, the visualization system provided in this embodiment can integrate one or more of the following rendering strategies: MPRRenderStrategy: A multi-plane reconstructed section for generating medical images, focusing on precise positioning of the 2D view.
[0032] Volume Render Strategy: This strategy uses 3D texture mapping or ray casting algorithms to reconstruct and visualize 3D volume data, suitable for stereoscopic display of dose bands or anatomical structures.
[0033] SurfaceRenderStrategy: Responsible for rendering structural data represented by the Region of Interest (ROI) to achieve accurate reconstruction of the geometric surface.
[0034] IsolinesRenderStrategy: Draws isodose line data, focusing on the extraction of dose boundaries.
[0035] Point rendering strategy: Draw point data represented by keypoints (POIs) to display markers and reference points.
[0036] Graphic Render Strategy: Used to draw window-based two-dimensional graphics, such as dose profiles, dose-volume histograms (DVH curves), etc.
[0037] TextRenderStrategy: Responsible for rendering text data such as text labels and annotations in the scene.
[0038] As mentioned above, medical data can include several categories such as imaging data, structural data (including geometric model data, contour data, etc.), dosage data, and textual data.
[0039] For image data, the data carrier in VTK is vtkImageData (image data), which can be rendered using both slice rendering and volume rendering strategies. Specifically, in the 2D rendering scene controller, a slice rendering strategy can be used to render image data. The core of this strategy is to ensure accurate resampling and smoothness on any inclined plane. In the 3D view, a volume rendering strategy can be used to simulate the transmission and attenuation of light in volume data, providing a panoramic stereoscopic view of the anatomical structure. The two rendering strategies for image data are explained below.
[0040] I. Section rendering: First, perform spatial geometric transformations. Specifically, this can be achieved by reslicing the transformation matrix. , the pixel coordinates of the image data A point mapped to the world coordinate system of the input 3D volume data The formula is expressed as: Ensure geometric consistency during registration and rotation operations.
[0041] Then, trilinear interpolation is performed. Specifically, trilinear interpolation is used to calculate the points. grayscale value , From its surrounding 8 neighboring voxels Interpolation is used to determine and avoid artifacts caused by resampling. Grayscale value. The calculation formula is: , Based on neighborhood voxels and points The trilinear interpolation weights are determined by the distance between them.
[0042] Finally, pseudo-color mapping (also known as color mapping) is performed. Specifically, the visualization system in this embodiment supports pseudo-color mapping of image data. It will display intensity. Mapped to the final RGB color values The formula is expressed as: ,in, It is a mapping function defined by a color lookup table.
[0043] In summary, the complete process of facet rendering can be viewed as a process starting from the pixel coordinates of image data. and the current transformation state To the final color Functions:
[0044] To implement this transformation process, the aspect rendering strategy uses VTK data structures such as vtkImageActor (actor (graphic character)), vtkImageReslice (image reslicer), and vtkImageMapToWindowLevelColors (image window width and window level color mapper) to build the rendering pipeline. Its complete VTK rendering pipeline is as follows: Figure 3 As shown.
[0045] The slicing strategy pipeline internally uses vtkImageReslice for image reslicing, vtkImageMapToWindowLevelColors for window width and level adjustment, and vtkLookupTable for color lookup tables. Furthermore, it supports image rotation and translation via vtkTransform, or adjustment of pseudocolor mapping, thereby enabling clearer observation of the position and state of various tissue structures within the image.
[0046] II. Volume rendering: The volume rendering strategy aims to present image data as a semi-transparent 3D image, allowing users to visualize its internal structure. Through precisely defined color transfer and opacity transfer functions, the system can highlight bones (high-density areas) and soft tissues with high contrast, assisting doctors and physicists in preliminary structural identification. In the GPU implementation, a front-to-back alpha blending algorithm is used for discretized approximation calculations. Assuming that along the light rays... 1 sampling point, initial cumulative color Initial cumulative opacity For the first sampling points ( to Perform the following compound operations:
[0047] in: and It represents the color and opacity of the current sampling point. This represents the remaining transmittance at the current sampling point. The color of the pixel is... Its opacity is .
[0048] In summary, the complete volume rendering strategy of VTK is as follows: Figure 4 As shown, GPU-accelerated raycasting volume rendering is performed using vtkGPUVolumeRayCastMapper (GPU volume rendering raycasting mapper). The color and opacity transfer functions are finely controlled via vtkColorTransferFunction (color transfer function) and vtkPiecewiseFunction (piecewise function), respectively, while vtkVolumeProperty (volume rendering property) sets the overall rendering properties to achieve the mapping from raw data to a visual 3D image or dose distribution map.
[0049] Taking head model data as an example, the complete rendering effect of the image data is as follows: Figure 5 As shown, the horizontal crown arrow window represents the result generated by the sectional rendering strategy, while the 3D window represents the result generated by the volume rendering strategy.
[0050] For structural data in medical data, this specifically includes region of interest (ROI) data (e.g., contour data), geometric model data, and point of interest (POI) data. In this embodiment, a surface rendering strategy can be used to accurately display the ROI and geometric model structure, and a point cloud rendering strategy can be used to display the POI. These two core geometric rendering strategies are described in detail below.
[0051] I. Surface Rendering: The core task of surface rendering strategies is to visualize geometric surface models (represented as triangular meshes) in 3D space. This embodiment uses the Moving Cubes method (an isosurface extraction algorithm) as the core technology to achieve this transformation. The algorithm extracts given isosurfaces by traversing the input voxels. The geometric structure. The specific process of surface rendering includes: The first step is to perform index calculation: For each voxel, check the scalar values of its 8 vertices. and Compare and assign binary states These 8 states combine to form a configuration index from 0 to 255. :
[0052] The second step is to perform a topology lookup: using the configured indexes described above. The isosurface topology of the current voxel is determined from a predefined lookup table, which includes the number of triangular faces and the edges containing their vertices.
[0053] The third step is to calculate the vertex positions: the vertices of the triangular facets lie on the edges of the cube. For a line connecting the vertices... (State 1) and (State 0) edge, intersection point The coordinates are obtained through linear interpolation:
[0054] Step 4, Output Mesh: Collect all the generated triangular patches and output a complete triangular mesh (vtkPolyData) that approximates an isosurface.
[0055] The mathematical core of the image-to-surface transformation in surface rendering strategies can be summarized as an isosurface geometric reconstruction method based on spatial configuration classification and linear interpolation. Based on the above description, the VTK pipeline comprising surface rendering strategies is as follows: Figure 6 As shown.
[0056] This strategy is primarily used for rendering structural data. `vtkImageData` serves as input, carrying voxelized scalar field information, such as binary masks for ROIs or isosurface extraction. The `vtkMarchingCubes` filter is the core processing component in the pipeline. It processes the input volume data using the Marching Cubes algorithm, extracting isosurfaces and outputting the results as `vtkPolyData` (triangular mesh data). `vtkPolyData` contains the geometric topological information (vertices, edges, faces) of the isosurfaces. Subsequently, `vtkPolyDataMapper` acts as a mapper, responsible for converting the abstract geometric data (`vtkPolyData`) into geometric primitives that can be processed by the graphics hardware. Finally, `vtkActor`, as an entity in the scene, combines the geometric information output by the mapper with the optical properties (color, transparency, material, lighting model) defined by `vtkProperty`, and is rendered in the rendering environment defined by `vtkRenderer`, completing the surface rendering process. Figure 7 The rendering effect of ROI data in 2D and 3D windows is shown, which can clearly show the position of the region of interest in the head model image. Each ROI supports transparency and color settings.
[0057] II. Point Cloud Rendering The core task of point cloud rendering is to visualize discrete sets of spatial points (such as points of interest, POIs). Unlike surface rendering, point cloud rendering does not focus on continuous geometric topology, but rather on geometric instantiation (glyphing) and efficient rendering of each discrete point. The geometric processing of point cloud rendering mainly includes the following steps: 1. Data Input and Instantiation Processing: Accepts point data input in vtkPolyData format, containing only vertex information. vtkVertexGlyphFilter (a vertex glyph filter used to convert point data into vertex graphics) is responsible for performing the instantiation operation, replacing each vertex with a symbol (Glyph) with an actual geometric shape, thus giving the discrete points a visible size in 3D space, and outputting the result as updated vtkPolyData.
[0058] 2. Instantiated geometry configuration: The core of rendering lies in configuring the scaling, color, and orientation of these instantiated geometries to ensure their accurate representation and distinguishability in the world coordinate system.
[0059] Based on the above description, the VTK pipeline, composed of point cloud rendering strategies, is as follows: Figure 8 As shown.
[0060] This strategy is primarily used for rendering discrete geometric entities such as Points of Interest (POIs). `vtkPolyData` provides vertex position information. `vtkVertexGlyphFilter` is the core processor, performing geometry instantiation and assigning visible dimensions to discrete points. Subsequently, `vtkPolyDataMapper` converts the instantiated geometric data into graphical primitives. Finally, `vtkActor` combines the geometric information from the Mapper with the optical properties defined by `vtkProperty` to complete the visualization of discrete points in `vtkRenderer`.
[0061] For dose data in medical data, taking boron neutron capture therapy (BNCT) as an example, the dose field output by Monte Carlo (MC) simulation is the core physical result for evaluating BNCT treatment plans. The visualization system needs to display four dose components (boron dose, nitrogen dose, hydrogen dose, and gamma dose) and their biologically weighted doses. To accurately verify treatment efficacy and protect critical organs, the visualization system must support multi-modal, high-precision rendering of dose data.
[0062] Total dose generated by BNCT Decomposition and biological weighting are necessary to accurately assess its effects. Physical dose It consists of four core parts:
[0063] Boron dosage From¹ 0 B(n,α) 7 Li reaction is the main component of high LET treatment; proton backflushing dose Neutron recoil dose Elastic scattering from neutrons and the nuclei of atoms in the tissue; while gamma-ray dose Primarily derived from ¹H(n,γ) 2 Secondary radiation produced by the D reaction.
[0064] Final bioeffective dose It was calculated by applying space-dependent relative bioavailability (RBE) and compound bioavailability (CBE):
[0065] The visualization system provided in this embodiment supports [the following]. any component or Rendering is then performed. For the aforementioned multi-component biological weighted dose data, this invention supports configuring pseudo-color mappings separately for each dose component through a color transfer function in the rendering strategy, enabling the visualization of multi-channel dose fields. The system supports distinguishing the numerical magnitude of different doses using a vtkLookupTable or the color transfer function, drawing different colors accordingly. Dose visualization is presented in three core modes: dose lines (Isolines), dose bands (Dosimetry Bands), and dose cloud (ColorWash). Simultaneously, the system also supports using different colors to distinguish and display the doses of different biological components, assisting physicists in collaboratively analyzing the spatial contributions of each component.
[0066] Dosage visualization modes are mainly divided into dose lines, dose bands, and dose clouds. Figure 3 The dose line rendering is based on a contour rendering strategy to accurately display the boundaries of the dose distribution. The visualization system extracts multiple contour lines from a preset list of dose values and intuitively presents the dose gradient through numerical-color mapping.
[0067] The visualization system extracts multiple contour lines from dose data based on a preset list of dose values, and assigns different colors to each line according to a value-color mapping relationship, thus obtaining the distribution boundaries of specific dose levels. vtkContourFilter is used to extract contour lines from image data, combined with vtkLookupTable for color mapping. The mathematical expression for contour line extraction is:
[0068] in, This is the specified isodose value. The color mapping formula is:
[0069] The following is a typical mapping example, where the color will gradually change from blue to red as the dose increases:
[0070] This strategy is primarily used for rendering equivalent geometric boundaries in a dose field. The corresponding VTK pipeline for this strategy is as follows: Figure 9 As shown, the vtkContourFilter, acting as the core processor, performs isomorphic extraction on the resampled data or the original 3D dose field, and outputs the isomorphic geometry as vtkPolyData (line or triangular mesh data). vtkPolyData contains the geometric topology information of the isomorphic boundaries. The vtkContourFilter is dimension-adaptive: it uses the Marching Cubes algorithm for 3D data and the Marching Squares algorithm for 2D data; its 3D processing principle is consistent with the surface rendering strategy.
[0071] The final isodose line rendering result is as follows Figure 10 As shown, Figure 10 (a) is a mapping table between dose thresholds and display colors during dose rendering. The rendering strategy extracts contour lines from the dose data based on this mapping table and assigns corresponding colors to the dose lines within a specified interval. Figure 10 (be) shows the rendering effect of the dose lines in each window, allowing doctors or physicists to visually see the dose distribution in 3D views and 2D profiles.
[0072] This system achieves color display of the dose field in 2D and 3D views by reusing existing slice rendering and volume rendering strategies. Specifically, both dose bands and dose contour maps are implemented in the 2D rendering scene controller using the slice rendering strategy, the difference being the type of color mapping: dose bands use numerically discrete color mapping, mapping dose values to step-like color bands through a customized vtkLookupTable; while dose contour maps use numerically continuous color mapping, mapping dose value ranges to 255 RGB channels to achieve continuous gradient color rendering. In the 3D rendering scene controller, dose contour maps are implemented using the volume rendering strategy, the core of which is adjusting the opacity transfer function vtkPiecewiseFunction and the color transfer function vtkColorTransferFunction to achieve semi-transparent overlay of the dose contour map while ensuring the visibility of the background anatomical structure.
[0073] Figure 11 The rendering effects of dose bands and dose contour maps are demonstrated. Dose bands allow defining the color of dose thresholds in a dose threshold table, while dose contour maps are automatically generated color maps without user customization. All three dose representations can be applied in both 2D and 3D windows. Dose lines transform specific dose values into geometric boundaries, serving precise geometric conformity and quantitative indicator verification; dose bands provide rapid qualitative segmentation and dose gradient review within a region through numerically discrete color mapping; and dose contour maps, through continuous color and transparency overlays, display the continuous gradient and complex relationship between the dose field and anatomical structures in space, making them the best tool for overall qualitative assessment.
[0074] The visualization system provided in this embodiment can be integrated into the BNCT treatment planning system (BNCT-TPS) to visualize boron neutron capture therapy data. The boron neutron capture therapy data includes at least one of the following: medical imaging data; multi-component dose distribution data; patient fixation device geometric model data; collimator geometric model data; target area contour data; organ at risk contour data; beam direction data; and conformity data.
[0075] The visualization system provided in this embodiment features a highly flexible rendering architecture, capable of supporting all key visualization modes required for BNCT treatment planning, including multiplanar reconstruction of medical images, high-resolution structural surface rendering, and collimator and dose distribution display. This ensures that the system can accurately and efficiently process all data types unique to BNCT, including high-resolution volume data, complex geometric model data, and complex dose assessment results, providing a customized visualization foundation for the clinical application of BNCT.
[0076] In some optional embodiments, the rendering scene controller module is also used to manage at least one of coordinate system alignment, layer blending, and depth occlusion to achieve transparent overlay and spatial visualization of at least some medical data. For example, when the visualization system provided in this embodiment is applied to the visualization of boron neutron capture therapy data, transparent overlay and spatial relationship visualization of dose contour lines and equipment (patient fixation device or collimator) models can be achieved.
[0077] The visualization system provided in this embodiment integrates precise coordinate system transformation and image registration functions, which are crucial for ensuring high geometric accuracy during BNCT treatment. By establishing a unified software implementation standard, this visualization system can provide a stable and reliable engineered visualization solution for BNCT treatment planning systems.
[0078] In summary, the visualization system provided in this embodiment achieves deep decoupling between underlying medical data entities and high-level rendering algorithms and display context by constructing an abstract rendering data interface layer, a rendering strategy configuration layer, and a multi-dimensional scene control layer. Through the standardized encapsulation of heterogeneous medical data by the rendering object module and the dynamic matching of specific medical physics rendering algorithm pipelines by the rendering strategy module, the system can fuse and display various heterogeneous data, including anatomical images, multi-component physical / biological dose distributions, and complex geometric models, in real time within a unified spatial coordinate system. This invention solves the technical problems of poor flexibility in switching between various types of data visualization and low rendering efficiency in complex medical scenarios, significantly improving the intuitiveness and accuracy of clinical radiotherapy planning evaluation.
[0079] According to an embodiment of the present invention, a method for visualizing medical data is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0080] This embodiment provides a method for visualizing medical data, which can be used in any of the visualization systems described in the above embodiments. Figure 12 This is a flowchart of a medical data visualization method according to an embodiment of the present invention, such as... Figure 12 As shown, the process includes the following steps: Step S1201: Obtain multiple target medical data to be rendered.
[0081] The target medical data can be medical-related data, including imaging data, geometric model data, dosage data, etc.
[0082] Step S1202: Encapsulate the target medical data into rendering objects.
[0083] Step S1203: According to the target rendering strategy corresponding to each target medical data, select the corresponding target rendering scene controller from the pre-built multiple rendering scene controllers for rendering, and display it in the rendering window corresponding to the target rendering scene controller; The rendering strategy is a specific drawing algorithm.
[0084] The medical data visualization method provided in this embodiment can predefine and construct a variety of different rendering strategies. When rendering medical data to be rendered, the corresponding rendering strategy can be selected according to the rendering needs of the medical data, and the rendering can be carried out in the corresponding rendering scene controller. Ultimately, different types of medical data can be visualized.
[0085] Specifically, such as Figure 13 As shown, when implementing the visualization method provided in this embodiment using the visualization system provided in the above embodiments, a rendering scene controller of a specified type can be created according to actual needs and bound to the rendering window first. Then, medical data of the specified data type and its display attribute information are encapsulated into a rendering object. Finally, the rendering object is added to the rendering scene controller and rendering is performed using the specified rendering strategy.
[0086] This embodiment provides a method for visualizing medical data, which can be used in any of the visualization systems described in the above embodiments. The process includes the following steps: Step S1301: Obtain multiple target medical data to be rendered.
[0087] In some optional embodiments, the target medical data includes boron neutron capture therapy data.
[0088] In other words, the visualization method provided in this embodiment can be used to visualize boron neutron capture therapy (BNCT) data. Boron neutron capture therapy (BNCT) is a targeted binary radiotherapy technique. Its core mechanism involves selectively enriching boron-10-containing drugs in tumor tissue, followed by irradiation with a thermal neutron beam, causing boron-10 to capture neutrons and undergo ¹ 0 B(n,α) 7 The Li nucleus reaction produces high-energy-transfer (LET) alpha particles and lithium-7 recoil nuclei, enabling precise killing of tumor cells while maximally protecting normal tissues. The BNCT Treatment Planning System (BNCT-TPS) is the core software platform supporting the clinical application of boron neutron capture therapy (BNCT-TPS). Its medical data visualization module, as the primary human-computer interface, directly impacts the efficiency and final quality of treatment plan development due to its functional completeness, rendering performance, and ease of use. The visualization system provided in the above embodiment can serve as the medical data visualization module within the BNCT-TPS, utilizing the visualization method provided in this embodiment to visualize boron neutron capture therapy data. This allows physicians or physicists to efficiently complete all plan evaluation work within a single system without relying on external tools. Specifically, the visualization method provided in this embodiment directly serves the complex treatment plan optimization process of BNCT by accurately presenting various boron neutron capture therapy data (such as target area structure data, normal tissue structure data, and neutron-dose distribution data of BNCT). The visualization function supports doctors to conduct multi-dimensional dose assessment, effectively assists in optimizing target conformity and protection of organs at risk, significantly improves the efficiency of clinical assessment, shortens the complex review time of BNCT plans, and improves the efficiency of treatment delivery.
[0089] In some optional embodiments, the boron neutron capture therapy data includes at least one of the following: medical imaging data; multi-component dose distribution data; patient fixation device geometric model data; collimator geometric model data; target area contour data; organ at risk contour data; beam direction data; conformity data.
[0090] Specifically, BNCT treatment planning begins with precise geometric modeling of the patient's anatomy. Medical imaging data provides the macroscopic tissue density distribution needed to calculate neutron transport and dose attenuation, forming the basis of BNCT treatment. Medical imaging data relevant to boron neutron capture therapy includes various types, such as: computed tomography (CT) images, magnetic resonance imaging (MRI) data, and fluorine-18 labeled boron phenylalanine positron emission tomography (¹). 8 F-BPA PET image data, etc. For the rendering strategy of the image data, please refer to the above visualization system embodiment; it will not be repeated here.
[0091] Structural data, including patient fixation device geometry, collimator geometry, target area contour, and organ-at-risk contour, plays a central role in defining geometric partitions and external physical constraints in BNCT treatment planning. Regions of interest (ROI) data, such as target area and organ-at-risk contour data, are used in Monte Carlo simulations to classify tissue types and assign precise boron concentrations. Collimator geometry (i.e., neutron beam collimator model) data is used to define the external geometric constraints of the radiation field. Additionally, structural data includes points of interest (POIs), which serve as key reference markers. The rendering strategy for structural data is detailed in the visualization system example described above and will not be repeated here.
[0092] Doses associated with boron neutron capture therapy include boron dose, nitrogen dose, hydrogen dose, gamma dose, total physical dose, and bioweighted dose. A key step in the boron neutron capture therapy planning process is assessing the core physical output of the neutron transport equation—the dose field; therefore, visualization of multi-component dose distribution data is also necessary.
[0093] Step S1302: Encapsulate the target medical data into rendering objects.
[0094] Step S1303: Select the corresponding target rendering scene controller from the pre-built multiple rendering scene controllers, render the target medical data according to the target rendering strategy corresponding to each target medical data, and display it in the rendering window corresponding to the target rendering scene controller; wherein, the target rendering strategy is a specific drawing algorithm.
[0095] This embodiment provides a high-performance, highly available medical data visualization solution for BNCT application scenarios, which can improve the efficiency and accuracy of BNCT treatment planning.
[0096] In some optional implementations, before step S1303, that is, before selecting the corresponding target rendering scene controller from a plurality of pre-built rendering scene controllers and rendering the target medical data according to the target rendering strategy corresponding to each target medical data, the method further includes: Step 1: Obtain information on the presentation method of the target medical data, or obtain information on the presentation method of the data type to which the target medical data belongs.
[0097] Regarding the presentation method, the image data can be presented in ways such as cross-sectional view, coronal view, 3D view, etc., while the dose data can be presented in ways such as dose lines, dose bands, etc.
[0098] Step 2: Based on the presentation method information, select the corresponding target rendering strategy. Subsequently, this strategy will be used to render the target medical data. Here, the visualization system can select a suitable rendering strategy based on the presentation method.
[0099] The aforementioned presentation method can be user-specified, meaning the user can choose the presentation method for the target medical data as needed, or specify a particular presentation method for a certain type of medical data. Specifically, the user can select this through the interface at the application layer. Additionally, the user can also switch the presentation method (e.g., from dose lines to dose bands) at the application layer through the interface to perceive changes in the rendering effect.
[0100] In some optional implementations, the rendering windows corresponding to multiple target medical data are in the same viewport.
[0101] In this embodiment, multiple different target medical data can be fused and presented with high precision within the same viewport. These different target medical data can have different resolutions, sources, and data structures. This means that integrated display of multi-source heterogeneous data can be achieved.
[0102] When the visualization method provided in this embodiment is applied to a BNCT scene, anatomical images (CT / MRI), multi-component dose distributions (such as boron dose, total physical dose, biological weighted dose, etc.), and geometric models such as collimators can be fused and presented with high precision in the same viewport.
[0103] In some optional implementations, step S1302, namely encapsulating the target medical data into rendering objects, includes: The display attribute information corresponding to the target medical data and the target medical data are encapsulated into the rendering object; the visualization attributes include at least one of the following: color, transparency, visibility, pseudo-color mapping parameters, and transformation matrix; Step S1303, namely, selecting the corresponding target rendering scene controller from a plurality of pre-built rendering scene controllers and rendering the target medical data according to the target rendering strategy corresponding to each target medical data, includes: Using the target rendering scene controller and the target rendering strategy, the target medical data is rendered according to the display attribute information.
[0104] The visualization method provided in this embodiment enables fine-grained control over the attributes of rendered elements, ensuring the accuracy and reliability of medical data display.
[0105] In some optional implementations, the rendering strategy includes at least one of the following: aspect rendering strategy, volume rendering strategy, surface rendering strategy, contour rendering strategy, point cloud rendering strategy, graphics rendering strategy, and text rendering strategy. The section rendering strategy is used to generate multi-plane reconstructed sections of medical images; Volume rendering strategies are used to reconstruct and visualize 3D volume data through 3D texture mapping or ray casting algorithms; Surface rendering is used to render structural data and reconstruct geometric surfaces; Contour rendering strategy, used to draw isodose data; Point cloud rendering strategy, used to draw point data; Graphics rendering strategies are used to draw two-dimensional graphics; Text rendering strategy, used to render text data.
[0106] The rendering strategy provided in this embodiment is described in the above visualization system embodiment, and will not be repeated here.
[0107] This embodiment also provides a medical data visualization device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0108] This embodiment provides a device for visualizing medical data, such as... Figure 14 As shown, it includes: The data acquisition module 1401 is used to acquire multiple target medical data to be rendered; Encapsulation module 1402 is used to encapsulate the target medical data into rendering objects respectively; The rendering module 1403 is used to select the corresponding target rendering scene controller from a plurality of pre-built rendering scene controllers, render the target medical data according to the target rendering strategy corresponding to each target medical data, and display it in the rendering window corresponding to the target rendering scene controller; The target rendering strategy is a specific drawing algorithm.
[0109] The medical data visualization device provided in this embodiment of the invention can execute the medical data visualization method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.
[0110] Figure 15 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.
[0111] The following is a detailed reference. Figure 15 This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 1501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1502 or a program loaded from memory 1508 into random access memory (RAM) 1503. The RAM 1503 also stores various programs and data required for the operation of the electronic device. The processor 1501, ROM 1502, and RAM 1503 are interconnected via a bus 1504. An input / output (I / O) interface 1505 is also connected to the bus 1504.
[0112] Typically, the following devices can be connected to I / O interface 1505: input devices 1506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 1508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1509. Communication device 1509 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 15 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.
[0113] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 1509, or installed from a memory 1508, or installed from a ROM 1502. When the computer program is executed by the processor 1501, it performs the functions defined in the medical data visualization method of the embodiments of the present invention.
[0114] Figure 15 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.
[0115] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium may also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the method for visualizing medical data shown in the above embodiments is implemented.
[0116] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.
[0117] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A medical data visualization system, characterized in that, include: Rendering object module, rendering scene controller module, and rendering strategy module; The rendering object module is used to acquire multiple medical data to be rendered and encapsulate them respectively to obtain multiple rendering objects; The rendering strategy module is used to predefine multiple rendering strategies, with each rendering strategy corresponding to a specific rendering algorithm. The rendering scene controller module is used to manage one or more rendering scene controllers, which are used to render the rendering object using the corresponding rendering strategy.
2. The visualization system according to claim 1, characterized in that, The rendering strategy module is also used to define one or more of the rendering strategies; And / or, The multiple medical data sets to be rendered differ in at least one of the following: resolution, source, and data structure.
3. The visualization system according to claim 1, characterized in that, The rendering scene controller module is also used to manage at least one of coordinate system alignment, layer blending, and depth occlusion to achieve transparent overlay and spatial visualization of at least a portion of the medical data.
4. A method for visualizing medical data, characterized in that, The method, applied to the visualization system according to any one of claims 1-3, comprises: Acquire multiple target medical data to be rendered; The target medical data is encapsulated into rendering objects respectively; Select the corresponding target rendering scene controller from a plurality of pre-built rendering scene controllers, render the target medical data according to the target rendering strategy corresponding to each target medical data, and display it in the rendering window corresponding to the target rendering scene controller; The target rendering strategy is a specific drawing algorithm.
5. The method according to claim 4, characterized in that, Before selecting the corresponding target rendering scene controller from a plurality of pre-built rendering scene controllers and rendering the target medical data according to the target rendering strategy corresponding to each target medical data, the method further includes: Obtain the presentation method information of the target medical data, or obtain the presentation method information of the data type to which the target medical data belongs; Based on the presentation method information, select the corresponding target rendering strategy.
6. The method according to claim 4 or 5, characterized in that, The target medical data includes data on boron neutron capture therapy.
7. The method according to claim 6, characterized in that, The boron neutron capture therapy data includes at least one of the following: medical imaging data; multi-component dose distribution data; patient fixation device geometric model data; collimator geometric model data; target area contour data; organ at risk contour data; beam direction data; conformity data.
8. The method according to claim 4 or 5, characterized in that, The rendering windows corresponding to multiple target medical data are in the same viewport.
9. The method according to claim 4, characterized in that, The process of encapsulating the target medical data into rendering objects includes: The display attribute information corresponding to the target medical data and the target medical data are encapsulated into the rendering object; the display attribute information includes at least one of the following: color, transparency, visibility, pseudo-color mapping parameters, and transformation matrix; The step of selecting a corresponding target rendering scene controller from a plurality of pre-built rendering scene controllers and rendering the target medical data according to the target rendering strategy corresponding to each target medical data includes: Using the target rendering scene controller and the target rendering strategy, the target medical data is rendered according to the display attribute information.
10. The method according to claim 4 or 5, characterized in that, The rendering strategy includes at least one of the following: section rendering strategy, volume rendering strategy, surface rendering strategy, contour rendering strategy, point cloud rendering strategy, graphics rendering strategy, and text rendering strategy; The section rendering strategy is used to generate multi-plane reconstructed sections of medical images; Volume rendering strategies are used to reconstruct and visualize 3D volume data through 3D texture mapping or ray casting algorithms; Surface rendering is used to render structural data and reconstruct geometric surfaces; Contour rendering strategy, used to draw isodose data; Point cloud rendering strategy, used to draw point data; Graphics rendering strategies are used to draw two-dimensional graphics; Text rendering strategy, used to render text data.