A volume rendering method, apparatus, electronic device, and storage medium

Abstract

This invention discloses a volume rendering method, apparatus, electronic device, and storage medium. The method includes: acquiring scanned data of a target object; segmenting the scanned data into regions to obtain at least two segmented regions; determining region data information corresponding to each segmented region; determining region volume rendering data and region volume rendering parameters corresponding to each segmented region based on the region data information; performing volume rendering on the region volume rendering data using the region volume rendering parameters corresponding to each segmented region to obtain a region volume rendering result corresponding to the segmented region; and obtaining a target volume rendering result for the target object based on the region volume rendering results. By using corresponding volume rendering parameters for different regions, the volume rendering effect is improved.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a volume rendering method, apparatus, electronic device, and storage medium. Background Technology

[0002] Computed tomography (CT) technology first scans the object, then obtains tomographic data through reconstruction algorithms. To facilitate observation and judgment by medical staff, the data needs to be visualized. Visualizing body data reduces the workload of medical staff, allowing them to intuitively see the patient's entire body.

[0003] Traditional medical CT image visualization methods depict the target area by setting a set of fixed or finely adjustable volume rendering parameters. This results in inconsistent performance when reconstructing low-dose plain scans or images with high noise levels. Summary of the Invention

[0004] This invention provides a volume rendering method, apparatus, electronic device, and storage medium to improve the accuracy of volume rendering results.

[0005] According to one aspect of the present invention, a volume rendering method is provided, characterized in that it includes:

[0006] Acquire scanned data of the target object, segment the scanned data into regions to obtain at least two segmented regions, and determine the region data information corresponding to each segmented region.

[0007] Based on the region data information corresponding to each segmented region, determine the region volume drawing data and region volume drawing parameters corresponding to each segmented region.

[0008] For each segmented region, volume drawing is performed on the region volume drawing data using the region volume drawing parameters corresponding to the segmented region to obtain the region volume drawing result corresponding to the segmented region;

[0009] Based on the rendering results of each region, the rendering result of the target object is obtained.

[0010] According to another aspect of the present invention, a volume rendering apparatus is provided, characterized in that it comprises:

[0011] The region data information determination module is used to acquire scanned data of the target object, segment the scanned data into regions to obtain at least two segmented regions, and determine the region data information corresponding to each segmented region.

[0012] The region volume drawing information module is used to determine the region volume drawing data and region volume drawing parameters corresponding to each segmented region based on the region data information corresponding to each segmented region.

[0013] The region volume drawing module is used to perform volume drawing on the region volume drawing data for each segmented region using the region volume drawing parameters corresponding to the segmented region, so as to obtain the region volume drawing result corresponding to the segmented region.

[0014] The volume rendering result determination module is used to obtain the target volume rendering result of the target object based on the volume rendering results of each region.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the volume rendering method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the volume drawing method according to any embodiment of the present invention.

[0020] The technical solution of this invention involves acquiring scanned data of a target object, segmenting the scanned data to obtain at least two segmented regions, and determining the region data information corresponding to each segmented region. Based on the region data information corresponding to each segmented region, it determines the region volume rendering data and region volume rendering parameters corresponding to each segmented region. For each segmented region, it performs volume rendering on the region volume rendering data using the region volume rendering parameters corresponding to the segmented region to obtain the region volume rendering result corresponding to the segmented region. Based on the region volume rendering results, it obtains the target volume rendering result of the target object. By using corresponding volume rendering parameters for different regions, the volume rendering effect is improved.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

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

[0023] Figure 1 This is a flowchart illustrating a volume drawing method provided in an embodiment of the present invention;

[0024] Figure 2 This is a flowchart illustrating a volume drawing method provided in an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of a volume drawing device provided in an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1This is a schematic flowchart of a volume rendering method provided in an embodiment of the present invention. This embodiment is applicable to the case of volume rendering based on scanned images. The method can be executed by a volume rendering method device, which can be implemented in hardware and / or software. The volume rendering method device can be configured in the electronic equipment and / or computer products provided in the embodiment of the present invention.

[0031] like Figure 1 As shown, the method includes:

[0032] S110. Obtain the scanning data of the target object, perform regional segmentation on the scanning data to obtain at least two segmented regions, and determine the regional data information corresponding to each segmented region.

[0033] In this embodiment, in order to reconstruct good volume rendering results even for low-dose plain scans or images with a lot of noise, the image is divided into different parts, and corresponding volume rendering parameters are used for each part. This allows the volume rendering parameters to be applicable to the corresponding parts, resulting in good volume rendering results.

[0034] The scanned data of the target object can be obtained by scanning the target object using a computed tomography (CT) method. Optionally, the scanned data of the target object can be in DICOM format.

[0035] In this embodiment, the scanned data can be segmented using existing region segmentation methods to obtain at least two segmented regions. For example, region segmentation can be performed using methods such as threshold segmentation, region growing, region merging, and neural networks, and is not limited thereto.

[0036] Based on the above scheme, the scanned data is segmented to obtain at least two segmented regions, including:

[0037] The scanned data is input into a pre-trained deep learning segmentation model to obtain at least two segmented regions output by the deep learning segmentation model.

[0038] Optionally, a deep learning segmentation model can be pre-built. Training sample pairs are constructed based on historical scan data and corresponding segmentation regions. The pre-built deep learning segmentation model is then trained using these training sample pairs to obtain the trained deep learning segmentation model. When region segmentation is required, the scanned data is used as input to the deep learning segmentation model to obtain the segmented regions output by the model. The segmented regions output by the deep learning segmentation model may include segmentation region identifiers and region data information. Using a deep learning segmentation model for region segmentation results in more accurate segmented regions.

[0039] The deep learning segmentation model can be built based on existing neural networks. For example, the deep learning segmentation model can be built based on network structures such as convolutional neural networks, and there is no limitation here.

[0040] S120. Based on the region data information corresponding to each segmented region, determine the region volume drawing data and region volume drawing parameters corresponding to each segmented region.

[0041] In this embodiment, volume rendering is performed for each segmented region separately, and then the volume rendering results of each segmented region are combined to complete the volume rendering of the target object. During the volume rendering process for each segmented region, it is necessary to determine the region volume rendering data and region volume rendering parameters required for that segmented region. Adaptively adjusting the volume rendering parameters based on the region data characteristics of the segmented region can adapt to most DICOM datasets.

[0042] It should be noted that for each segmented region, the corresponding region data information has been obtained. Based on the region data information, the region volume drawing data and region volume drawing parameters required for volume drawing of the segmented region can be determined.

[0043] The data can be directly used as the region volume rendering data, or it can be processed based on the region data to obtain the region volume rendering data. It should be noted that different post-processing methods are required for different segmented regions to obtain the region volume rendering data for that segmented region. For example, for the nodule region, to preserve the nodule's burrs and texture features, the nodule mask is expanded by 2 dimensions and then multiplied by a voxel; other volume data is set to -1000. For the pleura region, to remove fragments inside and outside the pleura and obtain complete pleura surface information, the lung is expanded by 6 dimensions and lung erosion by 6 dimensions to obtain the pleura region, which is then multiplied by a voxel; the volume data outside the lung is set to -10000. For the vascular region, the blood vessel is multiplied by a voxel, and other volume data is set to -1000. For the region where the pleura intersects with the blood vessel, the volume data of the intersection of the pleura and the blood vessel is set back to the original voxel.

[0044] Region volume rendering parameters can include gradient opacity transfer functions, scalar opacity transfer functions, and color transfer functions. Understandably, different segmented regions may have different noise categories, leading to different region volume rendering parameters used during volume rendering. Therefore, the noise category can be determined based on the region data information of the segmented regions, and at least one of the gradient opacity transfer function, scalar opacity transfer function, and color transfer function can be determined based on the noise category, thereby determining the region volume rendering parameters.

[0045] In one embodiment of the present invention, determining the region volume drawing data and region volume drawing parameters corresponding to each of the segmented regions based on the region data information corresponding to each of the segmented regions includes:

[0046] The nodule region is cut into blocks to obtain the block region;

[0047] For each of the cut regions, based on the regional data information of each segmented region within the cut region, regional feature parameters of the set data features corresponding to each segmented region within the cut region are determined;

[0048] Based on the feature parameters of each region, the noise category of each segmented region is determined;

[0049] Based on the noise category of each segmented region, determine the region volume rendering data and region volume rendering parameters corresponding to each segmented region.

[0050] Optionally, the nodule region can be divided into blocks to obtain a region of a set size as the nodule region. Then, the set data features of the region can be statistically analyzed to obtain the region feature parameters corresponding to each set data feature. Then, the region feature parameters can be classified to distinguish the degree of noise and obtain the noise category of the segmented region. Finally, the region volume drawing data and region volume drawing parameters of the segmented region can be determined based on the noise category of the segmented region.

[0051] The defined data features include at least one of the following: mean, maximum, and minimum values. The segmented regions can be lung regions, nodule regions, and vascular regions. Therefore, the regional feature parameters of the defined data features for each segmented region include the mean, maximum, and minimum values ​​of the data for the nodule region, the mean, maximum, and minimum values ​​of the data for all regions within the lung, and the mean, maximum, and minimum values ​​of the data for the vascular region, resulting in the aforementioned nine data features.

[0052] Based on the above scheme, determining the noise category of each segmented region based on the feature parameters of each region includes:

[0053] The feature parameters of each region are normalized to obtain normalized feature parameters;

[0054] Clustering is performed on the normalized feature parameters to obtain the cluster category of each normalized feature parameter;

[0055] The noise category of the segmented region is determined based on the clustering category of each of the normalized feature parameters.

[0056] Optionally, clustering can be used to classify the regional feature parameters to obtain the noise category of the segmented region. Specifically, to ensure the unit consistency of the regional feature parameters of each segmented region, the regional feature parameters of each segmented region are first normalized to obtain normalized feature parameters. Then, a clustering algorithm is used for classification to obtain the noise category of the segmented region. Existing clustering algorithms can be used to classify the regional feature parameters, and there is no limitation here. For example, the K-Nearest Neighbor (KNN) algorithm can be used, which uses Euclidean distance to classify the regional feature parameters.

[0057] In one embodiment of the present invention, the segmented region is a blood vessel region, and the step of determining the region volume rendering data corresponding to the segmented region based on the noise category of the segmented region includes:

[0058] The growth range of the region is determined based on the noise category of the vascular region;

[0059] Based on the regional data information of the vascular region, regional growth is performed within the region growth range to obtain regional growth data;

[0060] Based on the region growth data, the region volume drawing data of the vascular region is determined.

[0061] To improve the rendering quality of blood vessel regions, data processing is performed on the region growth data of the blood vessel regions to obtain region volume rendering data, resulting in richer rendering effects. Optionally, region growth can be performed on the region growth data of the blood vessel regions using a combination of noise categories and voxel values ​​to obtain region volume rendering data for the blood vessel regions. The extent of the region growth is determined based on the noise category.

[0062] For example, the region growth range can be determined first based on the noise category, and then region growth can be performed on the region growth data to obtain region growth data. Then, the region growth data can be dilated to obtain the region volume drawing data of the blood vessel region.

[0063] Optionally, determining the volumetric rendering data of the vascular region based on the region growth data includes:

[0064] Determine the midline of the growth data in the region, and dilate the midline by a set number of pixels to obtain the dilated midline;

[0065] The region volume drawing data of the vascular region is determined by combining the expansion midline and the region growth data.

[0066] The process of dilating the region growth data can be summarized as follows: determine the midline of the region growth data, dilate the midline by two pixels, and then add the original data of the blood vessel region to obtain the region volume rendering data of the blood vessel region. Pixel dilation based on the midline makes the blood vessels drawn from the dilated data more consistent with the elongation characteristics of blood vessels, resulting in better rendering effects.

[0067] In some embodiments, determining the region volume rendering parameters corresponding to each segmented region based on the noise category of each segmented region includes:

[0068] Based on the noise category of each segmented region, determine the voxel value of the scalar opacity corresponding to each segmented region.

[0069] It is understandable that there is a strong correlation between the voxel value of scalar opacity and the color of volume rendering. Based on this, the voxel value of scalar opacity in the volume rendering parameters can be determined according to the noise category, resulting in richer colors in the volume rendering. For example, the voxel value of scalar opacity for the blood vessel region can be set to (n, n+50, m, m+1), (0, 0.92, 1, 0), where n and m depend on...

[0070] S130. For each segmented region, the volume drawing data of the region is drawn using the volume drawing parameters corresponding to the segmented region to obtain the volume drawing result of the region corresponding to the segmented region.

[0071] After determining the volume rendering data and parameters for each segmented region, volume rendering is performed for each segmented region using the corresponding volume rendering data and parameters to obtain the volume rendering result for that segmented region.

[0072] In this process, existing volume rendering methods can be used to render the volume of each segmented region, and no specific volume rendering method is restricted here.

[0073] S140. Based on the rendering results of each region, the rendering result of the target object is obtained.

[0074] After obtaining the region volume rendering results for each segmented region, the region volume rendering results of each segmented region are combined based on the position information of each segmented region to obtain the target volume rendering result of the target object.

[0075] The technical solution of this embodiment involves acquiring scanned data of a target object, segmenting the scanned data to obtain at least two segmented regions, and determining the region data information corresponding to each segmented region. Based on the region data information corresponding to each segmented region, it determines the region volume rendering data and region volume rendering parameters corresponding to each segmented region. For each segmented region, it performs volume rendering on the region volume rendering data using the region volume rendering parameters corresponding to the segmented region to obtain the region volume rendering result corresponding to the segmented region. Based on the region volume rendering results, it obtains the target volume rendering result of the target object. By using corresponding volume rendering parameters for different regions, the volume rendering effect is improved.

[0076] Example 2

[0077] Figure 2 This is a schematic flowchart of a volume rendering method provided by an embodiment of the present invention. Based on the above embodiments, this embodiment provides a preferred embodiment. Figure 2 As shown, the method includes:

[0078] S210. Use a deep learning segmentation model for region segmentation.

[0079] Optionally, the res-unet deep learning segmentation model can be used to segment and obtain nodule masks, lung masks, and pulmonary vessel masks.

[0080] S220. Determine the regional characteristic parameters of each segmented region.

[0081] For example, the nodule region is divided into blocks to obtain an n*n*n region (e.g., n=6). Then, the density of this region (including the entire lung region, the nodule region, and the blood vessel region) is statistically analyzed to obtain the mean HU value of the nodule region, the mean HU value of the entire lung region, the mean HU value of the blood vessel region, as well as the maximum and minimum values ​​of each region, thus obtaining 9 data features of the DICOM.

[0082] S230. Determine the noise category for each segmented region.

[0083] Optionally, the nine data features of the DICOM can be normalized, and the KNN algorithm using Euclidean distance can be used to classify the DICOM into four categories to distinguish the degree of noise. Alternatively, regression methods or other classification models can be used to classify the regional data features and determine the noise category of the segmented region.

[0084] S240, Determine the region volume drawing data for the blood vessel area.

[0085] Optionally, region growing can be performed using a segmented mask combined with DICOM voxel values. The extent of the region growing is defined by the DICOM category. Then, the midline of the grown blood vessel is calculated, and the midline is expanded by two pixels. The original blood vessel is then added to obtain the region-grown blood vessel. The left image below shows the original segmented blood vessel, and the right image shows the extended blood vessel.

[0086] S250: Configure volume rendering parameters for blood vessels and pleura.

[0087] The volume rendering transfer functions include gradient opacity transfer functions, scalar opacity transfer functions, and color transfer functions. Different parameters are used to render different DICOM classes. The voxel values ​​for scalar opacity can be set to (n, n+50, m, m+1) or (0, 0.92, 1, 0), where n and m depend on the DICOM class.

[0088] S260. Configure the volume drawing parameters for the nodules.

[0089] The voxel value of the scalar opacity can be set to (n+x,n+x+50,m,m+1) or (0,0.9,0.9,0), where n and m depend on the dicom category and x depends on the type of nodule (ground-glass nodule, solid nodule).

[0090] S270. Post-process body data using masks of nodules, blood vessels, and pleura.

[0091] Optionally, post-processing of the volume data may include: 1) To preserve the burrs and texture features of the nodules, the nodule mask is expanded by 2 dimensions and then multiplied with voxels; other volume data is set to -1000. 2) To remove fragments inside and outside the pleura and obtain complete pleural surface information, the lung is expanded by 6 dimensions and the lung erosion by 6 dimensions is subtracted to obtain the pleural region; then multiplied with voxels; volume data outside the lung is set to -10000. 3) Blood vessels are multiplied with voxels; other volume data is set to -1000. 4) Volume data where the pleura intersects with blood vessels is set back to the original voxels.

[0092] S280. Use the post-processed volume data to perform volume drawing.

[0093] Optionally, the target area can be drawn using the processed volume data and the ray projection-based volume rendering method provided by VTK to obtain the volume rendering result.

[0094] The volume rendering method provided in this invention combines deep learning segmentation mask and uses a multi-voxel rendering scheme, which improves the volume rendering effect and can clearly display the relationship between nodules, pleura and blood vessels. It is applicable to low-dose plain scans and noisy DICOM scans.

[0095] Example 3

[0096] Figure 3 This is a schematic diagram of the structure of a volume rendering device provided in an embodiment of the present invention. Figure 3 As shown, the device includes:

[0097] The region data information determination module 310 is used to acquire scanned data of the target object, perform region segmentation on the scanned data to obtain at least two segmented regions, and determine the region data information corresponding to each segmented region.

[0098] The region volume drawing information module 320 is used to determine the region volume drawing data and region volume drawing parameters corresponding to each segmented region based on the region data information corresponding to each segmented region.

[0099] The region volume drawing module 330 is used to perform volume drawing on the region volume drawing data for each segmented region using the region volume drawing parameters corresponding to the segmented region, so as to obtain the region volume drawing result corresponding to the segmented region.

[0100] The volume rendering result determination module 340 is used to obtain the target volume rendering result of the target object based on the volume rendering results of each region.

[0101] The technical solution of this embodiment involves acquiring scanned data of a target object, segmenting the scanned data to obtain at least two segmented regions, and determining the region data information corresponding to each segmented region. Based on the region data information corresponding to each segmented region, it determines the region volume rendering data and region volume rendering parameters corresponding to each segmented region. For each segmented region, it performs volume rendering on the region volume rendering data using the region volume rendering parameters corresponding to the segmented region to obtain the region volume rendering result corresponding to the segmented region. Based on the region volume rendering results, it obtains the target volume rendering result of the target object. By using corresponding volume rendering parameters for different regions, the volume rendering effect is improved.

[0102] Optionally, based on the above scheme, the region volume drawing information module 320 is specifically used for:

[0103] The nodule region is cut into blocks to obtain the block region;

[0104] For each of the cut regions, based on the regional data information of each segmented region within the cut region, regional feature parameters of the set data features corresponding to each segmented region within the cut region are determined;

[0105] Based on the feature parameters of each region, the noise category of each segmented region is determined;

[0106] Based on the noise category of each segmented region, determine the region volume rendering data and region volume rendering parameters corresponding to each segmented region.

[0107] Optionally, based on the above scheme, the region volume drawing information module 320 is specifically used for:

[0108] The feature parameters of each region are normalized to obtain normalized feature parameters;

[0109] Clustering is performed on the normalized feature parameters to obtain the cluster category of each normalized feature parameter;

[0110] The noise category of the segmented region is determined based on the clustering category of each of the normalized feature parameters.

[0111] Optionally, based on the above scheme, the region volume drawing information module 320 is specifically used for:

[0112] The growth range of the region is determined based on the noise category of the vascular region;

[0113] Based on the regional data information of the vascular region, regional growth is performed within the region growth range to obtain regional growth data;

[0114] Based on the region growth data, the region volume drawing data of the vascular region is determined.

[0115] Optionally, based on the above scheme, the region volume drawing information module 320 is specifically used for:

[0116] Determine the midline of the growth data in the region, and dilate the midline by a set number of pixels to obtain the dilated midline;

[0117] The region volume drawing data of the vascular region is determined by combining the expansion midline and the region growth data.

[0118] Optionally, based on the above scheme, the region volume drawing information module 320 is specifically used for:

[0119] Based on the noise category of each segmented region, determine the voxel value of the scalar opacity corresponding to each segmented region.

[0120] Optionally, based on the above scheme, the regional data information determination module 310 is specifically used for:

[0121] The scanned data is input into a pre-trained deep learning segmentation model to obtain at least two segmented regions output by the deep learning segmentation model.

[0122] The volume rendering apparatus provided in this embodiment of the invention can execute the volume rendering method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0123] Example 4

[0124] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0125] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0126] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0127] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as volume rendering methods.

[0128] In some embodiments, the volume drawing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the volume drawing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the volume drawing method by any other suitable means (e.g., by means of firmware).

[0129] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0130] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0131] Example 5

[0132] This invention provides a computer-readable storage medium storing computer instructions for causing a processor to execute a method for drawing an object, the method comprising:

[0133] Acquire scanned data of the target object, segment the scanned data into regions to obtain at least two segmented regions, and determine the region data information corresponding to each segmented region.

[0134] Based on the region data information corresponding to each segmented region, determine the region volume drawing data and region volume drawing parameters corresponding to each segmented region.

[0135] For each segmented region, volume drawing is performed on the region volume drawing data using the region volume drawing parameters corresponding to the segmented region to obtain the region volume drawing result corresponding to the segmented region;

[0136] Based on the rendering results of each region, the rendering result of the target object is obtained.

[0137] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0138] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0139] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0140] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0141] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the volume rendering method according to any embodiment of the invention.

[0142] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0143] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A volume rendering method, characterized in that, include: Acquire scanned data of the target object, segment the scanned data into regions to obtain at least two segmented regions, and determine the region data information corresponding to each segmented region. Based on the region data information corresponding to each segmented region, determine the region volume drawing data and region volume drawing parameters corresponding to each segmented region. For each segmented region, volume drawing is performed on the region volume drawing data using the region volume drawing parameters corresponding to the segmented region to obtain the region volume drawing result corresponding to the segmented region; Based on the rendering results of each region, the rendering result of the target object is obtained; The step of determining the region volume drawing data and region volume drawing parameters corresponding to each segmented region based on the region data information corresponding to each segmented region includes: The nodule region is cut into blocks to obtain the block region; For each of the cut regions, based on the regional data information of each segmented region within the cut region, regional feature parameters of the set data features corresponding to each segmented region within the cut region are determined; Based on the feature parameters of each region, the noise category of each segmented region is determined; Based on the noise category of each segmented region, determine the region volume drawing data and region volume drawing parameters corresponding to each segmented region; The step of determining the noise category of each segmented region based on the feature parameters of each region includes: The region feature parameters are normalized to obtain normalized feature parameters; wherein, the region feature parameters are DICOM data features; Clustering is performed on the normalized feature parameters to obtain the cluster category of each normalized feature parameter; The noise category of the segmented region is determined based on the clustering category of each of the normalized feature parameters.

2. The method according to claim 1, characterized in that, The segmented region is a blood vessel region. The step of determining the corresponding region volume rendering data based on the noise category of the segmented region includes: The growth range of the region is determined based on the noise category of the vascular region; Based on the regional data information of the vascular region, regional growth is performed within the region growth range to obtain regional growth data; Based on the region growth data, the region volume drawing data of the vascular region is determined.

3. The method according to claim 2, characterized in that, The process of determining the volumetric rendering data of the vascular region based on the region growth data includes: Determine the midline of the growth data in the region, and dilate the midline by a set number of pixels to obtain the dilated midline; The region volume drawing data of the vascular region is determined by combining the expansion midline and the region growth data.

4. The method according to claim 1, characterized in that, Based on the noise category of each segmented region, determine the region volume rendering parameters corresponding to each segmented region, including: Based on the noise category of each segmented region, determine the voxel value of the scalar opacity corresponding to each segmented region.

5. The method according to claim 1, characterized in that, The scanning and acquisition data is segmented to obtain at least two segmented regions, including: The scanned data is input into a pre-trained deep learning segmentation model to obtain at least two segmented regions output by the deep learning segmentation model.

6. A volume drawing device, characterized in that, include: The region data information determination module is used to acquire scanned data of the target object, segment the scanned data into regions to obtain at least two segmented regions, and determine the region data information corresponding to each segmented region. The region volume drawing information module is used to determine the region volume drawing data and region volume drawing parameters corresponding to each segmented region based on the region data information corresponding to each segmented region. The region volume drawing module is used to perform volume drawing on the region volume drawing data for each segmented region using the region volume drawing parameters corresponding to the segmented region, so as to obtain the region volume drawing result corresponding to the segmented region. The volume rendering result determination module is used to obtain the target volume rendering result of the target object based on the volume rendering results of each region; The region volume drawing information module is specifically used for: cutting the nodule region into blocks to obtain block regions; for each block region, determining the region feature parameters of the set data features corresponding to each segmented region within the block region based on the region data information of each segmented region within the block region; determining the noise category of each segmented region based on the region feature parameters; and determining the region volume drawing data and region volume drawing parameters corresponding to each segmented region according to the noise category of each segmented region. The region volume rendering information module is specifically used for: normalizing each region feature parameter to obtain normalized feature parameters; wherein, the region feature parameters are DICOM data features; clustering the normalized feature parameters to obtain the clustering category of each normalized feature parameter; and determining the noise category of the segmented region based on the clustering category of each normalized feature parameter.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the volume drawing method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the volume drawing method according to any one of claims 1-5.

Images