WO2020168698A1 - 基于VRDS 4D医学影像的静脉的Ai内镜分析方法及产品 - Google Patents

基于VRDS 4D医学影像的静脉的Ai内镜分析方法及产品 Download PDF

Info

Publication number
WO2020168698A1
WO2020168698A1 PCT/CN2019/101160 CN2019101160W WO2020168698A1 WO 2020168698 A1 WO2020168698 A1 WO 2020168698A1 CN 2019101160 W CN2019101160 W CN 2019101160W WO 2020168698 A1 WO2020168698 A1 WO 2020168698A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
target
data set
medical image
vein
Prior art date
Application number
PCT/CN2019/101160
Other languages
English (en)
French (fr)
Inventor
李斯图尔特平
李戴维伟
Original Assignee
未艾医疗技术(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 未艾医疗技术(深圳)有限公司 filed Critical 未艾医疗技术(深圳)有限公司
Priority to US17/432,483 priority Critical patent/US20220148162A1/en
Priority to AU2019430369A priority patent/AU2019430369B2/en
Priority to EP19916348.6A priority patent/EP3929869A4/en
Publication of WO2020168698A1 publication Critical patent/WO2020168698A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10068—Endoscopic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10076—4D tomography; Time-sequential 3D tomography
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10088—Magnetic resonance imaging [MRI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10104—Positron emission tomography [PET]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30056—Liver; Hepatic
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30084—Kidney; Renal
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30101—Blood vessel; Artery; Vein; Vascular
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30244—Camera pose

Definitions

  • This application relates to the technical field of medical imaging devices, in particular to an Ai endoscopic analysis method and product of veins based on VRDS 4D medical images.
  • CT Computed Tomography
  • MRI Magnetic Resonance Imaging
  • DTI Diffusion Tensor Imaging
  • Positron Emission Computed Tomography Computed Tomography
  • PET Magnetic Resonance Imaging
  • PET Positron Emission Computed Tomography
  • the embodiments of this application provide an Ai endoscopic analysis method and product for veins based on VRDS 4D medical images, which can display vascular structures without intravenous injection of contrast agent, without ionizing radiation and wounds; economical and convenient, reducing the technical level of the operator Dependence, enhance repeatability.
  • an embodiment of the present application provides an Ai endoscopic analysis method of veins based on VRDS 4D medical images, which is applied to a medical imaging device; the method includes:
  • the first medical image data including the original data set of the target vein, the original data set of the partial arteries, the data set of the kidney, the hepatic portal
  • the original data set of the blood vessel of the target vein and the original data set of the partial arteries include the fusion data of the intersection position
  • the original data set of the blood vessel of the target vein is the surface of the target vein and the target
  • the original data set of the part of the artery is the transfer function result of the cube space of the part of the artery surface and the tissue structure inside the part of the artery
  • the data set of the kidney Is the transfer function result of the cube space of the tissue structure inside the kidney and the surface of the kidney
  • the data set of the hepatic hilum is the transfer function result of the cube space of the tissue structure inside the hepatic hilum surface and the hepatic hilum ;
  • the second medical image data including the segmentation data set of the target vein, the segmentation data set of the partial artery, the data set of the kidney, the The data set of the hepatic hilum, the first data of the segmented data set of the target vein and the second data of the segmented data set of the partial artery are independent of each other, and the first data and the second data are the intersection position The data;
  • the embodiments of the present application provide an Ai endoscopic analysis device for veins based on VRDS Ai 4D medical images, which is applied to medical imaging devices;
  • the Ai endoscopic analysis device for veins based on VRDS Ai 4D medical images includes processing Unit and communication unit, where,
  • the processing unit is configured to determine a bitmap BMP data source according to multiple scanned images of a target part of a target user, the target part including a target vein to be observed and arteries, kidneys, and hepatic portals associated with the target vein; And for generating first medical image data according to the BMP data source, the first medical image data including the original data set of the target vein, the original data set of the partial arteries, the data set of the kidney, and the The data set of the hepatic portal, the original data set of the blood vessels of the target vein and the original data set of the partial arteries include the fusion data of the intersection position, and the original data set of the blood vessels of the target vein is the surface of the target vein and
  • the transfer function result of the cube space of the tissue structure inside the target vein, the raw data set of the part of the artery is the transfer function result of the cube space of the part of the artery surface and the tissue structure inside the part of the artery, the kidney
  • the data set is the result of the transfer function of the
  • the second data is the data of the intersection position; and used to process the second medical image data to obtain target medical image data; and used to extract the target vein in the target medical image data; and used to pass
  • the communication unit performs 4D medical imaging according to the data set of the target vein to display the internal image of the target vein.
  • an embodiment of the present application provides a medical imaging device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured by the above Executed by a processor, the above-mentioned program includes instructions for executing steps in any method of the first aspect of the embodiments of the present application.
  • an embodiment of the present application provides a computer-readable storage medium, wherein the foregoing computer-readable storage medium stores a computer program for electronic data exchange, wherein the foregoing computer program enables a computer to execute In one aspect, some or all of the steps described in any method.
  • embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute For example, some or all of the steps described in any method of the first aspect.
  • the computer program product may be a software installation package.
  • the medical imaging device first determines the bitmap BMP data source according to multiple scanned images of the target part of the target user, and secondly, generates the first medical image data according to the BMP data source, and again, according to the first The medical image data generates the second medical image data.
  • the second medical image data is processed to obtain the target medical image data, and then the target vein data set in the target medical image data is extracted, and finally 4D medical imaging is performed according to the target vein data set for display The internal image of the target vein.
  • the target part includes the target vein to be observed and the arteries, kidneys, and hepatic portal associated with the target vein.
  • the first medical image data includes the original data set of the target vein, the original data set of some arteries, the data set of the kidney, and the hepatic portal.
  • the original data set of the blood vessel of the target vein and the original data set of the partial arteries include the fusion data of the cross position, and the original data set of the blood vessel of the target vein is the transmission of the cube space of the tissue structure of the target vein surface and the target vein Function result, the original data set of part of the artery is the result of the transfer function of the cube space of the tissue structure of the part of the artery surface and part of the artery, and the data set of the kidney is the result of the transfer function of the cube space of the tissue structure of the kidney surface and the internal structure of the kidney.
  • the data set of the portal is the result of the transfer function of the cube space of the hepatic portal surface and the internal tissue structure of the portal.
  • the second medical image data includes the segmented data set of the target vein, the segmented data set of part of the artery, the data set of the kidney, and the hepatic portal.
  • the first data of the target vein segmentation data collection and the second data of the partial artery segmentation data collection are independent of each other.
  • the first data and the second data are the data of the intersection position. It can be seen that the medical imaging device of this application passes Data preprocessing, separation, integration, and 4D medical imaging are beneficial to improve the accuracy and convenience of inferior vena cava imaging by medical imaging devices.
  • FIG. 1 is a schematic structural diagram of a medical image intelligent analysis and processing system based on VRDS Ai according to an embodiment of the present application;
  • FIG. 2 is a schematic flowchart of an Ai endoscopic analysis method of veins based on VRDS 4D medical images provided by an embodiment of the present application;
  • FIG. 3 is a schematic structural diagram of a medical imaging device provided by an embodiment of the present application.
  • FIG. 4 is a block diagram of functional units of an Ai endoscopic analysis device for veins based on VRDS Ai 4D medical images provided by an embodiment of the present application.
  • the medical imaging devices involved in the embodiments of this application refer to various instruments that use various media as information carriers to reproduce the internal structure of the human body as images.
  • the image information and the actual structure of the human body have spatial and temporal distributions.
  • DICOM data refers to the original image file data collected by medical equipment that reflects the internal structural characteristics of the human body. It can include electronic computed tomography CT, magnetic resonance MRI, diffusion tensor imaging DTI, and positron emission computed tomography PET-
  • image source refers to the Texture2D/3D image volume data generated by analyzing the original DICOM data.
  • VRDS refers to the Virtual Reality Doctor system (VRDS for short).
  • FIG. 1 is a schematic structural diagram of a VRDS Ai medical image intelligent analysis and processing system 100 based on an embodiment of the present application.
  • the system 100 includes a medical imaging device 110 and a network database 120.
  • the medical imaging device 110 may include The local medical imaging device 111 and/or the terminal medical imaging device 112, the local medical imaging device 111 or the terminal medical imaging device 112 are used to base on the original DICOM data, using the VRDS Ai 4D medical image presented in the embodiment of the present application.
  • the mirror analysis algorithm it performs the recognition, positioning and four-dimensional volume rendering of the human tumor area to realize the four-dimensional stereo imaging effect (the four-dimensional medical image specifically refers to the medical image including the internal spatial structure characteristics and external spatial structure characteristics of the displayed tissue.
  • the internal spatial structure feature means that the slice data inside the tissue has not been lost, that is, the medical imaging device can present the internal structure of target organs, blood vessels and other tissues.
  • the external spatial structure feature refers to the environmental characteristics between tissues, including tissues and tissues.
  • the spatial position characteristics including intersection, interval, fusion), etc., such as the edge structure characteristics of the intersection position between the kidney and the artery, etc.
  • the local medical imaging device 111 can also be used to compare the image relative to the terminal medical imaging device 112.
  • the source data is edited to form the transfer function result of the four-dimensional human body image.
  • the transfer function result can include the transfer function result of the surface of the internal organs and the tissue structure in the internal organs, and the transfer function result of the cube space, as required by the transfer function Cube edit box and arc edit array quantity, coordinates, color, transparency and other information.
  • the network database 120 may be, for example, a cloud server.
  • the network database 120 is used to store the image source generated by analyzing the original DICOM data and the transfer function result of the four-dimensional human body image edited by the local medical imaging device 111.
  • the image source may be from multiple sources.
  • a local medical imaging device 111 to realize interactive diagnosis of multiple doctors.
  • HMDS Head mounted Displays Set
  • the operating actions refer to the user’s actions through the medical imaging device.
  • An external intake device such as a mouse, keyboard, etc., controls the operation of the four-dimensional human body image to achieve human-computer interaction.
  • the operation action includes at least one of the following: (1) Change the color and/or of a specific organ/tissue Transparency, (2) positioning zoom view, (3) rotating view, realizing multi-view 360-degree observation of four-dimensional human body image, (4) "entering" human organs to observe internal structure, real-time clipping effect rendering, (5) moving up and down view.
  • FIG. 2 is a schematic flowchart of an Ai endoscopic analysis method for veins based on VRDS 4D medical imaging according to an embodiment of the present application, which is applied to the medical imaging device described in FIG. 1; as shown in the figure,
  • the Ai endoscopic analysis method of vein based on VRDS 4D medical image includes:
  • the medical imaging device determines a bitmap BMP data source according to multiple scanned images of a target part of a target user, the target part including a target vein to be observed and arteries, kidneys, and hepatic portals associated with the target vein;
  • BMP full name Bitmap
  • DDB device-dependent bitmap
  • DIB device-independent bitmap
  • the medical imaging device determines the bitmap BMP data source according to multiple scanned images of the target part of the target user, including: the medical imaging device obtains the data collected by the medical equipment and reflects the internal structural characteristics of the target user. Scan images; filter out at least one scan image containing the target part from the plurality of scan images, and use the at least one scan image as the medical digital imaging and communication DICOM data of the target user; parsing the DICOM
  • the data generates the image source of the target user, the image source includes texture 2D/3D image volume data; the first preset processing is performed on the image source to obtain the BMP data source, and the first preset processing includes at least the following One operation: VRDS limited contrast adaptive histogram equalization, mixed partial differential denoising, VRDS Ai elastic deformation processing.
  • DICOM Digital Imaging and Communications in Medicine
  • DICOM Digital Imaging and Communications in Medicine
  • the medical imaging device first acquires multiple scanned images that reflect the internal structural characteristics of the target user's human body, and can screen out at least one suitable scanned image that contains the target organ through sharpness and accuracy. Further processing is performed on the scanned image to obtain a bitmap BMP data source.
  • the medical imaging device can obtain a bitmap BMP data source after filtering, parsing, and first preset processing based on the acquired scanned image, which improves the accuracy and clarity of medical image imaging.
  • the VRDS limited contrast adaptive histogram equalization includes the following steps: regional noise ratio limiting, global contrast limiting; dividing the local histogram of the image source into multiple partitions, and for each partition, Determine the slope of the transformation function according to the slope of the cumulative histogram of the neighborhood of the partition, determine the degree of contrast magnification around the pixel value of the partition according to the gradient of the transformation function, and then perform a limited cropping process according to the degree of contrast magnification, Generate the distribution of the effective histogram, and also generate the value of the effective and usable neighborhood size, and evenly distribute the cropped part of the histogram to other areas of the histogram; the hybrid partial differential denoising includes the following steps: VRDS Ai curvature drive and VRDS Ai high-order hybrid denoising, making the curvature of the image edge less than the preset curvature, realizing a hybrid partial differential denoising model that can protect the edge of the image and avoid the step effect in the smoothing process; the VRDS Ai elastic
  • At least one image processing operation may be performed on the image source to obtain the BMP data source, including but not limited to: VRDS restricted contrast adaptive histogram equalization, hybrid partial differential denoising, VRDS Ai elastic deformation processing.
  • the hybrid partial differential denoising can use CDD and high-order denoising models to process the image source;
  • the CDD model (Curvature Driven Diffusions) model is based on the TV (Total Variation) model with the introduction of curvature drive and It solves the problem that the TV model cannot repair the visual connectivity of the image.
  • high-order denoising refers to denoising the image based on the partial differential equation (PDE) method.
  • the image source perform noise filtering according to the specified differential equation function change, thereby filtering out the noise in the image source, and the solution of the partial differential equation is the BMP data source obtained after denoising
  • the PDE-based image denoising method has the characteristics of anisotropic diffusion, so it can perform different degrees of diffusion in different regions of the image source, thereby achieving the effect of suppressing noise while protecting the edge texture information of the image.
  • the medical imaging device uses at least one of the following image processing operations: VRDS limited contrast adaptive histogram equalization, hybrid partial differential denoising, VRDS Ai elastic deformation processing, which improves the execution efficiency of image processing, and Improve the image quality and protect the edge texture of the image.
  • the medical imaging device generates first medical image data according to the BMP data source, where the first medical image data includes a raw data set of the target vein, a raw data set of the partial arteries, and the kidney
  • the data set, the data set of the hepatic hilum, the raw data set of the blood vessels of the target vein and the raw data set of the partial arteries include the fusion data of the intersection position, and the raw data set of the blood vessels of the target vein is the
  • the transfer function result of the cube space of the target vein surface and the tissue structure inside the target vein, and the original data set of the part of the artery is the transfer function result of the cube space of the part of the artery surface and the tissue structure inside the part of the artery
  • the data set of the kidney is the result of the transfer function of the cube space of the tissue structure inside the kidney and the surface of the kidney
  • the data set of the hepatic hilum is the tissue structure of the hepatic hilum surface and the internal hepatic hilum
  • the medical imaging device generates first medical image data according to the BMP data source, including: the medical imaging device imports the BMP data source into a preset VRDS medical network model, and uses the VRDS medical network
  • the model calls each transfer function in the pre-stored transfer function set, processes the BMP data source through multiple transfer functions in the transfer function set, and obtains the first medical image data
  • the transfer function set includes reverse editing
  • the transfer function of the target vein, the transfer function of the artery, the transfer function of the kidney and the transfer function of the hepatic portal are preset by the device.
  • the VRDS medical network model is a preset network model, and its training method includes the following three steps: image sampling and scale scaling; 3D convolutional neural network feature extraction and scoring; medical imaging device evaluation and network training.
  • sampling is required to obtain N BMP data sources, and then M BMP data sources are extracted from N BMP data sources at a preset interval. It needs to be explained that the preset interval can be flexibly set according to the usage scenario.
  • Sample M from N then scale the sampled M BMP data sources to a fixed size (for example, the length is S pixels and the width is S pixels), and the resulting processing result is used as the input of the 3D convolutional neural network .
  • M BMP data sources are used as the input of the 3D convolutional neural network.
  • a 3D convolutional neural network is used to perform 3D convolution processing on the BMP data source to obtain a feature map.
  • the medical imaging device can obtain the first medical image data based on the preset VRDS medical network model and the BMP data source, which improves the accuracy and convenience of obtaining the first medical image data.
  • the medical imaging device generates second medical image data according to the first medical image data, where the second medical image data includes a segmentation data set of the target vein, a segmentation data set of the partial artery, and the The kidney data set, the hepatic hilum data set, the first data of the target vein segmentation data set and the second data of the partial artery segmentation data set are independent of each other, and the first data and the first data set are independent of each other.
  • the second data is the data of the intersection position;
  • the medical imaging device generating second medical image data according to the first medical image data includes: the medical imaging device collects the raw data of the target vein in the first medical image data, The original data set of the partial arteries is imported into the cross blood vessel network model, and the fused data at the cross position is spatially divided through the cross blood vessel network model to obtain the first data and the second data; Generating a segmented data set of the target vein from the original data set of the target vein and the first data, and generating a segmented data set of the partial artery according to the original data set of the partial artery and the second data; and The segmentation data set of the target vein, the segmentation data set of the partial artery, the data set of the kidney, and the data set of the hepatic hilum are used to obtain the second medical image data.
  • the cross blood vessel network model is a trained neural network model.
  • the medical imaging device can obtain second medical image data based on the cross-vessel network model and the first medical image data, which improves the accuracy and convenience of obtaining the second medical image data.
  • the medical imaging device processes the second medical image data to obtain target medical image data
  • processing the second medical image data by the medical imaging device to obtain target medical image data includes: the medical imaging device performs at least one of the following processing operations on the second medical image data to obtain the target medical image data : 2D boundary optimization processing, 3D boundary optimization processing, data enhancement processing.
  • the 3D boundary optimization processing can be processed by a 3D convolutional network.
  • enhancing the edge of the image we choose Laplacian to enhance the BGR channel of the image separately.
  • the medical imaging device can perform at least one image optimization operation to obtain a target medical image, which improves the quality of the medical image and ensures the clarity and accuracy of the image.
  • the 2D boundary optimization processing includes the following operations: multiple sampling to obtain low-resolution information and high-resolution information, where the low-resolution information can provide the contextual semantic information of the segmentation target in the entire image, namely Features reflecting the relationship between the target and the environment, the segmentation target includes the target vein;
  • the 3D boundary optimization processing includes the following operations: putting the second medical image data into a 3D convolutional layer for 3D convolution Operation to obtain a feature map; the 3D pooling layer compresses the feature map and performs nonlinear activation; performs a cascade operation on the compressed feature map to obtain the prediction result image output by the model;
  • the data enhancement processing Including at least one of the following: data enhancement based on arbitrary angle rotation, data enhancement based on histogram equalization, data enhancement based on white balance, data enhancement based on mirroring operations, data enhancement based on random clipping, and data enhancement based on simulating different lighting changes Data enhancement.
  • the medical imaging device may sample the second medical image multiple times to obtain low-resolution information and high-resolution information to display the relationship between the target vein and the environment in the second medical image.
  • the number of times can be preset times or historical sampling times.
  • the convolutional neural network is composed of input layer, convolution layer, activation function, pooling layer, and fully connected layer, namely INPUT-CONV-RELU-POOL-FC.
  • the convolutional layer performs feature extraction; the pooling layer compresses the input feature map. On the one hand, it makes the feature map smaller and simplifies the network calculation complexity. On the other hand, it performs feature compression to extract main features; the fully connected layer connects all the features. Send the output value to the classifier.
  • specific methods of data enhancement include, but are not limited to, rotation at any angle, histogram equalization, white balance, mirror operation, random cropping, simulation of different lighting changes, and so on.
  • the data enhancement based on the rotation of any angle and the data enhancement based on the simulation of different illumination changes have greater significance for improving the model effect.
  • the medical imaging device can perform at least one image optimization operation such as 2D boundary optimization processing, 3D boundary optimization processing, and data enhancement processing to obtain target medical images, which improves the quality of medical images and ensures The clarity and accuracy of the image.
  • image optimization operation such as 2D boundary optimization processing, 3D boundary optimization processing, and data enhancement processing to obtain target medical images, which improves the quality of medical images and ensures The clarity and accuracy of the image.
  • the medical imaging device extracts a data set of the target vein in the target medical image data
  • the target medical image may be screened to improve the accuracy of the target medical image data and the data set of the target vein.
  • the medical imaging device may screen the enhanced data with a quality score greater than a preset score from the target medical image data as the imaging data, that is, the preferred target medical image.
  • the medical imaging device performs 4D medical imaging according to the data set of the target vein to display the internal image of the target vein.
  • the medical imaging device performs 4D medical imaging according to the data set of the target vein to display the internal image of the target vein, including: the medical imaging device displays the target according to the data set of the target vein The image of the outer wall of the vein; when a selection operation for the image of the outer wall is detected, retrieve the internal data of the target vein in the area where the touch position is located; display the touch position according to the internal data The intravenous slice image of the area.
  • the image of the target vein data set is displayed on the display device.
  • the selected vein and the inner vein image of the selected position are retrieved .
  • the operation of selecting and viewing a certain vein includes, but is not limited to, touching the touch screen and selecting with a cursor.
  • the medical imaging device can select the vein and location to be viewed based on the target vein image data, and display the intravenous slice image of the selected vein and location, ensuring the clarity and convenience of image retrieval and viewing Sex.
  • the medical imaging device first determines the bitmap BMP data source according to multiple scanned images of the target part of the target user, and secondly, generates the first medical image data according to the BMP data source, and again, according to the first The medical image data generates the second medical image data.
  • the second medical image data is processed to obtain the target medical image data, and then the target vein data set in the target medical image data is extracted, and finally 4D medical imaging is performed according to the target vein data set for display The internal image of the target vein.
  • the target part includes the target vein to be observed and the arteries, kidneys, and hepatic portal associated with the target vein.
  • the first medical image data includes the original data set of the target vein, the original data set of some arteries, the data set of the kidney, and the hepatic portal.
  • the original data set of the blood vessel of the target vein and the original data set of the partial arteries include the fusion data of the cross position, and the original data set of the blood vessel of the target vein is the transmission of the cube space of the tissue structure of the target vein surface and the target vein Function result, the original data set of part of the artery is the result of the transfer function of the cube space of the tissue structure of the part of the artery surface and part of the artery, and the data set of the kidney is the result of the transfer function of the cube space of the tissue structure of the kidney surface and the internal structure of the kidney.
  • the data set of the portal is the result of the transfer function of the cube space of the hepatic portal surface and the internal tissue structure of the portal.
  • the second medical image data includes the segmented data set of the target vein, the segmented data set of part of the artery, the data set of the kidney, and the hepatic portal.
  • the first data of the target vein segmentation data collection and the second data of the partial artery segmentation data collection are independent of each other.
  • the first data and the second data are the data of the intersection position. It can be seen that the medical imaging device of this application passes Data preprocessing, separation, integration, and 4D medical imaging are beneficial to improve the accuracy and convenience of inferior vena cava imaging by medical imaging devices.
  • the method further includes: the medical imaging device performs intraoperative navigation according to the intravenous slice image during the operation on the target user.
  • the medical imaging device can use the internal image of the target vein to provide surgical navigation, real-time control, and operation warning during the operation of the target user.
  • the medical imaging device can perform intraoperative navigation based on the internal image of the target vein, which significantly improves the efficiency and safety of the operation.
  • FIG. 3 is a schematic structural diagram of a medical imaging apparatus 300 provided by an embodiment of the present application.
  • the medical imaging apparatus 300 includes a processor 310, a memory 320, a communication interface 330, and one or more programs 321, wherein the one or more programs 321 are stored in the above-mentioned memory 320 and are configured to be executed by the above-mentioned processor 310, and the one or more The program 321 includes instructions for performing the following steps;
  • the first medical image data including the original data set of the target vein, the original data set of the partial arteries, the data set of the kidney, the hepatic portal
  • the original data set of the blood vessel of the target vein and the original data set of the partial arteries include the fusion data of the intersection position
  • the original data set of the blood vessel of the target vein is the surface of the target vein and the target
  • the original data set of the part of the artery is the transfer function result of the cube space of the part of the artery surface and the tissue structure inside the part of the artery
  • the data set of the kidney Is the transfer function result of the cube space of the tissue structure inside the kidney and the surface of the kidney
  • the data set of the hepatic hilum is the transfer function result of the cube space of the tissue structure inside the hepatic hilum surface and the hepatic hilum ;
  • the second medical image data including the segmentation data set of the target vein, the segmentation data set of the partial artery, the data set of the kidney, the The data set of the hepatic hilum, the first data of the segmented data set of the target vein and the second data of the segmented data set of the partial artery are independent of each other, and the first data and the second data are the intersection position The data;
  • the medical imaging device first determines the bitmap BMP data source according to multiple scanned images of the target part of the target user, and secondly, generates the first medical image data according to the BMP data source, and again, according to the first The medical image data generates the second medical image data.
  • the second medical image data is processed to obtain the target medical image data, and then the target vein data set in the target medical image data is extracted, and finally 4D medical imaging is performed according to the target vein data set for display The internal image of the target vein.
  • the target part includes the target vein to be observed and the arteries, kidneys, and hepatic portal associated with the target vein.
  • the first medical image data includes the original data set of the target vein, the original data set of some arteries, the data set of the kidney, and the hepatic portal.
  • the original data set of the blood vessel of the target vein and the original data set of the partial arteries include the fusion data of the cross position, and the original data set of the blood vessel of the target vein is the transmission of the cube space of the tissue structure of the target vein surface and the target vein Function result, the original data set of part of the artery is the result of the transfer function of the cube space of the tissue structure of the part of the artery surface and part of the artery, and the data set of the kidney is the result of the transfer function of the cube space of the tissue structure of the kidney surface and the internal structure of the kidney.
  • the data set of the portal is the result of the transfer function of the cube space of the hepatic portal surface and the internal tissue structure of the portal.
  • the second medical image data includes the segmented data set of the target vein, the segmented data set of part of the artery, the data set of the kidney, and the hepatic portal.
  • the first data of the target vein segmentation data collection and the second data of the partial artery segmentation data collection are independent of each other.
  • the first data and the second data are the data of the intersection position. It can be seen that the medical imaging device of this application passes Data preprocessing, separation, integration, and 4D medical imaging are beneficial to improve the accuracy and convenience of inferior vena cava imaging by medical imaging devices.
  • the instructions in the program are specifically used to perform the following operations: import the BMP data source into a preset VRDS medical network Model, call each transfer function in the pre-stored transfer function set through the VRDS medical network model, process the BMP data source through multiple transfer functions in the transfer function set to obtain the first medical image data,
  • the transfer function set includes the transfer function of the target vein, the transfer function of the artery, the transfer function of the kidney, and the transfer function of the hepatic port which are preset by a reverse editor.
  • the instructions in the program are specifically used to perform the following operations:
  • the original data set of the target vein and the original data set of the partial arteries are imported into the cross blood vessel network model, and the fusion data at the cross position is spatially segmented through the cross blood vessel network model to obtain the first data And the second data; generating the segmentation data set of the target vein according to the original data set of the target vein and the first data, and generating the segmentation data set according to the original data set of the partial arteries and the second data Partial artery segmentation data set; synthesize the segmentation data set of the target vein, the segmentation data set of the partial artery, the data set of the kidney, and the data set of the hepatic hilum to obtain the second medical image data.
  • the instructions in the program are specifically used to perform the following operations: execute at least one of the following for the second medical image data
  • the target medical image data is obtained by two processing operations: 2D boundary optimization processing, 3D boundary optimization processing, and data enhancement processing.
  • the instructions in the program are specifically used to perform the following operations: multiple sampling to obtain low-resolution information and high-resolution information, where low-resolution information can be Provides the contextual semantic information of the segmentation target in the entire image, that is, the characteristics that reflect the relationship between the target and the environment.
  • the segmentation target includes the target vein;
  • the instructions in the program are specifically used for Perform the following operations: put the second medical image data into a 3D convolution layer to perform a 3D convolution operation to obtain a feature map; the 3D pooling layer compresses the feature map and performs nonlinear activation;
  • the latter feature maps are cascaded to obtain the prediction result image output by the model.
  • the instructions in the program are specifically used to perform the following operations: data enhancement based on arbitrary angle rotation, data enhancement based on histogram equalization, data enhancement based on white balance, data enhancement based on mirroring operations , Data enhancement based on random clipping and data enhancement based on simulating different lighting changes.
  • the instructions in the program are specifically used to perform the following operations:
  • the vein data set displays the outer wall image of the target vein; when a selection operation for the outer wall image is detected, the internal data of the target vein in the area where the touch position is located is retrieved; according to the The internal data shows the internal slice image of the vein in the area where the touch position is located.
  • the program further includes instructions for performing the following operations: during the operation of the target user, intraoperative navigation is performed according to the intravenous slice image.
  • the instructions in the program are specifically used to perform the following operations: Obtain the reflected target collected by the medical device Multiple scanned images of the internal structural features of the user’s human body; at least one scanned image containing the target part is selected from the multiple scanned images, and the at least one scanned image is used as the medical digital imaging and Communicate DICOM data; parse the DICOM data to generate the image source of the target user, the image source includes Texture 2D/3D image volume data; perform the first preset processing on the image source to obtain the BMP data source, the The first preset processing includes at least one of the following operations: VRDS limited contrast adaptive histogram equalization, hybrid partial differential denoising, and VRDS Ai elastic deformation processing.
  • the instructions in the program are specifically used to perform the following operations: regional noise ratio limiting, global contrast limiting; localization of the image source
  • the histogram is divided into multiple partitions. For each partition, the slope of the transformation function is determined according to the slope of the cumulative histogram of the neighborhood of the partition, and the degree of contrast amplification around the pixel value of the partition is determined according to the slope of the transformation function , And then perform a limited cropping process according to the contrast magnification level to generate the distribution of the effective histogram, and also generate the value of the effective and available neighborhood size, and evenly distribute the cropped part of the histogram to other areas of the histogram;
  • the instructions in the program are specifically used to perform the following operations: through VRDS Ai curvature drive and VRDS Ai high-order hybrid denoising, so that the curvature of the image edge is less than the preset curvature.
  • a hybrid partial differential denoising model that protects the edges of the image and avoids the step effect in the smoothing process; in terms of the VRDS Ai elastic deformation processing, the instructions in the program are specifically used to perform the following operations: on the image lattice, Superimpose the positive and negative random distances to form a difference position matrix, and then the gray scale at each difference position forms a new dot matrix, which can realize the distortion and deformation of the image, and then rotate, distort, and translate the image.
  • the medical imaging apparatus includes hardware structures and/or software modules corresponding to each function.
  • this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software-driven hardware depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.
  • the embodiment of the present application may divide the medical imaging device into functional units according to the foregoing method examples.
  • each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical function division, and there may be other division methods in actual implementation.
  • FIG. 4 is a block diagram of the functional unit composition of the Ai endoscopic analysis device 400 based on the veins of VRDS Ai 4D medical images involved in the embodiments of the present application.
  • the Ai endoscopic analysis device 400 for veins based on VRDS Ai 4D medical images is applied to a medical imaging device.
  • the Ai endoscopic analysis device 400 for veins based on VRDS Ai 4D medical images includes a processing unit and a communication unit, among which,
  • the processing unit is configured to determine a bitmap BMP data source according to multiple scanned images of a target part of a target user, the target part including a target vein to be observed and arteries, kidneys, and hepatic portals associated with the target vein; And for generating first medical image data according to the BMP data source, the first medical image data including the original data set of the target vein, the original data set of the partial arteries, the data set of the kidney, and the The data set of the hepatic portal, the original data set of the blood vessels of the target vein and the original data set of the partial arteries include the fusion data of the intersection position, and the original data set of the blood vessels of the target vein is the surface of the target vein and
  • the transfer function result of the cube space of the tissue structure inside the target vein, the original data set of the part of the artery is the transfer function result of the cube space of the part of the artery surface and the tissue structure inside the part of the artery, the kidney
  • the data set is the result of the transfer function of the
  • the second data is the data of the intersection position; and used to process the second medical image data to obtain target medical image data; and used to extract the target vein in the target medical image data; and used to pass
  • the communication unit performs 4D medical imaging according to the data set of the target vein to display the internal image of the target vein.
  • the apparatus 400 for implementing a video conference may further include a storage unit 403 for storing program codes and data of the electronic device.
  • the processing unit 401 may be a processor
  • the communication unit 402 may be a touch screen or a transceiver
  • the storage unit 403 may be a memory.
  • the medical imaging device first determines the bitmap BMP data source according to multiple scanned images of the target part of the target user, and secondly, generates the first medical image data according to the BMP data source, and again, according to the first The medical image data generates the second medical image data.
  • the second medical image data is processed to obtain the target medical image data, and then the target vein data set in the target medical image data is extracted, and finally 4D medical imaging is performed according to the target vein data set for display The internal image of the target vein.
  • the target part includes the target vein to be observed and the arteries, kidneys, and hepatic portal associated with the target vein.
  • the first medical image data includes the original data set of the target vein, the original data set of some arteries, the data set of the kidney, and the hepatic portal.
  • the original data collection of the blood vessel of the target vein and the original data collection of part of the arteries include the fusion data of the cross position, and the original data collection of the blood vessel of the target vein is the transmission of the cube space of the tissue structure of the target vein surface and the target vein Function result, the original data set of part of the artery is the result of the transfer function of the cube space of the tissue structure of the part of the artery surface and part of the artery, and the data set of the kidney is the result of the transfer function of the cube space of the tissue structure of the kidney surface and the internal tissue of the kidney.
  • the data set of the portal is the result of the transfer function of the cube space of the hepatic portal surface and the internal tissue structure of the portal.
  • the second medical image data includes the segmented data set of the target vein, the segmented data set of part of the artery, the data set of the kidney, and the hepatic portal.
  • the first data of the target vein segmentation data collection and the second data of the partial artery segmentation data collection are independent of each other.
  • the first data and the second data are the data of the intersection position. It can be seen that the medical imaging device of this application passes Data preprocessing, separation, integration, and 4D medical imaging are beneficial to improve the accuracy and convenience of inferior vena cava imaging by medical imaging devices.
  • the processing unit 401 is specifically configured to: import the BMP data source into a preset VRDS medical network model, and pass all The VRDS medical network model calls each transfer function in a set of pre-stored transfer functions, and processes the BMP data source through multiple transfer functions in the transfer function set to obtain first medical image data, and the transfer function set includes The transfer function of the target vein, the transfer function of the artery, the transfer function of the kidney, and the transfer function of the hepatic portal are preset through the reverse editor.
  • the processing unit 401 is specifically configured to: combine the data of the target vein in the first medical image data
  • the original data set and the original data set of the partial arteries are imported into the cross blood vessel network model, and the fusion data at the cross position is spatially divided through the cross blood vessel network model to obtain the first data and the first data Two data; generating a segmentation data set of the target vein according to the original data set of the target vein and the first data, and generating a segmentation of the partial artery according to the original data set of the partial artery and the second data Data collection; integrating the segmentation data collection of the target vein, the segmentation data collection of the partial arteries, the data collection of the kidney, and the data collection of the hepatic hilum to obtain the second medical image data.
  • the processing unit 401 is specifically configured to: perform at least one of the following processing operations on the second medical image data to obtain Target medical image data: 2D boundary optimization processing, 3D boundary optimization processing, data enhancement processing.
  • the processing unit 401 is specifically configured to: obtain low-resolution information and high-resolution information through multiple sampling, where the low-resolution information can provide segmentation targets
  • the contextual semantic information in the entire image that is, the characteristics that reflect the relationship between the target and the environment, the segmentation target includes the target vein
  • the processing unit 401 is specifically configured to:
  • the second medical image data is put into a 3D convolution layer to perform 3D convolution operations to obtain a feature map;
  • the 3D pooling layer compresses the feature map and performs nonlinear activation; and performs a stage on the compressed feature map Joint operation to obtain the prediction result image output by the model.
  • the processing unit 401 is specifically configured to: data enhancement based on arbitrary angle rotation, data enhancement based on histogram equalization, data enhancement based on white balance, data enhancement based on mirroring operations, data enhancement based on random clipping Cut data enhancement and data enhancement based on simulating different lighting changes.
  • the processing unit 401 is specifically configured to: according to the data set of the target vein Display the outer wall image of the target vein; when a selection operation for the outer wall image is detected, retrieve the internal data of the target vein in the area where the touch position is located; display the internal data according to the internal data The intravenous slice image of the area where the touch position is located.
  • the processing unit 401 is further configured to perform intraoperative navigation according to the intravenous slice image during the operation on the target user.
  • the processing unit 401 is specifically configured to: obtain the internal body of the target user collected by the medical device. A plurality of scanned images with structural characteristics; at least one scanned image containing the target part is selected from the multiple scanned images, and the at least one scanned image is used as the medical digital imaging and communication DICOM data of the target user;
  • the DICOM data is parsed to generate the image source of the target user, the image source includes Texture 2D/3D image volume data;
  • the first preset processing is performed on the image source to obtain the BMP data source, the first preset
  • the processing includes at least one of the following operations: VRDS limited contrast adaptive histogram equalization, hybrid partial differential denoising, and VRDS Ai elastic deformation processing.
  • the processing unit 401 is specifically configured to: limit the regional noise ratio and limit the global contrast; divide the local histogram of the image source more For each partition, the slope of the transformation function is determined according to the slope of the cumulative histogram of the neighborhood of the partition, and the degree of contrast amplification around the pixel value of the partition is determined according to the slope of the transformation function, and then according to the The contrast magnification degree is cut to a limit, and the distribution of the effective histogram is generated, and at the same time, the value of the effective and usable neighborhood size is also generated, and these cropped parts of the histogram are evenly distributed to other areas of the histogram; the mixed bias Differential denoising includes the following steps: through VRDS Ai curvature drive and VRDS Ai high-order hybrid denoising, so that the curvature of the image edge is less than the preset curvature, which can protect the image edge and avoid the mixed deviation of the step effect in the
  • the VRDS Ai elastic deformation processing includes the following steps: superimpose positive and negative random distances on the image lattice to form a difference position matrix, and then form a new point on the gray level at each difference position Array, you can realize the distortion inside the image, and then rotate, distort, and translate the image.
  • An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method as recorded in the above method embodiment ,
  • the aforementioned computer includes a medical imaging device.
  • the embodiments of the present application also provide a computer program product.
  • the above-mentioned computer program product includes a non-transitory computer-readable storage medium storing a computer program. Part or all of the steps of the method.
  • the computer program product may be a software installation package, and the computer includes a medical imaging device.
  • the disclosed device may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the above-mentioned units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or integrated. To another system, or some features can be ignored, or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical or other forms.
  • the units described above as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.
  • the above integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable memory.
  • the technical solution of the present application essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, A number of instructions are included to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the foregoing methods of the various embodiments of the present application.
  • the aforementioned memory includes: U disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
  • the program can be stored in a computer-readable memory, and the memory can include: flash disk , Read-only memory (English: Read-Only Memory, abbreviation: ROM), random access device (English: Random Access Memory, abbreviation: RAM), magnetic disk or optical disc, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Biomedical Technology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Quality & Reliability (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

本申请实施例公开了一种基于VRDS 4D医学影像的静脉的Ai内镜分析方法及产品，应用于医学成像装置；方法包括：根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，目标部位包括待观测的目标静脉和与目标静脉关联的动脉、肾脏、肝门；根据BMP数据源生成第一医学影像数据；根据第一医学影像数据生成第二医学影像数据；处理第二医学影像数据得到目标医学影像数据；提取目标医学影像数据中目标静脉的数据集合；根据目标静脉的数据集合进行4D医学成像以展示目标静脉的内部影像。本申请实施例有利于提高医学成像装置进行下腔静脉成像的准确度和便捷性。

Description

基于VRDS 4D医学影像的静脉的Ai内镜分析方法及产品 技术领域
本申请涉及医学成像装置技术领域，具体涉及一种基于VRDS 4D医学影像的静脉的Ai内镜分析方法及产品。
背景技术
目前，医生通过电子计算机断层扫描(Computed Tomography，CT)、磁共振成像(Magnetic Resonance Imaging，MRI)、弥散张量成像(Diffusion Tensor Imaging，DTI)、正电子发射型计算机断层显像(Positron Emission Computed Tomography，PET)等技术获取病变组织的形态、位置、拓扑结构等信息。医生仍然采用观看阅读连续的二维切片数据，以此对患者的病变组织如肿瘤进行判断分析。然而，仅仅通过直接观看两维切片数据会严重影响到医生对疾病的诊断，医生不能获得直观、真实的四维体结构。随着医学成像技术的飞速发展，人们对医学成像提出了新的需求。
发明内容
本申请实施例提供了一种基于VRDS 4D医学影像的静脉的Ai内镜分析方法及产品，无须静脉注射造影剂可显示血管结构，无电离辐射及创口；经济方便，减少了对操作者技术水平的依赖，增强可重复性。
第一方面，本申请实施例提供一种基于VRDS 4D医学影像的静脉的Ai内镜分析方法，应用于医学成像装置；所述方法包括：
根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，所述目标部位包括待观测的目标静脉和与所述目标静脉关联的动脉、肾脏、肝门；
根据所述BMP数据源生成第一医学影像数据，所述第一医学影像数据包括所述目标静脉的原始数据集合、所述部分动脉的原始数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的血管的原始数据集合和所述部分动脉的原始数据集合包括交叉位置的融合数据，所述目标静脉的血管的原始数据集合为所述目标静脉表面和所述目标静脉内部的组织结构的立方体空间的传递函数结果，所述部分动脉的原始数据集合为所述部分动脉表面和所述部分动脉内部的组织结构的立方体空间的传递函数结果，所述肾脏的数据集合为所述肾脏表面和所述肾脏内部的组织结构的立方体空间的传递函数结果，所述肝门的数据集合为所述肝门表面和所述肝门内部的组织结构的立方体空间的传递函数结果；
根据所述第一医学影像数据生成第二医学影像数据，所述第二医学影像数据包括所述目标静脉的分割数据集合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的分割数据集合的第一数据和所述部分动脉的分割数据集合的第二数据相互独立，所述第一数据和所述第二数据为所述交叉位置的数据；
处理所述第二医学影像数据得到目标医学影像数据；
提取所述目标医学影像数据中所述目标静脉的数据集合；
根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像。
第二方面，本申请实施例提供一种基于VRDS Ai 4D医学影像的静脉的Ai内镜分析装置，应用于医学成像装置；所述基于VRDS Ai 4D医学影像的静脉的Ai内镜分析装置包括处理单元和通信单元，其中，
所述处理单元，用于根据目标用户的目标部位的多张扫描图像确定位图BMP数据源， 所述目标部位包括待观测的目标静脉和与所述目标静脉关联的动脉、肾脏、肝门；以及用于根据所述BMP数据源生成第一医学影像数据，所述第一医学影像数据包括所述目标静脉的原始数据集合、所述部分动脉的原始数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的血管的原始数据集合和所述部分动脉的原始数据集合包括交叉位置的融合数据，所述目标静脉的血管的原始数据集合为所述目标静脉表面和所述目标静脉内部的组织结构的立方体空间的传递函数结果，所述部分动脉的原始数据集合为所述部分动脉表面和所述部分动脉内部的组织结构的立方体空间的传递函数结果，所述肾脏的数据集合为所述肾脏表面和所述肾脏内部的组织结构的立方体空间的传递函数结果，所述肝门的数据集合为所述肝门表面和所述肝门内部的组织结构的立方体空间的传递函数结果；以及用于根据所述第一医学影像数据生成第二医学影像数据，所述第二医学影像数据包括所述目标静脉的分割数据集合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的分割数据集合的第一数据和所述部分动脉的分割数据集合的第二数据相互独立，所述第一数据和所述第二数据为所述交叉位置的数据；以及用于处理所述第二医学影像数据得到目标医学影像数据；以及用于提取所述目标医学影像数据中所述目标静脉的数据集合；以及用于通过所述通信单元根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像。
第三方面，本申请实施例提供一种医学成像装置，包括处理器、存储器、通信接口以及一个或多个程序，其中，上述一个或多个程序被存储在上述存储器中，并且被配置由上述处理器执行，上述程序包括用于执行本申请实施例第一方面任一方法中的步骤的指令。
第四方面，本申请实施例提供了一种计算机可读存储介质，其中，上述计算机可读存储介质存储用于电子数据交换的计算机程序，其中，上述计算机程序使得计算机执行如本申请实施例第一方面任一方法中所描述的部分或全部步骤。
第五方面，本申请实施例提供了一种计算机程序产品，其中，上述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，上述计算机程序可操作来使计算机执行如本申请实施例第一方面任一方法中所描述的部分或全部步骤。该计算机程序产品可以为一个软件安装包。
可以看出，本申请实施例中，医学成像装置首先根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，其次，根据BMP数据源生成第一医学影像数据，再次，根据第一医学影像数据生成第二医学影像数据，再次，处理第二医学影像数据得到目标医学影像数据，然后提取目标医学影像数据中目标静脉的数据集合，最后根据目标静脉的数据集合进行4D医学成像以展示目标静脉的内部影像。其中，目标部位包括待观测的目标静脉和与目标静脉关联的动脉、肾脏、肝门，第一医学影像数据包括目标静脉的原始数据集合、部分动脉的原始数据集合、肾脏的数据集合、肝门的数据集合，目标静脉的血管的原始数据集合和部分动脉的原始数据集合包括交叉位置的融合数据，目标静脉的血管的原始数据集合为目标静脉表面和目标静脉内部的组织结构的立方体空间的传递函数结果，部分动脉的原始数据集合为部分动脉表面和部分动脉内部的组织结构的立方体空间的传递函数结果，肾脏的数据集合为肾脏表面和肾脏内部的组织结构的立方体空间的传递函数结果，肝门的数据集合为肝门表面和肝门内部的组织结构的立方体空间的传递函数结果，第二医学影像数据包括目标静脉的分割数据集合、部分动脉的分割数据集合、肾脏的数据集合、肝门的数据集合，目标静脉的分割数据集合的第一数据和部分动脉的分割数据集合的第二数据相互独立，第一数据和第二数据为交叉位置的数据，可见，本申请的医学成像装置通过数据的预处理、分离、整合，并进行4D医学成像，有利于提高医学成像装置进行下腔静脉成像的准确度和便捷性。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的一种基于VRDS Ai医学影像智能分析处理系统的结构示意图；
图2是本申请实施例提供的一种基于VRDS 4D医学影像的静脉的Ai内镜分析方法的流程示意图；
图3是本申请实施例提供的一种医学成像装置的结构示意图；
图4是本申请实施例提供的一种基于VRDS Ai 4D医学影像的静脉的Ai内镜分析装置的功能单元组成框图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
本申请实施例所涉及到的医学成像装置是指利用各种不同媒介作为信息载体，将人体内部的结构重现为影像的各种仪器，其影像信息与人体实际结构有着空间和时间分布上的对应关系。“DICOM数据”是指通过医疗设备采集的反映人体内部结构特征的原始图像文件数据，可以包括电子计算机断层扫描CT、核磁共振MRI、弥散张量成像DTI、正电子发射型计算机断层显像PET-CT等信息，“图源”是指解析原始DICOM数据生成的Texture2D/3D图像体数据。“VRDS”是指虚拟现实医用系统(Virtual Reality Doctor system，简称为VRDS)。
请参阅图1，图1是本申请实施例提供了一种基于VRDS Ai医学影像智能分析处理系统100的结构示意图，该系统100包括医学成像装置110和网络数据库120，其中医学成像装置110可以包括本地医学成像装置111和/或终端医学成像装置112，本地医学成像装置111或终端医学成像装置112用于基于原始DICOM数据，以本申请实施例所呈现的基于VRDS Ai 4D医学影像的静脉的内镜分析算法为基础，进行人体肿瘤区域的识别、定位和四维体绘制，实现四维立体成像效果(该四维医学影像具体是指医学影像包括所显示组织的内部空间结构特征及外部空间结构特征，所述内部空间结构特征是指组织内部的切片数据未丢失，即医学成像装置可以呈现目标器官、血管等组织的内部构造，外部空间结构特性是指组织与组织之间的环境特征，包括组织与组织之间的空间位置特性(包括交叉、间隔、融合)等， 如肾脏与动脉之间的交叉位置的边缘结构特性等)，本地医学成像装置111相对于终端医学成像装置112还可以用于对图源数据进行编辑，形成四维人体图像的传递函数结果，该传递函数结果可以包括人体内脏器官表面和人体内脏器官内的组织结构的传递函数结果，以及立方体空间的传递函数结果，如传递函数所需的立方编辑框与弧线编辑的数组数量、坐标、颜色、透明度等信息。网络数据库120例如可以是云服务器等，该网络数据库120用于存储解析原始DICOM数据生成的图源，以及本地医学成像装置111编辑得到的四维人体图像的传递函数结果，图源可以是来自于多个本地医学成像装置111以实现多个医生的交互诊断。
用户通过上述医学成像装置110进行具体的图像显示时，可以选择显示器或者虚拟现实VR的头戴式显示器(Head mounted Displays Set，HMDS)结合操作动作进行显示，操作动作是指用户通过医学成像装置的外部摄入设备，如鼠标、键盘等，对四维人体图像进行的操作控制，以实现人机交互，该操作动作包括以下至少一种：(1)改变某个具体器官/组织的颜色和/或透明度，(2)定位缩放视图，(3)旋转视图，实现四维人体图像的多视角360度观察，(4)“进入”人体器官内部观察内部构造，实时剪切效果渲染，(5)上下移动视图。
下面对本申请实施例涉及到的基于VRDS Ai医学影像的肿瘤识别算法进行详细介绍。
请参阅图2，图2是本申请实施例提供了一种基于VRDS 4D医学影像的静脉的Ai内镜分析方法的流程示意图，应用于如图1所述的医学成像装置；如图所示，本基于VRDS 4D医学影像的静脉的Ai内镜分析方法包括：
S201，医学成像装置根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，所述目标部位包括待观测的目标静脉和与所述目标静脉关联的动脉、肾脏、肝门；
其中，BMP(全称Bitmap)是Windows操作系统中的标准图像文件格式，可以分成两类：设备相关位图(DDB)和设备无关位图(DIB)。所述扫描图像包括以下任意一种：CT图像、MRI图像、DTI图像、PET-CT图像。
具体实现中，所述医学成像装置根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，包括：所述医学成像装置获取通过医疗设备采集的反映目标用户的人体内部结构特征的多张扫描图像；从所述多张扫描图像中筛选出包含所述目标部位的至少一张扫描图像，将所述至少一张扫描图像作为目标用户的医学数字成像和通信DICOM数据；解析所述DICOM数据生成目标用户的图源，所述图源包括纹理Texture 2D/3D图像体数据；针对所述图源执行第一预设处理得到所述BMP数据源，所述第一预设处理包括以下至少一种操作：VRDS限制对比度自适应直方图均衡、混合偏微分去噪、VRDS Ai弹性变形处理。
其中，所述DICOM(Digital Imaging and Communications in Medicine)即医学数字成像和通信，是医学图像和相关信息的国际标准。
具体实现中，所述医学成像装置先获取已经采集的反映目标用户的人体内部结构特征的多张扫描图像，可以通过清晰度、准确度等筛选出合适的包含目标器官的至少一张扫描图像，再对所述扫描图像执行进一步处理，得到位图BMP数据源。
可见，本示例中，所述医学成像装置可以基于获取的扫描图像，进行筛选、解析和第一预设处理处理后得到位图BMP数据源，提高了医学影像成像的准确度和清晰度。
在一个可能的示例中，所述VRDS限制对比度自适应直方图均衡包括以下步骤：区域噪音比度限幅、全局对比度限幅；将图源的局部直方图划分多个分区，针对每个分区，根据该分区的邻域的累积直方图的斜度确定变换函数的斜度，根据该变换函数的斜度确定该分区的像素值周边的对比度放大程度，然后根据该对比度放大程度进行限度裁剪处理，产生有效直方图的分布，同时也产生有效可用的邻域大小的取值，将这些裁剪掉的部分直方图均匀的分布到直方图的其他区域；所述混合偏微分去噪包括以下步骤：通过VRDS Ai曲率驱动和VRDS Ai高阶混合去噪，使得图像边缘的曲率小于预设曲率，实现即可保护图像 边缘、又可以避免平滑过程中出现阶梯效应的混合偏微分去噪模型；所述VRDS Ai弹性变形处理包括以下步骤：在图像点阵上，叠加正负向随机距离形成差值位置矩阵，然后在每个差值位置上的灰度，形成新的点阵，可以实现图像内部的扭曲变形，再对图像进行旋转、扭曲、平移操作。
具体实现中，可以针对所述图源执行至少一种图像处理操作得到所述BMP数据源，包括但不限于：VRDS限制对比度自适应直方图均衡、混合偏微分去噪、VRDS Ai弹性变形处理。
其中，所述混合偏微分去噪可以采用CDD和高阶去噪模型对所述图源进行处理；CDD模型(Curvature Driven Diffusions)模型是在TV(Total Variation)模型的基础上引进了曲率驱动而形成的，解决了TV模型不能修复图像视觉连通性的问题。其中，高阶去噪是指基于偏微分方程(PDE)方法对图像进行去噪处理。具体实现中，让所述图源按照指定的微分方程函数变化进行滤噪作用，从而滤除所述图源中的噪点，而偏微分方程的解就是去噪后的得到的所述BMP数据源，基于PDE的图像去噪方法具有各向异性扩散的特点，因此能够在所述图源的不同区域进行不同程度的扩散作用，从而取得抑制噪声的同时保护图像边缘纹理信息的效果。
可见，本示例中，所述医学成像装置通过以下至少一种图像处理操作：VRDS限制对比度自适应直方图均衡、混合偏微分去噪、VRDS Ai弹性变形处理，提高了图像处理的执行效率，还提高了图像质量，保护图像边缘纹理。
S202，所述医学成像装置根据所述BMP数据源生成第一医学影像数据，所述第一医学影像数据包括所述目标静脉的原始数据集合、所述部分动脉的原始数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的血管的原始数据集合和所述部分动脉的原始数据集合包括交叉位置的融合数据，所述目标静脉的血管的原始数据集合为所述目标静脉表面和所述目标静脉内部的组织结构的立方体空间的传递函数结果，所述部分动脉的原始数据集合为所述部分动脉表面和所述部分动脉内部的组织结构的立方体空间的传递函数结果，所述肾脏的数据集合为所述肾脏表面和所述肾脏内部的组织结构的立方体空间的传递函数结果，所述肝门的数据集合为所述肝门表面和所述肝门内部的组织结构的立方体空间的传递函数结果；
具体实现中，所述医学成像装置根据所述BMP数据源生成第一医学影像数据，包括：所述医学成像装置将所述BMP数据源导入预设的VRDS医学网络模型，通过所述VRDS医学网络模型调用预存的传递函数集合中的每个传递函数，通过所述传递函数集合中的多个传递函数处理所述BMP数据源，得到第一医学影像数据，所述传递函数集合包括通过反向编辑器预先设置的所述目标静脉的传递函数、动脉的传递函数、所述肾脏的传递函数和所述肝门的传递函数。
其中，所述VRDS医学网络模型为预设网络模型，其训练方法包含如下三个步骤：图像采样及尺度缩放；3D卷积神经网络特征提取及打分；医学成像装置评价与网络训练。在实施过程中，先将需要进行采样，获取N个BMP数据源，再按照预设的间隔从N个BMP数据源中提取出M个BMP数据源。需要进行说明的是，预设的间隔可根据使用场景进行灵活设定。从N个中采样出M个，然后，将采样出来的M个BMP数据源缩放到固定尺寸(例如，长为S像素，宽为S像素)，得到的处理结果作为3D卷积神经网络的输入。这样将M个BMP数据源作为3D卷积神经网络的输入。具体的，利用3D卷积神经网络对所述BMP数据源进行3D卷积处理，获得特征图。
可见，本示例中，所述医学成像装置可以基于预设的VRDS医学网络模型和所述BMP数据源得到第一医学影像数据，提高了获取所述第一医学影像数据的准确度和便捷性。
S203，所述医学成像装置根据所述第一医学影像数据生成第二医学影像数据，所述第二医学影像数据包括所述目标静脉的分割数据集合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的分割数据集合的第一数据和所述部分动脉的分割数据集合的第二数据相互独立，所述第一数据和所述第二数据为所述交叉位置的数据；
具体实现中，所述医学成像装置根据所述第一医学影像数据生成第二医学影像数据，包括：所述医学成像装置将所述第一医学影像数据中的所述目标静脉的原始数据集合、所述部分动脉的原始数据集合导入所述交叉血管网络模型，通过所述交叉血管网络模型对所述交叉位置的融合数据进行空间分割处理，得到所述第一数据和所述第二数据；根据所述目标静脉的原始数据集合和所述第一数据生成所述目标静脉的分割数据集合，根据所述部分动脉的原始数据集合和所述第二数据生成所述部分动脉的分割数据集合；综合所述目标静脉的分割数据集合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门的数据集合，得到所述第二医学影像数据。
具体实现中，所述交叉血管网络模型为训练好的神经网络模型。
可见，本示例中，所述医学成像装置可以基于所述交叉血管网络模型和所述第一医学影像数据得到第二医学影像数据，提高了获取所述第二医学影像数据的准确度和便捷性。
S204，所述医学成像装置处理所述第二医学影像数据得到目标医学影像数据；
具体实现中，所述医学成像装置处理所述第二医学影像数据得到目标医学影像数据，包括：所述医学成像装置针对所述第二医学影像数据执行以下至少一种处理操作得到目标医学影像数据：2D边界优化处理、3D边界优化处理、数据增强处理。
来处理具体实现中，3D边界优化处理可以利用3D卷积网络来处理，当增强图像边缘时我们选择拉普拉斯分别对图像BGR通道分别增强。
可见，本示例中，所述医学成像装置可以通过执行至少一种影像优化操作，以得到目标医学影像，提高了医学影像的质量，确保了影像的清晰度和准确性。
在一个可能的示例中，所述2D边界优化处理包括以下操作：多次采样获取低分辨率信息和高分辨率信息，其中，低分辨率信息能够提供分割目标在整个图像中上下文语义信息，即反映目标与环境之间关系的特征，所述分割目标包括所述目标静脉；所述3D边界优化处理包括以下操作：将所述第二医学影像数据分别放入3D卷积层中进行3D卷积操作，获取特征图；3D池化层对所述特征图进行压缩，并进行非线性激活；对压缩后的所述特征图进行级联操作，获取模型输出的预测结果图像；所述数据增强处理包括以下至少一种：基于任意角度旋转的数据增强、基于直方图均衡的数据增强、基于白平衡的数据增强、基于镜像操作的数据增强、基于随机剪切的数据增强和基于模拟不同光照变化的数据增强。
本示例中，所述医学成像装置可以对所述第二医学影像进行多次采样获取低分辨率信息和高分辨率信息，以显示所述第二医学影像中目标静脉与环境的关系，所述多次可以为预置次数，也可为历史采样次数等。
其中，卷积神经网络由输入层、卷积层、激活函数、池化层、全连接层组成，即INPUT-CONV-RELU-POOL-FC。卷积层进行特征提取；池化层对输入的特征图进行压缩，一方面使特征图变小，简化网络计算复杂度，一方面进行特征压缩，提取主要特征；全连接层连接所有的特征，将输出值送给分类器。
具体实现中，该卷积神经网络用于图像处理，以图像作为输入和输出，例如：将第二医学影像数据放入卷积层C1i(K1i，F1i)和C2i(K2i，F2i)，(i＝1)中进行3D卷积操作，其中，K1i表示主通道第i层卷积的卷积核大小，K2i表示辅通道第i层卷积的卷积核大小，F1i和F2i分别表示主通道和辅通道的第i层卷积输出的特征图个数。对卷积得到的特征图进行批归一 化操作，并对批归一化后的特征图进行非线性激活，针对i＝2，3，4…，分别对激活后所得的特征图重复卷积和归一化，直到主通道最后生成9x9x9的数据块，辅通道生成3x3x3的数据块。对3x3x3的数据块进行上采样(即反卷积)，生成与主通道输出大小一致的数据块(即也生成9x9x9的数据块)。
其中，数据增强的具体方式包括但不限于任意角度的旋转、直方图均衡、白平衡、镜像操作、随机剪切、模拟不同光照变化等等。其中，基于任意角度的旋转的数据增强和基于模拟不同光照变化的数据增强的操作对提升模型效果有着更大的意义。
可见，本示例中，所述医学成像装置可以通过执行2D边界优化处理、3D边界优化处理、数据增强处理等至少一种影像优化操作，以得到目标医学影像，提高了医学影像的质量，确保了影像的清晰度和准确性。
S205，所述医学成像装置提取所述目标医学影像数据中所述目标静脉的数据集合；
其中，在提取目标静脉之前，可以对所述目标医学影像进行筛选，以提高所述目标医学影像数据和所述目标静脉的数据集合的准确度。
具体实现中，所述医学成像装置可以从所述目标医学影像数据中筛选质量评分大于预设评分的增强数据作为成像数据，即优选的目标医学影像。
S206，所述医学成像装置根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像。
具体实现中，所述医学成像装置根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像，包括：所述医学成像装置根据所述目标静脉的数据集合显示所述目标静脉的外侧壁影像；在检测到针对所述外侧壁影像的选择操作时，调取所述触控位置所处区域的所述目标静脉的内部数据；根据所述内部数据显示所述触控位置所处区域的静脉内部切片影像。
其中，根据目标医学图像提取所述目标静脉后，在显示设备上显示出目标静脉的数据集合的影像，当检测到针对某静脉的选择时，调取被选择静脉和被选择位置的静脉内侧影像。其中，选择查看某静脉的操作，包括但不限于对触摸屏的触控，利用光标选择。
可见，本示例中，所述医学成像装置可以基于目标静脉影像数据，选择需要查看的静脉和位置，显示被选择静脉和位置的静脉内部切片影像，确保了影像调取和查看的清晰度和便捷性。
可以看出，本申请实施例中，医学成像装置首先根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，其次，根据BMP数据源生成第一医学影像数据，再次，根据第一医学影像数据生成第二医学影像数据，再次，处理第二医学影像数据得到目标医学影像数据，然后提取目标医学影像数据中目标静脉的数据集合，最后根据目标静脉的数据集合进行4D医学成像以展示目标静脉的内部影像。其中，目标部位包括待观测的目标静脉和与目标静脉关联的动脉、肾脏、肝门，第一医学影像数据包括目标静脉的原始数据集合、部分动脉的原始数据集合、肾脏的数据集合、肝门的数据集合，目标静脉的血管的原始数据集合和部分动脉的原始数据集合包括交叉位置的融合数据，目标静脉的血管的原始数据集合为目标静脉表面和目标静脉内部的组织结构的立方体空间的传递函数结果，部分动脉的原始数据集合为部分动脉表面和部分动脉内部的组织结构的立方体空间的传递函数结果，肾脏的数据集合为肾脏表面和肾脏内部的组织结构的立方体空间的传递函数结果，肝门的数据集合为肝门表面和肝门内部的组织结构的立方体空间的传递函数结果，第二医学影像数据包括目标静脉的分割数据集合、部分动脉的分割数据集合、肾脏的数据集合、肝门的数据集合，目标静脉的分割数据集合的第一数据和部分动脉的分割数据集合的第二数据相互独立，第一数据和第二数据为交叉位置的数据，可见，本申请的医学成像装置通过数据 的预处理、分离、整合，并进行4D医学成像，有利于提高医学成像装置进行下腔静脉成像的准确度和便捷性。
在一个可能的示例中，所述方法还包括：所述医学成像装置在对目标用户进行手术的过程中，根据所述静脉内部切片影像进行术中导航。
其中，所述医学成像装置可以利用所述目标静脉的内部影像，在目标用户手术时，提供手术导航、实时对照和操作预警等。
可见，本示例中，所述医学成像装置可以基于目标静脉的内部影像进行术中导航，显著提高手术的效率和安全性。
与上述图2所示的实施例一致的，请参阅图3，图3是本申请实施例提供的一种医学成像装置300的结构示意图，如图所示，所述医学成像装置300包括处理器310、存储器320、通信接口330以及一个或多个程序321，其中，所述一个或多个程序321被存储在上述存储器320中，并且被配置由上述处理器310执行，所述一个或多个程序321包括用于执行以下步骤的指令；
根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，所述目标部位包括待观测的目标静脉和与所述目标静脉关联的动脉、肾脏、肝门；
根据所述BMP数据源生成第一医学影像数据，所述第一医学影像数据包括所述目标静脉的原始数据集合、所述部分动脉的原始数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的血管的原始数据集合和所述部分动脉的原始数据集合包括交叉位置的融合数据，所述目标静脉的血管的原始数据集合为所述目标静脉表面和所述目标静脉内部的组织结构的立方体空间的传递函数结果，所述部分动脉的原始数据集合为所述部分动脉表面和所述部分动脉内部的组织结构的立方体空间的传递函数结果，所述肾脏的数据集合为所述肾脏表面和所述肾脏内部的组织结构的立方体空间的传递函数结果，所述肝门的数据集合为所述肝门表面和所述肝门内部的组织结构的立方体空间的传递函数结果；
根据所述第一医学影像数据生成第二医学影像数据，所述第二医学影像数据包括所述目标静脉的分割数据集合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的分割数据集合的第一数据和所述部分动脉的分割数据集合的第二数据相互独立，所述第一数据和所述第二数据为所述交叉位置的数据；
处理所述第二医学影像数据得到目标医学影像数据；
提取所述目标医学影像数据中所述目标静脉的数据集合；
根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像。
可以看出，本申请实施例中，医学成像装置首先根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，其次，根据BMP数据源生成第一医学影像数据，再次，根据第一医学影像数据生成第二医学影像数据，再次，处理第二医学影像数据得到目标医学影像数据，然后提取目标医学影像数据中目标静脉的数据集合，最后根据目标静脉的数据集合进行4D医学成像以展示目标静脉的内部影像。其中，目标部位包括待观测的目标静脉和与目标静脉关联的动脉、肾脏、肝门，第一医学影像数据包括目标静脉的原始数据集合、部分动脉的原始数据集合、肾脏的数据集合、肝门的数据集合，目标静脉的血管的原始数据集合和部分动脉的原始数据集合包括交叉位置的融合数据，目标静脉的血管的原始数据集合为目标静脉表面和目标静脉内部的组织结构的立方体空间的传递函数结果，部分动脉的原始数据集合为部分动脉表面和部分动脉内部的组织结构的立方体空间的传递函数结果，肾脏的数据集合为肾脏表面和肾脏内部的组织结构的立方体空间的传递函数结果，肝门的数据集合为肝门表面和肝门内部的组织结构的立方体空间的传递函数结果，第二医学影像数据包括目标静脉的分割数据集合、部分动脉的分割数据集合、肾脏的数据集合、肝门的 数据集合，目标静脉的分割数据集合的第一数据和部分动脉的分割数据集合的第二数据相互独立，第一数据和第二数据为交叉位置的数据，可见，本申请的医学成像装置通过数据的预处理、分离、整合，并进行4D医学成像，有利于提高医学成像装置进行下腔静脉成像的准确度和便捷性。
在一个可能的示例中，在所述根据所述BMP数据源生成第一医学影像数据方面，所述程序中的指令具体用于执行以下操作：将所述BMP数据源导入预设的VRDS医学网络模型，通过所述VRDS医学网络模型调用预存的传递函数集合中的每个传递函数，通过所述传递函数集合中的多个传递函数处理所述BMP数据源，得到第一医学影像数据，所述传递函数集合包括通过反向编辑器预先设置的所述目标静脉的传递函数、动脉的传递函数、所述肾脏的传递函数和所述肝门的传递函数。
在一个可能的示例中，在所述根据所述第一医学影像数据生成第二医学影像数据方面，所述程序中的指令具体用于执行以下操作：将所述第一医学影像数据中的所述目标静脉的原始数据集合、所述部分动脉的原始数据集合导入所述交叉血管网络模型，通过所述交叉血管网络模型对所述交叉位置的融合数据进行空间分割处理，得到所述第一数据和所述第二数据；根据所述目标静脉的原始数据集合和所述第一数据生成所述目标静脉的分割数据集合，根据所述部分动脉的原始数据集合和所述第二数据生成所述部分动脉的分割数据集合；综合所述目标静脉的分割数据集合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门的数据集合，得到所述第二医学影像数据。
在一个可能的示例中，在所述处理所述第二医学影像数据得到目标医学影像数据方面，所述程序中的指令具体用于执行以下操作：针对所述第二医学影像数据执行以下至少一种处理操作得到目标医学影像数据：2D边界优化处理、3D边界优化处理、数据增强处理。
在一个可能的示例中，在所述2D边界优化处理方面，所述程序中的指令具体用于执行以下操作：多次采样获取低分辨率信息和高分辨率信息，其中，低分辨率信息能够提供分割目标在整个图像中上下文语义信息，即反映目标与环境之间关系的特征，所述分割目标包括所述目标静脉；在所述3D边界优化处理方面，所述程序中的指令具体用于执行以下操作：将所述第二医学影像数据分别放入3D卷积层中进行3D卷积操作，获取特征图；3D池化层对所述特征图进行压缩，并进行非线性激活；对压缩后的所述特征图进行级联操作，获取模型输出的预测结果图像。在所述数据增强处理方面，所述程序中的指令具体用于执行以下操作：基于任意角度旋转的数据增强、基于直方图均衡的数据增强、基于白平衡的数据增强、基于镜像操作的数据增强、基于随机剪切的数据增强和基于模拟不同光照变化的数据增强。
在一个可能的示例中，在所述根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像方面，所述程序中的指令具体用于执行以下操作：根据所述目标静脉的数据集合显示所述目标静脉的外侧壁影像；在检测到针对所述外侧壁影像的选择操作时，调取所述触控位置所处区域的所述目标静脉的内部数据；根据所述内部数据显示所述触控位置所处区域的静脉内部切片影像。
在一个可能的示例中，所述程序还包括用于执行以下操作的指令：在对目标用户进行手术的过程中，根据所述静脉内部切片影像进行术中导航。
在一个可能的示例中，在所述根据目标用户的目标部位的多张扫描图像确定位图BMP数据源方面，所述程序中的指令具体用于执行以下操作：获取通过医疗设备采集的反映目标用户的人体内部结构特征的多张扫描图像；从所述多张扫描图像中筛选出包含所述目标部位的至少一张扫描图像，将所述至少一张扫描图像作为目标用户的医学数字成像和通信DICOM数据；解析所述DICOM数据生成目标用户的图源，所述图源包括纹理Texture 2D/3D 图像体数据；针对所述图源执行第一预设处理得到所述BMP数据源，所述第一预设处理包括以下至少一种操作：VRDS限制对比度自适应直方图均衡、混合偏微分去噪、VRDS Ai弹性变形处理。
在一个可能的示例中，在所述VRDS限制对比度自适应直方图均衡方面，所述程序中的指令具体用于执行以下操作：区域噪音比度限幅、全局对比度限幅；将图源的局部直方图划分多个分区，针对每个分区，根据该分区的邻域的累积直方图的斜度确定变换函数的斜度，根据该变换函数的斜度确定该分区的像素值周边的对比度放大程度，然后根据该对比度放大程度进行限度裁剪处理，产生有效直方图的分布，同时也产生有效可用的邻域大小的取值，将这些裁剪掉的部分直方图均匀的分布到直方图的其他区域；在所述混合偏微分去噪方面，所述程序中的指令具体用于执行以下操作：通过VRDS Ai曲率驱动和VRDS Ai高阶混合去噪，使得图像边缘的曲率小于预设曲率，实现即可保护图像边缘、又可以避免平滑过程中出现阶梯效应的混合偏微分去噪模型；在所述VRDS Ai弹性变形处理方面，所述程序中的指令具体用于执行以下操作：在图像点阵上，叠加正负向随机距离形成差值位置矩阵，然后在每个差值位置上的灰度，形成新的点阵，可以实现图像内部的扭曲变形，再对图像进行旋转、扭曲、平移操作。
上述主要从方法侧执行过程的角度对本申请实施例的方案进行了介绍。可以理解的是，医学成像装置为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所提供的实施例描述的各示例的单元及算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本申请实施例可以根据上述方法示例对医学成像装置进行功能单元的划分，例如，可以对应各个功能划分各个功能单元，也可以将两个或两个以上的功能集成在一个处理单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。需要说明的是，本申请实施例中对单元的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
图4是本申请实施例中所涉及的基于VRDS Ai 4D医学影像的静脉的Ai内镜分析装置400的功能单元组成框图。该基于VRDS Ai 4D医学影像的静脉的Ai内镜分析装置400应用于医学成像装置，该基于VRDS Ai 4D医学影像的静脉的Ai内镜分析装置400包括处理单元和通信单元，其中，
所述处理单元，用于根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，所述目标部位包括待观测的目标静脉和与所述目标静脉关联的动脉、肾脏、肝门；以及用于根据所述BMP数据源生成第一医学影像数据，所述第一医学影像数据包括所述目标静脉的原始数据集合、所述部分动脉的原始数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的血管的原始数据集合和所述部分动脉的原始数据集合包括交叉位置的融合数据，所述目标静脉的血管的原始数据集合为所述目标静脉表面和所述目标静脉内部的组织结构的立方体空间的传递函数结果，所述部分动脉的原始数据集合为所述部分动脉表面和所述部分动脉内部的组织结构的立方体空间的传递函数结果，所述肾脏的数据集合为所述肾脏表面和所述肾脏内部的组织结构的立方体空间的传递函数结果，所述肝门的数据集合为所述肝门表面和所述肝门内部的组织结构的立方体空间的传递函数结果；以及用于根据所述第一医学影像数据生成第二医学影像数据，所述第二医学影像数据包括所述目标静脉的分割数据合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门 的数据集合，所述目标静脉的分割数据集合的第一数据和所述部分动脉的分割数据集合的第二数据相互独立，所述第一数据和所述第二数据为所述交叉位置的数据；以及用于处理所述第二医学影像数据得到目标医学影像数据；以及用于提取所述目标医学影像数据中所述目标静脉的数据集合；以及用于通过所述通信单元根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像。
其中，所述视频会议实现装置400还可以包括存储单元403，用于存储电子设备的程序代码和数据。所述处理单元401可以是处理器，所述通信单元402可以是触控显示屏或者收发器，存储单元403可以是存储器。
可以看出，本申请实施例中，医学成像装置首先根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，其次，根据BMP数据源生成第一医学影像数据，再次，根据第一医学影像数据生成第二医学影像数据，再次，处理第二医学影像数据得到目标医学影像数据，然后提取目标医学影像数据中目标静脉的数据集合，最后根据目标静脉的数据集合进行4D医学成像以展示目标静脉的内部影像。其中，目标部位包括待观测的目标静脉和与目标静脉关联的动脉、肾脏、肝门，第一医学影像数据包括目标静脉的原始数据集合、部分动脉的原始数据集合、肾脏的数据集合、肝门的数据集合，目标静脉的血管的原始数据集合和部分动脉的原始数据集合包括交叉位置的融合数据，目标静脉的血管的原始数据集合为目标静脉表面和目标静脉内部的组织结构的立方体空间的传递函数结果，部分动脉的原始数据集合为部分动脉表面和部分动脉内部的组织结构的立方体空间的传递函数结果，肾脏的数据集合为肾脏表面和肾脏内部的组织结构的立方体空间的传递函数结果，肝门的数据集合为肝门表面和肝门内部的组织结构的立方体空间的传递函数结果，第二医学影像数据包括目标静脉的分割数据集合、部分动脉的分割数据集合、肾脏的数据集合、肝门的数据集合，目标静脉的分割数据集合的第一数据和部分动脉的分割数据集合的第二数据相互独立，第一数据和第二数据为交叉位置的数据，可见，本申请的医学成像装置通过数据的预处理、分离、整合，并进行4D医学成像，有利于提高医学成像装置进行下腔静脉成像的准确度和便捷性。
在一个可能的示例中，在所述根据所述BMP数据源生成第一医学影像数据方面，所述处理单元401具体用于：将所述BMP数据源导入预设的VRDS医学网络模型，通过所述VRDS医学网络模型调用预存的传递函数集合中的每个传递函数，通过所述传递函数集合中的多个传递函数处理所述BMP数据源，得到第一医学影像数据，所述传递函数集合包括通过反向编辑器预先设置的所述目标静脉的传递函数、动脉的传递函数、所述肾脏的传递函数和所述肝门的传递函数。
在一个可能的示例中，在所述根据所述第一医学影像数据生成第二医学影像数据方面，所述处理单元401具体用于：将所述第一医学影像数据中的所述目标静脉的原始数据集合、所述部分动脉的原始数据集合导入所述交叉血管网络模型，通过所述交叉血管网络模型对所述交叉位置的融合数据进行空间分割处理，得到所述第一数据和所述第二数据；根据所述目标静脉的原始数据集合和所述第一数据生成所述目标静脉的分割数据集合，根据所述部分动脉的原始数据集合和所述第二数据生成所述部分动脉的分割数据集合；综合所述目标静脉的分割数据集合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门的数据集合，得到所述第二医学影像数据。
在一个可能的示例中，在所述处理所述第二医学影像数据得到目标医学影像数据方面，所述处理单元401具体用于：针对所述第二医学影像数据执行以下至少一种处理操作得到目标医学影像数据：2D边界优化处理、3D边界优化处理、数据增强处理。
在一个可能的示例中，在所述2D边界优化处理方面，所述处理单元401具体用于：多 次采样获取低分辨率信息和高分辨率信息，其中，低分辨率信息能够提供分割目标在整个图像中上下文语义信息，即反映目标与环境之间关系的特征，所述分割目标包括所述目标静脉；在所述3D边界优化处理方面，所述处理单元401具体用于：将所述第二医学影像数据分别放入3D卷积层中进行3D卷积操作，获取特征图；3D池化层对所述特征图进行压缩，并进行非线性激活；对压缩后的所述特征图进行级联操作，获取模型输出的预测结果图像。在所述数据增强处理方面，所述处理单元401具体用于：基于任意角度旋转的数据增强、基于直方图均衡的数据增强、基于白平衡的数据增强、基于镜像操作的数据增强、基于随机剪切的数据增强和基于模拟不同光照变化的数据增强。
在一个可能的示例中，在所述根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像方面，所述处理单元401具体用于：根据所述目标静脉的数据集合显示所述目标静脉的外侧壁影像；在检测到针对所述外侧壁影像的选择操作时，调取所述触控位置所处区域的所述目标静脉的内部数据；根据所述内部数据显示所述触控位置所处区域的静脉内部切片影像。
在一个可能的示例中，所述处理单元401还用于：在对目标用户进行手术的过程中，根据所述静脉内部切片影像进行术中导航。
在一个可能的示例中，在所述根据目标用户的目标部位的多张扫描图像确定位图BMP数据源方面，所述处理单元401具体用于：获取通过医疗设备采集的反映目标用户的人体内部结构特征的多张扫描图像；从所述多张扫描图像中筛选出包含所述目标部位的至少一张扫描图像，将所述至少一张扫描图像作为目标用户的医学数字成像和通信DICOM数据；解析所述DICOM数据生成目标用户的图源，所述图源包括纹理Texture 2D/3D图像体数据；针对所述图源执行第一预设处理得到所述BMP数据源，所述第一预设处理包括以下至少一种操作：VRDS限制对比度自适应直方图均衡、混合偏微分去噪、VRDS Ai弹性变形处理。
在一个可能的示例中，在所述VRDS限制对比度自适应直方图均衡方面，所述处理单元401具体用于：区域噪音比度限幅、全局对比度限幅；将图源的局部直方图划分多个分区，针对每个分区，根据该分区的邻域的累积直方图的斜度确定变换函数的斜度，根据该变换函数的斜度确定该分区的像素值周边的对比度放大程度，然后根据该对比度放大程度进行限度裁剪处理，产生有效直方图的分布，同时也产生有效可用的邻域大小的取值，将这些裁剪掉的部分直方图均匀的分布到直方图的其他区域；所述混合偏微分去噪包括以下步骤：通过VRDS Ai曲率驱动和VRDS Ai高阶混合去噪，使得图像边缘的曲率小于预设曲率，实现即可保护图像边缘、又可以避免平滑过程中出现阶梯效应的混合偏微分去噪模型；所述VRDS Ai弹性变形处理包括以下步骤：在图像点阵上，叠加正负向随机距离形成差值位置矩阵，然后在每个差值位置上的灰度，形成新的点阵，可以实现图像内部的扭曲变形，再对图像进行旋转、扭曲、平移操作。
本申请实施例还提供一种计算机存储介质，其中，该计算机存储介质存储用于电子数据交换的计算机程序，该计算机程序使得计算机执行如上述方法实施例中记载的任一方法的部分或全部步骤，上述计算机包括医学成像装置。
本申请实施例还提供一种计算机程序产品，上述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，上述计算机程序可操作来使计算机执行如上述方法实施例中记载的任一方法的部分或全部步骤。该计算机程序产品可以为一个软件安装包，上述计算机包括医学成像装置。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知 悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置，可通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如上述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。
上述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
上述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储器中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例上述方法的全部或部分步骤。而前述的存储器包括：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储器中，存储器可以包括：闪存盘、只读存储器(英文：Read-Only Memory，简称：ROM)、随机存取器(英文：Random Access Memory，简称：RAM)、磁盘或光盘等。
以上对本申请实施例进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。

Claims (20)

  1. 一种基于VRDS 4D医学影像的静脉的Ai内镜分析方法，其特征在于，应用于医学成像装置；所述方法包括：
    根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，所述目标部位包括待观测的目标静脉和与所述目标静脉关联的动脉、肾脏、肝门；
    根据所述BMP数据源生成第一医学影像数据，所述第一医学影像数据包括所述目标静脉的原始数据集合、所述部分动脉的原始数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的血管的原始数据集合和所述部分动脉的原始数据集合包括交叉位置的融合数据，所述目标静脉的血管的原始数据集合为所述目标静脉表面和所述目标静脉内部的组织结构的立方体空间的传递函数结果，所述部分动脉的原始数据集合为所述部分动脉表面和所述部分动脉内部的组织结构的立方体空间的传递函数结果，所述肾脏的数据集合为所述肾脏表面和所述肾脏内部的组织结构的立方体空间的传递函数结果，所述肝门的数据集合为所述肝门表面和所述肝门内部的组织结构的立方体空间的传递函数结果；
    根据所述第一医学影像数据生成第二医学影像数据，所述第二医学影像数据包括所述目标静脉的分割数据集合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的分割数据集合的第一数据和所述部分动脉的分割数据集合的第二数据相互独立，所述第一数据和所述第二数据为所述交叉位置的数据；
    处理所述第二医学影像数据得到目标医学影像数据；
    提取所述目标医学影像数据中所述目标静脉的数据集合；
    根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述BMP数据源生成第一医学影像数据，包括：
    将所述BMP数据源导入预设的VRDS医学网络模型，通过所述VRDS医学网络模型调用预存的传递函数集合中的每个传递函数，通过所述传递函数集合中的多个传递函数处理所述BMP数据源，得到第一医学影像数据，所述传递函数集合包括通过反向编辑器预先设置的所述目标静脉的传递函数、动脉的传递函数、所述肾脏的传递函数和所述肝门的传递函数。
  3. 根据权利要求1或2所述的方法，其特征在于，所述根据所述第一医学影像数据生成第二医学影像数据，包括：
    将所述第一医学影像数据中的所述目标静脉的原始数据集合、所述部分动脉的原始数据集合导入所述交叉血管网络模型，通过所述交叉血管网络模型对所述交叉位置的融合数据进行空间分割处理，得到所述第一数据和所述第二数据；
    根据所述目标静脉的原始数据集合和所述第一数据生成所述目标静脉的分割数据集合，根据所述部分动脉的原始数据集合和所述第二数据生成所述部分动脉的分割数据集合；
    综合所述目标静脉的分割数据集合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门的数据集合，得到所述第二医学影像数据。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，所述处理所述第二医学影像数据得到目标医学影像数据，包括：
    针对所述第二医学影像数据执行以下至少一种处理操作得到目标医学影像数据：2D边界优化处理、3D边界优化处理、数据增强处理。
  5. 根据权利要求4所述的方法，其特征在于，所述2D边界优化处理包括以下操作：多次采样获取低分辨率信息和高分辨率信息，其中，低分辨率信息能够提供分割目标在整个图像中上下文语义信息，即反映目标与环境之间关系的特征，所述分割目标包括所述目标 静脉；
    所述3D边界优化处理包括以下操作：将所述第二医学影像数据分别放入3D卷积层中进行3D卷积操作，获取特征图；3D池化层对所述特征图进行压缩，并进行非线性激活；对压缩后的所述特征图进行级联操作，获取模型输出的预测结果图像；
    所述数据增强处理包括以下至少一种：基于任意角度旋转的数据增强、基于直方图均衡的数据增强、基于白平衡的数据增强、基于镜像操作的数据增强、基于随机剪切的数据增强和基于模拟不同光照变化的数据增强。
  6. 根据权利要求1-5任一项所述的方法，其特征在于，所述根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像，包括：
    根据所述目标静脉的数据集合显示所述目标静脉的外侧壁影像；
    在检测到针对所述外侧壁影像的选择操作时，调取所述触控位置所处区域的所述目标静脉的内部数据；
    根据所述内部数据显示所述触控位置所处区域的静脉内部切片影像。
  7. 根据权利要求6所述的方法，其特征在于，所述方法还包括：
    在对目标用户进行手术的过程中，根据所述静脉内部切片影像进行术中导航。
  8. 根据权利要求1所述的方法，其特征在于，所述根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，包括：
    获取所述多张扫描图像；
    解析所述多张扫描图像的图像参数，所述图像参数包括以下至少一种：清晰度、准确度；
    根据所述图像参数筛选出大于预设图像参数，且包含目标器官的至少一张扫描图像；
    对所述至少一张扫描图像做图像预处理，得到位图BMP数据源。
  9. 根据权利要求1所述的方法，其特征在于，在所述提取所述目标医学影像数据中所述目标静脉的数据集合之前，所述方法还包括：
    从所述目标医学影像数据中筛选质量评分大于预设评分的增强数据作为成像数据；
    根据所述成像数据得到目标医学影像。
  10. 一种基于VRDS Ai 4D医学影像的静脉的Ai内镜分析装置，其特征在于，应用于医学成像装置；所述基于VRDS Ai 4D医学影像的静脉的Ai内镜分析装置包括处理单元和通信单元，其中，
    所述处理单元，用于根据目标用户的目标部位的多张扫描图像确定位图BMP数据源，所述目标部位包括待观测的目标静脉和与所述目标静脉关联的动脉、肾脏、肝门；以及用于根据所述BMP数据源生成第一医学影像数据，所述第一医学影像数据包括所述目标静脉的原始数据集合、所述部分动脉的原始数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的血管的原始数据集合和所述部分动脉的原始数据集合包括交叉位置的融合数据，所述目标静脉的血管的原始数据集合为所述目标静脉表面和所述目标静脉内部的组织结构的立方体空间的传递函数结果，所述部分动脉的原始数据集合为所述部分动脉表面和所述部分动脉内部的组织结构的立方体空间的传递函数结果，所述肾脏的数据集合为所述肾脏表面和所述肾脏内部的组织结构的立方体空间的传递函数结果，所述肝门的数据集合为所述肝门表面和所述肝门内部的组织结构的立方体空间的传递函数结果；以及用于根据所述第一医学影像数据生成第二医学影像数据，所述第二医学影像数据包括所述目标静脉的分割数据集合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门的数据集合，所述目标静脉的分割数据集合的第一数据和所述部分动脉的分割数据集合的第二数据相互独立，所述第一数据和所述第二数据为所述交叉位置的数据；以及用于处 理所述第二医学影像数据得到目标医学影像数据；以及用于提取所述目标医学影像数据中所述目标静脉的数据集合；以及用于通过所述通信单元根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像。
  11. 根据权利要求10所述的装置，其特征在于，在所述根据所述BMP数据源生成第一医学影像数据方面，所述处理单元具体用于：将所述BMP数据源导入预设的VRDS医学网络模型，通过所述VRDS医学网络模型调用预存的传递函数集合中的每个传递函数，通过所述传递函数集合中的多个传递函数处理所述BMP数据源，得到第一医学影像数据，所述传递函数集合包括通过反向编辑器预先设置的所述目标静脉的传递函数、动脉的传递函数、所述肾脏的传递函数和所述肝门的传递函数。
  12. 根据权利要求10或11所述的装置，其特征在于，在所述根据所述第一医学影像数据生成第二医学影像数据方面，所述处理单元具体用于：将所述第一医学影像数据中的所述目标静脉的原始数据集合、所述部分动脉的原始数据集合导入所述交叉血管网络模型，通过所述交叉血管网络模型对所述交叉位置的融合数据进行空间分割处理，得到所述第一数据和所述第二数据；根据所述目标静脉的原始数据集合和所述第一数据生成所述目标静脉的分割数据集合，根据所述部分动脉的原始数据集合和所述第二数据生成所述部分动脉的分割数据集合；综合所述目标静脉的分割数据集合、所述部分动脉的分割数据集合、所述肾脏的数据集合、所述肝门的数据集合，得到所述第二医学影像数据。
  13. 根据权利要求10-12任一项所述的装置，其特征在于，在所述处理所述第二医学影像数据得到目标医学影像数据方面，所述处理单元具体用于：针对所述第二医学影像数据执行以下至少一种处理操作得到目标医学影像数据：2D边界优化处理、3D边界优化处理、数据增强处理。
  14. 根据权利要求13所述的装置，其特征在于，所述2D边界优化处理包括以下操作：多次采样获取低分辨率信息和高分辨率信息，其中，低分辨率信息能够提供分割目标在整个图像中上下文语义信息，即反映目标与环境之间关系的特征，所述分割目标包括所述目标静脉；所述3D边界优化处理包括以下操作：将所述第二医学影像数据分别放入3D卷积层中进行3D卷积操作，获取特征图；3D池化层对所述特征图进行压缩，并进行非线性激活；对压缩后的所述特征图进行级联操作，获取模型输出的预测结果图像；所述数据增强处理包括以下至少一种：基于任意角度旋转的数据增强、基于直方图均衡的数据增强、基于白平衡的数据增强、基于镜像操作的数据增强、基于随机剪切的数据增强和基于模拟不同光照变化的数据增强。
  15. 根据权利要求10-14任一项所述的装置，其特征在于，在所述根据所述目标静脉的数据集合进行4D医学成像以展示所述目标静脉的内部影像方面，所述通信单元具体用于：根据所述目标静脉的数据集合显示所述目标静脉的外侧壁影像；在检测到针对所述外侧壁影像的选择操作时，调取所述触控位置所处区域的所述目标静脉的内部数据；根据所述内部数据显示所述触控位置所处区域的静脉内部切片影像。
  16. 根据权利要求15所述的装置，其特征在于，所述通信单元还具体用于：在对目标用户进行手术的过程中，根据所述静脉内部切片影像进行术中导航。
  17. 根据权利要求10所述的装置，其特征在于，在所述根据目标用户的目标部位的多张扫描图像确定位图BMP数据源方面，所述处理单元具体用于：获取所述多张扫描图像；解析所述多张扫描图像的图像参数，所述图像参数包括以下至少一种：清晰度、准确度；根据所述图像参数筛选出大于预设图像参数，且包含目标器官的至少一张扫描图像；对所述至少一张扫描图像做图像预处理，得到位图BMP数据源。
  18. 根据权利要求10所述的装置，其特征在于，在所述根据目标用户的目标部位的多 张扫描图像确定位图BMP数据源方面，所述处理单元还具体用于：从所述目标医学影像数据中筛选质量评分大于预设评分的增强数据作为成像数据；根据所述成像数据得到目标医学影像。
  19. 一种医学成像装置，其特征在于，包括处理器、存储器、通信接口，以及一个或多个程序，所述一个或多个程序被存储在所述存储器中，并且被配置由所述处理器执行，所述程序包括用于执行如权利要求1-9任一项所述的方法中的步骤的指令。
  20. 一种计算机可读存储介质，其特征在于，存储用于电子数据交换的计算机程序，其中，所述计算机程序使得计算机执行如权利要求1-9任一项所述的方法。
PCT/CN2019/101160 2019-02-22 2019-08-16 基于VRDS 4D医学影像的静脉的Ai内镜分析方法及产品 WO2020168698A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US17/432,483 US20220148162A1 (en) 2019-02-22 2019-08-16 Method and product for ai endoscope analyzing of vein based on vrds 4d medical images
AU2019430369A AU2019430369B2 (en) 2019-02-22 2019-08-16 VRDS 4D medical image-based vein Ai endoscopic analysis method and product
EP19916348.6A EP3929869A4 (en) 2019-02-22 2019-08-16 PROCEDURE FOR ENDOSCOPIC KI VEIN ANALYSIS BASED ON MEDICAL 4D VRDS IMAGES AND PRODUCT

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910132383.0A CN111612792B (zh) 2019-02-22 2019-02-22 基于VRDS 4D医学影像的静脉的Ai内镜分析方法及产品
CN201910132383.0 2019-02-22

Publications (1)

Publication Number Publication Date
WO2020168698A1 true WO2020168698A1 (zh) 2020-08-27

Family

ID=72144487

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/101160 WO2020168698A1 (zh) 2019-02-22 2019-08-16 基于VRDS 4D医学影像的静脉的Ai内镜分析方法及产品

Country Status (5)

Country Link
US (1) US20220148162A1 (zh)
EP (1) EP3929869A4 (zh)
CN (1) CN111612792B (zh)
AU (1) AU2019430369B2 (zh)
WO (1) WO2020168698A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112635029A (zh) * 2020-12-31 2021-04-09 上海联影智能医疗科技有限公司 一种医学影像处理方法、装置、终端及存储介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115482248B (zh) * 2022-09-22 2023-12-08 推想医疗科技股份有限公司 图像分割方法、装置、电子设备及存储介质
CN116188294B (zh) * 2022-12-22 2023-09-19 东莞理工学院 用于医学图像的数据增强方法、系统、智能终端及介质
CN116523940B (zh) * 2023-06-26 2023-09-01 聊城市第二人民医院 一种用于肾结石图像的轮廓分析系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104956405A (zh) * 2013-02-13 2015-09-30 三菱电机株式会社 用于模拟胸部4dct的方法
CN106170246A (zh) * 2014-01-17 2016-11-30 阿特瑞斯公司 用于四维(4d)流磁共振成像的设备、方法和产品
WO2017039663A1 (en) * 2015-09-03 2017-03-09 Siemens Healthcare Gmbh Multi-view, multi-source registration of moving anatomies and devices
CN106725846A (zh) * 2016-11-21 2017-05-31 厦门强本宇康科技有限公司 一种基于人体器官3d模型的手术仿真系统及方法

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1554695A2 (en) * 2002-10-16 2005-07-20 Koninklijke Philips Electronics N.V. Hierarchical image segmentation
WO2005055008A2 (en) * 2003-11-26 2005-06-16 Viatronix Incorporated Automated segmentation, visualization and analysis of medical images
CN101116103B (zh) * 2005-02-11 2010-05-19 皇家飞利浦电子股份有限公司 从三维医学图像中自动提取肺动脉树的方法
EP1790289A3 (en) * 2005-11-02 2007-07-18 Kabushiki Kaisha Toshiba X-ray computed tomography apparatus and method of analyzing X-ray computed tomogram data
CN101529475B (zh) * 2006-10-17 2013-12-25 皇家飞利浦电子股份有限公司 3d图像结合2d投影图像的呈现
CN101178814B (zh) * 2007-11-30 2010-09-08 华南理工大学 一种融合解剖与功能成像信息数据场的半透明体绘制方法
CN102222352B (zh) * 2010-04-16 2014-07-23 株式会社日立医疗器械 图像处理方法和图像处理装置
JP5263995B2 (ja) * 2011-03-18 2013-08-14 富士フイルム株式会社 ネットワーク構築装置および方法ならびにプログラム
KR101989156B1 (ko) * 2012-11-01 2019-06-13 삼성전자주식회사 장기의 영상에서 장기에 포함된 객체의 영상을 분리하는 방법, 장치 및 의료 영상 시스템
US10978184B2 (en) * 2013-11-04 2021-04-13 Terarecon, Inc. Evolving contextual clinical data engine for medical information
CN103646418B (zh) * 2013-12-31 2017-03-01 中国科学院自动化研究所 基于自动多阈值的多层着色体绘制方法
CN103745495A (zh) * 2014-02-08 2014-04-23 黑龙江八一农垦大学 基于医学体数据的体绘制方法
US9697603B2 (en) * 2014-12-19 2017-07-04 Toshiba Medical Systems Corporation Medical image data processing system and method for vessel segmentation using pre- and post-contrast data
WO2018015414A1 (en) * 2016-07-21 2018-01-25 Siemens Healthcare Gmbh Method and system for artificial intelligence based medical image segmentation
CN106204733B (zh) * 2016-07-22 2024-04-19 青岛大学附属医院 肝脏和肾脏ct图像联合三维构建系统
US10582907B2 (en) * 2016-10-31 2020-03-10 Siemens Healthcare Gmbh Deep learning based bone removal in computed tomography angiography
CN106991712A (zh) * 2016-11-25 2017-07-28 斯图尔特平李 一种基于hmds的医学成像系统
CN107049475A (zh) * 2017-04-19 2017-08-18 纪建松 肝癌局部消融方法及系统
US10692273B2 (en) * 2017-06-01 2020-06-23 Siemens Healthcare Gmbh In-context photorealistic 3D visualization for surgical decision support
CN107481254A (zh) * 2017-08-24 2017-12-15 上海术理智能科技有限公司 医学图像的处理方法、装置、介质和电子设备
CN108364297B (zh) * 2018-03-19 2020-08-14 青岛海信医疗设备股份有限公司 血管图像分割方法、终端、存储介质
CN108830870B (zh) * 2018-05-21 2021-12-28 千寻位置网络有限公司 基于多尺度结构学习的卫星影像高精度农田边界提取方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104956405A (zh) * 2013-02-13 2015-09-30 三菱电机株式会社 用于模拟胸部4dct的方法
CN106170246A (zh) * 2014-01-17 2016-11-30 阿特瑞斯公司 用于四维(4d)流磁共振成像的设备、方法和产品
WO2017039663A1 (en) * 2015-09-03 2017-03-09 Siemens Healthcare Gmbh Multi-view, multi-source registration of moving anatomies and devices
CN106725846A (zh) * 2016-11-21 2017-05-31 厦门强本宇康科技有限公司 一种基于人体器官3d模型的手术仿真系统及方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LV XIAO-QI; ZHANG CHUAN-TING; REN GUO-YIN; ZHANG BAO-HUA: "Four-dimensional visualization technology based on graphic processing unit for lung and pulmonary lesions", CHINESE JOURNAL OF MEDICAL IMAGING TECHNOLOGY, vol. 29, no. 11, 20 November 2013 (2013-11-20), CN, pages 1901 - 1905, XP055730683, ISSN: 1003-3289, DOI: 10.13929/j.1003-3289.2013.11.001 *
See also references of EP3929869A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112635029A (zh) * 2020-12-31 2021-04-09 上海联影智能医疗科技有限公司 一种医学影像处理方法、装置、终端及存储介质

Also Published As

Publication number Publication date
CN111612792A (zh) 2020-09-01
EP3929869A1 (en) 2021-12-29
US20220148162A1 (en) 2022-05-12
EP3929869A4 (en) 2022-12-14
CN111612792B (zh) 2024-03-08
AU2019430369A1 (en) 2021-09-16
AU2019430369B2 (en) 2023-05-25

Similar Documents

Publication Publication Date Title
US20190156526A1 (en) Image color adjustment method and system
US10713856B2 (en) Medical imaging system based on HMDS
WO2020168698A1 (zh) 基于VRDS 4D医学影像的静脉的Ai内镜分析方法及产品
WO2021030995A1 (zh) 基于vrds ai下腔静脉影像的分析方法及产品
WO2021081771A1 (zh) 基于vrds ai医学影像的心脏冠脉的分析方法和相关装置
WO2020173054A1 (zh) Vrds 4d医学影像处理方法及产品
WO2020173055A1 (zh) VRDS 4D医学影像多设备Ai联动显示方法及产品
WO2020168695A1 (zh) 基于VRDS 4D医学影像的肿瘤与血管Ai处理方法及产品
WO2020168694A1 (zh) 基于VRDS 4D医学影像的肿瘤Ai处理方法及产品
WO2020168697A1 (zh) 基于VRDS 4D医学影像的栓塞的Ai识别方法及产品
WO2021081772A1 (zh) 基于vrds ai脑部影像的分析方法和相关装置
WO2021081839A1 (zh) 基于vrds 4d的病情分析方法及相关产品
WO2021081850A1 (zh) 基于vrds 4d医学影像的脊椎疾病识别方法及相关装置
WO2021081842A1 (zh) 基于vrds ai医学影像的肠肿瘤与血管分析方法和相关装置
WO2020168696A1 (zh) 基于VRDS 4D医学影像的动脉与静脉Ai处理方法及产品
WO2021030994A1 (zh) 基于vrds ai静脉影像的识别方法及产品
WO2021081835A1 (zh) 基于VRDS 4D医学影像的动脉瘤Ai处理方法及产品
WO2021081836A1 (zh) 基于vrds 4d医学影像的胃肿瘤识别方法及相关产品

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19916348

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2019430369

Country of ref document: AU

Date of ref document: 20190816

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2019916348

Country of ref document: EP

Effective date: 20210922