WO2021081842A1 - Intestinal neoplasm and vascular analysis method based on vrds ai medical image and related device - Google Patents

Abstract

An intestinal neoplasm and vascular analysis method based on a VRDS AI medical image, and a related device. The method comprises: obtaining a scanned image of an intestinal canal of a user, wherein the scanned image further comprises an intestinal neoplasm and a blood vessel around the intestinal canal (S201); generating image data of the intestinal canal, image data of the intestinal neoplasm, and image data of the blood vessel according to the scanned image (S202); and determining a position area of the intestinal neoplasm in the intestinal canal and the number and distribution of supplying vessels of the intestinal neoplasm according to the image data of the intestinal canal, the image data of the intestinal neoplasm, and the image data of the blood vessel, and performing 4D medical imaging on the image data of the intestinal canal, the image data of the intestinal neoplasm, and the image data of the blood vessel to output the intestinal neoplasm and the number and distribution of supplying vessels (S203). The intestinal neoplasm and vascular analysis method and the related device can improve the diagnostic efficiency of enteric diseases.

Description

Intestinal tumor and blood vessel analysis method and related devices based on VRDS AI medical image Technical field

This application relates to the technical field of medical imaging devices, and in particular to intestinal tumor and blood vessel analysis methods and related devices based on VRDS AI medical imaging.

Background technique

At present, doctors use Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Diffusion Tensor Imaging (DTI), and Positron Emission Computed Tomography (Computed Tomography). Tomography, PET) and other technologies obtain information such as the shape, location, and topology of the intestinal tract. Doctors still use continuous two-dimensional slice scan images to view and read in order to diagnose the condition. However, the two-dimensional slice scan image cannot show the spatial structure of the intestine, which affects the doctor's diagnosis of the disease. With the rapid development of medical imaging technology, people have put forward new demands for medical imaging.

Summary of the invention

The embodiments of the present application provide methods and related devices for analyzing intestinal tumors and blood vessels based on VRDS AI medical images. Implementing the embodiments of the present application can improve the diagnosis efficiency of intestinal diseases.

The first aspect of the embodiments of the present application provides a method for intestinal tumor and blood vessel analysis based on VRDS AI medical imaging, including:

Acquiring a scanned image of the user's intestine, where the scanned image further includes intestinal tumors and blood vessels around the intestine;

Generating image data of the intestine, image data of the intestine tumor, and image data of the blood vessel according to the scanned image;

Determining the location area of the intestinal tumor in the intestine and the number and distribution of blood supply vessels of the intestinal tumor according to the imaging data of the intestine, the imaging data of the intestinal tumor, and the imaging data of the blood vessel;

Perform 4D medical imaging on the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel to output the location area and the number and distribution of the blood supply blood vessel.

A second aspect of the embodiments of the present application provides a medical imaging device, including:

An acquisition module for acquiring a scanned image of the user's intestine, wherein the scanned image further includes intestinal tumors and blood vessels around the intestine;

A generating module for generating image data of the intestine, image data of the intestine tumor, and image data of the blood vessel according to the scanned image;

The determining module is used to determine the location area of the intestine tumor in the intestine and the blood supply vessel of the intestine tumor according to the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel. Quantity and distribution;

The output module is used to perform 4D medical imaging on the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel to output the location area and the number and distribution of the blood supply vessel.

A third aspect of the embodiments 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 are generated It is executed by the processor to execute the instructions of the steps in any one of the methods of the first aspect of the above claims.

The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, where the computer-readable storage medium is used to store a computer program, and the stored computer program is executed by the processor to implement the first aspect of the claims. Any of the methods.

It can be seen that in the above technical solution, a scanned image of the user’s intestine is acquired, where the scanned image also includes the intestinal tumor and blood vessels around the intestine, and the image data of the intestine, the image data of the intestinal tumor and the blood vessels are generated according to the scanned image. Then, according to the image data of the intestine, the image data of the intestinal tumor, and the image data of the blood vessel, determine the location area of the intestinal tumor and the number and distribution of the blood supply vessels of the intestinal tumor, so as to realize the rapid response to the intestinal disease Diagnosis, to avoid the problem of low efficiency in diagnosing intestinal diseases due to the inability of the two-dimensional slice scan image to show the spatial structure of the intestine. At the same time, 4D medical imaging is performed on intestinal imaging data, intestinal tumor imaging data, and blood vessel imaging data to output the location area and the number and distribution of blood vessels, which facilitates doctors to locate symptoms and improves the diagnosis efficiency of intestinal diseases.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

among them:

FIG. 1 is a schematic structural diagram of an intestinal tumor and blood vessel analysis system based on VRDS AI medical imaging according to an embodiment of the application;

2A is a schematic flowchart of a method for analyzing intestinal tumors and blood vessels based on VRDS AI medical imaging according to an embodiment of the application;

2B is a schematic diagram of a coordinate system provided by an embodiment of this application;

FIG. 3 is a schematic flowchart of yet another method for analyzing intestinal tumors and blood vessels based on VRDS AI medical imaging according to an embodiment of the application;

4 is a schematic diagram of a medical imaging device provided by an embodiment of the application;

FIG. 5 is a schematic structural diagram of a medical imaging device in a hardware operating environment related to an embodiment of the application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by a person of ordinary skill in the art without creative work shall fall within the protection scope of this application.

Detailed descriptions are given below.

The terms "first", "second", and "third" in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific sequence. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

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. Correspondence. "DICOM data" refers to the original image file data that reflects the internal structural characteristics of the human body collected by medical equipment, which can include electronic computed tomography CT, magnetic resonance MRI, diffusion tensor imaging DTI, and positron emission computed tomography PET- For information such as CT, "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).

First, referring to Fig. 1, Fig. 1 is a schematic structural diagram of an intestinal tumor and blood vessel analysis system 100 based on VRDS AI medical imaging according to an embodiment of the present application. The system 100 includes a medical imaging device 110 and a network database 120. The medical imaging The device 110 may include a local medical imaging device 111 and/or a terminal medical imaging device 112. The local medical imaging device 111 or the terminal medical imaging device 112 is used for the VRDS AI medical imaging based on the original DICOM data presented in the embodiment of this application. Based on the analysis algorithm of intestinal tumors and blood vessels, it carries out the recognition, positioning, four-dimensional volume rendering, and abnormal analysis of the human intestinal image area to realize the four-dimensional stereo imaging effect (the four-dimensional medical image specifically refers to the medical image including the inside of the displayed tissue Spatial structural features and external spatial structural features. The internal spatial structural features mean that the slice data inside the tissue is not lost, that is, the medical imaging device can present the internal structure of tissues such as intestines and blood vessels. The external spatial structural characteristics refer to tissues and tissues. The environmental characteristics between the tissues, including the spatial location characteristics between tissues (including intersections, intervals, fusions, etc., such as the edge structure characteristics of the intersection between arteries and veins, etc.), the local medical imaging device 111 is relative to the terminal The medical imaging device 112 can also be used to edit the scanned image to form a transfer function result of a four-dimensional human body image. The transfer function result may include the transfer function result of the surface of the human intestine and the tissue structure in the human intestine, and the transfer of the cube space. Function results, such as the number of cube edit boxes and arc edit arrays, coordinates, colors, transparency and other information required by the transfer function. The network database 120 may be, for example, a cloud medical imaging device, etc. 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 scanned image may be from Multiple local medical imaging devices 111 are used to realize interactive diagnosis of multiple doctors.

When the user performs specific image display through the above-mentioned medical imaging device 110, he can select a display or a head-mounted display (Head-mounted Displays Set, HMDS) of virtual reality VR to display in combination with operating actions. The operating actions refer to the user’s actions through the medical imaging device. External ingestion equipment, such as mouse, keyboard, tablet (portable android device, Pad), iPad (internet portable apple device), etc., operate and control the four-dimensional human image to achieve human-computer interaction. The operation actions include at least the following One: (1) Change the color and/or transparency of a specific organ/tissue, (2) Position the zoom view, (3) Rotate the view, realize the multi-view 360-degree observation of the four-dimensional human body image, (4) "Enter" Observe the internal structure of human organs, render real-time clipping effects, and (5) move the view up and down.

Refer to FIG. 2A, which is a schematic flowchart of a method for analyzing intestinal tumors and blood vessels based on VRDS AI medical imaging according to an embodiment of the application. Wherein, as shown in FIG. 2A, an intestinal tumor and blood vessel analysis method based on VRDS AI medical imaging provided by an embodiment of the present application may include:

201. A medical imaging device acquires a scanned image of a user's intestine, where the scanned image further includes an intestinal tumor and blood vessels around the intestine.

Wherein, the scan image includes any one of the following: CT image, MRI image, DTI image, PET-CT image.

202. The medical imaging device generates image data of the intestine, image data of the intestine tumor, and image data of the blood vessel according to the scanned image.

Among them, blood vessels include arteries and veins. Further, the arteries may include, for example, superior mesenteric artery, inferior mesenteric artery, and the like. The veins may include mesenteric veins and the like, for example.

Wherein, the image data of the intestine includes the three-dimensional image data of the intestine, the image data of the intestinal tumor includes the three-dimensional image data of the intestinal tumor, and the image data of the blood vessel includes the three-dimensional image data of the blood vessel. Spatial image data.

203. The medical imaging device determines the location area of the intestine tumor in the intestine and the blood supply vessel of the intestine tumor according to the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel. Quantity and distribution.

Wherein, in a possible implementation manner, the location area of the intestine tumor in the intestine is determined according to the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel. The number and distribution of blood supply vessels of the intestinal tumor includes: determining the location area according to the image data of the intestine and the image data of the intestine tumor; determining the location area of each blood vessel in the image data of the blood vessel , To obtain multiple blood vessel location information; determine the number and distribution of the blood supply vessels according to the location area and the multiple blood vessel location information.

For example, the image data of the blood vessel includes multiple blood vessels, where the first blood vessel is any one of the multiple blood vessels. It is assumed that the blood vessel position information corresponding to the first blood vessel is related to the intestinal tumor in the intestinal tract. If the position and area match of, it is determined that the first blood vessel is the blood supply vessel of the intestinal tumor.

Further, the determining the number and distribution of the blood supply vessels according to the position area and the position information of the plurality of blood vessels includes: matching the position area and the position information of the plurality of blood vessels; and determining according to the matching result The number and distribution of the blood supply vessels.

Wherein, each blood vessel position information in the multiple blood vessel position information includes multiple spatial positions of each blood vessel distributed in the image data of the blood vessel.

For example, the first blood vessel position information is any one of the multiple blood vessel position information, and the first blood vessel position information may include: (X1, Y1, Z1), (X2, Y2, Z2), and ( X3, Y3, Z3) and so on.

It can be seen that in the above technical solution, the location area is determined according to the image data of the intestine and the image data of the intestine tumor, and then the location area of each blood vessel in the image data of the blood vessel is determined to obtain multiple blood vessel location information. Finally, The number and distribution of blood supply vessels are determined according to the location area and the location information of multiple blood vessels, thereby improving the accuracy of determining the location area of the bowel tumor in the intestine and the number and distribution of the blood supply blood vessels of the bowel tumor.

Further, optionally, in a possible implementation manner, the determining the location area according to the imaging data of the intestine and the imaging data of the intestinal tumor includes: combining the imaging data of the intestine Compare with the image data of the intestine tumor to determine the first image data matching the image data of the intestine tumor in the image data of the intestine; determine the image of the first image data in the intestine The spatial position in the data; the spatial position is set as the position area.

It can be seen that in the above technical solution, the intestinal imaging data is compared with the intestinal tumor imaging data to determine the first image data matching the intestinal tumor imaging data in the intestinal imaging data, thereby determining the first image data. The spatial position of the image data in the image data of the intestine, thereby determining the location area, improves the accuracy of determining the location area of the intestine tumor in the intestine.

Optionally, in a possible implementation manner, the imaging data of the intestine is compared with the imaging data of the intestine tumor to determine the difference between the imaging data of the intestine and the intestine tumor. The first image data matched by the image data includes: segmenting the image data of the intestine according to the category to which the intestine belongs to obtain multiple image sub-data of the intestine; Each image sub-data in the image sub-data performs the following steps, including: determining the target intestine included in the currently processed image sub-data; obtaining template image sub-data according to the target intestine included in the currently processed image sub-data, wherein The template image sub-data includes image data of the target intestine in a healthy state; compare the currently processed image sub-data with the template image sub-data; if the currently processed image sub-data does not match the template image sub-data , Acquire the second image sub-data that does not match the template image sub-data in the currently processed image sub-data, and compare the second image sub-data with the image data of the bowel tumor to determine the first The second image sub-data is the first image data.

For example, if the target intestine is the small intestine, then the template image sub-data includes image data of the small intestine in a healthy state.

Optionally, in a possible implementation manner, the comparing the currently processed image sub-data with the template image sub-data includes: establishing a first coordinate system according to the currently processed image sub-data, and the first coordinate system The origin of a coordinate system is the center of the target intestine, and the X, Y, and Z axes of the first coordinate system are perpendicular to each other and follow the right-hand spiral law; starting from the origin of the first coordinate system, follow the The preset distance is along the positive and negative directions of the Z axis of the first coordinate system to extract multiple layers of first intestinal cell layers from the currently processed image sub-data; and combine the multiple layers of first intestinal cell layers with A comparison is made with multiple second intestinal cell layers, which are extracted from the template image sub-data.

Wherein, each layer of the first intestinal cell layer includes a first intestinal cell data set and feature data corresponding to the first intestinal cell data set, and the feature data corresponding to the first intestinal cell data set includes the first intestinal cell data set. The shape corresponding to each first intestinal cell data in the first intestinal cell data set, the size corresponding to each first intestinal cell data in the first intestinal cell data set, and each in the first intestinal cell data set The spatial location of the first intestinal cell data;

Each second intestinal cell layer includes a second intestinal cell data set and feature data corresponding to the second intestinal cell data set, and the feature data corresponding to the second intestinal cell data set includes the second intestine The shape corresponding to each second intestinal cell data in the tract cell data set, the size corresponding to each second intestinal cell data in the second intestinal cell data set, and each second intestinal cell data in the second intestinal cell data set. The spatial location of the intestinal cell data.

Wherein, the first intestinal cell layer is any intestinal cell layer in the multi-layer first intestinal cell layer, and the second intestinal cell layer is the multi-layer second intestinal cell layer and the The first intestinal cell layer has an associated cell layer, and the associated relationship is the spatial position and location of each first intestinal cell data in the first intestinal cell data set included in the first intestinal cell layer. The second intestinal cell data set included in the second intestinal cell layer matches the spatial position of each second intestinal cell data set, and the first intestinal cell layer is compared with the second intestinal cell layer , Including: acquiring the first intestinal cell data set included in the first intestinal cell layer and characteristic data corresponding to the first intestinal cell data set; and separately collecting the first intestinal cell data set for each The shape and size corresponding to the first intestinal cell data are compared with the shape and size corresponding to each second intestinal cell data in the second intestinal cell data set.

It can be seen that in the above technical solution, by comparing the currently processed image sub-data with the template image sub-data, it is possible to find out the abnormal image data in the currently processed image sub-data more accurately, which improves the efficiency of data comparison. .

Optionally, in a possible implementation manner, the position of the intestinal tumor in the intestine is determined based on the imaging data of the intestine, the imaging data of the intestinal tumor, and the imaging data of the blood vessel The area and the number and distribution of blood supply vessels of the intestinal tumor include: determining the location area according to the imaging data of the intestine and the imaging data of the intestinal tumor; and determining the location area according to the imaging data of the blood vessel and the intestinal tumor Determine the connection position and connection angle of each blood vessel with the intestinal tumor from the image data; determine the number and distribution of the blood supply blood vessels according to the connection position and the connection angle.

It can be seen that in the above technical solution, the location area is determined based on the image data of the intestine and the image data of the intestinal tumor, and then the connection position and angle of connection between each blood vessel and the intestine tumor are determined according to the image data of the blood vessel and the image data of the intestine tumor. Finally, the number and distribution of blood supply vessels are determined according to the connection position and connection angle, which improves the accuracy of determining the location area of intestinal tumors in the intestine and the number and distribution of blood supply vessels for intestinal tumors.

204. The medical imaging device performs 4D medical imaging on the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel to output the location area and the number and distribution of the blood supply vessels.

It can be seen that in the above technical solution, a scanned image of the user’s intestine is acquired, where the scanned image also includes the intestinal tumor and blood vessels around the intestine, and the image data of the intestine, the image data of the intestinal tumor and the blood vessels are generated according to the scanned image. Then, according to the image data of the intestine, the image data of the intestinal tumor, and the image data of the blood vessel, determine the location area of the intestinal tumor and the number and distribution of the blood supply vessels of the intestinal tumor, so as to realize the rapid response to the intestinal disease Diagnosis, to avoid the problem of low efficiency in diagnosing intestinal diseases due to the inability of the two-dimensional slice scan image to show the spatial structure of the intestine. At the same time, 4D medical imaging is performed on intestinal imaging data, intestinal tumor imaging data, and blood vessel imaging data to output the location area and the number and distribution of blood vessels, which facilitates doctors to locate symptoms and improves the diagnosis efficiency of intestinal diseases.

Optionally, in a possible implementation manner, said generating the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel according to the scan image includes: performing a first operation on the scan image. Preset processing to obtain a bitmap BMP data source; import the BMP data source into a preset VRDS medical network model to obtain first medical image data, where the first medical image data includes a first data set of the intestine and The data set of the blood vessel, the first data set of the intestine includes the data set of the intestinal tumor, the data set of the blood vessel includes the fusion data of the intersection position of the artery and the vein, and the first data of the intestine The set is the transfer function result of the cube space of the tissue structure inside the intestine and the surface of the intestine, and the data set of the blood vessel is the transfer function result of the cube space of the tissue structure inside the blood vessel and the surface of the blood vessel Importing the first medical image data into a preset cross-vascular network model to obtain second medical image data, the second medical image data including a first data set of the intestine, a data set of the arteries, and The data set of the vein, and the first data in the data set of the artery and the second data in the data set of the vein are independent of each other, and the first data is the data associated with the intersection position, so The second data is data associated with the intersection position; the second medical image data is processed to obtain image data of the intestine, image data of the intestine tumor, and image data of the blood vessel.

Wherein, 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.

Wherein, the VRDS limited contrast adaptive histogram equalization includes the following steps: performing regional noise ratio limiting and global contrast limiting on the image source; dividing the local histogram of the image source into multiple partitions; The slope of the cumulative histogram of the neighborhood of each of the multiple partitions determines multiple slopes of the multiple transformation functions; the pixels of each of the multiple partitions are determined according to the multiple slopes The degree of contrast magnification around the value; according to the degree of contrast magnification around the pixel value of each of the multiple partitions, the multiple partitions are subject to limited cropping processing to obtain the distribution of the effective histogram and the effectively usable neighborhood The value of the size; the histogram cut by the limit is evenly distributed to other areas of the local histogram of the image source.

The hybrid partial differential denoising includes the following steps: the image source is processed 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 edge of the image, and The mixed partial differential denoising model that can avoid the step effect in the smoothing process;

The VRDS Ai elastic deformation processing includes the following steps: acquiring the image dot matrix of the image source, superimposing the positive and negative random distances on the image dot matrix to form a difference position matrix, and for each of the difference position matrix Perform grayscale processing on each difference position to obtain a new difference position matrix, so as to realize the distortion inside the image, and then perform rotation, distortion, and translation operations on the image.

Wherein, the hybrid partial differential denoising is processed by the medical imaging device using a CDD and a high-order denoising model to process the image source.

Wherein, the CDD model (Curvature Driven Diffusions) model is formed by introducing a curvature drive on the basis of the TV (Total Variation) model, which solves the problem that the TV model cannot repair the visual connectivity of the image.

Wherein, the high-order denoising refers to denoising the image based on a partial differential equation (PDE) method. In specific implementation, the image source is subjected to a noise filtering effect according to the specified differential equation function change to obtain the BMP data source. Among them, the solution of the partial differential equation is the BMP data source obtained after high-order denoising. The PDE-based image denoising method has the characteristics of anisotropic diffusion, so it can perform different degrees in different regions of the image source. The effect of diffusion, so as to achieve the effect of suppressing noise while protecting the edge texture information of the image.

It can be seen that in this example, 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 image quality and protect the edge texture of the image.

Wherein, in a possible implementation manner, the performing the first preset processing on the scanned image to obtain the bitmap BMP data source includes: setting the scanned image as the user's medical digital imaging and communication DICOM Data; parsing the DICOM data to generate the image source of the user, the image source including texture 2D/3D image volume data; performing the first preset processing on the image source to obtain the BMP data source.

Among them, the DICOM (Digital Imaging and Communications in Medicine) refers to medical digital imaging and communication, and is an international standard for medical images and related information. In specific implementation, the medical imaging device first acquires multiple scanned images that reflect the internal structural characteristics of the user's intestines, and can screen out at least one suitable scanned image containing the intestinal tract based on clarity, accuracy, etc. Further processing is performed on the scanned image to obtain a bitmap BMP data source.

It can be seen that, in this example, 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.

It can be seen that in this example, the medical imaging device processes the scanned image into image data that can reflect the spatial structure characteristics of the intestine through a series of data processing, and the venous image data and arterial image data at the crossing position are independent of each other, supporting three-dimensional Accurate presentation of space improves the accuracy and comprehensiveness of data processing.

In a possible example of the present application, the importing the BMP data source into the preset VRDS medical network model to obtain the first medical image data includes: importing the BMP data source into the preset VRDS medical network model , Call each transfer function in the set of pre-stored transfer functions through the VRDS medical network model, and process the BMP data source through multiple transfer functions in the transfer function set to obtain the first medical image data. The function set includes the transfer function of the intestine and the transfer function of the blood vessel preset by a reverse editor.

Among them, BMP (full name Bitmap) is a standard image file format in the Windows operating system, which can be divided into two categories: device-dependent bitmap (DDB) and device-independent bitmap (DIB). The scan image includes any one of the following: CT image, MRI image, DTI image, PET-CT image.

Wherein, 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. In the implementation process, first sampling will be required to obtain N BMP data sources, and then M BMP data sources will be extracted from the 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, the width is S pixels), and the resulting processing result is used as the input of the 3D convolutional neural network . In this way, M BMP data sources are used as the input of the 3D convolutional neural network. Specifically, a 3D convolutional neural network is used to perform 3D convolution processing on the BMP data source to obtain a feature map.

Optionally, in a possible implementation manner, the medical imaging device extracts the first data from the blood vessel data set including the fusion data of the intersection of the artery and the vein, and uses a preset data separation algorithm to separate The fusion data is separated to obtain arterial boundary point data.

The second data is extracted by the medical imaging device from the fusion data of the intersection position of the artery and the vein in the blood vessel data set, and the fusion data is separated by using a preset data separation algorithm to obtain the vein boundary point data.

Wherein, the second preset processing includes at least one of the following operations: 2D boundary optimization processing, 3D boundary optimization processing, and data enhancement processing.

Wherein, the 2D boundary optimization processing includes: multiple sampling to obtain low-resolution information and high-resolution information, where the low-resolution information can provide contextual semantic information of the segmentation target in the entire image, that is, reflecting the segmentation target and the environment The features of the relationship between these features are used to determine the object category, and the high-resolution information is used to provide more refined features, such as gradients, for the segmentation target.

Among them, segmentation targets include intestines, arteries and veins.

The 3D boundary optimization processing includes: 3D convolution, 3D max pooling, and 3D upward convolution layer, the input data size is a1, a2, a3, the number of channels is c, the filter size is f, that is, the filter dimension is f*f*f*c, the number of filters is n, the final output of the 3-dimensional convolution is:

(a1-f+1)*(a2-f+1)*(a3-f+1)*n

With analysis path and synthesis path. In the analysis path, each layer contains two 3*3*3 convolution kernels, each of which is followed by an activation function (Relu), and then there is a maximum pooling of 2*2*2 in each dimension to merge the two Steps. In the synthesis path, each layer is composed of 2*2*2 upward convolutions, with a step size of 2 in each dimension, and then two 3*3*3 convolutions, and then Relu. Then in the analysis path, the shortcut connections of equal resolution layers provide the basic high-resolution features of the synthesized path. In the last layer, 1*1*1 convolution reduces the number of output channels.

Further, the 3D boundary optimization processing includes the following operations: inputting the second medical image data into a 3D convolution layer to perform a 3D convolution operation to obtain a feature map; inputting the feature map to a 3D pooling layer for pooling And non-linear activation to obtain a first feature map; cascading the first feature map to obtain a prediction result.

Wherein, the data enhancement processing includes any 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 operation, data enhancement based on random cut And data enhancement based on simulating different lighting changes.

Optionally, in a possible implementation manner, the first data set of the intestines further includes fusion data of the cross positions of the intestines, and the second medical image data is processed to obtain all the data. The image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel include: importing the second medical image data into a preset cross-intestinal network model to obtain third medical image data, so The third medical image data includes a second data set of the intestine, a data set of the arteries, and a data set of the veins, and the second data set of the intestine includes the separation of the cross positions of the intestines Data, the surface features of the intestine and the data collection of the intestinal tumor; performing a second preset processing on the third medical image data to obtain the image data of the intestine, the image data of the intestine tumor, and The image data of the blood vessel.

It can be seen that in the above technical solution, the second medical image data is imported into the preset cross-intestinal network model to obtain the third medical image data. The third medical image data includes the second data set of the intestine and the data set of the arteries. As well as the data set of veins, the second data set of the intestine includes the separation data of the cross position of the intestine, the surface characteristics of the intestine and the data set of the intestinal tumor. Then, the second preset processing is performed on the third medical image data to Obtain intestinal imaging data, intestinal tumor imaging data, and blood vessel imaging data, so that the medical imaging data can better restore the original organs or tissues, improve the authenticity of medical imaging data, facilitate doctors to locate symptoms, and improve intestinal diseases Diagnostic efficiency

Optionally, in a possible implementation manner, the 4D medical imaging is performed on the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel to output the location area and The quantity and distribution of the blood supply vessels include: acquiring image data of the intestine, the image data of the intestine tumor, and multiple image quality scores corresponding to the image data of the blood vessel, respectively; according to the multiple image quality The score selects a plurality of enhanced data with an image quality score greater than a preset image quality score from the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel; Perform 4D medical imaging to output the location area and the number and distribution of the blood supply vessels.

Wherein, the multiple image quality scores include multiple image quality scores corresponding to the image data of the intestine, multiple image quality scores corresponding to the image data of the intestine tumor, and multiple image quality scores corresponding to the image data of the blood vessel. Image quality score.

Wherein, the plurality of enhancement data includes enhancement data with an image quality score greater than the preset image quality score in the image data of the intestine, and an image quality score greater than the preset image quality in the image data of the bowel tumor The scored enhancement data and the enhancement data of the image data of the blood vessel with an image quality score greater than the preset image quality score.

It can be seen that in the above technical solution, multiple image quality scores corresponding to the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel are obtained respectively; according to the multiple image quality scores, the image data of the intestine, Intestinal tumor image data and blood vessel image data, multiple enhancement data with image quality scores greater than the preset image quality score are screened out; multiple enhancement data are subjected to 4D medical imaging to output the location area and the number and distribution of blood vessels, Thereby assisting doctors in rapid diagnosis and improving the diagnosis efficiency of intestinal diseases. At the same time, the use of enhanced data for 4D medical imaging improves image clarity and accuracy.

Optionally, in a possible implementation manner, the method further includes: establishing a coordinate system according to the imaging data of the intestinal tumor, the origin of the coordinate system is the center of the intestinal tumor, and the X of the coordinate system The axis, Y axis, and Z axis are perpendicular to each other and follow the right-handed spiral rule; starting from the origin of the coordinate system, follow the preset distance along the positive and negative directions of the Z axis of the coordinate system from the bowel tumor Multi-layer intestinal tumor cell layers are extracted from the image data, and each intestinal tumor cell layer includes an intestinal tumor cell data set; preset processing is performed on each intestinal tumor cell layer in the multi-layer intestinal tumor cell layer to obtain the first An intestinal tumor cell data set, where the first intestinal tumor cell data set is the outermost intestinal tumor cell data in the intestinal tumor; determining the growth cycle corresponding to the intestinal tumor according to the first intestinal tumor cell data set; When the growth cycle does not match the preset growth cycle, determine the intestinal tumor simulated resection strategy corresponding to the growth cycle and the location area from the intestinal tumor simulated resection strategy library; call according to the intestinal tumor simulated resection strategy The bowel tumor simulated resection algorithm processes the bowel tumor to generate image data for resection of the bowel tumor; and outputs the image data for resection of the bowel tumor.

Among them, the preset distance is determined according to the thickness of the intestinal tumor cell layer.

Refer to Figure 2B. Figure 2B is a schematic diagram of a coordinate system provided by an embodiment of the application. As shown in Figure 2B, the origin of the coordinates is the center of the bowel tumor, and the X-axis, Y-axis and Z-axis of the coordinate system are perpendicular to each other and follow the right hand The law of spirals.

Optionally, in a possible implementation manner, the determining the growth cycle corresponding to the intestinal tumor according to the first intestinal tumor cell data set includes: acquiring each first intestinal tumor cell data set in the first intestinal tumor cell data set. The spatial position corresponding to the intestinal tumor cell data; determine the positional relationship between each first intestinal tumor cell data and the intestine according to the spatial position corresponding to each first intestinal tumor cell data in the first intestinal tumor cell data set; according to The positional relationship determines the growth cycle corresponding to the intestinal tumor.

Wherein, the positional relationship includes one of the following: each first intestinal tumor cell data is located inside the intestine or each first intestinal tumor cell data is located outside the intestine.

Among them, the growth cycle can include, for example, stage 0, stage I, stage II, stage III and stage IV. Stage 0: cancer is at an early stage and cancer cells only exist in the innermost layer of the intestine. Stage I: cancer cells invade the inner wall of the colon and intestine. Many areas; stage II: cancer cells have spread to the surrounding tissues but have not spread to the lymph nodes; stage III: cancer cells have spread to the peripheral lymph nodes, but have not spread to other parts of the body. Stage IV: Cancer cells have spread to other parts of the body.

Among them, the preset growth cycle is the time required to increase the probability of self-healing by removing the intestinal tumor.

It can be seen that, in the above technical solution, by determining the growth cycle corresponding to the intestinal tumor according to the position relationship, the accuracy of the growth cycle determination is improved.

Optionally, in a possible embodiment, each intestinal tumor cell layer includes characteristic data corresponding to the intestinal tumor cell data set, and the characteristic data corresponding to the intestinal tumor cell data set includes the intestinal tumor cell data. Collecting the shape corresponding to each intestinal tumor cell data and the size corresponding to each intestinal tumor cell data in the intestinal tumor cell data set, the preset processing includes the following steps: obtaining the intestinal tumor corresponding to the intestinal tumor from the intestinal tumor cell database The outermost intestinal tumor cell data includes the shape and size corresponding to the outermost intestinal tumor cell data, and the intestinal tumor cell database includes each intestinal tumor in a variety of intestinal tumors. The outermost intestinal tumor cell data corresponding to the tumor in different growth cycles; the second intestinal tumor cell data whose shape and size are similar to the data of the outermost intestinal tumor cell are extracted from each intestinal tumor cell layer.

It can be seen that in the above technical solution, the data acquisition of the outermost colorectal tumor cells of the colorectal tumor is achieved, and the accuracy of data acquisition of the outermost colorectal tumor cells of the colorectal tumor is improved through the comparison of shapes and sizes.

Among them, the intestinal tumor simulated resection strategy library includes a variety of intestinal tumor growth cycles and a variety of intestinal tumor locations in the intestine corresponding to a variety of intestinal tumor simulated resection strategies. Each intestinal tumor simulated resection strategy is different from each other.

Wherein, the image data of the resection of the intestine tumor may include, for example, video data of the resection of the intestine tumor.

It can be seen that in the above technical solution, the intestinal tumor simulated resection strategy corresponding to the growth cycle and location area is determined from the intestinal tumor simulated resection strategy database when the growth cycle does not match the preset growth cycle, and then the intestinal tumor simulated resection strategy is determined according to the intestinal tumor The simulated resection strategy calls the intestinal tumor simulation resection algorithm to process the intestinal tumor to generate the image data for the resection of the intestinal tumor. Finally, the image data of the resection of the intestinal tumor is output, which improves the accuracy of the simulated resection of the intestinal tumor and provides the doctor with resection. Intestinal tumor imaging data to improve the success rate of intestinal tumor resection.

Refer to FIG. 3, which is a schematic flowchart of another method for analyzing bowel tumors and blood vessels based on VRDS AI medical imaging according to an embodiment of the application. Among them, as shown in Figure 3, it includes:

301. The medical imaging device determines the growth cycle corresponding to the intestinal tumor according to the number and distribution of the blood supply vessels.

Among them, the growth cycle can include, for example, stage 0, stage I, stage II, stage III and stage IV. Stage 0: cancer is at an early stage and cancer cells only exist in the innermost layer of the intestine. Stage I: cancer cells invade the inner wall of the colon and intestine. Many areas; stage II: cancer cells have spread to the surrounding tissues but have not spread to the lymph nodes; stage III: cancer cells have spread to the peripheral lymph nodes, but have not spread to other parts of the body. Stage IV: Cancer cells have spread to other parts of the body.

302. When the growth period does not match the preset growth period, the medical imaging device determines the intestinal tumor simulated resection strategy corresponding to the growth period and the location area from the intestinal tumor simulated resection strategy library.

Among them, the preset growth cycle is the time required to increase the probability of self-healing by removing the intestinal tumor.

Among them, the intestinal tumor simulated resection strategy library includes a variety of intestinal tumor growth cycles and multiple intestinal tumor simulated resection strategies corresponding to the location area of multiple intestinal tumors in the intestine. Each intestinal tumor simulated resection strategy is different from each other.

303. The medical imaging device invokes an intestinal tumor simulated resection algorithm to process the intestinal tumor according to the intestinal tumor simulated resection strategy to generate image data for resection of the intestinal tumor.

Wherein, the image data of the resection of the intestine tumor may include, for example, video data of the resection of the intestine tumor.

304. The medical imaging device outputs image data for resection of the intestinal tumor.

It can be seen that in the above technical solution, the growth cycle of intestinal tumors is determined according to the number and distribution of blood supply vessels. Then, when the growth cycle does not match the preset growth cycle, the growth cycle is determined from the intestinal tumor simulation resection strategy library. The intestinal tumor simulation resection strategy corresponding to the location area, and then according to the intestinal tumor simulation resection strategy, the intestinal tumor simulation resection algorithm is called to process the intestinal tumor to generate the image data of the resection of the intestine tumor, and finally, the image data of the resection of the intestine tumor is output. Improve the accuracy of the process of simulating the resection of intestinal tumors, and provide doctors with imaging data of the resection of intestinal tumors to improve the success rate of intestinal tumor resection.

Referring to FIG. 4, a schematic diagram of a medical imaging apparatus 400 provided by an embodiment of the present application. The medical imaging apparatus 400 may include:

The obtaining module 401 is configured to obtain a scanned image of the user's intestine, where the scanned image further includes intestinal tumors and blood vessels around the intestine;

Wherein, the scan image includes any one of the following: CT image, MRI image, DTI image, PET-CT image.

The generating module 402 is configured to generate the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel according to the scanned image;

Among them, blood vessels include arteries and veins. Further, the arteries may include, for example, superior mesenteric artery, inferior mesenteric artery, and the like. The veins may include mesenteric veins and the like, for example.

Wherein, the image data of the intestine includes the three-dimensional image data of the intestine, the image data of the intestinal tumor includes the three-dimensional image data of the intestinal tumor, and the image data of the blood vessel includes the three-dimensional image data of the blood vessel. Spatial image data.

Optionally, the generating module is specifically configured to perform first preset processing on the scanned image to obtain a bitmap BMP data source; import the BMP data source into a preset VRDS medical network model to obtain the first medical image Data, the first medical image data includes a first data set of the intestine and a data set of the blood vessel, the first data set of the intestine includes a data set of the intestine tumor, and the data of the blood vessel The set includes the fusion data of the intersection position of the artery and the vein, the first data set of the intestine is the transfer function result of the cube space of the tissue structure of the intestine surface and the inside of the intestine, and the data set of the blood vessel Is the transfer function result of the cube space of the blood vessel surface and the tissue structure inside the blood vessel; the first medical image data is imported into the preset cross blood vessel network model to obtain the second medical image data. The image data includes a first data set of the intestine, a data set of the arteries, and a data set of the veins, and the first data in the arterial data set and the second data in the vein data set The data are independent of each other, the first data is data associated with the intersection position, and the second data is data associated with the intersection position; the second medical image data is processed to obtain the intestinal tract Image data of, image data of the bowel tumor, and image data of the blood vessel.

The determining module 403 is configured to determine the location area of the intestine tumor in the intestine and the blood supply vessel of the intestine tumor according to the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel The number and distribution of;

Optionally, the determining module is specifically configured to determine the location area according to the image data of the intestine and the image data of the intestine tumor; determine the location area of each blood vessel in the image data of the blood vessel to Obtain multiple blood vessel location information; determine the number and distribution of the blood supply vessels according to the location area and the multiple blood vessel location information.

Optionally, the determining module is specifically configured to compare the image data of the intestine with the image data of the intestine tumor to determine that the image data of the intestine matches the image data of the intestine tumor Determine the spatial position of the first image data in the image data of the intestinal tract; set the spatial position as the position area.

Optionally, the determining module is specifically configured to segment the image data of the intestine according to the category to which the intestine belongs to obtain multiple image sub-data of the intestine; Each of the image sub-data performs the following steps, including: determining the target intestine included in the currently processed image sub-data; obtaining template image sub-data according to the target intestine included in the currently processed image sub-data, wherein, The template image sub-data includes image data of the target intestine in a healthy state; compare the currently processed image sub-data with the template image sub-data; if the currently processed image sub-data is different from the template image sub-data Match, acquire the second image sub-data that does not match the template image sub-data in the currently processed image sub-data, and compare the second image sub-data with the image data of the bowel tumor to determine the The second image sub-data is the first image data.

Optionally, the determining module is specifically configured to determine the location area according to the imaging data of the intestine and the imaging data of the intestinal tumor; determine the location area according to the imaging data of the blood vessel and the imaging data of the intestinal tumor The connection position and connection angle between each blood vessel and the intestine tumor, and each blood vessel is a blood vessel connected to the intestine tumor in the image data of the blood vessel; the connection position and the connection angle are determined according to the connection position and the connection angle. The number and distribution of blood vessels.

The output module 404 is configured to perform 4D medical imaging on the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel to output the location area and the number and distribution of the blood supply vessels.

Optionally, the device further includes a resection module, which is used to determine the growth cycle of the bowel tumor according to the number and distribution of the blood supply vessels; when the growth cycle does not match a preset growth cycle At the time, determine the intestinal tumor simulated resection strategy corresponding to the growth cycle and the location area from the intestinal tumor simulated resection strategy library; call the intestinal tumor simulated resection algorithm according to the intestinal tumor simulated resection strategy to process the intestinal tumor To generate image data for resection of the intestinal tumor; output image data for resection of the intestine tumor.

Optionally, the device further includes a resection module, and the resection module is configured to establish a coordinate system according to the image data of the bowel tumor, the origin of the coordinate system is the center of the bowel tumor, and the coordinate system The X-axis, Y-axis, and Z-axis are perpendicular to each other and follow the right-handed spiral rule; starting from the origin of the coordinate system, from the intestinal tumor along the positive and negative directions of the Z-axis of the coordinate system at a preset distance, Multi-layer intestinal tumor cell layers are extracted from the image data of the intestine tumor cell layer, and each intestinal tumor cell layer includes an intestinal tumor cell data set; preset processing is performed for each intestinal tumor cell layer in the multi-layer intestinal tumor cell layer to obtain the first An intestinal tumor cell data set, where the first intestinal tumor cell data set is the outermost intestinal tumor cell data in the intestinal tumor; the growth cycle corresponding to the intestinal tumor is determined according to the first intestinal tumor cell data set When the growth cycle does not match the preset growth cycle, determine the intestinal tumor simulated resection strategy corresponding to the growth cycle and the location area from the intestinal tumor simulated resection strategy library; according to the intestinal tumor simulated resection strategy The intestinal tumor simulated resection algorithm is called to process the intestinal tumor to generate image data for resecting the intestinal tumor; and the image data for resecting the intestinal tumor is output.

Wherein, each intestinal tumor cell layer includes feature data corresponding to the intestinal tumor cell data set, and the feature data corresponding to the intestinal tumor cell data set includes the shape and the corresponding shape of each intestinal tumor cell data in the intestinal tumor cell data set. The size corresponding to each intestinal tumor cell data in the intestinal tumor cell data set, the preset processing includes the following steps:

Obtain the outermost intestinal tumor cell data corresponding to the intestinal tumor from the intestinal tumor cell database. The outermost intestinal tumor cell data includes the shape and size corresponding to the outermost intestinal tumor cell data. The tumor cell database includes the outermost intestinal tumor cell data corresponding to each intestinal tumor in a different growth cycle in a variety of intestinal tumors;

The second intestinal tumor cell data whose shape and size are similar to the data of the outermost intestinal tumor cell are extracted from each intestinal tumor cell layer.

Referring to FIG. 5, FIG. 5 is a schematic structural diagram of a medical imaging apparatus in a hardware operating environment involved in an embodiment of the application. Wherein, as shown in FIG. 5, the medical imaging device in the hardware operating environment involved in the embodiment of the present application may include:

The processor 501 is, for example, a CPU.

The memory 502, optionally, the memory may be a high-speed RAM memory, or a stable memory, such as a disk memory.

The communication interface 503 is used to implement connection and communication between the processor 501 and the memory 502.

Those skilled in the art can understand that the structure of the medical imaging device shown in FIG. 5 does not constitute a limitation to it, and may include more or less components than those shown in the figure, or a combination of certain components, or different component arrangements. .

As shown in FIG. 5, the memory 502 may include an operating system, a network communication module, and an information processing program. The operating system is a program that manages and controls the hardware and software resources of the medical imaging device, and supports the operation of personnel management programs and other software or programs. The network communication module is used to implement communication between various components in the memory 502 and communication with other hardware and software in the medical imaging device.

In the medical imaging device shown in FIG. 5, the processor 501 is configured to execute the information migration program stored in the memory 502, and implement the following steps: Obtain a scanned image of the user's intestines, where the scanned image also includes intestinal tumors And the blood vessels around the intestine; generate the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel according to the scan image; according to the image data of the intestine, the image data of the intestine tumor The imaging data and the imaging data of the blood vessels determine the location area of the intestine tumor in the intestine and the number and distribution of the blood supply vessels of the intestinal tumor; the imaging data of the intestine and the imaging of the intestine tumor The data and the image data of the blood vessel are subjected to 4D medical imaging to output the number and distribution of the location area and the blood supply blood vessel.

For the specific implementation of the medical imaging device involved in the present application, please refer to the foregoing embodiments of the intestinal tumor and blood vessel analysis method based on VRDS AI medical imaging, which will not be repeated here.

The present application also provides a computer-readable storage medium for storing a computer program, and the stored computer program is executed by the processor to implement the following steps: Obtain a scan of the user’s intestines Image, wherein the scanned image further includes an intestine tumor and blood vessels around the intestine; according to the scanned image, image data of the intestine, image data of the intestine tumor, and image data of the blood vessel are generated; The imaging data of the intestine, the imaging data of the intestine tumor, and the imaging data of the blood vessel determine the location area of the intestine tumor in the intestine and the number and distribution of blood supply vessels of the intestine tumor; The image data of the intestine, the image data of the intestinal tumor, and the image data of the blood vessel are subjected to 4D medical imaging to output the location area and the number and distribution of the blood supply vessels.

For the specific implementation of the computer-readable storage medium involved in this application, please refer to the above-mentioned embodiments of the intestinal tumor and blood vessel analysis method based on VRDS AI medical imaging, which will not be repeated here.

It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not subject to the described sequence of actions. Limitation, because according to this application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application. In the above-mentioned embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in an embodiment, reference may be made to related descriptions of other embodiments.

Claims (20)

1. The intestinal tumor and blood vessel analysis method based on VRDS AI medical imaging is characterized by:

   Acquiring a scanned image of the user's intestine, where the scanned image further includes intestinal tumors and blood vessels around the intestine;

   Generating image data of the intestine, image data of the intestine tumor, and image data of the blood vessel according to the scanned image;

   Determining the location area of the intestinal tumor in the intestine and the number and distribution of blood supply vessels of the intestinal tumor according to the imaging data of the intestine, the imaging data of the intestinal tumor, and the imaging data of the blood vessel;

   Perform 4D medical imaging on the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel to output the location area and the number and distribution of the blood supply blood vessel.
2. The method of claim 1, wherein the position of the intestine tumor in the intestine is determined based on the imaging data of the intestine, the imaging data of the intestine tumor, and the imaging data of the blood vessel The area and the number and distribution of blood vessels for the intestinal tumor, including:

   Determining the location area according to the imaging data of the intestine and the imaging data of the intestinal tumor;

   Determining the position area of each blood vessel in the image data of the blood vessel to obtain multiple blood vessel position information;

   The number and distribution of the blood supply blood vessels are determined according to the position area and the position information of the multiple blood vessels.
3. The method according to claim 2, wherein the determining the location area according to the imaging data of the intestine and the imaging data of the intestinal tumor comprises:

   Comparing the image data of the intestine with the image data of the intestine tumor to determine the first image data that matches the image data of the intestine tumor among the image data of the intestine;

   Determining the spatial position of the first image data in the image data of the intestine;

   The spatial location is set as the location area.
4. The method according to claim 3, wherein the imaging data of the intestine is compared with the imaging data of the intestine tumor to determine the difference between the imaging data of the intestine and the intestine tumor. The first image data matched by the image data includes:

   Segmenting the image data of the intestine according to the category to which the intestine belongs to obtain multiple image sub-data of the intestine;

   Performing the following steps for each of the multiple image sub-data of the intestines includes:

   Determine the target intestine included in the currently processed image sub-data; obtain template image sub-data according to the target intestine included in the currently processed image sub-data, wherein the template image sub-data includes the image data of the target intestine in a healthy state Compare the currently processed image sub-data with the template image sub-data; if the currently processed image sub-data does not match the template image sub-data, then obtain the currently processed image sub-data and the template image sub-data For the second image sub-data whose data does not match, the second image sub-data is compared with the image data of the bowel tumor to determine that the second image sub-data is the first image data.
5. The method of claim 1, wherein the position of the intestine tumor in the intestine is determined based on the imaging data of the intestine, the imaging data of the intestine tumor, and the imaging data of the blood vessel The area and the number and distribution of blood vessels for the intestinal tumor, including:

   Determining the location area according to the imaging data of the intestine and the imaging data of the intestinal tumor;

   Determine the connection position and connection angle between each blood vessel and the intestine tumor according to the image data of the blood vessel and the image data of the intestine tumor, where each blood vessel is connected to the intestine tumor in the image data of the blood vessel Blood vessel

   The number and distribution of the blood supply vessels are determined according to the connection position and the connection angle.
6. The method according to any one of claims 1-5, wherein the method further comprises:

   Determining the corresponding growth cycle of the intestinal tumor according to the number and distribution of the blood supply vessels;

   When the growth cycle does not match the preset growth cycle, determining the intestinal tumor simulated resection strategy corresponding to the growth cycle and the location area from the intestinal tumor simulated resection strategy library;

   Invoking an intestinal tumor simulated resection algorithm to process the intestinal tumor according to the intestinal tumor simulated resection strategy to generate image data for resection of the intestinal tumor;

   Output the image data of the resection of the bowel tumor.
7. The method according to any one of claims 1-5, wherein the method further comprises:

   Establishing a coordinate system according to the imaging data of the bowel tumor, the origin of the coordinate system is the center of the bowel tumor, and the X-axis, Y-axis, and Z-axis of the coordinate system are perpendicular to each other and follow the right-hand spiral rule;

   Starting from the origin of the coordinate system, extract multiple layers of intestinal tumor cell layers from the image data of the intestine tumor along the positive and negative directions of the Z axis of the coordinate system according to a preset distance, and each layer of intestinal tumor The cell layer includes a data set of intestinal tumor cells;

   Perform preset processing for each intestinal tumor cell layer in the multi-layered intestinal tumor cell layer to obtain a first intestinal tumor cell data set, the first intestinal tumor cell data set being the outermost layer in the intestinal tumor Intestinal tumor cell data;

   Determining the growth cycle corresponding to the intestinal tumor according to the first intestinal tumor cell data set;

   When the growth cycle does not match the preset growth cycle, determining the intestinal tumor simulated resection strategy corresponding to the growth cycle and the location area from the intestinal tumor simulated resection strategy library;

   Invoking an intestinal tumor simulated resection algorithm to process the intestinal tumor according to the intestinal tumor simulated resection strategy to generate image data for resection of the intestinal tumor;

   Output the image data of the resection of the bowel tumor.
8. The method according to claim 7, wherein each intestinal tumor cell layer includes characteristic data corresponding to the intestinal tumor cell data set, and the characteristic data corresponding to the intestinal tumor cell data set includes the intestinal tumor cell data Collecting the shape corresponding to each intestinal tumor cell data and the size corresponding to each intestinal tumor cell data in the intestinal tumor cell data set, and the preset processing includes the following steps:

   Obtain the outermost intestinal tumor cell data corresponding to the intestinal tumor from the intestinal tumor cell database. The outermost intestinal tumor cell data includes the shape and size corresponding to the outermost intestinal tumor cell data. The tumor cell database includes the outermost intestinal tumor cell data corresponding to each intestinal tumor in a different growth cycle in a variety of intestinal tumors;

   The second intestinal tumor cell data whose shape and size are similar to the data of the outermost intestinal tumor cell are extracted from each intestinal tumor cell layer.
9. The method according to claim 1, wherein said generating the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel according to the scanned image comprises:

   Performing the first preset processing on the scanned image to obtain a bitmap BMP data source;

   Import the BMP data source into a preset VRDS medical network model to obtain first medical image data. The first medical image data includes a first data set of the intestine and a data set of the blood vessel. The first data set of the intestine includes the data set of the intestinal tumor, the data set of the blood vessel includes the fusion data of the intersection position of the artery and the vein, and the first data set of the intestine is the surface of the intestine and the The transfer function result of the cube space of the tissue structure inside the intestine, and the data set of the blood vessel is the transfer function result of the cube space of the tissue structure inside the blood vessel and the surface of the blood vessel;

   Import the first medical image data into a preset cross-vascular network model to obtain second medical image data. The second medical image data includes a first data set of the intestine, a data set of the arteries, and all The data set of the vein, and the first data in the arterial data set and the second data in the vein data set are independent of each other, the first data is data associated with the intersection position, and the The second data is data associated with the intersection position;

   The second medical image data is processed to obtain image data of the intestine, image data of the intestinal tumor, and image data of the blood vessel.
10. A medical imaging device is characterized in that it comprises:

    An acquisition module for acquiring a scanned image of the user's intestine, wherein the scanned image further includes intestinal tumors and blood vessels around the intestine;

    A generating module for generating image data of the intestine, image data of the intestine tumor, and image data of the blood vessel according to the scanned image;

    The determining module is used to determine the location area of the intestine tumor in the intestine and the blood supply vessel of the intestine tumor according to the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel. Quantity and distribution;

    The output module is used to perform 4D medical imaging on the image data of the intestine, the image data of the intestine tumor, and the image data of the blood vessel to output the location area and the number and distribution of the blood supply vessel.
11. The device according to claim 10, wherein the determining module is specifically configured to determine the location area according to the image data of the intestine and the image data of the intestine tumor; and determine the image data of the blood vessel The location area of each blood vessel in the middle to obtain multiple blood vessel location information; the number and distribution of the blood supply vessels are determined according to the location area and the multiple blood vessel location information.
12. The device according to claim 11, wherein the determining module is specifically configured to compare the image data of the intestine with the image data of the intestine tumor to determine whether the image data of the intestine is The first image data matched with the image data of the intestine tumor; the spatial position of the first image data in the image data of the intestine is determined; the spatial position is set as the position area.
13. The device according to claim 12, wherein the determining module is specifically configured to segment the image data of the intestine according to the category to which the intestine belongs, so as to obtain a plurality of images of the intestine Data; for each of the multiple image sub-data of the intestine, the following steps are performed, including: determining the target intestine included in the currently processed image sub-data; according to the target intestine included in the currently processed image sub-data Obtain template image sub-data, where the template image sub-data includes the image data of the target intestine in a healthy state; compare the currently processed image sub-data with the template image sub-data; if the currently processed image sub-data If the data does not match the template image sub-data, then obtain the second image sub-data that does not match the template image sub-data in the currently processed image sub-data, and compare the second image sub-data with that of the intestine tumor The image data is compared to determine that the second image sub-data is the first image data.
14. The device according to claim 10, wherein the determining module is specifically configured to determine the location area according to the imaging data of the intestine and the imaging data of the intestinal tumor; and according to the imaging data of the blood vessel And the image data of the intestine tumor to determine the connection position and angle of connection between each blood vessel and the intestine tumor, where each blood vessel is the blood vessel connected to the intestine tumor in the image data of the blood vessel; The position and the connection angle determine the number and distribution of the blood supply vessels.
15. The device according to any one of claims 10-14, wherein the device further comprises a resection module, and the resection module is configured to determine the growth of the intestinal tumor according to the number and distribution of the blood supply vessels Cycle; when the growth cycle does not match the preset growth cycle, determine the intestinal tumor simulated resection strategy corresponding to the growth cycle and the location area from the intestinal tumor simulated resection strategy library; according to the intestinal tumor simulated resection The strategy calls the intestinal tumor simulated resection algorithm to process the intestinal tumor to generate image data for resecting the intestinal tumor; and output the image data for resecting the intestinal tumor.
16. The device according to any one of claims 10-14, wherein the device further comprises a resection module, and the resection module is configured to establish a coordinate system based on the image data of the intestinal tumor, and the coordinate system The origin is the center of the bowel tumor, and the X-axis, Y-axis, and Z-axis of the coordinate system are perpendicular to each other and follow the right-hand spiral rule; starting from the origin of the coordinate system, follow the preset distance along the coordinate system. The positive and negative directions of the Z-axis of the intestine tumor are extracted from the image data of the intestinal tumor. Each intestinal tumor cell layer includes the intestinal tumor cell data set; Each intestinal tumor cell layer performs preset processing to obtain a first intestinal tumor cell data set, where the first intestinal tumor cell data set is the intestinal tumor cell data of the outermost layer in the intestinal tumor; according to the first intestinal tumor cell data set; The intestinal tumor cell data set determines the growth cycle corresponding to the intestinal tumor; when the growth cycle does not match the preset growth cycle, determine the growth cycle and the location area corresponding to the growth cycle and the location area from the intestinal tumor simulation resection strategy library Intestinal tumor simulated resection strategy; according to the intestinal tumor simulated resection strategy, an intestinal tumor simulated resection algorithm is called to process the intestinal tumor to generate image data for resection of the intestinal tumor; and the image data for resection of the intestinal tumor is output.
17. The device according to claim 16, wherein each layer of intestinal tumor cell layer includes characteristic data corresponding to the intestinal tumor cell data set, and the characteristic data corresponding to the intestinal tumor cell data set includes the intestinal tumor cell data Collecting the shape corresponding to each intestinal tumor cell data and the size corresponding to each intestinal tumor cell data in the intestinal tumor cell data set, and the preset processing includes the following steps:

    Obtain the outermost intestinal tumor cell data corresponding to the intestinal tumor from the intestinal tumor cell database. The outermost intestinal tumor cell data includes the shape and size corresponding to the outermost intestinal tumor cell data. The tumor cell database includes the outermost intestinal tumor cell data corresponding to each intestinal tumor in a different growth cycle in a variety of intestinal tumors;

    The second intestinal tumor cell data whose shape and size are similar to the data of the outermost intestinal tumor cell are extracted from each intestinal tumor cell layer.
18. The device according to claim 1, wherein the generating module is specifically configured to perform a first preset processing on the scanned image to obtain a bitmap BMP data source; import the BMP data source into a preset VRDS The medical network model obtains first medical image data, the first medical image data includes a first data set of the intestine and a data set of the blood vessel, and the first data set of the intestine includes the intestinal tumor The data set of the blood vessel includes the fusion data of the intersection position of the artery and the vein, and the first data set of the intestine is the transmission of the cubic space of the tissue structure of the intestine surface and the inside of the intestine Function result, the data set of the blood vessel is the result of the transfer function of the cube space of the blood vessel surface and the tissue structure inside the blood vessel; the first medical image data is imported into the preset cross blood vessel network model to obtain the second Medical imaging data, the second medical imaging data includes a first data set of the intestine, a data set of the arteries, and a data set of the veins, and the first data and all the data in the arterial data set The second data in the data set of the veins are independent of each other, the first data is data associated with the intersection position, and the second data is data associated with the intersection position; for the second medical image The data is processed to obtain image data of the intestine, image data of the intestine tumor, and image data of the blood vessel.
19. A medical imaging device is characterized by comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and are generated by the processor Execute to execute the instructions of the steps in any one of the methods of claims 1-9.
20. A computer-readable storage medium, characterized in that the computer-readable storage medium is used to store a computer program, and the stored computer program is executed by the processor to implement the method described in any one of claims 1-9 method.

Images