CN114170075A - Image splicing method, device and equipment - Google Patents
Image splicing method, device and equipment Download PDFInfo
- Publication number
- CN114170075A CN114170075A CN202111248842.5A CN202111248842A CN114170075A CN 114170075 A CN114170075 A CN 114170075A CN 202111248842 A CN202111248842 A CN 202111248842A CN 114170075 A CN114170075 A CN 114170075A
- Authority
- CN
- China
- Prior art keywords
- image
- segment
- attribute
- images
- splicing
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 85
- 238000012545 processing Methods 0.000 claims abstract description 32
- 239000011229 interlayer Substances 0.000 claims description 21
- 238000012163 sequencing technique Methods 0.000 claims description 17
- 238000012952 Resampling Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 8
- 238000007499 fusion processing Methods 0.000 claims description 5
- 239000010410 layer Substances 0.000 description 28
- 238000003384 imaging method Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000002595 magnetic resonance imaging Methods 0.000 description 3
- 238000012805 post-processing Methods 0.000 description 3
- 206010028980 Neoplasm Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 206010027476 Metastases Diseases 0.000 description 1
- 208000034578 Multiple myelomas Diseases 0.000 description 1
- 206010035226 Plasma cell myeloma Diseases 0.000 description 1
- 206010058907 Spinal deformity Diseases 0.000 description 1
- 238000002583 angiography Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000002872 contrast media Substances 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000002597 diffusion-weighted imaging Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 210000003141 lower extremity Anatomy 0.000 description 1
- 230000009401 metastasis Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000008733 trauma Effects 0.000 description 1
- 231100000216 vascular lesion Toxicity 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The application discloses an image splicing method, device and equipment, relates to the technical field of medical image processing, and can meet the requirement of splicing images with no overlapping area or small overlapping area, so that the adaptability of image splicing scenes is improved. The method comprises the following steps: acquiring mark information associated with each image segment to be spliced, wherein the mark information comprises image position information and image attribute information; searching the mark information associated with each image segment in a traversing way, and selecting image attribute information meeting the splicing condition as the splicing attribute information of each image segment; processing each image segment into an image segment containing the same image attribute information according to the splicing attribute information of each image segment; and stacking and splicing the images with the same image attribute information section by section according to the image position information to obtain spliced images.
Description
Technical Field
The present application relates to the field of medical image processing technologies, and in particular, to an image stitching method, an image stitching device, and an image stitching apparatus.
Background
Magnetic resonance whole-body imaging technology has more and more extensive clinical application in recent years, for example, magnetic resonance whole-spine imaging has higher diagnostic value for diseases such as spinal deformity, lateral bending and multiple myeloma, diffusion weighted imaging DWIBS with magnetic resonance whole-body background suppression has more and more application in projects such as exploration of tumor metastasis, high-end physical examination tumor screening and the like, and magnetic resonance blood vessel imaging technology MRA of head and neck, lower limbs and whole body has more and more extensive application in clinic due to the advantages of no trauma, no need of contrast agent, three-dimensional imaging, multi-angle observation and the like in vascular lesion examination. But since the magnet length and gradient range of current magnetic resonance devices are physically limited, and the magnetic field uniformity is worse the further away from the center one imaging is. At present, the whole body magnetic resonance imaging mostly adopts multiple sections for scanning, and then the whole image is obtained by an image splicing technology.
In the related art, for a magnetic resonance image scanned in a sagittal or coronal direction, taking magnetic resonance full spine imaging as an example, in order to obtain an image stitching result, overlapping regions of adjacent segments of images to be stitched can be specifically determined, then, registration is performed on the overlapping regions or extended regions of the overlapping regions to obtain a registered image, and the registered image is stitched; for a magnetic resonance image scanned at a transverse position, taking a Magnetic Resonance Angiography (MRA) as an example, in order to obtain an image stitching result, specifically, MIP post-processing reconstruction can be performed on each section of MRA original image obtained by scanning, then each section of MIP post-processing reconstruction image is rotated 360 degrees in the same rotation direction and the same step length, a screen capture operation is performed on the image on each step length in the rotation process, an MIP screen capture sequence image of each section of original image is obtained, so as to obtain an image parallel to the long axis direction of a human body, each obtained MIP screen capture sequence image is used as input, the same stitching process as that of an image scanned at a sagittal position or a coronal position is performed, and an image stitching result is finally obtained.
The image stitching process is mostly realized based on a mode of firstly registering and then stitching overlapped areas in images, however, stitching based on registration is time-consuming and requires a certain overlapped area between each section of images to be stitched, and if no overlapped area or a small overlapped area exists, the image stitching based on registration is difficult to successfully execute stitching operation, so that the adaptability of an image stitching scene is poor.
Disclosure of Invention
In view of this, the present application provides an image stitching method, an image stitching device, and an image stitching apparatus, and mainly aims to solve the problem that in the prior art, for an image with no overlapping area or a small overlapping area, the image stitching based on registration is difficult to successfully perform the stitching operation, so that the adaptability of an image stitching scene is poor.
According to a first aspect of the present application, there is provided an image stitching method, including:
acquiring mark information associated with each image segment to be spliced, wherein the mark information comprises image position information and image attribute information;
searching the mark information associated with each image segment in a traversing way, and selecting image attribute information meeting the splicing condition as the splicing attribute information of each image segment;
processing each image segment into an image segment containing the same image attribute information according to the splicing attribute information of each image segment;
and stacking and splicing the images with the same image attribute information section by section according to the image position information to obtain spliced images.
Further, the acquiring of the mark information associated with each segment of the image to be stitched specifically includes:
reading label data of standard format images contained in each segment of images to be spliced from image data by inquiring the imported image data in a preset standard protocol file;
and acquiring mark information associated with the images aiming at the label data of the standard format images contained in each section of image to obtain the mark information associated with each section of image to be spliced.
Further, after the obtaining of the mark information associated with each image segment to be stitched, the method further includes:
and performing intra-segment sequencing and inter-segment sequencing on the image segments according to the direction sequence set by the image position information to obtain the image segments with the same sequencing rule.
Further, the image attribute information records attribute values of images marked on different attribute features, and the image attribute information that meets the splicing condition is selected as the splicing attribute information of each segment of image by querying the mark information associated with each segment of image in a traversal manner, specifically including:
traversing and inquiring the mark information associated with each image segment, and respectively extracting the attribute values marked on different attribute characteristics of each image segment;
and selecting image attribute information meeting the splicing condition as the splicing attribute information of each image segment by comparing the attribute values marked on different attribute characteristics of each image segment.
Further, the selecting, by comparing the attribute values marked on the different attribute features of the respective segments of images, image attribute information that meets the stitching condition as stitching attribute information of the respective segments of images specifically includes:
and respectively selecting the minimum attribute values marked on the pixel attribute characteristics and the interlayer distance attribute characteristics of the images aiming at the images by comparing the attribute values marked on the different attribute characteristics of the images, and selecting the maximum attribute value of the cross-section view characteristic attribute calculated by using the attribute values marked on the preset attribute characteristics of the images as the splicing attribute information of the images.
Further, the processing, according to the stitching attribute information of each segment of image, each segment of image into each segment of image containing the same image attribute information specifically includes:
respectively extracting splicing attribute values used by the images on pixel attribute characteristics, interlayer distance attribute characteristics and cross section view attribute characteristics according to the splicing attribute information of the images;
performing resampling and zero filling operations on the attribute values of the internal multilayer images in each image on the pixel attribute characteristics and the cross section view attribute characteristics by using the splicing attribute values of each image on the pixel attribute characteristics and the cross section view attribute characteristics, so that each image contains the same image attribute information in the segments;
and performing resampling and zero filling operations on the attribute values of the images on the interlayer space attribute characteristics by using the splicing attribute values of the images on the interlayer space attribute characteristics so that the images contain the same image attribute information among the segments.
Further, the step of stacking and splicing the segments of images with the same image attribute information segment by segment according to the image position information to obtain a spliced image specifically includes:
selecting reference segment images from the images with the same image attribute information according to the direction sequence set by the image position information;
and splicing the reference segment image with the adjacent segment image according to the image position information by taking the reference segment image as a reference image, and continuously updating the reference segment image in the splicing process until the splicing of all the segment images is finished to obtain a spliced image.
Further, the continuously updating the reference segment image in the stitching process specifically includes:
judging whether the reference segment image and the adjacent segment image have an overlapping area in the splicing process;
and if so, performing weighted fusion processing on an overlapping area formed by the reference segment image and the adjacent segment image, and updating the reference segment image, otherwise, performing stacking splicing on the reference segment image and the adjacent segment image, and updating the reference segment image.
According to a second aspect of the present application, there is provided an image stitching apparatus comprising:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring mark information associated with each segment of image to be spliced, and the mark information comprises image position information and image attribute information;
the selecting unit is used for searching the mark information associated with each image segment in a traversing manner, and selecting the image attribute information meeting the splicing condition as the splicing attribute information of each image segment;
the processing unit is used for processing the images into the images with the same image attribute information according to the splicing attribute information of the images;
and the splicing unit is used for stacking and splicing the images with the same image attribute information section by section according to the image position information to obtain spliced images.
Further, the acquisition unit includes:
the reading module is used for reading label data of standard format images contained in each section of images to be spliced from the image data by inquiring the imported image data in a preset standard protocol file;
and the acquisition module is used for acquiring the label information associated with the image aiming at the label data of the standard format image contained in each section of image to obtain the label information associated with each section of image to be spliced.
Further, the apparatus further comprises:
and the sequencing unit is used for sequencing the images in sections and sequencing the images in sections according to the direction sequence set by the image position information after the mark information associated with the images to be spliced is obtained, so as to obtain the images with the same sequencing rule.
Further, the image attribute information records attribute values of the image marked on different attribute features, and the selecting unit includes:
the query module is used for traversing and querying the mark information associated with each segment of image and respectively extracting the attribute values marked on different attribute characteristics of each segment of image;
and the comparison module is used for selecting the image attribute information meeting the splicing condition as the splicing attribute information of each image segment by comparing the attribute values marked on different attribute characteristics of each image segment.
Further, the comparison module is specifically configured to compare attribute values of the segments of images marked on different attribute features, select a minimum attribute value of the image marked on a pixel attribute feature and a layer interval attribute feature for each segment of the image, and select a maximum attribute value of a cross-sectional view feature attribute calculated by using the attribute value of the image marked on a preset attribute feature as the splicing attribute information of each segment of the image.
Further, the processing unit includes:
the extraction module is used for respectively extracting the splicing attribute values of the images on the pixel attribute feature, the interlayer distance attribute feature and the cross section view attribute feature according to the splicing attribute information of the images;
the first processing module is used for performing resampling and zero filling operations on the attribute values of the internal multilayer images in each image on the pixel attribute characteristics and the cross section view attribute characteristics by using the splicing attribute values of each image on the pixel attribute characteristics and the cross section view attribute characteristics so that each image contains the same image attribute information in each segment;
and the second processing module is used for performing resampling and zero filling operations on the attribute values of the image segments on the interlayer space attribute characteristics by using the splicing attribute values of the image segments on the interlayer space attribute characteristics, so that the image segments contain the same image attribute information.
Further, the splicing unit includes:
the selection module is used for selecting reference segment images from the images with the same image attribute information according to the direction sequence set by the image position information;
and the splicing module is used for splicing the reference segment image with the adjacent segment image according to the image position information by taking the reference segment image as a reference image, and continuously updating the reference segment image in the splicing process until the splicing of all the segment images is finished to obtain a spliced image.
Further, the splicing module is specifically configured to determine whether an overlapping area exists between the reference segment image and an adjacent segment image in a splicing process;
the splicing module is specifically configured to perform weighted fusion processing on an overlapping region formed by the reference segment image and the adjacent segment image if the reference segment image and the adjacent segment image overlap each other, and update the reference segment image, and otherwise, perform stacking splicing on the reference segment image and the adjacent segment image, and update the reference segment image.
According to a third aspect of the present application, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the image stitching method described above.
According to a fourth aspect of the present application, there is provided an image stitching apparatus comprising a storage medium, a processor and a computer program stored on the storage medium and executable on the processor, the processor implementing the image stitching method when executing the program.
By means of the technical scheme, compared with the mode of firstly registering and then splicing overlapping areas in images in the prior art, the image splicing method, the image splicing device and the image splicing equipment provided by the application have the advantages that the label information related to the images of the sections to be spliced is obtained, the label information comprises image position information and image attribute information, the label information related to the images of the sections is further inquired in a traversing manner, the image attribute information meeting the splicing condition is selected as the splicing attribute information of the images of the sections, the images of the sections are processed into the images containing the same image attribute information according to the splicing attribute information, the images of the sections with the same image attribute information are stacked and spliced section by section according to the image position information, the process depends on the image position information in the label information to splice the images, the splicing efficiency is high, and the problem that the splicing operation cannot be executed due to the fact that no overlapping areas or the overlapping areas are small in the images is solved, the requirement of image real-time splicing is met, and the adaptability of an image splicing scene is improved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 shows a schematic flowchart of an image stitching method provided in an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating another image stitching method provided in the embodiment of the present application;
FIG. 3 is a block flow diagram illustrating an image stitching process provided by an embodiment of the present application;
FIG. 4 is a schematic structural diagram illustrating an image stitching apparatus provided in an embodiment of the present application;
fig. 5 shows a schematic structural diagram of another image stitching device provided in the embodiment of the present application.
Detailed Description
The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In the related art, most image stitching processes are realized in a mode of firstly registering and then stitching overlapped areas. First, the registration-based image stitching process is usually time-consuming, and for an MRI operator in the scanning process to check the stitching result in time to determine whether to rescan the patient, the stitching efficiency cannot meet the requirements of the operator; secondly, the image stitching mode based on the registration requires a certain overlapping area between the images to be stitched, and if the overlapping area is not available or is small, the stitching operation is difficult to be successfully executed; thirdly, the existing image stitching method mainly aims at images obtained by scanning coronal or sagittal positions, and is generally applied to stitching of full spine images, but for images scanned in transverse positions, direct stitching based on scanned images cannot be realized, MPR or MIP post-processing reconstruction needs to be carried out on the images scanned in transverse positions, images parallel to the long axis direction of a human body are obtained firstly, and then the obtained images parallel to the long axis direction of the human body are stitched layer by layer, so that on one hand, the operation of stitching the whole image is complex, the stitching efficiency of the image is affected, on the other hand, the stitching result cannot be reconstructed in MIP mode, and the requirement of viewing the MPR or MIP reconstructed images of the stitching result from any angle cannot be met clinically.
In order to solve the problem, this embodiment provides an image stitching method, as shown in fig. 1, the method depends on the label information in the image to perform an image stitching process, so as to improve the image stitching efficiency, and meanwhile, the method can also avoid the problem that no overlapping area or a small overlapping area can not perform image stitching, and the method can be directly applied to a server of a medical platform, and includes the following steps:
101. and acquiring mark information associated with each image segment to be spliced.
The images to be spliced can be magnetic resonance images obtained by scanning different parts of a human body by using medical equipment, and the scanning mode of the magnetic resonance images is not limited, and can be a sagittal scanning mode or a coronal scanning mode, and can also be a transverse scanning mode. Generally, in order to unify the storage format of images in the medical field, a magnetic resonance image scanned by a medical device is stored in a preset standard protocol file, where the preset standard protocol is DICOM (Digital Imaging and Communications in Medicine), the DICOM file takes each layer of images scanned as an independent file, the DICOM file includes a file header and a data set, the file header includes related information identifying the data set, the data set includes related information of medical images, such as medical instrument information, image acquisition information, and patient information, and specifically includes DICOM data elements arranged in a certain order, the DICOM data elements record image-related tag information, and the image-related tag information can be obtained by reading the DICOM file
The mark information includes Image Position information and Image attribute information, the Image obtained by different scanning modes stores the mark information, the Image Position information may include Image Position information and Image coding direction information Image original information, and the Image attribute information may include Image Pixel size information Pixel Spacing, Spacing Between devices, Image width information Columns, Image height information Rows, and the like.
The execution main body of the embodiment of the invention can be an image splicing device, and can be particularly configured at a service end of a medical platform, the mark information associated with each image section to be spliced is obtained, the mark information has definite image position information and image attribute information, the possibility can be provided for the subsequent splicing process of each image section, and the splicing operation can be directly executed without a complicated splicing process under the condition that no overlapping area or a small overlapping area exists between each image section, so that the image splicing efficiency is improved.
102. And through traversing and inquiring the mark information associated with each image segment, selecting the image attribute information meeting the splicing condition as the splicing attribute information of each image segment.
Because each segment of the stitched image is an image representing different parts of a human body, different marking information is generally formed inside each segment of the image and among each segment of the image in the process of scanning each segment of the image layer by using medical equipment, specifically, different image position information is provided for each layer of the image inside the image, and different pixel value sizes, layer spacing information, cross section view field sizes and the like are provided for each segment of the image. In order to ensure the image stitching effect, the image attribute information of each image segment needs to be unified, so that the unified image attribute information is used as the stitching attribute information for stitching the subsequent images.
It is understood that, in the process of traversing and querying the label information associated with each segment image, the image attribute information can be extracted for the label information associated with each segment image, since the image attribute information may have a plurality of attributes, the image attribute information with the largest attribute value or the smallest attribute value may be selected as the splicing attribute information of each image segment, for example, each image segment has three attributes ABC, the maximum value of the attribute A and the minimum value of the attribute B and the attribute C can be selected as the splicing attribute information of each image segment, and the weighted calculation can be performed according to a plurality of attribute values contained in each image segment to generate the image attribute information meeting the splicing condition as the splicing attribute information of each image segment, for example, each image segment has three attributes ABC, the three attribute values of the attribute ABC may be weighted and averaged to serve as the stitching attribute information of each segment of the image.
103. And processing each image segment into an image segment containing the same image attribute information according to the splicing attribute information of each image segment.
Considering that the adjacent images need to be kept consistent in the splicing process, the splicing attribute information is used as a splicing basis, and each image is processed into an image containing the same image attribute information. Specifically, each segment of image can be subjected to segment processing, and each layer of image in the segment is subjected to resampling and zero padding operation by using splicing attribute information, so that each layer of image has the same image attribute information; and processing the images among the segments, and performing resampling and zero filling operation on the images among the segments by using the splicing attribute information so as to enable the images among the segments to have the same image attribute information.
104. And stacking and splicing the images with the same image attribute information section by section according to the image position information to obtain spliced images.
It can be understood that, since the orientation directions of the mark information associated with the respective images may be irregular or different from each other regularly, for example, the a-segment images may use the first orientation direction to the foot, the B-segment images may use the second orientation direction to the head, and the images may need to use the same orientation direction during the image stitching process, here, the images may be sorted according to the image position information before being stitched, so that each image uses the same orientation direction.
Compared with the prior art in which the overlapping areas in the images are registered first and then spliced, the image splicing method provided by the embodiment of the application acquires the mark information associated with each segment of the images to be spliced, the mark information comprises image position information and image attribute information, further searches the mark information associated with each segment of the images in a traversing manner, selects the image attribute information meeting the splicing condition as the splicing attribute information of each segment of the images, processes each segment of the images into each segment of the images containing the same image attribute information according to the splicing attribute information, and performs segment-by-segment stacking and splicing on each segment of the images with the same image attribute information according to the image position information, and the process depends on the image position information in the mark information to perform image splicing, so that the splicing efficiency is high, and simultaneously, the problem that the splicing operation cannot be performed due to no overlapping area or small overlapping area in the images is avoided, the requirement of image real-time splicing is met, and the adaptability of an image splicing scene is improved.
It should be added that, in the embodiment of the present invention, the medical device to which the image stitching method is applied is not limited. In practical application scenarios, because the magnetic resonance imaging mostly adopts multiple segments for scanning, the image stitching process is applicable to medical equipment for magnetic resonance whole-body imaging, but the image stitching process is also applicable to each segment of image obtained by segmented scanning using other medical equipment, for example, each segment of image obtained by segmented scanning of CT medical equipment and each segment of image obtained by segmented scanning of PET medical equipment can both be applicable to the image stitching process.
Further, as a refinement and an extension of the specific implementation of the foregoing embodiment, in order to fully describe the specific implementation process of the present embodiment, the present embodiment provides another image stitching method, as shown in fig. 2, where the method includes:
201. and reading label data of standard format images contained in each segment of images to be spliced from the image data by inquiring the image data imported from a preset standard protocol file.
It can be understood that the preset standard protocol is equivalent to a standard output format of a medical image, and for medical image files with different formats generated by different medical imaging devices, a complete storage mechanism is arranged in the preset standard protocol file, so that image data in the medical image files can be stored in a unified format.
Because the preset standard protocol file organizes and stores the information in the images according to the DICOM standard, the label data of standard format images contained in each segment of images to be spliced in the preset standard protocol file can be read through programming, and the label data is specified for the DICOM standard.
202. And acquiring mark information associated with the images aiming at the label data of the standard format images contained in each section of image to obtain the mark information associated with each section of image to be spliced.
Since the image position information and the image attribute information are used in the image stitching process, the label data related to the image position information and the image attribute information are mainly acquired as the mark information related to the image, the label data related to the image position information mainly comprises an image position and an image coding direction, the image position indicates the image coordinate of the first pixel at the upper left corner of the image, namely the first pixel coordinate of DICOM file transmission, the image direction indicates the direction cosine values of the first row and the first column of the image relative to the patient, and the direction of the coordinate axis is determined according to the direction of the patient. The label data relating to the image attribute information mainly includes image pixels, a layer pitch, which refers to a distance between two scanned layer images in an image, an image width, an image height, and the like.
203. And performing intra-segment sequencing and inter-segment sequencing on the image segments according to the direction sequence set by the image position information to obtain the image segments with the same sequencing rule.
The direction sequence set by the image positions is equivalent to the human body orientation sequence, the direction from the head to the leg of the human body can be selected, the direction from the leg to the head of the human body can be selected, aiming at intra-segment sequencing, all scanning layer images can be sequenced according to the positions and the image coding directions of all scanning layer images in all the image segments according to the set direction sequence, all the scanning layer images in all the images use the uniform human body orientation sequence, aiming at inter-segment sequencing, all the image segments are sequenced according to the set direction sequence also according to the positions and the image coding directions of all the image segments, all the image segments use the uniform human body orientation sequence, and then all the image segments with the same sequencing rule are obtained.
204. And traversing and inquiring the mark information associated with each segment of image, and respectively extracting the attribute values marked on different attribute characteristics of each segment of image.
205. And selecting image attribute information meeting the splicing condition as the splicing attribute information of each image segment by comparing the attribute values marked on different attribute characteristics of each image segment.
The attribute information of the image records attribute values marked on different attribute features of the image, and the attribute values marked on different attribute features of each image segment can be different due to different scanning parameters used in the process of scanning each image segment layer by layer, wherein the attribute features mainly relate to pixel attribute features, interlayer spacing attribute features and cross-sectional view attribute features of the image.
As a preferred embodiment, the attribute values of the segments of images marked on different attribute features may be compared, the minimum attribute value marked on the pixel attribute feature and the interlayer distance attribute feature of the images is respectively selected for each segment of images, and the maximum attribute value of the cross-sectional view feature attribute calculated by using the attribute value marked on the preset attribute feature of the images is selected as the stitching attribute information of each segment of images.
It will be appreciated that the above-mentioned in-pixel attribute features and the interlayer distance attribute features can be read directly from the image-associated mark information, whereas the cross-sectional view feature attributes can not be read directly from the image-associated mark information, but require indirect attribute features obtained by calculation from the attribute values of the image on the preset attribute marks.
206. And processing each image segment into an image segment containing the same image attribute information according to the splicing attribute information of each image segment.
Because the inside and outside of each image have different attribute characteristics needed to be used in the image stitching process, specifically, the splicing attribute values used by the image segments on the pixel attribute feature, the interlayer distance attribute feature and the cross-sectional view attribute feature can be respectively extracted according to the splicing attribute information of the image segments, and by using the splicing attribute values of each image on the pixel attribute characteristics and the cross-section view attribute characteristics, the attribute values of the internal multi-layer image in each image segment on the pixel attribute feature and the cross-section view attribute feature are resampled and zero-filled, so that each image segment contains the same image attribute information in the segment, and by utilizing the splicing attribute value used by each image segment on the interlayer space attribute characteristic, and performing resampling and zero filling operation on the attribute values of the image segments on the interlayer space attribute characteristics, so that the image segments contain the same image attribute information among the segments.
The resampling and zero padding operation may be performed by performing a difference value layer by layer on the image by using an interpolation algorithm, and performing zero padding on the expanded view portion, where after interpolation and zero padding processing, each layer of image in the image has the same attribute value on the cross-sectional view attribute feature and the image pixel attribute feature.
207. And selecting reference segment images from the images with the same image attribute information according to the direction sequence set by the image position information.
208. And splicing the reference segment image with the adjacent segment image according to the image position information by taking the reference segment image as a reference image, and continuously updating the reference segment image in the splicing process until the splicing of all the segment images is finished to obtain a spliced image.
Specifically, in the process of stacking and splicing each section of image after sequencing, a reference section image can be set, adjacent section images and the reference section image are spliced according to image position information, and the reference section image is updated, wherein the reference section image is equivalent to a spliced reference image, namely, which section of image is taken as a reference for splicing, and in the splicing process, two sections of images A, B are spliced in a section-by-section manner, for example, the images to be spliced comprise A, B, C, D four sections of images, which correspond to positions of a human body from foot to head or head to foot, first taking the image a as the reference section image, and the splicing result is the image a-B, then taking the image a-B as the updated reference section image, splicing the two sections of the image a-B, C to obtain the image a-B-C, and then, splicing the two sections of the image A-B-C, D by taking the image A-B-C as an updated reference section image to obtain an image A-B-C-D and obtain a spliced image.
Further, considering the overlapping area between the images of the respective segments, specifically in the process of updating the image of the reference segment, it may be determined whether there is an overlapping area between the image of the reference segment and the image of the adjacent segment in the stitching process, if so, performing weighted fusion processing on the overlapping area formed by the image of the reference segment and the image of the adjacent segment, and updating the image of the reference segment, otherwise, performing stacking stitching on the image of the reference segment and the image of the adjacent segment, and updating the image of the reference segment.
In an actual application scenario, as shown in fig. 3, in the image stitching process, image information, that is, mark information associated with each segment of images to be stitched is first obtained, and the images are sorted, where the images may be sorted according to a direction sequence set by image position information, then stitching attribute information is determined, where the stitching attribute information is the same image attribute information used in the stitching process, the image layers are further resampled, each segment of images is processed into images with the same image attribute information specifically using the stitching attribute information, then resampling is performed on the reference segment layers, and each segment of images are stitched according to resampling between the position layers, and each segment of images are stacked and stitched layer by layer specifically using the same layer distance in the stitching attribute information, so as to obtain a final image stitching result.
It can be understood that, specifically, after determining the stitching attribute information, one way may directly perform intra-segment and inter-segment processing on each segment of image, so that the intra-segment and inter-segment of each segment of image use the same attribute information, and then directly perform the stack stitching processing on each segment of image, and another way may first perform intra-segment processing on each segment of image, so that the intra-segment of each segment of image uses the same attribute information, select a reference segment of image, resample each segment of image into the interlayer spacing information in the stitching attribute information during the stitching process, and then perform the stack stitching processing on the reference segment of image and the adjacent segment of image according to the position of each segment of image, where the stitching refers to performing the stack sorting of image layers according to the position information, and during the stitching process, determine whether there is an overlapping region between each segment of images according to the position information of each segment of image, and if the overlapped area exists, the overlapped area is subjected to weighted fusion to obtain updated image data, the data of the non-overlapped area is kept unchanged, the obtained result is used as an updated reference segment image, and the splicing operation is repeatedly performed on the updated reference segment image and the adjacent segment image in sequence until the splicing of all the segment images is completed to obtain a spliced image.
Further, as a specific implementation of the method in fig. 1-2, an embodiment of the present application provides an image stitching apparatus, as shown in fig. 4, the apparatus includes: the device comprises an acquisition unit 31, a selection unit 32, a processing unit 33 and a splicing unit 34.
The device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring mark information associated with each segment of image to be spliced, and the mark information comprises image position information and image attribute information;
the selecting unit is used for searching the mark information associated with each image segment in a traversing manner, and selecting the image attribute information meeting the splicing condition as the splicing attribute information of each image segment;
the processing unit is used for processing the images into the images with the same image attribute information according to the splicing attribute information of the images;
and the splicing unit is used for stacking and splicing the images with the same image attribute information section by section according to the image position information to obtain spliced images.
Compared with the prior art in which the overlapping areas in the images are registered first and then spliced, the image splicing device provided by the embodiment of the invention acquires the mark information associated with each segment of the image to be spliced, wherein the mark information comprises image position information and image attribute information, further searches the mark information associated with each segment of the image in a traversing manner, selects the image attribute information meeting the splicing condition as the splicing attribute information of each segment of the image, processes each segment of the image into each segment of the image containing the same image attribute information according to the splicing attribute information, and performs segment-by-segment stacking and splicing on each segment of the image with the same image attribute information according to the image position information, and the process depends on the image position information in the mark information to perform image splicing, so that the splicing efficiency is high, and simultaneously the problem that the splicing operation cannot be performed due to no overlapping area or small overlapping area in the image is avoided, the requirement of image real-time splicing is met, and the adaptability of an image splicing scene is improved.
In a specific application scenario, as shown in fig. 5, the obtaining unit 31 includes:
the reading module 311 may be configured to read, from the image data, tag data of a standard format image included in each segment of images to be stitched by querying image data imported from a preset standard protocol file;
the obtaining module 312 may be configured to obtain, for the tag data of the standard format image included in each segment of image, the tag information associated with the image, so as to obtain the tag information associated with each segment of image to be stitched.
In a specific application scenario, as shown in fig. 5, the apparatus further includes:
the sorting unit 35 may be configured to, after the mark information associated with each segment of the images to be stitched is obtained, perform intra-segment sorting and inter-segment sorting on each segment of the images according to the direction sequence set by the image position information, so as to obtain each segment of the images with the same sorting rule.
In a specific application scenario, as shown in fig. 5, the image attribute information records attribute values of an image marked on different attribute features, and the selecting unit 32 includes:
the query module 321 may be configured to query the label information associated with each segment of image in a traversal manner, and extract attribute values of each segment of image labeled on different attribute features respectively;
the comparing module 322 may be configured to select image attribute information meeting the stitching condition as the stitching attribute information of each image segment by comparing the attribute values marked on different attribute features of each image segment.
In a specific application scenario, the comparing module 322 may be specifically configured to compare attribute values of the segments of images marked on different attribute features, select a minimum attribute value of the image marked on a pixel attribute feature and a layer interval attribute feature for each segment of the image, and select a maximum attribute value of a cross-sectional view feature attribute calculated by using the attribute value of the image marked on a preset attribute feature as the stitching attribute information of each segment of the image.
In a specific application scenario, as shown in fig. 5, the processing unit 33 includes:
the extracting module 331 may be configured to extract, according to the stitching attribute information of each segment of image, a stitching attribute value used by each segment of image on the pixel attribute feature, the interlayer distance attribute feature, and the cross-sectional view attribute feature, respectively;
the first processing module 332 may be configured to perform resampling and zero padding on attribute values of the internal multilayer image in each image on the pixel attribute feature and the cross-sectional view attribute feature by using a stitching attribute value used by each image segment on the pixel attribute feature and the cross-sectional view attribute feature, so that each image segment contains the same image attribute information in each segment;
the second processing module 333 may be configured to perform resampling and zero padding operations on the attribute values of the segments of images on the interlayer space attribute features by using the stitching attribute values of the segments of images on the interlayer space attribute features, so that the segments of images contain the same image attribute information between the segments.
In a specific application scenario, as shown in fig. 5, the splicing unit 34 includes:
a selecting module 341, configured to select, according to the direction sequence set by the image location information, a reference segment image from the images with the same image attribute information;
the stitching module 342 may be configured to stitch the reference segment image with the adjacent segment image according to the image position information, and continuously update the reference segment image in a stitching process until all the segment images are stitched, so as to obtain a stitched image.
In a specific application scenario, the stitching module 342 may be specifically configured to determine whether an overlapping area exists between the reference segment image and an adjacent segment image in a stitching process;
the stitching module 342 may be specifically configured to, if yes, perform weighted fusion processing on an overlapping region formed by the reference segment image and an adjacent segment image, and update the reference segment image, and otherwise, perform stack stitching on the reference segment image and the adjacent segment image, and update the reference segment image.
It should be noted that other corresponding descriptions of the functional units related to the image stitching device applicable to the server side provided in this embodiment may refer to the corresponding descriptions in fig. 1 and fig. 2, and are not repeated herein.
Based on the method shown in fig. 1-2, correspondingly, the present application further provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the image stitching method shown in fig. 1-2;
based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.), and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the implementation scenarios of the present application.
Based on the method shown in fig. 1-2 and the virtual device embodiment shown in fig. 4-5, in order to achieve the above object, an embodiment of the present application further provides a server entity device, which may specifically be a computer, a server, or other network devices, and the entity device includes a storage medium and a processor; a storage medium for storing a computer program; a processor for executing a computer program to implement the image stitching method as shown in fig. 1-2.
Optionally, the above entity devices may further include a user interface, a network interface, a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, and the like. The user interface may include a Display screen (Display), an input unit such as a keypad (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), etc.
Those skilled in the art will appreciate that the structure of the image stitching solid device provided in the present embodiment does not constitute a limitation to the solid device, and may include more or less components, or combine some components, or arrange different components.
The storage medium may further include an operating system and a network communication module. The operating system is a program for managing hardware and software resources of the physical device for image stitching, and supports the operation of an information processing program and other software and/or programs. The network communication module is used for realizing communication among components in the storage medium and communication with other hardware and software in the information processing entity device.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present application can be implemented by software plus a necessary general hardware platform, and can also be implemented by hardware. Through the technical scheme, compared with the existing mode, the image splicing method and the image splicing device can rely on the image position information in the mark information to perform image splicing, not only are the splicing efficiency high, but also the problem that the splicing operation cannot be performed due to the fact that no overlapping area or the overlapping area is very small in the image is avoided, the requirement for image real-time splicing is met, and the adaptability of an image splicing scene is improved.
Those skilled in the art will appreciate that the figures are merely schematic representations of one preferred implementation scenario and that the blocks or flow diagrams in the figures are not necessarily required to practice the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario may be distributed in the devices in the implementation scenario according to the description of the implementation scenario, or may be located in one or more devices different from the present implementation scenario with corresponding changes. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above application serial numbers are for description purposes only and do not represent the superiority or inferiority of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of the present application, but the present application is not limited thereto, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present application.
Claims (11)
1. An image stitching method, comprising:
acquiring mark information associated with each image segment to be spliced, wherein the mark information comprises image position information and image attribute information;
searching the mark information associated with each image segment in a traversing way, and selecting image attribute information meeting the splicing condition as the splicing attribute information of each image segment;
processing each image segment into an image segment containing the same image attribute information according to the splicing attribute information of each image segment;
and stacking and splicing the images with the same image attribute information section by section according to the image position information to obtain spliced images.
2. The method according to claim 1, wherein the obtaining of the mark information associated with each image segment to be stitched specifically includes:
reading label data of standard format images contained in each segment of images to be spliced from image data by inquiring the imported image data in a preset standard protocol file;
and acquiring mark information associated with the images aiming at the label data of the standard format images contained in each section of image to obtain the mark information associated with each section of image to be spliced.
3. The method according to claim 1, wherein after the obtaining of the mark information associated with the image segments to be stitched, the method further comprises:
and performing intra-segment sequencing and inter-segment sequencing on the image segments according to the direction sequence set by the image position information to obtain the image segments with the same sequencing rule.
4. The method according to claim 1, wherein the image attribute information records attribute values of images marked on different attribute features, and the step of selecting image attribute information meeting the stitching condition as the stitching attribute information of each image segment by querying the mark information associated with each image segment in a traversal manner specifically includes:
traversing and inquiring the mark information associated with each image segment, and respectively extracting the attribute values marked on different attribute characteristics of each image segment;
and selecting image attribute information meeting the splicing condition as the splicing attribute information of each image segment by comparing the attribute values marked on different attribute characteristics of each image segment.
5. The method according to claim 4, wherein the selecting image attribute information that meets the stitching condition as the stitching attribute information of each image segment by comparing the attribute values marked on different attribute features of each image segment specifically comprises:
and respectively selecting the minimum attribute values marked on the pixel attribute characteristics and the interlayer distance attribute characteristics of the images aiming at the images by comparing the attribute values marked on the different attribute characteristics of the images, and selecting the maximum attribute value of the cross-section view characteristic attribute calculated by using the attribute values marked on the preset attribute characteristics of the images as the splicing attribute information of the images.
6. The method according to any one of claims 1 to 5, wherein the processing the images into the images containing the same image attribute information according to the splicing attribute information of the images comprises:
respectively extracting splicing attribute values used by the images on pixel attribute characteristics, interlayer distance attribute characteristics and cross section view attribute characteristics according to the splicing attribute information of the images;
performing resampling and zero filling operations on the attribute values of the internal multilayer images in each image on the pixel attribute characteristics and the cross section view attribute characteristics by using the splicing attribute values of each image on the pixel attribute characteristics and the cross section view attribute characteristics, so that each image contains the same image attribute information in the segments;
and performing resampling and zero filling operations on the attribute values of the images on the interlayer space attribute characteristics by using the splicing attribute values of the images on the interlayer space attribute characteristics so that the images contain the same image attribute information among the segments.
7. The method according to any one of claims 1 to 5, wherein the step of stacking and splicing the segments of the images with the same image attribute information segment by segment according to the image position information to obtain a spliced image specifically comprises:
selecting reference segment images from the images with the same image attribute information according to the direction sequence set by the image position information;
and splicing the reference segment image with the adjacent segment image according to the image position information by taking the reference segment image as a reference image, and continuously updating the reference segment image in the splicing process until the splicing of all the segment images is finished to obtain a spliced image.
8. The method according to claim 7, wherein the continuously updating the reference segment images during the stitching process includes:
judging whether the reference segment image and the adjacent segment image have an overlapping area in the splicing process;
and if so, performing weighted fusion processing on an overlapping area formed by the reference segment image and the adjacent segment image, and updating the reference segment image, otherwise, performing stacking splicing on the reference segment image and the adjacent segment image, and updating the reference segment image.
9. An image stitching device, comprising:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring mark information associated with each segment of image to be spliced, and the mark information comprises image position information and image attribute information;
the selecting unit is used for searching the mark information associated with each image segment in a traversing manner, and selecting the image attribute information meeting the splicing condition as the splicing attribute information of each image segment;
the processing unit is used for processing the images into the images with the same image attribute information according to the splicing attribute information of the images;
and the splicing unit is used for stacking and splicing the images with the same image attribute information section by section according to the image position information to obtain spliced images.
10. A storage medium having stored thereon a computer program, characterized in that the program, when executed by a processor, implements the image stitching method of any one of claims 1 to 8.
11. An image stitching apparatus comprising a storage medium, a processor and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the image stitching method according to any one of claims 1 to 8 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111248842.5A CN114170075A (en) | 2021-10-26 | 2021-10-26 | Image splicing method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111248842.5A CN114170075A (en) | 2021-10-26 | 2021-10-26 | Image splicing method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114170075A true CN114170075A (en) | 2022-03-11 |
Family
ID=80477321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111248842.5A Pending CN114170075A (en) | 2021-10-26 | 2021-10-26 | Image splicing method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114170075A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102124320A (en) * | 2008-06-18 | 2011-07-13 | 苏尔吉克斯有限公司 | A method and system for stitching multiple images into a panoramic image |
| CN102855613A (en) * | 2011-07-01 | 2013-01-02 | 株式会社东芝 | Image processing device and image processing method |
| CN105279735A (en) * | 2015-11-20 | 2016-01-27 | 沈阳东软医疗系统有限公司 | Fusion method, fusion device and fusion equipment of image splicing |
| CN106056537A (en) * | 2016-05-20 | 2016-10-26 | 沈阳东软医疗系统有限公司 | Medical image splicing method and device |
| US20170178317A1 (en) * | 2015-12-21 | 2017-06-22 | Canon Kabushiki Kaisha | Physical registration of images acquired by fourier ptychography |
| CN107220933A (en) * | 2017-05-11 | 2017-09-29 | 上海联影医疗科技有限公司 | A kind of reference line determines method and system |
| CN110473143A (en) * | 2019-07-23 | 2019-11-19 | 平安科技（深圳）有限公司 | A kind of three-dimensional MRA medical image joining method and device, electronic equipment |
-
2021
- 2021-10-26 CN CN202111248842.5A patent/CN114170075A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102124320A (en) * | 2008-06-18 | 2011-07-13 | 苏尔吉克斯有限公司 | A method and system for stitching multiple images into a panoramic image |
| CN102855613A (en) * | 2011-07-01 | 2013-01-02 | 株式会社东芝 | Image processing device and image processing method |
| CN105279735A (en) * | 2015-11-20 | 2016-01-27 | 沈阳东软医疗系统有限公司 | Fusion method, fusion device and fusion equipment of image splicing |
| US20170178317A1 (en) * | 2015-12-21 | 2017-06-22 | Canon Kabushiki Kaisha | Physical registration of images acquired by fourier ptychography |
| CN106056537A (en) * | 2016-05-20 | 2016-10-26 | 沈阳东软医疗系统有限公司 | Medical image splicing method and device |
| CN107220933A (en) * | 2017-05-11 | 2017-09-29 | 上海联影医疗科技有限公司 | A kind of reference line determines method and system |
| CN110473143A (en) * | 2019-07-23 | 2019-11-19 | 平安科技（深圳）有限公司 | A kind of three-dimensional MRA medical image joining method and device, electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107220933B (en) | Reference line determining method and system | |
| JP6700622B2 (en) | System and method for processing multimodal images | |
| JP5684382B2 (en) | Image diagnosis support apparatus and method | |
| JP4542591B2 (en) | Image processing system, image storage device, image processing device, image processing method, and program | |
| WO2018205232A1 (en) | Method for automatically and accurately positioning reference line according to spliced result | |
| US7822254B2 (en) | Automatic positioning of matching multi-planar image reformatting (MPR) views of multiple 3D medical images | |
| KR20220031695A (en) | Image recognition method and related devices and devices | |
| US8306292B2 (en) | Image display device and image display program storage medium | |
| US20160125162A1 (en) | Method for controlling information terminal, and recording medium | |
| US20060056680A1 (en) | 3D volume construction from DICOM data | |
| US20180064409A1 (en) | Simultaneously displaying medical images | |
| KR102149369B1 (en) | Method for visualizing medical image and apparatus using the same | |
| US11468659B2 (en) | Learning support device, learning support method, learning support program, region-of-interest discrimination device, region-of-interest discrimination method, region-of-interest discrimination program, and learned model | |
| US8068665B2 (en) | 3D-image processing apparatus, 3D-image processing method, storage medium, and program | |
| KR101885562B1 (en) | Method for mapping region of interest in first medical image onto second medical image and apparatus using the same | |
| US20190005354A1 (en) | Learning data generation support apparatus, operation method of learning data generation support apparatus, and learning data generation support program | |
| CN116469545A (en) | Method, device and equipment for carrying out auxiliary disease prediction by using medical image | |
| JP5363962B2 (en) | Diagnosis support system, diagnosis support program, and diagnosis support method | |
| CN114170075A (en) | Image splicing method, device and equipment | |
| US20210256741A1 (en) | Region correction apparatus, region correction method, and region correction program | |
| US20220076462A1 (en) | Correction instruction region display apparatus, correction instruction region display method, and correction instruction region display program | |
| CN104105441A (en) | Region extraction system | |
| JP2006304840A (en) | Medical image display system | |
| JP4336100B2 (en) | Image diagnostic system, medical image processing apparatus, medical image storage method, and program | |
| US20060045319A1 (en) | Image processing method and apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |