WO2021012520A1

WO2021012520A1 - Three-dimensional mra medical image splicing method and apparatus, and electronic device and computer-readable storage medium

Info

Publication number: WO2021012520A1
Application number: PCT/CN2019/118065
Authority: WO
Inventors: 李宝林
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-07-23
Filing date: 2019-11-13
Publication date: 2021-01-28
Also published as: CN110473143A; CN110473143B

Abstract

Provided are a three-dimensional MRA medical image splicing method and apparatus, and an electronic device and a computer-readable storage medium, belonging to the technical field of medical image processing. The method comprises: performing Laplace denoising, enhancement and irregular smoothing processing on two adjacent three-dimensional MRA medical images to be spliced that are received in real time, in order to obtain a first image and a second image; performing overlapping layer detection on the first image and the second image to determine a first overlapping region in the first image and a second overlapping region in the second image; and performing, by using a weighted average method, fusion splicing processing on the first overlapping region and the second overlapping region to obtain a third image after fusion splicing. In the present application, overlapping layer detection is respectively carried out on two pre-processed adjacent three-dimensional MRA medical images to be spliced, overlapping regions in the two three-dimensional MRA medical images to be spliced are determined, and the two overlapping regions are then fused and spliced, so that the efficiency of the determination of an overlapping region in an image can be improved, thereby improving the image splicing efficiency.

Description

Three-dimensional MRA medical image mosaic method, device, electronic equipment and computer readable storage medium

This application claims the priority of the Chinese patent application 201910666640.9 filed on July 23, 2019 with the title of "Three-dimensional MRA Medical Image Mosaic Method and Apparatus, Electronic Equipment", and the entire contents of which are incorporated herein by reference.

Technical field

This application relates to the technical field of medical image processing, and in particular to a method, device, electronic equipment and computer-readable storage medium for 3D MRA medical image splicing.

Background technique

Magnetic resonance angiography (Magnetic Resonance Angiography, MRA) is an examination method that uses electromagnetic waves to generate three-dimensional medical images that describe human body information. Through this examination method, a panoramic three-dimensional medical image can be obtained, which can better help doctors to diagnose the condition. Comprehensive and intuitive evaluation.

However, in the MRA examination, due to the limitation of the MRA equipment, a panoramic 3D medical image cannot be obtained by scanning at one time. It is usually necessary to perform segmented imaging, and then stitch every two adjacent segments to obtain a panoramic 3D medical image. Therefore, 3D medical image stitching has a wide range of applications in medical imaging research, and even becomes a new application method in life insurance risk control in the financial industry. For example, by intelligently performing panoramic 3D medical images of the insurance applicant after stitching. Analysis can help review the insurance applicant’s application for insurance.

However, the inventor of the present application realizes that in the prior art, when performing 3D medical image stitching, the doctor usually manually merges the 3D medical images to be stitched through operations such as translation to achieve the visual overlap area fusion to determine the image Image stitching is performed on the overlapping area. However, in this way, the efficiency of manually determining the overlapping area of the image is too low, and the accuracy is not high, and it takes a long time, resulting in too low efficiency of image stitching.

Summary of the invention

In order to solve the above technical problems, an object of the present application is to provide a method, device, electronic equipment, and computer-readable storage medium for 3D MRA medical image splicing.

Among them, the technical solutions adopted in this application are:

In the first aspect, a method for splicing three-dimensional MRA medical images includes: receiving two adjacent three-dimensional MRA medical images to be spliced sent by a scanning device in real time; performing Laplacian on the two adjacent three-dimensional MRA medical images to be spliced Denoising, enhancement, and irregular smoothing processing to obtain a first image and a second image; respectively perform overlapping layer detection on the first image and the second image to determine the first overlap area in the first image And the second overlapping area in the second image; using a weighted average method to perform fusion splicing processing on the first overlapping area and the second overlapping area to obtain a fused and spliced third image.

In the second aspect, a three-dimensional MRA medical image splicing device includes: a receiving unit for receiving two adjacent three-dimensional MRA medical images to be spliced sent by a scanning device in real time; The three-dimensional MRA medical image to be stitched is processed by Laplacian denoising, enhancement and irregular smoothing to obtain a first image and a second image; the detection unit is used to overlap the first image and the second image respectively Layer detection to determine the first coincidence area in the first image and the second coincidence area in the second image; the stitching unit is used to use a weighted average method to compare the first coincidence area and the second coincidence area The overlapping area is processed by fusion splicing to obtain a third image after fusion splicing.

In the third aspect, an electronic device includes: a processor; and

The memory is configured to store a three-dimensional MRA medical image splicing program of the processor; wherein the processor is configured to execute the above-mentioned three-dimensional MRA medical image splicing method by executing the three-dimensional MRA medical image splicing program.

In a fourth aspect, a computer-readable storage medium storing a three-dimensional MRA medical image splicing program, wherein the three-dimensional MRA medical image splicing program is executed by a processor to realize the above-mentioned three-dimensional MRA medical image splicing method.

In a fifth aspect, a computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute as described in the first aspect of the embodiment of the present invention Or any possible implementation of the first aspect.

In the above technical solution, two adjacent three-dimensional MRA medical images to be spliced received in real time are respectively preprocessed and then overlapped layer detection is performed to determine the overlap area in the two three-dimensional MRA medical images to be spliced, and weights are used. The averaging method merges and splices the two overlapping areas, which can improve the efficiency of determining the overlapping areas in the image, thereby improving the efficiency of image stitching.

It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the application.

Description of the drawings

The drawings herein are incorporated into the specification and constitute a part of the specification, show embodiments that conform to the application, and are used together with the specification to explain the principle of the application.

FIG. 1 is a schematic structural diagram of a three-dimensional MRA medical image splicing device disclosed in an embodiment of the present application;

2 is a schematic flowchart of a method for stitching three-dimensional MRA medical images disclosed in an embodiment of the present application;

3 is a schematic flowchart of another three-dimensional MRA medical image stitching method disclosed in an embodiment of the present application;

FIG. 4 is a schematic flowchart of another three-dimensional MRA medical image stitching method disclosed in an embodiment of the present application;

5 is a schematic structural diagram of another three-dimensional MRA medical image splicing device disclosed in an embodiment of the present application;

6 is a schematic structural diagram of another three-dimensional MRA medical image splicing device disclosed in an embodiment of the present application;

FIG. 7 is a schematic structural diagram of another three-dimensional MRA medical image splicing device disclosed in an embodiment of the present application.

Through the above drawings, the specific embodiments of the application have been shown, and there will be more detailed descriptions in the following. These drawings and text descriptions are not intended to limit the scope of the concept of the application in any way, but by referring to specific embodiments. The concept of this application is explained to those skilled in the art.

Detailed ways

Here, an exemplary embodiment will be described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are only examples of devices and methods consistent with some aspects of the application as detailed in the appended claims.

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms, and should not be construed as being limited to the examples set forth herein; on the contrary, the provision of these embodiments makes this application more comprehensive and complete, and fully conveys the concept of the example embodiments To those skilled in the art. The described features, structures or characteristics may be combined in one or more embodiments in any suitable way.

Example one

The implementation environment of this application can be electronic devices, such as smart phones, tablet computers, and desktop computers.

In an application scenario, the method disclosed in the embodiments of this application is suitable for life insurance risk control in the financial industry. Specifically, by intelligently analyzing the panoramic 3D medical images of the applicant after stitching, it can help review the insurance applicant’s insurance Application. In another application scenario, the method disclosed in the embodiments of the present application is suitable for magnetic resonance imaging equipment in the medical field. The segmented three-dimensional MRA medical images scanned by the scanning equipment are stitched to obtain a panoramic three-dimensional medical image. It can help doctors make a comprehensive and intuitive evaluation of the condition.

Fig. 1 is a schematic structural diagram of a three-dimensional MRA medical image splicing device disclosed in an embodiment of the present application. The apparatus 100 may be the aforementioned electronic device. As shown in FIG. 1, the device 100 may include one or more of the following components: a processing component 102, a memory 104, a power supply component 106, a multimedia component 108, an audio component 110, a sensor component 114, and a communication component 116.

The processing component 102 generally controls the overall operations of the device 100, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 102 may include one or more processors 118 to execute instructions to complete all or part of the steps of the following method. In addition, the processing component 102 may include one or more modules to facilitate the interaction between the processing component 102 and other components. For example, the processing component 102 may include a multimedia module to facilitate the interaction between the multimedia component 108 and the processing component 102.

The memory 104 is configured to store various types of data to support operations in the device 100. Examples of these data include instructions for any application or method operating on the device 100. The memory 104 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, SRAM for short), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory) Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read-Only Memory (EPROM for short), Programmable Red-Only Memory (PROM for short), Read-only memory ( Read-Only Memory, ROM for short), magnetic storage, flash memory, magnetic disk or optical disk. The memory 104 also stores one or more modules, and the one or more modules are configured to be executed by the one or more processors 118 to complete all or part of the steps in the method shown below.

The power supply component 106 provides power to various components of the device 100. The power supply component 106 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 100.

The multimedia component 108 includes a screen that provides an output interface between the device 100 and the user. In some embodiments, the screen may include a liquid crystal display (Liquid Crystal Display, LCD for short) and a touch panel. If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor can not only sense the boundary of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. The screen may also include an organic electroluminescence display (Organic Light Emitting Display, OLED for short).

The audio component 110 is configured to output and/or input audio signals. For example, the audio component 110 includes a microphone (Microphone, MIC for short). When the device 100 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive external audio signals. The received audio signal can be further stored in the memory 104 or sent via the communication component 116. In some embodiments, the audio component 110 further includes a speaker for outputting audio signals.

The sensor component 114 includes one or more sensors for providing the device 100 with various aspects of state evaluation. For example, the sensor component 114 can detect the open/close state of the device 100 and the relative positioning of components. The sensor component 114 can also detect the position change of the device 100 or a component of the device 100 and the temperature change of the device 100. In some embodiments, the sensor component 114 may also include a magnetic sensor, a pressure sensor or a temperature sensor.

The communication component 116 is configured to facilitate wired or wireless communication between the apparatus 100 and other devices. The device 100 can access a wireless network based on a communication standard, such as WiFi (Wireless-Fidelity, wireless fidelity). In the embodiment of the present application, the communication component 116 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In this embodiment of the present application, the communication component 116 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth technology and other technologies. .

In an exemplary embodiment, the apparatus 100 may be implemented by one or more Application Specific Integrated Circuits (ASIC for short), digital signal processors, digital signal processing equipment, programmable logic devices, field programmable gate arrays, The controller, microcontroller, microprocessor or other electronic components are implemented to perform the following methods.

Example two

Please refer to FIG. 2. FIG. 2 is a schematic flowchart of a method for stitching three-dimensional MRA medical images disclosed in an embodiment of the present application. As shown in FIG. 2, the 3D MRA medical image stitching method may include the following steps:

201. Receive two adjacent three-dimensional MRA medical images to be spliced from the scanning device in real time.

It should be noted that the format of the three-dimensional MRA medical image to be spliced should be Digital Imaging and Communications in Medicine (DICOM) format, that is, the medical image format used for data exchange.

202. Perform Laplacian denoising, enhancement and irregular smoothing processing on two adjacent three-dimensional MRA medical images to be spliced to obtain a first image and a second image.

In the embodiments of the present application, due to the limitation of the MRA equipment, the obtained three-dimensional MRA medical images to be stitched inevitably have noise. Therefore, it is necessary to preprocess the 3D MRA medical images to be stitched. First, perform Laplacian denoising on two adjacent 3D MRA medical images to be spliced to remove unnecessary and useless interference signals, then perform enhancement processing on the denoised image, and finally perform irregular image smoothing on the enhanced image Processing, as far as possible to provide high-quality first image and second image for the next step.

As another optional implementation manner, a weighted neighborhood averaging method may also be used to smoothly denoise the three-dimensional MRA medical image to be spliced. Among them, the weighted neighborhood average method refers to multiplying different coefficients for each pixel in the neighborhood, and multiplying the more important pixels with a larger weight. For example, assuming that the medical image is, if the neighborhood S is taken, the calculation formula of the weighted neighborhood average is:

Among them, ∑ is the summation symbol, used to indicate the summation operation; a is the upper bound of the first summation operation, -a is the lower bound of the first summation operation, and a can be a specified constant to indicate the value of s The range is [-a, a], which limits the value range of the argument of the first summation operation. In the same way, b is the upper bound of the second summation operation, -b is the lower bound of the second summation operation, and b can be a designated constant to indicate that the value range of t is [-b, b], thus limiting the first 2. The value range of the argument of the summation operation. Among them, is a weight function, which belongs to a commonly used weight function. It is a function with the distance between each point in the neighborhood and the center point as a variable. In this function, the center point has the largest weight, indicating that the point is weighted The decision contribution of the neighborhood average is inversely proportional to the distance from the center point. Among them, (s, t) is the coordinate of each point in the neighborhood, and w is the weight corresponding to the point.

Implementation of this embodiment can increase the speed of denoising processing.

203. Perform overlapping layer detection on the first image and the second image respectively to determine the first overlapping area in the first image and the second overlapping area in the second image.

In the embodiments of the present application, due to the limitation of the MRA equipment, a panoramic three-dimensional medical image cannot be obtained by scanning at one time. It is usually necessary to perform segmented imaging, and then stitch every two adjacent segments to obtain a panoramic three-dimensional medical image. It should be noted that the first image and the second image described in the embodiments of this application are essentially three-dimensional MRA medical images, but compared to panoramic three-dimensional medical images, both the first image and the second image refer to Is the segment obtained by segment imaging.

It can be understood that because the three-dimensional MRA medical image is used to display the patient’s lesions, in order to avoid the omission of scanned information, there is an overlap area between the first image and the second image, and these two overlap areas exist in the two images respectively. Both ends of the junction. Among them, the junction of the two images can be the boundary of any side of any image.

Wherein, the first image and the second image may be images acquired by the same scanning device under different conditions, and the different conditions may include different weather, illuminance, camera position and angle, etc.

It should be noted that, since the overlapped area generally has the same or close number of overlapped layers, the overlapped layer detection on the first image and the second image can determine the overlapped area.

204. Perform a fusion splicing process on the first coincidence area and the second coincidence area by using a weighted average method to obtain a third image after fusion and splicing.

In the embodiment of this application, the weighted average method is used to weight the pixels in the first overlap area and the second overlap area respectively, and then superimpose and average them. Each pixel is given a different weight according to its importance in the entire image. Thereby, a smooth transition of the image can be realized, and the stitching in the image can be effectively eliminated.

It can be seen that the method described in Figure 2 is implemented, and two adjacent three-dimensional MRA medical images to be spliced are respectively preprocessed in real time and then overlapped layer detection is performed to determine the overlap area in the two three-dimensional MRA medical images to be spliced. , And use the weighted average method to merge and splice the two overlapping areas, which can improve the efficiency of determining the overlapping areas in the image, thereby improving the efficiency of image splicing.

Example three

Please refer to FIG. 3, which is a schematic flowchart of another three-dimensional MRA medical image stitching method disclosed in an embodiment of the present application. As shown in Fig. 3, the 3D MRA medical image stitching method may include the following steps:

301～303. For the description of steps 301 to 303, please refer to the detailed description of steps 201 to 203 in the second embodiment, which will not be repeated in this application.

304. Divide the first overlapping area into a plurality of first to-be-fused column areas, and divide the second overlapping area into a plurality of second-to-be-fused column areas, where the first to-be-fused column area and the second to-be-fused column area correspond one-to-one.

Wherein, the one-to-one correspondence between the first row area to be fused and the second row area to be fused has an overlapping relationship.

305. Obtain the first preset weight coefficient of each first column area to be fused in sequence in the descending order of the distance between each first column area to be merged and the second overlapping area, where the first preset weight coefficient increases with The distance between the corresponding first column area to be fused and the second overlapping area becomes larger and smaller.

It can be understood that, in the first overlapping area, the closer to the second overlapping area the first column area to be fused has a greater contribution to decision making, and therefore the preset weight coefficient should be larger. Similarly, in the second coincidence area, the closer to the first coincidence area the second column area to be merged has a greater contribution to decision making, and therefore the preset weight coefficient should be larger. Optionally, a first preset weight coefficient can be preset for the first column area to be merged according to the distance between the first column area to be merged and the second overlapping area.

For example, if there are two first to-be-melted column areas in the first overlapping area, namely A and B, the first to-be-fused column area B is closer to the edge of the first overlapping area than the first to-be-fused column area A, It is also closer to the second overlap area, so the first preset weight coefficient of the first row area A to be fused is 0.8, and the first preset weight coefficient of the first row area B to be fused is 0.6. Of course, other values can also be set, such as 0.4 or 0.5, which is not limited here.

306. According to the first preset weight coefficient, obtain a second preset weight coefficient of the second column area to be fused corresponding to the first column area to be fused, wherein the sum of the first preset weight coefficient and the second preset weight coefficient Equal to one.

Based on the above example, there are also two second column regions to be blended in the second overlapping area, namely C and D. The second column area to be blended C is closer to the edge of the second overlapping area than the second column area to be blended D. It is also closer to the first overlap area, then the second preset weight coefficient of the second row area C corresponding to the first row area A to be fused in the second overlap area is 1-0.8=0.2, and the second overlap area The second preset weight coefficient of the second column region D corresponding to the first column region B to be fused is 1-0.6=0.4.

307. According to the first preset weight coefficient and the second preset weight coefficient, add the pixel values of each first column area to be fused and the corresponding second column area to be fused to obtain a fused pixel value to obtain a fusion splicing After the third image.

Steps 304 to 307 are implemented, by dividing the overlapping area into multiple column areas to be fused, and according to the importance of the column areas to be fused, different weight coefficients are configured for them, and the preset weight coefficients of any two adjacent column areas to be fused Different, the first image and the second image can be smoothly and seamlessly spliced, making the image transition more natural, improving the splicing effect, and enhancing the visual effect.

308. Perform smoothing filtering processing on the third image by using a low-pass filter to obtain a target smooth image.

It can be seen that the implementation of the method described in Figure 3 can improve the efficiency of determining the overlap area in the image, thereby improving the efficiency of image stitching. It can also receive in real time two adjacent three-dimensional MRA medical images to be spliced from the scanning device and the three-dimensional MRA to be spliced. Medical images are preprocessed to provide high-quality first and second images for the next step. In addition, by dividing the overlapping area into multiple column areas to be fused, and according to the importance of the column area to be fused, different weight coefficients are configured for it, and the preset weight coefficients of any two adjacent column areas to be fused are different. The first image and the second image are stitched smoothly and seamlessly to make the image transition more natural, improve the stitching effect, and enhance the visual effect.

Example four

Please refer to FIG. 4. FIG. 4 is a schematic flowchart of another three-dimensional MRA medical image stitching method disclosed in an embodiment of the present application. As shown in FIG. 4, the 3D MRA medical image stitching method may include the following steps:

401～402. For the description of steps 401 to 402, please refer to the detailed description of steps 201 to 202 in the second embodiment, which will not be repeated in this application.

403. Compare the respective maximum density projection imaging of the first image and the second image to determine the first overlap segment in the first image and the second overlap segment in the second image.

Among them, the maximum intensity projection (Maximal Intensity Projection, MIP) is a widely used 3D MRA medical image processing technology. MIP uses perspective to obtain two-dimensional images, which are generated by calculating the maximum density pixels encountered along each ray along the scanned object. When the fiber bundle passes through the original image of a piece of tissue, the pixels with the highest density in the image are retained and projected onto a two-dimensional plane to form a MIP reconstructed image. MIP can reflect the X-ray attenuation value of the corresponding pixel, and small density changes can also be displayed on the MIP image, which can well show the stenosis, expansion, filling defect of the blood vessel and distinguish the calcification on the blood vessel wall from the contrast in the blood vessel cavity Agent. Therefore, through the maximum intensity projection imaging, the first overlapping segment in the first image and the second overlapping segment in the second image can be preliminarily determined.

404. Divide the first overlapping segment into a plurality of first regions to be tested, and divide the second overlapping segment into a plurality of second regions to be tested, where the first region to be tested corresponds to the second region to be tested one-to-one.

405. Determine in sequence whether the difference in the number of overlapping layers between each first area to be tested and the corresponding second area to be tested is less than a preset value. If yes, go to step 406; otherwise, end this process.

Among them, the preset value may be set in advance by the developer according to actual conditions.

406. Use the first area to be measured as a component of the first coincidence area in the first image, and use the corresponding second area to be measured as a component of the second coincidence area in the second image to determine the first coincidence area And the second overlap area.

407. Determine a sampling point according to the image position information of the first image and the second image. Wherein, the image position information is used to describe the positions of the first image and the second image corresponding to the human anatomical coordinate system.

It should be noted that the image location information can be obtained from the device scan information provided in the header files of the first image and the second image. The device scan information includes image location, image direction, pixel resolution, layer thickness, patient position, and Scan information such as beds.

It can be understood that by the origin of the image corresponding to the position of the human anatomical coordinate system, any point in the image can be found to be in the position of the human anatomical coordinate system. Therefore, the sampling point can be the above-mentioned origin or any other than the above-mentioned origin. A coincidence point. Among them, the origin of the image is located at the upper left corner of the image, the image coordinates of this origin in the image coordinate system are zero, and this origin corresponds to the human anatomical coordinates in the human anatomical coordinate system, which can be obtained from the image position information. Therefore, according to the first The human anatomical coordinates of the origin of the first image and the second image can also describe the positional relationship between the first image and the second image.

Among them, the human anatomical coordinate system refers to the anatomical space coordinate system in the field of medical image processing technology, also called the patient coordinate system. The human anatomical coordinate system is composed of three planes, used to describe the anatomical position of the standard human body. Among them, the three decent planes include a cross section, a coronal plane and a sagittal plane; among them, the cross section is parallel to the ground, separating the head and feet of the human body; the coronal plane is perpendicular to the ground, separating the front and back of the human body; sagittal The face is perpendicular to the ground, separating the left and right parts of the human body.

408. Obtain a registration transformation matrix according to the human anatomical coordinates of the sampling points, the first image coordinates of the sampling points in the first image, and the second image coordinates in the second image.

Among them, the human anatomical coordinates refer to the coordinate information of the sampling point corresponding to the human anatomical coordinate system; the first image coordinates or the second image coordinates refer to the coordinate information of the sampling point in the image coordinate system.

Wherein, the registration transformation matrix is used to perform one or more of operations such as translation, scale transformation, and rotation on the first image or the second image. Generally, when the points of the same human anatomical coordinates in two images are known, the registration transformation matrix can be determined. For example, [the second image coordinates of the sampling points in the second image]*[the registration transformation matrix]=[the first image coordinates of the sampling points in the first image].

409. According to the registration transformation matrix, register the first coincidence area and the second coincidence area.

As an optional implementation manner, step 409 may include:

Using the first overlapping area as the reference area, the points with the same human anatomical coordinates in the second overlapping area are registered to the same position in the first overlapping area through the registration transformation matrix; or, taking the second overlapping area as the reference area, The points with the same human anatomical coordinates in the first coincidence area are registered to the same position in the second coincidence area through the registration transformation matrix.

The implementation of this embodiment, compared with the method of manually determining the image overlap area in the prior art, saves time and improves efficiency while also increasing the accuracy of image stitching.

As another optional implementation manner, before step 409 is performed, the first overlap area and the second overlap area may be expanded according to the size of the pre-selected image processing operator to obtain the first area to be registered And the second area to be registered. Further optionally, step 409 may include: obtaining a registration coefficient based on a mutual information maximization method, and registering points with the same feature in the first area to be registered and the second area to be registered by the registration coefficient according to the registration coefficient To the same location. Among them, image processing operators include but are not limited to Roberts operator (also known as Roberts operator) that uses local difference operators to find edges, Sobel operators for edge detection, and Prewitt for edge detection of first-order differential operators. Operator, Laplacian operator or Gauss-Laplacian operator for second-order differentiation.

By implementing this embodiment, by performing expansion processing on the determined first coincident area and second coincident area, the registration is performed based on the expanded first area to be registered and the second area to be registered, which can improve the accuracy of image registration. Performance, while improving the effect of image processing.

410. Perform a fusion splicing process on the first coincidence area and the second coincidence area by using a weighted average method to obtain a third image after fusion and splicing.

It can be seen that implementing the method described in FIG. 4 can improve the efficiency of determining the overlapping area in the image, thereby improving the efficiency of image stitching. In addition, by taking one overlapping area as the reference area, the points with the same human anatomical coordinates in the other overlapping area are registered to the same position through the registration transformation matrix, which is compared with the manual determination of the image overlapping area in the prior art. This way, while saving time and improving efficiency, it can also increase the accuracy of image stitching.

Example five

Please refer to FIG. 5. FIG. 5 is a schematic structural diagram of another 3D MRA medical image splicing device disclosed in an embodiment of the present application. As shown in Fig. 5, the 3D MRA medical image splicing device may include a receiving unit 501, a denoising unit 502, a detecting unit 503, and a splicing unit 504, where:

The receiving unit 501 is configured to receive two adjacent three-dimensional MRA medical images to be spliced from the scanning device in real time.

The denoising unit 502 is configured to perform Laplacian denoising, enhancement and irregular smoothing processing on two adjacent three-dimensional MRA medical images to be spliced to obtain a first image and a second image.

The detection unit 503 is configured to perform overlap layer detection on the first image and the second image to determine the first overlap area in the first image and the second overlap area in the second image.

The splicing unit 504 is configured to perform fusion splicing processing on the first overlapping area and the second overlapping area by using a weighted average method to obtain a third image after fusion splicing.

It can be seen that the implementation of the device shown in Fig. 5 is used to preprocess the two adjacent three-dimensional MRA medical images to be spliced received in real time and then perform overlapping layer detection to determine the overlapping area in the two three-dimensional MRA medical images to be spliced. , And use the weighted average method to merge and splice the two overlapping areas, which can improve the efficiency of determining the overlapping areas in the image, thereby improving the efficiency of image splicing.

Example Six

Please refer to FIG. 6, which is a schematic structural diagram of another three-dimensional MRA medical image splicing device disclosed in an embodiment of the present application. The three-dimensional MRA medical image splicing device shown in FIG. 6 is optimized by the three-dimensional MRA medical image splicing device shown in FIG. 5. Compared with the three-dimensional MRA medical image splicing device shown in Figure 5, in the three-dimensional MRA medical image splicing device shown in Figure 6:

The above-mentioned denoising unit 502 is further configured to perform fusion stitching processing on the first and second overlapping regions by the weighted average method in the stitching unit 504 to obtain the fused and stitched third image, and then use a low-pass filter to Three images are smoothed and filtered to obtain a target smooth image.

As an optional implementation manner, in the device shown in FIG. 6, the splicing unit 504 may include:

The dividing subunit 5041 is used to divide the first overlapping area into a plurality of first to-be-merged column areas, and divide the second overlapping area into a plurality of second to-be-merged column areas, the first to-be-merged column area and the second to-be-fused column area The regions correspond one to one.

The first obtaining subunit 5042 is configured to sequentially obtain the first preset weight coefficient of each first column area to be merged in the descending order of the distance between each first column area to be merged and the second overlapping area, where the first A preset weight coefficient becomes smaller as the distance between the corresponding first column area to be fused and the second overlap area increases.

The second obtaining subunit 5043 is configured to obtain, according to the first preset weight coefficient, the second preset weight coefficient of the second column area to be fused corresponding to the first column area to be fused, where the first preset weight coefficient and the second The sum of the preset weight coefficients is equal to one.

The splicing subunit 5044 is configured to add the pixel values of each first column area to be fused and the corresponding second column area to be fused according to the first preset weight coefficient and the second preset weight coefficient to obtain the fused pixel value , To obtain the third image after fusion splicing.

To implement this embodiment, the overlapping area is divided into multiple column areas to be fused, and different weight coefficients are assigned to the column areas to be fused according to the importance of the column areas to be fused, and the preset weight coefficients of any two adjacent column areas to be fused are different , Can smoothly and seamlessly splice the first image and the second image, make the image transition more natural, improve the splicing effect, and enhance the visual effect.

As another optional implementation manner, the aforementioned denoising unit 502 is further configured to use a weighted neighborhood average method to smoothly denoise the three-dimensional MRA medical image to be spliced. Among them, the weighted neighborhood average method refers to multiplying different coefficients for each pixel in the neighborhood, and multiplying the more important pixels with a larger weight. For example, assuming that the medical image is, if the neighborhood S is taken, the calculation formula of the weighted neighborhood average is:

It can be seen that the implementation of the device shown in Figure 6 can improve the efficiency of determining the overlapping area in the image, thereby improving the efficiency of image stitching. It can also divide the overlapping area into multiple column areas to be fused, and according to the importance of the column areas to be fused, It is configured with different weight coefficients, and the preset weight coefficients of any two adjacent column areas to be fused are different. The first image and the second image can be smoothly and seamlessly stitched, making the image transition more natural, improving the stitching effect, and improving Visual effect.

Example Seven

Please refer to FIG. 7. FIG. 7 is a schematic structural diagram of another three-dimensional MRA medical image splicing device disclosed in an embodiment of the present application. The three-dimensional MRA medical image splicing device shown in FIG. 7 is optimized by the three-dimensional MRA medical image splicing device shown in FIG. 6. Compared with the three-dimensional MRA medical image splicing device shown in FIG. 6, the three-dimensional MRA medical image splicing device shown in FIG. 7 may further include: a comparison unit 505, a determination unit 506, an acquisition unit 507, and a registration unit 508, wherein,

The comparison unit 505 is configured to detect the overlap layer of the first image and the second image by the detection unit 503 to determine the first overlap area in the first image and the second overlap area in the second image, and compare the first The respective maximum density projection imaging of the image and the second image are compared to determine the first overlap segment in the first image and the second overlap segment in the second image.

Correspondingly, the above-mentioned detection unit 503 is used to detect the overlapping layer of the first image and the second image respectively to determine the first overlapping area in the first image and the second overlapping area in the second image. :

The aforementioned detection unit 503 is configured to perform overlap layer detection on the first overlap segment and the second overlap segment to determine the first overlap area in the first image and the second overlap area in the second image.

Further optionally, the aforementioned detection unit 503 is configured to perform overlap layer detection on the first overlap segment and the second overlap segment to determine the manner of the first overlap area in the first image and the second overlap area in the second image Specifically:

The aforementioned detection unit 503 is used to divide the first overlapping segment into a plurality of first areas to be measured, and to divide the second overlapping segment into a plurality of second areas to be measured, the first area to be measured and the second area to be measured one by one Corresponding; and sequentially determine whether the difference in the number of overlapping layers between each first area to be tested and the corresponding second area to be tested is less than a preset value; if the difference is less than the preset value, the first area to be tested is taken as the first For the component part of the first overlapping area in an image, the corresponding second area to be measured is used as the component part of the second overlapping area in the second image to determine the first overlapping area and the second overlapping area.

The determining unit 506 is configured to use the first to-be-measured area as a component of the first overlapping area in the first image and the corresponding second to-be-measured area as the second overlapping area in the second image in the aforementioned detecting unit 503 After determining the first overlapping area and the second overlapping area, and the above-mentioned splicing unit 504 uses the weighted average method to perform the fusion splicing process on the first and second overlapping areas to obtain the fused and spliced third image , Determine the sampling point according to the image location information of the first image and the second image. Wherein, the image position information is used to describe the positions of the first image and the second image corresponding to the human anatomical coordinate system.

The obtaining unit 507 is configured to obtain the registration transformation matrix according to the human anatomical coordinates of the sampling points, the first image coordinates of the sampling points in the first image, and the second image coordinates in the second image.

The registration unit 508 is configured to register the first coincidence area and the second coincidence area according to the registration transformation matrix.

As an optional implementation manner, the registration unit 508 is configured to register the first coincidence area and the second coincidence area according to the registration transformation matrix:

The registration unit 508 is used to register the points with the same human anatomical coordinates in the second overlap area to the same position in the first overlap area through the registration transformation matrix using the first overlap area as the reference area; or The overlapping area is the reference area, and the points with the same human anatomical coordinates in the first overlapping area are registered to the same position in the second overlapping area through the registration transformation matrix.

As another optional implementation manner, the registration unit 508 is configured to register the first coincidence area and the second coincidence area according to the registration transformation matrix:

The registration unit 508 is configured to perform expansion processing on the first coincidence area and the second coincidence area respectively according to the size of the preselected image processing operator to obtain the first area to be registered and the second area to be registered; and, based on The mutual information maximization method obtains the registration coefficient, and according to the registration coefficient, the points of the same feature in the first area to be registered and the second area to be registered are registered to the same position through the registration coefficient. Among them, image processing operators include but are not limited to Roberts operator (also known as Roberts operator) that uses local difference operators to find edges, Sobel operators for edge detection, and Prewitt for edge detection of first-order differential operators. Operator, Laplacian operator or Gauss-Laplacian operator for second-order differentiation.

It can be seen that implementing the device shown in FIG. 7 can improve the efficiency of determining the overlapping area in the image, thereby improving the efficiency of image stitching. In addition, by taking one overlapping area as the reference area, the points with the same human anatomical coordinates in the other overlapping area are registered to the same position through the registration transformation matrix, which is compared with the manual determination of the image overlapping area in the prior art. This way, while saving time and improving efficiency, it can also increase the accuracy of image stitching.

This application also provides an electronic device, which includes:

processor;

A memory storing computer-readable instructions, and when the computer-readable instructions are executed by the processor, the three-dimensional MRA medical image splicing method as shown above is realized.

The electronic device may be the apparatus 100 shown in FIG. 1.

In an exemplary embodiment, the present application further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the three-dimensional MRA medical image splicing method as shown above is realized.

In an exemplary embodiment, the present application also provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the above The three-dimensional MRA medical image stitching method shown. The computer program product includes program code, and when the program product runs on a terminal device, the program code is used to make the terminal device execute the various methods described in the “exemplary method” section of this specification. Steps of an exemplary embodiment.

It should be understood that the present application is not limited to the precise structure that has been described above and shown in the drawings, and various modifications and changes can be performed without departing from its scope. The scope of the application is only limited by the appended claims.

Claims

A three-dimensional MRA medical image stitching method, the method includes:

Receive two adjacent 3D MRA medical images to be spliced from the scanning device in real time;

Performing Laplacian denoising, enhancement and irregular smoothing processing on the two adjacent three-dimensional MRA medical images to be spliced to obtain a first image and a second image;

Performing overlapping layer detection on the first image and the second image respectively to determine a first overlapping area in the first image and a second overlapping area in the second image;

A weighted average method is used to perform fusion splicing processing on the first overlapping area and the second overlapping area to obtain a third image after fusion splicing.
The method according to claim 1, wherein the method performs a fusion splicing process on the first coincident area and the second coincident area using a weighted average method, and after obtaining a third image after fusion splicing, the method further include:

A low-pass filter is used to perform smoothing filtering processing on the third image to obtain a target smooth image.
3. The method according to claim 2, wherein the detection of overlapping layers is performed on the first image and the second image respectively to determine the first overlap area in the first image and the second image Before the second coincidence area in, the method further includes:

Comparing the respective maximum density projection imaging of the first image and the second image to determine the first overlapping segment in the first image and the second overlapping segment in the second image;

And, the performing overlapping layer detection on the first image and the second image respectively to determine the first overlapping area in the first image and the second overlapping area in the second image includes:

Perform overlap layer detection on the first overlap segment and the second overlap segment to determine the first overlap area in the first image and the second overlap area in the second image.
The method according to claim 3, wherein said detecting the overlapping layer of the first overlapping segment and the second overlapping segment to determine the first overlapping area and the second overlapping area in the first image The second overlap area in the image includes:

Divide the first overlapping segment into a plurality of first regions to be tested, and divide the second overlapping segment into a plurality of second regions to be tested, the first region to be tested and the second region to be tested one by one correspond;

Sequentially determining whether the difference in the number of overlapping layers between each of the first area to be tested and the corresponding second area to be tested is less than a preset value;

If the difference is less than the preset value, the first area to be measured is taken as a component of the first overlapping area in the first image, and the corresponding second area to be measured is taken as the first The component parts of the second overlapping area in the two images are used to determine the first overlapping area and the second overlapping area.
The method according to claim 4, wherein the first area to be measured is used as a component of the first overlapping area in the first image, and the corresponding second area to be measured is used as the After determining the components of the second overlapping area in the second image, the first overlapping area and the second overlapping area are determined, and the first overlapping area and the second overlapping area are merged and spliced using the weighted average method Before processing, before obtaining the fused and spliced third image, the method further includes:

Determine the sampling point according to the image position information of the first image and the second image; wherein the image position information is used to describe the position of the first image and the second image corresponding to the human anatomical coordinate system ；

Obtaining a registration transformation matrix according to the human anatomical coordinates of the sampling point, the first image coordinates of the sampling point in the first image, and the second image coordinates in the second image;

According to the registration transformation matrix, the first coincidence area and the second coincidence area are registered.
The method according to claim 5, wherein the registering the first coincidence area and the second coincidence area according to the registration transformation matrix comprises:

Using the first overlapping area as a reference area, the points with the same human anatomical coordinates in the second overlapping area are registered to the same position in the first overlapping area through the registration transformation matrix; or,

Using the second overlapping area as a reference area, the points with the same human anatomical coordinates in the first overlapping area are registered to the same position in the second overlapping area through the registration transformation matrix.
7. The method according to any one of claims 1 to 6, wherein the weighted average method is used to perform fusion splicing processing on the first coincident area and the second coincident area to obtain a third image after fusion splicing, include:

The first overlapping area is divided into a plurality of first to-be-merged column areas, and the second overlapping area is divided into a plurality of second to-be-merged column areas, the first to-be-fused column area and the second to-be-fused column area One-to-one correspondence between column areas;

According to the order of the distance between each of the first to-be-fused column regions and the second overlapping region, the first preset weight coefficient of each of the first to-be-fused column regions is sequentially obtained, wherein the first The preset weight coefficient becomes smaller as the distance between the corresponding first column area to be fused and the second overlapping area increases;

According to the first preset weight coefficient, a second preset weight coefficient of the second column area to be fused corresponding to the first column area to be fused is obtained, wherein the first preset weight coefficient and the first column area are 2. The sum of the preset weight coefficients is equal to one;

According to the first preset weight coefficient and the second preset weight coefficient, add the pixel values of each of the first column area to be fused and the corresponding second column area to be fused to obtain a fused pixel Value to obtain the third image after fusion splicing.
A three-dimensional MRA medical image splicing device, the device comprising:

The receiving unit is used to receive two adjacent three-dimensional MRA medical images to be spliced from the scanning device in real time;

A denoising unit, configured to perform Laplacian denoising, enhancement and irregular smoothing processing on the two adjacent three-dimensional MRA medical images to be spliced to obtain a first image and a second image;

A detection unit, configured to perform overlap layer detection on the first image and the second image respectively to determine the first overlap area in the first image and the second overlap area in the second image;

The stitching unit is configured to perform fusion stitching processing on the first overlapping area and the second overlapping area using a weighted average method to obtain a third image after fusion stitching.
The device according to claim 8, after the splicing unit is configured to use a weighted average method to perform a fusion splicing process on the first overlapping area and the second overlapping area to obtain a third image after fusion splicing, The denoising unit is further configured as:

A low-pass filter is used to perform smoothing filtering processing on the third image to obtain a target smooth image.
The device according to claim 9, wherein the detection unit is used to detect the overlapping layer of the first image and the second image respectively to determine the first overlap area in the first image and the Before the second overlapping area in the second image, it also includes:

The comparison unit is configured to compare the respective maximum density projection imaging of the first image and the second image to determine the first overlapped segment in the first image and the second overlapped segment in the second image Coincident fragments

And, the detection unit is configured to:

Perform overlap layer detection on the first overlap segment and the second overlap segment to determine the first overlap area in the first image and the second overlap area in the second image.
The apparatus according to claim 10, wherein the detection unit is configured to:

Divide the first overlapping segment into a plurality of first regions to be tested, and divide the second overlapping segment into a plurality of second regions to be tested, the first region to be tested and the second region to be tested one by one correspond;

Sequentially determining whether the difference in the number of overlapping layers between each of the first area to be tested and the corresponding second area to be tested is less than a preset value;

If the difference is less than the preset value, the first area to be measured is taken as a component of the first overlapping area in the first image, and the corresponding second area to be measured is taken as the first The component parts of the second overlapping area in the two images are used to determine the first overlapping area and the second overlapping area.
The device according to claim 11, wherein the detection unit is configured to use the first area to be measured as a component of the first overlapping area in the first image, and to set the corresponding second area to be measured As a component of the second coincidence area in the second image, after the first coincidence area and the second coincidence area are determined, and the splicing unit is used to perform a weighted average method on the first coincidence area. Before performing fusion splicing processing on the region and the second overlapping region, and before obtaining the fused and spliced third image, the method further includes:

The determining unit is configured to determine sampling points according to the image location information of the first image and the second image; wherein the image location information is used to describe that the first image and the second image correspond to a human body The position of the anatomical coordinate system;

An obtaining unit, configured to obtain a registration transformation matrix according to the human anatomical coordinates of the sampling point, the first image coordinates of the sampling point in the first image, and the second image coordinates in the second image ；

The registration unit is configured to register the first coincidence area and the second coincidence area according to the registration transformation matrix.
The device according to claim 12, the registration unit is configured to:

Using the first overlapping area as a reference area, the points with the same human anatomical coordinates in the second overlapping area are registered to the same position in the first overlapping area through the registration transformation matrix; or,

Using the second overlapping area as a reference area, the points with the same human anatomical coordinates in the first overlapping area are registered to the same position in the second overlapping area through the registration transformation matrix.
The device according to claims 8-13, the splicing unit is configured to:

The first overlapping area is divided into a plurality of first to-be-merged column areas, and the second overlapping area is divided into a plurality of second to-be-merged column areas, the first to-be-fused column area and the second to-be-fused column area One-to-one correspondence between column areas;

According to the order of the distance between each of the first to-be-fused column regions and the second overlapping region, the first preset weight coefficient of each of the first to-be-fused column regions is sequentially obtained, wherein the first The preset weight coefficient becomes smaller as the distance between the corresponding first column area to be fused and the second overlapping area increases;

According to the first preset weight coefficient, a second preset weight coefficient of the second column area to be fused corresponding to the first column area to be fused is obtained, wherein the first preset weight coefficient and the first column area are 2. The sum of the preset weight coefficients is equal to one;

According to the first preset weight coefficient and the second preset weight coefficient, add the pixel values of each of the first column area to be fused and the corresponding second column area to be fused to obtain a fused pixel Value to obtain the third image after fusion splicing.
An electronic device comprising: a processor; and a memory for storing a three-dimensional MRA medical image stitching program of the processor; wherein the processor is configured to execute the following processing by executing the three-dimensional MRA medical image stitching program :

Receive two adjacent 3D MRA medical images to be spliced from the scanning device in real time;

Performing Laplacian denoising, enhancement and irregular smoothing processing on the two adjacent three-dimensional MRA medical images to be spliced to obtain a first image and a second image;

Performing overlapping layer detection on the first image and the second image respectively to determine a first overlapping area in the first image and a second overlapping area in the second image;

A weighted average method is used to perform fusion splicing processing on the first overlapping area and the second overlapping area to obtain a third image after fusion splicing.
The electronic device according to claim 15, wherein said detecting the overlapping layer of the first image and the second image respectively to determine the first overlapping area and the second overlapping area in the first image Before the second overlapping area in the image, the method further includes:

Comparing the respective maximum density projection imaging of the first image and the second image to determine the first overlapping segment in the first image and the second overlapping segment in the second image;

And, the performing overlapping layer detection on the first image and the second image respectively to determine the first overlapping area in the first image and the second overlapping area in the second image includes:

Perform overlap layer detection on the first overlap segment and the second overlap segment to determine the first overlap area in the first image and the second overlap area in the second image.
The electronic device according to claim 16, wherein the detection of the overlapping layer of the first overlapping segment and the second overlapping segment is performed to determine the first overlapping area and the first overlapping area in the first image The second overlap area in the second image includes:

Divide the first overlapping segment into a plurality of first regions to be tested, and divide the second overlapping segment into a plurality of second regions to be tested, the first region to be tested and the second region to be tested one by one correspond;

Sequentially determining whether the difference in the number of overlapping layers between each of the first area to be tested and the corresponding second area to be tested is less than a preset value;

If the difference is less than the preset value, the first area to be measured is taken as a component of the first overlapping area in the first image, and the corresponding second area to be measured is taken as the first The component parts of the second overlapping area in the two images are used to determine the first overlapping area and the second overlapping area.
The electronic device according to claim 17, wherein the first area to be measured is used as a component of the first overlapping area in the first image, and the corresponding second area to be measured is used as the After determining the components of the second overlapping area in the second image, the first overlapping area and the second overlapping area are determined, and the weighted average method is used to fuse the first overlapping area and the second overlapping area Before the splicing process to obtain the third image after fusion splicing, the method further includes:

Determine the sampling point according to the image position information of the first image and the second image; wherein the image position information is used to describe the position of the first image and the second image corresponding to the human anatomical coordinate system ；

Obtaining a registration transformation matrix according to the human anatomical coordinates of the sampling point, the first image coordinates of the sampling point in the first image, and the second image coordinates in the second image;

According to the registration transformation matrix, the first coincidence area and the second coincidence area are registered.
The electronic device according to claim 18, wherein the registering the first coincidence area and the second coincidence area according to the registration transformation matrix comprises:

Using the first overlapping area as a reference area, the points with the same human anatomical coordinates in the second overlapping area are registered to the same position in the first overlapping area through the registration transformation matrix; or,

Using the second overlapping area as a reference area, the points with the same human anatomical coordinates in the first overlapping area are registered to the same position in the second overlapping area through the registration transformation matrix.
15. The electronic device according to claim 15, wherein said obtaining the user characteristic differences between each of the user characteristic combinations in the first score range and the user characteristic combinations in each second score range to obtain multiple user characteristic differences, include:

Acquiring the first user feature combination element of each user feature combination in the first score range;

Acquiring a second user feature combination element of each user feature combination in the second score range;

Obtain the distinguishing features of each of the first user feature combination elements and each of the second user feature combination elements, and obtain each user feature combination of the first score range and each user feature combination of the second score range The difference in user characteristics.
The electronic device according to claims 15-20, wherein said using a weighted average method to perform fusion splicing processing on said first coincident area and said second coincident area to obtain a third image after fusion splicing comprises:

The first overlapping area is divided into a plurality of first to-be-merged column areas, and the second overlapping area is divided into a plurality of second to-be-merged column areas, the first to-be-fused column area and the second to-be-fused column area One-to-one correspondence between column areas;

According to the order of the distance between each of the first to-be-fused column regions and the second overlapping region, the first preset weight coefficient of each of the first to-be-fused column regions is sequentially obtained, wherein the first The preset weight coefficient becomes smaller as the distance between the corresponding first column area to be fused and the second overlapping area increases;

According to the first preset weight coefficient, a second preset weight coefficient of the second column area to be fused corresponding to the first column area to be fused is obtained, wherein the first preset weight coefficient and the first column area are 2. The sum of the preset weight coefficients is equal to one;

According to the first preset weight coefficient and the second preset weight coefficient, add the pixel values of each of the first column area to be fused and the corresponding second column area to be fused to obtain a fused pixel Value to obtain the third image after fusion splicing.
A computer-readable storage medium storing a three-dimensional MRA medical image splicing program, wherein the three-dimensional MRA medical image splicing program is executed by a processor to implement the following processing:

Receive two adjacent 3D MRA medical images to be spliced from the scanning device in real time;

Performing Laplacian denoising, enhancement and irregular smoothing processing on the two adjacent three-dimensional MRA medical images to be spliced to obtain a first image and a second image;

Performing overlapping layer detection on the first image and the second image respectively to determine a first overlapping area in the first image and a second overlapping area in the second image;

A weighted average method is used to perform fusion splicing processing on the first overlapping area and the second overlapping area to obtain a third image after fusion splicing.