WO2023109212A1

WO2023109212A1 - Cbct image denoising method and apparatus, storage medium and electronic device

Info

Publication number: WO2023109212A1
Application number: PCT/CN2022/118526
Authority: WO
Inventors: 易前娥; 张康平; 孙宇; 张文宇; 王亚杰; 吴宏新
Original assignee: 北京朗视仪器股份有限公司
Priority date: 2021-12-16
Filing date: 2022-09-13
Publication date: 2023-06-22
Also published as: CN114298927B; CN114298927A

Abstract

A CBCT image denoising method and apparatus, a storage medium, and an electronic device. The method comprises: acquiring a CBCT image (S101); calculating a dynamic segmentation threshold corresponding to region growth according to according to Otsu segmentation thresholds corresponding to slices of a cross-section, a coronal plane, and a sagittal plane of the CBCT image (S102); calculating a growth seed point of a cavity region according to the CBCT image (S103); performing region growth on the cross section, the coronal plane and the sagittal plane of the CBCT image according to the dynamic segmentation threshold and the growth seed point to obtain a segmentation result of the CBCT image (S104); performing dilation and erosion processing on the CBCT image segmentation result to obtain a corresponding CBCT segmentation image (S105); and combining the CBCT segmentation image and performing processing on the CBCT image to obtain a denoised CBCT image (S106). The present method uses a dynamic segmentation threshold value as a growth condition when performing region growth, such that over-segmentation and under-segmentation are unlikely to occur in an image with a high noise level difference, improving adaptability. Therefore, by implementing the present method, self-adaption of a threshold parameter is realized, and the robustness of the algorithm is improved.

Description

A CBCT image denoising method, device, storage medium and electronic equipment

Cross References to Related Applications

This application claims the priority of the Chinese patent application with the application number 202111546228.7 and the title "A CBCT image denoising method, device, storage medium and electronic equipment" submitted to the State Intellectual Property Office of China on December 16, 2021. The entire contents are incorporated by reference in this application.

technical field

The present application relates to the technical field of radiation imaging, in particular to a CBCT image denoising method, device, storage medium and electronic equipment.

Background technique

In stomatology, CBCT data plays an important role, but the obtained CBCT tomographic images are often accompanied by a large amount of electronic noise and quantum noise. For example, in the brain, there are multiple cavity areas such as the mouth, throat, and nasal cavity. Ideally, these cavity areas are filled with air, and the gray value on the CBCT image should be zero. However, due to noise pollution, serious The contrast between the image cavity area and other tissue structure information is reduced, and the visual effect is poor, which affects the doctor's observation and judgment of the lesion, and also affects the post-processing task of the image information. The existing CBCT image denoising methods include TV denoising, three-dimensional block matching method, wavelet filtering method, etc., and there are many problems: the traditional region growing segmentation algorithm uses a fixed threshold as the growth condition, and it is easy to appear when encountering images with large noise levels. Over-segmentation or under-segmentation, poor adaptability.

Contents of the invention

In view of this, the embodiment of the present application provides a CBCT image denoising method, device, storage medium, and electronic equipment to solve the problem of over-segmentation or under-segmentation and poor adaptability when segmenting CBCT images in the prior art. technical problem.

The technical scheme that this application proposes is as follows:

The first aspect of the embodiment of the present application provides a CBCT image denoising method. The CBCT image denoising method includes: acquiring a CBCT image; calculating the otsu segmentation threshold corresponding to the cross section, coronal plane and sagittal plane slices of the CBCT image The dynamic segmentation threshold corresponding to the region growth; calculate the growth seed point of the cavity area according to the CBCT image; perform the cross-section, coronal plane and sagittal plane of the CBCT image according to the dynamic segmentation threshold and the growth seed point Region growing to obtain the CBCT image segmentation result; performing dilation and erosion processing on the CBCT image segmentation result to obtain a corresponding CBCT segmented image; combining the CBCT segmented image and processing the CBCT image to obtain a denoised CBCT image .

Optionally, the acquiring the CBCT image includes: acquiring an initial CBCT image from the acquired CBCT three-dimensional tomographic image; performing bilateral filtering on the initial CBCT image to obtain the CBCT image.

Optionally, the calculating the growth seed point of the cavity region according to the CBCT image includes: segmenting any two-dimensional image of the cross-section, coronal plane and sagittal plane of the CBCT image to obtain the first binary value Image and record the segmentation threshold and determine the foreground area and background area in the first binary image; compare the area of the corresponding soft tissue area in the foreground area with the preset area threshold; when the corresponding soft tissue area in the foreground area The area of the soft tissue area is smaller than the preset area threshold, and the corresponding soft tissue area in the foreground area is removed from the foreground area to obtain a corresponding second binary image; The foreground area corresponding to the image is processed to obtain a grayscale image; the foreground area after the distance transformation is traversed and the pixel point corresponding to the maximum value of the pixel value in the foreground area after the distance transformation is used as the growth seed point of the cavity area.

Optionally, performing region growth on the transverse plane, coronal plane, and sagittal plane of the CBCT image according to the dynamic segmentation threshold and the growth seed point to obtain the segmentation result of the CBCT image includes: calculating the points to be measured The difference between the gray value and the gray value corresponding to the growth point; the difference is compared with the dynamic segmentation threshold, and the difference is smaller than the dynamic segmentation threshold as the growth criterion and the corresponding neighbor of the growth seed point Region growing is performed in the domain to obtain the segmentation results of the cross-section, coronal plane and sagittal plane of the CBCT image.

Optionally, the method further includes: performing an OR operation on the segmentation results of the cross-section, coronal plane and sagittal plane of the CBCT image and combining the segmentation information of the cross-section, coronal plane and sagittal plane of the CBCT image The result of the CBCT image segmentation is obtained.

Optionally, the combining the CBCT segmented image and processing the CBCT image to obtain a denoised CBCT image includes: traversing the CBCT data corresponding to the acquired CBCT three-dimensional tomographic image, and converting the corresponding The location of the foreground region is assigned zero.

The second aspect of the embodiment of the present application provides a CBCT image denoising device, the CBCT image denoising device includes: an acquisition module, used to acquire a CBCT image; a first calculation module, used to The otsu segmentation threshold corresponding to the slice of the sagittal plane calculates the dynamic segmentation threshold corresponding to the region growth; the second calculation module is used to calculate the growth seed point of the cavity area according to the CBCT image; the growth module is used to calculate the growth seed point according to the dynamic The segmentation threshold and the growth seed point perform region growth on the cross-section, coronal plane and sagittal plane of the CBCT image to obtain the segmentation result of the CBCT image; a processing module is used to expand and erode the segmentation result of the CBCT image The corresponding CBCT segmented image is obtained by processing; the second processing module is used to combine the CBCT segmented image and process the CBCT image to obtain a denoised CBCT image.

Optionally, the device further includes: a first acquisition module, configured to acquire an initial CBCT image from the acquired CBCT three-dimensional tomographic image; a third processing module, configured to perform bilateral filtering on the initial CBCT image to obtain the CBCT images.

The third aspect of the embodiment of the present application provides a computer-readable storage medium, the computer-readable storage medium stores computer instructions, and the computer instructions are used to make the computer execute the first aspect and the first aspect of the embodiment of the present application. The CBCT image denoising method described in any one of the aspects.

The fourth aspect of the embodiment of the present application provides an electronic device, including: a memory and a processor, the memory and the processor are connected to each other in communication, the memory stores computer instructions, and the processor executes the Computer instructions, so as to execute the CBCT image denoising method as described in the first aspect of the embodiment of the present application and any one of the first aspect.

The technical scheme provided by this application has the following effects:

The CBCT image denoising method provided in the embodiment of the present application obtains a CBCT image; calculates the dynamic segmentation threshold corresponding to the region growth according to the otsu segmentation threshold corresponding to the cross section, coronal plane, and sagittal plane slice of the CBCT image; according to the CBCT image The image calculates the growth seed point of the cavity area; according to the dynamic segmentation threshold and the growth seed point, the cross-section, coronal plane and sagittal plane of the CBCT image are region-grown to obtain the CBCT image segmentation result; The CBCT image segmentation result is expanded and eroded to obtain a corresponding CBCT segmented image; the CBCT segmented image is combined and processed to obtain a denoised CBCT image. This method adopts the dynamic segmentation threshold as the growth condition in the region growing, and it is not easy to over-segment or under-segment when encountering images with large noise level differences, and has good adaptability. Therefore, by implementing the present application, the threshold parameter self-adaptation is realized, and the robustness of the algorithm is increased.

Description of drawings

In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the accompanying drawings that need to be used in the description of the specific embodiments or prior art. Obviously, the accompanying drawings in the following description The figures show some implementations of the present application, and those skilled in the art can obtain other figures based on these figures without any creative effort.

Fig. 1 is the flowchart of the CBCT image denoising method according to the embodiment of the application;

Fig. 2 is a schematic diagram of a CBCT image according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a CBCT image after denoising according to an embodiment of the present application;

FIG. 4 is a structural block diagram of a CBCT image denoising device according to an embodiment of the present application;

Fig. 5 is a schematic structural diagram of a computer-readable storage medium provided according to an embodiment of the present application;

Fig. 6 is a schematic structural diagram of an electronic device provided according to an embodiment of the present application.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of this application.

The embodiment of the present application provides a CBCT image denoising method, as shown in Figure 1, the method includes the following steps:

Step S101: acquiring a CBCT image. Specifically, before denoising, the corresponding CBCT image is acquired first. In one embodiment, as shown in FIG. 2 , a CBCT image of a certain patient is acquired.

Step S102: Calculate the dynamic segmentation threshold corresponding to the region growth according to the otsu segmentation thresholds corresponding to the slices of the cross-section, coronal plane and sagittal plane of the CBCT image. Specifically, there are large differences in the gray value and noise level between different slices in a CBCT image, and using a fixed threshold as a region growing condition can easily lead to under-segmentation or over-segmentation. Therefore, after the CBCT image is obtained, the dynamic segmentation threshold corresponding to the region growing is calculated before the slice segmentation of the CBCT image. Specifically, it is calculated according to the otsu segmentation threshold corresponding to the slices of the cross-section, coronal plane and sagittal plane of the CBCT image, and the specific calculation formula is:

T′ _X (i)=μ·T _X (i), i∈(0,1,2,…,X _X -1)

In the formula, T _X (i) represents the otsu segmentation threshold corresponding to the i-th slice of the CBCT image cross-section/coronal/sagittal plane; μ represents the preset coefficient; N _X represents the CBCT image cross-section/coronal/sagittal plane The total number of slices.

Step S103: Calculate the growth seed point of the cavity area according to the CBCT image. Specifically, after the CBCT image is obtained, the CBCT image is processed and calculated to obtain the growth seed point of the cavity region. Among them, the CBCT image contains multiple cavity regions.

In one embodiment, the acquired CBCT image of the brain includes multiple cavities such as the oral cavity, throat, and nasal cavity.

Step S104: performing region growing on the transverse plane, coronal plane and sagittal plane of the CBCT image according to the dynamic segmentation threshold and the growth seed point to obtain the segmentation result of the CBCT image. Specifically, after the dynamic segmentation threshold and the growth seed point are obtained, the growth seed point is used as the starting point of growth and combined with the dynamic segmentation threshold to perform region growth on the transverse, coronal, and sagittal planes of the CBCT image to obtain the CBCT image. Split results.

Step S105: Dilate and erode the CBCT image segmentation result to obtain a corresponding CBCT segmented image. After the CBCT image segmentation result is obtained, the segmentation result is processed based on three-dimensional morphology. Specifically, the expansion process can remove the noise caused by excessive noise, and optimize the cavity area of part of the under-segmentation of the slice, and then perform the erosion process to remove part of the boundary pixels, and obtain the final otsu segmented image, which is the corresponding CBCT segmented image .

Step S106: Combining the CBCT segmented image and processing the CBCT image to obtain a denoised CBCT image. Specifically, the denoised CBCT image can be obtained by processing the originally acquired CBCT image in combination with the segmentation result, that is, the CBCT segmented image.

As an optional implementation manner of the embodiment of the present application, when acquiring a CBCT image, first acquire an initial CBCT image from the acquired CBCT three-dimensional tomographic image, and then perform bilateral filtering on the initial CBCT image to obtain a corresponding CBCT image. Specifically, CT scanning is first used to acquire 3D tomographic images. Since some noise points are difficult to distinguish during the segmentation process, which will reduce the segmentation accuracy, bilateral filtering is performed on the acquired 3D tomographic images to obtain corresponding CBCT images. Among them, the bilateral filtering process can eliminate the noise mixed in when the image is digitized.

As an optional implementation of the embodiment of the present application, when calculating the growth seed point of the cavity region based on the CBCT image, firstly segment any two-dimensional image of the cross-section, coronal plane, and sagittal plane of the CBCT image to obtain The first binary image and record the segmentation threshold, and determine the foreground area and the background area in the first binary image. Specifically, select any two-dimensional image X _plane (i) of the sagittal plane (any one of the cross-section, coronal plane and sagittal plane of the CBCT image) in the CBCT image, and use the threshold segmentation method (otsu) to perform Roughly segment and record the otsu segmentation threshold, where the pixel area whose gray value is less than the otsu segmentation threshold is the foreground area, and the corresponding pixel value is 1; the pixel area whose gray value is greater than the otsu segmentation threshold is the background area, and the corresponding pixel value is 0. After segmentation, the corresponding first binary image B _X (i) can be obtained. Among them, any two-dimensional image of each cross section, coronal plane and sagittal plane in the CBCT image is selected and segmented; the otsu segmentation threshold is a threshold automatically calculated by the otsu method, and otsu is a threshold segmentation algorithm that can Calculate the optimal segmentation threshold based on the image.

After determining the foreground area and background area, due to the large noise, the gray value of some soft tissue structures in the CBCT image is close to the noise gray value, and the rough segmentation using the threshold segmentation method (otsu) is easy to make the gray value close to the noise gray value The soft tissue area is misclassified as a foreground area, that is, the foreground area in the first binary image B _x (i) contains part of the soft tissue area, so the mis-segmented soft tissue area in the foreground area needs to be removed. Specifically, the area of multiple foreground regions in B _X (i) is compared with the preset area threshold, and when the area of the foreground region is smaller than the preset area threshold, the foreground region is removed, and the area of all foreground regions is screened to obtain The corresponding second binary image B' _X (i), and then calculate the seed point corresponding to the foreground area in B' _X (i).

Because the threshold segmentation method is easy to cause over-segmentation, if the foreground area in B′ _X (i) is directly used as the growth seed, there may be a problem of wrong calculation of the seed point. In addition, there are a variety of structural shapes in the cavity area contained in the cranial brain. When the centroid of the foreground area is selected as the seed, it is easy to cause the centroid to not be in the foreground area. Therefore, in order to accurately calculate the effective seed point of the cavity area, firstly, according to the distance transformation method to process the foreground area corresponding to the second binary image to obtain a grayscale image; then traverse the foreground area pixels after distance transformation, and use the pixel point corresponding to the maximum value of the pixel value in the foreground area after distance transformation as the cavity area Grow seed points.

Specifically, first use the distance transformation method to process the foreground area in the binary image B′ _X (i) to obtain a grayscale image. After the distance transformation method, the farther away from the background area, the higher the pixel value of the corresponding foreground area. After the transformation, the determined foreground area is partially highlighted, and then the foreground area after the distance transformation is traversed, and the pixel coordinate corresponding to its maximum value is used as the growth seed.

As an optional implementation of the embodiment of the present application, after the dynamic segmentation threshold and the growth seed point are determined, region growing is performed on the cross-sectional, coronal, and sagittal planes of the CBCT image to obtain the CBCT image segmentation result. First calculate the difference between the gray value of the point to be measured and the gray value corresponding to the growing point, and compare the difference with the dynamic segmentation threshold, and use the difference less than the dynamic segmentation threshold as the growth criterion and within the corresponding neighborhood of the growth seed point The segmentation results of the cross-section, coronal plane and sagittal plane of the CBCT image were obtained by region growing. Specifically, the obtained growth seed point (x, y) is used as the starting point of growth, and the difference between the gray value of the measured point and the gray value corresponding to the growth point (x, y) is less than the dynamic segmentation threshold T′ _X (i) as Growth criteria, in the 8 adjacent neighborhoods of the growth seed point: (x-1, y-1), (x-1, y), (x-1, y+1), (x, y-1 ), (x, y+1), (x+1, y-1), (x+1, y), (x+1, y+1) perform region growth, and merge pixels that meet the growth criteria, And the merged pixel is used as a new growth seed, and the 8 adjacent neighbor pixels are continuously grown and merged until there is no pixel point that meets the growth criterion, and the growth is stopped. Using the region growing method to perform region growth on the cross-section, coronal plane and sagittal plane of the CBCT image can obtain the segmentation results corresponding to the cross-section, coronal plane and sagittal plane of the CBCT image. Each slice segmentation process and the three-dimensional segmentation process meet the independent calculation conditions, and the processing efficiency is effectively improved by parallel computing, and the time consumption is shorter.

In one embodiment, region growing is performed on the cross-sectional two-dimensional image Z _plane (k), the coronal plane Y _plane (j) and the sagittal plane X _plane (i) of the CBCT data respectively to obtain the segmentation result

Finally, the CBCT image segmentation result can be obtained by performing an OR operation on the cross-sectional, coronal and sagittal plane segmentation results of the obtained CBCT image and combining the cross-sectional, coronal and sagittal plane segmentation information of the CBCT image.

In one embodiment, the two-dimensional segmentation results are combined into three-dimensional results:

in,

Represent the three-dimensional results based on sagittal plane, coronal plane, and cross-sectional segmentation, respectively. right

Perform or operation to effectively combine the segmentation information of the three sections to obtain the segmentation result

That is, the result of CBCT image segmentation.

As an optional implementation of the embodiment of the present application, combining the CBCT segmented image and processing the CBCT image to obtain a denoised CBCT image includes: traversing the CBCT data corresponding to the acquired CBCT three-dimensional tomographic image , and assign the corresponding position of the foreground area to zero. Specifically, combined with the CBCT image segmentation results

By traversing the CBCT data corresponding to the originally acquired CBCT three-dimensional tomographic image, and assigning the corresponding foreground area position as 0, the CBCT image after denoising the cavity area can be obtained. The processing method of assigning the position of the corresponding foreground area to 0 can completely remove the noise in the cavity area without affecting the clarity of other structures. Specifically, compared with the image shown in Figure 2, all black areas in the image shown in Figure 3 have achieved effective denoising, which improves the contrast between the image air area and other tissue structure information, that is, does not affect the clarity of other structures, and completely The noise in the cavity area is removed, and the visual effect is better.

The embodiment of the present application also provides a CBCT image denoising device, as shown in Figure 4, the device includes:

The obtaining module 401 is configured to obtain a CBCT image; for details, refer to the relevant description of step S101 in the above method embodiment.

The first calculation module 402 is used to calculate the dynamic segmentation threshold corresponding to the region growth according to the otsu segmentation threshold corresponding to the cross section, coronal plane and sagittal plane slice of the CBCT image; for details, refer to the relevant step S102 in the above method embodiment describe.

The second calculation module 403 is configured to calculate the growth seed point of the cavity region according to the CBCT image; for details, refer to the relevant description of step S103 in the above method embodiment.

A growing module 404, configured to perform region growth on the cross-sectional, coronal, and sagittal planes of the CBCT image according to the dynamic segmentation threshold and the growth seed point to obtain the segmentation result of the CBCT image; for details, refer to the implementation of the above method The related description of step S104 in the example.

The first processing module 405 is configured to perform dilation and erosion processing on the CBCT image segmentation result to obtain a corresponding CBCT segmented image; for details, refer to the relevant description of step S105 in the above method embodiment.

The second processing module 406 is configured to combine the CBCT segmented image and process the CBCT image to obtain a denoised CBCT image; for details, refer to the relevant description of step S106 in the above method embodiment.

The CBCT image denoising device provided in the embodiment of the present application acquires a CBCT image; calculates the dynamic segmentation threshold corresponding to the region growth according to the otsu segmentation threshold corresponding to the cross section, coronal plane, and sagittal plane slice of the CBCT image; according to the CBCT image The image calculates the growth seed point of the cavity area; according to the dynamic segmentation threshold and the growth seed point, the cross-section, coronal plane and sagittal plane of the CBCT image are region-grown to obtain the CBCT image segmentation result; The CBCT image segmentation result is expanded and eroded to obtain a corresponding CBCT segmented image; the CBCT segmented image is combined and processed to obtain a denoised CBCT image. The dynamic segmentation threshold is used as the growth condition in the region growing, and it is not easy to be over-segmented or under-segmented when encountering images with large differences in noise levels, and the adaptability is better. Therefore, by implementing the present application, the threshold parameter self-adaptation is realized, and the robustness of the algorithm is increased.

As an optional implementation of the embodiment of the present application, the acquisition module includes: a first acquisition module, configured to acquire an initial CBCT image from the acquired CBCT three-dimensional tomographic image; a third processing module, configured to process the The initial CBCT image is processed by bilateral filtering to obtain the CBCT image.

As an optional implementation of the embodiment of the present application, the device further includes: a segmentation processing module, configured to segment any two-dimensional image of the transverse plane, coronal plane, and sagittal plane of the CBCT image to obtain the first A binary image and record the segmentation threshold and determine the foreground area and the background area in the first binary image; a comparison module is used to compare the area of the corresponding soft tissue area in the foreground area with the preset area threshold a removal module, configured to remove the soft tissue region corresponding to the foreground region in the foreground region and obtain the corresponding second Binary image; the fourth processing module is used to process the foreground area corresponding to the second binary image according to the distance transformation method to obtain a grayscale image; the first determination module is used to traverse the distance transformed foreground area and The pixel point corresponding to the maximum value of the pixel value in the foreground area after the distance transformation is used as the growth seed point of the cavity area.

As an optional implementation of the embodiment of the present application, the device further includes: a third calculation module, configured to calculate the difference between the gray value of the point to be measured and the gray value corresponding to the growth point; the second determination module, Comparing the difference with the dynamic segmentation threshold, using the difference smaller than the dynamic segmentation threshold as a growth criterion and performing region growth in the neighborhood corresponding to the growth seed point to obtain the cross-section of the CBCT image, Segmentation results of coronal and sagittal planes.

As an optional implementation of the embodiment of the present application, the device further includes: an operation module, configured to perform an OR operation on the segmentation results of the cross-section, coronal plane, and sagittal plane of the CBCT image and combine the CBCT The segmentation information of the transverse plane, coronal plane and sagittal plane of the image is used to obtain the segmentation result of the CBCT image.

As an optional implementation of the embodiment of the present application, the device further includes: an assignment module, configured to traverse the CBCT data corresponding to the acquired CBCT three-dimensional tomographic image, and assign the corresponding position of the foreground area to zero .

For a detailed description of the function of the CBCT image denoising device provided in the embodiment of the present application, refer to the description of the CBCT image denoising method in the foregoing embodiments.

The embodiment of the present application also provides a storage medium, as shown in FIG. 5 , on which a computer program 601 is stored. When the instruction is executed by a processor, the steps of the CBCT image denoising method in the above embodiment are implemented. The storage medium also stores audio and video stream data, feature frame data, interaction request signaling, encrypted data, and preset data sizes. Wherein, the storage medium can be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive) , abbreviation: HDD) or solid-state hard disk (Solid-State Drive, SSD) etc.; The storage medium may also include a combination of the above-mentioned types of memory.

Those skilled in the art can understand that all or part of the processes in the methods of the above-mentioned embodiments can be completed by instructing related hardware through computer programs, and the programs can be stored in a computer-readable storage medium. During execution, it may include the processes of the embodiments of the above-mentioned methods. Wherein, the storage medium can be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), a random access memory (RandomAccessMemory, RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive) , abbreviation: HDD) or solid-state hard disk (Solid-State Drive, SSD) etc.; The storage medium may also include a combination of the above-mentioned types of memory.

The embodiment of the present application also provides an electronic device. As shown in FIG. 6, the electronic device may include a processor 51 and a memory 52, wherein the processor 51 and the memory 52 may be connected through a bus or in other ways. In FIG. Take the bus connection as an example.

The processor 51 may be a central processing unit (Central Processing Unit, CPU). Processor 51 can also be other general processors, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or Other chips such as programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above-mentioned types of chips.

The memory 52, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as the corresponding program instructions/modules in the embodiments of the present application. The processor 51 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory 52, that is, implements the CBCT image denoising method in the above method embodiments.

The memory 52 may include a program storage area and a data storage area, wherein the program storage area may store an application program required by the operating device and at least one function; the data storage area may store data created by the processor 51 and the like. In addition, the memory 52 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 52 may optionally include a memory that is remotely located relative to the processor 51, and these remote memories may be connected to the processor 51 through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The one or more modules are stored in the memory 52, and when executed by the processor 51, the CBCT image denoising method in the embodiment shown in Figs. 1-3 is executed.

Specific details of the above-mentioned electronic device can be understood by referring to corresponding descriptions and effects in the embodiments shown in FIG. 1 to FIG. 3 , and details are not repeated here.

Although the embodiment of the application has been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the application, and such modifications and variations all fall within the scope of the appended claims. within the bounds of the requirements.

Claims

A CBCT image denoising method, is characterized in that, comprises the steps:

Acquire CBCT images;

Calculate the dynamic segmentation threshold value corresponding to the region growth according to the otsu segmentation threshold value corresponding to the slices of the CBCT image cross-section, coronal plane and sagittal plane;

calculating the growth seed point of the cavity region according to the CBCT image;

performing region growth on the cross-section, coronal plane, and sagittal plane of the CBCT image according to the dynamic segmentation threshold and the growth seed point to obtain the segmentation result of the CBCT image;

Carrying out expansion and erosion processing on the CBCT image segmentation results to obtain corresponding CBCT segmentation images;

Combining the CBCT segmented image and processing the CBCT image to obtain a denoised CBCT image.
The method according to claim 1, wherein said acquiring a CBCT image comprises:

Obtain an initial CBCT image from the acquired CBCT three-dimensional tomographic image;

performing bilateral filtering on the initial CBCT image to obtain the CBCT image.
The method according to claim 1, wherein the calculation of the growth seed point of the cavity region according to the CBCT image comprises:

Segment any two-dimensional image of the cross section, coronal plane and sagittal plane of the CBCT image to obtain a first binary image and record the segmentation threshold and determine the foreground area and background area in the first binary image;

comparing the area of the corresponding soft tissue area in the foreground area with a preset area threshold;

When the area of the corresponding soft tissue area in the foreground area is smaller than the preset area threshold, remove the corresponding soft tissue area in the foreground area and obtain a corresponding second binary image;

Processing the foreground area corresponding to the second binary image according to the distance transformation method to obtain a grayscale image;

The foreground area after the distance transformation is traversed, and the pixel point corresponding to the maximum value of the pixel value in the foreground area after the distance transformation is used as the growth seed point of the cavity area.
The method according to claim 1, wherein the CBCT image is obtained by performing region growth on the cross-section, coronal plane and sagittal plane of the CBCT image according to the dynamic segmentation threshold and the growth seed point Segmentation results, including:

Calculate the difference between the gray value of the point to be measured and the gray value corresponding to the growth seed point;

Comparing the difference with the dynamic segmentation threshold, using the difference smaller than the dynamic segmentation threshold as a growth criterion, and performing region growth in the neighborhood corresponding to the growth seed point to obtain the cross-section and coronal plane of the CBCT image Segmentation results with sagittal plane.
The method according to claim 4, characterized in that the method further comprises:

performing an OR operation on the segmentation results of the cross-section, coronal plane, and sagittal plane of the CBCT image and combining the segmentation information of the cross-section, coronal plane, and sagittal plane of the CBCT image to obtain the segmentation result of the CBCT image.
The method according to claim 3, wherein said combining said CBCT segmented image and processing said CBCT image to obtain a denoised CBCT image comprises:

The CBCT data corresponding to the acquired CBCT three-dimensional tomographic image is traversed, and the corresponding position of the foreground area is assigned a value of zero.
A CBCT image denoising device, characterized in that it comprises:

Obtain module, be used for obtaining CBCT image;

The first calculation module is used to calculate the dynamic segmentation threshold corresponding to the region growth according to the otsu segmentation threshold corresponding to the slice of the CBCT image cross section, coronal plane and sagittal plane;

The second calculation module is used to calculate the growth seed point of the cavity area according to the CBCT image;

A growth module, configured to perform region growth on the cross-section, coronal plane, and sagittal plane of the CBCT image according to the dynamic segmentation threshold and the growth seed point to obtain the segmentation result of the CBCT image;

The first processing module is used to expand and erode the CBCT image segmentation result to obtain a corresponding CBCT segmented image;

The second processing module is configured to combine the CBCT segmented image and process the CBCT image to obtain a denoised CBCT image.
The device according to claim 7, wherein the device further comprises:

A first acquisition module, configured to acquire an initial CBCT image from the acquired CBCT three-dimensional tomographic image;

The third processing module is configured to perform bilateral filtering processing on the initial CBCT image to obtain the CBCT image.
A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to perform the CBCT image removal described in any one of claims 1-6. noise method.
An electronic device, characterized in that it includes: a memory and a processor, the memory and the processor are connected to each other in communication, the memory stores computer instructions, and the processor executes the computer instructions, thereby Execute the CBCT image denoising method as described in any one of claims 1-6.