CN109949233B - Method, system, device and storage medium for filtering scattered rays in X-ray image - Google Patents
Method, system, device and storage medium for filtering scattered rays in X-ray image Download PDFInfo
- Publication number
- CN109949233B CN109949233B CN201910123586.3A CN201910123586A CN109949233B CN 109949233 B CN109949233 B CN 109949233B CN 201910123586 A CN201910123586 A CN 201910123586A CN 109949233 B CN109949233 B CN 109949233B
- Authority
- CN
- China
- Prior art keywords
- image
- scattered
- ray image
- rays
- detail
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The application provides a method, a system, equipment and a storage medium for filtering scattered rays in an X-ray image, which comprises the following steps: extracting the image characteristics of scattered rays in the original image; removing scattered ray image components in the original image according to the scattered ray image characteristics; performing detail restoration processing on the original image without the scattered ray image components to obtain a detail restoration image; and adjusting the gray value of the detail reduction image to reach the standard state, and obtaining the X-ray image after the scattered rays are filtered. The scattered ray image components are removed, and the original image after the scattered ray image components are removed is subjected to detail restoration processing, so that the interference of the scattered ray can be removed while the original details in the image are kept to the maximum extent; obtaining a direct-ray image with good contrast by selecting specified extraction parameters k, b and c; the noise reduction processing is completely avoided in the complete image processing process, and the information in the X-ray image is greatly reserved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, a system, a device, and a storage medium for filtering scattered rays in an X-ray image.
Background
The X-ray has strong penetrability, can make the film placed behind the object sensitive, and according to the Beer-Lambert law, the X-ray can generate energy attenuation in an exponential form in the process of entering a medium, which is the theoretical basis of X-ray imaging. In practice, multiple complex microscopic interactions of X-rays with the medium occur. According to the action result, the method can be roughly classified into two aspects: on the one hand, the ray energy loss, namely the energy attenuation is realized; on the other hand, the direction of the ray is changed, namely scattered rays are generated. For imaging, energy attenuation is beneficial for improving image quality (beam hardening effect and the like are not considered temporarily), and on the contrary, scattered rays can cause image quality degradation, which is manifested by low contrast resolution and reduced spatial resolution of images, thereby affecting clinical diagnosis and even possibly causing missed diagnosis.
To eliminate the effect of scattered radiation, it is conventional to use a mechanical grid arrangement, placed between the body and the detector, to filter out the scattered radiation directly from the transmitted radiation that has passed through the body. However, the method has obvious disadvantages that the exposure dosage is required to be large and the grid shadow is brought. Another approach is to effectively overcome these problems by using a pure image processing means, i.e. a digital grid, instead of a mechanical grid, to perform the scatter suppression processing on the original image. At present, the existing digital grid technology generally adopts multi-resolution gain processing to enhance image details, wherein multiplicative gain under multiple scales can multiply amplified noise, and the amplified noise under each scale is superposed again in the final image reconstruction, so that the noise problem is further aggravated. On the other hand, too strong noise reduction processing also brings potential information loss side effects inevitably.
Disclosure of Invention
In view of the above, embodiments of the present invention are proposed to provide a method, system, device and storage medium for filtering out scattered radiation in X-ray images that overcome or at least partially solve the above-mentioned problems.
In order to solve the above problems, the embodiment of the present invention discloses a method for filtering scattered rays in an X-ray image, which comprises the following steps:
extracting the image characteristics of scattered rays in the original image;
removing scattered ray image components in the original image according to the scattered ray image characteristics;
performing detail restoration processing on the original image without the scattered ray image components to obtain a detail restoration image;
and adjusting the gray value of the detail reduction image to reach the standard state, and obtaining the X-ray image after the scattered rays are filtered.
Optionally, the step of extracting the image features of the scattered rays in the original image includes:
decomposing the original image into a medium area and a non-medium area;
scattered ray image features in the medium region and the non-medium region are extracted separately.
Optionally, the step of extracting the scattered ray image features in the medium region and the non-medium region respectively comprises:
acquiring the lowest relative intensity of the direct rays in the medium region and the difference parameters of the highest and the lowest relative intensities of the direct rays, and obtaining the scattered ray image characteristics in the medium region according to the lowest relative intensity of the direct rays in the medium region and the difference parameters of the highest and the lowest relative intensities of the direct rays;
and acquiring the lowest relative intensity of the direct rays in the non-medium area and obtaining the scattered ray image characteristics in the non-medium area according to the lowest relative intensity of the direct rays in the non-medium area.
Optionally, the image component of the scattered ray in the original image is calculated according to the following formula:
I st ＝I-I sc
wherein I represents an original image, I st Representing a direct ray image component, I sc Representing the image component of the scattered radiation, omega m A region of the medium in the image is represented,
representing a non-medium region in the image, k representing a difference parameter of highest and lowest relative intensities of the straight rays in the medium region, b representing a lowest relative intensity of the straight rays in the medium region, and c representing a relative intensity of the straight rays in the non-medium region.
Optionally, the step of performing detail reduction processing on the original image from which the scattered ray image component is removed to obtain a detail reduction image includes:
carrying out image decomposition processing on the original image without the scattered ray image components to obtain image decomposition data;
performing gain amplification processing on image details in the image decomposition data to obtain image decomposition data after gain;
and performing image reconstruction on the gained image decomposition data to obtain the detail recovery image.
Optionally, before the step of adjusting the gray value of the detail restored image to reach the standard and obtaining the X-ray image with scattered rays filtered out, the method further includes:
respectively judging whether the gray value of the detail restoration image respectively meets the storage requirement and the display requirement;
if not, adjusting the gray value of the detail reduction image to reach the standard state, and obtaining the X-ray image after the scattered rays are filtered.
Optionally, the step of adjusting the gray value of the detail restored image to reach the standard to obtain the X-ray image with scattered rays filtered out includes:
and adjusting the gray scale domain of the detail restoration image to reach the standard through LUT mapping processing.
In order to solve the above problems, an embodiment of the present invention discloses a system for filtering scattered rays in an X-ray image, which includes the following specific modules:
the extraction module is used for extracting the image characteristics of the scattered rays in the original image;
a removing module, configured to remove scattered ray image components in the original image according to the scattered ray image features;
the restoring module is used for carrying out detail restoring processing on the original image without the scattered ray image components to obtain a detail restored image;
and the adjusting module is used for adjusting the gray value of the detail reduction image to a standard reaching state to obtain an X-ray image after scattered rays are filtered.
In order to solve the above problem, an embodiment of the present invention discloses a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements the method for filtering scattered radiation in an X-ray image according to any one of the embodiments of the present invention.
In order to solve the above problem, an embodiment of the present invention discloses a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the method for filtering out scattered radiation in an X-ray image according to any one of the embodiments of the present invention.
Compared with the prior art, the method has the following advantages:
in the embodiment of the invention, the original image after the scattered ray image components are removed and the scattered ray image components are removed is subjected to detail reduction processing, so that the interference of scattered rays can be removed while the original details in the image are kept to the maximum extent; obtaining a direct-ray image with good contrast by selecting specified extraction parameters k, b and c; the detail recovery effect of the image is good by selecting the designated high-frequency signal gain parameter; the noise reduction processing is completely avoided in the complete image processing process, and the information in the X-ray image is greatly reserved.
Drawings
FIG. 1 is a flowchart illustrating steps of a method for filtering scattered radiation from an X-ray image according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of a method for filtering scattered radiation from an X-ray image according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an original image of a phantom according to an embodiment of the present invention;
FIG. 4 is a schematic view of a phantom scatter feature image according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a phantom raw image after removing scattered ray image features according to an embodiment of the present invention;
FIG. 6 is a schematic view of a phantom detail restored image according to an embodiment of the present invention;
FIG. 7 is a schematic representation of a phantom X-ray image after the scattered radiation has been filtered out according to a method of an embodiment of the present invention;
FIG. 8 is a block diagram of an apparatus for filtering scattered radiation from an X-ray image according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
1. An extraction module; 2. removing the module; 3. a reduction module; 4. an adjustment module; 12. a computer device; 14. an external device; 16. a processing unit; 18. a bus; 20. a network adapter; 22. an (I/O) interface; 24. a display; 28. a system memory; 30. random Access Memory (RAM); 32. a cache memory; 34. a storage system; 40. a program/utility tool; 42. and (4) program modules.
The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
In addition, technical solutions between the embodiments may be combined with each other, but must be based on the realization of the technical solutions by a person skilled in the art, and when the technical solutions are contradictory to each other or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
Finally, the embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
Referring to fig. 1, a flowchart illustrating steps of embodiment 1 of a method for filtering scattered rays in an X-ray image according to the present application is shown, which may specifically include the following steps:
s1, extracting scattered ray image features in an original image;
s2, removing scattered ray image components in the original image according to the scattered ray image characteristics;
s3, performing detail restoration processing on the original image without the scattered ray image components to obtain a detail restoration image;
and S4, adjusting the gray value of the detail reduction image to reach the standard state, and obtaining the X-ray image after the scattered rays are filtered.
As described in the step S1, the scattered ray image features in the original image are extracted, where the original image is generally a comprehensive quantum image I reaching the detector, and the comprehensive quantum image I generally includes the direct quantum image features I st Scattering quantum image characteristics I sc And quantum noise image characteristics I n Note that, the image characteristics I are due to quantum noise n Is the non-uniform distribution and energy spectrum dispersion of X-ray photons, and therefore is not considered separately in the embodiments of the present invention but is included in the direct quantum image feature I st And scattered quantum image characteristics I sc Therefore, the image features of the original image (i.e., the integrated quantum image I) described in the embodiments of the present invention only include the direct quantum image feature I st And scattered quantum image characteristics I sc 。
It should be noted that, the above extraction process generally needs to split the original image into a medium region and a non-medium region, and then extract the scattered ray image features in the two regions respectively.
As described in the step S2, the scattered ray image component in the original image is removed according to the scattered ray image feature, in this embodiment, the removal method generally modifies the pixel value of the corresponding region, specifically modifies the original image by subtracting the scattered ray image pixel formed by the scattered ray image feature, and does not adjust the range of the image pixel value after the scattered ray component is removed.
The method comprises the following steps: deleting the pixel matched with the scattered ray image characteristic or adjusting the pixel value of the pixel to be 0 or 255 to obtain an original image with the scattered ray image component removed; and obtaining an original image after the scattered ray image components are removed by adjusting the pixel values of the pixels which are matched with the scattered ray image characteristics to the pixel values which are the same as the pixel values of the nearby area.
As described in step S3 above, the original image from which the scattered ray image component is removed is subjected to detail reduction processing to obtain a detail reduction image, where it should be noted that the detail reduction process generally includes three steps, specifically: firstly, carrying out image decomposition processing on the original image from which the scattered ray image components are removed; then, gain amplification processing is carried out on the specified partial image details in the image after the decomposition processing; and finally, carrying out image reconstruction processing on the image subjected to the detail gain amplification processing to obtain the detail restoration image.
As described in the step S4, adjusting the gray value of the detail reduced image to the standard-reaching state to obtain the X-ray image after the scattered rays are filtered out, it should be noted that the adjusting of the gray value of the detail reduced image to the standard-reaching state generally includes two determinations: whether the storage requirement of the X-ray image is met or not and whether the display requirement of the X-ray image is met or not, the gray value of the detail restoration image meets the standard transition state only when the storage requirement and the display requirement are met.
Referring to fig. 2, a flowchart illustrating steps of embodiment 2 of the method for filtering out scattered rays in an X-ray image according to the present application is shown, which may specifically include the following steps:
in an embodiment of the present invention, the step of extracting the image features of the scattered rays in the original image includes:
s11, decomposing the original image into a medium area and a non-medium area;
and S12, respectively extracting scattered ray image features in the medium region and the non-medium region.
As described in step S11, the original image is decomposed into a medium region and a non-medium region, where the medium region is a tissue region in the original image and the non-medium region is a non-tissue region in the original image.
As described in step S12 above, the scattered ray image features in the medium region and the non-medium region are respectively extracted, and it should be noted that the scattered ray image features are obtained through the following sub-steps:
a substep S12-1, obtaining the lowest relative intensity of the straight rays in the medium region and the difference parameters of the highest and the lowest relative intensities of the straight rays, and obtaining the scattered ray image characteristics in the medium region according to the lowest relative intensity of the straight rays in the medium region and the difference parameters of the highest and the lowest relative intensities of the straight rays;
and a substep S12-2 of obtaining the lowest relative intensity of the direct rays in the non-medium region and obtaining the scattered ray image characteristics in the non-medium region according to the lowest relative intensity of the direct rays in the non-medium region.
In practical operation, the sub-step S12-3 calculates the scattered ray image components in the original image medium region and the non-medium region according to the following formula:
I st ＝I-I sc
wherein I represents an original image, I st Representing a direct ray image component, I sc Representing the component of the scattered ray image, Ω m A region of the medium in the image is represented,
representing a non-medium region in the image, k representing a difference parameter of highest and lowest relative intensities of the straight rays in the medium region, b representing a lowest relative intensity of the straight rays in the medium region, and c representing a relative intensity of the straight rays in the non-medium region.
In the embodiment of the present invention, the step of performing detail reduction processing on the original image from which the scattered ray image component is removed to obtain a detail reduction image includes:
s31, performing image decomposition processing on the original image without the scattered ray image components to obtain image decomposition data;
s32, carrying out gain amplification processing on image details in the image decomposition data to obtain image decomposition data after gain;
and S33, carrying out image reconstruction on the image decomposition data after the gain to obtain the detail restoration image.
It should be noted that, in the Laplacian pyramid, the higher the resolution is, the higher the corresponding frequency band is, for example: when the number of the decomposition layers is 8, the resolution of the first layer is the same as that of the original image, and the frequency is highest; the eighth layer has the lowest resolution and the lowest frequency; the resolution and frequency of the second layer to the seventh layer are reduced in sequence.
It should be noted that the high frequency band and the low frequency band described in the embodiments of the present invention are relative values rather than limited values, that is, the current highest frequency band and the current lowest frequency band in a complete image processing process are the high frequency band and the low frequency band in the image processing process.
Similarly, the high-frequency signal and the low-frequency signal described in the embodiments of the present invention are also relative values rather than limited values, that is, in the same layer of image, the high-frequency signal represents a finer detailed tissue image signal; the low frequency signal represents the image signal of the relatively thick edge, such as: the edges of the bone.
As described in the step S31, the original image from which the scattered ray image component is removed is subjected to image decomposition processing to obtain image decomposition data, where the image decomposition processing is generally Laplacian pyramid decomposition, and the decomposition manner generally includes direct sampling decomposition, gaussian filter decomposition, mean value filter decomposition, and the like, where the direct sampling decomposition specifically includes the following steps:
(1) Taking an original image as a first-layer input image, and directly performing resolution halving downsampling on the first-layer input image to obtain a second-layer input image;
(2) Performing interpolation up-sampling with doubled resolution on the second layer input image to obtain a predicted image with the same resolution as the first layer input image, wherein the interpolation method comprises nearest neighbor interpolation, bilinear interpolation, bicubic interpolation, gaussian interpolation and the like, and the specific method is determined according to the precision requirement and the actual problem;
(3) Obtaining a difference image according to the first layer input image and the predicted image, wherein the difference image is a Laplacian pyramid first layer (base layer);
difference image = first layer input image-predicted image
(4) And (3) continuing to repeat the process by taking the j-th layer of input image (j =2,3, \8230;, n) as an input image, finally obtaining a series of difference images (comprising j, j =2,3, \8230;, n), namely images of each layer of the Laplacian pyramid, and finally enabling the n + 1-th difference image = the n + 1-th layer of input image (top layer), thereby obtaining the Laplacian pyramid of the n +1 layer.
The Gaussian filter decomposition is specifically as follows:
the only difference between Gaussian filter decomposition and direct sampling decomposition is that the way to obtain the approximate jth layer input image j is different: the direct sampling decomposition is to directly perform resolution halving down-sampling, while the Gaussian filter decomposition is to perform Gaussian filtering first and then perform resolution halving down-sampling on the filtered image. The rest processes are the same, and thus are not described in detail.
The mean filter decomposition is specifically as follows:
the only difference from the Gaussian filter decomposition is that the filter used to generate the approximate j-th layer input image is different, and the rest processes are the same, so the description is omitted.
The specific decomposition mode is determined according to the precision requirement and the problem bias of the image, and as long as the final reduction result does not generate substantial difference, the decomposition mode can be used as the decomposition mode of any embodiment of the invention, wherein the pyramid decomposition layer number is generally more than 4, preferably 4-8, and certainly, the layer number can be reduced to less than 4 or increased to more than 8 on the premise of not affecting the detail recovery effect;
as described in step S32, the image detail in the image decomposition data is subjected to gain amplification processing to obtain the image decomposition data after the gain is obtained, wherein in the process of performing the gain on the image detail, the image detail frequency band subjected to the gain includes full-frequency-band data in the image decomposition data, and the gain amplitude of the data of each frequency band is determined by the curvature control parameter of the frequency band, wherein the curvature control parameter, the frequency band, and the enhancement strength are in positive correlation with each other, that is, the higher the frequency band is, the larger the curvature control parameter is, the higher the enhancement strength is.
In practical application, the image details of the specified part in the image decomposition data are subjected to gain amplification processing, specifically, sigmoid curve transformation is performed layer by layer on the image decomposition data obtained by Laplacian pyramid decomposition in the step S31, and a specific formula is as follows:
σ(x)＝1/(1+e -x )
in the formula:
(a, b) are symmetric center coordinates of the Sigmoid curve; m is an output value range control parameter used for controlling the output amplitude range of the Sigmoid curve; and c is a Sigmoid curve curvature control parameter used for controlling the signal amplification degree.
As described in step S33, the image decomposition data after the gain is subjected to image reconstruction to obtain the detail restored image, where the image reconstruction process is generally Laplacian pyramid reconstruction, and the reconstruction method is an inverse process of the decomposition method, that is, the reconstruction method implemented in this step is an inverse process of the decomposition method adopted in step S31 in the same step, and if there is a reconstruction method obtained by substituting the inverse decomposition method adopted in step S31, the reconstruction method of this step may also be used.
In an embodiment of the present invention, before the step of adjusting the gray level of the detail reduced image to reach the standard and obtaining the X-ray image with scattered rays filtered out, the method further includes:
s41, respectively judging whether the gray value of the detail restoration image respectively meets the storage requirement and the display requirement;
and S42, if not, adjusting the gray value of the detail reduction image to reach the standard state, and obtaining the X-ray image after the scattered rays are filtered.
S41, respectively judging whether the gray value of the detail reduced image respectively meets the storage requirement and the display requirement, wherein in the judging step, the judgment result is yes only when the storage requirement and the display requirement simultaneously meet the standard, namely, when any one of the storage requirement and the display requirement meets the requirement, and the other one does not meet the requirement, or when the storage requirement and the display requirement do not meet the requirement, the judgment result is no;
s42, if not, adjusting the gray value of the detail reduction image to reach the standard state to obtain an X-ray image after scattered rays are filtered; and S43, if so, outputting the detail reduced image as the X-ray image after the scattered rays are filtered, wherein if the judgment result is negative, namely the gray value of the detail reduced image needs to be adjusted, the adjustment of the gray value is generally carried out through mapping processing, and the step of screening pixels before the adjustment is generally included so as to screen out the area needing the gray value adjustment.
In practical applications, the gray scale domain of the detail restoration image is adjusted to reach the standard state through LUT mapping processing.
Referring to fig. 2-7, in the present embodiment, an X-ray image (as shown in fig. 3) including a plurality of organic glass mold bodies is taken as an example, wherein the thickness of the organic glass mold bodies sequentially increases from ROI1 to ROI7, which will be referred to as a mold body X-ray image for short:
inputting the phantom X-ray image serving as a phantom original image Img _ org (X, y) (the X, y are coordinates of pixel points in the image), and the method specifically comprises the following steps:
inputting the original image Img _ org (x, y) of the phantom, and extracting scattered ray image features from the original image Img _ org (x, y) of the phantom according to the following formula:
in the formula, img _ sc (x, y) is a model scattered ray image characteristic; k represents the difference parameter of the highest and lowest relative intensities of the straight rays in the medium region, b represents the lowest relative intensity of the straight rays in the medium region, and c represents the relative intensity of the straight rays in the non-medium region; t = (c-b)/k is a gray threshold for distinguishing medium and non-medium areas;
the scattered ray component is subtracted from the original image by the following formula:
Img_st(x,y)＝Img_org(x,y)-Img_sc(x,y)
in the formula, img _ st (x, y) is a phantom original image after scattered ray components are removed;
performing Laplacian pyramid decomposition on the original phantom image Img _ st (x, y) after the scattered ray components are removed, and in the specific embodiment, decomposing the image by Gaussian filter decomposition:
a. taking Img _ st (x, y) as a first-layer input image G 1 And to G 1 5 x 5 Gaussian kernel filtering is carried out, and then down-sampling with half resolution is carried out to obtain a second layer input image G 2 ；
b. For G 2 Interpolation up-sampling acquisition and G for resolution doubling 1 Predicted image P of the same resolution 1 Interpolation methods include, but are not limited to: nearest neighbor interpolation, bilinear interpolation, bicubic interpolation, and gaussian interpolation, depending on the accuracy requirement and practical problem, the gaussian interpolation is selected in this embodiment;
c. according to G 1 、P 1 Find out the difference image L 1 Wherein L is 1 ＝G 1 -P 1 ，L 1 A first layer (base layer) of a Laplacian pyramid;
with G j (j =2,3.. N.) the above steps a-c are repeated for the input image to obtain a series of difference images L j (j =2, 3.... N), i.e., laplacian pyramid layer image, and finally let L n+1 ＝G n+1 (top layer) to obtain a Laplacian pyramid of n +1 layers
And (3) performing the following Sigmoid curve transformation on each layer of the Laplacian pyramid to restore and organize the details of each layer:
in the formula, L in (x, y) is an input Laplacian pyramid layer image, L out (x, y) is an output Laplacian pyramid layer image; sigma (x) = 1/(1 + e) -x ) (ii) a The parameter pair (a, b) is a symmetric center coordinate of a Sigmoid transformation curve; m is an output value range control parameter for controlling the output amplitude range of the Sigmoid conversion curve; and c, controlling the detail amplification degree of each layer by using a Sigmoid curve curvature control parameter.
Reconstructing the Laplacian pyramid to obtain a die body detail reduction image Img _ r (x, y) after detail reduction, wherein the reconstruction process is an inverse process of pyramid decomposition
And adjusting the gray scale domain of Img _ r (X, y) to an optimal value range in an LUT mapping mode, and outputting a final result image, namely the phantom X-ray image after scattered rays are filtered.
For the system embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
Referring to fig. 3, a flowchart illustrating steps of an embodiment of the system for filtering scattered rays in an X-ray image according to the present invention is shown, which may specifically include the following modules:
the extraction module 1 is used for extracting the image characteristics of the scattered rays in the original image;
a removing module 2, configured to remove scattered ray image components in the original image according to the scattered ray image features;
the restoring module 3 is used for carrying out detail restoring processing on the original image without the scattered ray image components to obtain a detail restored image;
and the adjusting module 4 is used for adjusting the gray value of the detail reduction image to a standard reaching state to obtain an X-ray image after scattered rays are filtered.
The extraction module 1 is generally configured to extract image features of scattered rays in an original image, where the original image is generally a comprehensive quantum image I reaching a detector, and the comprehensive quantum image I generally includes direct quantum image features I st Scattering quantum image feature I sc And quantum noise image characteristics I n Note that, the image characteristics I are due to quantum noise n Is the non-uniform distribution and energy spectrum dispersion of X-ray photons, and therefore is not considered separately in the embodiments of the present invention but is included in the direct quantum image feature I st And scattered quantum image characteristics I sc Therefore, the image features of the original image (i.e., the integrated quantum image I) described in the embodiments of the present invention only include the direct quantum image feature I st And scattered quantum image characteristics I sc 。
It should be noted that, the above extraction process generally needs to split the original image into a medium region and a non-medium region, and then extract the scattered ray image features in the two regions respectively.
The removing module 2 is generally configured to remove a scattered ray image component in the original image according to the characteristic of the scattered ray image, and in this embodiment, the removing generally includes two methods for removing, including: deleting the pixel matched with the scattered ray image characteristic or adjusting the pixel value of the pixel to be 0 or 255 to obtain an original image with the scattered ray image component removed; and obtaining an original image after the scattered ray image components are removed by adjusting the pixel values of the pixels which are matched with the scattered ray image characteristics to the pixel values which are the same as the pixel values of the nearby area.
The restoring module 3 is generally configured to perform detail restoring processing on the original image from which the scattered ray image components are removed to obtain a detail restored image, where it should be noted that the detail restoring process generally includes three steps, specifically: firstly, carrying out image decomposition processing on the original image from which the scattered ray image components are removed; then, gain amplification processing is carried out on the specified partial image details in the image after the decomposition processing; and finally, carrying out image reconstruction processing on the image subjected to the detail gain amplification processing to obtain the detail restoration image.
The adjusting module 4 is generally configured to adjust the gray value of the detail reduced image to a standard state, and obtain the X-ray image after the scattered rays are filtered, and it should be noted that the adjustment of the gray value of the detail reduced image to the standard state generally includes two aspects of determination: whether the storage requirement of the X-ray image is met or not and whether the display requirement of the X-ray image is met or not, the gray value of the detail restoration image meets the standard transition state only when the storage requirement and the display requirement are met.
Referring to fig. 4, a computer device for implementing the method for filtering scattered rays in an X-ray image according to the present invention is shown, which may specifically include the following:
the computer device 12 described above is embodied in the form of a general purpose computing device, and the components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (commonly referred to as "hard drives"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 by one or more data media interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, with the program modules 42 configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42, and program data, each of which examples or some combination thereof may include an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of embodiments of the invention as described.
The processing unit 16 executes programs stored in the system memory 28 to perform various functional applications and data processing, such as implementing the method for filtering scattered radiation in X-ray images provided by the embodiment of the present invention.
That is, the processing unit 16 implements, when executing the program,: extracting the image characteristics of scattered rays in the original image; removing scattered ray image components in the original image according to the scattered ray image characteristics; performing detail restoration processing on the original image without the scattered ray image components to obtain a detail restoration image; and adjusting the gray value of the detail reduction image to reach the standard state to obtain an X-ray image after the scattered rays are filtered.
In an embodiment of the present invention, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the method for filtering out scattered radiation in an X-ray image as provided in all embodiments of the present application:
that is, the program when executed by the processor implements: extracting the image characteristics of scattered rays in the original image; removing scattered ray image components in the original image according to the scattered ray image characteristics; performing detail restoration processing on the original image without the scattered ray image components to obtain a detail restoration image; and adjusting the gray value of the detail reduction image to reach the standard state to obtain an X-ray image after the scattered rays are filtered.
Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer-readable storage medium or a computer-signal medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPOM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
In any of the embodiments of the present invention, by removing the image component of the scattered radiation and performing detail reduction processing on the original image after removing the image component of the scattered radiation, the interference of the scattered radiation can be removed while the original details in the image are kept to the maximum extent; obtaining a direct-ray image with good contrast by selecting specified extraction parameters k, b and c; the detail recovery effect of the image is good by selecting the designated high-frequency signal gain parameter; the noise reduction processing is completely avoided in the complete image processing process, and the information in the X-ray image is greatly reserved.
The method, system, device and storage medium for filtering out scattered rays in an X-ray image provided by the present application are introduced in detail above, and specific examples are applied herein to explain the principles and embodiments of the present application, and the description of the above embodiments is only used to help understand the method and its core ideas of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (8)
1. A method for filtering scattered radiation from an X-ray image, comprising the steps of:
extracting the image characteristics of scattered rays in the original image; specifically, the original image is decomposed into a medium region and a non-medium region; respectively extracting scattered ray image features in a medium area and a non-medium area; the step of respectively extracting the scattered ray image features in the medium area and the non-medium area comprises the following steps: acquiring the lowest relative intensity of the direct rays in the medium region and the difference parameters of the highest and lowest relative intensities of the direct rays, and obtaining the scattered ray image characteristics in the medium region according to the lowest relative intensity of the direct rays in the medium region and the difference parameters of the highest and lowest relative intensities of the direct rays; acquiring the lowest relative intensity of the direct rays in the non-medium region and obtaining the image characteristics of the scattered rays in the non-medium region according to the lowest relative intensity of the direct rays in the non-medium region;
removing scattered ray image components in the original image according to the scattered ray image characteristics;
performing detail restoration processing on the original image without the scattered ray image components to obtain a detail restoration image;
and adjusting the gray value of the detail reduction image to reach the standard state, and obtaining the X-ray image after the scattered rays are filtered.
2. The method of claim 1, wherein the image component of the scattered radiation in the original image is calculated according to the following set of equations:
I st ＝I-I sc
wherein I represents an original image, I st Indicating direct radiationLine image component, I sc Representing the component of the scattered ray image, Ω m A region of the medium in the image is represented,
representing a non-medium region in the image, k representing a difference parameter of highest and lowest relative intensities of the straight rays in the medium region, b representing a lowest relative intensity of the straight rays in the medium region, and c representing a relative intensity of the straight rays in the non-medium region.
3. The method according to claim 1, wherein the step of performing detail reduction processing on the original image from which the scattered ray image component is removed to obtain a detail reduced image includes:
carrying out image decomposition processing on the original image without the scattered ray image components to obtain image decomposition data;
performing gain amplification processing on image details in the image decomposition data to obtain gained image decomposition data;
and carrying out image reconstruction on the gained image decomposition data to obtain the detail restoration image.
4. The method of claim 1, further comprising, before the step of adjusting the gray-level value of the detail reduction image to reach a standard state and obtaining the X-ray image after filtering out scattered rays:
respectively judging whether the gray value of the detail reduction image respectively meets the storage requirement and the display requirement;
if not, adjusting the gray value of the detail reduction image to reach the standard state, and obtaining the X-ray image after the scattered rays are filtered.
5. The method of claim 1, wherein the step of adjusting the gray level of the detail reduction image to reach a standard state to obtain the X-ray image after the scattered rays are filtered comprises:
and adjusting the gray scale domain of the detail restoration image to reach the standard state through LUT mapping processing.
6. A system for filtering scattered rays in an X-ray image is characterized by comprising the following specific modules:
the extraction module is used for extracting the image characteristics of the scattered rays in the original image;
the removing module is used for removing scattered ray image components in the original image according to the scattered ray image characteristics;
the restoring module is used for carrying out detail restoring processing on the original image without the scattered ray image components to obtain a detail restored image;
and the adjusting module is used for adjusting the gray value of the detail reduction image to reach the standard state and obtaining the X-ray image after the scattered rays are filtered.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any one of claims 1 to 5 when executing the program.
8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910123586.3A CN109949233B (en) | 2019-02-18 | 2019-02-18 | Method, system, device and storage medium for filtering scattered rays in X-ray image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910123586.3A CN109949233B (en) | 2019-02-18 | 2019-02-18 | Method, system, device and storage medium for filtering scattered rays in X-ray image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109949233A CN109949233A (en) | 2019-06-28 |
| CN109949233B true CN109949233B (en) | 2022-12-13 |
Family
ID=67006765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910123586.3A Active CN109949233B (en) | 2019-02-18 | 2019-02-18 | Method, system, device and storage medium for filtering scattered rays in X-ray image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109949233B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111462004B (en) * | 2020-03-30 | 2023-03-21 | 推想医疗科技股份有限公司 | Image enhancement method and device, computer equipment and storage medium |
| CN113134171B (en) * | 2021-04-23 | 2022-12-30 | 上海联影医疗科技股份有限公司 | Positioning method of radiotherapy quality control measuring point and computer equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102793551A (en) * | 2011-05-24 | 2012-11-28 | 柯尼卡美能达医疗印刷器材株式会社 | Chest diagnostic support information generation system |
| CN103079466A (en) * | 2010-08-27 | 2013-05-01 | 柯尼卡美能达医疗印刷器材株式会社 | Thoracic diagnosis assistance system and program |
| CN106033598A (en) * | 2015-03-18 | 2016-10-19 | 北京纳米维景科技有限公司 | Digital filter wire grid imaging method used for eliminating scattered radiation influence |
| CN107811647A (en) * | 2017-11-24 | 2018-03-20 | 上海联影医疗科技有限公司 | CT equipment, the X-ray detection X method with reference to detection device and radiographic source |
Family Cites Families (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5648997A (en) * | 1995-12-29 | 1997-07-15 | Advanced Optical Technologies, Inc. | Apparatus and method for removing scatter from an x-ray image |
| CN100510725C (en) * | 2006-11-14 | 2009-07-08 | 北京国药恒瑞美联信息技术有限公司 | Virtual grid imaging method and system used for eliminating influence of scattered radiation |
| CN100461218C (en) * | 2007-03-29 | 2009-02-11 | 杭州电子科技大学 | Method for enhancing medical image with multi-scale self-adaptive contrast change |
| EP2071513A1 (en) * | 2007-12-10 | 2009-06-17 | Agfa HealthCare NV | Method of generating a multiscale contrast enhanced image |
| WO2010058329A1 (en) * | 2008-11-21 | 2010-05-27 | Philips Intellectual Property & Standards Gmbh | System and method for x-ray scatter correction |
| CN101779962B (en) * | 2010-01-19 | 2014-08-13 | 西安华海医疗信息技术股份有限公司 | Method for enhancing medical X-ray image display effect |
| US8559692B2 (en) * | 2010-06-08 | 2013-10-15 | Zakrytoe akcionernoe obshchestvo “Impul's” | Method for correction of digital images |
| US8989469B2 (en) * | 2010-12-20 | 2015-03-24 | The Board Of Trustees Of The Leland Stanford Junior University | Systems and methods for simultaneous acquisition of scatter and image projection data in computed tomography |
| CN102737395B (en) * | 2011-04-15 | 2017-07-11 | 深圳迈瑞生物医疗电子股份有限公司 | Image processing method and device in a kind of medical X-ray system |
| CN103578082A (en) * | 2012-08-09 | 2014-02-12 | 江苏超惟科技发展有限公司 | Cone beam CT scatter correction method and system |
| CN104299187B (en) * | 2013-07-15 | 2018-08-31 | 上海联影医疗科技有限公司 | The image processing method and device of X-ray shooting system |
| CN104915930B (en) * | 2014-03-14 | 2019-05-28 | 深圳迈瑞生物医疗电子股份有限公司 | The method and device of grey level compensation and noise suppressed is carried out to image |
| JP6145889B2 (en) * | 2014-03-24 | 2017-06-14 | 富士フイルム株式会社 | Radiation image processing apparatus and method, and program |
| CN106570836A (en) * | 2016-11-03 | 2017-04-19 | 北京航星机器制造有限公司 | Radiation image local enhancement method |
| CN106504222B (en) * | 2016-11-21 | 2019-09-06 | 河海大学常州校区 | A kind of underwater Polarization Image Fusion system based on bionic visual mechanism |
| CN108227029A (en) * | 2017-12-26 | 2018-06-29 | 北京无线电计量测试研究所 | A kind of mm-wave imaging compensation method, equipment and readable computer storage medium |
| CN108577872B (en) * | 2017-12-29 | 2021-07-16 | 上海联影医疗科技股份有限公司 | Medical image de-scattering method, system and storage medium |
| CN108447028A (en) * | 2018-02-12 | 2018-08-24 | 中国科学院西安光学精密机械研究所 | Underwater picture quality improving method based on Multiscale Fusion |
| CN109345608B (en) * | 2018-10-22 | 2022-10-28 | 中国人民解放军战略支援部队信息工程大学 | Asymmetric scattering correction plate-based cone beam CT image reconstruction method |
-
2019
- 2019-02-18 CN CN201910123586.3A patent/CN109949233B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103079466A (en) * | 2010-08-27 | 2013-05-01 | 柯尼卡美能达医疗印刷器材株式会社 | Thoracic diagnosis assistance system and program |
| CN102793551A (en) * | 2011-05-24 | 2012-11-28 | 柯尼卡美能达医疗印刷器材株式会社 | Chest diagnostic support information generation system |
| CN106033598A (en) * | 2015-03-18 | 2016-10-19 | 北京纳米维景科技有限公司 | Digital filter wire grid imaging method used for eliminating scattered radiation influence |
| CN107811647A (en) * | 2017-11-24 | 2018-03-20 | 上海联影医疗科技有限公司 | CT equipment, the X-ray detection X method with reference to detection device and radiographic source |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109949233A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107481297B (en) | CT image reconstruction method based on convolutional neural network | |
| US8542944B2 (en) | Method and apparatus for multi-scale based dynamic range compression and noise suppression | |
| Ibrahim et al. | A medical image enhancement based on generalized class of fractional partial differential equations | |
| JP2013127773A (en) | Noise reduction method in digital x ray frame series | |
| JP2011028588A (en) | Information processing apparatus, line noise reduction processing method, and program | |
| CN107133933B (en) | Mammary X-ray image enhancement method based on convolutional neural network | |
| WO2013125984A2 (en) | Method for suppressing noise in digital x-rays | |
| JP2001057677A (en) | Image processing method, system and recording medium | |
| EP2191438A1 (en) | Method of generating a multiscale contrast enhanced image | |
| CN115409733A (en) | Low-dose CT image noise reduction method based on image enhancement and diffusion model | |
| CN109949233B (en) | Method, system, device and storage medium for filtering scattered rays in X-ray image | |
| Shu et al. | Alternating minimization algorithm for hybrid regularized variational image dehazing | |
| CN111882503A (en) | Image noise reduction method and application thereof | |
| Liu et al. | Enhancement of low illumination images based on an optimal hyperbolic tangent profile | |
| US20120087565A1 (en) | Method and apparatus for enhancing representations of micro-calcifications in a digital mammogram image | |
| Borah et al. | A GPU-accelerated modified unsharp-masking method for high-frequency background-noise suppression | |
| CN112819739B (en) | Image processing method and system for scanning electron microscope | |
| CN107274372B (en) | Pyramid local contrast-based dynamic image enhancement method and device | |
| CN102890817A (en) | Method and system for processing medical images | |
| Gabralla et al. | Denoising CT Images using wavelet transform | |
| CN110246090B (en) | Image processing method and device | |
| Rao et al. | An effective CT medical image enhancement system based on DT-CWT and adaptable morphology | |
| CN111462004B (en) | Image enhancement method and device, computer equipment and storage medium | |
| Shabana Sulthana et al. | Kinetic gas molecule optimization (KGMO)-based speckle noise reduction in ultrasound images | |
| WO2021039211A1 (en) | Machine learning device, machine learning method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: No.103, baguang District Service Center, No.2 BaiShaWan Road, baguang community, Kuiyong street, Dapeng New District, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Lanying Medical Technology Co.,Ltd. Address before: 518000 Shenzhen, Baoan District, Guangdong Shiyan street, Lang Xin neighborhood committee, brick factory village, Liyuan Industrial Zone, hung lung hi tech Industrial Park (blue Yun Industrial Park), 1 1 buildings. Applicant before: SHENZHEN LANYUN MEDICAL IMAGE CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |