A CT image reconstruction method and system
Through the segmentation and processing technology of CT projected images, the boundary lines are extracted for contrast enhancement and smoothing processing, combined with forward projection and reconstruction, the problem of aliasing artifacts in CT scan is solved, and the resolution is achieved without losing The effect of removing artifacts.
Patent Information
- Application Number
- CN202210681013.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-15
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2042-06-15
AI Technical Summary
During the CT scan, aliasing artifacts caused by undersampling in the Z direction are difficult to effectively remove, and existing hardware improvement costs are high and software processing will lose Z direction resolution.
By acquiring CT projected images for pre-processing, segmenting into air areas, soft tissue areas and bone areas, junction lines are extracted and contrast enhancement and smoothing are performed, combining forward projection and reconstruction techniques, artifact images are calculated and removed from the original image Artifact.
While not losing Z-directional resolution, it effectively reduces aliasing artifacts, which are suitable for any CT model, avoiding technical transformation costs and no increase in energy consumption.
Smart Images

Figure CN114943742B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical image processing, and in particular to a CT image reconstruction method and system. Background Art
[0002] When using a CT machine for CT scanning, if the width of each row of detectors is too large, or the conditions used during scanning are affected, undersampling in the Z direction will occur, and aliasing artifacts will be generated at the edges of the scanned object that change significantly in the Z direction, which appear as radial black and white artifacts centered on the sharp structural edges.
[0003] In order to remove the aliasing artifacts in the Z direction, it can generally be solved from the hardware and software aspects. In terms of hardware, aliasing artifacts can be improved by Z-direction flying focus technology. This technology increases the sampling rate by alternately switching the position of the focus in the Z direction. However, for tubes that do not support this technology, aliasing artifacts cannot be solved, the applicability is poor, and it will increase costs and increase tube losses. In terms of software processing, it is generally through Z-direction low-pass filtering, or low-pass filtering combined with other technologies to maintain the edges and noise of the image, but these technologies will cause a certain loss of Z-direction resolution.
[0004] Therefore, a new CT image reconstruction method and system are needed to effectively remove aliasing artifacts from images. Summary of the invention
[0005] In order to overcome the above technical defects, the object of the present invention is to provide a CT image reconstruction method and system, which can significantly reduce the manifestation of aliasing artifacts in the image without losing the Z-direction resolution.
[0006] The present invention discloses a CT image reconstruction method, comprising the following steps:
[0007] Acquire CT projection images and preprocess the CT projection images to form an original image Img ori ;
[0008] The original image Img ori Segmenting the image into an air region image, a soft tissue region image and a bone region image, and extracting a boundary line between any two images among the air region image, the soft tissue region image and the bone region image;
[0009] The contrast enhancement process is performed on the area where the boundary line is located in the air area image, the soft tissue area image and the bone area image, and the area without the boundary line in the air area image, the soft tissue area image and the bone area image is smoothed to form a processed image Img sharp ;
[0010] For the original image Imgori Smoothing is performed to form a smooth image Img smooth ;
[0011] Processing image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp , and based on the projection image Img fbp and smoothed image Img smooth Get the artifact image Img art ;
[0012] Based on the artifact image Img art and the original image Img ori , get the reconstructed image Img corr .
[0013] Preferably, a CT projection image is acquired and preprocessed to form an original image Img. ori The steps include:
[0014] Acquire CT projection images, and re-arrange and filter back-project the CT projection images to form an original image Img ori ;
[0015] The original image Img ori The steps of segmenting the image into an air region image, a soft tissue region image and a bone region image, and extracting a boundary line between any two images among the air region image, the soft tissue region image and the bone region image include:
[0016] According to the original image Img ori Including the air part, soft tissue part and bone part, the original image Img ori Segmentation into air region image, soft tissue region image and bone region image;
[0017] The edges of any two images among the air region image, the soft tissue region image and the bone region image are extracted as the boundary line and stored as the boundary line region image.
[0018] Preferably, the contrast enhancement process is performed on the region where the boundary line is located in the air region image, the soft tissue region image and the bone region image, and the region without the boundary line in the air region image, the soft tissue region image and the bone region image is smoothed to form a processed image Img. sharp The steps include:
[0019] Based on the following Sigmoid function, the contrast of the boundary area image is enhanced:
[0020] Where L = 1, k = 1, x0 = 0
[0021] And the contrast of the edge pixels of the boundary line area image remains unchanged, so that the contrast of the edge pixels of the boundary line image is continuous with the contrast of the pixels adjacent to the edge pixels and located in the area without the boundary line.
[0022] Preferably, the processed image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp , and based on the projection image Img fbp and smoothed image Img smooth Get the artifact image Img art The steps include:
[0023] Processing image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp ;
[0024] The artifact image Img is calculated based on the following formula art :
[0025] Img art =Img smooth -Img fbp ;
[0026] The projected object is completely located in the processed image Img sharp in the display area.
[0027] Preferably, based on the artifact image Img art and the original image Img ori , get the reconstructed image Img corr The steps include:
[0028] The reconstructed image Img is calculated based on the following formula corr :
[0029] Img corr =Img ori -Img art ,
[0030] Repeat the above steps until the image Img is reconstructed. corr Artifacts are not included.
[0031] The present invention also discloses a CT image reconstruction system, comprising:
[0032] The preprocessing module obtains the CT projection image and preprocesses the CT projection image to form an original image Img ori ;
[0033] The segmentation module transforms the original image Img oriSegmenting the image into an air region image, a soft tissue region image and a bone region image, and extracting a boundary line between any two images among the air region image, the soft tissue region image and the bone region image;
[0034] The processing module performs contrast enhancement processing on the area where the boundary line is located in the air area image, the soft tissue area image and the bone area image, and performs smoothing processing on the area without the boundary line in the air area image, the soft tissue area image and the bone area image to form a processed image Img sharp ;
[0035] The processing module processes the original image Img ori Smoothing is performed to form a smooth image Img smooth ;
[0036] The processing module processes the image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp , and based on the projection image Img fbp and smoothed image Img smooth Get the artifact image Img arg ;
[0037] The processing module is based on the artifact image Img art and the original image Img ori , get the reconstructed image Img corr .
[0038] Preferably, the preprocessing module acquires the CT projection image, and reorders and reconstructs the CT projection image by filtering back projection to form an original image Img ori ;
[0039] The segmentation module is based on the original image Img ori Including the air part, soft tissue part and bone part, the original image Img ori Segmentation into air region image, soft tissue region image and bone region image;
[0040] The segmentation module extracts the edges of any two images among the air region image, the soft tissue region image and the bone region image as the boundary line, and stores the edges as the boundary line region image.
[0041] Preferably, the processing module performs contrast enhancement processing on the boundary area image based on the following Sigmoid function:
[0042] Where L = 1, k = 1, x0 = 0
[0043] And the contrast of the edge pixels of the boundary line area image remains unchanged, so that the contrast of the edge pixels of the boundary line image is continuous with the contrast of the pixels adjacent to the edge pixels and located in the area without the boundary line.
[0044] Preferably, the processing module processes the image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp ;
[0045] The processing module calculates the artifact image Img based on the following formula art :
[0046] Img art =Img smooth -Img fbp ;
[0047] The projected object is completely located in the processed image Img sharp in the display area.
[0048] Preferably, the processing module calculates the reconstructed image Img based on the following formula: corr :
[0049] Img corr =Img ori -Img art ,
[0050] Repeat the above steps until the image Img is reconstructed. corr Artifacts are not included.
[0051] Compared with the prior art, the above technical solution has the following beneficial effects:
[0052] 1. It can be applied to any type or model of CT machine, eliminating the cost of technical transformation;
[0053] 2. No loss of Z-axis resolution, no increase in energy consumption, and strong effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] Figure 1 A schematic diagram of a flow chart of a CT image reconstruction method in accordance with a preferred embodiment of the present invention;
[0055] Figure 2a A schematic diagram of an original image with aliasing artifacts in accordance with a preferred embodiment of the present invention;
[0056] Figure 2b A schematic diagram of a reconstructed image for removing aliasing artifacts in accordance with a preferred embodiment of the present invention;
[0057] Figure 3This is a schematic diagram of a Sigmoid function in a preferred embodiment of the present invention. DETAILED DESCRIPTION
[0058] The advantages of the present invention are further described below in conjunction with the accompanying drawings and specific embodiments.
[0059] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0060] The terms used in this disclosure are for the purpose of describing specific embodiments only and are not intended to limit the disclosure. The singular forms of "a", "said" and "the" used in this disclosure and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0061] It should be understood that although the terms first, second, third, etc. may be used in the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0062] In the description of the present invention, it is necessary to understand that the terms "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.
[0063] In the description of the present invention, unless otherwise specified and limited, it should be noted that the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection, or it can be the internal connection between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.
[0064] In the following description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present invention, and have no specific meanings. Therefore, "module" and "component" can be used interchangeably.
[0065] See also Figure 1 , is a flow chart of a CT image reconstruction method in accordance with a preferred embodiment of the present invention. In this embodiment, to remove aliasing artifacts, the CT image reconstruction method includes the following steps:
[0066] S100: Acquire a CT projection image and pre-process the CT projection image to form an original image Img ori ;
[0067] After the CT image is acquired, it can be projected (projected in the forward direction or slightly offset) to obtain a CT projection image on a certain section, and the original image Img can be obtained after preprocessing the CT projection image. ori , the original image Img ori Includes parts with aliasing artifacts.
[0068] S200: The original image Img ori Segmenting the image into an air region image, a soft tissue region image and a bone region image, and extracting a boundary line between any two images among the air region image, the soft tissue region image and the bone region image;
[0069] According to the regional segmentation including different contents (any known segmentation algorithm can be used, such as feature extraction, etc.), an air region image, a soft tissue region image and a bone region image are formed, that is, the air region image only includes the background part, the soft tissue region image only includes the soft tissue part, and the bone region image only includes the bone part. It can be understood that since the same type of parts may be scattered in the original image Img ori If the segmented regions are different, the segmented small regions can be still arranged in a scattered manner (without splicing) to highlight that the segmented regions correspond to the original image Img ori location.
[0070] S300: performing contrast enhancement processing on the area where the boundary line is located in the air area image, the soft tissue area image and the bone area image, and performing smoothing processing on the area without the boundary line in the air area image, the soft tissue area image and the bone area image, so as to form a processed image Img sharp ;
[0071] The cause of aliasing artifacts is the stripe radiation caused by undersampling of tissue structures with drastic changes in the Z direction. Therefore, the intersection of the air area image, soft tissue area image and bone area image is used as the segmentation standard, and the boundary line of the intersection is contrast enhanced to restore its sharpness in the Z direction. Then, the aliasing artifacts are regenerated through forward projection and reconstruction, and then removed from the original image.
[0072] S400: processing the original image Img ori Smoothing is performed to form a smooth image Img smooth ;
[0073] Smoothing is the process of smoothing the original image Img ori Remove the image noise so that the original image Img ori The inner similar areas are made more similar, weakening the characteristics of the basically indistinguishable parts.
[0074] S500: processing the image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp , and based on the projection image Img fbp and smoothed image Img smooth Get the artifact image Img art ;
[0075] Since the image Img is processed sharp The boundaries of different structures are enhanced, that is, their sharpness in the Z direction is restored. After forward projection and reconstruction, the generated image contains aliasing artifacts generated by the structure with restored sharpness. The smoothed image Img smooth It can be considered as an image without aliasing artifacts or with weak aliasing artifacts, and the artifact image Img can be obtained. art .
[0076] S600: Based on the artifact image Img art and the original image Img ori , get the reconstructed image Img corr .
[0077] Finally, the artifact image Img art From the original image Img ori The reconstructed image Img is obtained by removing corr There are no more aliasing artifacts (if there are still some, the above operation can be repeated until they are completely removed).
[0078] See also Figure 2a and Figure 2b According to the configuration of the above CT image reconstruction method, the aliasing artifacts in the CT image have been corrected ( Figure 2aThe windmill artifacts in 2b have been removed without significant change in image resolution).
[0079] In a preferred embodiment, step S100 includes:
[0080] S110: Acquire a CT projection image, and re-arrange and filter back-project the CT projection image to form an original image Img ori ;
[0081] Step S200 includes:
[0082] S210: Based on the original image Img ori Including the air part, soft tissue part and bone part, the original image Img ori Segmentation into air region image, soft tissue region image and bone region image;
[0083] S220: extracting the edge of any two images among the air region image, the soft tissue region image and the bone region image as a boundary line, and storing the edge as a boundary region image.
[0084] It is understandable that the boundary line may be extracted with a wider standard or a narrower standard due to the pixel resolution, and this may be determined based on the degree of aliasing artifacts visible to the naked eye.
[0085] Further, step S300 includes:
[0086] S310: Based on the following Sigmoid function, contrast enhancement processing is performed on the boundary area image:
[0087] Where L = 1, k = 1, x0 = 0
[0088] See also Figure 3 , Sigmoid function is also called Logistic function, which is used for hidden layer neuron output, with a value range of (0,1). It can map a real number to the interval of (0,1) and can be used for binary classification. It works better when the feature difference is complex or the difference is not particularly large. And during contrast enhancement processing, the contrast of the edge pixels of the image in the boundary area remains unchanged, so that the contrast of the edge pixels of the boundary image is continuous with the contrast of the pixels adjacent to the edge pixels and located in the area without the boundary, so as to avoid creating a new boundary and generating an image that does not conform to the original image Img. ori Artifacts in .
[0089] In a preferred embodiment, step S500 includes:
[0090] S510: Processing the image Img sharpPerform forward projection and reconstruction to obtain the projection image Img fbp ;
[0091] The projected image Img fbp Inside is the regenerated image with aliasing artifacts.
[0092] S520: Calculate the artifact image Img based on the following formula art :
[0093] Img art =Img smooth -Img fbp ;
[0094] The processed image Img sharp During forward projection, the effective layer thickness and layer interval are appropriate, and in order to ensure that the generated aliasing artifacts match the artifact performance on the original image, it is necessary to ensure that the projected object is completely within the current display area. If not, it is necessary to use an image with a larger display area to perform the above forward projection and reconstruction operations.
[0095] In the smoothed image Img smooth The extraction within can completely remove the artifact image Img art From the smoothed image Img smooth The images are screened out without any mis-extraction (the non-boundary areas are smoothed and will not affect the generation of artifacts).
[0096] Finally, step S600 includes:
[0097] S610: Calculate the reconstructed image Img based on the following formula corr :
[0098] Img corr =Img ori -Img art ,
[0099] Finally, the original image Img ori The artifact image Img art By removing it, a corrected image without aliasing artifacts can be obtained.
[0100] S620: Repeat the above steps until the image Img is reconstructed. corr Artifacts are not included.
[0101] The present invention also discloses a CT image reconstruction system, comprising: a preprocessing module, which obtains a CT projection image and preprocesses the CT projection image to form an original image Img ori ; Segmentation module, the original image Img oriThe image is segmented into an air region image, a soft tissue region image and a bone region image, and a boundary line between any two images among the air region image, the soft tissue region image and the bone region image is extracted; a processing module performs contrast enhancement processing on the region where the boundary line is located in the air region image, the soft tissue region image and the bone region image, and performs smoothing processing on the region without the boundary line in the air region image, the soft tissue region image and the bone region image, so as to form a processed image Img sharp ; The processing module processes the original image Img ori Smoothing is performed to form a smooth image Img smooth ; The processing module processes the image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp , and based on the projection image Img fbp and smoothed image Img smooth Get the artifact image Img art ; The processing module is based on the artifact image Img art and the original image Img ori , get the corrected reconstructed image Img corr .
[0102] Preferably, the preprocessing module acquires the CT projection image, and reorders and reconstructs the CT projection image by filtering back projection to form an original image Img ori ; The segmentation module is based on the original image Img ori Including the air part, soft tissue part and bone part, the original image Img ori The image is segmented into an air region image, a soft tissue region image and a bone region image; the segmentation module extracts the edges of any two images among the air region image, the soft tissue region image and the bone region image as the boundary line, and stores them as the boundary line region image.
[0103] Preferably, the processing module performs contrast enhancement processing on the boundary area image based on the following Sigmoid function:
[0104] Where L = 1, k = 1, x0 = 0
[0105] And the contrast of the edge pixels of the boundary line area image remains unchanged, so that the contrast of the edge pixels of the boundary line image is continuous with the contrast of the pixels adjacent to the edge pixels and located in the area without the boundary line.
[0106] Preferably, the processing module processes the image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp ; The processing module calculates the artifact image Img based on the following formula art :Imgart =Img smooth -Img fbp ; The projected object is completely located in the processed image Img sharp in the display area.
[0107] Preferably, the processing module calculates the reconstructed image Img based on the following formula: corr :Img corr =Img ori -Img art , repeatedly iterate the above steps until the image Img is reconstructed corr The artifact image Img is not included art .
[0108] It should be noted that the embodiments of the present invention have better practicability and do not impose any form of limitation on the present invention. Any technician familiar with the field may use the technical content disclosed above to change or modify it into an equivalent effective embodiment. However, any modification or equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.
Claims
1. A CT image reconstruction method, characterized in that: The following steps are involved: Acquire a CT projection image and preprocess the CT projection image to form an original image Img ori ; The original image Img ori Segmenting the image into an air region image, a soft tissue region image and a bone region image, and extracting a boundary line between any two images among the air region image, the soft tissue region image and the bone region image; The contrast enhancement process is performed on the area where the boundary line is located in the air area image, the soft tissue area image and the bone area image, and the area without the boundary line in the air area image, the soft tissue area image and the bone area image is smoothed to form a processed image Img sharp ; For the original image Img ori Smoothing is performed to form a smooth image Img smooth ; The processed image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp , and based on the projection image Img fbp and smoothed image Img smooth Get the artifact image Img art ; Based on the artifact image Img art and the original image Img ori , get the reconstructed image Img corr .
2. The CT image reconstruction method according to claim 1, characterized in that: Acquire a CT projection image and preprocess the CT projection image to form an original image Img ori The steps include: Acquire a CT projection image, and re-arrange and filter back-project the CT projection image to form an original image Img ori ; The original image Img ori The steps of segmenting the image into an air region image, a soft tissue region image and a bone region image, and extracting a boundary line between any two images among the air region image, the soft tissue region image and the bone region image include: According to the original image Img ori Including the air part, soft tissue part and bone part, the original image Img ori Segmentation into air region image, soft tissue region image and bone region image; The edges of any two images among the air region image, the soft tissue region image and the bone region image are extracted as the boundary line and stored as the boundary line region image.
3. The CT image reconstruction method according to claim 2, characterized in that: The contrast enhancement process is performed on the area where the boundary line is located in the air area image, the soft tissue area image and the bone area image, and the area without the boundary line in the air area image, the soft tissue area image and the bone area image is smoothed to form a processed image Img sharp The steps include: Based on the following Sigmoid function, the image in the boundary area is subjected to contrast enhancement processing: Where L = 1, k = 1, x0 = 0 And the contrast of the edge pixels of the boundary line area image remains unchanged, so that the contrast of the edge pixels of the boundary line image is continuous with the contrast of the pixels adjacent to the edge pixels and located in the area without the boundary line.
4. The CT image reconstruction method according to claim 1, characterized in that: The processed image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp , and based on the projection image Img fbp and smoothed image Img smooth Get the artifact image Img art The steps include: The processed image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp ; The artifact image Img is calculated based on the following formula art : Img art =Img smooth -Img fbp ; The projected object is completely located in the processed image Img sharp in the display area.
5. The CT image reconstruction method according to claim 4, characterized in that: Based on the artifact image Img art and the original image Img ori , get the reconstructed image Img corr The steps include: The reconstructed image Img is calculated based on the following formula corr : Img corr =Img ori -Img art , Repeat the above steps until the image Img is reconstructed. corr Artifacts are not included.
6. A CT image reconstruction system, characterized in that: include: The preprocessing module obtains the CT projection image and preprocesses the CT projection image to form an original image Img ori ; The segmentation module transforms the original image Img ori Segmenting the image into an air region image, a soft tissue region image and a bone region image, and extracting a boundary line between any two images among the air region image, the soft tissue region image and the bone region image; The processing module performs contrast enhancement processing on the area where the boundary line is located in the air area image, the soft tissue area image and the bone area image, and performs smoothing processing on the area without the boundary line in the air area image, the soft tissue area image and the bone area image to form a processed image Img sharp ; The processing module processes the original image Img ori Smoothing is performed to form a smooth image Img smooth ; The processing module processes the image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp , and based on the projection image Img fbp and smoothed image Img smooth Get the artifact image Img art ; The processing module is based on the artifact image Img art and the original image Img ori , get the reconstructed image Img corr .
7. The CT image reconstruction system according to claim 6, characterized in that: The preprocessing module obtains the CT projection image, and reorders and filters the CT projection image to reconstruct the image to form an original image Img. ori ; The segmentation module is based on the original image Img ori Including the air part, soft tissue part and bone part, the original image Img ori Segmentation into air region image, soft tissue region image and bone region image; The segmentation module extracts the edges of any two images among the air region image, the soft tissue region image and the bone region image as the boundary line, and stores the edges as the boundary line region image.
8. The CT image reconstruction system according to claim 7, characterized in that: The processing module performs contrast enhancement processing on the boundary area image based on the following Sigmoid function: Where L = 1, k = 1, x0 = 0 And the contrast of the edge pixels of the boundary line area image remains unchanged, so that the contrast of the edge pixels of the boundary line image is continuous with the contrast of the pixels adjacent to the edge pixels and located in the area without the boundary line.
9. The CT image reconstruction system according to claim 6, characterized in that: The processing module processes the image Img sharp Perform forward projection and reconstruction to obtain the projection image Img fbp ; The processing module calculates the artifact image Img based on the following formula art : Img art =Img smooth -Img fbp ; The projected object is completely located in the processed image Img sharp in the display area.
10. The CT image reconstruction system according to claim 9, characterized in that: The processing module calculates the reconstructed image Img based on the following formula corr : Img corr =Img ori -Img art , Repeat the above steps until the image Img is reconstructed. corr Artifacts are not included.
