A method, system and x-ray image reconstruction method for correction of metal artifacts

Abstract

The embodiment of the present specification provides a metal artifact correction method, a system and an X-ray image reconstruction method. The metal artifact correction method comprises: acquiring a to-be-processed image containing a metal artifact; using a data repair method to repair data of a metal track part in the to-be-processed image to obtain repaired projection data; performing low-pass filtering on the repaired projection data to obtain filtered repaired projection data; and based on the filtered repaired projection data, obtaining a repaired image through back projection reconstruction.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of medical technology, and in particular to a metal artifact correction method, a system and an X-ray image reconstruction method. BACKGROUND

[0002] Since metal is highly attenuated to rays (for example, X-rays), that is, a large proportion of rays are absorbed by the metal, the detector receives very few rays when performing ray imaging. Therefore, in the clinical application of ray imaging, the metal implants (such as metal dentures, bone nails, etc.) carried in the patient's body will absorb rays, resulting in that data at the metal is not collected, which brings serious strip artifacts, also known as metal artifacts, to the reconstructed image, and greatly affects the diagnostic accuracy.

[0003] Therefore, it is desirable to provide a metal artifact correction method in a medical image, which can effectively remove the metal artifact in the medical image and improve the diagnostic accuracy. SUMMARY

[0004] One aspect of the present specification provides a metal artifact correction method in a medical image. The method comprises: acquiring a to-be-processed image containing a metal artifact; using a data repair method to perform data repair on a metal track part in the to-be-processed image to obtain repaired projection data; performing low-pass filtering on the repaired projection data to obtain filtered repaired projection data; and obtaining a repaired image through back projection reconstruction based on the filtered repaired projection data.

[0005] In some embodiments, the low-pass filtering of the repaired projection data to obtain the filtered repaired projection data comprises: dividing the repaired projection data into a first data part and a second data part, the first data part being original data that has not undergone the data repair, and the second data part being repaired data that has undergone the data repair; and performing low-pass filtering on the repaired data corresponding to the metal track part to obtain the filtered repaired projection data.

[0006] In some embodiments, the data repair method is used to perform data repair on the metal track part in the to-be-processed image to obtain the repaired projection data, which comprises: determining a metal image based on the to-be-processed image; determining a metal track sinogram based on the metal image, the metal track sinogram reflecting the position of the metal track in the to-be-processed image; and using a data repair method to perform data repair based on the metal track sinogram to obtain the repaired projection data.

[0007] Another aspect of the present disclosure provides a system for correcting metal artifacts in a medical image. The system includes: an acquisition module configured to acquire a to-be-processed image containing metal artifacts; a data repairing module configured to perform data repairing on a metal track portion in the to-be-processed image using a data repairing method to obtain repaired projection data; a filtering module configured to perform low-pass filtering on the repaired projection data to obtain filtered repaired projection data; and an image generation module configured to perform back-projection reconstruction based on the filtered repaired projection data to obtain a repaired image.

[0008] In some embodiments, the filtering module is configured to: divide the repaired projection data into a first data portion and a second data portion, the first data portion being original data that has not been repaired, and the second data portion being repaired data that has been repaired; and perform low-pass filtering on the repaired data corresponding to the metal track portion to obtain the filtered repaired projection data.

[0009] Another aspect of the present disclosure provides a device for correcting metal artifacts, including: at least one storage medium storing computer instructions; and at least one processor executing the computer instructions to implement the method for correcting metal artifacts as described above.

[0010] Another aspect of the present disclosure provides a computer-readable storage medium storing computer instructions, when a computer reads the computer instructions in the storage medium, the computer executes the method for correcting metal artifacts as described above.

[0011] Another aspect of the present disclosure provides a method for reconstructing an X-ray image, executed by at least one processor in communication with a storage device storing executable instructions that, when executed, instruct the at least one processor to perform the method. The method includes: acquiring an X-ray image containing metal artifacts; performing data repairing on a metal track portion in the X-ray image using a data repairing method to obtain repaired projection data; performing low-pass filtering on the repaired projection data to obtain filtered repaired projection data; and performing image reconstruction based on the filtered repaired projection data to obtain a repaired image.

[0012] In some embodiments, the performing low-pass filtering on the repaired projection data to obtain filtered repaired projection data includes: dividing the repaired projection data into a first data portion and a second data portion, the first data portion being original data that has not been repaired, and the second data portion being repaired data that has been repaired; and performing low-pass filtering on the repaired data corresponding to the metal track portion to obtain the filtered repaired projection data.

[0013] In some embodiments, the method for repairing data based on the X-ray image, the metal track part in the X-ray image is repaired to obtain the repaired projection data, comprising: determining a metal image based on the X-ray image; determining a metal track sinogram based on the metal image; repairing data based on the metal track sinogram to obtain the repaired projection data.

[0014] The method and / or system provided in the embodiments of the present specification can eliminate metal artifacts while filtering out high-frequency data generated in the data repair process through low-pass filtering of the repaired projection data, thereby avoiding the generation of high-frequency artifacts when obtaining a reconstructed image based on the repaired projection data, and improving the image quality of the reconstructed image. BRIEF DESCRIPTION OF DRAWINGS

[0015] The present specification will be further illustrated in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, the same reference numbers represent the same structures, wherein:

[0016] Figure 1 is an application scenario diagram of an exemplary metal artifact correction system according to some embodiments of the present specification;

[0017] Figure 2 is a module diagram of an exemplary metal artifact correction system according to some embodiments of the present specification;

[0018] Figure 3 is a flow diagram of an exemplary metal artifact correction method according to some embodiments of the present specification;

[0019] Figure 4 is a flow diagram of an exemplary filtering of repaired data according to some embodiments of the present specification;

[0020] Figure 5 is a flow diagram of an exemplary data repair according to some embodiments of the present specification;

[0021] Figure 6 is a diagram of an exemplary image containing metal artifacts according to some embodiments of the present specification;

[0022] Figure 7 is a diagram of an exemplary data repair according to some embodiments of the present specification;

[0023] Figure 8 is a diagram of an exemplary image before and after correction according to some embodiments of the present specification. DETAILED DESCRIPTION

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some examples or embodiments of the present specification, and for those skilled in the art, the present specification can also be applied to other similar scenarios without creative labor on the basis of these drawings. Unless it is obvious from the language environment or otherwise stated, the same reference numbers in the drawings represent the same structures or operations.

[0025] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0026] Generally, the term "module", "unit" or "block" used herein refers to logic embodied in hardware or firmware, or a collection of software instructions. The modules, units or blocks described herein can be implemented as software and / or hardware and can be stored in any type of non-transitory computer-readable medium or another storage device. In some embodiments, the software modules / units / blocks can be compiled and linked into executable programs. It should be understood that the software modules can be invoked from other modules / units / blocks or from themselves, and / or can be invoked in response to detected events or interrupts. The software modules / units / blocks configured to execute on a computing device can be provided on a computer-readable medium (e.g., an optical disc, a digital video disc, a flash drive, a magnetic disc or any other tangible medium) or as a digital download (which can initially be stored in a compressed or installable format, requiring installation, decompression or decryption before execution). The software code here can be partially or entirely stored in the storage device of the computing device performing the operation and applied in the operation of the computing device. The software instructions can be embedded in firmware, such as EPROM. It should also be understood that the hardware modules / units / blocks can include connected logic components, such as gates and flip-flops, and / or can include programmable units, such as programmable gate arrays or processors. The modules / units / blocks or computing device functions described herein can be implemented as software modules / units / blocks, but can be represented in hardware or firmware. Generally, the modules / units / blocks described herein refer to logical modules / units / blocks, which can be combined with other modules / units / blocks or divided into sub-modules / sub-units / sub-blocks, although they are physically organized or stored devices. The description can be applied to the system, engine or part thereof.

[0027] It will be understood that, when a unit, engine, module, or block is referred to as being "on", "connected to", or "coupled to" another unit, engine, module, or block, that it can be directly on, connected to, or coupled to the other unit, engine, module, or block, or intervening units, engines, modules, or blocks can be present. In this specification, the term "and / or" includes any one or more of the associated listed items, and the terms "comprises", "comprising", "includes", "including", or the like are inclusive when used in this specification, and do not exclude additional, unrecited elements or method steps. In this specification, the term "image" can refer to a 2D image, a 3D image, or a 4D image.

[0028] These and other features, characteristics, and advantages of the present specification can become more apparent with reference to the following detailed description and accompanying drawings, in which:

[0029] As used in this specification and claims, the words "can", "canning", "may", and "possibly" are not intended to convey any exclusivity of possibility, unless the context clearly dictates otherwise. Generally, the terms "comprise", "comprising", "include", "including" and the like are not used inconsistently, and are intended to permit, with some exceptions, for items, components, elements, or steps not expressly listed or inherent to the process or device.

[0030] Flow diagrams are used in this specification to illustrate the operation of systems in accordance with embodiments of the present specification, and associated descriptions are presented to assist in the appreciation of the magnetic resonance imaging method and / or system. It will be understood that the operations as set forth in the figures or otherwise in this specification are not necessarily to be executed in the order shown or in sequential order. Instead, various operations can be handled in parallel or be handled with documents in reverse order, depending on the circumstances. Also, other operations can be added or removed as appropriate.

[0031] Figure 1 is a schematic diagram of an application scenario of an exemplary metal artifact correction system according to some embodiments of the present specification.

[0032] As Figure 1As shown, in some embodiments, the metal artifact correction system 100 can include an imaging device 110, a processing device 120, a terminal device 130, a storage device 140, and a network 150. In some embodiments, various components in the metal artifact correction system 100 can be connected to each other through the network 150 or directly connected without the network 150. For example, the imaging device 110 and the terminal device 130 can be connected through the network 150. For another example, the imaging device 110 and the processing device 120 can be connected through the network 150 or directly connected. For yet another example, the imaging device 110 and the terminal device 130 can be connected through the network 150 or directly connected.

[0033] The imaging device 110 can be configured to scan a target object or a portion thereof located in a detection region thereof and generate an image (e.g., a to-be-processed image) related to the target object or the portion thereof. In some embodiments, the target object can be biological or non-biological. For example, the target object can include a patient, a man-made object, etc. In some embodiments, the target object can include a specific part of a body, such as a head, a chest, an abdomen, etc. or any combination thereof. In some embodiments, the target object can include a specific organ, such as a heart, an esophagus, a trachea, a bronchus, a stomach, a gallbladder, a small intestine, a colon, a bladder, a ureter, a uterus, a fallopian tube, etc. or any combination thereof. In some embodiments, the target object can include a region of interest (ROI), such as a tumor, a nodule, etc.

[0034] In some embodiments, the imaging device 110 can be or include an X-ray imaging device. For example, the X-ray imaging device can include a DSA (digital subtraction angiography), a digital radiography (DR), a computed radiography (CR), a digital fluorography (DF), a CT scanner, a magnetic resonance scanner, a mammography machine, a C-arm device, etc.

[0035] The processing device 120 can process data and / or information obtained from the imaging device 110, the terminal device 130, and / or the storage device 140. For example, the processing device 120 can perform data inpainting, low-pass filtering, reconstruction, etc. on a metal artifact containing image obtained by the imaging device 110 to obtain an inpainted image with high-frequency metal artifacts filtered out. In some embodiments, the processing device 120 can be a single server or a group of servers. The group of servers can be centralized or distributed. In some embodiments, the processing device 120 can be local or remote. For example, the processing device 120 can access information and / or data from the imaging device 110, the terminal device 130, and / or the storage device 140 through the network 150. For another example, the processing device 120 can be directly connected to the imaging device 110, the terminal device 130, and / or the storage device 140 to access information and / or data. In some embodiments, the processing device 120 can be implemented on a cloud platform. For example, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, etc. or any combination thereof.

[0036] The terminal device 130 can include a mobile device 131, a tablet 132, a notebook computer 133, etc. or any combination thereof. In some embodiments, the terminal device 130 can interact with other components in the metal artifact correction system 100 through the network 150. For example, the terminal device 130 can send one or more control instructions to the imaging device 110 through the network 150 to control the imaging device 110 to scan a target object according to the instructions. For another example, the terminal device 130 can also receive the inpainted image with high-frequency metal artifacts filtered out generated by the processing device 120 through the network 150 and display the inpainted image for an operator to analyze and confirm. In some embodiments, the mobile device 131 can include a smart home device, a wearable device, a mobile device, a virtual reality device, an augmented reality device, etc. or any combination thereof.

[0037] In some embodiments, the terminal device 130 can be a part of the processing device 120. In some embodiments, the terminal device 130 can be integrated with the processing device 120 as an operation station of the imaging device 110. For example, a user / operator (e.g., a doctor or a nurse) of the metal artifact correction system 100 can control the operation of the imaging device 110, such as scanning a target object, etc. through the operation station. In some embodiments, the processing device 120 can be integrated in the imaging device 110.

[0038] The storage device 140 can store data (e.g., an image to be processed, a matching template, a repaired image, etc.), instructions, and / or any other information. In some embodiments, the storage device 140 can store data acquired from the imaging device 110, the processing device 120, and / or the terminal device 130. For example, the storage device 140 can store an image to be processed of a target object acquired from the imaging device 110, etc. For another example, the storage device 140 can store a repaired image of filtering high-frequency metal artifacts acquired from the processing device 120, etc. In some embodiments, the storage device 140 can store data and / or instructions that the processing device 120 can execute or use to perform the exemplary methods described in this specification.

[0039] In some embodiments, the storage device 140 can include one or a combination of a mass storage, a removable storage, a volatile read-write memory, a read-only memory (ROM), etc. In some embodiments, the storage device 140 can be implemented through a cloud platform described in this specification.

[0040] In some embodiments, the storage device 140 can be connected to the network 150 to enable communication between one or more components in the metal artifact correction system 100 (e.g., the processing device 120, the terminal device 130). One or more components in the metal artifact correction system 100 can read data or instructions in the storage device 140 through the network 150. In some embodiments, the storage device 140 can be part of the processing device 120 or can be independent and directly or indirectly connected to the processing device 120.

[0041] The network 150 can include any suitable network capable of facilitating the exchange of information and / or data between the components of the metal artifact correction system 100. In some embodiments, one or more components of the metal artifact correction system 100 (e.g., the imaging device 110, the processing device 120, the terminal device 130, the storage device 140) can exchange information and / or data between one or more components of the metal artifact correction system 100 via the network 150. For example, the processing device 120 can obtain the image to be processed of the target object from the imaging device 110 via the network 150. In some embodiments, the network 150 can include one or more of a public network (e.g., the Internet), a private network (e.g., a local area network (LAN), a wide area network (WAN)), a wired network (e.g., an Ethernet network), a wireless network (e.g., an 802.11 network, a wireless Wi-Fi network, etc.), a cellular network (e.g., a long term evolution (LTE) network), a frame relay network, a virtual private network (VPN), a satellite network, a telephone network (e.g., a

[0042] It should be noted that the foregoing description is only illustrative of the application and not intended to be limiting. Numerous variations and modifications will become apparent to those skilled in the art once the contents of this specification are appreciated. Features, structures, methods and other characteristics of the exemplary embodiments described herein can be combined in various ways to obtain additional and / or alternative exemplary embodiments. For example, the system 100 can further include a display device for outputting a display of the magnetic resonance image generated by the processing device 120. However, such variations and modifications do not depart from the scope of the specification.

[0043] Figure 2 is a block diagram of an exemplary metal artifact correction system according to some embodiments of the present specification.

[0044] As Figure 2 shown, in some embodiments, the metal artifact correction system 200 can include an acquisition module 210, a data repair module 220, a filtering module 230, and an image generation module 240. In some embodiments, one or more of the modules of the metal artifact correction system 200 can be connected to each other. The connection can be wireless or wired. At least a portion of the metal artifact correction system 200 can be implemented on the imaging device 110, the processing device 120, or the terminal device 130 as Figure 1 shown.

[0045] The acquisition module 210 can be configured to acquire a to-be-processed image containing metal artifacts. For example, the to-be-processed image can include an X-ray imaging image.

[0046] The data repairing module 220 can be configured to perform data repairing. In some embodiments, the data repairing module 220 can be configured to perform data repairing on the metal track portion in the to-be-processed image by using a data repairing method to obtain repaired projection data. In some embodiments, the data repairing module 220 can be configured to determine a metal image based on the to-be-processed image; determine a metal track sinogram based on the metal image; perform data repairing based on the metal track sinogram by using the data repairing method to obtain the repaired projection data. The metal track sinogram can reflect the position of the metal track in the to-be-processed image.

[0047] The filtering module 230 can be configured to filter the repaired projection data. In some embodiments, the filtering module 230 can be configured to perform low-pass filtering on the repaired projection data to obtain filtered repaired projection data. In some embodiments, the filtering module 230 can be configured to divide the repaired projection data into a first data portion and a second data portion, and perform low-pass filtering on the repaired data corresponding to the metal track portion to obtain the filtered repaired projection data. The first data portion is original data that has not been subjected to data repairing, and the second data portion is repaired data that has been subjected to data repairing.

[0048] The image generating module 240 can be configured to generate a reconstructed image. In some embodiments, the image generating module 240 can be configured to obtain a repaired image with high-frequency metal artifacts filtered out by back-projection reconstruction based on the filtered repaired projection data.

[0049] It should be noted that the above description of the metal artifact correction system 200 is for illustrative purposes only, and is not intended to limit the scope of the present specification. Various modifications and changes can be made by those of ordinary skill in the art based on the present specification. However, these modifications and changes do not depart from the scope of the present specification. For example, one or more modules of the metal artifact correction system 200 described above can be omitted or integrated into a single module. For another example, the metal artifact correction system 200 can include one or more additional modules, such as a storage module for data storage, etc.

[0050] Figure 3 is a flowchart of an exemplary metal artifact correction method according to some embodiments of the present specification.

[0051] In some embodiments, the process 300 can be performed by the metal artifact correction system 100 (e.g., the imaging device 110, the processing device 120, or the terminal device 130 in the metal artifact correction system 100) or the metal artifact correction system 200. For example, the process 300 can be implemented as instructions (e.g., an application program) and stored in, for example, the storage device 140 or a memory external to the metal artifact correction system (e.g., the metal artifact correction system 100 or the metal artifact correction system 200) and accessible by the processing device 120 or the metal artifact correction system 200. The processing device 120 or the metal artifact correction system 200 can execute the instructions, and upon execution of the instructions, can be configured to perform the process 300. The operation schematic of the process 300 presented below is illustrative. In some embodiments, the process can be accomplished with one or more additional operations not described and / or one or more operations not discussed. Additionally, Figure 3 The order of the operations of the process 300 shown in FIG. 6 and described below is non-limiting.

[0052] At step 310, an image to be processed containing metal artifacts is obtained. In some embodiments, the step 310 can be performed by the processing device 120 or the obtaining module 210.

[0053] The image to be processed can refer to an initial scanning image containing metal artifacts without processing, for example, an image obtained by scanning by the imaging device 110. In some embodiments, the image to be processed can include a radiographic image containing metal artifacts.

[0054] When the imaging device scans a target object, the rays from the ray source are fixed to the target object through the ray filter, the rays passing through the target object are detected by the detector as an electrical signal, and the output signal of the detector is collected, amplified, and converted into a digital signal for each detector channel to produce projection data.

[0055] In radiographic imaging, due to the high attenuation of metal to rays, a large proportion of rays are absorbed by metal, and the rays received by the detector are very small. In clinical applications, when a target object is radiographically imaged, the patient carries metal implants (such as metal dentures, bone pins, etc.) in the body, and the corresponding data at the metal is not collected due to the absorption of most rays by the metal implants, resulting in insufficient data acquisition of the obtained projection data, and the read projection value is very different from the true value, thereby forming metal artifacts in the reconstructed image. Metal artifacts are usually represented as a blank strip with no actual information on the sinogram, i.e., data missing (for example, Figure 6 as shown in 610 in (a)), and as a serious strip in the reconstructed image (for example, Figure 6 as shown in 620 in (b)).

[0056] In some embodiments, the image to be processed can include projection data (e.g., Figure 6 reconstructed images (e.g., based on the projection data shown in (a)) obtained by projection reconstruction. In some embodiments, the image to be processed containing metal artifacts can be acquired from the imaging device 110 and / or the storage device 140. Figure 6 Figure 6 In some embodiments, the image to be processed can include projection data (e.g., Figure 6 reconstructed images (e.g., based on the projection data shown in (a)) obtained by projection reconstruction. In some embodiments, the image to be processed containing metal artifacts can be acquired from the imaging device 110 and / or the storage device 140.

[0057] In step 320, the metal track part in the image to be processed is repaired by using a data repair method to obtain repaired projection data. In some embodiments, step 320 can be performed by the processing device 120 or the data repair module 220.

[0058] In some embodiments, the repaired projection data can include projection data of the target corresponding metal part (i.e., missing data) and projection data of other parts collected, for example, as shown in (c). Figure 7

[0059] Data repair can refer to recovering the uncollected data corresponding to the metal part in the projection data. In some embodiments, the data repair method can be used to repair the metal track part in the image to be processed.

[0060] In some embodiments, the data repair method can include but is not limited to an interpolation method. The interpolation method can achieve data recovery by interpolating the metal region. For example, the processing device 120 can segment the metal image from the image to be processed by using a threshold segmentation method, and determine the metal track sinogram based on the metal image. Further, the projection data corresponding to the metal part can be fitted according to the collected projection data of the metal track edge in the metal track sinogram, so as to achieve data recovery.

[0061] In some embodiments, the metal image can be determined based on the image to be processed, the metal track sinogram can be determined based on the metal image, the data repair method can be used to repair the data based on the metal track sinogram, and the repaired projection data can be obtained. For more details, please refer to Figure 5 and related descriptions thereof, which will not be repeated here.

[0062] In step 330, the repaired projection data is low-pass filtered to obtain filtered repaired projection data. In some embodiments, step 330 can be performed by the processing device 120 or the filtering module 230.

[0063] Data inpainting is a method of inferring uncollected data based on collected or recovered data, and the inpainted data depends on the reference data. Inevitably, some high-frequency data is introduced in the data inpainting process. Accordingly, when the metal track part in the image to be processed is subjected to data inpainting, some high-frequency data is introduced in the inpainted data.

[0064] In some embodiments, the inpainted projection data can be subjected to low-pass filtering to filter out the high-frequency data in the inpainted data. In some embodiments, the high-frequency data can include inpainted data with a pixel value or a frequency value greater than a preset value, which will manifest as strip-shaped artifacts of varying sizes in the reconstructed image (e.g. Figure 8 The reconstructed image shown in (a) is not subjected to filtering). The preset value can be any reasonable value, for example, the mean value, the maximum value, etc. of the projection data corresponding to the metal part obtained based on a plurality of sets of clinical scan data, which is not limited in the present specification.

[0065] In some embodiments, the inpainted data corresponding to the metal track part can be subjected to low-pass filtering to obtain filtered inpainted projection data. In some embodiments, the inpainted data corresponding to the metal track part can be subjected to low-pass filtering while the original data is retained to obtain the filtered inpainted projection data. For more information on low-pass filtering of the inpainted projection data, see Figure 4 and the related description, which will not be repeated here.

[0066] In some embodiments, the inpainted data corresponding to the metal track part can be subjected to low-pass filtering and fused with the original data (e.g. the first data part) to obtain the filtered inpainted projection data.

[0067] At step 340, based on the filtered inpainted projection data, a reconstructed image is obtained by back-projection reconstruction. In some embodiments, step 340 can be performed by the imaging device 110, the processing device 120, or the image generation module 240.

[0068] In some embodiments, based on the filtered inpainted projection data, a reconstructed image with high-frequency artifacts and / or metal artifacts filtered out can be obtained by back-projection reconstruction. In some embodiments, the filtered inpainted projection data can be reconstructed by a back-projection reconstruction algorithm to obtain an intermediate reconstructed image, and based on the intermediate reconstructed image and the metal image, the reconstructed image is obtained. For example, Figure 8 The image shown in (a) is a reconstructed image without filtering (i.e. a reconstructed image obtained based on the inpainted projection data), and the image contains some small fine strip-shaped artifacts, i.e. high-frequency artifacts, Figure 8(b) The image shown is the repaired image, in which the small fine line-like artifacts are weakened. In some embodiments, the intermediate reconstructed image can be fused with the segmented metal image to obtain the repaired image. For example, the metal can be superimposed on the intermediate reconstructed image to obtain the repaired image.

[0069] In some embodiments, the back-projection reconstruction algorithm can include, but is not limited to, parallel ray beam filtered back-projection reconstruction and / or fan ray beam back-projection reconstruction. In some embodiments, the repaired image can be obtained by other image reconstruction methods, such as analytical reconstruction, planar reconstruction, maximum density projection, volume roaming technology VRT, etc., which are not limited by the present specification.

[0070] It should be noted that the above description of the flow 300 is only for example and illustration, and does not limit the scope of the present specification. Various modifications and changes can be made to the flow 300 under the guidance of the present specification by those skilled in the art. However, these modifications and changes are still within the scope of the present specification.

[0071] Figure 4 is a flow diagram of an example of filtering repaired data according to some embodiments of the present specification. In some embodiments, the flow 400 can be performed by the metal artifact correction system 100 (e.g., the imaging device 110, the processing device 120 or the terminal device 130 in the metal artifact correction system 100) or the metal artifact correction system 200 (e.g., the filtering module 230). The operation diagram of the flow 400 presented below is illustrative. In some embodiments, the process can be completed with one or more additional operations not described and / or one or more operations not discussed.

[0072] As shown in Figure 4 In some embodiments, the repaired projection data 410 can be divided into a first data portion 425 and a second data portion 427, as shown in some embodiments. The first data portion 425 is the original data that has not been repaired, i.e., the projection data collected. The second data portion 427 is the repaired data that has been repaired, i.e., the projection data corresponding to the metal portion.

[0073] In some embodiments, the second data portion 427 (i.e., the repaired data corresponding to the metal track portion) in the repaired projection data 410 can be determined by using the template, the second data portion 427 can be low-pass filtered to obtain the filtered data 440, and the filtered data 440 and the first data portion 425 in the repaired projection data 410 can be used to obtain the filtered repaired projection data 450. In some embodiments, the repaired projection data 410 can be low-pass filtered to obtain the filtered data 440 corresponding to the metal portion (i.e., the second data portion 427). In some embodiments, the repaired projection data can be low-pass filtered by using a Gaussian low-pass filtering method to obtain the filtered repaired projection data. In some embodiments, the repaired projection data can be low-pass filtered by using other low-pass filtering methods, which are not limited in the present specification.

[0074] In some embodiments, the original data corresponding to the first data portion 425 (i.e., the data collected in the repaired projection data) can be retained, and the filtered data 440 and the original data corresponding to the first data portion 425 can be used to obtain the filtered repaired projection data 450. In some embodiments, the filtered repaired projection data 450 can be obtained by fusing the filtered data 440 and the original data corresponding to the first data portion 425.

[0075] For example only, the processing device 120 can low-pass filter the repaired projection data 410 to obtain the filtered data. Then, the filtered data and the original data corresponding to the first data portion 425 can be superimposed to obtain the filtered repaired projection data 450. Figure 7 (b) to determine the first data portion 425 and the second data portion 427 in the repaired projection data. Further, the filtered data 440 corresponding to the second data portion 427 in the filtered data can be obtained, and the filtered data 440 and the original data corresponding to the first data portion 425 can be superimposed to obtain the filtered repaired projection data 450.

[0076] By low-pass filtering the repaired projection data 410, the high-frequency data introduced in the data repair process can be filtered out, so as to avoid generating high-frequency artifacts when obtaining the reconstructed image based on the repaired projection data, and improve the image quality of the reconstructed image.

[0077] Figure 5 is a flow diagram of an example data repair according to some embodiments of the present specification.

[0078] In some embodiments, the flow 500 can be performed by the metal artifact correction system 100 (e.g., the imaging device 110, the processing device 120, or the terminal device 130 in the metal artifact correction system 100) or the metal artifact correction system 200 (e.g., the data repairing module 220). The operation schematic of the flow 500 presented below is illustrative. In some embodiments, the process can be completed with one or more additional operations not described and / or one or more operations not discussed.

[0079] At step 510, a metal image is determined based on the image to be processed.

[0080] The metal image can refer to a reconstructed image of a metal corresponding part in the target object, for example Figure 7 the image shown in (a). In some embodiments, the metal image in the image to be processed can be extracted by thresholding. For example, in CT imaging, the CT values of different tissues differ greatly, the CT value of air is generally -1000HU, the CT value of fat is -120-90HU, the CT value of bone is 300-2000HU, and the CT values of various metals are much greater than 2000HU, even tens of thousands. The processing device 120 can determine the corresponding metal image (for example Figure 6 the image shown in (a)) by thresholding based on the reconstructed image (for example Figure 7 the image shown in (b)). For another example, the processing device 120 can set a pixel threshold value based on the pixel values of different tissues in the reconstructed image, and segment the metal image from the reconstructed image based on the pixel threshold value. In some embodiments, the metal image in the image to be processed can be extracted by a trained machine learning model (for example, a U-net model).

[0081] In some embodiments, the image to be processed can be pre-processed, and the metal image can be determined based on the pre-processed image to be processed. For example, the pre-processing can include but is not limited to noise reduction, bilateral filtering, etc.

[0082] At step 520, a metal trajectory sinogram is determined based on the metal image.

[0083] In some embodiments, the projection data of the target object can be in the form of a sinogram. The metal trajectory sinogram can refer to the projection data corresponding to the metal part, for example Figure 7 the image shown in (b). In some embodiments, the metal trajectory sinogram can be determined by the forward projection method based on the metal image. In some embodiments, the metal trajectory sinogram can be directly determined based on the original projection data. For example, the metal trajectory sinogram can be determined by thresholding and other methods based on the projection data shown in (a). Figure 6

[0084] ​At step 530, data is repaired based on the metal trajectory sinogram by using a data repair method to obtain repaired projection data.

[0085] In some embodiments, the projection data of the metal neighborhood can be determined based on the metal trajectory sinogram, and data is repaired based on the projection data of the metal neighborhood by using a data repair method to obtain repaired projection data. For example, the data values in the metal region can be calculated based on the data values in the metal neighborhood to obtain the repaired projection data. In some embodiments, the projection data corresponding to the metal part can be determined by interpolation. In some embodiments, data is repaired based on the metal trajectory sinogram and a reference image to obtain repaired projection data. For example, a soft tissue CT value can be used to fill the metal region segmented in the reconstructed image by using a class organization model, and the filled reconstructed image is clustered by using a three-dimensional K-means algorithm to cluster the human tissue into air, fat, soft tissue, and bone, and the different clusters of tissue are assigned values to obtain a reference image, and the data corresponding to the metal region is determined based on the corresponding projection data of the reference image and the metal trajectory to obtain the repaired projection data.

[0086] It should be noted that the above description of the processes 400 and / or 500 is only for example and illustration, and does not limit the scope of the present specification. Various modifications and changes can be made to the processes 400 and / or 500 under the guidance of the present specification. For example, in the process 400, the high-frequency artifacts in the repaired projection data can be repaired based on the trained machine learning model to obtain a reconstructed image without metal artifacts and high-frequency artifacts. However, these modifications and changes are still within the scope of the present specification.

[0087] The beneficial effects that can be brought by the embodiments of the present specification include but are not limited to: (1) by performing low-pass filtering on the repaired projection data, the high-frequency data generated in the data repair process can be filtered out while eliminating the metal artifacts, avoiding the generation of high-frequency artifacts when obtaining the reconstructed image based on the repaired projection data, and improving the image quality of the reconstructed image; (2) by performing low-pass filtering on the repaired data in the repaired projection data, and not filtering the rest of the data, the image quality corresponding to the rest of the data can be avoided; (3) by performing low-pass filtering on the repaired projection data, the strip-shaped artifacts in the repaired image can be weakened or eliminated, thereby improving the image quality of the repaired image; (4) by eliminating the metal artifacts while suppressing the generation of high-frequency artifacts, the accuracy of the diagnosis result of the diagnosed region can be further improved. It should be noted that different embodiments can produce different beneficial effects, and in different embodiments, the beneficial effects that can be produced can be any one or a combination of the above, or any other beneficial effects that can be obtained.

[0088] Having described the basic concepts, it is obvious that the above detailed disclosure is intended to be illustrative only and not restrictive of the present description. Although the present description has been described with reference to specific exemplary embodiments, it will be apparent to those having ordinary skill in the art that a variety of modifications, improvements and / or alterations can be made to the present description. Such modifications, improvements and / or alterations are therefore contemplated and are within the spirit and scope of the exemplary embodiments of the present description.

[0089] Also, the present description can use particular terminology when describing embodiments of the present description. For example, the terms "one embodiment," "an embodiment," "some embodiments," or "one alternative" are used interchangeably, and are not necessarily referring to the same embodiment or alternative. Furthermore, the use of these terms does not necessarily eliminate the possibility of combinations with one another or with other alternatives.

[0090] Also, unless the claims recite otherwise, the order of process elements and sequence of processes described in the present description, the use of numerical terms, or the use of other names, does not limit the scope of the processes and methods of the present description. Although the above disclosure discusses some presently preferred embodiments of the application, it is understood that variations and modifications of the disclosed embodiments can be made by those skilled in the art without departing from the spirit and scope of the inventive concepts disclosed herein. For example, although the system components described above can be implemented by hardware devices, they can also be implemented by software solutions only, such as installing the described system on an existing server or mobile device.

[0091] Similarly, it is noted that the above description has been presented for the purpose of simplifying the description of the present description and to help understand one or more embodiments of the present description. The above description of the embodiments of the present description may, at times, combine various features into a single embodiment, drawing, or description of the same. However, this method of disclosure is not to be interpreted as a limitation on the scope of the claims. Indeed, the scope of the claims is to be understood as not including a requirement that features be present in all embodiments of the present description.

[0092] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0093] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0094] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method of correction of metal artifacts, characterized in that, The method comprises: acquiring a to-be-processed image containing a metal artifact; using a data repair method to perform data repair on a metal track part in the to-be-processed image to obtain repaired projection data; performing low-pass filtering on the repaired projection data to obtain filtered repaired projection data; based on the filtered repaired projection data, performing back-projection reconstruction to obtain a repaired image; the low-pass filtering is Gaussian low-pass filtering. The low-pass filtering on the repaired projection data to obtain filtered repaired projection data comprises:

2. The method of claim 1, wherein, dividing the repaired projection data into a first data part and a second data part, the first data part being original data that has not undergone the data repair, and the second data part being repaired data that has undergone the data repair. The data repair method comprises:

3. The method of claim 1, wherein, based on the to-be-processed image, determining a metal image; based on the metal image, determining a metal track sinogram; based on the metal track sinogram, performing data repair to obtain the repaired projection data. comprises:

4. A system for correction of metal artifacts, characterized in that an acquisition module configured to acquire a to-be-processed image containing a metal artifact; a data repair module configured to use a data repair method to perform data repair on a metal track part in the to-be-processed image to obtain repaired projection data; a filtering module configured to perform low-pass filtering on the repaired projection data to obtain filtered repaired projection data; the low-pass filtering is Gaussian low-pass filtering. an image generation module configured to perform back-projection reconstruction based on the filtered repaired projection data to obtain a repaired image. The filtering module is configured to:

5. The system of claim 4, wherein, divide the repaired projection data into a first data part and a second data part, the first data part being original data that has not undergone the data repair, and the second data part being repaired data that has undergone the data repair; perform low-pass filtering on the repaired data corresponding to the metal track part to obtain the filtered repaired projection data.

6. A computer-readable storage medium, the storage medium storing computer instructions, when a computer reads the computer instructions, the computer executes the method of any one of claims 1-3. comprises:

7. A metal artifact correction apparatus, characterized by, at least one storage medium storing computer instructions; at least one processor executing the computer instructions to implement the method of any one of claims 1-3. ​ 8. An X-ray image reconstruction method performed by at least one processor in communication with a storage device storing executable instructions that, when executed, instruct the at least one processor to perform the method, the method comprising: obtaining an X-ray image containing a metal artifact; performing data repair on a metal track portion in the X-ray image using a data repair method to obtain repaired projection data; performing low-pass filtering on the repaired projection data to obtain filtered repaired projection data; the performing low-pass filtering on the repaired projection data to obtain filtered repaired projection data comprises performing low-pass filtering on repaired data corresponding to the metal track portion to obtain the filtered repaired projection data, and the low-pass filtering is Gaussian low-pass filtering; performing image reconstruction based on the filtered repaired projection data to obtain a repaired image.

9. The method of claim 8, wherein, the performing low-pass filtering on the repaired projection data to obtain filtered repaired projection data comprises: dividing the repaired projection data into a first data portion and a second data portion, the first data portion being original data that has not undergone the data repair, and the second data portion being repaired data that has undergone the data repair.

10. The method of claim 8, wherein, the performing data repair on the metal track portion in the X-ray image using the data repair method to obtain repaired projection data comprises: determining a metal image based on the X-ray image; determining a metal track sinogram based on the metal image; performing data repair based on the metal track sinogram using a data repair method to obtain the repaired projection data.

Images