Medical image processing methods and systems

Abstract

This specification provides a medical image processing method and system. The method includes acquiring raw scan data of a scanned object; performing image reconstruction on the raw scan data to obtain a reconstructed image, wherein the reconstructed image contains metal artifacts; performing a first repair on the raw scan data based on the reconstructed image to remove metal artifacts and obtain first repaired scan data; segmenting the reconstructed image to obtain a skeletal image of the scanned object; performing a second repair on the first repaired scan data based on the skeletal image to obtain second repaired scan data; and reconstructing a target image based on the second repaired scan data. This method removes metal artifacts from the reconstructed image while reducing image artifacts caused by missing skeletal information, greatly improving the quality of the final reconstructed image and enhancing diagnostic effectiveness.

Description

Technical Field

[0001] This manual relates to the field of medical imaging, and in particular to a medical image processing method and system. Background Technology

[0002] Computed tomography (CT) is a widely used medical imaging method. In clinical CT use, because metals highly attenuate X-rays, a large proportion of X-rays are absorbed by the metal, resulting in very little radiation received by the detector. This leads to missing data, with measured values ​​deviating significantly from the true values. Consequently, metal artifacts appear in the reconstructed images, reducing image quality and affecting diagnostic accuracy. Currently, metal artifacts can be removed by repairing CT scan data and using the repaired scan data for image reconstruction. However, for complex skeletal areas such as the head, it is common to encounter situations where bone data is almost completely lost in the scan data, resulting in artifacts in the reconstructed images. Sometimes, this impact on image quality is even more severe than that of metal artifacts.

[0003] Therefore, it is desirable to provide a medical image processing method and system to remove image artifacts caused by missing bone data. Summary of the Invention

[0004] One embodiment of this specification provides a medical image processing method. The method includes: acquiring original scan data of a scanned object; performing image reconstruction on the original scan data to obtain a reconstructed image, the reconstructed image containing metal artifacts; performing a first repair on the original scan data based on the reconstructed image to remove the metal artifacts and obtain first repaired scan data; segmenting the reconstructed image to obtain a skeletal image of the scanned object; performing a second bone-related repair on the first repaired scan data based on the skeletal image to obtain second repaired scan data; and reconstructing a target image based on the second repaired scan data.

[0005] In some embodiments, a metal image of the scanned object can be obtained by segmenting the reconstructed image; orthographic projection of the metal image can be performed to obtain a metal projection image; and the original scan data can be repaired based on the metal projection image to obtain the first repaired scan data.

[0006] In some embodiments, the segmentation of the reconstructed image can be threshold segmentation.

[0007] In some embodiments, the target image can be obtained by reconstructing the image based on the metal image and the second post-repair scan data.

[0008] In some embodiments, the bone image can be orthographically projected to obtain a bone projection image; the first repaired scan data can be repaired based on the bone projection image to obtain the second repaired scan data.

[0009] In some embodiments, the bone data in the bone projection image can be added to the missing bone data area of ​​the first repaired scan data according to a preset ratio to obtain the second repaired scan data.

[0010] In some embodiments, the preset ratio may be related to the degree of missing bone data in the first post-repair scan data.

[0011] In some embodiments, the first repair may be performed using interpolation.

[0012] In some embodiments, the raw scan data may be cone-beam computed tomography (CBCT) scan data.

[0013] One embodiment of this specification provides a medical image processing system, including a medical imaging device and a processor. The medical imaging device is configured to perform a medical scan on a scanned object; the processor is configured to acquire raw scan data of the scanned object from the medical imaging device to execute the medical image processing method.

[0014] One embodiment of this specification provides another medical image processing system, including a data acquisition module, a first reconstruction module, a first repair module, an image segmentation module, a second repair module, and a second reconstruction module. The data acquisition module acquires raw scan data of the scanned object; the first reconstruction module performs image reconstruction on the raw scan data to obtain a reconstructed image, wherein the reconstructed image contains metal artifacts; the first repair module performs a first repair on the raw scan data based on the reconstructed image to remove the metal artifacts, obtaining first repaired scan data; the image segmentation module segments the reconstructed image to obtain a skeletal image of the scanned object; the second repair module performs a second bone-related repair on the first repaired scan data based on the skeletal image, obtaining second repaired scan data; and the second reconstruction module reconstructs a target image based on the second repaired scan data.

[0015] One embodiment of this specification provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the medical image processing method described in this embodiment.

[0016] In some embodiments of this specification, metal artifacts are removed from the final reconstructed image (i.e., the target image) by segmenting a metal image from the reconstructed image of the original scan data and repairing the original scan data based on the metal image. Simultaneously, bone images are segmented from the reconstructed image of the original scan data, and bone data from the bone images is added to the scan data (i.e., the first repaired scan data). This preserves the bone data, enhances the integrity and comprehensiveness of the repaired scan data (i.e., the second repaired scan data), reduces image artifacts caused by missing bone information, greatly improves the quality of the final reconstructed image, and improves the diagnostic effect. Attached Figure Description

[0017] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0018] Figure 1 These are schematic diagrams illustrating application scenarios of exemplary medical image processing systems according to some embodiments of this specification;

[0019] Figure 2 This is a block diagram of an exemplary medical image processing system according to some embodiments of this specification;

[0020] Figure 3 This is a flowchart illustrating an exemplary medical image processing method according to some embodiments of this specification;

[0021] Figure 4 This is a flowchart illustrating an exemplary first repair according to some embodiments of this specification;

[0022] Figure 5 This is a flowchart illustrating an exemplary second repair according to some embodiments of this specification;

[0023] Figure 6 This is a schematic diagram of an exemplary medical image processing method according to some embodiments of this specification;

[0024] Figure 7A and Figure 7B These are schematic diagrams of exemplary medical images shown according to some embodiments of this specification. Detailed Implementation

[0025] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0026] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0027] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0028] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0029] Figure 1 These are schematic diagrams illustrating application scenarios of exemplary medical image processing systems according to some embodiments of this specification. For example... Figure 1 As shown, in some embodiments, the medical image processing system 100 may include a medical imaging device 110, a processing device 120, a storage device 130, a terminal 140, and a network 150.

[0030] Medical imaging device 110 refers to a medical device that uses various media to reproduce the internal structures of the human body as images. In some embodiments, medical imaging device 110 can be any medical device that includes a detector and uses X-rays to image or treat designated body parts of a patient, such as a CT scanner, cone-beam computed tomography (CBCT) scanner, etc. The medical imaging device 110 described above is for illustrative purposes only and is not intended to limit its scope. This specification uses CBCT as an example for all medical imaging devices 110. Medical imaging device 110 can scan a target (e.g., a human body, an animal) and send the scan data to processing device 120. Medical imaging device 110 can receive instructions from a doctor via terminal 140 and perform related operations according to the instructions, such as scanning and imaging. In some embodiments, medical imaging device 110 can exchange data and / or information with other components in medical image processing system 100 (e.g., processing device 120, storage device 130, terminal 140) via network 150. In some embodiments, the medical imaging device 110 may be directly connected to other components in the system 100. In some embodiments, one or more components of the medical image processing system 100 (e.g., processing device 120, storage device 130) may be included within the medical imaging device 110.

[0031] Processing device 120 can process data and / or information obtained from other devices or system components, and perform medical image processing methods shown in some embodiments of this specification based on this data, information, and / or processing results to accomplish one or more functions described in some embodiments of this specification. For example, processing device 120 can perform image reconstruction based on scan data from medical imaging device 110. As another example, processing device 120 can perform segmentation, projection, and other processing on medical images. As yet another example, processing device 120 can repair the original scan data from medical imaging device 110. In some embodiments, processing device 120 can send the processed data to storage device 130 for storage. In some embodiments, processing device 120 can retrieve pre-stored data and / or information, such as original scan data, from storage device 130.

[0032] In some embodiments, the processing device 120 may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core multi-chip processing device). By way of example only, the processing device 120 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction processor (ASIP), a graphics processing unit (GPU), a physical processor (PPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, or any combination thereof.

[0033] Storage device 130 can store data or information generated by other devices. In some embodiments, storage device 130 can store data and / or information acquired by medical imaging device 110, such as scan data. In some embodiments, storage device 130 can store data and / or information processed by processing device 120, such as reconstructed images, segmented images, projected images, repaired scan data, etc. Storage device 130 may include one or more storage components, each of which may be a separate device or part of other devices. The storage device may be local or implemented via the cloud.

[0034] Terminal 140 can control the operation of medical imaging equipment 110. Doctors can issue operating instructions to medical imaging equipment 110 through terminal 140 to cause it to perform specified operations, such as scanning and imaging a specified body part of a patient. In some embodiments, terminal 140 can instruct processing device 120 to perform medical image processing methods as shown in some embodiments of this specification. In some embodiments, terminal 140 can receive reconstructed images from processing device 120 for effective and targeted examination and / or treatment of the patient. In some embodiments, terminal 140 can be one or any combination of mobile device 140-1, tablet computer 140-2, laptop computer 140-3, desktop computer, and other devices with input and / or output functions.

[0035] Network 150 can connect the various components of the system and / or connect the system to external resources. Network 150 enables communication between the components and with other parts outside the system, facilitating the exchange of data and / or information. In some embodiments, one or more components of the medical image processing system 100 (e.g., medical imaging device 110, processing device 120, storage device 130, terminal 140) can send data and / or information to other components via network 150. In some embodiments, network 150 can be any one or more of a wired network or a wireless network.

[0036] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this specification. Various changes and modifications can be made by those skilled in the art based on the content of this specification. Features, structures, methods, and other features of the exemplary embodiments described herein can be combined in various ways to obtain other and / or alternative exemplary embodiments. For example, the processing device 120 may be based on a cloud computing platform, such as a public cloud, private cloud, community cloud, and hybrid cloud. However, these changes and modifications will not depart from the scope of this specification.

[0037] Figure 2 This is a block diagram of an exemplary medical image processing system according to some embodiments of this specification. For example... Figure 2 As shown, the medical image processing system 200 includes a data acquisition module 210, a first reconstruction module 220, a first repair module 230, an image segmentation module 240, a second repair module 250, and a second reconstruction module 260. In some embodiments, each module in the medical image processing system 200 can be implemented by the processing device 120.

[0038] The data acquisition module 210 is used to acquire the raw scan data of the scanned object. For more information on how to acquire the raw scan data, please refer to step S310.

[0039] The first reconstruction module 220 is used to perform image reconstruction on the original scan data to obtain a reconstructed image, wherein the reconstructed image contains metal artifacts. For more information on how to obtain the reconstructed image, see step S320.

[0040] The first repair module 230 is used to perform a first repair on the original scan data based on the reconstructed image to remove metal artifacts, thereby obtaining first repaired scan data. For more information on how to obtain the first repaired scan data, see step S330.

[0041] The image segmentation module 240 is used to segment the reconstructed image to obtain a skeletal image of the scanned object. For more information on how to obtain the skeletal image, see step S340.

[0042] The second repair module 250 is used to perform bone-related second repairs on the first repaired scan data based on the bone image to obtain second repaired scan data. For more information on how to obtain the second repaired scan data, see step S350.

[0043] The second reconstruction module 260 is used to obtain the target image through image reconstruction based on the second post-repair scan data. For more information on how the target image is obtained, see step S360.

[0044] Figure 3This is a flowchart illustrating an exemplary medical image processing method according to some embodiments of this specification. For example... Figure 3 As shown, process 300 includes the following steps. In some embodiments, process 300 may be executed by processing device 120.

[0045] Step S310: Acquire the raw scan data of the scanned object. In some embodiments, step S310 may be performed by the data acquisition module 210.

[0046] The scanned object refers to the object scanned by medical imaging equipment. Scanned objects include humans, animals, etc. In some embodiments, the scanned object can be a part of a human or animal body. For example, the scanned object can be the human head, mouth, limbs, torso, etc. Raw scan data is data directly acquired by medical imaging equipment through scanning. Raw scan data can include detector data from the medical imaging equipment, two-dimensional or three-dimensional images, etc. In some embodiments, raw scan data can be cone-beam computed tomography (CBCT) scan data, which includes multiple two-dimensional scan images of the scanned object from different angles. For example, raw scan data can be obtained from... Figure 7A Subgraph a in the diagram represents this.

[0047] The processing device 120 can scan the object using a medical imaging device (e.g., medical imaging device 110) to obtain the raw scan data of the object. In some embodiments, the processing device 120 can obtain the raw scan data of the object in other ways. For example, the processing device 120 can obtain the raw scan data of the object from a storage device (e.g., storage device 130).

[0048] Step S320: Image reconstruction is performed on the original scan data to obtain a reconstructed image. In some embodiments, step S320 may be performed by the first reconstruction module 220.

[0049] The processing device 120 can perform back-projection reconstruction on the original scan data to obtain a reconstructed image. In some embodiments, when the original scan data is CBCT scan data, the reconstructed image can be a three-dimensional image of the scanned object. Due to the high attenuation of X-rays by metals, metal artifacts exist in the reconstructed image, i.e., artifacts caused by metals. For example... Figure 7A and Figure 7B These are schematic diagrams of exemplary medical images shown according to some embodiments of this specification. The reconstructed images can be... Figure 7A Subgraph b in the text, subgraph b is composed of Figure 7A Sub-image a (original scan data) was obtained through back projection reconstruction. The two blank bands 710 in sub-image a are the scan data missing areas caused by metal absorption of X-rays, and 720 in sub-image b is the metal artifact caused by 710.

[0050] In some embodiments, the processing device 120 may perform image reconstruction on the original scan data in other ways. For example, image reconstruction may be performed using a machine learning model or based on an image reconstruction algorithm.

[0051] Step S330: Based on the reconstructed image, perform a first repair on the original scan data to remove metal artifacts and obtain first repaired scan data. In some embodiments, step S330 may be performed by the first repair module 230.

[0052] The first repair, also known as the first processing, is used to remove metal artifacts from the reconstructed image. The first-repaired scan data, i.e., the metal-free image data, is scan data from the original scan data with the missing data areas caused by metal removed. In some embodiments, the processing device 120 can obtain a metal image of the scanned object by segmenting the reconstructed image. The processing device 120 can perform orthographic projection on the metal image to obtain a metal projection image. The processing device 120 can perform the first repair on the original scan data based on the metal projection image to obtain the first-repaired scan data. For more information on how to obtain the first-repaired scan data, see [link to documentation]. Figure 4 .

[0053] Step S340: Segment the reconstructed image to obtain a skeletal image of the scanned object. In some embodiments, step S340 may be performed by the image segmentation module 240.

[0054] If the scanned object contains areas with complex skeletons (e.g., a patient's head), there is often a significant lack of bone data for that area in the first post-repair scan data, leading to severe artifacts in subsequent images reconstructed based on the first post-repair scan data. For example, Figure 7A In the diagram, sub-image f is the reconstructed image obtained based on sub-images e and c. Sub-image f may contain artifacts caused by missing skeletal data. After step S320 or S330, the processing device 120 can perform threshold segmentation on the reconstructed image to obtain a skeletal image of the scanned object, which contains the skeletal data of the scanned object. It is understandable that when the reconstructed image is a three-dimensional image, the segmented skeletal image is also a three-dimensional image. For example, Figure 7B In the image, the first restored scan data is sub-image h, and the part enclosed in the frame is the area where the skeletal data is missing; the skeletal image is sub-image i, which is obtained by segmenting the reconstructed image.

[0055] In some embodiments, the processing device 120 may segment the skeletal image from the reconstructed image in other ways, such as by using a machine learning model or by using an image segmentation algorithm.

[0056] Step S350: Perform bone-related second repair on the first repaired scan data based on the bone image to obtain second repaired scan data. In some embodiments, step S350 may be performed by the second repair module 250.

[0057] The second repair, also known as the second processing, is used to remove artifacts in the reconstructed image caused by missing bone data. The second-repaired scan data is scan data supplemented with the missing bone data based on the first-repaired scan data. In some embodiments, after step S330, the processing device 120 can perform orthographic projection on the bone image to obtain a bone projection image. After step S340, the processing device 120 can perform a second repair on the first-repaired scan data based on the bone projection image to obtain the second-repaired scan data. For more information on how to obtain the second-repaired scan data, see [link to documentation]. Figure 5 .

[0058] Step S360: Based on the second repaired scan data, the target image is obtained through image reconstruction. In some embodiments, step S360 may be performed by the second reconstruction module 260.

[0059] A target image refers to a reconstructed image of the scanned object that contains complete information about the scanned object and removes artifacts. For example, the target object could be a reconstructed image that includes metal information from the scanned object and removes metal artifacts and artifacts caused by missing bones.

[0060] The processing device 120 can obtain a target image through image reconstruction based on a metal image and second post-repair scan data. Specifically, the processing device 120 can perform image reconstruction on the second post-repair scan data in a manner similar to that used for image reconstruction based on the original scan data, which will not be described in detail here. Based on the reconstructed image obtained from the second post-repair scan data, the processing device 120 can replace the image in the reconstructed image with the metal portion from the metal image at the same location as the metal portion, thereby obtaining a complete reconstructed image containing the metal information of the scanned object, and using this complete reconstructed image as the target image. In some embodiments, the processing device 120 can add the metal portion from the metal image to the reconstructed image in various ways, which are not limited in this specification. For example, the processing device 120 can replace the image content in the reconstructed image at the same location as the metal portion with the metal portion from the metal image. By obtaining a target image through image reconstruction based on a metal image and second post-repair scan data, artifacts caused by metal artifacts and bone loss can be eliminated, while the missing metal portion in the original scan data can be added to the reconstructed image to obtain a complete reconstructed image, thereby improving the quality of the reconstructed image.

[0061] In some embodiments of this specification, the quality of the reconstructed image is improved by segmenting the metal image and the bone image from the reconstructed image of the original scan data and performing two repairs on the original scan data to remove metal artifacts and artifacts caused by bone defects, respectively.

[0062] Figure 4 This is a flowchart illustrating an exemplary first repair according to some embodiments of this specification. For example... Figure 4 As shown, process 400 includes the following steps. In some embodiments, processing device 120 or first repair module 230 can implement step S330 by executing process 400, that is, performing a first repair on the original scan data based on the reconstructed image to remove metal artifacts and obtain first repaired scan data.

[0063] Step S410: Obtain the metal image of the scanned object by segmenting and reconstructing the image.

[0064] A metal image is an image representing the metallic parts of a scanned object. These metallic parts can include metal accessories on the object, metal implants inside the body, etc. For example, Figure 7A In the image, sub-image c is the metal image, and 730 represents the segmented metal portion. Sub-image c is composed of sub-images... Figure 7A Sub-image b in the image is obtained through image segmentation. For example, Figure 7B The metal image in the middle is sub-image g, and the area within the box is the metal area. The metal within the box can correspond to a part of 730. The method of obtaining the metal image of the scanned object by segmenting and reconstructing the image is similar to that of obtaining the skeleton image by segmenting and reconstructing the image, see step S340.

[0065] By segmenting the reconstructed image to obtain a metal image, the metal region in the original scan data can be separated, distinguishing the metal part of the scanned object from other parts, which facilitates the subsequent removal of the adverse effects of metal from the original scan data, thereby removing metal artifacts in the reconstructed image; at the same time, by adding the metal part from the metal image to the reconstructed image, the integrity and comprehensiveness of the reconstructed image can be improved.

[0066] Step S420: Perform orthographic projection on the metal image to obtain a metal projection image.

[0067] Processing device 120 can perform orthographic projection on a three-dimensional metal image to obtain a two-dimensional metal projection image. Orthographic projection is the process of obtaining a two-dimensional image from a three-dimensional image through projection. The metal projection image includes metal tracks formed by the metal in the scanned object; these metal tracks represent data gaps in the original scan data caused by the metal. For example, Figure 7AIn the diagram, sub-image d is the projected image of the metal, and 740 is the metal trajectory. Sub-image d is obtained by orthographic projection of sub-image c. It can be seen that part 710 in sub-image a is consistent with 740 (metal trajectory) in sub-image d.

[0068] Step S430: Perform a first repair on the original scan data based on the metal projection image to obtain the first repaired scan data.

[0069] The first post-repair scan data does not include metal information from the scanned object. In some embodiments, the first repair may include removing the metal trajectory portion from the metal projection image in the original scan data and repairing the area where the metal trajectory was removed. For example, Figure 7A In the diagram, subgraph e represents the scan data after the first repair, and subgraph e represents the data based on subgraph c. Figure 7A The first repair is performed on subgraph a in the image.

[0070] In some embodiments, the first repair can be performed using interpolation. For example, as... Figure 7A As shown, the processing device 120 can remove the portion corresponding to 740 (i.e., portion 710) in sub-image a, thereby removing the metal influence in the original scan data. Understandably, after removal, the area corresponding to portion 740 in the original scan data is blank. Then, the processing device 120 can fill the blank portion with data through interpolation based on the pixel values ​​of image pixels in adjacent areas to perform repair, thus obtaining sub-image e. Sub-image f is a reconstructed image of the scanned object obtained by image reconstruction based on sub-image e. It can be seen that the metal artifact 720 in sub-image b has been removed in sub-image f. By using interpolation to repair the original scan data, it is possible to remove the adverse effects of metal in the original scan data while supplementing the scan data in the metal area, thereby improving the quality of the scan data while maintaining its integrity.

[0071] In some embodiments of this specification, by segmenting the metal image from the reconstructed image of the original scan data, and by orthographically projecting the metal image to obtain a metal projection image containing the metal trajectory, and by performing a first repair on the original scan data based on the metal projection image, the first repaired scan data is obtained. This can remove the influence caused by the metal in the original scan data, thereby removing metal artifacts in the subsequent reconstructed image and improving the quality of the reconstructed image.

[0072] Figure 5 This is a flowchart illustrating an exemplary second repair according to some embodiments of this specification. For example... Figure 5As shown, process 500 includes the following steps. In some embodiments, the processing device 120 or the second repair module 250 can implement step S350 by executing process 500, that is, performing a bone-related second repair on the first repaired scan data based on the bone image to obtain the second repaired scan data.

[0073] Step S510: Perform orthographic projection on the skeletal image to obtain a skeletal projection image.

[0074] A skeletal projection image is a two-dimensional image obtained by projecting a three-dimensional skeletal image. The method of orthographic projection of a skeletal image is similar to that of orthographic projection of a metal image, see step S420.

[0075] Step S520: Perform a second repair on the first repaired scan data based on the bone projection image to obtain the second repaired scan data.

[0076] In some embodiments, the processing device 120 can add bone data from a bone projection image to the missing bone data area of ​​the first repaired scan data according to a preset ratio to obtain second repaired scan data. The preset ratio can be a number greater than 0. For example, Figure 7B In the first post-repair scan data, sub-image j is obtained by performing a second repair on sub-image h based on sub-image i. For each pixel P1 in the skeletal region within the box in sub-image i, the processing device 120 can multiply the pixel value of pixel P1 by a preset ratio (e.g., 0.5, 0.8, 1, etc.) and then add it to the pixel value of the corresponding pixel P1' in the first post-repair scan data. The position of P1 in the skeletal projection image is the same as the position of P1' in the first post-repair scan data. After such processing, sub-image j is obtained from the first post-repair scan data. It can be seen that, compared to sub-image h, the skeletal region information in sub-image j is complete and without missing data. By adding the skeletal data to the missing skeletal data region of the first post-repair scan data according to a preset ratio, the missing skeletal data in the first post-repair scan data can be supplemented, improving the completeness of the subsequent reconstructed image and enhancing the quality of the reconstructed image.

[0077] The preset ratio can be obtained in various ways, such as based on empirical values ​​or the degree of missing bone data. In some embodiments, the preset ratio can be related to the degree of missing bone data in the first restored scan data. The higher the degree of missing data, the larger the preset ratio; the lower the degree of missing data, the smaller the preset ratio. By determining the preset ratio based on the degree of missing bone data, a smooth transition between the bone region and other regions in the second restored scan data can be achieved, thereby improving the quality of subsequent reconstructed images.

[0078] In some embodiments of this specification, a bone projection image is obtained by projecting a bone image, and a second repair is performed on the first repaired scan data based on the bone projection image to obtain the second repaired scan data. This can overcome the problem of missing bone data in complex bone regions, supplement bone data in the first repaired scan data, improve the integrity of the subsequent reconstructed image, and remove artifacts caused by missing bone data in the reconstructed image, thereby improving the quality of the reconstructed image.

[0079] Figure 6 This is a schematic diagram of an exemplary medical image processing method according to some embodiments of this specification. In some embodiments, each module in the processing device 120 or the medical image processing system 200 may implement at least one step in process 300 by performing at least a portion of the methods in process 600.

[0080] like Figure 6 As shown, the processing device 120 performs back-projection reconstruction on the acquired original scan data 610 of the scanned object to obtain a reconstructed image 620, as shown in step S320. The processing device 120 performs threshold segmentation on the reconstructed image 620 to obtain a metal image 630 and a bone image 640, as shown in steps S330, S340 and S410.

[0081] Processing device 120 orthogonally projects the metal image 630 to obtain a metal projection image 650. Then, it performs interpolation processing on the metal projection image 650 to obtain the first restored scan data 670, as described in steps S330, S420, and S430. Processing device 120 orthogonally projects the bone image 640 to obtain a bone projection image 660, as described in steps S350 and S510. Processing device 120 superimposes the bone projection image 660 onto the first restored scan data 670, that is, it adds the bone data from the bone projection image 660 to the missing bone data areas of the first restored scan data 670 according to a preset ratio, to obtain the second restored scan data 680, as described in steps S350 and S520.

[0082] The processing device 120 performs image reconstruction on the second repaired scan data 680, and performs data replacement based on the metal image 630 in the obtained reconstructed image, that is, replaces the image of the area in the reconstructed image that is at the same position as the metal part with the metal part in the metal image 630, thereby obtaining the target image 690.

[0083] It should be noted that the above descriptions of processes 300, 400, 500, and 600 are for illustrative purposes only and do not limit the scope of this specification. Those skilled in the art can make various modifications and changes to processes 300, 400, 500, and 600 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, metal and skeletal images can be obtained entirely by segmenting the reconstructed image in one step, i.e., steps S340 and S410 can be combined into one step. As another example, steps S340 and S510 can be performed after step S340 or simultaneously with step S340, with step S520 executed after steps S340 and S510 are completed.

[0084] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0085] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0086] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0087] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0088] 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.

[0089] 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.

[0090] 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 medical image processing method, comprising: Obtain the raw scan data of the object being scanned; The original scan data is used to perform image reconstruction to obtain a reconstructed image, which contains metal artifacts; Based on the reconstructed image, the original scan data is subjected to a first repair to remove the metal artifacts to obtain the first repaired scan data; The reconstructed image is segmented to obtain the skeletal image of the scanned object; Based on the bone image, a second bone-related repair is performed on the first repaired scan data to obtain a second repaired scan data. The target image is obtained by reconstructing the image based on the second repaired scan data.

2. The method as described in claim 1, characterized in that, The first restoration process, which removes metal artifacts from the original scan data based on the reconstructed image to obtain the first restored scan data, includes: The metal image of the scanned object is obtained by segmenting the reconstructed image; The metal image is orthographically projected to obtain a metal projection image; The first repair is performed on the original scan data based on the metal projection image to obtain the first repaired scan data.

3. The method as described in claim 2, characterized in that, The segmentation of the reconstructed image is threshold segmentation.

4. The method as described in claim 2, characterized in that, The process of reconstructing the target image based on the second repaired scan data includes: The target image is obtained by reconstructing the image based on the metal image and the second post-repair scan data.

5. The method as described in claim 1, characterized in that, The step of performing bone-related second repair on the first repaired scan data based on the bone image to obtain second repaired scan data includes: The bone image is orthographically projected to obtain a bone projection image; The second repair is performed on the first repaired scan data based on the bone projection image to obtain the second repaired scan data.

6. The method as described in claim 5, characterized in that, The step of performing the second repair on the first repaired scan data based on the bone projection image to obtain the second repaired scan data includes: The bone data in the bone projection image is added to the missing bone data area of ​​the first repaired scan data according to a preset ratio to obtain the second repaired scan data.

7. The method as described in claim 6, characterized in that, The preset ratio is related to the degree of missing bone data in the first post-repair scan data.

8. The method as described in claim 1, characterized in that, The first repair was performed using interpolation.

9. A medical image processing system, comprising a data acquisition module, a first reconstruction module, a first repair module, an image segmentation module, a second repair module, and a second reconstruction module; The data acquisition module is used to acquire the original scan data of the scanned object; The first reconstruction module is used to perform image reconstruction on the original scan data to obtain a reconstructed image, wherein, The reconstructed image contains metallic artifacts; The first repair module is used to perform a first repair on the original scan data based on the reconstructed image to remove the metal artifacts and obtain the first repaired scan data; The image segmentation module is used to segment the reconstructed image to obtain the skeletal image of the scanned object; The second repair module is used to perform bone-related second repair on the first repaired scan data based on the bone image to obtain second repaired scan data; The second reconstruction module is used to reconstruct the target image based on the second repaired scan data.

10. A medical image processing system, comprising: Medical imaging equipment, configured to perform medical scans on the object being scanned; and The processor is configured to acquire raw scan data of the scanned object from the medical imaging device to perform the method of any one of claims 1 to 8.

Images