A medical image processing method, system, processing device and storage medium

Abstract

Embodiments of the present specification provide a medical image processing method, system, processing device and storage medium. The method comprises: acquiring at least two CT images of a region of interest, the at least two CT images respectively corresponding to at least two motion phase; determining a target pixel value according to a maximum pixel value and a minimum pixel value of at least two pixel values corresponding to the same position in the at least two CT images; obtaining a target image of the region of interest based on the target pixel value; and performing attenuation correction on a PET image based on the target image.

Description

Technical Field

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

[0002] Positron emission tomography / computed tomography (PET / CT) is an advanced medical imaging technique that combines functional metabolic imaging (PET) and anatomical imaging (CT). Taking myocardial perfusion imaging as an example, CT-based attenuation correction (CTAC) images can be generated from CT images acquired over multiple respiratory cycles, which can then be used to attenuate PET images. However, CTAC images may contain noise and motion artifacts, affecting the attenuation correction effect on PET images.

[0003] Therefore, it is necessary to provide a medical image processing method to reduce noise and motion artifacts in CATC images, thereby improving the accuracy of attenuation correction for PET images. Summary of the Invention

[0004] This specification provides one or more embodiments of a medical image processing method, the method comprising: acquiring at least two CT images of a region of interest, the at least two CT images corresponding to at least two motion phases; determining a target pixel value based on the maximum and minimum pixel values ​​of at least two pixel values ​​corresponding to the same location in the at least two CT images; obtaining a target image of the region of interest based on the target pixel value; and performing attenuation correction on a PET image based on the target image.

[0005] This specification provides one or more embodiments of a medical image processing system, the system comprising: an image acquisition module for acquiring at least two CT images of a region of interest, the at least two CT images corresponding to at least two motion phases; a target pixel value determination module for determining a target pixel value based on the maximum and minimum pixel values ​​of at least two pixel values ​​corresponding to the same location in the at least two CT images; a target image acquisition module for obtaining a target image of the region of interest based on the target pixel value; and attenuation correction of a PET image based on the target image.

[0006] One or more embodiments of this description improve a medical image processing apparatus, the apparatus including at least one storage medium storing computer instructions; and at least one processor executing the computer instructions to implement a medical image processing method.

[0007] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes a medical image processing method. Attached Figure Description

[0008] 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:

[0009] Figure 1 These are schematic diagrams illustrating application scenarios of a medical image processing system according to some embodiments of this specification;

[0010] Figure 2 These are exemplary block diagrams of medical image processing according to some embodiments of this specification;

[0011] Figure 3 This is an exemplary flowchart of medical image processing according to some embodiments of this specification;

[0012] Figure 4 This is an exemplary flowchart illustrating the determination of a target pixel value based on harmonic pixel values ​​according to some embodiments of this specification;

[0013] Figure 5 This is an exemplary flowchart illustrating the determination of target pixel values ​​based on line fitting according to some embodiments of this specification;

[0014] Figure 6 This is a schematic diagram illustrating the determination of target pixel values ​​based on harmonic pixel values ​​according to some embodiments of this specification;

[0015] Figure 7 This is a schematic diagram illustrating the determination of target pixel values ​​based on linear fitting according to some embodiments of this specification. Detailed Implementation

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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.

[0020] Figure 1 This is a schematic diagram illustrating the application scenarios of a medical image processing system according to some embodiments of this specification.

[0021] In some embodiments, such as Figure 1 As shown, the medical image processing system 100 may include an imaging device 110, a processing device 120, a terminal device 130, a network 140, and a storage device 150. The components of the medical image processing system 100 may be connected in one or more ways. This is merely an example. Figure 1 As shown, imaging device 110 can be connected to processing device 120 via network 140. Alternatively, imaging device 110 can be directly connected to processing device 120 (as indicated by the dashed double-headed arrow connecting imaging device 110 and processing device 120). As a further example, storage device 150 can be connected to processing device 120 directly or via network 140. As a further example, terminal device 130 can be directly (as indicated by the dashed double-headed arrow connecting terminal device 130 and processing device 120) and / or via network 140 to processing device 120.

[0022] Imaging device 110 can acquire images of the object being scanned. In some embodiments, the object being scanned may include, but is not limited to, the human body, organs, organisms, damaged areas, tumors, objects, phantoms, etc. In some embodiments, imaging device 110 may include a multimodal imaging device, such as a positron emission tomography / computed tomography (PET / CT) scanning device. Another example is a single-photon emission tomography / computed tomography (SPECT / CT) scanning device. In some embodiments, imaging device 110 can scan the object to acquire PET images, SPECT images, and CT images of the object. In some embodiments, imaging device 110 may include a single-modal imaging device, such as a PET device for scanning the object to acquire PET images, a SPECT device for scanning the object to acquire SPECT images, or a CT device for scanning the object to acquire CT images.

[0023] Processing device 120 can process data and / or information acquired from imaging device 110, terminal device 130, and / or storage device 150. For example, processing device 120 can acquire scan data from imaging device 110 and determine corresponding CT images based on the scan data. Alternatively, processing device 120 can determine target images based on CT images. In some embodiments, processing device 120 may include a central processing unit (CPU), digital signal processor (DSP), system-on-a-chip (SoC), microcontroller unit (MCU), and / or any combination thereof. In some embodiments, processing device 120 may include a computer, user console, a single server, or a group of servers. The server group may be centralized or distributed. In some embodiments, processing device 120 may be local or remote. For example, processing device 120 may access information and / or data stored in imaging device 110, terminal device 130, and / or storage device 150 via network 140. Alternatively, processing device 120 may directly connect to imaging device 110, terminal device 130, and / or storage device 150 to access stored information and / or data. In some embodiments, the processing device 120 may be implemented on a cloud platform. By way of example only, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multi-cloud, etc., or any combination thereof. In some embodiments, the processing device 120 or a portion thereof may be integrated into the imaging device 110.

[0024] Terminal device 130 can display CT images to a user and / or receive user input. Terminal device 130 may include mobile device 131, tablet computer 132, laptop computer 133, etc., or any combination thereof. In some embodiments, terminal device 130 may be part of processing device 120.

[0025] Network 140 may include any suitable network that facilitates the exchange of information and / or data between the medical image processing system 100 and the medical image processing system 100. In some embodiments, one or more components of the medical image processing system 100 (e.g., imaging device 110, processing device 120, terminal device 130, storage device 150) may communicate information and / or data with one or more other components of the medical image processing system 100 via network 140. In some embodiments, network 140 may be and / or include public networks, private networks, wide area networks (WANs), wired networks, wireless networks, cellular networks, frame relay networks, virtual private networks, satellite networks, telephone networks, routers, hubs, switches, and any combination thereof. In some embodiments, network 140 may include one or more network access points. For example, network 140 may include wired and / or wireless network access points such as base stations and / or internet switching points, through which one or more components of the medical image processing system 100 may connect to network 140 to exchange data and / or information.

[0026] Storage device 150 can store data, instructions, and / or any other information. In some embodiments, storage device 150 can store data acquired from imaging device 110, terminal device 130, and / or processing device 120. In some embodiments, storage device 150 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), and any combination thereof. In some embodiments, storage device 150 may be implemented on a cloud platform. In some embodiments, storage device 150 may be connected to network 140 to communicate with one or more other components of medical image processing system 100 (e.g., imaging device 110, processing device 120, terminal device 130). One or more components of medical image processing system 100 may access the data or instructions stored in storage device 150 via network 140. In some embodiments, storage device 150 may be directly connected to or communicate with one or more other components of medical image processing system 100 (e.g., imaging device 110, processing device 120, storage device 150, terminal device 130). In some embodiments, storage device 150 may be part of processing device 120.

[0027] 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. However, these changes and modifications will not depart from the scope of this specification.

[0028] Figure 2 These are exemplary block diagrams of a medical image processing system according to some embodiments of this specification. Figure 2 As shown, the medical image processing system 200 may include an image acquisition module 210, a target pixel value determination module 220, a target image acquisition module 230, and an image correction module 240.

[0029] The image acquisition module 210 can be used to acquire at least two CT images of the region of interest. In some embodiments, the at least two CT images may each correspond to at least two motion phases. A detailed description of the image acquisition module 210 can be found in the relevant description of step 310, and will not be repeated here.

[0030] The target pixel value determination module 220 can be used to determine the target pixel value based on the maximum and minimum pixel values ​​of at least two pixel values ​​corresponding to the same location in at least two CT images.

[0031] In some embodiments, the target pixel value determination module 220 may perform one or more of the following operations: determining the maximum pixel value, minimum pixel value, and average pixel value of at least two pixel values ​​corresponding to the same location in at least two CT images; determining a corresponding harmonic pixel value based on the maximum and minimum pixel values ​​corresponding to each location; and determining a corresponding target pixel value based on the harmonic pixel value and average pixel value corresponding to each location. In some embodiments, the target pixel value determination module 220 may perform one or more of the following operations: determining a first coefficient corresponding to the maximum pixel value and a second coefficient corresponding to the minimum pixel value; and determining the corresponding harmonic pixel value based on the maximum pixel value, minimum pixel value, first coefficient, and second coefficient corresponding to each location. In some embodiments, the target pixel value determination module 220 may perform one or more of the following operations: determining a third coefficient corresponding to the harmonic pixel value and a fourth coefficient corresponding to the average pixel value; and determining a corresponding target pixel value based on the harmonic pixel value, average pixel value, third coefficient, and fourth coefficient corresponding to each location.

[0032] In some embodiments, the target pixel value determination module 220 may perform one or more of the following operations: fitting at least two pixel values ​​corresponding to the same location in at least two CT images; determining the maximum fitted pixel value for each location based on the fitting result; and determining the corresponding target pixel value based on the maximum fitted pixel value. In some embodiments, the fitting may include linear fitting. In some embodiments, the target pixel value determination module 220 may determine a fifth coefficient corresponding to the maximum fitted pixel value; and determine the corresponding target pixel value based on the maximum fitted pixel value and the fifth coefficient for each location.

[0033] For a detailed description of the target pixel value determination module 220, please refer to the relevant description of step 320, which will not be repeated here.

[0034] The target image acquisition module 230 can be used to obtain a target image of the region of interest based on the target pixel values. A detailed description of the target image acquisition module 230 can be found in the relevant description of step 330, and will not be repeated here.

[0035] The image correction module can perform attenuation correction on the PET image based on the target image. A detailed description of the image correction module 240 can be found in the relevant description of step 340, and will not be repeated here.

[0036] Figure 3 This is an exemplary flowchart of a medical image processing method according to some embodiments of this specification. In some embodiments, process 300 can be executed by medical image processing system 200 (e.g., processing device 120). For example, process 300 can be stored in a storage device (e.g., storage device 150, system storage unit) in the form of a program or instructions, and process 300 can be implemented when processing device 120 or medical image processing system 200 executes the instructions. The operational schematic diagram of process 300 presented below is illustrative. In some embodiments, the process can be accomplished using one or more additional operations not described and / or one or more operations not discussed. Additionally, Figure 3 The order of operations shown in the diagram and described below in process 300 is not restrictive.

[0037] Step 310: Acquire at least two CT images of the region of interest. Specifically, step 310 can be performed by the image acquisition module 210.

[0038] The region of interest can be a specific part of the scanned object. For example, the scanned object can be patient A, and the region of interest can be patient A's heart.

[0039] CT images can be images of regions of interest acquired by imaging equipment. In some embodiments, the format of CT images may include, but is not limited to, Joint Photographic Experts Group (JPEG) format, Tagged ImageFile Format (TIFF) format, Graphics Interchange Format (GIF) format, Kodak Flash PiX (FPX) format, Digital Imaging and Communications in Medicine (DICOM) format, etc. In some embodiments, CT images can be 2D images or 3D images.

[0040] In some embodiments, the image acquisition module 210 can acquire scan data of a region of interest based on an imaging device, and then reconstruct a CT image of the region of interest based on the scan data according to a reconstruction algorithm. In some embodiments, the reconstruction algorithm may include, but is not limited to, analytical reconstruction algorithms, iterative reconstruction algorithms, etc.

[0041] Acquisition time can be the time it takes for the imaging device to acquire each set of scan data corresponding to each CT image.

[0042] In some embodiments, each phase of motion may correspond to a physiological motion phase of the scanned object. Physiological motion may include respiratory motion, cardiac motion, etc. For example, each phase of motion may correspond to a respiratory phase of the scanned object, such as end-expiration, end-inspiration, etc. As another example, each phase of motion may correspond to a cardiac motion phase of the scanned object, such as diastole, systole, etc.

[0043] In some embodiments, dynamic CT images (e.g., cinematic CT images) of the region of interest can be acquired, including at least two CT images, each corresponding to at least two motion phases. For example, each CT image may correspond to one motion phase. As an example, the image acquisition module 210 may sequentially acquire the first set of scan data, the second set of scan data, ..., the Nth set of scan data of the patient's heart using an imaging device in the first motion phase, the second motion phase, ..., the Nth motion phase, and then generate the corresponding first CT image, second CT image, ..., the Nth CT image according to the reconstruction algorithm.

[0044] In some embodiments, gating techniques, such as respiratory gating or cardiac gating, can be used to acquire the at least two CT images. It is understood that other methods can also be used to acquire the at least two CT images, and this application does not limit this approach.

[0045] In some embodiments, the imaging device used to scan and acquire the at least two CT images of the region of interest can be imaging device 110 or other imaging devices.

[0046] Step 320: Determine the target pixel value based on the maximum and minimum pixel values ​​of at least two pixel values ​​corresponding to the same location in at least two CT images. Specifically, step 320 can be performed by the target pixel value determination module 220.

[0047] The same location in at least two CT images can be a pixel location in the same row and column of at least two CT images. For example, the pixel location in the first row and first column of the first CT image, the second CT image, ..., the Nth CT image is a common location W1 in the first CT image, the second CT image, ..., the Nth CT image. It can be understood that if each CT image includes k pixels, then at least two CT images each contain k corresponding common locations.

[0048] The target pixel value can be the corresponding pixel value in the target image. For a detailed description of the target image, please refer to step 330, which will not be repeated here.

[0049] In some embodiments, the target pixel value determination module 220 may determine the target pixel value based on the harmonic pixel value. For a detailed description of determining the target pixel value based on the harmonic pixel value, please refer to... Figure 4 The details and related descriptions will not be repeated here.

[0050] In some embodiments, the target pixel value determination module 220 may determine the target pixel value based on fitting. For a detailed description of determining the target pixel value based on fitting, please refer to... Figure 5 The details and related descriptions will not be repeated here.

[0051] Step 330: Based on the target pixel values, obtain the target image of the region of interest. Specifically, step 330 can be executed by the target image acquisition module 230.

[0052] The target image may be a CT image used for attenuation correction of PET and / or SPECT images. In some embodiments, the target image acquisition module 230 may use the target pixel value at each location as the pixel value on the target image to obtain the target image of the region of interest.

[0053] For example, the target pixel value P corresponding to position W1, position W2, position W3... position Wk. W1 P W2 P W3 …P Wk The target image of the region of interest is obtained by using the pixel values ​​on the target image.

[0054] In some embodiments of this specification, the maximum pixel is harmonized using the minimum pixel value, and the target pixel value is determined based on the harmonized pixel value (i.e., the harmonized pixel value), thereby mitigating the problems of over-restoration and excessive noise in the generated target image caused by the maximum pixel value.

[0055] Step 340: Based on the target image, perform attenuation correction on the PET image. Specifically, step 340 can be performed by the image correction module 240.

[0056] PET images are reconstructed by detecting rays emitted from the human body, revealing the metabolic state of various tissues. However, the accuracy of these rays is affected by scattering and attenuation as they pass through human tissue. Therefore, attenuation correction is necessary to obtain a corrected PET image. In some embodiments, the PET image of the region of interest can be obtained by scanning the region of interest using imaging device 110, or by scanning the region of interest using other imaging devices.

[0057] In some embodiments, the image correction module 240 can obtain the attenuation coefficient in the PET image based on the CTAC image (i.e., the target image) to perform attenuation correction on the PET image. For example, the attenuation coefficient can be multiplied by the PET image to obtain the corrected PET image. Since the CT radiation energy is different from the PET radiation energy, it is necessary to convert the attenuation coefficient obtained from the CT energy to the attenuation coefficient under the PET energy.

[0058] In some embodiments, the method for attenuation correction of PET images based on target images may include scaling, segmentation, bilinear and dual-energy methods, etc., and this application does not limit the scope of the method.

[0059] In some embodiments, the image correction module 240 can also correct the SPECT image based on the target image. The method for correcting the SPECT image based on the target image can be found in the method for correcting PET images, and will not be described again here.

[0060] It should be noted that the above description of process 300 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 description herein. However, these changes and modifications do not depart from the scope of this specification. In some embodiments, process 300 may include one or more additional operations, or one or more of the aforementioned operations may be omitted.

[0061] Figure 4This is an exemplary flowchart illustrating the determination of a target pixel value based on harmonic pixel values ​​according to some embodiments of this specification. In some embodiments, process 400 may be executed by medical image processing system 200 (e.g., target pixel value determination module 220) or processing device 120. For example, process 400 may be stored in a storage device (e.g., storage device 150, system storage unit) in the form of a program or instructions, and process 400 may be implemented when processing device 120 or medical image processing system 200 executes the instructions. The operational schematic diagram of process 400 presented below is illustrative. In some embodiments, the process may be accomplished using one or more additional operations not described and / or one or more operations not discussed. Additionally, Figure 4 The order of operations of process 400 shown and described below is not limiting. In some embodiments, process 400 may be performed by target pixel value determination module 220.

[0062] Step 410: Determine the maximum pixel value, minimum pixel value, and average pixel value of at least two pixel values ​​corresponding to the same location in at least two CT images.

[0063] Figure 6 This is a schematic diagram illustrating the determination of target projection values ​​based on harmonic pixel values, according to some embodiments of this specification. For example, such as... Figure 6 As shown, the target pixel value determination module 220 can determine the position W1 (not shown) in the first CT image S1, the second CT image S2, the third CT image S3...the Nth CT image S... N The corresponding pixel value Maximum pixel value (For example, Minimum pixel value (For example, Average pixel value for Similarly, the target pixel value determination module 220 can determine the positions W2, W3...Wk in the first CT image S1, the second CT image S2, the third CT image S3...the Nth CT image S... N The maximum pixel values ​​in the corresponding pixel values ​​are respectively The minimum pixel values ​​are respectively The average pixel values ​​are respectively

[0064] Step 420: Determine the corresponding harmonic pixel value based on the maximum pixel value and the minimum pixel value corresponding to each position.

[0065] The pixel value can be obtained by harmonizing the maximum and minimum pixel values.

[0066] In some embodiments, the target pixel value determination module 220 can determine a first coefficient corresponding to the maximum pixel value and a second coefficient corresponding to the minimum pixel value.

[0067] The first coefficient corresponding to the maximum pixel value and the second coefficient corresponding to the minimum pixel value can be coefficients used to adjust the ratio of the maximum and minimum pixel values ​​in the harmonic pixel value. In some embodiments, the first and second coefficients can be decimals between 0 and 1.

[0068] In some embodiments, the first and second coefficients can be determined based on actual conditions, for example, based on the image quality of at least two CT images (e.g., a combination of at least one or more of signal-to-noise ratio, noise intensity, artifact intensity, resolution, contrast, and sharpness). For example, when the image quality of the CT image is poor, a smaller first coefficient and / or a larger second coefficient can be set to reduce the proportion of the maximum pixel value in the harmonic pixel value, thereby reducing noise in the target image. For example, the first coefficient is 0.25 and the second coefficient is 0.75.

[0069] In some embodiments, the target pixel value determination module 220 may use a first image quality assessment model to determine a first coefficient and a second coefficient based on at least two CT images.

[0070] Specifically, the first image quality assessment model can first extract the first quality features of at least two CT images, and then map the first quality features into a first coefficient and / or a second coefficient.

[0071] In some embodiments, the first quality feature of a CT image may be a combination of at least one or more of signal-to-noise ratio, noise intensity, artifact intensity, resolution, contrast, and sharpness.

[0072] In some embodiments, the first image quality assessment model may be, but is not limited to, one or more combinations of Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short Term Memory Network (LSTM).

[0073] For example, when the signal-to-noise ratio of the CT image extracted by the first image quality assessment model is low, a smaller first coefficient and / or a larger second coefficient can be output to reduce the proportion of the maximum pixel value in the harmonic pixel value and reduce noise in the target image. For example, the first coefficient is 0.25 and the second coefficient is 0.75.

[0074] In some embodiments, a first image quality assessment model can be trained based on a large number of first training samples bearing a first identifier. Specifically, the first training samples bearing the first identifier are input into the first image quality assessment model, and the parameters of the first image quality assessment model are updated through training. In some embodiments, the first training samples may include at least two historical CT images corresponding to at least two historical acquisition times. In some embodiments, the first identifier may be a first annotation coefficient and / or a second annotation coefficient manually annotated based on the first training samples.

[0075] In some embodiments, the target pixel value determination module 220 may receive a first coefficient and / or a second coefficient input by the user from the terminal device 130.

[0076] In some embodiments, at least one of the first coefficient and the second coefficient can be a fixed value. For example, the second coefficient can be set to a fixed value, such as 0.5, while the first coefficient can be determined according to the actual situation (e.g., CT image quality), for example, a value range of 0–0.5, 0–0.25, etc. For instance, when the CT image quality is poor, a smaller first coefficient can be set to reduce the proportion of the maximum pixel value in the harmonic pixel value, thereby reducing noise in the target image. For example, the first coefficient can be 0.1.

[0077] In some embodiments, the target pixel value determination module 220 can determine the corresponding harmonic pixel value based on the maximum pixel value, minimum pixel value, first coefficient, and second coefficient corresponding to each position. Specifically, the target pixel value determination module 220 can obtain the corresponding harmonic pixel value by summing the product of the maximum pixel value and the first coefficient corresponding to each position with the product of the minimum pixel value and the second coefficient. For example, as Figure 6 As shown, the maximum pixel value corresponding to position W1 (not shown) The product of the first coefficient 0.75 and the minimum pixel value Summing the product of the second coefficient 0.25 and the second coefficient, we can determine the harmonic pixel value corresponding to position W1. Similarly, the target pixel value determination module 220 can obtain the harmonic pixel values ​​corresponding to positions W2, W3...Wk, respectively.

[0078] In some embodiments of this specification, based on a first quality feature of the CT image, the ratio of the maximum and minimum pixel values ​​in the harmonic pixel values ​​is harmonized using a first coefficient and / or a second coefficient. This allows for the automatic determination of harmonic pixel values ​​suitable for different CT images based on CT images with different noise levels, thereby improving the applicability to CT images with different noise levels.

[0079] Step 430: Determine the corresponding target pixel value based on the harmonic pixel value and average pixel value corresponding to each position.

[0080] In some embodiments, the target pixel value determination module 220 may determine a third coefficient corresponding to the harmonic pixel value and a fourth coefficient corresponding to the average pixel value.

[0081] The third coefficient corresponding to the harmonic pixel value and the fourth coefficient corresponding to the average pixel value can be coefficients used to adjust the proportions of the harmonic pixel value and the average pixel value in the harmonic pixel value, respectively. In some embodiments, the third coefficient and the fourth coefficient can be decimals between 0 and 1.

[0082] In some embodiments, the third and fourth coefficients can be determined based on actual conditions, for example, based on the image quality of at least two CT images (e.g., a combination of at least one or more of signal-to-noise ratio, noise intensity, artifact intensity, resolution, contrast, and sharpness). For example, when the CT image quality is poor, a smaller third coefficient and / or a larger fourth coefficient can be set to increase the proportion of the average pixel value in the target pixel value, thereby improving the accuracy of the target image and reducing motion artifacts in the target image. For example, the third coefficient is 0.3 and the fourth coefficient is 0.7.

[0083] In some embodiments, the target pixel value determination module 220 may utilize a second image quality assessment model to determine a third and a fourth coefficient based on at least two CT images. Specifically, the second image quality assessment model may first extract second quality features from at least two CT images, and then map the second quality features to the third and / or fourth coefficients.

[0084] In some embodiments, the second quality feature may be a combination of at least one or more of the following: signal-to-noise ratio, noise intensity, artifact intensity, resolution, contrast, and sharpness.

[0085] For a detailed description of the second quality model, please refer to the relevant description of the first image quality assessment model, which will not be repeated here.

[0086] For example, when the CT image extracted by the second image quality assessment model has low clarity, a smaller third coefficient and / or a larger fourth coefficient can be output to increase the proportion of the average pixel value in the target pixel value, thereby improving the accuracy of the target image and reducing motion artifacts in the target image. For example, the third coefficient is 0.3 and the fourth coefficient is 0.7.

[0087] In some embodiments, a second image quality assessment model can be trained based on a large number of second training samples with second identifiers. Specifically, the second training samples with second identifiers are input into the first image quality assessment model, and the parameters of the second image quality assessment model are updated through training. A detailed description of the second training samples can be found in the relevant description of the first training samples, and will not be repeated here. In some embodiments, the second identifier may include third and / or fourth annotation coefficients manually annotated based on the second training samples.

[0088] In some embodiments, the target pixel value determination module 220 may receive a third coefficient and / or a fourth coefficient input by the user from the terminal device 130.

[0089] In some embodiments, at least one of the third and fourth coefficients can be a fixed value. For example, the third and fourth coefficients can be set to a fixed value, such as 0.5.

[0090] In some embodiments, the target pixel value determination module 220 can determine the corresponding target pixel value based on the harmonic pixel value, average pixel value, third coefficient, and fourth coefficient corresponding to each position. Specifically, the target pixel value determination module 220 can obtain the corresponding target pixel value by summing the product of the harmonic pixel value and the third coefficient corresponding to each position with the product of the average pixel value and the fourth coefficient. For example, continuing with... Figure 6 For example, the harmonic pixel value corresponding to position W1 (not shown) The product of the third coefficient 0.3 and the average pixel value Summing the product of the first and fourth coefficients (0.7) determines the target pixel value at position W1. Similarly, the target pixel value determination module 220 can obtain the target pixel value P corresponding to positions W2, W3...Wk respectively. W2 P W3 …P Wk .

[0091] In some embodiments of this specification, based on the second quality characteristics of the CT image, the proportion of the average pixel value and the harmonic pixel value in the target pixel value is harmonized using a third coefficient and / or a fourth coefficient to ensure that the target pixel value is between the average pixel value and the maximum pixel value. This allows for the automatic determination of target pixel values ​​suitable for different CT images based on CT images of different image qualities, improving the applicability to CT images of different resolutions.

[0092] In some embodiments of this specification, the target pixel value is determined based on the minimum pixel value, the maximum pixel value, and the average pixel value, which alleviates the lack of activity recovery in PET and / or SPECT images based on target image attenuation correction caused by the average value method (i.e., determining the target pixel value based on the average pixel value), while reducing the over-recovery and excessive noise caused by the maximum density method (i.e., determining the target pixel value based on the maximum pixel value).

[0093] Figure 5 This is an exemplary flowchart illustrating the determination of target pixel values ​​based on line fitting according to some embodiments of this specification. In some embodiments, process 500 may be executed by medical image processing system 200 (e.g., target pixel value determination module 220) or processing device 120. For example, process 500 may be stored in a storage device (e.g., storage device 150, system storage unit) in the form of a program or instructions, and process 500 may be implemented when processing device 120 or medical image processing system 200 executes the instructions. The operational schematic diagram of process 500 presented below is illustrative. In some embodiments, the process may be accomplished using one or more additional operations not described and / or one or more operations not discussed. Additionally, Figure 5 The order of operations of process 500 shown and described below is not limiting. In some embodiments, process 500 may be performed by target pixel value determination module 220.

[0094] Step 510: Fit at least two pixel values ​​corresponding to the same location in at least two CT images.

[0095] In some embodiments, fitting may include linear fitting. Specifically, in some embodiments, the target pixel value determination module 220 may perform linear fitting on at least two pixel values ​​corresponding to the same location in at least two CT images, thereby obtaining multiple straight lines corresponding to multiple locations.

[0096] Figure 7 This is a schematic diagram illustrating the determination of target pixel values ​​based on linear fitting, according to some embodiments of this specification. For example... Figure 7 As shown, the coordinate system for linear fitting can use the index of the motion phase as the abscissa and the pixel value corresponding to any position on the CT image for each motion phase as the ordinate. For example, the N pixel values ​​(represented by hollow dots in the figure) corresponding to position W1 (not shown) in N CT images across N motion phases can be: d1, d2, d3, d4, d5, ... d N Perform line fitting to obtain line segment L1 corresponding to position W1. Similarly, for each of the k positions, perform line fitting on the N pixel values ​​corresponding to the N images to obtain k line segments corresponding to the k positions: L1, L2, L3…L… k.

[0097] In some embodiments of this specification, linear fitting is used to better distribute different CT images corresponding to the same location at both ends of a straight line. That is, the values ​​of multiple pixels are harmonized using a straight line, thereby reducing the impact of the target pixel value on noise in the target image when the maximum fitted pixel value is subsequently obtained based on the linear fitting. A detailed description of the maximum fitted pixel value can be found in step 520, and will not be repeated here.

[0098] In some embodiments, fitting may further include curve fitting. Similar to straight-line fitting, in some embodiments, the target pixel value determination module 220 can fit at least two pixel values ​​corresponding to the same location in at least two CT images into a curve, thereby obtaining multiple curve segments corresponding to multiple locations.

[0099] Step 520: Based on the fitting results, determine the maximum fitted pixel value for each position.

[0100] The fitted pixel value can be the pixel value corresponding to each CT image in each fitted result.

[0101] Continue with Figure 7 For example, the fitted pixel values ​​can include the pixel values ​​(represented by solid dots) corresponding to N CT images on the fitted result (i.e., line segment L1) at position W1 (not shown): e1, e2, e3, e4, e5, ... e N Similarly, the fitted pixel values ​​can include k fitted results corresponding to k positions (i.e., line segments L1, L2, L3…L…). k The pixel values ​​corresponding to N CT images are shown on the image.

[0102] Similar to fitting line segments, in some embodiments, the fitted pixel values ​​can be the pixel values ​​corresponding to each CT image on each fitted curve segment.

[0103] The maximum fitted pixel value at a certain location can be the maximum value among at least two fitted pixel values ​​in the corresponding fitting results of at least two CT images.

[0104] In some embodiments, the target pixel value determination module 220 can determine the maximum fitted pixel value for each location based on the maximum value among the fitted pixel values ​​corresponding to each fitted line segment in at least two CT images. For example, the maximum fitted pixel value for a certain location can be the fitted pixel value corresponding to an endpoint on the corresponding fitted line segment (such as the endpoint corresponding to the first CT image or the endpoint corresponding to the Nth CT image).

[0105] Continue with Figure 7For example, the maximum fitted pixel value M1 corresponding to position W1 (not shown) can be the fitted pixel values ​​e1, e2, e3, e4, e5, ... e1 corresponding to the fitted line L1 of N CT images. N The maximum value e1 in the set is the fitted pixel value corresponding to the first CT image. Similarly, the maximum fitted pixel values ​​M2, M3, ..., Mk corresponding to positions W2, W3...Wk can be obtained. k .

[0106] Similar to fitting a straight line, in some embodiments, the target pixel value determination module 220 can determine the maximum fitted pixel value for each location based on the maximum value among the fitted pixel values ​​corresponding to each fitted curve segment from at least two CT images. For example, the maximum fitted pixel value for each location could be the fitted pixel value closest to the vertex of the corresponding fitted curve segment.

[0107] In some embodiments of this specification, the fitted maximum pixel value obtained by fitting approximates the trend of all pixels corresponding to the same position, such that the fitted maximum pixel value is harmonized based on the maximum pixel value, the minimum pixel value, and the average pixel value.

[0108] Step 530: Determine the corresponding target pixel value based on the fitted maximum pixel value.

[0109] In some embodiments, the target pixel value determination module 220 may determine the fifth coefficient corresponding to the fitted maximum pixel value.

[0110] The fifth coefficient can be a coefficient used to adjust the ratio between the fitted maximum pixel value and the target pixel value. Specifically, in some embodiments, the target pixel value determination module 220 may use the fifth coefficient as a decimal between 0 and 1.

[0111] In some embodiments, the fifth coefficient can be determined based on the actual situation, for example, it can be determined based on the image quality of at least two CT images (e.g., a combination of at least one or more of signal-to-noise ratio, noise intensity, artifact intensity, resolution, contrast, and sharpness). For example, when the CT image quality is poor, a smaller fifth coefficient can be set to reduce the proportion of the fitted maximum pixel value in the target pixel value, thereby reducing noise in the target image. For example, the fifth coefficient could be 0.4.

[0112] In some embodiments, the target pixel value determination module 220 may utilize a third image quality assessment model to determine a fifth coefficient based on at least two CT images. Specifically, the third image quality assessment model may first extract third quality features from at least two CT images, and then map the third quality features to the fifth coefficient.

[0113] For a detailed description of the third quality feature, please refer to the relevant description of the first quality feature; it will not be repeated here. For a detailed description of the third quality model, please refer to the relevant description of the first image quality assessment model; it will not be repeated here.

[0114] For example, when the signal-to-noise ratio of the CT image extracted by the third image quality assessment model is low, a smaller fifth coefficient can be output, thereby reducing the proportion of the fitted maximum pixel value in the target pixel value and reducing noise in the target image. For example, the fifth coefficient can be 0.4.

[0115] In some embodiments, a third image quality assessment model can be trained based on a large number of third training samples with third identifiers. Specifically, the third training samples with third identifiers are input into the third image quality assessment model, and the parameters of the third image quality assessment model are updated through training. A detailed description of the third training samples can be found in the relevant description of the first training samples, and will not be repeated here. In some embodiments, the third identifier may include a fifth manually labeled coefficient based on manually labeled third training samples.

[0116] In some embodiments, the target pixel value determination module 220 may receive a fifth coefficient input by the user from the terminal device 130.

[0117] In some embodiments, the fifth coefficient can be a fixed value, for example, 2 / 3.

[0118] Furthermore, in some embodiments, the target pixel value determination module 220 can determine the corresponding target pixel value based on the fitted maximum pixel value and the fifth coefficient corresponding to each position.

[0119] Specifically, the target pixel determination module 220 can multiply the fitted maximum pixel value corresponding to each position by the fifth coefficient to determine the corresponding target pixel value. For example, multiplying the fitted maximum pixel value M1 corresponding to position W1 by the fifth coefficient 0.8 determines the target pixel value P′ corresponding to position W1. W1 =0.8M1. Similarly, the target pixel value determination module 220 can obtain the target pixel value P′ corresponding to position W2, position W3...position Wk respectively. W2 、P′ W3 …P′ Wk .

[0120] In some embodiments of this specification, the proportion of the fitted maximum pixel value in the target pixel value is adjusted based on the fifth coefficient, thereby automatically determining the target pixel value suitable for different CT images based on CT images with different noise levels, further improving the applicability to CT images with different noise levels.

[0121] The beneficial effects that the embodiments of this specification may bring include, but are not limited to: (1) harmonizing the minimum pixel value, the maximum pixel value and the average pixel value to determine the target pixel value, and obtaining the target image based on the target pixel value, which alleviates the lack of activity recovery of PET images and / or SPECT images based on target image attenuation correction caused by the average value method (i.e., determining the target pixel value based on the average pixel value), and at the same time reduces the over-recovery and excessive noise caused by the maximum density method (i.e., determining the target pixel value based on the maximum pixel value); (2) determining the first coefficient, the second coefficient, the third coefficient, the fourth coefficient and / or the fifth coefficient according to the different quality characteristics of CT images (such as the first quality characteristic, the second quality characteristic and / or the third quality characteristic), thereby adjusting the proportion of the maximum pixel value, the minimum pixel value and / or the average pixel value in the target pixel value, thereby automatically determining the target pixel value suitable for different CT images based on CT images of different quality, and improving the applicability to CT images of different quality; (3) the fitted maximum pixel value obtained by the fitting method approximates the trend of all pixels corresponding to the same position, so that the fitted maximum pixel value is harmonized based on the maximum pixel value, the minimum pixel value and the average pixel value.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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, characterized in that, include: Acquire at least two CT images of the region of interest, wherein the at least two CT images correspond to at least two motion phases; The target pixel value is determined based on the maximum and minimum pixel values ​​of at least two pixel values ​​corresponding to the same location in the at least two CT images; Based on the target pixel values, the target image of the region of interest is obtained; Based on the target image, attenuation correction is performed on the PET image; The step of determining the target pixel value based on the maximum and minimum pixel values ​​of at least two pixel values ​​corresponding to the same location in the at least two CT images includes: Fit the values ​​of at least two pixels at the same location in the at least two CT images; Based on the fitting results, determine the maximum fitted pixel value for each position; Based on the fitted maximum pixel value, the corresponding target pixel value is determined.

2. The method as described in claim 1, characterized in that, Determining the target pixel value based on the maximum and minimum pixel values ​​of at least two pixel values ​​corresponding to the same location in the at least two CT images includes: Determine the maximum pixel value, minimum pixel value, and average pixel value of at least two pixel values ​​corresponding to the same location in the at least two CT images; Based on the maximum and minimum pixel values ​​corresponding to each position, determine the corresponding harmonic pixel value; The corresponding target pixel value is determined based on the harmonic pixel value and the average pixel value corresponding to each position.

3. The method as described in claim 2, characterized in that, The step of determining the corresponding harmonic pixel value based on the maximum and minimum pixel values ​​corresponding to each position includes: Determine the first coefficient corresponding to the maximum pixel value and the second coefficient corresponding to the minimum pixel value; The corresponding harmonic pixel value is determined based on the maximum pixel value, the minimum pixel value, the first coefficient, and the second coefficient corresponding to each position.

4. The method as described in claim 2, characterized in that, Determining the corresponding target pixel value based on the harmonic pixel value and the average pixel value corresponding to each position includes: Determine the third coefficient corresponding to the harmonic pixel value and the fourth coefficient corresponding to the average pixel value; The corresponding target pixel value is determined based on the harmonic pixel value, the average pixel value, the third coefficient, and the fourth coefficient for each position.

5. The method as described in claim 1, characterized in that, Determining the corresponding target pixel value based on the fitted maximum pixel value includes: Determine the fifth coefficient corresponding to the maximum fitted pixel value; The corresponding target pixel value is determined based on the fitted maximum pixel value and the fifth coefficient for each position.

6. The method as described in claim 1, characterized in that, The fitting includes linear fitting.

7. A medical image processing system, characterized in that, include: The image acquisition module is used to acquire at least two CT images of the region of interest, wherein the at least two CT images correspond to at least two motion phases, respectively; The target pixel value determination module is used to determine the target pixel value based on the maximum and minimum pixel values ​​of at least two pixel values ​​corresponding to the same position in the at least two CT images; The target image acquisition module is used to obtain the target image of the region of interest based on the target pixel values; An image correction module is used to perform attenuation correction on the PET image based on the target image; The target pixel value determination module is further configured to: Fit the values ​​of at least two pixels at the same location in the at least two CT images; Based on the fitting results, determine the maximum fitted pixel value for each position; Based on the fitted maximum pixel value, the corresponding target pixel value is determined.

8. A medical image processing device, characterized in that, The device includes: At least one storage medium that stores computer instructions; At least one processor executes the computer instructions to implement the medical image processing method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing computer instructions that, when read by a computer, execute the medical image processing method as described in any one of claims 1 to 6.

Images