Medical image processing method and device and medical equipment

Abstract

The embodiment of the invention provides a medical image processing method and device and medical device.The medical image processing method comprises the steps that original projection data obtained after a to-be-detected object is scanned are obtained, and an original medical image is obtained through reconstruction; performing multi-valued processing on the original medical image to obtain a multi-valued image; according to the corresponding relation between the contribution degree of each tissue on a ray path which does not penetrate through a specific material part in the multi-valued image and the ray absorption amount and the original projection value corresponding to the ray path in the original projection data, the multi-valued image is obtained; determining a predicted projection value of a track corresponding to the specific material part in the original projection data; and obtaining a first medical image according to the predicted projection value and the original projection data.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of medical equipment technology, and in particular, to a medical image processing method, apparatus, and medical equipment. Background Art

[0002] In the process of computed tomography (CT), detectors are used to collect data of X-rays passing through the object to be detected, and then these collected X-ray data are processed to obtain projection data. These projection data can be used to reconstruct CT images. Complete projection data can reconstruct accurate CT images for diagnosis.

[0003] In clinical diagnosis of CT, potential metal implants in the body of the object to be detected (such as tooth fillings, artificial joints, spinal implants, vascular stents, etc.) will cause the loss of tissue-related attenuation coefficients during the X-ray projection process, and cause streaks or shadow-like artifacts to appear in the reconstructed image, which will reduce the quality of the reconstructed image. With the widespread popularity and application of metal implants, Metal Artifact Reduction (MAR) has become a medical image analysis task with high clinical value based on CT systems. Summary of the invention

[0004] Embodiments of the present application provide a medical image processing method, apparatus, and medical equipment.

[0005] According to one aspect of an embodiment of the present application, a medical image processing method is provided, the method comprising:

[0006] Acquire original projection data obtained after scanning the object to be detected, and reconstruct the original medical image;

[0007] Performing multi-value processing on the original medical image to obtain a multi-valued image;

[0008] Determine a predicted projection value of a trajectory corresponding to the specific material part in the original projection data according to a correspondence between a contribution of each tissue related to the radiation absorption amount on a ray path that does not pass through the specific material part in the multi-valued image and an original projection value corresponding to the ray path in the original projection data;

[0009] A first medical image is obtained according to the predicted projection value and the original projection data.

[0010] According to one aspect of an embodiment of the present application, a medical image processing device is provided, the device comprising:

[0011] A first reconstruction unit, which acquires original projection data obtained after scanning the object to be detected, and reconstructs an original medical image;

[0012] A segmentation unit, which performs multi-valued processing on the original medical image to obtain a multi-valued image;

[0013] a first determining unit, which determines a predicted projection value of a trajectory corresponding to a specific material part in the original projection data according to a corresponding relationship between a contribution of each tissue related to the radiation absorption amount on a ray path that does not pass through the specific material part in the multi-valued image and an original projection value corresponding to the ray path in the original projection data;

[0014] A second reconstruction unit is configured to obtain a first medical image according to the predicted projection value and the original projection data.

[0015] According to one aspect of an embodiment of the present application, a medical device is provided, wherein the medical device includes the medical image processing apparatus described in the aforementioned aspect.

[0016] With reference to the following description and accompanying drawings, the specific implementation of the embodiment of the present application is disclosed in detail, indicating the way in which the principle of the embodiment of the present application can be adopted. It should be understood that the implementation of the present application is not limited in scope. Within the scope of the spirit and clauses of the attached claims, the implementation of the present application includes many changes, modifications and equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The included drawings are used to provide a further understanding of the embodiments of the present application, which constitute a part of the specification, are used to illustrate the implementation methods of the present application, and together with the text description, explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other implementation methods can be obtained based on these drawings without creative work. In the drawings:

[0018] Figure 1 is a schematic diagram of CT field of view parameters of an embodiment of the present application;

[0019] Figure 2 is a schematic diagram of a medical image processing method according to an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of an original medical image in an embodiment of the present application;

[0021] Figure 4 is a schematic diagram of a multi-valued image according to an embodiment of the present application;

[0022] Figure 5 is a schematic diagram of the metal artifact removal principle of an embodiment of the present application;

[0023] Figure 6 is a schematic diagram of a method for determining a corresponding relationship in an embodiment of the present application;

[0024] Figure 7 is a schematic diagram of a first medical image in an embodiment of the present application;

[0025] Figure 8 is a schematic diagram of the medical image processing method of an embodiment of the present application;

[0026] Fig. 9 is a schematic diagram of a medical image processing device according to an embodiment of the present application;

[0027] Fig.10 is a schematic diagram of a medical image processing device according to an embodiment of the present application;

[0028] Fig.11 is a schematic diagram of a medical device according to an embodiment of the present application;

[0029] Fig.12 is a schematic diagram of a reconstructed image of a specific material part in an embodiment of the present application;

[0030] Fig.13 It is a schematic diagram of the trajectory of a specific material part in the original projection data of an embodiment of the present application. DETAILED DESCRIPTION

[0031] With reference to the accompanying drawings, the foregoing and other features of the embodiments of the present application will become apparent through the following description. In the description and the accompanying drawings, specific embodiments of the present application are specifically disclosed, which show some embodiments in which the principles of the embodiments of the present application can be adopted. It should be understood that the present application is not limited to the described embodiments. On the contrary, the embodiments of the present application include all modifications, variations and equivalents that fall within the scope of the attached claims.

[0032] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements in terms of title, but do not indicate the spatial arrangement or temporal order of these elements, etc., and these elements should not be limited by these terms. The term "and / or" includes any one and all combinations of one or more of the associated listed terms. The terms "comprising", "including", "having", etc. refer to the presence of the stated features, elements, components or components, but do not exclude the presence or addition of one or more other features, elements, components or components.

[0033] In the embodiments of the present application, the singular forms "a", "the", etc. include plural forms and should be broadly understood as "a kind" or "a type" rather than being limited to the meaning of "one"; in addition, the term "said" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. In addition, the term "according to" should be understood as "at least in part according to...", and the term "based on" should be understood as "at least in part based on...", unless the context clearly indicates otherwise.

[0034] Features described and / or shown for one embodiment may be used in one or more other embodiments in the same or similar manner, combined with features in other embodiments, or replace features in other embodiments. The term "includes / comprising" when used herein refers to the presence of a feature, an entirety, a step, or a component, but does not exclude the presence or addition of one or more other features, entireties, steps, or components.

[0035] The device for obtaining medical imaging data described in this article may be applicable to various medical imaging modalities, including but not limited to computed tomography (CT) equipment or any other suitable medical imaging equipment.

[0036] For example, CT uses X-rays to perform continuous cross-sectional scans around a part of the scanned object. The detector receives the X-rays that pass through that layer and converts them into visible light, or directly converts the received photon signals and performs a series of processing to reconstruct the image. MRI is based on the principle of nuclear magnetic resonance of atomic nuclei. It transmits radio frequency pulses to the scanned object, receives electromagnetic signals released by the scanned object, and reconstructs images.

[0037] The system for obtaining medical images may include the aforementioned medical imaging device, and may also include a separate computer device connected to the medical imaging device, and may also include a computer device connected to the Internet cloud, wherein the computer device is connected to the medical imaging device or a storage device storing medical images via the Internet. The imaging method may be implemented independently or jointly by the aforementioned medical imaging device, the computer device connected to the medical imaging device, and the computer device connected to the Internet cloud.

[0038] In addition, the medical imaging workstation can be set up locally in the medical imaging device, that is, the medical imaging workstation is set up near the medical imaging device, and the medical imaging workstation and the medical imaging device can be co-located in the scanning room, imaging department or the same hospital. The medical image cloud platform analysis system can be located away from the medical imaging device, for example, in the cloud that communicates with the medical imaging device.

[0039] As an example, after a medical institution completes an imaging scan using a medical imaging device, the scanned data is stored in a storage device; a medical imaging workstation can directly read the scanned data and perform image processing through its processor. As another example, a medical image cloud platform analysis system can read medical images in a storage device through remote communication to provide "Software as a Service" (SaaS). SaaS can exist between hospitals, between hospitals and imaging centers, or between hospitals and third-party online diagnosis and treatment service providers.

[0040] In the embodiments of the present application, the term "object to be detected" may include any object to be imaged. The terms "projection data" and "projection image" and "sinogram" may be interchangeable.

[0041] Figure 1 Schematic diagram of the field of view parameters in the CT scan of the embodiment of the present application. Figure 1 As shown, the area of ​​the largest circle 1 represents the circular bore of the rack housing, the area of ​​circle 2 represents the maximum area of ​​valid data that can be collected by the detector, and the area of ​​circle 3 is the area of ​​the image to be reconstructed. The position and size of circle 3 can be adjusted.

[0042] When performing a CT scan, it is usually necessary to set the scan field of view (SFOV) and the display field of view (DFOV, also known as the reconstruction field of view). SFOV is the scanning range set by the CT device itself, corresponding to the area of ​​circle 2. For different inspection parts, an SFOV of appropriate size can be selected, such as 40cm to 50cm. DFOV corresponds to the area of ​​circle 3, which is the display range of the reconstructed image set before the inspection. After the scan is completed, the display field size can be changed to reconstruct the image. Usually, DFOV is less than or equal to SFOV, such as 25cm or 36cm. The smaller the DFOV, the higher the resolution of the reconstructed image. During the scan, the scanned object can be placed in the SFOV, for example, by aligning the center of the scanned object 1 with the center of the SFOV, so that the SFOV covers the scanned object, and the reconstructed image can reflect the complete information of the scanned object. When the scanned object is obese, the center of the scanned object is offset, or the scanned object is in a special posture, for example, part of the scanned object 2 will be outside the SFOV, and the reconstructed image will be truncated. In this case, an extended field of view (EFOV, extended Field of View, also called maximum field of view MaxFOV, corresponding to the area of ​​the circle 1, such as 75 to 80 cm, etc.) algorithm can be used for image reconstruction to complete the truncated data and obtain complete information of the scanned object 2.

[0043] At present, CT metal artifact removal methods are mainly based on the logic of the standard MAR (NMAR, Normalized metal artifact reduction) algorithm, that is, the sinusoidal interpolation method, but the inventors believe that this method still has residual artifacts to be eliminated to a certain extent, such as a black ring-shaped shadow (halo) around the metal, which may be misdiagnosed as a metal fracture; or, blurring problems (blur) may appear on or near the metal, reducing the resolution; or, there may be residual streaks, or even worse streaks may be produced in other areas.

[0044] In response to at least one of the above-mentioned technical problems, an embodiment of the present application provides a medical image processing method, an apparatus and a medical device, which perform multi-valued processing on the original medical image to obtain a multi-valued image; according to the correspondence between the contribution of each tissue related to the radiation absorption amount on the ray path that does not pass through the specific material part in the multi-valued image and the original projection value corresponding to the ray path in the original projection data, the predicted projection value of the trajectory corresponding to the specific material part in the original projection data is determined, thereby further removing metal artifacts in the reconstructed image and significantly improving the image quality.

[0045] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0046] An embodiment of the present application provides a method for medical image processing. Figure 2 is a schematic diagram of a medical image processing method according to an embodiment of the present application. Figure 2 As shown, the method includes:

[0047] 201, acquiring original projection data obtained after scanning the object to be detected, and reconstructing an original medical image;

[0048] 202, performing multi-valued processing on the original medical image to obtain a multi-valued image;

[0049] 203, determining a predicted projection value of a trajectory corresponding to the specific material part in the original projection data according to a correspondence between a contribution of each tissue related to the radiation absorption amount on a ray path that does not pass through the specific material part in the multi-valued image and an original projection value corresponding to the ray path in the original projection data;

[0050] 204. Obtain a first medical image according to the predicted projection value and the original projection data.

[0051] In some embodiments, in 201, the object to be detected is scanned, including but not limited to computed tomography (CT) or any other suitable medical imaging technology, and the data (raw data) collected by the scan is processed to obtain raw projection data (sinogram data). For details, reference may be made to related technologies, which will not be described in detail here. The raw projection data is reconstructed to obtain an original medical image. The image reconstruction algorithm may include, for example, a back projection (FBP) reconstruction method, an adaptive statistical iterative reconstruction (ASIR) method, a conjugate gradient (CG) method, a maximum likelihood expectation maximization (MLEM) method, a model-based iterative reconstruction (MBIR) method, etc. For details, reference may be made to related technologies, and the embodiments of the present application are not limited thereto.

[0052] In some embodiments, the original medical image is an image reconstructed within a first predetermined field of view (DFOV1), and the size of the first predetermined field of view (DFOV1) needs to enable the reconstructed image to include the entire boundary or outline of the object to be detected or the entire boundary or outline of the region of interest of the object to be detected, so as to ensure that the reconstructed original medical image includes the object to be detected, such as a metal implant, and artifacts generated by the metal implant. For example, the size of the first predetermined field of view is the size of the extended imaging field of view EFOV or the maximum imaging field of view MaxFOV, or in other words, for the original projection data, the original medical image is reconstructed using the extended imaging field of view or the maximum imaging field of view algorithm, but the embodiments of the present application are not limited to this, for example, the size of the first predetermined field of view may also be the size of the SFOV, or in other words, for the original projection data, the original medical image is reconstructed within the SFOV, or in other words, in this case, DFOV1 is equal to the SFOV.

[0053] In some embodiments, in 202, the original medical image is multi-valued to obtain a multi-valued image; including: comparing the CT value of each pixel position in the original medical image with multiple thresholds corresponding to the CT values ​​of different types of tissues, and re-determining the pixel value of each pixel position according to the comparison result to obtain the multi-valued image, wherein in the multi-valued image, the pixel values ​​corresponding to different tissues are different, and the pixel values ​​corresponding to the same tissue are the same.

[0054] In some embodiments, the CT value of each pixel position is the corresponding value of the linear attenuation coefficient of the tissue or organ to the radiation (in HU), which can measure the absorption rate of the tissue or organ to the radiation. For example, the CT value of water is usually 0, the CT value of air is usually -1000, the CT value of fat is usually -150 to -50, the CT value of muscle is 40 to 80, the CT value of bone is usually 200 to 3000, and the CT value of metal is usually greater than 4000. That is to say, different tissues in the original medical image can be distinguished according to the different CT values ​​of each tissue. The CT value of each tissue can be referred to the prior art, which is only an example here, and the embodiments of the present application are not limited to this.

[0055] In some embodiments, the threshold values ​​of the CT values ​​of different types of tissues may be the upper and lower limits of a range of values, or may be a single value (an upper limit or a lower limit), for example, the metal threshold value is 4000, the bone threshold value is 200 and 3000, the muscle threshold value is 40 and 80, the fat threshold value is -150 and -50, the air threshold value is -1000, the water threshold value is 0, etc. These are merely examples and the embodiments of the present application are not limited thereto.

[0056] In some embodiments, the thresholds of CT values ​​of different types of tissues are pre-set, and the thresholds of CT values ​​of tissues set for different objects to be detected or for different regions of interest (or organs) may be the same or different, and the embodiments of the present application are not limited thereto. For example, for the head or spine area, the thresholds of CT values ​​of various types of tissues are set as follows: metal threshold (Tm1), bone threshold (Tb1), muscle threshold (Tc1), fat threshold (Tf1), and air threshold (Ta1). For the joint area, the thresholds of CT values ​​of various types of tissues are set as follows: metal threshold (Tm2), bone threshold (Tb2), muscle threshold (Tc2), fat threshold (Tf2), and air threshold (Ta2), which are not listed one by one here.

[0057] In some embodiments, the thresholds of CT values ​​of different types of tissues can be adaptively set according to the object to be detected. For example, the thresholds of CT values ​​of different types of tissues for the object to be detected can be determined based on the CT values ​​of each tissue in the reconstructed image of other slices of the object to be detected that are not contaminated by specific material parts (hereinafter taking metal as an example). For example, the thresholds of CT values ​​of different types of tissues of the object to be detected can be determined based on the average value of the CT values ​​of each tissue in the reconstructed image of the slices of the object to be detected that are not contaminated by specific material parts (hereinafter taking metal as an example). The embodiments of the present application are not limited to this.

[0058] In some embodiments, before the multi-valued processing, it is also necessary to pre-set the pixel value representing each type of tissue in the multi-valued image, or to pre-set the pixel value assigned to each type of tissue in the multi-valued image. In the multi-valued image, different tissues have different pixel values, and the same tissue has the same pixel value (in the same multi-valued image, the radiation absorption coefficient corresponding to the same tissue is the same), or the same pixel value corresponds to the same type of tissue, and different pixel values ​​correspond to different types of tissue. For example, the assigned pixel value can be positively correlated with the CT value of each type of tissue, that is, although the pixel value is not the CT value of each type of tissue, it can reflect the relative magnitude relationship of the linear attenuation coefficient of each type of tissue to radiation. For example, the assigned pixel value can be the threshold of the CT value of the above-mentioned various types of tissue, or the average value of the threshold, or the assigned pixel value can be the radiation absorption coefficient of different tissues or an integral multiple of the absorption coefficient (for example, the muscle absorption coefficient is 1, the bone absorption coefficient is 3, and the fat absorption coefficient is 0.5). This is only an example, and the embodiments of the present application are not limited to this. For example, in a multi-valued image, the pixel value corresponding to metal is assigned to 200, the pixel value corresponding to bone is assigned to 100, the pixel value corresponding to muscle is assigned to 50, the pixel value corresponding to fat is assigned to 20, etc., which will not be described one by one here. The pixel value is a grayscale value. In addition, in order to facilitate the calculation of contribution described later, the pixel value of a specific material part (hereinafter taking metal as an example) can be assigned to 0, but the embodiment of the present application is not limited to this.

[0059] In some embodiments, the CT value of each pixel position in the original medical image is compared with multiple thresholds corresponding to CT values ​​of different types of tissues, and the pixel value of each pixel position is re-determined according to the comparison result to obtain the multi-valued image. For example, the value range of the CT value of each pixel position in the original medical image is determined, that is, the tissue corresponding to the value range can be determined, and the pixel value of the pixel position is re-assigned to a pre-set pixel value representing the tissue in the multi-valued image. In other words, the multi-valued image has the same size and number of pixels as the original medical image, but the pixel value of each pixel position is different. Figure 3 is a schematic diagram of an original medical image in an embodiment of the present application, Figure 4 is a schematic diagram of a multi-valued image in an embodiment of the present application, that is, Figure 3 After multi-valued processing of the original medical image in Figure 4 The multi-valued image shown.

[0060] In an embodiment of the present application, the influence of metal artifacts can be minimized by performing multi-valued processing on the original medical image to obtain a multi-valued image, and using the multi-valued image to predict projection values. This is because the inventors have found that regardless of whether the original medical image contains metal artifacts, the multi-valued image is basically consistent after multi-valued processing. In other words, the multi-valued image is basically not affected by metal artifacts. Therefore, using the multi-valued image for subsequent processing can avoid the influence of metal artifacts to the greatest extent.

[0061] The following first combines Figure 5 The metal artifact removal principle of the embodiment of the present application is described as follows: Figure 5 As shown, the straight line in the figure can be regarded as a ray path, which passes through different tissues in the original medical image (or multi-valued image). If a ray path A does not pass through (goes through) metal, the projection value of the projection position corresponding to the ray path in the original projection data is not affected by the metal, or the projection value is accurate. If a ray path B passes through (goes through) metal, the projection value of the projection position corresponding to the ray path in the original projection data is affected by the metal, or the projection value is inaccurate. According to the projection principle of the original projection data and the original medical image, the projection position corresponding to the ray path can be determined on the sinusoidal graph corresponding to the original projection data (uniquely determined according to the projection angle and the detector channel position, and specific reference can be made to the relevant technology), and the projection value of the projection position is equal to the weighted sum of the pixel values ​​passed by the ray path in the reconstructed image, and the weighting function is the line segment length of the ray path in the pixel. The inventors have found that although the weighted sum of the pixel values ​​(due to being reassigned) passed by the ray path in the multi-valued image is not equal to the projection value, there is also a corresponding relationship (functional relationship) between the contribution of each tissue passed by any ray path in the multi-valued image (the meaning of the contribution will be explained later) and the original projection value of the projection position corresponding to the ray path in the original projection data. That is to say, for each ray path (such as A and B) (assuming that the specific material part does not exist), the corresponding relationship (functional relationship f) is the same. Therefore, the projection value of the projection position corresponding to the ray path passing through the specific material part can be predicted based on the corresponding relationship, and the predicted projection value can be used to replace the original inaccurate projection value, so as to remove the artifacts of the specific material part. It should be noted that the specific material part below in this application takes metal as an example, but this application is not limited to this.

[0062] In some embodiments, before 203, the method further includes: determining a corresponding relationship between a contribution of each tissue on a ray path that does not pass through a specific material portion in the multi-valued image and an original projection value corresponding to the ray path in the original projection data; Figure 6is a schematic diagram of a method for determining the corresponding relationship in an embodiment of the present application, such as Figure 6 As shown, the method includes:

[0063] 601, determining the contribution of each tissue passed through by a plurality of different first ray paths in the multi-valued image and the original projection values ​​of the projection positions corresponding to the plurality of different first ray paths in the original projection data; the first ray path is a ray path that does not pass through the specific material part;

[0064] 602 , obtaining the corresponding relationship by fitting the contribution of each tissue on the plurality of first ray paths and the plurality of original projection values.

[0065] For ease of understanding, the following first describes how to determine a specific material portion and a trajectory corresponding to the specific material portion in the original projection data.

[0066] In some embodiments, determining the location of the specific material part in the original medical image includes: comparing the CT value of each pixel in the original medical image with a preset CT value corresponding to the specific material; and determining the location of the pixel where the CT value is greater than the preset CT value as the specific material part. For example, when the specific material part is metal, the preset CT value may be 4000HU, then Figure 3 In the original medical image shown in FIG. 1 , the area where the pixels with CT values ​​greater than 4000HU are located is determined as a metal part. The CT value of each pixel except the specific material part in the original medical image can be set to 0. In this way, the image except the specific material part can be removed from the original medical image. Fig.12 As shown, an intermediate image including only metal parts is obtained.

[0067] In some embodiments, the position of the specific material part in the original medical image is forward projected to determine the trajectory corresponding to the specific material part in the original projection data. For example, the intermediate image is forward projected into the sine domain space to obtain the projection data of the intermediate image. In this way, the trajectory corresponding to the specific material part can be located in the sinusoidal image data (original projection data), such as Fig.13 As shown, the trajectory corresponding to the specific material part is marked on the sinusoidal graph corresponding to the original projection data.

[0068] In some embodiments, in 601, N different first ray paths may be selected, and the first ray path is a ray path that does not pass through the specific material part. In order to improve the accuracy of the prediction result of the projection value, N first ray paths may be selected, and the distance between the projection position corresponding to the N first ray paths in the original projection data and the projection position corresponding to the second ray path described later in the original projection data is less than or equal to a preset value, and the preset value may be set as needed, and the embodiments of the present application are not limited thereto. In other words, using the projection value of the projection position near the projection position corresponding to the second ray path to predict the projection value of the projection position corresponding to the second ray path can make the prediction result more accurate, and the second ray path will be described later.

[0069] In some embodiments, in 601, after selecting N first ray paths, for each first ray path, the length or area (representing the size of each tissue) of each tissue passed by the first ray path in the multi-valued image is calculated, and the length or area (which can be regarded as a geometric contribution) is multiplied by the contribution weight value of the tissue (which can be regarded as a physical contribution) to obtain the contribution degree of the tissue, wherein the contribution weight value reflects the degree of ray absorption of the tissue, for example, the contribution weight value is equal to the ray absorption coefficient of the tissue. For example, the muscle absorption coefficient is 1, the bone absorption coefficient is 3, the fat absorption coefficient is 0.5, etc. The absorption coefficients of different tissues are also related to the scanning voltage. For details, please refer to the relevant technology, which will not be described one by one here.

[0070] Taking a first ray path as an example, it passes through four tissues: fat, bone, muscle, and air in the multi-valued image. The length of each tissue in the multi-valued image is L1, L2, L3, and L4, and the ray absorption coefficient of each tissue is C1, C2, C3, and C4. Then, the contribution of each tissue passed by the first ray path in the multi-valued image is L1×C1, L2×C2, L3×C3, and L4×C4.

[0071] In some embodiments, the length of each tissue on the first ray path can be calculated using a forward projection method, that is, the length of the line segment of each tissue within the pixel (corresponding to the aforementioned weighting function). For details, please refer to the relevant technology, and no one example is given here. In some cases, considering the width of the detector channel, the area of ​​each tissue on the first ray path can be calculated, that is, the sum of the areas of the pixels occupied by each tissue. The number of pixels occupied by each tissue on the first ray path can be calculated using a forward projection method. The sum of the areas is equal to the area of ​​each pixel multiplied by the number of pixels, which will not be repeated here.

[0072] In some embodiments, in 602, N projection positions of the N first ray paths on the sinusoidal graph corresponding to the original projection data may be determined according to the projection relationship, and projection values ​​P corresponding to the N projection positions may be determined in the original projection data. sino1 ,...,P sinoN , the corresponding relationship is obtained by fitting the contribution of each tissue passed through in the multi-valued image on the multiple first ray paths and the multiple original projection values. The corresponding relationship can also be obtained by using the function y=f(x1, x2, ..., x Z ) represents, where y represents the projection value P sino , x1, x2, ..., x Z Represents the contribution of each tissue. The number Z can be determined based on the number of all tissue types in the multi-valued image except for the specific material part, that is, Z is equal to the number of all tissue types in the multi-valued image - 1. If the first ray path does not pass through a certain tissue, the contribution of the tissue is 0. For example, the multi-valued image includes 5 types of tissues: metal, fat, bone, muscle, and air, then Z = 4. A first ray path A1 passes through fat (length L1), bone (length L2), and air (length L4) in the multi-valued image. The contribution of each tissue is L1×C1, L2×C2, and L4×C4. Since the first ray path A1 has not passed through the muscle (L3=0) except for the specific material part in the multi-valued image, the contribution of the muscle on the first ray path A1 can be regarded as 0, and the projection value corresponding to the first ray path A1 is P sino1 , P sino1 =f(L1×C1, L2×C2, 0, L4×C4), and so on. For the first ray path AN, P sinoN =f(L1 N ×C1,L2 N ×C2,L3 N ×C3,L4 N ×C4).

[0073] In some embodiments, the contribution of each tissue and the multiple original projection values ​​passed through by the multiple first ray paths in the multi-valued image can be fitted according to a machine learning or deep learning method to obtain the corresponding relationship P sino =f(x1, x2, ..., x Z ), specific fitting processing methods include, for example, high-order polynomial fitting, etc., and specific reference may be made to related technologies, and the embodiments of the present application are not limited thereto.

[0074] In some embodiments, for a track corresponding to a specific material portion on a sinusoidal graph corresponding to the raw projection data (eg, Fig.13For each (M) projection position on the substrate (as shown in the mark), the ray path corresponding to each projection position is determined according to the back projection method, and the above ray paths are used as M second ray paths. Therefore, the second ray paths are ray paths passing through the specific material part, and the above N and M are integers greater than 1.

[0075] In some embodiments, in 203, the contribution of each tissue except the specific material part that the second ray path passes through in the multi-valued image is first determined, that is, assuming that the specific material part does not exist, the length or area of ​​each tissue except the specific material part that the second ray path passes through in the multi-valued image is calculated respectively, and the length or area is multiplied by the contribution weighted value of the tissue to obtain the contribution of the tissue, for example, the contribution weighted value is equal to the ray absorption coefficient of the tissue. For example, the muscle absorption coefficient is 1, the bone absorption coefficient is 3, the fat absorption coefficient is 0.5, etc. The absorption coefficients of different tissues are also related to the scanning voltage. For details, please refer to the relevant technology, which will not be repeated here. The difference from the first ray path is that, when calculating the contribution, the first ray path does not pass through the specific material part, and therefore, the contribution of the specific material part is not calculated. The second ray path passes through the specific material part, but assumes that the specific material part does not exist, and therefore, the contribution of the specific material part is not calculated. Alternatively, for ease of calculation, the contribution weighted value of the specific material part can be regarded as 0, that is, on the second ray path, the contribution of the specific material part is 0, and it can also be regarded as the non-existence of the specific material part. The embodiments of the present application are not limited to this.

[0076] In some embodiments, in 203, according to the corresponding relationship P sino =f(x1, x2, ..., x Z ), determine the projection value corresponding to the contribution of each tissue except the specific material part on the second ray path as the predicted projection value. For example, for each second ray path, the contribution of each tissue except the specific material part W1, W2, ..., W Z Substitute it into the above function and use the function value as the predicted projection value, that is, P sino-predict =f(W1, W2, ..., W Z ), thereby determining the predicted projection value of the trajectory corresponding to the specific material part in the original projection data.

[0077] In some embodiments, according to the foregoing analysis, it can be known that the second ray path passes through a specific material part (such as metal), and the projection value of the projection position corresponding to the second ray path in the original projection data is affected by the specific material part and is inaccurate. The predicted projection value obtained in 203 is determined based on the contribution of each tissue related to the radiation absorption amount on the ray path that does not pass through the specific material part and the corresponding relationship between the original projection value corresponding to the ray path in the original projection data. Therefore, the influence of the specific material part can be avoided, and the predicted projection value of other tissues when they are not contaminated by the specific material part is obtained when assuming that the specific material part does not exist, and the medical image (excluding the specific material part) is reconstructed based on the predicted projection value, which is described in detail below.

[0078] In some embodiments, in 204, the predicted projection value is used to replace the original projection value of the trajectory corresponding to the specific material part in the original projection data to obtain the first projection data; and the first medical image is obtained according to the first projection data. For example, the first projection data is reconstructed to obtain the first medical image, and the image reconstruction algorithm may include: for example, a back projection (FBP) reconstruction method, an adaptive statistical iterative reconstruction (ASIR) method, a conjugate gradient (CG) method, a maximum likelihood expectation maximization (MLEM) method, a model-based iterative reconstruction (MBIR) method, etc. For details, reference may be made to the relevant technology, and the embodiments of the present application are not limited thereto.

[0079] In some embodiments, the predicted projection value and the projection value of the position near the predicted projection value in the original projection data may be non-smooth and discontinuous. To address this problem, after obtaining the first projection data in 204, in the first projection data, the predicted projection value is corrected using the original projection value around the position where the predicted projection value is located to obtain the second projection data; the above-mentioned nearby position includes a predetermined number of projection positions on the left and right of the position of the predicted projection value, and the correction processing includes multiplying the projection value and / or the predicted projection value of the above-mentioned nearby position by a preset smoothing function in the first projection data to obtain the second projection data. The design of the smoothing function can refer to the relevant technology, and the embodiment of the present application is not limited to this. Then, the second projection data is reconstructed to obtain the first medical image, and the image reconstruction algorithm may include: for example, back projection (FBP) reconstruction method, adaptive statistical iterative reconstruction (ASIR) method, conjugate gradient (CG) method, maximum likelihood expectation maximization (MLEM) method, model-based iterative reconstruction (MBIR) method, etc., and the specific reference can be made to the relevant technology, and the embodiment of the present application is not limited to this. Through this correction processing, the potential artifacts of the metal boundary can be reduced.

[0080] In some embodiments, the first medical image is an image reconstructed within a second predetermined field of view (DFOV2). The size of the second predetermined field of view (DFOV2) may be less than or equal to the first predetermined field of view. For example, it may be determined based on the region of interest (imaging organ) of the object to be detected, for example, it may be set to 25 cm or 36 cm. For details, please refer to the relevant technology, and the embodiments of the present application are not limited to this.

[0081] In some embodiments, according to the aforementioned embodiments, the first medical image reconstructed using the predicted projection values ​​does not include the specific material part (because the predicted projection values ​​are obtained on the assumption that the specific material part does not exist). Figure 7 is a schematic diagram of a first medical image in an embodiment of the present application, such as Figure 7 As shown, the first medical image is a medical image in which the specific material part is a hole 71, that is, the first medical image does not contain a reconstructed image of the specific material part. Figure 3 In comparison, the reconstructed image of other tissues in the first medical image will not be contaminated by the specific material site, the metal artifacts in the image are removed, and the image quality is significantly improved.

[0082] It can be seen from the above embodiments that the first medical image is a reconstructed image that does not include a specific material part. In order to obtain a complete diagnostic image, the method may further include: (optional)

[0083] 205, reconstructing a second medical image of the specific material part;

[0084] 206 , fill the second medical image into the first medical image to generate a diagnostic image.

[0085] In some embodiments, for the original projection data, an image can be reconstructed within a third predetermined field of view (DFOV3) to obtain a second medical image, and the image of a specific material part (the determination method is as described above and will not be repeated here) in the second medical image is backfilled into the hole 71 of the first medical image to generate a diagnostic image. For example, the third predetermined field of view can be equal to the second predetermined field of view.

[0086] In some embodiments, in order to improve the resolution of a specific material part (for example, when the special material part is a screw, in order to clearly see the thread, etc.), for the original projection data, a second medical image of the specific material part can be reconstructed with a third predetermined field of view smaller than the second predetermined field of view. Fig.12After the specific material part is determined in the steps shown, the center position of the specific material part can be used as the center position of the third predetermined field of view, and the second medical image can be reconstructed in the third predetermined field of view for the original projection data, and the image of the specific material part is determined in the second medical image (for example, the area where the pixels with CT values ​​greater than 4000HU are located is determined as the metal part, wherein the CT value of each pixel in the second medical image except the specific material part can be set to 0). Since the second medical image and the first medical image are reconstructed in fields of view of different sizes, the specific material part in the second medical image is scaled according to the scaling factor; the scaled image of the specific material part is filled into the corresponding position of the first medical image to obtain the diagnostic image. The scaling factor is related to the size of the second predetermined field of view and the third predetermined field of view. For example, the scaling factor is equal to DFOV2 / DFOV3, and the image of the specific material part in the second medical image is multiplied by the scaling factor to obtain a scaled image, and the scaled image is backfilled into the hole 71 of the first medical image to obtain a diagnostic image. The backfilling operation includes superimposing the pixel values ​​of the scaled image and the first medical image to generate a diagnostic image, which will not be explained here one by one.

[0087] The following combination Figure 8 The medical image processing process of this application is further explained.

[0088] In some embodiments, in 801, original projection data obtained after scanning the object to be detected is obtained, and in 802, the original projection data is reconstructed within a first predetermined field of view to obtain an original medical image; in 803, the original medical image is multi-valued to obtain a multi-valued image; in 804, the correspondence between the contribution of each tissue related to the radiation absorption amount on the ray path that does not pass through the specific material part in the multi-valued image and the original projection value corresponding to the ray path in the original projection data is determined; in 805, a second ray path is determined according to the trajectory corresponding to the specific material part, and according to the correspondence, a predicted projection value of the projection position corresponding to the second ray path in the original projection data is determined; in 806, the original projection value of the trajectory corresponding to the specific material part in the original projection data is replaced with the predicted projection value to obtain the first projection data; in the first projection data, the predicted projection value is corrected using the original projection values ​​around the position where the predicted projection value is located to obtain the second projection data; in 807, the first medical image is reconstructed within a second predetermined field of view for the second projection data.

[0089] In some embodiments, in 808, a specific material part is determined for the original medical image, in 809, the original projection data is reconstructed within a third predetermined field of view with the specific material part as the center to obtain a second medical image, in 810, an image of the specific material part is determined in the second medical image, in 811, the image of the specific material part in 810 is scaled according to the scaling factor, and in 812, the scaled image is filled into the first medical image obtained in 807 to obtain a final diagnostic image. It is worth noting that the above attached image Figure 2 or Figure 8 The embodiments of the present application are only schematically described, but the present application is not limited thereto. For example, the execution order of the various operations can be appropriately adjusted, and other operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above content, and are not limited to the above appended Figure 2 or Figure 8 Records of.

[0090] The above embodiments are merely exemplary of the embodiments of the present application, but the present application is not limited thereto, and appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined. The embodiments of the present application are not limited thereto.

[0091] The present application also provides a medical image processing device, Fig. 9 is a schematic diagram of a medical image processing device according to an embodiment of the present application. Fig. 9 As shown, the device 900 includes:

[0092] A first reconstruction unit 901, which acquires original projection data obtained after scanning the object to be detected, and reconstructs an original medical image;

[0093] A segmentation unit 902 performs multi-valued processing on the original medical image to obtain a multi-valued image;

[0094] A first determining unit 903, which determines a predicted projection value of a trajectory corresponding to a specific material part in the original projection data according to a corresponding relationship between a contribution of each tissue related to the radiation absorption amount on a ray path that does not pass through the specific material part in the multi-valued image and an original projection value corresponding to the ray path in the original projection data;

[0095] The second reconstruction unit 904 obtains a first medical image according to the predicted projection value and the original projection data.

[0096] In some embodiments, the implementation of the first reconstruction unit 901, the segmentation unit 902, the first determination unit 903 and the second reconstruction unit 904 may refer to 201-204 in the aforementioned embodiments, and will not be repeated here.

[0097] In some embodiments, the apparatus may further include:

[0098] A second determination unit (not shown) determines the position of the specific material part in the original medical image, for example, by comparing the CT value of each pixel in the original medical image with a preset CT value corresponding to the specific material; and determines the position of the pixel having a CT value greater than the preset CT value as the specific material part.

[0099] In some embodiments, the second determination unit may also perform forward projection on the position of the specific material site in the original medical image to determine the trajectory corresponding to the specific material site in the original projection data.

[0100] In some embodiments, the device may further include: (not shown)

[0101] a third reconstruction unit, which reconstructs a second medical image of the specific material part;

[0102] A generating unit is configured to fill the second medical image into the first medical image to generate a diagnostic image.

[0103] The implementation of the second determination unit, the third reconstruction unit, and the generation unit may refer to the aforementioned embodiments and will not be described in detail here.

[0104] For simplicity, the above figures only illustrate the connection relationship or signal direction between various components or modules, but it should be clear to those skilled in the art that various related technologies such as bus connection can be used. The above components or modules can be implemented by hardware facilities such as processors and memories; the embodiments of the present application are not limited to this.

[0105] The above embodiments are merely exemplary of the embodiments of the present application, but the present application is not limited thereto, and appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0106] The present application also provides a medical image processing device. Fig.10 Schematic diagram of the structure of the medical image processing device of the embodiment of the present application. Fig.10As shown, the medical image processing device 1000 may include: one or more processors (e.g., central processing unit CPU) 1010 and one or more memories 1020; the memory 1020 is coupled to the processor 1010. The memory 1020 may store the corresponding relationship, etc.; in addition, the control program 1021 of the device is input, and the program 1021 is executed under the control of the processor 1010. The memory 1020 may include, for example, a ROM, a floppy disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, or a non-volatile memory card.

[0107] In some embodiments, the functions of the medical image processing apparatus 900 are integrated into the processor 1010. The processor 1010 is configured to implement the medical image processing method as described in the above embodiments. The implementation of the processor 1010 can refer to the above embodiments and will not be repeated here.

[0108] In some embodiments, the medical image processing device 900 is configured separately from the processor 1010 . For example, the medical image processing device 900 can be configured as a chip connected to the processor 1010 , and the functions of the medical image processing device 900 are realized through the control of the processor 1010 .

[0109] In addition, if Fig.10 As shown, the medical image processing device 1000 may also include: an input device 1030 and a display 1040 (displaying a user graphical interface, as well as various data generated during data acquisition and processing), etc.; wherein, the functions of the above components are similar to those of the prior art and are not described in detail here. It is worth noting that the medical image processing device 1000 does not necessarily have to include Fig.10 In addition, the medical image processing device 1000 may also include Fig.10 For components not shown in the figure, reference may be made to the related art.

[0110] The processor 1010 can respond to the operation of the input device to communicate with the medical device, display, etc., and can also control the input action and / or state of the input device. The processor 1010 can also be called a microcontroller unit (MCU), a microprocessor or a microcontroller or other processor device and / or logic device. The processor 1010 can include a reset circuit, a clock circuit, a chip, a microcontroller, etc. The function of the processor 1010 can be integrated on the mainboard of the medical device (for example, the processor 1010 is configured as a chip connected to the mainboard processor (CPU)), or it can be set independently of the mainboard, and the embodiments of the present application are not limited to this.

[0111] The embodiment of the present application further provides a medical device, which includes the medical image processing device 1000 described in the above embodiment. The implementation of the medical image processing device 1000 is as described above, and will not be repeated here.

[0112] In some embodiments, the medical device includes a computer tomography device, but the present application is not limited thereto, and the medical device may also be other devices that can acquire medical images.

[0113] The functions of the processor of the medical image processing device 1000 can be integrated on the mainboard of the medical device (for example, the processor is configured as a chip connected to the mainboard processor (CPU)), or it can be set independently of the mainboard. The embodiments of the present application are not limited to this.

[0114] In some embodiments, the medical device may further include other components, for which details may be referred to the prior art and will not be described in detail here.

[0115] The following is an example of a medical device, CT equipment. Fig.11 Schematic diagram of the CT system 10 of the embodiment of the present application. Fig.11 As shown, the system 10 includes a frame 12, on which an X-ray source 14 and a detector 18 are relatively arranged. The detector 18 is composed of a plurality of detector modules 20 and a data acquisition system (DAS) 26. The DAS 26 is used to convert the sampled analog attenuation data received by the plurality of detector modules 20 into digital signals for subsequent processing.

[0116] In some embodiments, the system 10 is used to collect projection data of the object to be detected at different angles, so the components on the gantry 12 are used to rotate around the rotation center 24 to collect projection data. During the rotation process, the X-ray radiation source 14 is used to project X-rays 16 that penetrate the object to be detected toward the detector 18, and the attenuated X-ray beam data is pre-processed as the projection data of the target volume of the object. Based on the projection data, an image of the object to be detected can be reconstructed, and the reconstructed image can show the internal features of the object to be detected, such as lesions, size, shape, etc. of the body tissue structure. The rotation center 24 of the gantry also defines the center of the scanning field 80.

[0117] The system 10 further includes an image reconstruction module 50. As described above, the DAS 26 samples and digitizes the projection data collected by the plurality of detector modules 20. Then, the image reconstruction module 50 performs high-speed image reconstruction based on the sampled and digitized projection data. In some embodiments, the image reconstruction module 50 stores the reconstructed image in a storage device or mass storage 46. Alternatively, the image reconstruction module 50 transmits the reconstructed image to the computer 40 to generate patient information for diagnosis and evaluation.

[0118] although Fig.11 4 shows an image reconstruction module 50 as a separate entity, but in some embodiments, the image reconstruction module 50 may form part of the computer 40. Alternatively, the image reconstruction module 50 may not be present in the system 10, or the computer 40 may perform one or more functions of the image reconstruction module 50. In addition, the image reconstruction module 50 may be located at a local or remote location and may be connected to the system 10 using a wired or wireless network. In some embodiments, computing resources concentrated in a cloud network may be used for the image reconstruction module 50.

[0119] In some embodiments, the system 10 includes a control mechanism 30. The control mechanism 30 may include an X-ray controller 34 for providing power and timing signals to the X-ray radiation source 14. The control mechanism 30 may also include a gantry controller 32 for controlling the rotation speed and / or position of the gantry 12 based on imaging requirements. The control mechanism 30 may also include a carrier bed controller 36 for driving the carrier bed 28 to move to a suitable position to position the object to be detected in the gantry 12 to collect projection data of a target volume of the object to be detected. Further, the carrier bed 28 includes a drive device, and the carrier bed controller 36 can control the carrier bed 28 by controlling the drive device.

[0120] In some embodiments, the system 10 further includes a computer 40, to which the data sampled and digitized by the DAS 26 and / or the images reconstructed by the image reconstruction module 50 are transmitted or processed. In some embodiments, the computer 40 stores the data and / or images in a storage device such as a mass storage device 46. The mass storage device 46 may include a hard drive, a floppy disk drive, a compact disk read / write (CD-R / W) drive, a digital versatile disk (DVD) drive, a flash drive, and / or a solid-state storage device, etc. In some embodiments, the computer 40 transmits the reconstructed images and / or other information to a display 42, which is communicatively connected to the computer 40 and / or the image reconstruction module 50. In some embodiments, the computer 40 can be connected to a local or remote display, printer, workstation, and / or similar device, for example, such equipment in a medical institution or hospital, or connected to a remote device via one or more configured wires or a wireless network such as the Internet and / or a virtual private network.

[0121] In addition, the computer 40 can provide commands and parameters to the DAS 26, and the control mechanism 30 (including the gantry controller 32, the X-ray controller 34 and the carrier bed controller 36) based on user-provided and / or system-defined commands and parameters to control system operations, such as data acquisition and / or processing. In some embodiments, the computer 40 controls system operations based on user input. For example, the computer 40 can receive user input, including commands, scan protocols and / or scan parameters, through an operator console 48 connected thereto. The operator console 48 may include a keyboard (not shown) and / or a touch screen to allow the user to enter / select commands, scan protocols and / or scan parameters.

[0122] In some embodiments, the system 10 may include or be connected to a picture archiving and communication system (PACS) (not shown). In some embodiments, the PACS is further connected to a remote system such as a radiology department information system, a hospital information system, and / or an internal or external network (not shown) to allow operators located in different locations to provide commands and parameters, and / or access image data.

[0123] The methods or processes in the aforementioned embodiments may be stored as executable instructions in a non-volatile memory on a computing device of the storage system 10. For example, the computer 40 may include executable instructions in a non-volatile memory and may apply the medical image processing method in the embodiments of the present application.

[0124] The computer 40 may be configured and / or arranged to be used in different ways. For example, in some implementations, a single computer 40 may be used; in other implementations, multiple computers 40 are configured to work together (e.g., based on a distributed processing configuration) or individually, with each computer 40 configured to handle specific aspects and / or functions, and / or process data used to generate models that are only used for a specific system 10. In some implementations, the computer 40 may be local (e.g., co-located with one or more systems 10, such as within the same facility and / or the same local network); in other implementations, the computer 40 may be remote and therefore only accessible via a remote connection (e.g., via the Internet or other available remote access technology). In a particular implementation, the computer 40 may be configured in a cloud-like manner and may be accessed and / or used in a manner substantially similar to the manner in which other cloud-based systems are accessed and used.

[0125] Once the data is generated and / or configured, the data can be copied and / or loaded into the medical system 10, which can be done in different ways. For example, the model can be loaded via a directional connection or link between the system 10 and the computer 40. In this regard, the communication between the different elements can be completed using available wired and / or wireless connections and / or according to any suitable communication (and / or network) standards or protocols. Alternatively or additionally, the data can be loaded into the system 10 indirectly. For example, the data can be stored in a suitable machine-readable medium (e.g., a flash card, etc.), and then the medium is used to load the data into the system 10 (on-site, such as by a user or authorized personnel of the system), or the data can be downloaded to an electronic device capable of local communication (e.g., a laptop, etc.), and then the device is used on-site (e.g., by a user or authorized personnel of the system) to upload the data to the system 10 via a direct connection (e.g., a USB connector, etc.).

[0126] An embodiment of the present application also provides a computer-readable program, wherein when the program is executed, the program enables the computer to execute the medical image processing method described in the aforementioned embodiment in the apparatus or medical device.

[0127] An embodiment of the present application also provides a storage medium storing a computer-readable program, wherein the computer-readable program enables a computer to execute the medical image processing method described in the aforementioned embodiment in an apparatus or medical device.

[0128] The above embodiments are merely exemplary of the embodiments of the present application, but the present application is not limited thereto, and appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0129] The present application is described above in conjunction with specific implementation methods, but it should be clear to those skilled in the art that these descriptions are exemplary and are not intended to limit the scope of protection of the present application. Those skilled in the art can make various modifications and variations to the present application based on the spirit and principles of the present application, and these modifications and variations are also within the scope of the present application.

[0130] The preferred embodiments of the present application are described above with reference to the accompanying drawings. Many features and advantages of these embodiments are clear from this detailed description, and therefore the appended claims are intended to cover all such features and advantages of these embodiments that fall within their true spirit and scope. In addition, since many modifications and variations are easily conceivable to those skilled in the art, the embodiments of the present application are not intended to be limited to the precise structures and operations illustrated and described, but all suitable modifications, variations, and equivalents that fall within their scope may be covered.

Claims

1. A medical image processing method, characterized in that: The method comprises: Acquire original projection data obtained after scanning the object to be detected, and reconstruct the original medical image; Performing multi-value processing on the original medical image to obtain a multi-valued image; Determine a predicted projection value of a trajectory corresponding to the specific material part in the original projection data according to a correspondence between a contribution of each tissue related to the radiation absorption amount on a ray path that does not pass through the specific material part in the multi-valued image and an original projection value corresponding to the ray path in the original projection data; A first medical image is obtained according to the predicted projection value and the original projection data.

2. The method according to claim 1, wherein: Performing multi-valued processing on the original medical image to obtain a multi-valued image includes: comparing the CT value of each pixel position in the original medical image with multiple thresholds corresponding to CT values ​​of different types of tissues, and re-determining the pixel value of each pixel position according to the comparison result to obtain the multi-valued image, wherein in the multi-valued image, the pixel values ​​corresponding to different tissues are different, and the pixel values ​​corresponding to the same tissue are the same.

3. The method according to claim 1, wherein: The method further includes: determining the corresponding relationship; including: Determining the contribution of each tissue passed through by a plurality of different first ray paths in the multi-valued image and the original projection values ​​of the projection positions corresponding to the plurality of different first ray paths in the original projection data; the first ray paths are ray paths that do not pass through the specific material part; The corresponding relationship is obtained by fitting the contribution of each tissue on the multiple first ray paths and the multiple original projection values.

4. The method according to claim 1 or 3, wherein: Determining the predicted projection value of the trajectory corresponding to the specific material part in the original projection data according to the corresponding relationship between the contribution of each tissue related to the radiation absorption amount on the ray path that does not pass through the specific material part in the multi-valued image and the original projection value corresponding to the ray path in the original projection data includes: determining a contribution of each tissue other than the specific material site passed through by a second ray path in the multi-valued image, wherein the second ray path is a ray path passing through the specific material site; According to the corresponding relationship, a projection value corresponding to the contribution of each tissue except the specific material part on the second ray path is determined as the predicted projection value.

5. The method according to claim 3, wherein: Determining the contribution of each tissue passed through by the first ray path in the multi-valued image includes: The length or area of ​​each tissue passed by the first ray path in the multi-valued image is calculated, and the contribution degree of the tissue is obtained by multiplying the length or area by the contribution weighted value of the tissue, wherein the contribution weighted value reflects the degree of ray absorption of the tissue.

6. The method according to claim 5, wherein: The contribution weighted value is equal to the radiation absorption coefficient of the tissue.

7. The method according to claim 5, wherein: The length of each tissue passed by the first ray path in the multi-valued image is calculated using a forward projection method.

8. The method according to claim 4, wherein: A distance between projection positions corresponding to a plurality of different first ray paths in the original projection data and a projection position corresponding to the second ray path in the original projection data is less than or equal to a preset value.

9. The method according to claim 1, wherein: Obtaining a first medical image according to the predicted projection value and the original projection data includes: Using the predicted projection value to replace the original projection value of the trajectory corresponding to the specific material part in the original projection data, to obtain first projection data; The first medical image is obtained according to the first projection data.

10. The method according to claim 9, wherein: Obtaining the first medical image according to the first projection data includes: In the first projection data, the predicted projection value is corrected using the original projection values ​​around the position where the predicted projection value is located to obtain the second projection data; The second projection data is reconstructed to obtain the first medical image.

11. The method according to claim 1, wherein: The method further comprises: Determining the location of the specific material part in the original medical image includes: comparing the CT value of each pixel in the original medical image with a preset CT value corresponding to the specific material; and determining the location of the pixel having a CT value greater than the preset CT value as the specific material part.

12. The method according to claim 11, wherein: The method further comprises: The position of the specific material part in the original medical image is forward projected to determine the trajectory corresponding to the specific material part in the original projection data.

13. The method according to claim 1, wherein: The method further comprises: reconstructing a second medical image of the specific material site; Filling the second medical image into the first medical image generates a diagnostic image.

14. The method according to claim 13, wherein: The original medical image is an image reconstructed within a first predetermined field of view, the first predetermined field of view is an extended imaging field of view, the first medical image is an image reconstructed within a second predetermined field of view, the second medical image is an image reconstructed within a third predetermined field of view, and the second predetermined field of view is less than or equal to the first predetermined field of view.

15. The method according to claim 13 or 14, wherein: The method further comprises: Scaling the specific material part in the second medical image according to the scaling factor; The zoomed image of the specific material part is filled into the corresponding position of the first medical image to obtain the diagnostic image.

16. The method according to claim 15, wherein: The scaling factor is related to the size of the second predetermined field of view and the third predetermined field of view.

17. The method according to claim 1, wherein: The specific material portion includes a metal portion.

18. The method according to claim 2 or 5, wherein: In the multi-valued image, the pixel value corresponding to the specific material part is assigned a value of 0, or the contribution weighted value corresponding to the specific material part is 0.

19. A medical image processing device, characterized in that: The device comprises: A first reconstruction unit, which acquires original projection data obtained after scanning the object to be detected, and reconstructs an original medical image; A segmentation unit, which performs multi-valued processing on the original medical image to obtain a multi-valued image; a first determining unit, which determines a predicted projection value of a trajectory corresponding to a specific material part in the original projection data according to a corresponding relationship between a contribution of each tissue related to the radiation absorption amount on a ray path that does not pass through the specific material part in the multi-valued image and an original projection value corresponding to the ray path in the original projection data; A second reconstruction unit is configured to obtain a first medical image according to the predicted projection value and the original projection data.

20. A medical device, characterized in that: The medical equipment comprises the medical image processing apparatus according to claim 19.

Images