Image reconstruction method and computer device

Abstract

The present application relates to an image reconstruction method and a computer device. The method includes: obtaining original projection data of a scanning object; performing image reconstruction on the original projection data to obtain a distance image sequence corresponding to the reconstructed image; the distance image sequence includes at least one distance image, and the motion artifacts of each distance image are different; generating a medical image of the scanning object according to the distance image sequence corresponding to the reconstructed image; the medical image is an image after motion artifact correction processing. That is, in the process of image reconstruction in the present application, a distance image sequence corresponding to the reconstructed image is obtained to analyze the change of motion artifacts in the reconstructed image through multiple distance images in the distance image sequence, and then the final medical image is generated according to the distance image sequence. The medical image is an image after motion artifact correction processing. In this way, through the distance image sequence of the reconstructed image, the motion artifacts in the medical image can be effectively reduced, and the image quality of the medical image can be improved.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, and particularly to an image reconstruction method and a computer device. Background Art

[0002] During the process of using a medical imaging device to scan a certain scanning area of a scanned object, the scanned object may have voluntary or involuntary movements (for example, small-scale movements or rotations of the torso of the scanned object, voluntary breathing movements, involuntary heartbeats, and gastrointestinal peristalsis, etc.). These voluntary or involuntary movements will all form motion artifacts on the reconstructed image.

[0003] The appearance of motion artifacts will reduce the clarity of the reconstructed image, and further affect the accuracy of the diagnostic results obtained based on the reconstructed image. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide an image reconstruction method and a computer device that can reduce the motion artifacts of the reconstructed image and improve the accuracy of the image reconstruction result.

[0005] In a first aspect, this application provides an image reconstruction method, which includes:

[0006] Obtain the original projection data of the scanned object;

[0007] Perform image reconstruction on the original projection data to obtain a distance image sequence corresponding to the reconstructed image; the distance image sequence includes at least one distance image, and the motion artifacts of each distance image are different;

[0008] Generate a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image; the medical image is an image after motion artifact correction processing.

[0009] In one embodiment, the reconstructed image includes multiple reconstructed slice images, and the distance image sequence includes a first image sequence;

[0010] Performing image reconstruction on the original projection data to obtain a distance image sequence corresponding to multiple reconstructed images includes:

[0011] Performing image reconstruction on the original projection data based on a preset distance weight relationship to obtain a first image sequence corresponding to each reconstructed slice image.

[0012] In one embodiment, performing image reconstruction on the original projection data based on a preset distance weight relationship to obtain a first image sequence corresponding to each reconstructed slice image includes:

[0013] Weight the original projection data according to the distance weight relationship based on the distance from the projection light source point to the reconstruction plane, to obtain multiple weighted projection data corresponding to the images of each reconstruction plane;

[0014] Perform image reconstruction on the multiple weighted projection data corresponding to the images of each reconstruction plane, to obtain a first image sequence corresponding to the images of each reconstruction plane.

[0015] In one embodiment, generating a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image includes:

[0016] Determine the target plane image corresponding to the image of each reconstruction plane according to the first image sequence corresponding to the image of each reconstruction plane;

[0017] Generate a medical image of the scanned object according to the target plane image corresponding to the image of each reconstruction plane.

[0018] In one embodiment, determining the target plane image corresponding to the image of each reconstruction plane according to the first image sequence corresponding to the image of each reconstruction plane includes:

[0019] Based on the first image sequence corresponding to the image of each reconstruction plane, subtract adjacent first images, and analyze the change intensity of motion artifacts in the first image sequence;

[0020] Select the target plane image from the first image sequence corresponding to the image of each reconstruction plane according to the change intensity of motion artifacts in the first image sequence.

[0021] In one embodiment, determining the target plane image corresponding to the image of each reconstruction plane according to the first image sequence corresponding to the image of each reconstruction plane includes:

[0022] Analyze the motion feature information of the scanned object in the image of each reconstruction plane according to the first image sequence corresponding to the image of each reconstruction plane;

[0023] Perform artifact correction on the first image sequence corresponding to the image of each reconstruction plane according to the motion feature information of the scanned object in the image of each reconstruction plane, and determine the target plane image corresponding to the image of each reconstruction plane.

[0024] In one embodiment, generating a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image includes:

[0025] Based on a preset evaluation index, score each of the multiple candidate images respectively, to obtain the scoring results of each candidate image; the candidate images are composed according to the first image sequences corresponding to the multiple reconstruction plane images;

[0026] Determine the medical image of the scanned object according to the scoring results of each candidate image.

[0027] In one embodiment, the reconstructed image includes a reconstructed volume image, and the distance image sequence includes a second image sequence;

[0028] Performing image reconstruction on the original projection data to obtain the distance image sequence corresponding to the reconstructed image, including:

[0029] Performing image reconstruction on the original projection data based on a preset distance weight relationship to obtain the second image sequence corresponding to the reconstructed volume image.

[0030] In one embodiment, generating a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image, including:

[0031] Based on a preset evaluation index, respectively scoring multiple second images in the second image sequence corresponding to the reconstructed volume image to obtain the scoring results of each second image;

[0032] Determining the medical image of the scanned object according to the scoring results of each second image.

[0033] In a second aspect, the present application further provides an image reconstruction device, which includes:

[0034] An acquisition module, configured to acquire the original projection data of the scanned object;

[0035] A sequence reconstruction module, configured to perform image reconstruction on the original projection data to obtain the distance image sequence corresponding to the reconstructed image; the distance image sequence includes at least one distance image, and the motion artifacts of each distance image are different;

[0036] An image generation module, configured to generate a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image; the medical image is an image after motion artifact correction processing.

[0037] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of any method embodiment in the first aspect are implemented.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any method embodiment in the first aspect are implemented.

[0039] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of any method embodiment in the first aspect are implemented.

[0040] The above image reconstruction method and computer device, the computer device acquires the original projection data of the scanned object; performs image reconstruction on the original projection data to obtain a distance image sequence corresponding to the reconstructed image; and generates a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image. Among them, the distance image sequence includes at least one distance image, and the motion artifacts of each distance image are different. In the process of performing image reconstruction in this application, a distance image sequence corresponding to the reconstructed image is acquired to analyze the change of motion artifacts of the reconstructed image through multiple distance images in the distance image sequence, and then a final medical image is generated according to the distance image sequence. This medical image is an image after motion artifact correction processing. In this way, through the distance image sequence of the reconstructed image, the motion artifacts in the medical image can be effectively reduced, and the image quality of the medical image can be improved. Description of the Drawings

[0041] Figure 1 It is an application environment diagram of the image reconstruction method in an embodiment;

[0042] Figure 2 It is a flowchart of the image reconstruction method in an embodiment;

[0043] Figure 3 It is a schematic diagram of the distance weight relationship in an embodiment;

[0044] Figure 4 It is a schematic diagram of the distance image sequence in an embodiment;

[0045] Figure 5 It is a flowchart of generating a medical image in an embodiment;

[0046] Figure 6 It is a flowchart of generating a medical image in another embodiment;

[0047] Figure 7 It is a flowchart of generating a medical image in yet another embodiment;

[0048] Figure 8 It is a structural block diagram of the image reconstruction device in an embodiment;

[0049] Figure 9 It is an internal structure diagram of the computer device in an embodiment. Detailed Embodiments

[0050] In order to make the objectives, technical solutions and advantages of this application clearer, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0051] In the medical field, since scanning imaging takes a certain amount of time, during which the voluntary or involuntary movement of the scanned object destroys the consistency and integrity of the projection data, various artifacts appear in the reconstructed image, which are called motion artifacts. Motion artifacts mainly appear in various forms such as overlapping and blurring of tissue images, strip artifacts, displacement of image contours, and the appearance of objects similar to attachments in cavities. The appearance of artifacts will reduce the clarity of the reconstructed image, affect the normal diagnosis of doctors, and also bring difficulties to image post-processing work such as automatic lesion detection, computer-aided diagnosis, and three-dimensional reconstruction based on the reconstructed image, seriously restricting the development of scanning imaging and the application of reconstructed images in clinical diagnosis.

[0052] Based on this, the present application provides an image reconstruction method and a computer device. Image reconstruction is performed according to the original projection data of the scanned object. During the reconstruction process, distance images corresponding to multiple motion artifacts of the reconstructed image are obtained, and then a medical image after motion artifact correction processing is generated based on the multiple distance images. By generating the medical image of the scanned object through the sequence of distance images corresponding to the reconstructed image, the motion artifacts of the medical image can be effectively reduced and the quality of the medical image can be improved.

[0053] The image reconstruction method provided by the present application can be applied to an application environment as Figure 1 shown. As Figure 1 shown, this application environment may include an imaging device 110 and a computer device 120. The imaging device 110 communicates with the computer device 120 through a network to achieve data transmission and instruction interaction.

[0054] In some embodiments, the imaging device 110 may be a non-invasive biomedical imaging device for disease diagnosis or research purposes. For example, it may include a single-modal scanner and / or a multi-modal scanner. The single-modal scanner may include, for example, an ultrasonic scanner, an X-ray scanner, a CT scanner, a Magnetic Resonance Imaging (MRI) scanner, an ultrasound examination instrument, an Optical Coherence Tomography (OCT) scanner, an Ultra Sound (US) scanner, an Intra Vascular Ultra Sound (IVUS) scanner, a Near Infrared Spectrum Instrument (NIRS) scanner, a FarInfraRed (FIR) scanner, etc., or any combination of the above scanners. The multi-modal scanner may include, for example, an X-ray imaging - magnetic resonance imaging (X-ray - MRI) scanner, a single photon emission computed tomography - magnetic resonance imaging (SPECT-MRI) scanner, a positron emission tomography - computed tomography (PET-CT) scanner, a digital subtraction angiography - magnetic resonance imaging (DSA-MRI) scanner, etc. It should be understood that the scanners provided above are for illustrative purposes only and are not intended to limit the scope of the present application.

[0055] As an example, the imaging device 110 may specifically include a gantry, a detector, a detection area, a scanning bed, and a radiation source. The gantry can be used to support the detector and the radiation source, and the scanning bed can be used to place the scanning object for scanning; the radiation source can emit radiation to irradiate the scanning object; the detector can be used to receive the radiation that has passed through the scanning object.

[0056] Furthermore, the imaging device 110 may also include modules and / or components for performing imaging and / or related analysis. For example, the imaging device 110 may include a processor, and the processor can be used to execute the image reconstruction method provided by the present application.

[0057] Optionally, the imaging device 110 may also include a display screen, which can be used to observe the data information of the imaging device 110 and / or the scanning object scanned by the imaging device 110. For example, medical staff can observe the lesion information of the detection sites such as the chest cavity, bones, and mammary glands of the scanning object through the display screen.

[0058] In some embodiments, the imaging device 110 may also send the acquired scanning data (for example, the original projection data of the scanning object) to the computer device 120 via a network for further analysis, processing, and display.

[0059] Among them, the computer device 120 can be at least one device other than the imaging device 110. For example, various personal computers, laptop computers, smart phones, tablet computers, portable wearable devices or any combination of terminals; or, a single server or a server group, and the server group can be centralized or distributed.

[0060] Optionally, the above application environment may further include a storage device 130 ( Figure 1 not shown in the figure) for storing data, instructions, and / or any other information. For example, the storage device 130 can store the original projection data of the scanned object acquired by the imaging device 110, and / or the medical image of the scanned object processed by the computer device 120, etc.

[0061] As an example, the storage device may include one or more of a mass storage device, a removable storage device, a volatile read / write memory, a read-only memory, etc. In addition, the storage device may also be a data storage device including a cloud computing platform (such as a public cloud, a private cloud, a community cloud, and a hybrid cloud, etc.).

[0062] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of the present application. For those of ordinary skill in the art, various changes and modifications can be made under the guidance of the content of the present application. The features, structures, methods, and other features of the exemplary embodiments described in the present application can be combined in various ways to obtain additional and / or alternative exemplary embodiments, and these changes and modifications do not depart from the scope of the present application.

[0063] After introducing the application background and application environment of the present application, next, the technical solutions of the embodiments of the present application and how the technical solutions of the embodiments of the present application solve the above technical problems will be specifically described through embodiments and in conjunction with the accompanying drawings. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. It should be noted that for an image reconstruction method provided by an embodiment of the present application, the execution subject thereof can be Figure 1 the imaging device 110 including a processor in the figure, or Figure 1 the computer device 120 in the figure, or an image reconstruction device, and the device can be implemented as part or all of a processor (which can be specifically a processor in the imaging device / computer device) in a software, hardware, or software-hardware combination manner. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments.

[0064] In one embodiment, as Figure 2 shown, an image reconstruction method is provided. In this embodiment, it is described by taking the method applied to the computer device 120 as an example, and includes the following steps:

[0065] Step 210: Obtain the original projection data of the scanned object.

[0066] Among them, the original projection data is the projection data obtained after the imaging device 110 scans at least one part of the scanned object. The scanned object may include biological objects and / or non-biological objects. For example, the scanned object may include specific parts of the human body, such as one or more parts of the head, chest, abdomen, etc. The scanned object may also be a man-made component of living or non-living organic and / or inorganic substances, and this embodiment does not limit this.

[0067] When the execution subject is the computer device 120, the implementation process of step 210 is as follows: After the imaging device 110 completes the scanning operation of at least one part of the scanned object, the original projection data is obtained. Further, the computer device 120 obtains the original projection data of the scanned object from the imaging device 110.

[0068] It should be noted that if the scanned part is the chest, the motion artifacts existing in the medical image may be caused by the breathing motion of the scanned object. Through the image reconstruction method provided in this embodiment, the motion artifacts introduced by the breathing motion in the reconstructed image can be reduced; if the scanned part is the abdomen, the motion artifacts existing in the medical image may be caused by the intestinal cavity motion of the scanned object. Through the image reconstruction method provided in this embodiment, the motion artifacts introduced by the breathing motion in the reconstructed image can be reduced. In addition, the scanned part may also be other parts of the scanned object with autonomous or involuntary motion, and this embodiment does not limit this.

[0069] Step 220: Perform image reconstruction on the original projection data to obtain a distance image sequence corresponding to the reconstructed image; the distance image sequence includes at least one distance image, and the motion artifacts of each distance image are different.

[0070] Among them, when performing image reconstruction on the original projection data, two-dimensional image reconstruction can be performed, or three-dimensional image reconstruction can be directly performed. Therefore, the reconstructed images in this application include multiple reconstructed layer images and / or reconstructed volume images. Then, step 220 further includes the following two situations:

[0071] (1) The reconstructed image includes multiple reconstructed layer images, and the distance image sequence includes a first image sequence.

[0072] In this case, the implementation process of step 220 can be: Based on a preset distance weight relationship, perform image reconstruction on the original projection data to obtain the first image sequence corresponding to each reconstructed layer image.

[0073] Specifically, the reconstruction process of the reconstructed slice images can be as follows: According to the distance weight relationship, the original projection data is weighted according to the distance from the projection light source point to the reconstructed slice, and a plurality of weighted projection data corresponding to each reconstructed slice image are obtained; Image reconstruction is performed on the plurality of weighted projection data corresponding to each reconstructed slice image to obtain a first image sequence corresponding to each reconstructed slice image.

[0074] (2) The reconstructed image includes the reconstructed volume image, and the distance image sequence includes the second image sequence.

[0075] In this case, the implementation process of step 220 can be: Based on a preset distance weight relationship, image reconstruction is performed on the original projection data to obtain a second image sequence corresponding to the reconstructed volume image.

[0076] As an example, the distance weight relationship in the embodiments of the present application can be implemented using a Gaussian function or a similar function form. Refer to Figure 3 the shown distance weight curve. The abscissa represents the distance from the parallel beam light source of the imaging device to the image slice, and the ordinate represents the imaging weight of the original projection data at the corresponding distance.

[0077] Specifically, by adjusting the application position of the distance weight relationship (for example, horizontal movement), a series of distance images can be generated. The distance images in the distance image sequence have higher temporal resolution than the reconstructed image, and the artifacts in some slices will be significantly reduced.

[0078] Furthermore, Figure 4 the (a) in Figure 4 is the distance image generated by moving the distance weight curve to the left, Figure 4 the (b) in Figure 4 is the distance image generated without moving the distance weight curve, and

[0079] the (c) in Figure 4 is the distance image generated by moving the distance weight curve to the right. As can be seen from Figure 4 , by moving the position of the distance weight curve, different distance images can be generated, and the degree of motion artifacts in each distance image is different. Based on this, from multiple distance images of the same slice in the "time series", the distance image with the weakest motion artifacts and the best imaging quality can be found and used to generate the medical image of the scanned object.

[0079] Step 230: Generate a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image; the medical image is an image after motion artifact correction processing.

[0080] In a possible implementation, the implementation process of step 230 can be as follows: Analyze the motion artifacts of each distance image according to the distance image sequence corresponding to the reconstructed image, and generate a medical image of the scanned object based on the distance image with the weakest motion artifacts, so as to ensure that the motion artifacts of the medical image processed by artifact correction through the distance image sequence are the weakest and the image quality is the best.

[0081] In the above image reconstruction method, the computer device acquires the original projection data of the scanned object; performs image reconstruction on the original projection data to obtain a distance image sequence corresponding to the reconstructed image; and generates a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image. Among them, the distance image sequence includes at least one distance image, and the motion artifacts of each distance image are different. In the process of image reconstruction in this application, a distance image sequence corresponding to the reconstructed image is acquired to analyze the change of motion artifacts of the reconstructed image through multiple distance images in the distance image sequence, and then a final medical image is generated according to the distance image sequence. This medical image is an image after motion artifact correction processing. In this way, through the distance image sequence of the reconstructed image, the motion artifacts in the medical image can be effectively reduced, and the image quality of the medical image can be improved.

[0082] In one embodiment, during the scanning of the scanned object, a motion monitoring device can also be set to acquire the body surface motion information of the scanned object, and then adjust the distance weight relationship according to the body surface motion information.

[0083] Among them, the motion monitoring device can be a lidar, a millimeter wave radar, an infrared sensor, etc., and the body surface motion information can include the motion direction and motion amplitude of each part of the scanned object at a time point.

[0084] In a possible implementation, the adjustment process of the distance weight relationship can be as follows: Determine the change of the motion intensity of the scanned object during the scanning period according to the body surface motion information; adjust the imaging weights corresponding to each distance in the distance weight relationship according to the motion intensity at each time point.

[0085] As an example, for the acquisition of the original chest scan data of the scanned object at time T1, if the body surface motion information collected by the motion monitoring device indicates that the chest motion amplitude of the scanned object is large at time T1, when using the original scan data at time T1 for image reconstruction, motion artifacts are very likely to be introduced.

[0086] Based on this, the distance weight relationship can be adjusted to reduce the imaging weight value corresponding to the distance from the parallel beam light source of the imaging device to the image layer at time T1, reduce the imaging contribution rate of the original projection data collected at this distance to the reconstructed image, and reduce the possibility of motion artifacts existing in the reconstructed image.

[0087] It should be noted that the present embodiment does not limit the curve corresponding to the distance weight relationship, which may be Figure 3 the Gaussian function curve shown in the figure, or other function curves.

[0088] In this embodiment, in the scan imaging provided with a motion monitoring device, the imaging weights corresponding to each distance in the distance weight relationship can be adjusted according to the body surface motion information of the scanned object monitored in the same period, reducing the possibility of introducing motion artifacts in the image reconstruction process.

[0089] In one embodiment, when the reconstructed image is a reconstructed slice image and the distance image sequence is the first image sequence, as Figure 5 shown in the figure, the implementation process of generating a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image in step 230 above includes the following steps:

[0090] Step 510: Determine the target slice image corresponding to each reconstructed slice image according to the first image sequence corresponding to each reconstructed slice image.

[0091] Wherein, each reconstructed slice corresponds to a first image sequence, that is, each reconstructed slice corresponds to multiple first images, and the multiple first images are distance images obtained through the distance weight relationship and having a time sequence.

[0092] It should be noted that since the motion artifacts of the first images in the first image sequence are different, therefore, by analyzing the motion artifact conditions of the multiple first images corresponding to each reconstructed slice image, the first image with the weakest motion artifact is determined as the target slice image corresponding to the reconstructed slice.

[0093] In a possible implementation manner, the implementation process of step 510 may be: based on the first image sequence corresponding to each reconstructed slice image, subtract adjacent first images to analyze the change intensity of the motion artifacts of the first image sequence; select the target slice image from the first image sequences corresponding to each reconstructed slice image according to the change intensity of the motion artifacts of the first image sequence.

[0094] That is to say, analyze the motion artifact intensity of each first image in the first image sequence, determine the first image with the weakest change in motion artifacts from the multiple first images, and use it as the target slice image.

[0095] As an example, if the first image sequence includes 5 first images: Image 1, Image 2, Image 3, Image 4, and Image 5. First, subtract Image 2 from Image 1 to determine the first artifact intensity; subtract Image 3 from Image 2 to determine the second artifact intensity; subtract Image 4 from Image 3 to determine the third artifact intensity; subtract Image 5 from Image 4 to determine the fourth artifact intensity. Then, based on the first artifact intensity, the second artifact intensity, the third artifact intensity, and the fourth artifact intensity, analyze the change intensity of the motion artifacts of the 5 first images, and determine the target layer image as the first image with the weakest artifact intensity in the first image sequence.

[0096] In addition, if the motion artifacts of the first images in the first image sequence are different, the motion characteristic information of the scanned object reflected by each first image is also different. Furthermore, based on the motion characteristic information of the scanned object, artifact correction can be performed on the first image sequence to determine the target layer image.

[0097] In another possible implementation, the implementation process of step 510 can be: analyze the motion characteristic information of the scanned object in each reconstructed layer image according to the first image sequence corresponding to each reconstructed layer image; perform artifact correction on the first image sequence corresponding to each reconstructed layer image according to the motion characteristic information of the scanned object in each reconstructed layer image, and determine the target layer image corresponding to each reconstructed layer image.

[0098] Among them, the motion characteristic information includes the motion direction and the motion amplitude.

[0099] Furthermore, artifact correction of the first image sequence corresponding to each reconstructed layer can be implemented through a motion correction algorithm or through a network model trained by deep learning. This embodiment does not limit this.

[0100] As an example, taking the layer image prediction model trained by deep learning as an example, for any reconstructed layer, analyze the motion artifacts of each first image in the first image sequence through the layer image prediction model to determine the motion characteristic information of the scanned object in the reconstructed layer image. Then, the layer image prediction model performs artifact correction on the first image sequence corresponding to the reconstructed layer according to the motion characteristic information, and outputs the target layer image corresponding to the reconstructed layer according to the artifact correction result.

[0101] It should be noted that in this implementation, the target layer image can be directly output by combining the motion characteristic information and the first image sequence. It is also possible to perform artifact correction on multiple first images in the first image sequence according to the motion characteristic information, output the corrected first image sequence, and then determine the first image with the weakest motion artifact from the corrected first image sequence and use it as the target layer image.

[0102] Step 520: Generate a medical image of the scanned object based on the target layer images corresponding to the reconstructed layer images.

[0103] In this step, after obtaining the target layer images corresponding to the reconstructed layer images, a medical image of the scanned object can be generated based on the target layer images. This medical image is the image obtained after motion artifact correction processing.

[0104] In this embodiment, for each reconstructed layer image, the target layer image corresponding to the reconstructed layer image is determined according to the first image sequence corresponding to the reconstructed layer image, ensuring that the motion artifacts in the target layer image are the weakest, or ensuring that the target layer image is the optimal layer image obtained by artifact correction processing. In this way, a medical image of the scanned object is generated based on the target layer images corresponding to the reconstructed layer images, making the motion artifacts in the medical image the weakest and the image quality the best.

[0105] In another embodiment, when the reconstructed image is a reconstructed layer image and the distance image sequence is the first image sequence, as Figure 6 shown, the implementation process of generating a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image in the above step 230 includes the following steps:

[0106] Step 610: Based on a preset evaluation index, score each of the multiple candidate images respectively to obtain the scoring results of the candidate images.

[0107] Among them, the candidate images are composed of the first image sequences corresponding to multiple reconstructed layer images. That is, first select one first image in the corresponding chronological order from the first image sequence corresponding to each reconstructed layer image, and then form a candidate image according to one first image corresponding to each reconstructed layer image.

[0108] As an example, if there are 5 reconstructed layer images and the first image sequence corresponding to each reconstructed layer image includes 10 first images, then first select one first image from the 10 first images corresponding to each reconstructed layer image, and form a candidate image according to the 5 selected first images. By analogy, according to the first image sequences corresponding to the 5 reconstructed layer images, 10 candidate images can be generated, and each candidate image is composed of one first image in the 5 reconstructed layer images.

[0109] Furthermore, the preset evaluation index in this step is a parameter item for measuring the quality of the candidate images, and the evaluation index can include one or more of anatomical structure clarity, key part contrast, image signal uniformity, image noise level, and artifact suppression degree.

[0110] It should be understood that the anatomical structure clarity can be the clarity of the texture and its boundaries of each part (or each anatomical structure) on the image to be scored (i.e., the candidate image in step 610 and the second image in step 710). The anatomical structure can be the anatomical structure of the parts included in the image to be scored. For example, if the image to be scored is a brain image, the anatomical structure is the brain anatomical structure (such as the cerebrum, diencephalon, cerebellum, brainstem, etc.); another example is that if the image to be scored is a kidney image, then the anatomical structure is the kidney anatomical structure (such as renal cortex, renal medulla, etc.). The key part contrast can be the contrast between light and dark regions in the image to be scored, such as the contrast of different brightness levels between the white of the brightest region and the black of the darkest region, that is, the size of the gray-scale contrast in the image. The key part can be the part that needs to be observed of the patient or other medical experimental subjects, such as the cranial bone of the brain, the lung window of the chest, the soft tissue of the abdomen, etc. The image signal uniformity can be the degree of uniformity of the image signal obtained when the imaging device scans the scanned object. The image noise level can be the degree of inclusion of unwanted or redundant interference information existing in the image to be scored. For example, there may be some isolated noise points in certain regions of the image to be scored. The degree of artifact suppression can be the degree of elimination or suppression of artifacts in the image to be scored.

[0111] Furthermore, the score of each candidate image can be the score of the candidate image under at least one evaluation index, that is, including one or more of the score of anatomical structure clarity, the score of key part contrast, the score of image signal uniformity, the score of image noise level, and the score of degree of artifact suppression.

[0112] Among them, the score range of each evaluation index can be set by the user. For example, the score range can be set between 1 - 5 points. The higher the score, the better the image quality.

[0113] Specifically, the higher the score of anatomical structure clarity, the clearer the anatomical structure of the candidate image and the better the image quality; the higher the score of key part contrast, the higher the contrast of the target part of the candidate image and the better the image quality; the higher the score of image signal uniformity, the higher the image signal uniformity of the candidate image and the better the image quality; the higher the score of image noise level, the more the noise level of the candidate image meets the requirements (for example, the noise level in the uniform region of the image is lower and the region with objects contains an appropriate amount of noise), and the better the image quality; the higher the score of degree of artifact suppression, the lower the artifact level of the candidate image and the better the image quality.

[0114] Step 620: Determine the medical image of the scanned object according to the scoring results of each candidate image.

[0115] In this step, for any candidate image, according to the preset evaluation metrics, the candidate image is scored from at least one image quality evaluation dimension to obtain the scores of each evaluation metric. Further, according to the scores of at least one evaluation metric of each candidate image, the candidate image with the highest overall quality score is determined as the medical image of the scanned object.

[0116] As an example, the scores of each evaluation metric can be weighted and averaged to obtain the overall quality score of the candidate image.

[0117] Optionally, different weights can also be assigned to different evaluation metrics, and after multiplying the weights by the scores of their corresponding evaluation metrics and then summing and averaging, the overall quality score of the candidate image is obtained.

[0118] Among them, the weights of each evaluation metric can be determined according to medical diagnostic experience or by other means, and this embodiment does not limit this. For example, the evaluation metrics of the candidate image include anatomical structure clarity, target part contrast, and image signal uniformity, and their weights are 0.4, 0.5, and 0.3 respectively.

[0119] In this embodiment, multiple candidate images of the scanned object can be generated through the first image sequence corresponding to multiple reconstructed slice images. Since the motion artifacts of each first image in the first image sequence are different, the motion artifacts of each candidate image are also different. Further, the candidate images are evaluated from different image quality evaluation dimensions according to the preset evaluation metrics, and then according to the scoring results of each candidate image, the candidate image with the highest overall quality score is determined as the medical image of the scanned object, so that the motion artifacts of the medical image are the weakest and the image quality is the best.

[0120] In another embodiment, when the reconstructed image is specifically a reconstructed volume image and the distance image sequence is specifically a second image sequence, as Figure 7 shown, the implementation process of generating the medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image in step 230 above includes the following steps:

[0121] Step 710: Based on the preset evaluation metrics, score each of the multiple second images in the second image sequence corresponding to the reconstructed volume image to obtain the scoring results of each second image.

[0122] Among them, the preset evaluation metrics include one or more of anatomical structure clarity, key part contrast, image signal uniformity, image noise level, and artifact suppression degree.

[0123] It should be noted that the difference between step 710 and step 610 is only that the evaluation object of step 710 is multiple second images directly obtained by three-dimensional reconstruction, and the second images are three-dimensional volume images obtained by reconstruction; while the evaluation object of step 610 is a candidate volume image composed of reconstructed sectional images. However, the implementation principles and specific implementation processes of the two steps are similar, so they will not be elaborated here. For the explanations and limitations of step 610, please refer to the above content.

[0124] Step 720: Determine the medical image of the scanned object according to the scoring results of each second image.

[0125] In this step, for any second image, according to at least one of the above-listed evaluation indicators, the second image is scored from at least one image quality evaluation dimension to obtain the scores of each evaluation indicator. Further, according to the scores of each evaluation indicator of each second image, the second image with the highest overall quality score is determined as the medical image of the scanned object.

[0126] Optionally, the motion feature information of the scanned object corresponding to each second image in the second image sequence corresponding to the reconstructed volume image can be analyzed; then, according to the motion feature information of the scanned object, artifact correction is performed on the second image sequence corresponding to each reconstructed volume image to determine the medical image of the scanned object.

[0127] In this embodiment, for the multiple second images in the second image sequence corresponding to the reconstructed volume image, the motion artifacts of each second image are different. The second image is evaluated from different image quality evaluation dimensions according to the preset evaluation indicators, so as to determine the second image with the highest overall quality score as the medical image of the scanned object, making the motion artifacts of the medical image the weakest and the image quality the best.

[0128] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0129] Based on the same inventive concept, an embodiment of the present application further provides an image reconstruction apparatus for implementing the above-mentioned image reconstruction method. The solution provided by this apparatus for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the following image reconstruction apparatus can refer to the limitations on the image reconstruction method in the foregoing, and will not be repeated here.

[0130] In one embodiment, as Figure 8 shown, an image reconstruction apparatus is provided. The apparatus 800 includes: an acquisition module 810, a sequence reconstruction module 820, and an image generation module 830, where:

[0131] The acquisition module 810 is configured to acquire the original projection data of the scanned object;

[0132] The sequence reconstruction module 820 is configured to perform image reconstruction on the original projection data to obtain a distance image sequence corresponding to the reconstructed image; the distance image sequence includes at least one distance image, and the motion artifacts of each distance image are different;

[0133] The image generation module 830 is configured to generate a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image; the medical image is an image after motion artifact correction processing.

[0134] In one of the embodiments, the reconstructed image includes a plurality of reconstructed slice images, and the distance image sequence includes a first image sequence;

[0135] The sequence reconstruction module 820 includes:

[0136] The first reconstruction unit is configured to perform image reconstruction on the original projection data based on a preset distance weight relationship to obtain a first image sequence corresponding to each reconstructed slice image.

[0137] In one of the embodiments, the first reconstruction unit includes:

[0138] The data processing subunit is configured to perform weighted processing on the original projection data according to the distance weight relationship according to the distance from the projection light source point to the reconstructed slice to obtain a plurality of weighted projection data corresponding to each reconstructed slice image;

[0139] The reconstruction subunit is configured to perform image reconstruction on the plurality of weighted projection data corresponding to each reconstructed slice image to obtain a first image sequence corresponding to each reconstructed slice image.

[0140] In one of the embodiments, the image generation module 830 includes:

[0141] The first determination unit is configured to determine a target slice image corresponding to each reconstructed slice image according to the first image sequence corresponding to each reconstructed slice image;

[0142] An image generation unit, configured to generate a medical image of a scanned object according to target layer images corresponding to respective reconstructed layer images.

[0143] In one embodiment, the first determination unit includes:

[0144] An artifact analysis subunit, configured to subtract adjacent first images based on a first image sequence corresponding to each reconstructed layer image, and analyze the change intensity of motion artifacts in the first image sequence;

[0145] A selection subunit, configured to select a target layer image from the first image sequences corresponding to the respective reconstructed layer images according to the change intensity of motion artifacts in the first image sequence.

[0146] In one embodiment, the first determination unit includes:

[0147] A motion analysis subunit, configured to analyze motion feature information of the scanned object in each reconstructed layer image according to a first image sequence corresponding to each reconstructed layer image;

[0148] An artifact correction subunit, configured to perform artifact correction on the first image sequences corresponding to the respective reconstructed layer images according to the motion feature information of the scanned object in each reconstructed layer image, and determine target layer images corresponding to the respective reconstructed layer images.

[0149] In one embodiment, the image generation module 830 includes:

[0150] A first scoring unit, configured to score multiple candidate images respectively based on a preset evaluation index, and obtain scoring results of the respective candidate images; the candidate images are composed of first image sequences corresponding to multiple reconstructed layer images;

[0151] A second determination unit, configured to determine a medical image of the scanned object according to the scoring results of the respective candidate images.

[0152] In one embodiment, the reconstructed image includes a reconstructed volume image, and the distance image sequence includes a second image sequence;

[0153] The sequence reconstruction module 820 includes:

[0154] A second reconstruction unit, configured to perform image reconstruction on the original projection data based on a preset distance weight relationship to obtain a second image sequence corresponding to the reconstructed volume image.

[0155] In one embodiment, the image generation module 830 includes:

[0156] A second scoring unit, configured to score multiple second images in a second image sequence corresponding to a reconstructed body image respectively based on a preset evaluation index, and obtain a scoring result of each second image;

[0157] A third determining unit, configured to determine a medical image of a scanned object according to the scoring results of the second images.

[0158] Each module in the above image reconstruction device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in the computer device in the form of software, so as to facilitate the processor to call and execute operations corresponding to each of the above modules.

[0159] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 9 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program stored in the non-volatile storage medium to run. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The computer program, when executed by the processor, implements an image reconstruction method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0160] Those skilled in the art can understand that Figure 9 the structure shown in

[0161] is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0162] Obtain the original projection data of the scanned object;

[0163] Perform image reconstruction on the original projection data to obtain a sequence of distance images corresponding to the reconstructed images; the sequence of distance images includes at least one distance image, and the motion artifacts of each distance image are different;

[0164] Generate a medical image of the scanned object according to the sequence of distance images corresponding to the reconstructed images; the medical image is an image after motion artifact correction processing.

[0165] For a computer device provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0166] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0167] Obtain the original projection data of the scanned object;

[0168] Perform image reconstruction on the original projection data to obtain a sequence of distance images corresponding to the reconstructed images; the sequence of distance images includes at least one distance image, and the motion artifacts of each distance image are different;

[0169] Generate a medical image of the scanned object according to the sequence of distance images corresponding to the reconstructed images; the medical image is an image after motion artifact correction processing.

[0170] For a computer-readable storage medium provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0171] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0172] Obtain the original projection data of the scanned object;

[0173] Perform image reconstruction on the original projection data to obtain a sequence of distance images corresponding to the reconstructed images; the sequence of distance images includes at least one distance image, and the motion artifacts of each distance image are different;

[0174] Generate a medical image of the scanned object according to the sequence of distance images corresponding to the reconstructed images; the medical image is an image after motion artifact correction processing.

[0175] For a computer program product provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0176] It should be noted that the user information involved in this application (including but not limited to personal information of the scanned object, medical record information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties.

[0177] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0178] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0179] The above-described embodiments only represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of the patent of this application should be subject to the appended claims.

Claims

1. An image reconstruction method, characterized in that, The method includes: Obtaining the original projection data of the scanning object; Performing image reconstruction on the original projection data based on a preset distance weight relationship, and obtaining a distance image sequence corresponding to the reconstructed image by adjusting the application position of the distance weight relationship; the distance image sequence includes at least one distance image, and the motion artifacts of each distance image are different; wherein, the reconstructed image includes a plurality of reconstructed slice images, and the distance image sequence includes a first image sequence; the image reconstruction process includes: performing weighted processing on the original projection data according to the distance from the projection light source point to the reconstructed slice based on the distance weight relationship to obtain a plurality of weighted projection data corresponding to each reconstructed slice image; performing image reconstruction on the plurality of weighted projection data corresponding to each reconstructed slice image to obtain a first image sequence corresponding to each reconstructed slice image; Analyzing the motion artifact conditions of each distance image according to the distance image sequence corresponding to the reconstructed image, and generating a medical image of the scanning object according to the distance image with the weakest motion artifact; the medical image is an image after motion artifact correction processing.

2. The method according to claim 1, wherein The step of analyzing the motion artifact conditions of each distance image according to the distance image sequence corresponding to the reconstructed image, and generating a medical image of the scanning object according to the distance image with the weakest motion artifact includes: Determining a target slice image corresponding to each reconstructed slice image according to the first image sequence corresponding to each reconstructed slice image; Generating a medical image of the scanning object according to the target slice image corresponding to each reconstructed slice image.

3. The method according to claim 2, characterized in that, The step of determining a target slice image corresponding to each reconstructed slice image according to the first image sequence corresponding to each reconstructed slice image includes: Based on the first image sequence corresponding to each reconstructed slice image, subtracting adjacent first images, and analyzing the change intensity of the motion artifacts of the first image sequence; Selecting the target slice image from the first image sequence corresponding to each reconstructed slice image according to the change intensity of the motion artifacts of the first image sequence.

4. The method according to claim 2, characterized in that The step of determining a target slice image corresponding to each reconstructed slice image according to the first image sequence corresponding to each reconstructed slice image includes: Analyzing the motion feature information of the scanning object in each reconstructed slice image according to the first image sequence corresponding to each reconstructed slice image; Performing artifact correction on the first image sequence corresponding to each reconstructed slice image according to the motion feature information of the scanning object in each reconstructed slice image, and determining the target slice image corresponding to each reconstructed slice image.

5. The method according to claim 4, characterized in that, The motion feature information includes a motion direction and a motion amplitude.

6. The method according to claim 4, wherein The step of performing artifact correction on the first image sequence corresponding to each reconstructed slice image according to the motion feature information of the scanning object in each reconstructed slice image, and determining the target slice image corresponding to each reconstructed slice image includes: For any reconstructed slice, analyze the motion artifacts of each first image in the first image sequence corresponding to the reconstructed slice image through a slice image prediction model to determine the motion feature information of the scanned object in the reconstructed slice image; Based on the motion feature information, use the slice image prediction model to perform artifact correction on the first image sequence corresponding to the reconstructed slice; Output the target slice image corresponding to the reconstructed slice according to the artifact correction result.

7. The method according to claim 1, wherein The analyzing the motion artifact conditions of each of the distance images according to the distance image sequence corresponding to the reconstructed image and generating a medical image of the scanned object based on the distance image with the weakest motion artifact includes: Based on a preset evaluation metric, score each of a plurality of candidate volume images respectively to obtain the scoring results of each of the candidate volume images; the candidate volume images are composed of the first image sequences corresponding to a plurality of the reconstructed slice images; Determine the medical image of the scanned object according to the scoring results of each of the candidate volume images.

8. The method according to claim 1, characterized in that The reconstructed image includes a reconstructed volume image, and the distance image sequence includes a second image sequence; The performing image reconstruction on the original projection data based on a preset distance weight relationship and obtaining a distance image sequence corresponding to the reconstructed image by adjusting the application position of the distance weight relationship includes: Perform image reconstruction on the original projection data based on the distance weight relationship to obtain a second image sequence corresponding to the reconstructed volume image.

9. The method according to claim 8, wherein The analyzing the motion artifact conditions of each of the distance images according to the distance image sequence corresponding to the reconstructed image and generating a medical image of the scanned object includes: Based on a preset evaluation metric, score each of a plurality of second images in the second image sequence corresponding to the reconstructed volume image respectively to obtain the scoring results of each of the second images; Determine the medical image of the scanned object according to the scoring results of each of the second images.

10. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

Images