CN115018947A - Image reconstruction method and computer device - Google Patents

Abstract

The application relates to an image reconstruction method and a computer device, the method comprises the following steps: acquiring original projection data of a scanned object; carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image; the range image sequence comprises at least one range image, and the motion artifacts of the range images are different; generating a medical image of a scanned 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, the distance image sequence corresponding to the reconstructed image is acquired, so that the change condition of the motion artifact of the reconstructed image is analyzed through a plurality of distance images in the distance image sequence, and a final medical image is generated according to the distance image sequence, wherein the medical image is an image subjected to motion artifact correction processing. Therefore, the motion artifact in the medical image can be effectively weakened and the image quality of the medical image can be improved by reconstructing the distance image sequence of the image.

Description

Image reconstruction method and computer device

Technical Field

The present application relates to the field of medical imaging technology, and in particular, to an image reconstruction method and a computer device.

Background

During the scanning of a certain scanning area of a scanning object by using a medical imaging apparatus, there may be autonomous or involuntary movements of the scanning object (for example, small amplitude movements or rotations of the autonomous torso of the scanning object, autonomous respiratory movements, involuntary heart beats and gastrointestinal peristalsis, etc.), and these autonomous or involuntary movements may form motion artifacts on the reconstructed image.

The occurrence of motion artifacts can reduce the sharpness of the reconstructed image, which in turn affects the accuracy of the diagnostic results obtained from the reconstructed image.

Disclosure of Invention

In view of the foregoing, it is desirable to provide an image reconstruction method and a computer device that can reduce motion artifacts of a reconstructed image and improve accuracy of an image reconstruction result.

In a first aspect, the present application provides an image reconstruction method, including:

acquiring original projection data of a scanned object;

carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image; the range image sequence comprises at least one range image, and the motion artifacts of the range images are different;

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

In one embodiment, the reconstructed image comprises a plurality of reconstructed slice images, and the range image sequence comprises a first image sequence;

carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a plurality of reconstructed images, wherein the image reconstruction comprises the following steps:

and performing image reconstruction on the original projection data based on a preset distance weight relation to obtain a first image sequence corresponding to each reconstruction layer image.

In one embodiment, image reconstruction is performed on the original projection data based on a preset distance weight relationship, so as to obtain a first image sequence corresponding to each reconstruction slice image, including:

according to the distance weight relationship, weighting the original projection data according to the distance from the projection light source point to the reconstruction layer to obtain a plurality of weighted projection data corresponding to each reconstruction layer image;

and carrying out image reconstruction on the plurality of weighted projection data corresponding to each reconstruction layer image to obtain a first image sequence corresponding to each reconstruction layer image.

In one embodiment, generating a medical image of a scanned object from a sequence of range images corresponding to reconstructed images includes:

determining a target level image corresponding to each reconstruction level image according to the first image sequence corresponding to each reconstruction level image;

and generating a medical image of the scanned object according to the target plane image corresponding to each reconstruction plane image.

In one embodiment, determining the target slice image corresponding to each reconstruction slice image according to the first image sequence corresponding to each reconstruction slice image includes:

based on the first image sequence corresponding to each reconstruction layer image, subtracting adjacent first images, and analyzing the change intensity of the motion artifact of the first image sequence;

and selecting the target plane image from the first image sequence corresponding to each reconstruction plane image according to the change intensity of the motion artifact of the first image sequence.

In one embodiment, determining the target slice image corresponding to each reconstruction slice image according to the first image sequence corresponding to each reconstruction slice image includes:

analyzing the motion characteristic information of the scanning object in each reconstruction layer image according to the first image sequence corresponding to each reconstruction layer image;

and according to the motion characteristic information of the scanning object in each reconstruction layer image, artifact correction is carried out on the first image sequence corresponding to each reconstruction layer image, and the target layer image corresponding to each reconstruction layer image is determined.

In one embodiment, generating a medical image of a scanned object from a sequence of range images corresponding to reconstructed images includes:

respectively scoring the candidate body images based on preset evaluation indexes to obtain a scoring result of each candidate body image; the candidate body image is composed according to a first image sequence corresponding to a plurality of reconstruction layer images;

and determining a medical image of the scanning object according to the scoring result of each candidate body image.

In one embodiment, reconstructing the image comprises reconstructing a volumetric image, the range image sequence comprising a second image sequence;

carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image, wherein the image reconstruction comprises the following steps:

and performing image reconstruction on the original projection data based on a preset distance weight relation to obtain a second image sequence corresponding to the reconstructed body image.

In one embodiment, generating a medical image of a scanned object from a sequence of range images corresponding to reconstructed images includes:

respectively scoring a plurality of second images in a second image sequence corresponding to the reconstructed body image based on a preset evaluation index, and acquiring a scoring result of each second image;

and determining a medical image of the scanning object according to the grading result of each second image.

In a second aspect, the present application further provides an image reconstruction apparatus, comprising:

the acquisition module is used for acquiring original projection data of a scanning object;

the sequence reconstruction module is used for carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image; the range image sequence comprises at least one range image, and the motion artifacts of the range images are different;

the image generation module is used for 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.

In a third aspect, the present application further provides a computer device, where the computer device includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of any one of the method embodiments in the first aspect when executing the computer program.

In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of any of the method embodiments of the first aspect.

In a fifth aspect, the present application also provides a computer program product comprising a computer program that, when executed by a processor, performs the steps of any of the method embodiments of the first aspect.

According to the image reconstruction method and the computer device, the computer device obtains original projection data of a scanning object; carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image; and generating a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image. The range image sequence comprises at least one range image, and the motion artifacts of the range images are different. According to the method and the device, in the process of image reconstruction, the distance image sequence corresponding to the reconstructed image is obtained, the change condition of the motion artifact of the reconstructed image is analyzed through a plurality of distance images in the distance image sequence, and then a final medical image is generated according to the distance image sequence, wherein the medical image is an image subjected to motion artifact correction processing. Therefore, the motion artifact in the medical image can be effectively weakened and the image quality of the medical image can be improved by reconstructing the distance image sequence of the image.

Drawings

FIG. 1 is a diagram of an embodiment of an image reconstruction method;

FIG. 2 is a schematic flow chart diagram illustrating an exemplary method for reconstructing an image;

FIG. 3 is a diagram illustrating distance weight relationships in one embodiment;

FIG. 4 is a schematic diagram of a sequence of range images in one embodiment;

FIG. 5 is a schematic flow chart diagram of generating a medical image in one embodiment;

FIG. 6 is a schematic flow chart of generating a medical image according to another embodiment;

FIG. 7 is a schematic flow chart of generating a medical image in yet another embodiment;

FIG. 8 is a block diagram showing the structure of an image reconstruction apparatus according to an embodiment;

FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

In the medical field, since a certain time is required for scan imaging, the autonomous or non-autonomous motion of the scan object destroys the consistency and integrity of the projection data, thereby showing various artifacts, called motion artifacts, in the reconstructed image. The motion artifact mainly presents in a plurality of forms such as tissue image overlapping blurring, strip artifact, image contour displacement, and objects with similar attachments appearing in the cavity. The occurrence of artifacts can reduce the definition of a reconstructed image, influence the normal diagnosis of doctors, bring difficulties to the post-processing work of images such as automatic lesion detection, computer-aided diagnosis, three-dimensional reconstruction and the like based on the reconstructed image, and seriously restrict the development of scanning imaging and the application of the reconstructed image in clinical diagnosis.

Based on this, the application provides an image reconstruction method and computer equipment, which perform image reconstruction according to original projection data of a scanned object, acquire a plurality of distance images with different motion artifacts corresponding to a reconstructed image in a reconstruction process, and then generate a medical image after motion artifact correction processing according to the plurality of distance images. The medical image of the scanning object is generated by reconstructing the distance image sequence corresponding to the image, so that the motion artifact of the medical image can be effectively reduced, and the quality of the medical image is improved.

The image reconstruction method provided by the application can be applied to the application environment shown in fig. 1. As shown in fig. 1, the application environment may include an imaging device 110 and a computer device 120, the imaging device 110 communicating with the computer device 120 over a network to enable data transfer and instruction interaction.

In some embodiments, the imaging device 110 may be a non-invasive biomedical imaging apparatus, including, for example, a single modality scanner and/or a multi-modality scanner, for disease diagnosis or research purposes. Among others, the single modality scanner may include, for example, an ultrasound scanner, an X-ray scanner, a CT scanner, a Magnetic Resonance Imaging (MRI) scanner, an ultrasonograph, an Optical Coherence Tomography (OCT) scanner, an Ultrasound (US) scanner, an intravascular ultrasound (IVUS) scanner, a Near Infrared spectroscopy (NIRS) scanner, a Far Infrared (FIR) scanner, or the like, or any combination thereof. The multi-modality 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, and the like. It should be understood that the scanner provided above is provided for illustrative purposes only and is not intended to limit the scope of the present application.

As one example, the imaging device 110 may specifically include a gantry, a detector, an examination region, a scanning bed, and a radiation source. The stand can be used for supporting a detector and a ray source, and the scanning bed can be used for placing a scanning object to be scanned; the radiation source may emit radiation toward the scan object to irradiate the scan object; the detector may be configured to receive radiation that traverses the scanned object.

Further, imaging device 110 may also include modules and/or components for performing imaging and/or correlation analysis. For example, the imaging device 110 may include a processor that may be configured to perform the image reconstruction methods provided herein.

Optionally, the imaging device 110 may also include a display screen that may be used to observe data information of the imaging device 110 and/or a scanned object scanned by the imaging device 110. For example, the medical staff can observe the focus information of the detection parts of the chest, the bones, the mammary glands and the like of the scanning object through the display screen.

In some embodiments, the imaging device 110 may also send the acquired scan data (e.g., raw projection data of the scanned object) to the computer device 120 via a network for further analysis, processing, and display.

Wherein the computer device 120 may be at least one device other than the imaging device 110. For example, various personal computers, laptops, smart phones, tablets, portable wearable devices, or any combination thereof; also, for example, a single server or group of servers, the group of servers can be centralized or distributed.

Optionally, storage device 130 (not shown in fig. 1) may also be included in the application environment for storing data, instructions, and/or any other information. For example, the storage device 130 may store raw projection data of the scanned object acquired by the imaging device 110, and/or medical images of the scanned object processed by the computer device 120, and so on.

As one example, the storage device may include one or more of mass storage, removable storage, volatile read-write memory, read-only memory, and the like. Additionally, 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 and hybrid cloud, and the like).

It should be noted that the foregoing description is provided for illustrative purposes only, and is not intended to limit the scope of the present application. Many variations and modifications will occur to those skilled in the art in light of the teachings herein. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments, without departing from the scope of the present application.

After describing the application background and application environment of the present application, the following detailed description will be provided to specifically describe the technical solutions of the embodiments of the present application and how to solve the above technical problems by using the embodiments and referring to the drawings. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. It should be noted that an execution subject of the image reconstruction method provided in the embodiment of the present application may be the imaging device 110 including the processor in fig. 1, the computer device 120 in fig. 1, or an image reconstruction apparatus, and the apparatus may be implemented as part or all of the processor (which may be specifically a processor in the imaging device/the computer device) by software, hardware, or a combination of software and hardware. It is to be understood that the embodiments described are only some of the embodiments of the present application and not all of them.

In an embodiment, as shown in fig. 2, an image reconstruction method is provided, and the embodiment takes the application of the method to a computer device 120 as an example, and includes the following steps:

step 210: raw projection data of a scanned object is acquired.

The raw projection data is projection data obtained by scanning at least one portion of a scanned object by the imaging device 110, where the scanned object may include a biological object and/or a non-biological object. For example, the scan object may include a specific part of a human body, such as a head, a chest, an abdomen, or one or more parts. The scan object may also be an artificial composition of organic and/or inorganic matter, living or non-living, which the present embodiment does not limit.

When the execution subject is the computer device 120, the implementation process of step 210 is: the imaging device 110 obtains raw projection data after completing a scanning operation for scanning at least a portion of the object. Further, the computer device 120 acquires raw projection data of the scanned object from the imaging device 110.

It should be noted that, if the scanned region is a chest region, the motion artifact existing in the medical image may be caused by respiratory motion of the scanned object, and by the image reconstruction method provided in this embodiment, the motion artifact caused by respiratory motion in the reconstructed image can be reduced; if the scanned part is the abdomen, the motion artifact existing in the medical image may be caused by the intestinal lumen motion of the scanned object, and the motion artifact caused by respiratory motion in the reconstructed image can be reduced by the image reconstruction method provided by the embodiment. In addition, the scanning portion may also be other portions in the scanned object that have autonomous or involuntary movement, which is not limited in this embodiment.

Step 220: carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image; the range image sequence comprises at least one range image, and the range images differ in their motion artifacts.

When the original projection data is subjected to image reconstruction, two-dimensional image reconstruction can be performed, and three-dimensional image reconstruction can also be directly performed. Thus, if the reconstructed image in the present application includes a plurality of reconstructed slice images and/or reconstructed volume images, step 220 further includes the following two cases:

(1) the reconstructed image includes a plurality of reconstructed slice images and the range image sequence includes a first image sequence.

In this case, the implementation process of step 220 may be: and performing image reconstruction on the original projection data based on a preset distance weight relation to obtain a first image sequence corresponding to each reconstruction layer image.

Specifically, the reconstruction process of the reconstructed slice image may be: according to the distance weight relationship, weighting the original projection data according to the distance from the projection light source point to the reconstruction layer to obtain a plurality of weighted projection data corresponding to each reconstruction layer image; and carrying out image reconstruction on the plurality of weighted projection data corresponding to each reconstruction layer image to obtain a first image sequence corresponding to each reconstruction layer image.

(2) Reconstructing the image includes reconstructing the image, and the range image sequence includes the second image sequence.

In this case, the implementation process of step 220 may be: and performing image reconstruction on the original projection data based on a preset distance weight relation to obtain a second image sequence corresponding to the reconstructed body image.

As an example, the distance weight relationship in the embodiment of the present application may be implemented using a gaussian function or a similar functional form. Referring to the distance weight curve shown in fig. 3, the abscissa represents the distance from the parallel-beam light source of the imaging device to the image plane, and the ordinate represents the imaging weight of the original projection data at the corresponding distance.

Specifically, by adjusting the application position (e.g., horizontal movement) of the distance weight relationship, a series of distance images can be generated, the distance images in the distance image sequence have higher time resolution than the reconstructed images, and artifacts at partial planes can be obviously reduced.

Further, (a) in fig. 4 is a distance image generated by moving the distance weight curve leftward, and (b) in fig. 4 is a distance image generated without moving the distance weight curve, and (c) in fig. 4 is a distance image generated by moving the distance weight curve rightward. As can be seen from fig. 4, by shifting the position of the distance weight curve, different distance images can be generated, and the degree of motion artifact contained in each distance image differs. Based on the above, from a plurality of distance images of the same layer time series, the distance image with the weakest motion artifact and the best imaging quality can be found for generating the medical image of the scanning object.

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

In one possible implementation manner, the implementation procedure of step 230 may be: and analyzing the motion artifact condition of each distance image according to the distance image sequence corresponding to the reconstructed image, and generating the medical image of the scanning object according to the distance image with the weakest motion artifact so as to ensure that the motion artifact of the medical image subjected to artifact correction processing through the distance image sequence is weakest and the image quality is optimal.

In the image reconstruction method, computer equipment acquires original projection data of a scanned object; carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image; and generating a medical image of the scanned object according to the distance image sequence corresponding to the reconstructed image. The range image sequence comprises at least one range image, and the motion artifacts of the range images are different. According to the method and the device, in the process of image reconstruction, the distance image sequence corresponding to the reconstructed image is obtained, the change condition of the motion artifact of the reconstructed image is analyzed through a plurality of distance images in the distance image sequence, and then a final medical image is generated according to the distance image sequence, wherein the medical image is an image subjected to motion artifact correction processing. Therefore, the motion artifact in the medical image can be effectively weakened and the image quality of the medical image can be improved by reconstructing the distance image sequence of the image.

In one embodiment, in the process of scanning the scanning object, the body surface motion information of the scanning object can be acquired by arranging the motion monitoring device, and the distance weight relationship is adjusted according to the body surface motion information.

The motion monitoring device may be a laser radar, a millimeter wave radar, an infrared sensor, or the like, and the body surface motion information may include a motion direction and a motion amplitude of each part of the scanned object at a time point.

In one possible implementation manner, the adjusting process of the distance weight relationship may be: determining the change condition of the motion intensity of the scanning object in the scanning time period according to the body surface motion information; and adjusting the imaging weight corresponding to each distance in the distance weight relationship according to the motion intensity of each time point.

As an example, for the original chest scan data of the scanning object acquired at the time T1, if the body surface motion information acquired by the motion monitoring device indicates that the chest motion amplitude of the scanning object at the time T1 is large, motion artifacts are very easily introduced when the original chest scan data at the time T1 is used for image reconstruction.

Based on the distance weight relationship, the distance weight relationship can be adjusted, the imaging weight value corresponding to the distance from the parallel beam light source of the imaging device to the image plane at the time of T1 is reduced, the imaging contribution rate of the original projection data acquired at the distance to the reconstructed image is reduced, and the possibility that motion artifacts exist in the reconstructed image is reduced.

It should be noted that, in this embodiment, the curve corresponding to the distance weight relationship is not limited, and may be a gaussian function curve shown in fig. 3, or may be another function curve.

In this embodiment, in the scanning imaging provided with the motion monitoring device, the imaging weight corresponding to each distance in the distance weight relationship may be adjusted according to the body surface motion information of the scanned object monitored at the same time, so as to reduce the possibility of introducing a motion artifact in the image reconstruction process.

In an embodiment, when the reconstructed image is a reconstructed slice image and the range image sequence is a first image sequence, as shown in fig. 5, the implementation process of generating a medical image of the scanned object according to the range image sequence corresponding to the reconstructed image in step 230 includes the following steps:

step 510: and determining the target plane image corresponding to each reconstruction plane image according to the first image sequence corresponding to each reconstruction plane image.

Each reconstruction layer corresponds to one first image sequence, that is, one reconstruction layer corresponds to a plurality of first images, and the plurality of first images are distance images with a time sequence acquired through a distance weight relationship.

Since the motion artifacts of the first images in the first image sequence are different from each other, the first image with the weakest motion artifact is determined as the target slice image corresponding to the reconstruction slice by analyzing the motion artifact of the plurality of first images corresponding to the reconstruction slice images.

In one possible implementation manner, the implementation procedure of step 510 may be: based on the first image sequence corresponding to each reconstruction layer image, subtracting adjacent first images, and analyzing the change intensity of the motion artifact of the first image sequence; and selecting the target plane image from the first image sequence corresponding to each reconstruction plane image according to the change intensity of the motion artifact of the first image sequence.

That is, the intensity of the motion artifact of each first image in the first image sequence is analyzed, and one first image with the weakest degree of motion artifact change is determined from the plurality of first images and is used as the target slice image.

As an example, if the first image sequence comprises 5 first images: image 1, image 2, image 3, image 4 and image 5. Firstly, subtracting the image 2 from the image 1 to determine a first artifact strength; subtracting the image 3 from the image 2 to determine a second artifact strength; subtracting the image 4 and the image 3 to determine a third artifact strength; image 5 and image 4 are subtracted to determine a fourth artifact strength. Then, according to the first artifact strength, the second artifact strength, the third artifact strength and the fourth artifact strength, the motion artifact change strengths of the 5 first images are analyzed, and the first image with the weakest artifact strength in the first image sequence is determined as the target level image.

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 the first images is also different, and further, artifact correction can be performed on the first image sequence according to the motion characteristic information of the scanned object to determine the target slice image.

In another possible implementation manner, the implementation procedure of step 510 may be: analyzing the motion characteristic information of the scanning object in each reconstruction layer image according to the first image sequence corresponding to each reconstruction layer image; and according to the motion characteristic information of the scanning object in each reconstruction layer image, artifact correction is carried out on the first image sequence corresponding to each reconstruction layer image, and the target layer image corresponding to each reconstruction layer image is determined.

Wherein the motion characteristic information comprises a motion direction and a motion amplitude.

Further, artifact correction is performed on the first image sequence corresponding to each reconstruction layer, which may be implemented by a motion correction algorithm, or implemented by a deep learning trained network model, and this embodiment does not limit this.

As an example, taking a deeply-learned and trained layer image prediction model as an example, for any reconstruction layer, the layer image prediction model is used to analyze the motion artifact of each first image in the first image sequence, and determine the motion characteristic information of the scanning object in the reconstruction layer image. And then, the layer image prediction model performs artifact correction on the first image sequence corresponding to the reconstruction layer according to the motion characteristic information, and outputs a target layer image corresponding to the reconstruction layer according to an artifact correction result.

It should be noted that, in this implementation, the target level image may be directly output in combination with the motion feature information and the first image sequence. The artifact correction may be performed on a plurality of first images in the first image sequence according to the motion characteristic information, the corrected first image sequence may be output, and a first image with the weakest motion artifact may be determined from the corrected first image sequence and may be used as the target slice image.

Step 520: and generating a medical image of the scanned object according to the target plane image corresponding to each reconstruction plane image.

In this step, in obtaining the target level image corresponding to each reconstructed level image, a medical image of the scanned object may be generated according to the target level image, where the medical image is an image obtained after the motion artifact correction processing.

In this embodiment, for each reconstructed layer image, a target layer image corresponding to the reconstructed layer image is determined according to a first image sequence corresponding to the reconstructed layer image, and it is ensured that a motion artifact of the target layer image is weakest, or it is ensured that the target layer image is an optimal layer image obtained by artifact correction processing. In this way, the medical image of the scanned object is generated according to the target slice image corresponding to each reconstruction slice image, so that the motion artifact of the medical image is the weakest, and the image quality is the best.

In another embodiment, when the reconstructed image is a reconstructed slice image and the range image sequence is a first image sequence, as shown in fig. 6, the implementation process of generating a medical image of the scanned object according to the range image sequence corresponding to the reconstructed image in step 230 includes the following steps:

step 610: and respectively scoring the candidate body images based on a preset evaluation index to obtain a scoring result of each candidate body image.

The candidate body image is composed according to a first image sequence corresponding to a plurality of reconstruction slice images. That is, a first image in the corresponding time sequence is selected from the first image sequence corresponding to each reconstruction slice image, and then a candidate image is formed according to the first image corresponding to each reconstruction slice image.

As an example, if there are 5 reconstruction slice images, and the first image sequence corresponding to each reconstruction slice image includes 10 first images, a first image is selected from the 10 first images corresponding to each reconstruction slice image, and a candidate volume image is formed according to the selected 5 first images. By analogy, 10 candidate volume images can be generated according to the first image sequence corresponding to the 5 reconstruction slice images, and each candidate volume image is composed of one first image in the 5 reconstruction slice images.

Further, the evaluation index preset in this step is a parameter item for measuring the image quality of the candidate, and the evaluation index may include one or more of the definition of the anatomical structure, the contrast of the key region, the uniformity of the image signal, the level of the image noise, and the degree of artifact suppression.

It should be understood that the anatomical structure definition may be a definition of textures and boundaries of each portion (or each anatomical structure) on the image to be evaluated (i.e., the candidate body image in step 610 and the second image in step 710), and the anatomical structure may be an anatomical structure of a portion included in the image to be evaluated, for example, if the image to be evaluated is a brain image, the anatomical structure is a brain anatomical structure (e.g., brain, diencephalon, cerebellum, brainstem, etc.); as another example, if the image to be scored is a kidney image, then the anatomical structure is a kidney anatomical structure (e.g., kidney cortex, kidney medulla, etc.). The key part contrast may be a contrast between light and dark in a bright and dark area in the image to be evaluated, for example, a contrast of different brightness levels between white in the brightest area and black in the darkest area, i.e., a magnitude of gray contrast in the image. The critical site may be a site of a patient or other medical subject to be observed, such as the skull of the brain, the lung window of the chest, the soft tissues of the abdomen, etc. The image signal uniformity may be a degree of uniformity of an image signal acquired when the imaging device scans the scan object. The image noise level may be the degree of inclusion of unwanted or unwanted interference information present in the image to be scored. For example, some isolated noise points may be present in certain areas of the image to be scored. The artifact suppression degree can be the elimination or suppression degree of the artifact in the image to be evaluated.

Further, the score of each candidate volume image may be a score of the candidate volume image under at least one evaluation index, i.e., a score including one or more of a score of anatomical structure clarity, a score of key site contrast, a score of image signal uniformity, a score of image noise level, and a score of artifact suppression degree.

The rating range of each evaluation index may be set by a user. For example, the score range may be set to be 1-5 points, and the higher the score, the better the image quality.

Specifically, the higher the score of the sharpness of the anatomical structure, the clearer the anatomical structure representing the candidate volume image, and the better the image quality; the higher the score of the contrast of the key part is, the higher the contrast of the target part of the candidate body image is, and the better the image quality is; the higher the score of the uniformity of the image signals is, the higher the uniformity of the image signals of the candidate body image is, and the better the image quality is; the higher the score of the image noise level is, the more satisfactory the noise level of the candidate image is (for example, the lower the noise level of the uniform region of the image is, the object region contains a proper amount of noise), the better the image quality is; the higher the score of the artifact suppression degree, the lower the artifact level representing the candidate volume image, and the better the image quality.

Step 620: and determining the medical image of the scanning object according to the scoring result of each candidate body image.

In the step, for any candidate body image, according to the preset evaluation index, the candidate body image is scored from at least one image quality evaluation dimension, and the score of each evaluation index is obtained. Further, according to the score of at least one evaluation index of each candidate volume image, the candidate volume image with the highest overall quality score is determined as the medical image of the scanning object.

As an example, a weighted average operation may be performed on the scores of the evaluation indexes, so as to obtain an overall quality score of the candidate volume image.

Optionally, different weights may be given to different evaluation indexes, and the total quality score of the candidate image is obtained by multiplying the weight by the score of the corresponding evaluation index and then performing summation and averaging.

The weight of each evaluation index may be determined according to medical diagnosis experience, or may be determined in other manners, which is not limited in this embodiment. For example, the evaluation indexes of the candidate image include the anatomical structure sharpness, the target region contrast, and the image signal uniformity, and the weights thereof are 0.4, 0.5, and 0.3, respectively.

In this embodiment, a plurality of candidate volume images of the scan object may be generated from the first image sequence corresponding to the plurality of reconstruction slice images. Since the motion artifacts of the first images in the first image sequence are different, the motion artifacts of the candidate images are also different. Further, the candidate body images are evaluated from different image quality evaluation dimensions according to preset evaluation indexes, and then the candidate body image with the highest overall quality score is determined as the medical image of the scanning object according to the scoring result of each candidate body image, so that the motion artifact of the medical image is weakest, and the image quality is optimal.

In another embodiment, when the reconstructed image is specifically a reconstructed volume image and the range image sequence is specifically a second image sequence, as shown in fig. 7, the implementation process of generating a medical image of the scanned object according to the range image sequence corresponding to the reconstructed image in step 230 includes the following steps:

step 710: and respectively scoring the plurality of second images in the second image sequence corresponding to the reconstructed body image based on a preset evaluation index, and acquiring a scoring result of each second image.

Wherein the preset evaluation index comprises one or more of the definition of an anatomical structure, the contrast of a key part, the uniformity of an image signal, the noise level of an image and the suppression degree of an artifact.

The only difference between step 710 and step 610 is that the evaluation target of step 710 is a plurality of second images directly obtained by three-dimensional reconstruction, and the second images are three-dimensional volume images obtained by reconstruction; the evaluation object of step 610 is a candidate volume image composed by reconstructing a slice image, but the implementation principle and the specific implementation process of the two steps are similar, so that details are not repeated here, and refer to the explanation and limitation of step 610.

Step 720: and determining the medical image of the scanning object according to the grading result of each second image.

In this step, for any one of the second images, the second image is scored from at least one image quality evaluation dimension according to the listed at least one evaluation index, and a score of each evaluation index is obtained. Further, according to the scores of the evaluation indexes of the second images, the second image with the highest overall quality score is determined as the medical image of the scanning object.

Optionally, the motion characteristic information of the scanned object corresponding to each second image may be analyzed according to a plurality of second images in the second image sequence corresponding to the reconstructed volume image; and then, according to the motion characteristic information of the scanning object, artifact correction is carried out on the second image sequence corresponding to each reconstructed body image, and the medical image of the scanning object is determined.

In this embodiment, the motion artifact of each second image is different for a plurality of second images in the second image sequence corresponding to the reconstructed volume image. And evaluating the second image from different image quality evaluation dimensions according to a preset evaluation index so as to determine the second image with the highest overall quality score as the medical image of the scanning object, so that the motion artifact of the medical image is weakest and the image quality is optimal.

It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the present application further provides an image reconstruction apparatus for implementing the image reconstruction method. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme described in the above method, so specific limitations in one or more embodiments of the image reconstruction apparatus provided below may refer to the limitations on the image reconstruction method in the foregoing, and details are not described here.

In one embodiment, as shown in fig. 8, there is provided an image reconstruction apparatus 800, the apparatus comprising: an acquisition module 810, a sequence reconstruction module 820, and an image generation module 830, wherein:

an obtaining module 810, configured to obtain raw projection data of a scanned object;

a sequence reconstruction module 820, configured to perform image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image; the range image sequence comprises at least one range image, and the motion artifacts of the range images are different;

an image generation module 830, 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.

In one embodiment, the reconstructed image comprises a plurality of reconstructed slice images, and the range image sequence comprises a first image sequence;

a sequence reconstruction module 820, comprising:

and the first reconstruction unit is used for carrying out image reconstruction on the original projection data based on a preset distance weight relationship to obtain a first image sequence corresponding to each reconstruction layer image.

In one embodiment, the first reconstruction unit includes:

the data processing subunit is used for carrying out weighting processing on the original projection data according to the distance from the projection light source point to the reconstruction layer according to the distance weight relationship to obtain a plurality of weighted projection data corresponding to each reconstruction layer image;

and the reconstruction subunit is used for performing image reconstruction on the plurality of weighted projection data corresponding to each reconstruction slice image to obtain a first image sequence corresponding to each reconstruction slice image.

In one embodiment, the image generation module 830 includes:

the first determining unit is used for determining a target level image corresponding to each reconstruction level image according to the first image sequence corresponding to each reconstruction level image;

and the image generation unit is used for generating a medical image of the scanned object according to the target plane image corresponding to each reconstruction plane image.

In one embodiment, the first determining unit includes:

the artifact analysis subunit is configured to subtract adjacent first images based on the first image sequence corresponding to each reconstructed slice image, and analyze the motion artifact change strength of the first image sequence;

and the selecting subunit is used for selecting the target level image from the first image sequence corresponding to each reconstruction level image according to the motion artifact change strength of the first image sequence.

In one embodiment, the first determining unit includes:

the motion analysis subunit is used for analyzing the motion characteristic information of the scanning object in each reconstruction layer image according to the first image sequence corresponding to each reconstruction layer image;

and the artifact correction subunit is used for performing artifact correction on the first image sequence corresponding to each reconstruction layer image according to the motion characteristic information of the scanning object in each reconstruction layer image, and determining the target layer image corresponding to each reconstruction layer image.

In one embodiment, the image generation module 830 includes:

the first scoring unit is used for scoring the candidate body images respectively based on a preset evaluation index to obtain a scoring result of each candidate body image; the candidate body image is composed according to a first image sequence corresponding to a plurality of reconstruction layer images;

and the second determining unit is used for determining the medical image of the scanning object according to the grading result of each candidate body image.

In one embodiment, reconstructing the image comprises reconstructing a volumetric image, the range image sequence comprising a second image sequence;

a sequence reconstruction module 820, comprising:

and the second reconstruction unit is used for reconstructing the image of the original projection data based on a preset distance weight relationship to obtain a second image sequence corresponding to the reconstructed body image.

In one embodiment, the image generation module 830 includes:

the second scoring unit is used for scoring the plurality of second images in the second image sequence corresponding to the reconstructed body image respectively based on a preset evaluation index to obtain a scoring result of each second image;

and the third determining unit is used for determining the medical image of the scanning object according to the grading result of each second image.

The modules in the image reconstruction device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 9. The computer device comprises a processor, a memory, a communication interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile 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 to run on the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement an image reconstruction method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory having a computer program stored therein and a processor that when executing the computer program performs the steps of:

acquiring original projection data of a scanned object;

carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image; the range image sequence comprises at least one range image, and the motion artifacts of the range images are different;

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

The implementation principle and technical effect of the computer device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

acquiring original projection data of a scanned object;

carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image; the range image sequence comprises at least one range image, and the motion artifacts of the range images are different;

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

The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.

In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of:

acquiring original projection data of a scanned object;

carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image; the range image sequence comprises at least one range image, and the motion artifacts of the range images are different;

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

The foregoing embodiments provide a computer program product, which has similar implementation principles and technical effects to those of the foregoing method embodiments, and will not be described herein again.

It should be noted that, the user information (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.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A method of image reconstruction, the method comprising:

acquiring original projection data of a scanned object;

carrying out image reconstruction on the original projection data to obtain a distance image sequence corresponding to a reconstructed image; the range image sequence comprises at least one range image, and the motion artifact of each range image is 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.

2. The method of claim 1, wherein the reconstructed image comprises a plurality of reconstructed slice images, and wherein the sequence of range images comprises a first sequence of images;

the image reconstruction of the original projection data to obtain a distance image sequence corresponding to a reconstructed image includes:

and performing image reconstruction on the original projection data based on a preset distance weight relationship to obtain a first image sequence corresponding to each reconstruction layer image.

3. The method according to claim 2, wherein the performing image reconstruction on the original projection data based on a preset distance-weight relationship to obtain a first image sequence corresponding to each of the reconstructed slice images includes:

according to the distance weight relationship, weighting the original projection data according to the distance from a projection light source point to a reconstruction layer to obtain a plurality of weighted projection data corresponding to each reconstruction layer image;

and performing image reconstruction on the plurality of weighted projection data corresponding to each reconstruction slice image to obtain a first image sequence corresponding to each reconstruction slice image.

4. The method according to claim 2 or 3, wherein the generating of the medical image of the scanned object from the corresponding range image sequence of the reconstructed image comprises:

determining a target level image corresponding to each reconstruction level image according to a first image sequence corresponding to each reconstruction level image;

and generating a medical image of the scanning object according to the target plane image corresponding to each reconstruction plane image.

5. The method of claim 4, wherein determining the target slice image corresponding to each of the reconstruction slice images according to the first image sequence corresponding to each of the reconstruction slice images comprises:

based on the first image sequence corresponding to each reconstruction layer image, subtracting adjacent first images, and analyzing the change intensity of the motion artifact of the first image sequence;

and selecting the target plane image from the first image sequence corresponding to each reconstruction plane image according to the change intensity of the motion artifact of the first image sequence.

6. The method of claim 4, wherein determining the target slice image corresponding to each of the reconstruction slice images according to the first image sequence corresponding to each of the reconstruction slice images comprises:

analyzing the motion characteristic information of the scanning object in each reconstruction layer image according to the first image sequence corresponding to each reconstruction layer image;

and according to the motion characteristic information of the scanning object in each reconstruction plane image, performing artifact correction on the first image sequence corresponding to each reconstruction plane image, and determining a target plane image corresponding to each reconstruction plane image.

7. The method according to claim 2 or 3, wherein the generating of the medical image of the scanned object from the corresponding range image sequence of the reconstructed image comprises:

respectively scoring a plurality of candidate body images based on a preset evaluation index to obtain a scoring result of each candidate body image; the candidate body image is composed according to a first image sequence corresponding to a plurality of reconstruction slice images;

and determining a medical image of the scanning object according to the scoring result of each candidate body image.

8. The method of claim 1, wherein the reconstructed image comprises a reconstructed volume image, and wherein the sequence of range images comprises a second sequence of images;

the image reconstruction of the original projection data to obtain a distance image sequence corresponding to a reconstructed image includes:

and performing image reconstruction on the original projection data based on a preset distance weight relation to obtain a second image sequence corresponding to the reconstructed body image.

9. The method according to claim 8, wherein the generating of the medical image of the scanned object from the corresponding range image sequence of the reconstructed image comprises:

respectively scoring a plurality of second images in a second image sequence corresponding to the reconstructed body image based on a preset evaluation index to obtain a scoring result of each second image;

and determining a medical image of the scanning object according to the grading result of each second image.

10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 9 when executing the computer program.

Images