Method, device, computer equipment and storage medium for determining effective time resolution
By correcting medical images of the heartbeat and matching them with gold standard images, the problem of measuring the temporal resolution of CT equipment is solved, providing a quantitative performance evaluation tool and improving the imaging quality evaluation capability of CT equipment.
Patent Information
- Application Number
- CN202011049936.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-09-29
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2040-09-29
AI Technical Summary
Existing technologies cannot effectively measure the temporal resolution of CT equipment after the addition of artifact correction algorithms, which makes it impossible to quantitatively analyze the impact of artifact correction algorithms on the imaging quality of CT equipment, thus affecting doctors' accurate diagnosis of cardiac diseases.
By acquiring medical images of the heart beating for a preset resting duration, correcting the images, and matching them with a preset gold standard image, the effective temporal resolution of the imaging device is determined based on the corrected medical image.
It enables effective measurement of the temporal resolution of CT equipment after the artifact correction algorithm is applied, providing engineers with quantitative reference indicators and supporting the evaluation of imaging equipment performance and the effectiveness of artifact correction algorithms.
Smart Images

Figure CN114332263B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of medical image technology, and in particular to a method, apparatus, computer device and storage medium for determining effective temporal resolution. Background Art
[0002] Computerized tomography (CT) is widely used in the examination of various diseases due to its fast scanning time and clear images. However, during cardiac imaging, the heartbeat can cause serious motion artifacts. If the temporal resolution of the CT device used to scan the heart is low, it will seriously affect the imaging quality of the CT device, thereby affecting the doctor's accurate diagnosis of heart diseases.
[0003] To address the above issues, many artifact correction algorithms are currently provided to remove motion artifacts. However, the temporal resolution of the CT device after the artifact correction algorithm is added cannot be effectively measured, and thus it is impossible to quantitatively analyze the impact of the artifact correction algorithm on the imaging quality of the CT device, which is not conducive to engineers' improvement of the performance of CT equipment and the development and utilization of the artifact correction algorithm. Summary of the invention
[0004] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for determining the effective time resolution of a CT device after adding an artifact correction algorithm, in order to address the above technical problems.
[0005] In a first aspect, a method for determining an effective time resolution comprises:
[0006] Acquire medical images of the heart beating according to a preset resting time;
[0007] Correcting the medical image, and matching the corrected medical image with a preset gold standard image;
[0008] If the matching is successful, the effective time resolution of the imaging device is determined based on the corrected medical image that has successfully matched.
[0009] In one embodiment, acquiring a medical image of a heart beating according to a preset static duration includes:
[0010] Acquire projection data of the imaging device scanning the heart at a preset rotation angle, wherein the heart beats according to a preset static duration;
[0011] An image is reconstructed according to the projection data to obtain the medical image.
[0012] In one embodiment, the step of acquiring projection data of the imaging device scanning the heart at a preset rotation angle includes:
[0013] The imaging device and the heart are simulated in a preset simulation test scene to obtain projection data of the simulated heart when the simulated imaging device scans at the preset rotation angle and beats according to the preset static duration.
[0014] In one embodiment, the simulation test scenario includes an imaging device model and a heart beating model;
[0015] The imaging device model is used to simulate the imaging device scanning and imaging the heart beating model according to the preset rotation angle;
[0016] The heart beating model is used to simulate the heart beating along the trajectory of the preset static time length.
[0017] In one embodiment, determining the effective time resolution of the imaging device according to the successfully matched corrected medical image comprises:
[0018] The preset static time length of the heart beating in the successfully matched corrected medical image is determined as the effective time resolution of the imaging device.
[0019] In one embodiment, the correcting the medical image and matching the corrected medical image with a preset gold standard image includes:
[0020] Correcting the medical image;
[0021] Calculating the similarity between the artifact-corrected medical image and the gold standard image;
[0022] If the similarity is greater than a preset similarity threshold, it is determined that the artifact-corrected medical image and the gold standard image are matched successfully;
[0023] If the similarity is not greater than the preset similarity threshold, the preset static time is reset, and the process returns to the step of acquiring a medical image when the heart beats according to the preset static time.
[0024] In a second aspect, a method for determining an effective time resolution is provided, the method comprising:
[0025] Scanning the scanned object according to a preset state through a medical imaging device and acquiring a corresponding image;
[0026] Correcting the image, and matching the corrected image with a preset gold standard image;
[0027] If the matching is successful, the effective time resolution of the medical imaging device is determined based on the corrected image after the successful matching.
[0028] According to a third aspect, a device for determining an effective time resolution includes:
[0029] An acquisition module, used to acquire a medical image of a detection object, wherein the detection object moves according to a preset static time length;
[0030] A matching module, used for correcting the medical image and matching the corrected medical image with a preset gold standard image;
[0031] The determination module is used to determine the effective time resolution of the imaging device according to the corrected medical image after successful matching when the matching is successful.
[0032] In a fourth aspect, a computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.
[0033] In a fifth aspect, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.
[0034] The above-mentioned effective time resolution determination method, device, computer equipment and storage medium include: obtaining a medical image of the heart beating according to a preset static time length, correcting the medical image, and matching the corrected medical image with a preset gold standard image, and if the match is successful, determining the effective time resolution of the imaging device based on the corrected medical image after the successful match. This method realizes the function of effectively measuring the effective time resolution of the imaging device after the correction algorithm is added, and provides a quantitative reference indicator for engineers to evaluate the performance of the imaging device and / or the effect of the correction algorithm. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] Figure 1 is an internal structure diagram of a computer device in one embodiment;
[0036] Figure 2 A schematic diagram of a flow chart of a method for determining effective time resolution in one embodiment;
[0037] Figure 3 for Figure 2 A flowchart of an implementation method of S101 in the embodiment;
[0038] Figure 4 is a schematic diagram of a heart beat trajectory in one embodiment;
[0039] Figure 5 for Figure 2 A flowchart of an implementation method of S102 in the embodiment;
[0040] Figure 6 A schematic diagram of a flow chart of a method for determining effective time resolution in one embodiment;
[0041] Figure 7 is a structural block diagram of an effective time resolution determination device in one embodiment;
[0042] Figure 8 is a structural block diagram of an effective time resolution determination device in one embodiment;
[0043] Fig. 9 is a structural block diagram of an effective time resolution determination device in one embodiment;
[0044] Fig.10 is a structural block diagram of an effective time resolution determination device in one embodiment;
[0045] Fig.11 It is a structural block diagram of an effective time resolution determination device in one embodiment. DETAILED DESCRIPTION
[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0047] The effective time resolution determination method provided in the present application obtains a medical image of a detection object, where the detection object may be an organ or tissue such as the heart, head, joints, lungs, liver, etc., and the detection object moves according to a preset state; corrects the medical image, and matches the corrected medical image with a preset gold standard image; if the match is successful, determines the effective time resolution of the imaging device based on the corrected medical image after the successful match, for example, setting the retention time of the detection object in a preset state as the effective time resolution of the imaging device.
[0048] The detection object moving in a preset state may be that the detection object jumps / moves in a preset static time, and the detection object being static may be a period in which the detection state remains fixed or relatively static. Optionally, the medical image may be reconstructed from MRI data collected by an MRI device, CT data collected by an electronic computed tomography (CT) device, or PET imaging data collected by a positron emission tomography (PET) device, or imaging data collected by a multimodal imaging device such as PET-MR or PET-CT.
[0049] Optionally, the medical image of the detected object can be obtained by simulation. In one embodiment, taking the detected object as a heart as an example, a preset simulation test scene including an imaging device model and a heart beating model is provided, wherein the imaging device model is used to simulate the imaging device scanning and imaging the heart beating model according to a preset rotation angle; the heart beating model is used to simulate the heart beating according to the trajectory of a preset static duration. The imaging device and the heart are simulated in the preset simulation test scene to obtain projection data of the simulated heart when the simulated imaging device scans and beats according to the preset static duration at a preset rotation angle.
[0050] The above method can be applied to Figure 1 In the computer device shown in the figure, the computer device may be a server, or the computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 1 As shown. The computer device includes a processor, a memory, a network 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 operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an effective time resolution determination method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.
[0051] Those skilled in the art will understand that Figure 1 The structure shown in the figure 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 certain components, or have a different arrangement of components.
[0052] In one embodiment, Figure 2 As shown, a method for determining effective time resolution is provided, which is applied to Figure 1 The computer device in the example is used to illustrate, including the following steps:
[0053] S101, obtaining a medical image of a heart beating according to a preset resting time.
[0054] Among them, the preset static duration refers to the duration during which the volume of the heart beat cycle (movement cycle) remains relatively fixed / basically unchanged. During this period of time, the ventricles of the heart neither eject nor fill, that is, the amount of blood in the ventricles remains unchanged. Each physiological cycle of the heart usually includes eight phases, namely, isovolumetric contraction, rapid ejection, slow ejection, pre-diastole, isovolumetric relaxation, rapid filling, slow filling, and atrial contraction. The preset static duration can be, for example, a set phase such as the isovolumetric contraction or isovolumetric relaxation of the heart movement cycle, which can be determined in advance by the computer device according to the actual test requirements and the scanning duration of the imaging device. In this embodiment, the preset static duration is determined according to the tolerance of the test object, which can be different times such as 10ms, 20ms, 30ms, 40ms, 50ms, and 60ms.
[0055] Specifically, the computer device can simulate the heart and the imaging device in advance, and simulate the beating trajectory of the heart and the imaging process of the imaging device to obtain a medical image of the heart beating according to a preset static duration; optionally, the computer device can also directly obtain the medical image of the heart beating according to a preset static duration from a relevant imaging image information library; optionally, the computer device can also obtain the medical image of the heart prop beating according to a preset static duration through an offline experiment.
[0056] S102, correcting the medical image, and matching the corrected medical image with a preset gold standard image.
[0057] Among them, the gold standard image is a clinical cardiac image of high quality, which can be a cardiac image of high quality corresponding to different static time lengths of the heart. For example, it can be a cardiac image of the heart at different static time lengths such as 90ms, 100ms, and 120ms.
[0058] Specifically, when the computer device obtains a medical image about the heart beat based on the aforementioned steps, since the heart is beating, the medical image is equivalent to a moving image, so there are motion artifacts in the medical image. The motion artifacts will cause trouble for the later doctor's diagnosis based on the medical image. Therefore, in this embodiment, after the computer device obtains the medical image, it is necessary to further correct the medical image to improve the quality of the medical image, and then match the corrected medical image with the preset gold standard image. If the matching degree is high, it is determined that the match is successful, which means that the time resolution of the imaging device itself that obtains the medical image has been improved, and the improved time resolution is the effective time resolution of the imaging device, and at this time the effective time resolution of the imaging device is equivalent to the time resolution corresponding to the successfully matched gold standard image.
[0059] S103: If the matching is successful, determining the effective time resolution of the imaging device according to the corrected medical image that has successfully matched.
[0060] When the above-mentioned corrected medical image and the gold standard image are successfully matched, the computer device can directly determine the preset static time length in the successfully matched medical image as the time length required for the imaging device to rotate half a circle, that is, the effective time resolution of the imaging device. When the above-mentioned corrected medical image and the gold standard image are not successfully matched, a different preset static time length can be reset to obtain the medical image for re-matching until the match is successful; optionally, the computer device can also continue to select a new gold standard image to match the corrected medical image until the match is successful. The static beating time length of the heart contained in the new gold standard image is different from that contained in the previously used gold standard image. It should be noted that the effective time resolution finally determined by the computer device is the time resolution after the correction algorithm is added, and it is not the time resolution of the hardware of the imaging device.
[0061] In the above method for determining the time resolution, a medical image of the heart is obtained when it beats according to a preset static time, and the medical image is corrected, and the corrected medical image is matched with a preset gold standard image. If the match is successful, the time resolution of the imaging device is determined according to the preset static time. This method realizes the function of effectively measuring the time resolution of the imaging device after the artifact correction algorithm is added, and provides a quantitative reference for engineers to evaluate the performance of the imaging device and / or the effect of the artifact correction algorithm.
[0062] In one embodiment, an implementation of the above S101 is provided, such as Figure 3 As shown, the above S101 “obtaining a medical image of the heart beating according to a preset static time” includes:
[0063] S201, obtaining projection data of a heart scanned by an imaging device at a preset rotation angle, wherein the heart beats according to a preset static duration.
[0064] The preset rotation angle refers to the angle at which the imaging device rotates when scanning the heart, which is generally 180°, but may also be other angles. Specifically, the computer device may control the imaging device to scan the heart at the preset rotation angle when it beats according to the preset static duration, thereby obtaining projection data containing the heart beating. It is understandable that the heart beating according to the preset static duration may be a simulated heart model or a manufactured heart prop.
[0065] Optionally, when the object of the above scan is a heart prop, the heart prop can be connected using a corresponding driving device in accordance with the trajectory of the heart beating, and then the driving device is started to control the heart prop to beat according to a preset static time, and then the imaging device is controlled to scan and image the beating heart prop to obtain projection data about the heart beating according to the preset static time.
[0066] Optionally, when the object of the above scan is a heart model, this embodiment also provides an implementation method of S201, which includes: simulating an imaging device and a heart in a preset simulation test scene, and obtaining projection data of a simulated heart when the simulated imaging device scans at a preset rotation angle and beats according to a preset static time length.
[0067] The simulation test scenario includes an imaging device model and a heart beat model. The imaging device model is used for the imaging device to scan and image the heart beat model according to a preset rotation angle; the heart beat model is used to simulate the heart beating according to the trajectory of the preset static duration.
[0068] Specifically, the computer device can use the corresponding simulation computing application to build a simulation test scene in advance, that is, to establish a model of the imaging device and a model of the heart, and simulate the beating behavior of the heart according to the trajectory of the beating of the preset static time, drive the heart model to beat, and refer to the scanning parameters of the offline imaging device to simulate the imaging device to scan and image the heart model, thereby obtaining the projection data of the imaging device model scanning the heart model at a preset rotation angle.
[0069] It should be noted that when the computer device simulates the heart beating according to the preset static time, optionally, the following Figure 4 The motion trajectory shown is simulated. Figure 4 The horizontal axis in represents time, and the vertical axis represents the heart's beating displacement. The duration corresponding to the ab segment represents the preset static duration.
[0070] S202, reconstructing an image according to the projection data to obtain a medical image.
[0071] When the computer device acquires the projection data, it can use the pre-trained image reconstruction network to reconstruct the image based on the projection data to obtain a reconstructed medical image. Optionally, the computer device can also reconstruct the image based on the projection data through other image reconstruction algorithms to obtain a medical image.
[0072] In one embodiment, an implementation of the above S103 is provided, that is, the above S103 "determines the effective time resolution of the imaging device according to the successfully matched corrected medical image", including: determining the preset static time length when the heart beats in the successfully matched corrected medical image as the effective time resolution of the imaging device. Specifically, when the computer device matches the successfully corrected medical image with the gold standard image, the preset static time length when the heart beats in the successfully matched medical image can be determined as the effective time resolution of the imaging device. At this time, the imaging device is the imaging device that obtains the successfully matched medical image.
[0073] In one embodiment, a specific implementation of the above S102 “correcting the medical image and matching the corrected medical image with a preset gold standard image” is provided, such as Figure 5 As shown, the method includes:
[0074] S301, performing artifact correction on a medical image to obtain an artifact-corrected medical image.
[0075] In this embodiment, after the computer device executes the above-mentioned step S101, the computer device also needs to perform artifact correction on the acquired medical image. During the specific correction, the computer device can use a pre-trained correction network to perform artifact correction on the medical image, or can also use an existing artifact correction algorithm to perform artifact correction on the medical image, thereby obtaining an artifact-corrected medical image, so as to perform processing based on the artifact-corrected medical image later.
[0076] S302, calculating the similarity between the artifact-corrected medical image and the gold standard image, if the similarity is greater than a preset similarity threshold, executing step S303, if the similarity is not greater than the preset similarity threshold, executing step S304.
[0077] The preset similarity threshold can be determined by the computer device in advance according to the actual matching accuracy or matching requirements. The gold standard image can be acquired in advance by the computer device. The gold standard image can be an image of a still beating heart. However, in practical applications, it is impossible to have an image of an absolutely still beating heart. Therefore, the gold standard image is selected as close to an image of a still beating heart as possible. Specifically, images of hearts beating with different still durations can be selected, for example, images of hearts beating with still durations of 90ms, 100ms, 120ms, etc.
[0078] Specifically, the computer device pre-acquires the medical image after artifact correction, and further selects an image containing a heart with good quality as a gold standard image. The gold standard image may include an image of a heart beating at different resting times. After the computer device acquires the medical image after artifact correction and the gold standard image, a corresponding similarity calculation method may be used to calculate the similarity between the medical image after artifact correction and the gold standard image, and then the calculated similarity is compared with a preset similarity threshold to determine a matching result.
[0079] S303, determining whether the artifact-corrected medical image and the gold standard image match successfully.
[0080] This embodiment relates to an application scenario in which the similarity is greater than a preset similarity threshold. In this application scenario, the computer device determines that the artifact-corrected medical image and the gold standard image are successfully matched.
[0081] S304, resetting the preset still time, and returning to the step of acquiring a medical image when the heart beats according to the preset still time.
[0082] This embodiment relates to an application scenario where the similarity is not greater than a preset similarity threshold. In this application scenario, the computer device needs to reset the preset static time and obtain a medical image when the heart beats according to the new preset static time, and then continue to perform the subsequent steps until the similarity between the obtained artifact-corrected medical image and the gold standard image is greater than the preset similarity threshold. Optionally, the computer device can also reselect a new gold standard image, and then return to the above step S102 to rematch the artifact-corrected medical image with the new gold standard image until the similarity between the obtained artifact-corrected medical image and the gold standard image is greater than the preset similarity threshold.
[0083] The method described in the present application is exemplified. For example, assuming that the preset still time is set to 10 ms, the computer device simulates the beating of the heart according to the still time of 10 ms, and simulates the imaging device to rotate 180° to scan and image the heart (the physical scanning time corresponding to the rotation of 180° is 100 ms). The computer device can obtain the projection data of the heart beating according to the still time of 10 ms, and the computer device will reconstruct the image based on the projection data to obtain a medical image. Further, the computer device performs artifact correction on the medical image to obtain an artifact-corrected medical image, and then the computer device matches the artifact-corrected medical image with each pre-prepared gold standard image (the still beating time of the heart in the gold standard image is 100 ms). If the match is successful, it is considered that the time used for scanning by the imaging device after the artifact correction algorithm is added at a rotation angle of 180° is reduced from 100 ms to 10 ms. Obviously, the time resolution of the imaging device after the artifact correction algorithm is added is improved.
[0084] Based on all the above embodiments, the present application also provides a method for determining time resolution, such as Figure 6 As shown, the method includes:
[0085] S401, simulating an imaging device and a heart in a preset simulation test scene, and obtaining projection data of a simulated heart when the simulated imaging device scans at a preset rotation angle and beats according to a preset static duration.
[0086] S402, reconstructing an image according to the projection data to obtain a medical image.
[0087] S403, performing artifact correction on the medical image to obtain an artifact-corrected medical image.
[0088] S404, acquiring a gold standard image.
[0089] S405, calculating the similarity between the artifact-corrected medical image and the gold standard image, if the similarity is greater than a preset similarity threshold, executing step S406, if the similarity is not greater than the preset similarity threshold, executing step S407.
[0090] S406, determining whether the artifact-corrected medical image and the gold standard image are matched successfully.
[0091] S407, resetting the preset static time length, and returning to the step of acquiring the medical image when the heart beats according to the preset static time length, until the medical image after artifact correction matches the gold standard image successfully.
[0092] As for the methods described in the above steps, they are all explained in the aforementioned content. Please refer to the aforementioned content for specific explanations and will not be repeated here.
[0093] In one embodiment, the detection object is a coronary region of the heart, and the medical image is obtained by reconstructing CT data of the heart scanned by an electronic computer tomography (CT) device. The medical image includes multiple groups of reconstructed images, and each group of reconstructed images corresponds to a phase. Correcting the medical image may include:
[0094] First, for a reconstructed image corresponding to one of the multiple time phases, take the reconstructed image as the current image to be processed, and obtain multiple groups of reconstructed images adjacent to the time phase of the current image to be processed. More comprehensive physiological cycle motion information of organs or tissues is obtained through multiple groups of reconstructed images of adjacent time phases, and accurate motion vectors are obtained. Multiple adjacent groups of reconstructed images include a reconstructed image of the current image to be processed relative to the previous adjacent time phase, and a reconstructed image of the current image to be processed relative to the next adjacent time phase. In the embodiment of the present application, since a group of projection data corresponds to a state of the heart in the motion cycle, the reconstructed images corresponding to multiple time phases adjacent to the time phase of the current image to be processed can better show a motion trend of the region of interest.
[0095] Secondly, multiple groups of reconstructed images that are adjacent to the current image to be processed are respectively registered with the current image to be processed at multiple scales to obtain motion vectors between each reconstructed image that is adjacent to the current image to be processed and the current image to be processed. Considering that the motion amplitudes of different branches and segments of the coronary artery are different, the motion vectors obtained by the rigid registration method cannot accurately estimate different motions. In this embodiment, multiple groups of reconstructed images that are adjacent to the current image to be processed are respectively registered with the current image to be processed at multiple scales. First, a large scale is used for rough registration, and then a small scale is used for fine registration. By performing registration at multiple scales, the real motion state of the coronary region can be more accurately simulated to obtain a more accurate motion vector.
[0096] Finally, motion artifact correction is performed on the current image to be processed according to the motion vector to obtain an artifact-corrected medical image. In this embodiment, size compensation and direction compensation are performed on the coordinates of each pixel point in the current image to be processed and the corresponding motion vector, so that artifact removal processing can be performed on the artifact image to be corrected.
[0097] Compared with the prior art, the motion artifact correction method provided in this embodiment obtains a motion vector by aligning the reconstructed image with the artifact image to be corrected at different scale levels, which can achieve a more accurate estimation of different motions, thereby improving the accuracy of motion artifact correction.
[0098] In some of the embodiments, performing multi-level scale registration of multiple groups of reconstructed images adjacent in time to the current image to be processed with the current image to be processed includes: extracting the coronary artery centerlines of the multiple groups of reconstructed images adjacent in time as target centerlines; extracting the coronary artery centerline of the current image to be processed as a reference centerline; and performing multi-level scale registration of the multiple groups of target centerlines with the reference centerline.
[0099] In some embodiments, multiple groups of target centerlines are respectively registered with reference centerlines at multiple levels of scales, including: using a first-scale registration algorithm to respectively register multiple groups of target centerlines with reference centerlines; using a second-scale registration algorithm to register the registration results; the second scale is smaller than the first scale. The size of the scale indicates the range affected by the centerline. In this embodiment, a large scale is first used for registration to simulate the approximate state of motion, and then the size of the scale is adjusted based on the registration result to gradually approach the motion between the centerlines, thereby accurately simulating the motion state of each branch in the coronary region during imaging. It can be understood that this embodiment only uses the first scale and the second scale for registration as an example. In other embodiments, three scales, four scales, or more scales may also be used for registration.
[0100] In some embodiments, multiple groups of reconstructed images that are adjacent in time phase to the current image to be processed are respectively registered with the current image to be processed at multiple levels of scale, including: obtaining the coronary region of the current image to be processed; dividing the coronary region into multiple sub-regions; obtaining the prior motion trend of the multiple sub-regions; determining the corresponding scale used for registration of each sub-region according to the prior motion trend; for each group of reconstructed images that are adjacent in time phase, according to the determined scale, the multiple groups of the reconstructed images are respectively registered with the artifact image to be corrected at multiple levels of scale. The embodiment of the present application performs anatomical segmentation on the coronary region, and then uses the obtained different segmented motion trends as prior knowledge for the subsequent registration process. Different anatomical segments of the coronary region can be understood as a sub-region of the coronary region, and the appropriate registration scale is determined according to the prior motion trend corresponding to the sub-region, that is, the range of the motion vector field in different sub-regions that needs to act is determined, and then each sub-region is registered using the determined registration scale to obtain the motion vector. This embodiment uses prior knowledge to determine the registration scale, and performs multi-level scale registration according to the determined scale, thereby improving the registration efficiency.
[0101] It should be understood that although Figure 2-6 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-6At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.
[0102] In one embodiment, Figure 7 As shown, a device for determining effective time resolution is provided, comprising: an acquisition module 11, a matching module 12 and a determination module 13, wherein:
[0103] An acquisition module 11 is used to acquire a medical image of a heart beating according to a preset resting time;
[0104] A matching module 12, used for correcting the medical image and matching the corrected medical image with a preset gold standard image;
[0105] The determination module 13 is used to determine the effective time resolution of the imaging device according to the corrected medical image after successful matching when the matching is successful.
[0106] In one embodiment, Figure 8 As shown, the acquisition module 11 includes:
[0107] An acquisition unit 111 is used to acquire projection data of a heart that is beating according to a preset static time length when the imaging device scans the heart at a preset rotation angle;
[0108] The reconstruction unit 112 is used to reconstruct an image according to the projection data to obtain the medical image.
[0109] In one embodiment, the acquisition unit 111 is specifically used to simulate the imaging device and the heart in a preset simulation test scenario to obtain projection data of the simulated heart when the imaging device is scanned at the preset rotation angle and beats according to the preset static time length.
[0110] In one embodiment, the simulation test scene in the above-mentioned acquisition unit 111 includes an imaging device model and a heart beating model; wherein the imaging device model is used to simulate the imaging device scanning and imaging the heart beating model according to the preset rotation angle; the heart beating model is used to simulate the heart beating along the trajectory of the preset static time length.
[0111] In one embodiment, the determination module 13 is specifically configured to determine a preset static duration of a heart beat in the successfully matched medical image as an effective time resolution of the imaging device.
[0112] In one embodiment, the matching module 12 is further specifically configured to perform artifact correction on the medical image, and match the artifact-corrected medical image with a preset gold standard image.
[0113] In one embodiment, the matching module 12, such as Fig. 9 As shown, including:
[0114] A calculation unit 121, configured to calculate the similarity between the artifact-corrected medical image and the gold standard image;
[0115] A determination unit 122, configured to determine that the artifact-corrected medical image and the gold standard image are successfully matched when the similarity is greater than a preset similarity threshold;
[0116] The re-determination unit 123 is used to reset the preset stillness time when the similarity is not greater than the preset similarity threshold, and return to the step of acquiring the medical image when the heart beats according to the preset stillness time.
[0117] In one embodiment, Fig.10 As shown, a device for determining an effective time resolution is provided, comprising: an acquisition module 21, a matching module 22 and a determination module 23, wherein:
[0118] An acquisition module 21 is used to scan the scanned object according to a preset state through a medical imaging device and acquire a corresponding image;
[0119] A matching module 22, used for correcting the image and matching the corrected image with a preset gold standard image;
[0120] The determination module 23 is used to determine the effective time resolution of the medical imaging device according to the corrected image after successful matching when the matching is successful.
[0121] In one embodiment, Fig.11 As shown, a device for determining an effective time resolution is provided, comprising: an acquisition module 31, a matching module 32 and a determination module 33, wherein:
[0122] An acquisition module 31 is used to acquire a medical image of a detection object, where the detection object moves according to a preset static duration;
[0123] A matching module 32, used for correcting the medical image and matching the corrected medical image with a preset gold standard image;
[0124] The determination module 33 is used to determine the effective time resolution of the imaging device according to the corrected medical image after successful matching when the matching is successful.
[0125] For the specific definition of the effective time resolution determination device, please refer to the definition of the effective time resolution determination method above, which will not be repeated here. Each module in the above-mentioned effective time resolution determination device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0126] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0127] Acquire medical images of the heart beating according to a preset resting time;
[0128] Correcting the medical image, and matching the corrected medical image with a preset gold standard image;
[0129] If the matching is successful, the effective time resolution of the imaging device is determined based on the corrected medical image that has successfully matched.
[0130] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0131] Acquiring projection data of a heart that is scanned by the imaging device at a preset rotation angle and beats for a preset static time length;
[0132] An image is reconstructed according to the projection data to obtain the medical image.
[0133] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0134] The imaging device and the heart are simulated in a preset simulation test scene to obtain projection data of the simulated heart when the simulated imaging device scans at the preset rotation angle and beats according to the preset static duration.
[0135] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0136] The imaging device model is used to simulate the imaging device scanning and imaging the heart beating model according to the preset rotation angle;
[0137] The heart beating model is used to simulate the heart beating along the trajectory of the preset static time length.
[0138] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0139] The preset static time length of the heart beating in the successfully matched medical image is determined as the effective time resolution of the imaging device.
[0140] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0141] Artifact correction is performed on the medical image, and the artifact-corrected medical image is matched with a preset gold standard image.
[0142] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0143] Calculating the similarity between the artifact-corrected medical image and the gold standard image;
[0144] If the similarity is greater than a preset similarity threshold, it is determined that the artifact-corrected medical image and the gold standard image are matched successfully;
[0145] If the similarity is not greater than the preset similarity threshold, the preset static time is reset, and the process returns to the step of acquiring a medical image when the heart beats according to the preset static time.
[0146] The above embodiment provides a computer device, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.
[0147] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0148] Acquire medical images of the heart beating according to a preset resting time;
[0149] Correcting the medical image, and matching the corrected medical image with a preset gold standard image;
[0150] If the matching is successful, the effective time resolution of the imaging device is determined based on the corrected medical image that has successfully matched.
[0151] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0152] Acquiring projection data of a heart that is scanned by the imaging device at a preset rotation angle and beats for a preset static time length;
[0153] An image is reconstructed according to the projection data to obtain the medical image.
[0154] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0155] The imaging device and the heart are simulated in a preset simulation test scene to obtain projection data of the simulated heart when the simulated imaging device scans at the preset rotation angle and beats according to the preset static duration.
[0156] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0157] The imaging device model is used to simulate the imaging device scanning and imaging the heart beating model according to the preset rotation angle;
[0158] The heart beating model is used to simulate the heart beating along the trajectory of the preset static time length.
[0159] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0160] The preset static time length of the heart beating in the successfully matched medical image is determined as the effective time resolution of the imaging device.
[0161] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0162] Artifact correction is performed on the medical image, and the artifact-corrected medical image is matched with a preset gold standard image.
[0163] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0164] Calculating the similarity between the artifact-corrected medical image and the gold standard image;
[0165] If the similarity is greater than a preset similarity threshold, it is determined that the artifact-corrected medical image and the gold standard image are matched successfully;
[0166] If the similarity is not greater than the preset similarity threshold, the preset static time is reset, and the process returns to the step of acquiring a medical image when the heart beats according to the preset static time.
[0167] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.
[0168] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0169] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.
[0170] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
Claims
1. A method for determining effective time resolution, characterized in that: The method comprises: Acquire medical images of the heart beating according to a preset resting time; Performing artifact correction on the medical image to obtain an artifact-corrected medical image; Calculating the similarity between the artifact-corrected medical image and the gold standard image; If the similarity is greater than a preset similarity threshold, it is determined that the artifact-corrected medical image and the gold standard image are matched successfully; If the similarity is not greater than the preset similarity threshold, resetting the preset static time length, and returning to the step of acquiring the medical image when the heart beats according to the preset static time length; If the match is successful, the preset static time length of the heart beating in the corrected medical image after the successful match is determined as the effective time resolution of the imaging device.
2. The method according to claim 1, characterized in that The step of obtaining a medical image of a heart beating according to a preset static duration includes: Acquire projection data of the imaging device scanning the heart at a preset rotation angle, wherein the heart beats according to the preset static duration; An image is reconstructed according to the projection data to obtain the medical image.
3. The method according to claim 2, characterized in that The step of acquiring projection data of the imaging device scanning the heart at a preset rotation angle comprises: The imaging device and the heart are simulated in a preset simulation test scene to obtain projection data of the simulated heart when the simulated imaging device scans at the preset rotation angle and beats according to the preset static duration.
4. The method according to claim 3, characterized in that The simulation test scenario includes an imaging device model and a heart beating model; The imaging device model is used to simulate the imaging device scanning and imaging the heart beating model according to the preset rotation angle; The heart beating model is used to simulate the heart beating along the trajectory of the preset static time length.
5. The method according to claim 1, characterized in that The preset static time refers to the time during which the volume remains relatively fixed / basically unchanged during the heart beat cycle.
6. The method according to claim 1, characterized in that The gold standard image is a heart image with good quality corresponding to different static durations of the heart.
7. A method for determining effective time resolution, characterized in that: The method comprises: Controlling the medical imaging device to scan the heart when it beats according to a preset static time at a preset rotation angle, obtaining projection data containing the heart beating; scanning the scanned object according to a preset state through the medical imaging device, and obtaining a corresponding image; Reconstructing an image based on the projection data using a pre-trained image reconstruction network to obtain a reconstructed medical image; Performing artifact correction on the medical image to obtain an artifact-corrected medical image; Calculating the similarity between the artifact-corrected medical image and the gold standard image; If the similarity is greater than a preset similarity threshold, it is determined that the artifact-corrected medical image and the gold standard image are matched successfully; If the similarity is not greater than the preset similarity threshold, resetting the preset static time length, and returning to the step of acquiring the medical image when the heart beats according to the preset static time length; If the match is successful, the preset static time length of the heart beating in the corrected medical image after the successful match is determined as the effective time resolution of the imaging device.
8. An effective time resolution determination device, characterized in that: The device comprises: An acquisition module, used to acquire medical images of the heart when it beats according to a preset static duration; a matching module, configured to perform artifact correction on the medical image to obtain an artifact-corrected medical image; calculate the similarity between the artifact-corrected medical image and a gold standard image; if the similarity is greater than a preset similarity threshold, determine that the artifact-corrected medical image and the gold standard image are successfully matched; if the similarity is not greater than the preset similarity threshold, reset the preset static time length, and return to execute the step of obtaining a medical image when the heart beats according to the preset static time length; The determination module is used to determine, when the matching is successful, a preset static time length of the heart beating in the corrected medical image that has successfully matched as the effective time resolution of the imaging device.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
