Medical image reconstruction method and device, computer device and storage medium

Abstract

This application relates to a medical image reconstruction method, apparatus, computer device, and storage medium. Based on the channel values ​​of the detector in the scanning device, a field-of-view weighting function and a reconstruction range weighting function are determined. Based on these two functions, image reconstruction is performed on the raw data of the detected object. The field-of-view weighting function characterizes the relationship between the field-of-view position of a pixel and its weighted value; the reconstruction range weighting function characterizes the relationship between the position of the scanning bed and the reconstruction range weighted value of a pixel. In the embodiments of this application, after determining the field-of-view weighting function and the reconstruction range weighting function, the reconstruction range of the raw data can be determined based on these functions, ensuring that the range of raw data used for each pixel satisfies the sufficiency of the image to be reconstructed. This can improve the temporal resolution of the region of interest in the image to be reconstructed, simultaneously considering both temporal resolution and data completeness.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to a method, apparatus, computer device, and storage medium for medical image reconstruction. Background Technology

[0002] With continuous technological advancements and improvements, detectors are being used more extensively and deeply in the medical field. In detector systems, two X-ray tubes and two detectors are integrated into the scanning equipment. By acquiring images through these two sets of X-ray tubes and detectors, not only can the accuracy and efficiency of diagnosis be improved, but a safer and more comfortable examination experience is also provided for patients.

[0003] To reduce the cost of scanning equipment, current detector systems typically use asymmetric detectors. However, asymmetric detectors cannot simultaneously achieve both temporal resolution and data completeness. Summary of the Invention

[0004] Therefore, it is necessary to provide a medical image reconstruction method, apparatus, computer equipment, and storage medium that can simultaneously take into account temporal resolution and data integrity in order to address the aforementioned technical problems.

[0005] In a first aspect, this application provides a method for medical image reconstruction, comprising:

[0006] Based on the channel values ​​of the detector in the scanning device, a field-of-view weighting function is determined; the field-of-view weighting function is used to characterize the relationship between the field-of-view position of a pixel and the field-of-view weighting value.

[0007] Determine the reconstruction range weighting function; the reconstruction range weighting function is used to characterize the relationship between the position of the scanning bed and the reconstruction range weighting value of the pixel;

[0008] Image reconstruction is performed on the raw data of the detected object based on the field of view weighting function and the reconstruction range weighting function.

[0009] In one embodiment, the field-of-view weighting function includes a first function, a first transition function, and a second function. Determining the field-of-view weighting function based on the channel values ​​of the detector in the scanning device includes:

[0010] The first field-of-view position threshold is determined based on the channel value of the detector, and the second field-of-view position threshold is determined based on the temporal resolution of the image to be reconstructed.

[0011] The first function, the first transition function, and the second function are determined based on the first field of view position threshold and the second field of view position threshold.

[0012] The first function is used to characterize the relationship between the first field-view position interval of a pixel and the first preset field-view weighting value, and the second function is used to characterize the relationship between the second field-view position interval of a pixel and the second preset field-view weighting value.

[0013] In one embodiment, the reconstruction range weighting function includes a fourth function, a second transition function, and a third transition function, and determining the reconstruction range weighting function includes:

[0014] Based on the physiological signals of the object being detected, a first position threshold and a second position threshold of the scanning bed are determined, and a fourth function is determined based on a first position interval including the position between the first position threshold and the second position threshold; the fourth function is used to characterize the relationship between the first position interval and a preset reconstruction range weighted value.

[0015] The third position threshold and the fourth position threshold of the scanning bed are determined based on the attribute information of the rack in the scanning device, and a second transition function is determined based on a second position interval including the position between the first position threshold and the third position threshold, and a third position interval including the position between the second position threshold and the fourth position threshold.

[0016] Based on the channel values ​​of the detector, the fifth position threshold and the sixth position threshold of the scanning bed are determined, and a third transition function is determined based on the fourth position interval including the position between the third position threshold and the fifth position threshold, and the fifth position interval including the position between the fourth position threshold and the sixth position threshold.

[0017] In one embodiment, the step of performing image reconstruction on the raw data of the detected object based on the field-of-view weighting function and the reconstruction range weighting function includes:

[0018] The target field-view weighting value of the pixel is determined based on the field-view weighting function and the field-view position of the pixel.

[0019] The reconstruction interval of the pixel is determined based on the target field-of-view weighting value and the reconstruction range weighting function;

[0020] Image reconstruction is performed on the raw data corresponding to the region to be reconstructed for the pixel.

[0021] In one embodiment, determining the reconstruction interval of the pixel based on the target field-view weighting value and the reconstruction range weighting function includes:

[0022] When the target field of view weighting value is equal to the first preset field of view weighting value, the position interval of the scanning bed is taken as the reconstruction interval of the pixel; the position interval of the scanning bed includes the first position interval, the second position interval, the third position interval, the fourth position interval and the fifth position interval.

[0023] In one embodiment, determining the reconstruction interval of the pixel based on the target field-view weighting value and the reconstruction range weighting function includes:

[0024] If the target field weighting value is not equal to the first preset field weighting value, the reconstruction length of the pixel is determined by the product of the target field weighting value and the length of the raw data.

[0025] The reconstruction interval of the pixel is determined based on the reconstruction length of the pixel and the center position of the first position interval.

[0026] Secondly, this application also provides a medical image reconstruction apparatus, comprising:

[0027] The first determining module is used to determine the field-view weighting function based on the channel values ​​of the detector in the scanning device; the field-view weighting function is used to characterize the relationship between the field-view position of a pixel and the field-view weighting value;

[0028] The second determining module is used to determine the reconstruction range weighting function; the reconstruction range weighting function is used to characterize the relationship between the position of the scanning bed and the reconstruction range weighting value of the pixel.

[0029] The reconstruction module is used to perform image reconstruction on the raw data of the detected object based on the field of view weighting function and the reconstruction range weighting function.

[0030] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0031] Based on the channel values ​​of the detector in the scanning device, a field-of-view weighting function is determined; the field-of-view weighting function is used to characterize the relationship between the field-of-view position of a pixel and the field-of-view weighting value.

[0032] Determine the reconstruction range weighting function; the reconstruction range weighting function is used to characterize the relationship between the position of the scanning bed and the reconstruction range weighting value of the pixel;

[0033] Image reconstruction is performed on the raw data of the detected object based on the field of view weighting function and the reconstruction range weighting function.

[0034] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0035] Based on the channel values ​​of the detector in the scanning device, a field-of-view weighting function is determined; the field-of-view weighting function is used to characterize the relationship between the field-of-view position of a pixel and the field-of-view weighting value.

[0036] Determine the reconstruction range weighting function; the reconstruction range weighting function is used to characterize the relationship between the position of the scanning bed and the reconstruction range weighting value of the pixel;

[0037] Image reconstruction is performed on the raw data of the detected object based on the field of view weighting function and the reconstruction range weighting function.

[0038] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0039] Based on the channel values ​​of the detector in the scanning device, a field-of-view weighting function is determined; the field-of-view weighting function is used to characterize the relationship between the field-of-view position of a pixel and the field-of-view weighting value.

[0040] Determine the reconstruction range weighting function; the reconstruction range weighting function is used to characterize the relationship between the position of the scanning bed and the reconstruction range weighting value of the pixel;

[0041] Image reconstruction is performed on the raw data of the detected object based on the field of view weighting function and the reconstruction range weighting function.

[0042] The aforementioned medical image reconstruction method, apparatus, computer equipment, and storage medium determine a field-of-view weighting function and a reconstruction range weighting function based on the channel values ​​of the detector in the scanning device. Based on these two functions, image reconstruction is performed on the raw data of the detected object. The field-of-view weighting function characterizes the relationship between the field-of-view position of a pixel and its weighted value; the reconstruction range weighting function characterizes the relationship between the position of the scanning bed and the reconstruction range weighted value of a pixel. In this embodiment, after determining the field-of-view weighting function and the reconstruction range weighting function, the reconstruction range of the raw data can be determined based on these functions. This ensures that the range of raw data used for each pixel satisfies the sufficiency of the image to be reconstructed, preventing artifacts from appearing in the reconstructed image due to an insufficient range of raw data. Furthermore, the reconstruction range of the raw data can improve the temporal resolution of the region of interest in the image to be reconstructed, simultaneously considering both temporal resolution and data completeness. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is an application environment diagram of a medical image reconstruction method in one embodiment;

[0045] Figure 2 This is a flowchart illustrating a medical image reconstruction method in one embodiment;

[0046] Figure 3 This is a flowchart illustrating a method for determining the field-of-view weighting function in one embodiment;

[0047] Figure 4 This is a schematic diagram of the view weighting function in one embodiment;

[0048] Figure 5 This is a flowchart illustrating a method for determining the reconstruction range weighting function in one embodiment;

[0049] Figure 6 This is a schematic diagram of the reconstruction range weighting function in one embodiment;

[0050] Figure 7 This is a flowchart illustrating a medical image reconstruction method in another embodiment;

[0051] Figure 8 This is a schematic diagram of the reconstruction range weighting function in another embodiment;

[0052] Figure 9 This is a flowchart illustrating a medical image reconstruction method in another embodiment;

[0053] Figure 10 This is a flowchart illustrating a medical image reconstruction method in another embodiment.

[0054] Figure 11 This is a structural block diagram of a medical image reconstruction device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] The medical image reconstruction method provided in this application can be applied to, for example... Figure 1The application environment shown. In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows. Figure 1 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores relevant data for medical image reconstruction. The I / O interfaces allow the processor to exchange information with external devices. The communication interface allows communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a medical image reconstruction method. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0057] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0058] In one exemplary embodiment, such as Figure 2 As shown, a medical image reconstruction method is provided, which can be applied to... Figure 1 The following explanation uses computer equipment as an example, including the following steps S201 to S203. Wherein:

[0059] S201, Based on the channel values ​​of the detector in the scanning device, determine the field-of-view weighting function; the field-of-view weighting function is used to characterize the relationship between the field-of-view position of a pixel and the field-of-view weighting value.

[0060] The detector channel values ​​are inconsistent; that is, the detector can be an asymmetric dual-source detector or a single-source detector. Optionally, it can be dual-source dual-energy transcatheter aortic valve implantation (TAVI) imaging, other helical reconstruction imaging, similar to 4D computed tomography (CT), etc.

[0061] In this embodiment, a first field-of-view (FOV) position threshold can be determined based on the detector's channel values, and a second FAV position threshold can be determined based on the temporal resolution of the image to be reconstructed. The FAV weighting value corresponding to FAV positions greater than or equal to the first FAV threshold is set as a first preset FAV weighting value, thus obtaining a first function representing the FAV positions greater than or equal to the first FAV threshold and the first preset FAV weighting value. The FAV weighting value corresponding to FAV positions less than or equal to the second FAV threshold is set as a second preset FAV weighting value, thus obtaining a second function representing the FAV positions less than or equal to the second FAV threshold and the second preset FAV weighting value. The FAV weighting function for the FAV positions corresponding to the first and second FAV positions is set as a first transition function. The FAV weighting function includes the first function, the second function, and the first transition function.

[0062] In one possible implementation, the visual field weighting value located within the visual field interval corresponding to the first and second visual field position thresholds can be set as a third preset visual field weighting value. This yields a preset function representing the visual field position between the first and second visual field position thresholds and the third preset visual field weighting value. The visual field weighting function includes a first function, a second function, and a preset function.

[0063] S202, Determine the reconstruction range weighting function; the reconstruction range weighting function is used to characterize the relationship between the position of the scanning bed and the reconstruction range weighting value of the pixel.

[0064] In this embodiment, the scanning bed movement range during the scanning process can be divided into different stages, and different reconstruction range weighting functions can be obtained for different stages. The reconstruction range weighting functions obtained for different stages can be combined to obtain the reconstruction range weighting function.

[0065] In one possible implementation, a first position threshold and a second position threshold of the scanning bed can be determined based on the physiological signals of the object being detected. A reconstruction range weighting function, i.e., a fourth function, is used to characterize the relationship between the first position interval and a preset reconstruction range weighting value, based on a first position interval including the positions between the first and second position thresholds. A third position threshold and a fourth position threshold of the scanning bed are determined based on the attribute information of the gantry in the scanning device. A reconstruction range weighting function, i.e., a second transition function, is determined based on a second position interval including the positions between the first and third position thresholds, and a third position interval including the positions between the second and fourth position thresholds. The fourth function and the second transition function are used as the reconstruction range weighting functions.

[0066] In one possible implementation, the fifth and sixth position thresholds of the scanning bed can be determined based on the detector's channel values. Then, based on the fourth position interval (including positions between the third and fifth position thresholds) and the fifth position interval (including positions between the fourth and sixth position thresholds), a reconstruction range weighting function, i.e., the third transition function, is determined for the fourth and fifth position intervals. The fourth, second, and third transition functions are then used as the reconstruction range weighting functions.

[0067] S203, based on the field-of-view weighting function and the reconstruction range weighting function, performs image reconstruction on the raw data of the detected object.

[0068] In this embodiment, the target field-view weighting value of a pixel can be determined based on the field-view weighting function and the pixel's field-view location. Then, the reconstruction interval of the pixel is determined based on the target field-view weighting value and the reconstruction range weighting function. Finally, image reconstruction is performed on the raw data corresponding to the reconstruction interval of the pixel. That is, the reconstruction range weighting function is modified using the field-view weighting function to obtain the reconstruction interval and reconstruction range weighting value for each pixel.

[0069] In one possible implementation, the viewpoint location of a pixel can be divided into different viewpoint intervals. For viewpoints within the same viewpoint interval, any viewpoint within that interval can be randomly selected. Based on this viewpoint location and a viewpoint weighting function, a target viewpoint weighting value is obtained. Then, based on this target viewpoint weighting value and a reconstruction range weighting function, the region to be reconstructed for the pixel is determined. This region to be reconstructed is used as the region to be reconstructed for all pixels within that viewpoint interval. This process is repeated to obtain the region to be reconstructed for each viewpoint interval, thereby performing image reconstruction on the raw data corresponding to the region to be reconstructed for each pixel.

[0070] In the aforementioned medical image reconstruction method, a field-of-view weighting function and a reconstruction range weighting function are determined based on the channel values ​​of the detector in the scanning device. Based on these two functions, image reconstruction is performed on the raw data of the detected object. The field-of-view weighting function characterizes the relationship between the field-of-view position of a pixel and its weighted value; the reconstruction range weighting function characterizes the relationship between the position of the scanning bed and the reconstruction range weighted value of a pixel. In this embodiment, after determining the field-of-view weighting function and the reconstruction range weighting function, the reconstruction range of the raw data can be determined based on these functions. This ensures that the range of raw data used for each pixel satisfies the sufficiency of the image to be reconstructed, preventing artifacts from appearing in the reconstructed image due to an insufficient range of raw data. Furthermore, the reconstruction range of the raw data can improve the temporal resolution of the region of interest in the image to be reconstructed, simultaneously considering both temporal resolution and data completeness.

[0071] Figure 3 This is a flowchart illustrating a method for determining the field-of-view weighting function in one embodiment, as shown below. Figure 3 As shown, this application embodiment relates to a possible implementation of how to determine the field-of-view weighting function based on the channel values ​​of the detector in the scanning device, including the following steps:

[0072] S301, determine the first field-of-view position threshold based on the detector's channel value, and determine the second field-of-view position threshold based on the temporal resolution of the image to be reconstructed.

[0073] Among them, the first field of view threshold is greater than the second field of view threshold.

[0074] In this embodiment, when the detector is a dual-source detector, the first field-of-view threshold determines the difference in channel values ​​between the detectors. The channel values ​​of the dual-source detectors are compared, and the smaller channel value is used as the first field-of-view threshold. For example, if the channel values ​​of the dual-source detector are 350Fv and 500Fv, then 350 is used as the first field-of-view threshold. Alternatively, any value smaller than the smaller channel value can be used as the first field-of-view threshold, where Fv is the maximum reconstructable field of view of the detector. For example, 320 can be used as the first field-of-view threshold.

[0075] If the detector is a single-source detector, the channel value of the detector is directly used as the first field of view threshold, or the first field of view threshold is determined based on the channel value of the detector.

[0076] In one possible implementation, the temporal resolution of the image to be reconstructed is a crucial indicator of the ability to capture temporal changes in medical imaging. The level of temporal resolution directly affects the image's ability to capture temporal changes, and it is particularly important for diseases or lesions requiring observation of temporal variations, such as cardiac lesions and hemodynamic changes. Optionally, based on clinical experience, the visual field position corresponding to a satisfactory temporal resolution of the image to be reconstructed is generally 200 Fv, so 200 can be used as the second visual field threshold. If the required temporal resolution of the image to be reconstructed differs, the second visual field threshold can be appropriately increased or decreased.

[0077] S302, determine the first function, the first transition function, and the second function based on the first field of view position threshold and the second field of view position threshold.

[0078] The field-view weighting function includes a first function, a first transition function, and a second function. The first function is used to characterize the relationship between the first field-view position interval of a pixel and the first preset field-view weighting value, and the second function is used to characterize the relationship between the second field-view position interval of a pixel and the second preset field-view weighting value.

[0079] The first field of view position interval includes field of view positions that are not less than the first field of view position threshold. The field of view position interval corresponding to the first transition function includes field of view positions that are between the first field of view position threshold and the second field of view position threshold. The second field of view position interval includes field of view positions that are not greater than the second field of view position threshold. The first preset field of view weighting value is greater than the second preset field of view weighting value.

[0080] The first preset field of view weighting value is greater than the second preset field of view weighting value. Optionally, the first field of view threshold can be 1, and the second field of view threshold can be any number between 0 and 1.

[0081] In the embodiments of this application, such as Figure 4 As shown, Figure 4 This is a schematic diagram of a field-view weighting function in one embodiment, where the horizontal axis represents the field-view position corresponding to a pixel, and the vertical axis represents the field-view weighting value corresponding to the pixel. r1 is a first field-view threshold, and r2 is a second field-view threshold. The first preset field-view weighting value corresponding to the field-view position greater than or equal to the first field-view threshold r1 is set to Wr1 to obtain the first function; the second preset field-view weighting value corresponding to the field-view position less than or equal to the second field-view threshold r2 is set to Wr2. The weighting function corresponding to the field-view positions located between the first field-view threshold r1 and the second field-view threshold r2 is the first transition function.

[0082] In this embodiment, a first field-of-view position threshold is determined based on the detector's channel value, and a second field-of-view position threshold is determined based on the temporal resolution of the image to be reconstructed. Based on the first and second field-of-view position thresholds, a first function, a first transition function, and a second function are determined. The determination of the first field-of-view position threshold ensures that the reconstruction range of the subsequent generated data satisfies the sufficiency of the image to be reconstructed, and the determination of the second field-of-view position threshold ensures that the subsequently selected generated data can improve the temporal resolution of the image to be reconstructed.

[0083] Figure 5 This is a flowchart illustrating a method for determining the reconstruction range weighting function in one embodiment, as shown below. Figure 5 As shown, it includes the following steps:

[0084] S501, based on the physiological signal of the object being detected, a first position threshold and a second position threshold of the scanning bed are determined, and a fourth function is determined based on a first position interval including the position between the first position threshold and the second position threshold; the fourth function is used to characterize the relationship between the first position interval and the preset reconstruction range weighted value.

[0085] During the scanning process of the subject, physiological signals of the subject can be acquired. Optionally, for other helical reconstructions, such as 4D CT, respiratory signals can be used; for dual-energy TAVI imaging, electrocardiogram signals can be used, etc.

[0086] In this embodiment of the application, two peaks of the physiological signal are determined, and the scanning bed positions corresponding to the two peaks are used as a first position threshold and a second position threshold. For example... Figure 6 As shown, Figure 6 This is a schematic diagram of a reconstruction range weighting function in one embodiment, where the horizontal axis v represents the position of the scanning bed, and the vertical axis Wv represents the reconstruction range weighting value. The reconstruction range weighting value corresponding to the position between the first position threshold v1 and the second position threshold v2 is set as a preset reconstruction range weighting value to obtain the fourth function, i.e., when the scanning bed is located between the first position threshold v1 and the second position threshold v2, the reconstruction range weighting value is always Wv1.

[0087] For example, the default reconstruction range weighting value Wv1 is 1.

[0088] S502, determine the third position threshold and the fourth position threshold of the scanning bed based on the attribute information of the rack in the scanning device, and determine the second transition function based on the second position interval including the position between the first position threshold and the third position threshold, and the third position interval including the position between the second position threshold and the fourth position threshold.

[0089] In the embodiments of this application, such as Figure 6As shown, based on the attribute information and quasi-value information of the gantry in the scanning device, the third position threshold v3 and the fourth position threshold v4 are determined. The third position threshold v3 and the fourth position threshold v4 are symmetrical about the first position interval. The reconstruction range weighting function for the second position interval, which includes the position between the first position threshold v1 and the third position threshold v3, and the third position interval, which includes the second position threshold v2 and the fourth position threshold v4, is set as a second transition function similar to a sine or cosine. The value range of the reconstruction range weighting value corresponding to the second transition function is Wv2-Wv1. The second transition function can ensure that the temporal resolution of the image to be reconstructed meets the requirements.

[0090] Optionally, the reconstructed range weighting value corresponding to the second transition function can be in the range of 1-0.5.

[0091] S503, based on the channel value of the detector, determine the fifth position threshold and the sixth position threshold of the scanning bed, and based on the fourth position interval including the position between the third position threshold and the fifth position threshold, and the fifth position interval including the position between the fourth position threshold and the sixth position threshold, determine the third transition function.

[0092] In this embodiment of the application, the process continues as described above. Figure 6 As shown, based on the detector's channel values, the scanning range of the detected object, the scanning layer thickness, and the specific scanning protocol, the fifth position threshold v5 and the sixth position threshold v6 are determined. The reconstruction range weighting function for the fourth position interval (including the positions between the third position threshold v3 and the fifth position threshold v5) and the fifth position interval (including the positions between the fourth position threshold v4 and the sixth position threshold v6) is set to a third transition function similar to a sine or cosine function. The value range of the reconstruction range weighting value corresponding to the second transition function is 0-Wv2. The third transition function ensures the sufficiency and completeness of the generated data of the image to be reconstructed.

[0093] Optionally, the reconstructed range weighting value corresponding to the third transition function can be in the range of 0-0.5.

[0094] In this embodiment, a first position threshold and a second position threshold of the scanning bed are determined based on the physiological signals of the detected object. A fourth function is determined based on a first position interval including the positions between the first and second position thresholds. A third and fourth position thresholds of the scanning bed are determined based on the attribute information of the gantry in the scanning device. A second transition function is determined based on a second position interval including the positions between the first and third position thresholds and a third position interval including the positions between the second and fourth position thresholds. A fifth and sixth position thresholds of the scanning bed are determined based on the channel values ​​of the detector. A third transition function is determined based on a fourth position interval including the positions between the third and fifth position thresholds and a fifth position interval including the positions between the fourth and sixth position thresholds. This application divides the movement position of the scanning bed into three stages, obtaining the reconstruction range weighting function corresponding to each stage. Combining the fourth, second, and third transition functions yields the reconstruction range weighting function, which ensures that the data length of the reconstruction range weighting value used within a certain field of view meets the minimum range requirement of the image to be reconstructed, thus ensuring data sufficiency and completeness while considering temporal resolution.

[0095] Figure 7 This is a flowchart illustrating a medical image reconstruction method in another embodiment, such as... Figure 7 As shown, this application embodiment relates to a possible implementation of image reconstruction of raw data of a detected object based on a field-of-view weighting function and a reconstruction range weighting function, including the following steps:

[0096] S701 determines the target field-view weighting value of a pixel based on the field-view weighting function and the field-view position of the pixel.

[0097] In the embodiments of this application, for each pixel, the view position of the pixel is substituted into the view weighting function to obtain the target view weighting value of the pixel.

[0098] S702 determines the reconstruction interval of the pixel based on the target field weighting value and the reconstruction range weighting function.

[0099] In this embodiment, if the target field-of-view weighting value is a first preset field-of-view weighting value, the reconstruction range weighting function remains unchanged; that is, the area to be reconstructed for each pixel is the entire position range of the scanning bed corresponding to the reconstruction range weighting function. If the target field-of-view weighting value is not the first preset field-of-view weighting value, the reconstruction range weighting function is modified based on the target field-of-view weighting value; that is, the area to be reconstructed is obtained based on the target field-of-view weighting value and the reconstruction range weighting function. Figure 8As shown, the interval to be reconstructed is vf-vd, which can also be understood as the weighted function of the reconstructed range after correction being the weighted function of the reconstructed range corresponding to the interval to be reconstructed, vf-vd.

[0100] S703 performs image reconstruction on the raw data corresponding to the region to be reconstructed for each pixel.

[0101] In this embodiment, for each pixel, after obtaining the reconstruction region for each pixel, the raw data corresponding to the reconstruction region and the target reconstruction range weighted value corresponding to the pixel can be obtained based on the reconstruction region. Candidate data for that pixel is obtained based on the raw data corresponding to the reconstruction region and the target reconstruction range weighted value. The candidate data for each pixel is then filtered and back-projected to obtain the reconstructed image.

[0102] In this embodiment, the target field-view weighting value of a pixel is determined based on the field-view weighting function and the pixel's field-view position. The reconstruction interval of the pixel is then determined based on the target field-view weighting value and the reconstruction range weighting function. Image reconstruction is then performed on the raw data corresponding to the reconstruction interval of the pixel. The reconstruction interval and reconstruction range weighting value change with the target field-view weighting value of the pixel. That is, the reconstruction range weighting value used changes with the distance from the reconstruction center position of the pixel in the image to be reconstructed affected by the current ray. This ensures that the reconstruction range weighting values ​​used during the filtering backprojection process are inconsistent for rays corresponding to images to be reconstructed within different field-view ranges.

[0103] In one embodiment, determining the region to be reconstructed for a pixel based on the target field-of-view weighting value and the reconstruction range weighting function includes:

[0104] When the target field weighting value is equal to the first preset field weighting value, the position interval of the scanning bed is used as the reconstruction interval of the pixel; the position interval of the scanning bed includes the first position interval, the second position interval, the third position interval, the fourth position interval and the fifth position interval.

[0105] In this embodiment of the application, when the target field of view weighting value is equal to the first preset field of view weighting value, the position range of the scanning bed is taken as the reconstruction range of the pixel, that is, the complete movement range of the scanning bed during the entire scanning process is taken as the reconstruction range.

[0106] When the target field weighting value is not equal to the first preset field weighting value, the reconstruction length of the pixel is determined by the product of the target field weighting value and the length of the generated data; the reconstruction interval of the pixel is determined by the reconstruction length of the pixel and the center position of the first position interval.

[0107] In this embodiment, when the target field-view weighting value is not equal to the first preset field-view weighting value, that is, when the target field-view weighting value is the second preset field-view weighting value, or when the target field-view weighting value is the field-view weighting value corresponding to the first transition function, the reconstruction length of the pixel is determined based on the product of the target field-view weighting value and the length of the generated data. Continuing as described above... Figure 8 As shown, the reconstruction length is extended to both sides from the center position v0 of the first position interval. For example, if the length of the raw data is 10000, the center position v0 of the first position interval is 4000, and the target field weighting value is 0.2, then the reconstruction length is 5000, and the reconstruction interval vf-vd of the pixels is 1500-6500.

[0108] In this embodiment, when the target field-of-view weighting value equals the first preset field-of-view weighting value, the position interval of the scanning bed is used as the reconstruction interval of the pixel. When the target field-of-view weighting value does not equal the first preset field-of-view weighting value, the reconstruction length of the pixel is determined by multiplying the target field-of-view weighting value by the length of the raw data. The reconstruction interval of the pixel is then determined based on the reconstruction length and the center position of the first position interval. Since the image to be reconstructed may suffer from truncation artifacts due to inaccurate selection of the reconstruction data range, this application obtains different reconstruction intervals for different target field-of-view weighting values ​​of the pixel. This allows for the determination of different ranges of raw data based on different reconstruction intervals, improving the temporal resolution of the image to be reconstructed while ensuring data sufficiency.

[0109] Figure 9 This is a flowchart illustrating a medical image reconstruction method in another embodiment. Figure 10 This is a flowchart illustrating a medical image reconstruction method in another embodiment, such as... Figure 9 and Figure 10 As shown, it includes the following steps:

[0110] S901, determine the first field-of-view position threshold based on the detector's channel value, and determine the second field-of-view position threshold based on the temporal resolution of the image to be reconstructed;

[0111] S902, determine the first function, the first transition function, and the second function based on the first field of view position threshold and the second field of view position threshold;

[0112] The field-view weighting function includes a first function, a first transition function, and a second function. The first function is used to characterize the relationship between the first field-view position interval of a pixel and the first preset field-view weighting value, and the second function is used to characterize the relationship between the second field-view position interval of a pixel and the second preset field-view weighting value.

[0113] The first field of view position interval includes field of view positions that are not less than the first field of view position threshold. The field of view position interval corresponding to the first transition function includes field of view positions that are between the first field of view position threshold and the second field of view position threshold. The second field of view position interval includes field of view positions that are not greater than the second field of view position threshold. The first preset field of view weighting value is greater than the second preset field of view weighting value.

[0114] S903, based on the physiological signals of the detected object, determine the first position threshold and the second position threshold of the scanning bed, and based on the first position interval including the position between the first position threshold and the second position threshold, determine the fourth function; the fourth function is used to characterize the relationship between the first position interval and the preset reconstruction range weighted value;

[0115] S904, determine the third position threshold and the fourth position threshold of the scanning bed according to the attribute information of the rack in the scanning device, and determine the second transition function based on the second position interval including the position between the first position threshold and the third position threshold, and the third position interval including the second position threshold and the fourth position threshold;

[0116] S905, based on the channel value of the detector, determine the fifth position threshold and the sixth position threshold of the scanning bed, and based on the fourth position interval including the position between the third position threshold and the fifth position threshold, and the fifth position interval including the position between the fourth position threshold and the sixth position threshold, determine the third transition function;

[0117] Figure 10 The reconstructed data information may include detector channel values, physiological signals of the detected object, temporal resolution of the image to be reconstructed, and attribute information of the gantry in the scanning device.

[0118] S906, determine the target field weighting value of the pixel based on the field weighting function and the field position of the pixel;

[0119] S907, when the target field weighting value is equal to the first preset field weighting value, the position interval of the scanning bed is used as the interval to be reconstructed for the pixels; the position interval of the scanning bed includes the first position interval, the second position interval, the third position interval, the fourth position interval, and the fifth position interval;

[0120] S908, when the target field weighting value is not equal to the first preset field weighting value, the reconstruction length of the pixel is determined according to the product of the target field weighting value and the length of the raw data;

[0121] S909, determine the region to be reconstructed for the pixel based on the reconstructed length of the pixel and the center position of the first position region;

[0122] The target field-view weighting value is obtained using a field-view weighting function. Based on this weighted value, the region to be reconstructed for each pixel is then determined. Figure 10 The reconstruction range weighting function is modified by using the field of view weighting function to obtain the modified reconstruction range weighting function.

[0123] S910 performs image reconstruction on the raw data corresponding to the region to be reconstructed for each pixel.

[0124] That is Figure 10 The image is reconstructed by weighted filtering back projection on the raw data corresponding to the interval to be reconstructed of the pixels, and the output image is obtained.

[0125] In this embodiment, after determining the field-view weighting function and the reconstruction range weighting function, the reconstruction range of the raw data can be determined based on these functions. This ensures that the range of raw data used for each pixel satisfies the sufficiency of the image to be reconstructed, preventing artifacts from occurring in the reconstructed image due to an insufficient range of raw data. Furthermore, the reconstruction range of the raw data can improve the temporal resolution of the region of interest in the image to be reconstructed, thus simultaneously considering both temporal resolution and data completeness.

[0126] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0127] Based on the same inventive concept, this application also provides a medical image reconstruction apparatus for implementing the medical image reconstruction method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more medical image reconstruction apparatus embodiments provided below can be found in the limitations of the medical image reconstruction method described above, and will not be repeated here.

[0128] In one exemplary embodiment, such as Figure 11 As shown, a medical image reconstruction device is provided, comprising: a first determining module 11, a second determining module 12, and a reconstruction module 13, wherein:

[0129] The first determining module 11 is used to determine the field-view weighting function based on the channel value of the detector in the scanning device; the field-view weighting function is used to characterize the relationship between the field-view position of a pixel and the field-view weighting value;

[0130] The second determining module 12 is used to determine the reconstruction range weighting function; the reconstruction range weighting function is used to characterize the relationship between the position of the scanning bed and the reconstruction range weighting value of the pixel;

[0131] The reconstruction module 13 is used to reconstruct images of the raw data of the detected object based on the field of view weighting function and the reconstruction range weighting function.

[0132] In one embodiment, the first determining module 11 is specifically used to determine a first field-of-view position threshold based on the channel value of the detector, and to determine a second field-of-view position threshold based on the temporal resolution of the image to be reconstructed; and to determine a first function, a first transition function, and a second function based on the first field-of-view position threshold and the second field-of-view position threshold.

[0133] The field-view weighting function includes a first function, a first transition function, and a second function. The first function is used to characterize the relationship between the first field-view position interval of a pixel and the first preset field-view weighting value. The second function is used to characterize the relationship between the second field-view position interval of a pixel and the second preset field-view weighting value. The first field-view position interval includes field-view positions that are not less than the first field-view position threshold. The field-view position interval corresponding to the first transition function includes field-view positions that are between the first field-view position threshold and the second field-view position threshold. The second field-view position interval includes field-view positions that are not greater than the second field-view position threshold. The first preset field-view weighting value is greater than the second preset field-view weighting value.

[0134] In one embodiment, the second determining module 12 is specifically configured to: determine a first position threshold and a second position threshold of the scanning bed based on the physiological signal of the detected object; and determine a fourth function based on a first position interval including the position between the first and second position thresholds; the fourth function is used to characterize the relationship between the first position interval and a preset reconstruction range weighted value; determine a third position threshold and a fourth position threshold of the scanning bed based on the attribute information of the gantry in the scanning device; and determine a second transition function based on a second position interval including the position between the first and third position thresholds and a third position interval including the position between the second and fourth position thresholds; and determine a fifth position threshold and a sixth position threshold of the scanning bed based on the channel value of the detector; and determine a third transition function based on a fourth position interval including the position between the third and fifth position thresholds and a fifth position interval including the position between the fourth and sixth position thresholds.

[0135] In one embodiment, the reconstruction module 13 is specifically used to determine the target field-view weighting value of a pixel based on the field-view weighting function and the field-view position of the pixel; determine the reconstruction interval of the pixel based on the target field-view weighting value and the reconstruction range weighting function; and perform image reconstruction on the raw data corresponding to the reconstruction interval of the pixel.

[0136] In one embodiment, the reconstruction module 13 is specifically used to take the position interval of the scanning bed as the reconstruction interval of the pixel when the target field weighting value is equal to the first preset field weighting value; the position interval of the scanning bed includes a first position interval, a second position interval, a third position interval, a fourth position interval and a fifth position interval.

[0137] In one embodiment, the reconstruction module 13 is specifically used to determine the reconstruction length of a pixel based on the product of the target field weighting value and the length of the raw data when the target field weighting value is not equal to the first preset field weighting value; and to determine the reconstruction interval of a pixel based on the reconstruction length of the pixel and the center position of the first position interval.

[0138] Each module in the aforementioned medical image reconstruction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0139] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above method embodiments.

[0140] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above method embodiments.

[0141] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of any of the above method embodiments.

[0142] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0143] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. 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). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0144] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 application.

[0145] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for medical image reconstruction, characterized in that, The method includes: Based on the channel values ​​of the detector in the scanning device, a field-of-view weighting function is determined; the field-of-view weighting function is used to characterize the relationship between the field-of-view position of a pixel and the field-of-view weighting value. Determine the reconstruction range weighting function; the reconstruction range weighting function is used to characterize the relationship between the position of the scanning bed and the reconstruction range weighting value of the pixel; Image reconstruction is performed on the raw data of the detected object based on the field of view weighting function and the reconstruction range weighting function.

2. The method according to claim 1, characterized in that, The field-of-view weighting function includes a first function, a first transition function, and a second function. The determination of the field-of-view weighting function based on the channel values ​​of the detector in the scanning device includes: The first field-of-view position threshold is determined based on the channel value of the detector, and the second field-of-view position threshold is determined based on the temporal resolution of the image to be reconstructed. The first function, the first transition function, and the second function are determined based on the first field of view position threshold and the second field of view position threshold. The first function is used to characterize the relationship between the first field-view position interval of a pixel and the first preset field-view weighting value, and the second function is used to characterize the relationship between the second field-view position interval of a pixel and the second preset field-view weighting value.

3. The method according to claim 2, characterized in that, The reconstruction range weighting function includes a fourth function, a second transition function, and a third transition function. Determining the reconstruction range weighting function includes: Based on the physiological signals of the object being detected, a first position threshold and a second position threshold of the scanning bed are determined, and a fourth function is determined based on a first position interval including the position between the first position threshold and the second position threshold; the fourth function is used to characterize the relationship between the first position interval and a preset reconstruction range weighted value. The third position threshold and the fourth position threshold of the scanning bed are determined based on the attribute information of the rack in the scanning device, and a second transition function is determined based on a second position interval including the position between the first position threshold and the third position threshold, and a third position interval including the position between the second position threshold and the fourth position threshold. Based on the channel values ​​of the detector, the fifth position threshold and the sixth position threshold of the scanning bed are determined, and a third transition function is determined based on the fourth position interval including the position between the third position threshold and the fifth position threshold, and the fifth position interval including the position between the fourth position threshold and the sixth position threshold.

4. The method according to claim 3, characterized in that, The step of reconstructing the image from the raw data of the detected object based on the field-of-view weighting function and the reconstruction range weighting function includes: The target field-view weighting value of the pixel is determined based on the field-view weighting function and the field-view position of the pixel. The reconstruction interval of the pixel is determined based on the target field-of-view weighting value and the reconstruction range weighting function; Image reconstruction is performed on the raw data corresponding to the region to be reconstructed for the pixel.

5. The method according to claim 4, characterized in that, The step of determining the reconstruction interval of the pixel based on the target field-of-view weighted value and the reconstruction range weighted function includes: When the target field of view weighting value is equal to the first preset field of view weighting value, the position interval of the scanning bed is taken as the reconstruction interval of the pixel; the position interval of the scanning bed includes the first position interval, the second position interval, the third position interval, the fourth position interval and the fifth position interval.

6. The method according to claim 4, characterized in that, The step of determining the reconstruction interval of the pixel based on the target field-of-view weighted value and the reconstruction range weighted function includes: If the target field weighting value is not equal to the first preset field weighting value, the reconstruction length of the pixel is determined by the product of the target field weighting value and the length of the raw data. The reconstruction interval of the pixel is determined based on the reconstruction length of the pixel and the center position of the first position interval.

7. A medical image reconstruction device, characterized in that, The device includes: The first determining module is used to determine the field-view weighting function based on the channel values ​​of the detector in the scanning device; the field-view weighting function is used to characterize the relationship between the field-view position of a pixel and the field-view weighting value; The second determining module is used to determine the reconstruction range weighting function; the reconstruction range weighting function is used to characterize the relationship between the position of the scanning bed and the reconstruction range weighting value of the pixel. The reconstruction module is used to perform image reconstruction on the raw data of the detected object based on the field of view weighting function and the reconstruction range weighting function.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images