A method and system for handling projection data anomalies

Abstract

The embodiment of the present specification provides a projection data exception processing method and system, the method comprises: determining the abnormal data boundary corresponding to the target scanning condition based on the target scanning condition corresponding to the projection data; determining the target abnormal data in the projection data based on the abnormal data boundary.

Description

Technical Field

[0001] This specification relates to the field of medical imaging, and in particular to a method and system for processing projection data anomalies. Background Technology

[0002] In non-invasive scans used for disease diagnosis or research purposes, such as computed tomography (CT), detectors acquire and generate projection data, which is then processed to reconstruct the scanned image. However, due to potential equipment malfunctions, design flaws in the computer software, and patient movement (such as breathing or shaking) during the scanning process, some projection data may be abnormal, leading to artifacts and other problems in the final reconstructed image.

[0003] Therefore, a method and system are needed to identify and repair abnormal data in projection data. Summary of the Invention

[0004] One embodiment of this specification provides a method for handling projection data anomalies. The method includes: determining anomaly data boundaries corresponding to target scanning conditions based on the projection data; and determining target anomaly data in the projection data based on the anomaly data boundaries.

[0005] One embodiment of this specification provides a projection data anomaly processing system, the system comprising: a first determining module, configured to determine anomaly data boundaries corresponding to target scanning conditions based on the target scanning conditions corresponding to the projection data; and a second determining module, configured to determine target anomaly data in the projection data based on the anomaly data boundaries.

[0006] One embodiment of this specification provides a projection data anomaly processing apparatus, including a processor, the processor being configured to execute the projection data anomaly processing method as described in any of the above embodiments.

[0007] One embodiment of this specification provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the projection data anomaly handling method as described in any of the above embodiments. Attached Figure Description

[0008] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0009] Figure 1This is a schematic diagram illustrating an application scenario of the projection data anomaly processing system according to some embodiments of this specification;

[0010] Figure 2 This is a block diagram of the processing device 140 shown according to some embodiments of this specification;

[0011] Figure 3 This is an exemplary flowchart of a projection data anomaly handling method according to some embodiments of this specification;

[0012] Figure 4 This is an exemplary flowchart of a projection data anomaly handling method according to other embodiments of this specification;

[0013] Figure 5 This is an exemplary flowchart of a projection data anomaly handling method according to other embodiments of this specification;

[0014] Figure 6 This is an exemplary flowchart of a method for determining abnormal data boundaries according to some embodiments of this specification;

[0015] Figure 7 This is a schematic diagram illustrating yet another method for determining abnormal data boundaries according to some embodiments of this specification;

[0016] Figure 8 This is a schematic diagram illustrating yet another method for determining abnormal data boundaries according to some embodiments of this specification. Detailed Implementation

[0017] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0018] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0019] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0020] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0021] This application relates to a method, system, and storage medium for handling projection data anomalies. This method, system, and storage medium can be applied to computer data processing. In some embodiments, this method, system, and storage medium can be applied to processing abnormal data in projection data.

[0022] Figure 1 This is a schematic diagram illustrating an application scenario of a projection data anomaly processing system according to some embodiments of this specification.

[0023] The projection data anomaly processing system 100 can be used to process scanned data within projection data. For example... Figure 1 As shown, the projection data anomaly processing system 100 may include a scanning device 110, a network 120, a terminal device 130, a processing device 140, and a storage device 150.

[0024] The scanning device 110 can be used to scan an object to obtain scan data of that object. The object to be scanned can refer to the object that needs to be scanned; it can be a living organism (e.g., a patient, animal, etc.) or a non-living organism (e.g., a phantom, a water phantom, etc.). In some embodiments, the scanning device 110 can be a non-invasive imaging device for disease diagnosis or research purposes, including but not limited to ultrasound scanners, X-ray scanners, X-ray imaging-magnetic resonance imaging (X-ray-MRI) scanners, positron emission tomography-X-ray imaging (PET-X-ray) scanners, etc.

[0025] Network 120 can connect various components of the system and / or connect the system to external resources. In some embodiments, the various components of system 100 can exchange information and / or data through network 120. For example, scanning device 110 and terminal device 130 can connect or communicate through network 120. In some embodiments, network 120 may include at least one network access point. For example, network 120 may include wired and / or wireless network access points, such as base stations and / or internet switching points, through which at least one component of system 100 can connect to network 120 to exchange data and / or information.

[0026] Terminal device 130 can be various terminals used for sending or receiving instructions. Terminal device 130 can communicate and / or connect to scanning device 110, processing device 140, and / or storage device 150. For example, a user (such as a doctor or operator of the scanning device) can interact with scanning device 110 through terminal device 130 to control one or more components of scanning device 110. In some embodiments, terminal device 130 may include one or any combination of mobile device 131, tablet computer 132, laptop computer 133, or other devices with input and / or output functions.

[0027] Processing device 140 can process data and / or information obtained from other devices or various components of system 100. For example, processing device 140 can acquire and analyze scan data of a scanned object from scanning device 110. In some embodiments, processing device 140 can be a single server or a group of servers. The server group can be centralized or distributed. In some embodiments, processing device 140 can be local or remote. For example, processing device 140 can acquire and process scan data from scanning device 110. In some embodiments, processing device 140 can be implemented on a cloud platform. For example, the cloud platform can include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud cloud, multi-cloud, etc., or any combination thereof. In some embodiments, processing device 140 can include one or more processors (e.g., a single-chip processor or a multi-chip processor). In some embodiments, processing device 140 can be a standalone device. In some embodiments, processing device 140 can be part of scanning device 110 or terminal device 130. For example, processing device 140 can be integrated within scanning device 110.

[0028] Storage device 150 can store data, instructions, and / or any other information. Storage device 150 can store data (such as scan data, patient information, etc.) obtained from various components of system 100, such as scanning device 110, processing device 140, etc. In some embodiments, storage device 150 can store data and / or instructions used by processing device 140 to perform or complete the exemplary methods described herein. In some embodiments, storage device 150 may include mass storage, removable storage, volatile read-write storage, read-only storage (ROM), etc., or any combination thereof. In some embodiments, storage device 150 may be implemented on a cloud platform.

[0029] It should be noted that the application scenario of the projection data anomaly processing system 100 is provided for illustrative purposes only and is not intended to limit the scope of this application. Those skilled in the art can make various modifications or variations based on the description in this specification. For example, the projection data anomaly processing system 100 may also include an information source. Furthermore, the projection data anomaly processing system 100 may implement similar or different functions on other devices. However, these changes and modifications will not depart from the scope of this application.

[0030] Figure 2 This is a block diagram of the processing device 140 shown according to some embodiments of this specification.

[0031] like Figure 2 As shown, the processing device 140 may include a first determining module 210, a second determining module 220, a correction module 230, and a third determining module 240.

[0032] The first determining module 210 can be used to determine the abnormal data boundaries corresponding to the target scanning conditions based on the target scanning conditions corresponding to the projection data. For more information on projection data and target scanning conditions, please refer to [link to relevant documentation]. Figure 3 The details and related descriptions will not be repeated here.

[0033] The second determining module 220 can be used to determine target anomalous data in the projected data based on anomalous data boundaries. For further explanation of anomalous data boundaries and target anomalous data, see [link to documentation]. Figure 3 The details and related descriptions will not be repeated here.

[0034] The correction module 230 can be used to correct abnormal target data in the projection data to obtain corrected data.

[0035] The third determination module 240 can be used to determine abnormal components of the scanning device based on the data characteristics of the target abnormal data. For more information on data characteristics and abnormal components, please refer to [link to documentation / reference]. Figure 5 The details and related descriptions will not be repeated here.

[0036] It should be understood that Figure 2 The various modules of the processing device 140 shown can be implemented in various ways. For example, in some embodiments, they can be implemented by hardware, software, or a combination of both.

[0037] It should be noted that the above description of the various modules of the processing device 140 is for ease of description only and should not limit this specification to the scope of the illustrated embodiments. It is understood that those skilled in the art, after understanding the principles, may arbitrarily combine the various modules or form subsystems connected to other modules without departing from these principles. For example, the functions of the first determining module 210, the second determining module 220, and the third determining module 240 can be implemented on the same module, or the functions of the above modules can be jointly implemented by multiple modules.

[0038] Figure 3 This is an exemplary flowchart of a projection data anomaly handling method according to some embodiments of this specification. Figure 3 As shown, process 300 includes the following steps. In some embodiments, process 300 may be executed by processing device 140.

[0039] Step 310: Based on the target scanning conditions corresponding to the projection data, determine the abnormal data boundaries corresponding to the target scanning conditions. In some embodiments, this step 310 can be performed by the first determining module 210.

[0040] Projected data refers to the unprocessed data obtained after scanning an object using a scanning device. Specifically, a radiation source in the scanning device emits rays towards the scanned area of ​​the object, and a detector in the device collects the attenuated data after the rays pass through the scanned area; this data is then used as the projected data. The radiation source emits rays towards the scanned object, and the detector receives the rays that pass through the object.

[0041] In some embodiments, the projection data can be DICOM structured data or other structured data. The projection data acquired by the detector in a single acquisition can be defined as a projection data set, which may contain multiple scan data. The detector can acquire data multiple times to obtain multiple projection data sets. In some embodiments, the processing device 140 can sort and number the projection data acquired by the detector based on the order of acquisition, such as numbering the projection data sets acquired by the detector from the 1st to the 1000th acquisition as 1 to 1000. By looking up the number of the projection data set, the corresponding projection data set can be determined.

[0042] Target scanning conditions refer to the pre-set conditions for scanning the object. In some embodiments, target scanning conditions may include the model information of the scanning device, the scanning protocol, and the scanning area. The model information of the scanning device may refer to the model of the scanning device, such as U53, U64, etc. The scanning protocol may include the scanning method and scanning parameters of the scanning device, such as axial scanning, helical scanning, etc. The scanning area may be the part of the object to be scanned, such as the head, ears and nose, chest, abdomen, etc.

[0043] In some embodiments, the target scanning conditions may also include other scanning-related information, such as the projection data set number.

[0044] In some embodiments, the target scanning conditions can be determined by the user's preset settings. For example, a doctor can preset the scanning device model to U53, the scanning protocol to axial scanning, and the scanning site to the head before scanning a patient.

[0045] Anomalous data refers to scan data that has changed during the scanning process due to other factors (such as movement of the scanned area, metallic objects within the scanned object, or scanning equipment malfunction). Image reconstruction based on anomalous data will produce artifacts in the reconstructed image. Conversely, normal data refers to scan data that has not been affected by other factors during the scanning process.

[0046] An anomalous data boundary can refer to the boundary between normal and anomalous data in the projected data. In some embodiments, the anomalous data boundary can be two values. When the scanned data lies between the two values, it is considered normal data; when the scanned data lies outside the two values, it is considered anomalous data. For example, the anomalous data boundary can be m and n, where m < n. For a scanned data value l, when m ≤ l ≤ n, the scanned data is considered normal data; when m > l or l > n, the scanned data is considered anomalous data. In some embodiments, the anomalous data boundary can also be multiple values.

[0047] In some embodiments, different target scanning conditions correspond to different abnormal data boundaries.

[0048] In some embodiments, anomalous data boundaries can be determined by querying an anomalous data boundary table, which reflects the correspondence between target scanning conditions and anomalous data boundaries. For example, anomalous data boundaries can be queried using the following anomalous data boundary table:

[0049] Scanning device model Scanned area Scanning Protocol Abnormal data boundaries U53 head Axial scan M1, N1 U64 abdomen Spiral scan M2, N2

[0050] By consulting the table above, we can determine that when the scanning conditions are U53 scanning device, head scanning area, and axial scanning protocol, the abnormal data boundaries under these conditions are M1 and N1.

[0051] For more information on outlier boundary tables, please see [link / reference]. Figure 6 The details and related descriptions will not be repeated here.

[0052] Step 320: Based on the abnormal data boundaries, determine the target abnormal data in the projected data. In some embodiments, this step 320 may be performed by the second determining module 220.

[0053] Target anomalous data refers to abnormal data in the projection data under target scanning conditions. By comparing the data values ​​of each data point in the projection data with the boundaries of anomalous data, the target anomalous data in the projection data can be identified.

[0054] In some embodiments, the target anomalous data can also be determined in other ways. For example, image reconstruction can be performed directly based on the projection data to identify the artifact portions of the reconstructed image, and then backprojection can be performed on these artifact portions to determine the target anomalous data. Another example is determination by direct annotation of the projection data by the user.

[0055] Figure 4 This is an exemplary flowchart of a projection data anomaly handling method according to other embodiments of this specification. Figure 4 As shown, process 400 includes the following steps. In some embodiments, process 400 may be executed by processing device 140.

[0056] The detailed execution process of steps 410 to 420 has been described in detail in steps 310 and 320 of the above embodiments, and will not be repeated here.

[0057] Step 430: Correct the abnormal target data in the projection data to obtain corrected data. In some embodiments, step 430 may be performed by correction module 230.

[0058] In some embodiments, the projected data set containing abnormal data can be determined based on the abnormal data boundary, and the projected data set containing abnormal data can be corrected to obtain the corrected data.

[0059] In some embodiments, the correction method can be determined based on the number of abnormal data in each projection dataset. In some embodiments, when the amount of abnormal data in a projection dataset exceeds a preset threshold, the entire projection dataset can be repaired to obtain repaired data. Specifically, scan data from projection datasets with similar numbers that do not contain abnormal data can be called to repair all scan data in that projection dataset. The repair method may include, but is not limited to, algorithms such as interpolation and least squares.

[0060] In some embodiments, when the amount of abnormal data in the projection dataset is less than or equal to a preset threshold, the abnormal data portion of the projection dataset can be repaired to obtain repaired data. Specifically, the abnormal data in the projection dataset can be repaired based on the normal data in the projection dataset, and the repair methods may include, but are not limited to, interpolation, iteration, least squares, and other algorithms.

[0061] In some embodiments, the correction method can also be determined based on other methods. For example, the correction method can be determined based on the percentage of abnormal data in the projection dataset. When the percentage of abnormal data in the projection dataset is greater than a preset threshold, the entire projection dataset can be repaired to obtain repaired data. When the percentage of abnormal data in the projection dataset is less than or equal to a preset threshold, the entire projection dataset can be repaired to obtain repaired data.

[0062] Figure 5 This is an exemplary flowchart of a projection data anomaly handling method according to other embodiments of this specification. Figure 5 As shown, process 500 includes the following steps. In some embodiments, process 500 may be executed by processing device 140.

[0063] The detailed execution process of steps 510 to 520 has been described in detail in steps 310 and 320 of the above embodiments, and will not be repeated here.

[0064] Step 530: Based on the data characteristics of the target abnormal data, determine the abnormal components of the scanning device. In some embodiments, this step 530 may be performed by a third determining module 240.

[0065] The data characteristics of target anomalous data can refer to the properties of the target anomalous data. In some embodiments, the data characteristics of target anomalous data may include, but are not limited to, the size of the target anomalous data, the trend of the target anomalous data, and the number of the projected data set corresponding to the target anomalous data.

[0066] An abnormal component can be a part of the scanning equipment that is malfunctioning. For example, an abnormal component could be a radiation source in the scanning equipment. During the scanning process, an abnormal component can lead to the generation of abnormal data.

[0067] In some embodiments, different data characteristics of target anomalous data can correspond to different anomalous components. By using a preset correspondence, the anomalous components of the scanning device can be determined based on the data characteristics of the target anomalous data. This preset correspondence can be set by the user based on experience. For example, if the data characteristic of the target anomalous data is that the data value deviates from the anomalous data boundary by more than a preset threshold, the preset correspondence can be used to determine that the radiation source in the scanning device is anomalous.

[0068] Figure 6 This is an exemplary flowchart illustrating a method for determining abnormal data boundaries according to some embodiments of this specification. Figure 6 As shown, process 600 includes the following steps. In some embodiments, process 600 may be executed by processing device 140.

[0069] Step 610: Obtain normal and abnormal images under the target scanning conditions.

[0070] A normal image can refer to a clear CT image without artifacts, or with a small number of artifacts that do not affect the acquisition of image information.

[0071] Abnormal images can refer to CT images containing artifacts that affect the acquisition of image information.

[0072] In some embodiments, normal and abnormal images can be acquired in various ways. For example, normal and abnormal images can be acquired directly from historical data on a storage device, or directly via a network. In some embodiments, a candidate image set can also be acquired. This candidate image set may contain multiple candidate images obtained under the target scanning conditions; these candidate images may be normal or abnormal. The candidate images in the candidate image set can be input into a discrimination model, and the output is the category of the candidate image (e.g., the candidate image is a normal image).

[0073] Step 620: Based on normal and abnormal images, determine the boundary of abnormal data under the target scanning conditions.

[0074] In some embodiments, modeling or various data analysis algorithms, such as regression analysis and discriminant analysis, can be used to analyze and process normal and abnormal images corresponding to the target scanning conditions to determine the abnormal data boundaries under the target scanning conditions.

[0075] In some embodiments, normal and abnormal images can be processed based on an abnormal data boundary model to determine the abnormal data boundaries under the target scanning conditions. Normal and abnormal images under the target scanning conditions can be input into the abnormal data boundary model, and the output of the abnormal data boundary model is the abnormal data boundary under the target scanning conditions. In some embodiments, multiple normal and abnormal images can be input into the abnormal data boundary model. For example, five normal images and five abnormal images under the target scanning conditions can be input into the abnormal data boundary model.

[0076] In some embodiments, the anomaly data boundary model can be trained using normal and anomalous sample images from historical CT images under the same scanning conditions. These normal and anomalous sample images under the same scanning conditions can be used as training samples, and the anomaly data boundary under those conditions can be used as the labels for the training samples. The training samples can be obtained in various ways, such as through manual annotation. Alternatively, historical CT images can be input into a discriminative model, and the output of the discriminative model can determine the normal and anomalous sample images within the historical CT images; the labels for the training samples can be determined through manual annotation. A large number of labeled training samples are input into the initial anomaly data boundary model, and the parameters of the initial anomaly data boundary model are updated through training. Training ends when the trained model meets preset conditions, resulting in a well-trained anomaly data boundary model.

[0077] In some embodiments, the abnormal data boundary model may include, but is not limited to, a convolutional neural network model and a deep neural network model.

[0078] In some embodiments, based on normal and abnormal images, the abnormal data boundaries corresponding to the target scanning conditions can also be determined in other ways. For example, based on the abnormal image, a first data set in the first projection data corresponding to the abnormal image can be determined; based on the normal image, a second data set in the second projection data corresponding to the normal image can be determined; based on the second data set, a normal data range can be determined; and based on the normal data range, the abnormal data boundaries under the target scanning conditions can be determined. For more information on determining the normal data range based on normal and abnormal images to determine the abnormal data boundaries under the target scanning conditions, see [link to relevant documentation]. Figure 7 The details and related descriptions will not be repeated here.

[0079] In some embodiments, by processing normal and abnormal images under various scanning conditions, the abnormal data boundaries corresponding to each scanning condition can be determined. These abnormal data boundaries can then be compiled into an abnormal data boundary table for easy viewing.

[0080] Figure 7This is a schematic diagram illustrating yet another method for determining abnormal data boundaries according to some embodiments of this specification. In some embodiments, process 700 may be executed by a processing device. Figure 7 As shown, process 700 may include the following steps:

[0081] Step 710: Based on the abnormal image, determine the first data set in the first projection data corresponding to the abnormal image.

[0082] The first projection data may refer to the projection data corresponding to the abnormal image. In some embodiments, the first projection data can be obtained by backprojecting the abnormal image.

[0083] The first data set can be a range of projection data sets that may contain abnormal data in the first projection data. For example, if there are projection data sets numbered 1 to 1000 in the first projection data, the first data set can be the projection data set numbered 800 to 900.

[0084] In some embodiments, a machine learning model can be used to determine the regions in an abnormal image where artifacts exist, and the first projection data corresponding to the regions where artifacts exist can be determined as a first data set.

[0085] In some embodiments, the first data set may also be determined in other ways. For example, the first data set may be obtained by manually annotating the first projection data.

[0086] Step 720: Based on the normal image, determine the second data set in the second projection data corresponding to the normal image.

[0087] The second projection data can refer to the projection data corresponding to the normal image. Similar to the first projection data, the second projection data can be obtained by backprojecting the normal image.

[0088] The second data set can refer to the range of projection data sets used to determine the normal data range in the second projection data, where the normal data range can refer to the range corresponding to the scan data in the second data set. In some embodiments, the second data set can be all or part of the projection data sets in the second projection data. For example, when there are projection data sets numbered 1 to 1000 in the second projection data, the second data set can be the projection data sets numbered 1 to 1000. In some embodiments, the second data set can be the projection data set in the second projection data that corresponds to the first data set. For example, if the first data set is the projection data set numbered 800 to 900 in the first projection data, then the corresponding second data set can be the projection data set numbered 800 to 900 in the second projection data.

[0089] It should be understood that both normal and abnormal images are CT images obtained under target scanning conditions.

[0090] Step 730: Determine the normal data range based on the second dataset.

[0091] The normal data range can be determined based on the data values ​​of the scanned data in the second data set. In some embodiments, the minimum and maximum values ​​of the scanned data in the second data set can be determined and directly used as the endpoints of the normal data range. For example, if the minimum value of the scanned data in the second data set is m and the maximum value is n, then [m, n] can be used as the normal data range.

[0092] In some embodiments, the normal data range can also be determined based on other methods. For example, the minimum and maximum values ​​of the scanned data in the second data set can be adjusted based on preset values ​​to expand or shrink the normal data range, and the adjusted values ​​can be used as the endpoint values ​​of the normal data range. For example, if the minimum value of the scanned data in the second data set is m, the maximum value is n, and the preset value is x, then [mx, n+x] can be used as the normal data range. In some embodiments, multiple normal data ranges can be determined by modifying the aforementioned preset values.

[0093] Step 740: Based on the normal data range and the first data set, identify the abnormal data in the first data set.

[0094] The values ​​of the scanned data in the first data set can be compared with the range of normal data to identify abnormal data in the first data set. When the values ​​of the scanned data in the first data set are within the normal data range, the scanned data can be identified as normal data; when the values ​​of the scanned data in the first data set are not within the normal data range, the scanned data can be identified as abnormal data.

[0095] Step 750: Correct the abnormal data to obtain the corrected first projection data.

[0096] For more information on correcting outlier data, please see [link to relevant documentation]. Figure 4 The details and related descriptions will not be repeated here.

[0097] Step 760: Reconstruct the image based on the corrected first projection data to obtain the reconstructed image.

[0098] In some embodiments, a reconstructed image can be obtained by using an iterative algorithm based on the corrected first projection data.

[0099] Step 770: Determine whether the reconstructed image is a normal image.

[0100] In some embodiments, the reconstructed image can be input into a discriminative model, and the model's output can be used to determine whether the reconstructed image is a normal image. In some embodiments, the output of the discriminative model may also include specific problems present in the reconstructed image, such as regions containing artifacts. Correspondingly, the training labels may also include specific problems of anomalous images, which can be determined through manual annotation.

[0101] In some embodiments, it is also possible to determine whether the reconstructed image is a normal image through other means. For example, it can be determined directly through user annotations.

[0102] If the reconstructed image is not a normal image, more abnormal images can be added in step 710 for processing, iterative updates, and adjustment of boundary values ​​until the reconstructed image is determined to be a normal image.

[0103] Step 780: In response to the reconstructed image being a normal image, the boundary of the normal data range corresponding to the reconstructed image is taken as the abnormal data boundary corresponding to the target scanning condition.

[0104] It should be understood that when the scanned data value is within the normal data range, the scanned data is determined to be normal data; when the scanned data value is outside the normal data range, the scanned data is determined to be abnormal data. Therefore, the endpoints of the normal data range can be used as the boundaries of abnormal data. For example, when the normal data range is [m, n], m and n can be used as the boundaries of abnormal data.

[0105] In some embodiments, multiple sets of normal data ranges can be determined. Based on steps 730-750, reconstructed images corresponding to each of the multiple sets of normal data ranges can be obtained. The reconstructed images corresponding to each of the multiple sets of normal data ranges are input into a discrimination model, and the normal images in the reconstructed images can be determined based on the output of the discrimination model. When only one normal image exists in the reconstructed images, the boundary of the normal data range corresponding to that normal image can be used as the abnormal data boundary under the target scanning conditions. When multiple normal images exist in the reconstructed images, the abnormal data boundary can be determined in various ways. For example, the boundary of the normal data range corresponding to a random normal image can be used as the abnormal data boundary under the target scanning conditions. Another example is using the boundary of the largest normal data range in the normal images as the abnormal data boundary under the target scanning conditions. When no normal image exists in the reconstructed images, the normal data range can be adjusted (e.g., expanded), and the reconstructed images can be re-acquired for judgment until a normal image exists in the reconstructed images.

[0106] Some embodiments of this specification determine the boundaries of abnormal data by adjusting the range of normal data, which in some cases helps to solve the problem of not being able to obtain enough normal and abnormal images under target scanning conditions when determining the boundaries of abnormal data.

[0107] Figure 8 This is a schematic diagram illustrating yet another method for determining abnormal data boundaries according to some embodiments of this specification. In some embodiments, process 800 may be executed by a processing device. Figure 8 As shown, process 800 may include the following steps:

[0108] Step 810: Obtain a normal image under the target scanning conditions. For more information on target scanning conditions, see [link to relevant documentation]. Figure 3 For related descriptions and more information on normal images, please refer to [link / reference]. Figure 6 The details and related descriptions will not be repeated here.

[0109] Step 820: Based on the normal image, determine the second data set of the second projection data corresponding to the normal image. For details on the second projection data and the second data set, please refer to [link to relevant documentation]. Figure 7 The details and related descriptions will not be repeated here.

[0110] Step 830: Based on the second dataset, determine the normal data range. For more information on normal data ranges, see [link to relevant documentation]. Figure 7 The details and related descriptions will not be repeated here.

[0111] Step 840: Based on the normal data range, determine the abnormal data boundary corresponding to the target scanning conditions.

[0112] In some embodiments, the boundary of abnormal data under the target scanning conditions can be determined based on the normal data range corresponding to the normal images under the target scanning conditions. For example, the boundary value of the normal data range corresponding to the normal images under the target scanning conditions can be used as the boundary of abnormal data under the target scanning conditions. As another example, based on multiple normal images under the target scanning conditions, the normal data ranges corresponding to the multiple normal data ranges can be determined, and the boundary value of the intersection of these multiple normal data ranges can be determined as the boundary of abnormal data under the target scanning conditions.

[0113] It should be noted that the above descriptions of the various processes are for illustrative purposes only and do not limit the scope of this specification. Those skilled in the art can make various modifications and changes to the processes under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0114] Some embodiments of this specification also disclose a projection data anomaly processing device, including a processor, characterized in that the processor is used to execute the above-described projection data anomaly processing method.

[0115] Some embodiments of this specification also disclose a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the above-described projection data anomaly handling method.

[0116] The beneficial effects that the embodiments of this specification may bring include, but are not limited to: 1) By determining the scanning conditions of the projection data and querying the abnormal data boundary table, abnormal data can be quickly identified and repaired; 2) Different correction methods can be determined for different abnormal data situations in the projection data set, simplifying the correction steps as much as possible, improving correction efficiency, and saving computing power; 3) By using a discriminant model to discriminate candidate images, the type of candidate image can be quickly and accurately determined, saving manpower costs and improving discrimination efficiency; 4) By modifying the scanning conditions, different abnormal data boundaries can be determined based on different scanning conditions, and an abnormal data boundary table can be created for easy querying later; 5) By determining the data characteristics of abnormal data, abnormal parts of the scanning equipment can be identified, facilitating maintenance by repair personnel.

[0117] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0118] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0119] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0120] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0121] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0122] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0123] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for handling outliers in projection data, the method comprising: include: Based on the target scanning conditions corresponding to the projection data, the abnormal data boundary corresponding to the target scanning conditions is determined. The target scanning conditions include one or more of the following: model information of the scanning device, scanning protocol, and scanning part. The abnormal data boundary refers to the boundary between normal data and abnormal data in the projection data. Different target scanning conditions correspond to different abnormal data boundaries. Based on the abnormal data boundaries, the target abnormal data in the projected data is determined; The step of determining the abnormal data boundary corresponding to the target scanning conditions based on the projected data includes: Acquire normal and abnormal images under the target scanning conditions; Based on the abnormal image, determine the first data set in the first projection data corresponding to the abnormal image; Based on the normal image, determine the second data set in the second projection data corresponding to the normal image; Based on the second data set, determine the normal data range; Based on the normal data range and the first data set, abnormal data in the first data set are determined; The abnormal data is corrected to obtain the corrected first projection data; Based on the corrected first projection data, image reconstruction is performed to obtain a reconstructed image; Determine whether the reconstructed image is a normal image; In response to the reconstructed image being the normal image, the boundary of the normal data range corresponding to the reconstructed image is taken as the abnormal data boundary corresponding to the target scanning condition.

2. The method of claim 1, wherein, Also includes: The abnormal target data in the projection data is corrected to obtain the corrected data.

3. The method of claim 1, wherein, Also includes: Based on the data characteristics of the target abnormal data, the abnormal components of the scanning device are identified.

4. A projection data outlier handling system characterized by, include: The first determining module is used to determine the abnormal data boundary corresponding to the target scanning conditions based on the target scanning conditions corresponding to the projection data. The target scanning conditions include one or more of the following: model information of the scanning device, scanning protocol, and scanning part. The abnormal data boundary refers to the boundary of the scanning data that divides the normal data and abnormal data in the projection data. Different target scanning conditions correspond to different abnormal data boundaries. The second determining module is used to determine the target abnormal data in the projected data based on the abnormal data boundary; Wherein, the first determining module is further configured to: Acquire normal and abnormal images under the target scanning conditions; Based on the abnormal image, determine the first data set in the first projection data corresponding to the abnormal image; Based on the normal image, determine the second data set in the second projection data corresponding to the normal image; Based on the second data set, determine the normal data range; Based on the normal data range and the first data set, abnormal data in the first data set are determined; The abnormal data is corrected to obtain the corrected first projection data; Based on the corrected first projection data, image reconstruction is performed to obtain a reconstructed image; Determine whether the reconstructed image is a normal image; In response to the reconstructed image being the normal image, a boundary of the normal data range corresponding to the reconstructed image is taken as an abnormal data boundary corresponding to the target scan condition.

5. A projection data outlier handling apparatus comprising a processor, wherein, The processor is configured to perform the projection data abnormality processing method according to any one of claims 1-3. 6.A computer readable storage medium, the storage medium storing computer instructions, when a computer reads the computer instructions in the storage medium, the computer performs the projection data abnormality processing method according to any one of claims 1-3.

Images