Method and device for correcting data inconsistency and medical imaging equipment

Abstract

The invention relates to the technical field of medical imaging, and discloses a method and device for data inconsistency correction and medical imaging equipment, and the method comprises the steps: determining an overlapping region according to the scanning range of first scanning information and second scanning information; in the overlapping region, reconstructing the first scanning information to obtain a first image sequence, and reconstructing the second scanning information to obtain a second image sequence; determining a transformation field of the second image sequence according to the first image sequence; and adjusting the second image sequence or the first image sequence and the second image sequence according to the transformation field to obtain a corrected target image sequence. The second image sequence or the first image sequence and the second image sequence are adjusted by using the transformation field, so that the elimination of the inconsistency of the data between the first scanning information and the second scanning information is realized, and the image quality is improved.

Description

Technical Field

[0001] The present application relates to the field of medical imaging technology, for example, to a method and device for correcting data inconsistency, and medical imaging equipment. Background Art

[0002] As clinical needs continue to increase, medical imaging systems are becoming more and more complex. Images reconstructed from single scan information can no longer meet the needs of clinical diagnosis. Imaging methods are constantly changing, from two-dimensional to three-dimensional, single-modality to multi-modality, single-energy to multi-energy, single-sector to multi-sector, single-phase to multi-phase, and so on.

[0003] In the related art, during the imaging process, it is necessary to collect data containing more scanning information, integrate this information, and fuse and reconstruct high-quality images that are beneficial to clinical diagnosis.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] There is usually a certain time interval between the data collection of different information. During the scanning process, the patient may move subjectively or objectively, such as slight movement of the head, throat movement, heart movement, breathing movement, etc. These movements will cause inconsistency in the data between different scan information. If the inconsistent data is directly used for image reconstruction, the final imaging will cause tissue blur, ghosting, dislocation and other phenomena, which may affect the diagnosis in serious cases.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] The embodiments of the present disclosure provide a method and apparatus for correcting data inconsistency, and a medical imaging device to eliminate data inconsistency between different scanning information and improve image quality.

[0009] In some embodiments, a method for correcting data inconsistency includes: determining an overlapping area based on a scanning range of first scanning information and second scanning information; reconstructing the first scanning information within the overlapping area to obtain a first image sequence, and reconstructing the second scanning information to obtain a second image sequence; determining a transformation field of the second image sequence based on the first image sequence; and adjusting the second image sequence, or the first image sequence and the second image sequence, based on the transformation field to obtain a corrected target image sequence.

[0010] Optionally, the overlapping area is determined based on the scanning range of the first scanning information and the second scanning information, including: determining a first position range corresponding to the first scanning information and capable of reconstructing a complete image based on the scanning range of the first scanning information; determining a second position range corresponding to the second scanning information and capable of reconstructing a complete image based on the scanning range of the second scanning information; and determining an intersection of the first position range and the second position range as the overlapping area.

[0011] Optionally, determining the transformation field of the second image sequence according to the first image sequence includes: setting an initial transformation field; the transformation of the initial transformation field includes translation, rotation, uniform scaling or non-uniform scaling; and adjusting the initial transformation field according to the first image sequence and the second image sequence.

[0012] Optionally, the initial transformation field is adjusted according to the first image sequence and the second image sequence, including one or more iterative operations; the iterative operation includes: transforming the second image sequence using the current transformation field to obtain a transformed image sequence; evaluating the similarity between the first image sequence and the transformed image sequence using a similarity metric to obtain a similarity evaluation result; if the similarity evaluation result does not reach a similarity metric threshold, updating the current transformation field; wherein the convergence condition of the iterative operation is that the similarity evaluation result reaches the similarity metric threshold.

[0013] Optionally, the similarity metric includes a similarity metric based on Euclidean distance; using the similarity metric to evaluate the similarity between the first image sequence and the transformed image sequence includes: calculating the Euclidean distance between the first image sequence and the transformed image sequence; when the Euclidean distance is greater than or equal to a set threshold, updating the current transformation field; when the Euclidean distance is less than the set threshold, ending the iterative operation.

[0014] Optionally, according to the first image sequence, determining the transformation field of the second image sequence includes: inputting the first image sequence and the second image sequence into a pre-trained model to obtain the transformation field; wherein the pre-trained model is obtained in the following manner: obtaining a training image pair, the training image pair including a reference image and a moving image; using an initial model to learn the transformation relationship from the moving image to the reference image, the output of the initial model being the training transformation field; using the training transformation field to transform the moving image; designing a loss function to minimize the similarity measure between the reference image and the transformed moving image, to obtain a trained pre-trained model.

[0015] Optionally, the second image sequence, or the first image sequence and the second image sequence, is adjusted according to the transformation field, including: adjusting the positions of pixels in the second image sequence using the transformation field; or weight decomposing the transformation field to obtain a first transformation field of the first image sequence and a second transformation layer of the second image sequence; adjusting the positions of pixels in the first image sequence based on the first transformation field, and adjusting the positions of pixels in the second image sequence based on the second transformation field; wherein the scope of the transformation field includes the complete image sequence, or any partial angular image corresponding to the complete image sequence.

[0016] Optionally, the first scanning information and the second scanning information are information obtained by scanning at different times, and a target area moves during the process of obtaining the first scanning information and the second scanning information, and the target area is an area corresponding to the first scanning information and the second scanning information.

[0017] Optionally, the first scanning information corresponds to the first sector information of the heart scan, and the second scanning information corresponds to the second sector information of the heart scan; or, the first scanning information corresponds to the information obtained by the high energy scanning in the dual energy scanning, and the second scanning information corresponds to the information obtained by the low energy scanning in the dual energy scanning.

[0018] In some embodiments, an apparatus for data inconsistency correction includes a processor and a memory storing program instructions, wherein the processor is configured to execute the above-mentioned method for data inconsistency correction when executing the program instructions.

[0019] In some embodiments, the medical imaging device includes: a medical imaging device body; and the apparatus for correcting data inconsistency as described above, which is installed in the medical imaging device body.

[0020] The method and device for data inconsistency correction and the medical imaging device provided by the embodiments of the present disclosure can achieve the following technical effects:

[0021] In the case where it is necessary to eliminate the inconsistency of data between different scanning information, the first scanning information and the second scanning information are determined according to the actual application requirements, and the first scanning information is used as the reference data and the second scanning information is used as the data to be transformed. The overlapping area of ​​the first scanning information and the second scanning information in the scanning range is determined. The overlapping area can be used to enhance the correlation between different scanning information, and the overlapping area is used as a medium to eliminate the inconsistency. In the overlapping area, the first scanning information and the second scanning information are reconstructed respectively to obtain the first image sequence and the second image sequence. According to the transformation relationship between the first image sequence and the second image sequence, the transformation field of the second image sequence can be determined. Finally, the second image sequence, or the first image sequence and the second image sequence, is adjusted using the transformation field, so as to eliminate the inconsistency of data between the first scanning information and the second scanning information, and obtain the corrected target image sequence. Imaging according to the target image sequence can improve the image quality and obtain a clear, continuous, and highly confident image.

[0022] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0024] Figure 1 is a schematic diagram of a method for correcting data inconsistency provided by an embodiment of the present disclosure;

[0025] Figure 2 is a schematic diagram of an overlapping area provided by an embodiment of the present disclosure;

[0026] Figure 3 is a schematic diagram of another overlapping area provided by an embodiment of the present disclosure;

[0027] Figure 4 is a schematic diagram of adjusting a second image sequence using a transformation matrix provided by an embodiment of the present disclosure;

[0028] Figure 5 is a schematic diagram of another method for correcting data inconsistency provided by an embodiment of the present disclosure;

[0029] Figure 6 It is a schematic diagram of a device for correcting data inconsistency provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0031] The terms "first", "second", etc. in the technical solutions described in this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so as to describe the embodiments of the disclosed embodiments described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0032] Unless otherwise stated, the term "plurality" means two or more.

[0033] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0034] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0035] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0036] Combination Figure 1 As shown, the embodiment of the present disclosure provides a method for correcting data inconsistency, the execution subject of the method may be a processor, and the method includes:

[0037] S101: The processor determines an overlapping area according to a scanning range of first scanning information and a scanning range of second scanning information.

[0038] S102: The processor reconstructs the first scanning information in the overlapping area to obtain a first image sequence, and reconstructs the second scanning information to obtain a second image sequence.

[0039] S103: The processor determines a transformation field of the second image sequence according to the first image sequence.

[0040] S104: The processor adjusts the second image sequence, or the first image sequence and the second image sequence according to the transformation field to obtain a corrected target image sequence.

[0041] In the case where it is necessary to eliminate the inconsistency of data between different scanning information, the first scanning information and the second scanning information are determined according to the actual application requirements, and the first scanning information is used as the reference data and the second scanning information is used as the data to be transformed. The overlapping area of ​​the first scanning information and the second scanning information in the scanning range is determined. The overlapping area can be used to enhance the correlation between different scanning information, and the overlapping area is used as a medium to eliminate the inconsistency. In the overlapping area, the first scanning information and the second scanning information are reconstructed respectively to obtain the first image sequence and the second image sequence. According to the transformation relationship between the first image sequence and the second image sequence, the transformation field of the second image sequence can be determined. Finally, the second image sequence, or the first image sequence and the second image sequence, are adjusted using the transformation field, so as to eliminate the inconsistency of data between the first scanning information and the second scanning information, and obtain the corrected target image sequence. Imaging according to the target image sequence can improve the image quality and obtain a clear, continuous, and highly confident image.

[0042] Optionally, the second scanning information includes one or more scanning information.

[0043] In this embodiment, when there is only one second scanning information, the method for correcting data inconsistency provided by the embodiment of the present disclosure only needs to be executed once to eliminate the inconsistency of data between the first scanning information and the second scanning information. In the case of multiple second scanning information, it is necessary to execute the method for correcting data inconsistency provided by the embodiment of the present disclosure once for each second scanning information, and eliminate the inconsistency of data between the first scanning information and each second scanning information in turn. In addition, multiple second scanning information can also be used at the same time, first determining the overlapping area between the first scanning information and the multiple second scanning information, and reconstructing the first scanning information and each second scanning information in the overlapping area to obtain a first image sequence and multiple second image sequences, and then determining the transformation field from each second image sequence to the first image sequence, and using each transformation field to adjust the corresponding second image sequence.

[0044] Optionally, the first scanning information and the second scanning information are information obtained by scanning at different times, and a target area moves during the process of obtaining the first scanning information and the second scanning information, and the target area is an area corresponding to the first scanning information and the second scanning information.

[0045] Specifically, for dual-energy scanning, after high-energy scanning, low-energy scanning is performed. The information obtained by high-energy scanning can be the first scanning information, and the information obtained by low-energy scanning can be the second scanning information. The position of the target area during low-energy scanning may change compared to the high-energy scanning process, resulting in inconsistent data. The target area refers to the area corresponding to the first scanning information and the second scanning information. For cardiac scanning, in order to obtain a complete cardiac image with high temporal resolution, images of different sectors need to be fused, each sector corresponds to partial angle data, and the information collected by different sectors corresponds to the first scanning information and the second scanning information. Due to the irregularity of the movement state of the heart, the heart states collected by different sectors are inconsistent, which will cause the heart positions corresponding to the data of different sectors to be inconsistent. Among them, to reconstruct a complete cardiac image, it is necessary to collect data of at least 180° plus the sector angle. The partial angle data refers to the data corresponding to the partial angle within 180° plus the sector angle. The splicing of partial angle data of multiple sectors can constitute the data of 180° plus the sector angle.

[0046] Optionally, the overlapping area is determined based on the scanning range of the first scanning information and the second scanning information, including: determining a first position range corresponding to the first scanning information and capable of reconstructing a complete image based on the scanning range of the first scanning information; determining a second position range corresponding to the second scanning information and capable of reconstructing a complete image based on the scanning range of the second scanning information; and determining an intersection of the first position range and the second position range as the overlapping area.

[0047] In this embodiment, for the first scanning information and the second scanning information, the scanning range can be determined by determining the starting point and the ending point of the scanning, as well as the depth and the angle of the scanning. Then, the first position range and the second position range that can reconstruct the complete image are determined by combining the scanning layer thickness, the scanning spacing and the scanning angle. The position ranges of the first scanning information and the second scanning information are compared to determine the intersection. This intersection is the overlapping area, that is, the area covered by both the first scanning information and the second scanning information. For different scanning modes, the length of the overlapping area may be different, and the overlapping area may be as follows: Figure 2 The entire reconstruction sequence shown could also be Figure 3 In the partial reconstruction sequence shown, the area between the two dotted lines is the overlapping area. In addition, for the plurality of second scanning information, the position ranges of the first scanning information and the plurality of second scanning information can be compared together to determine the overlapping area covered by all scanning information.

[0048] Optionally, determining the transformation field of the second image sequence according to the first image sequence includes: setting an initial transformation field; the transformation of the initial transformation field includes translation, rotation, uniform scaling or non-uniform scaling; and adjusting the initial transformation field according to the first image sequence and the second image sequence.

[0049] Optionally, the transformation field includes a transformation matrix, a transformation function, a parametric equation, etc.

[0050] After back-projection reconstruction of the first scanning information and the second scanning information in the overlapping area, a first image sequence and a second image sequence with the same reconstruction position can be obtained. The first image sequence and the second image sequence are both three-dimensional structures, the cross-section of the image is the xy plane, and the direction along the image sequence is the z direction. For a certain coordinate position, the first image sequence is represented as R(x, y, z) and the second image sequence is represented as M(x, y, z). An initial transformation matrix is ​​set, and each coordinate position in the initial transformation matrix corresponds to an offset vector (Δx, Δy, Δz) = f(x, y, z). The offset vector can be used to deform the second image sequence.

[0051] Optionally, the initial transformation field is adjusted according to the first image sequence and the second image sequence, including one or more iterative operations; the iterative operation includes: transforming the second image sequence using the current transformation field to obtain a transformed image sequence; evaluating the similarity between the first image sequence and the transformed image sequence using a similarity metric to obtain a similarity evaluation result; if the similarity evaluation result does not reach a similarity metric threshold, updating the current transformation field; wherein the convergence condition of the iterative operation is that the similarity evaluation result reaches the similarity metric threshold.

[0052] In this embodiment, after the initial transformation matrix is ​​set, the initial transformation matrix needs to be adjusted iteratively one or more times. In one iteration, the second image sequence is transformed using the current transformation matrix. Figure 4As shown, the pixel point (x, y, z) in the second image sequence M(x, y, z) is adjusted using the offset vector (Δx, Δy, Δz) in the current transformation matrix to obtain the adjusted pixel point (x+Δx, y+Δy, z+Δz), thereby determining the transformed image sequence M'(x, y, z). The similarity between the first image sequence and the transformed image sequence is evaluated using a similarity metric, for example, using the mean square error to measure the difference in grayscale values ​​of corresponding pixels in the first image sequence and the transformed image sequence, using the structural similarity index to compare the differences in brightness, contrast, and structural information between the first image sequence and the transformed image sequence, and using the mutual information statistical method to measure the similarity of the pixel intensity distribution of the first image sequence and the transformed image sequence. After obtaining the similarity evaluation result, it is compared with the similarity measurement threshold. If the similarity evaluation result does not reach the similarity measurement threshold, it means that there are still large differences between the first image sequence and the transformed image sequence, and the offset vector of the current transformation matrix needs to be updated. The offset vector of each coordinate position in the updated current transformation matrix is ​​(Δx', Δy', Δz'), and the updated current transformation matrix is ​​evaluated for similarity measurement again. Until the similarity evaluation result reaches the similarity measurement threshold, it means that the first image sequence and the transformed image sequence are highly similar.

[0053] Optionally, the similarity metric includes a similarity metric based on Euclidean distance; using the similarity metric to evaluate the similarity between the first image sequence and the transformed image sequence includes: calculating the Euclidean distance between the first image sequence and the transformed image sequence; when the Euclidean distance is greater than or equal to a set threshold, updating the current transformation field; when the Euclidean distance is less than the set threshold, ending the iterative operation.

[0054] Combination Figure 5 As shown, the embodiment of the present disclosure provides another method for correcting data inconsistency, including:

[0055] S201: The processor determines an overlapping area according to a scanning range of first scanning information and a scanning range of second scanning information.

[0056] S202: The processor reconstructs the first scanning information in the overlapping area to obtain a first image sequence, and reconstructs the second scanning information to obtain a second image sequence.

[0057] S203: The processor sets an initial transformation field.

[0058] S204: The processor transforms the second image sequence using the current transformation field to obtain a transformed image sequence.

[0059] S205: The processor calculates the Euclidean distance between the first image sequence and the transformed image sequence.

[0060] S206, the processor determines whether the Euclidean distance is greater than or equal to a set threshold, if so, executes S207, if not, executes S208.

[0061] S207: The processor updates the current transformation field and executes S204.

[0062] S208: The processor adjusts the second image sequence, or the first image sequence and the second image sequence according to the transformation field to obtain a corrected target image sequence.

[0063] In this embodiment, the Euclidean distance L=║M'(x, y, z)-R(x, y, z)║ between the first image sequence and the transformed image sequence is calculated by using the similarity measurement based on the Euclidean distance. 2 , if the Euclidean distance L is greater than or equal to the set threshold ε, the offset vector in the current transformation matrix is ​​updated according to the calculated Euclidean distance, and the updated transformation matrix is ​​used again to transform the second image sequence, and the Euclidean distance is calculated again. The iterative operation ends when the calculated Euclidean distance is less than the set threshold.

[0064] Optionally, according to the first image sequence, determining the transformation field of the second image sequence includes: inputting the first image sequence and the second image sequence into a pre-trained model to obtain the transformation field; wherein the pre-trained model is obtained in the following manner: obtaining a training image pair, the training image pair including a reference image and a moving image; using an initial model to learn the transformation relationship from the moving image to the reference image, the output of the initial model being the training transformation field; using the training transformation field to transform the moving image; designing a loss function to minimize the similarity measure between the reference image and the transformed moving image, to obtain a trained pre-trained model.

[0065] In this embodiment, by introducing a pre-trained model, the accuracy and efficiency of determining the transformation matrix can be improved. During the training process of the model, a large number of training image pairs are collected, including reference images and moving images. The training image correspondence covers a variety of different scanning conditions, patient postures and possible movements, thereby ensuring the diversity and representativeness of the data. The initial model includes a convolutional neural network, which uses the convolutional neural network to learn the transformation relationship from the moving image to the reference image, and makes the output of the convolutional neural network a training transformation matrix from the moving image to the reference image. After the moving image is transformed using the training transformation matrix, a loss function is designed to minimize the similarity measure between the reference image and the transformed moving image. In the loss function, a regularization term can also be added to prevent overfitting and ensure the smoothness and interpretability of the transformation matrix.

[0066] Optionally, the second image sequence is adjusted according to the transformation field, including: adjusting the positions of pixel points in the second image sequence using the transformation field; wherein the scope of the transformation field includes the complete second image sequence, or any partial angular image corresponding to the complete second image sequence.

[0067] The inconsistency between the second image sequence and the first image sequence can be eliminated by adjusting the position of the pixels in the second image sequence using a transformation matrix. When the scope of the transformation matrix is ​​the entire image, it means that the transformation will be applied to every pixel in the image. This transformation is usually used for global geometric correction, such as rotation, translation, scaling or affine transformation of the image. In medical imaging, if the entire image needs to be corrected to eliminate systematic deviations or inconsistencies, such as deviations caused by improper equipment calibration or changes in patient position, then the transformation of the complete image will be used. When the scope of the transformation matrix is ​​limited to a certain part of the image, such as any partial angular image corresponding to the complete second image sequence, the partial angular image is an image reconstructed when the projection angle is less than 180°, this transformation is usually used for local geometric correction, for example, only rotating or translating a certain area in the image without affecting other areas. In medical imaging, this can be used to correct local artifacts or inconsistencies, such as artifacts caused by local patient motion, or when performing multimodal image fusion, only correcting specific areas to ensure that corresponding areas of different imaging modes are aligned. In addition, global and local transformations can be combined as needed to achieve the best correction effect. For example, global correction can be performed on the entire image first, and then refined correction can be performed on local areas.

[0068] Optionally, the first image sequence and the second image sequence are adjusted according to the transformation field, including: weight decomposing the transformation field to obtain the first transformation field of the first image sequence and the second transformation layer of the second image sequence; adjusting the position of the pixel points in the first image sequence based on the first transformation field, and adjusting the position of the pixel points in the second image sequence based on the second transformation field; wherein the scope of the transformation field includes the complete image sequence, or any partial angular image corresponding to the complete image sequence. The complete image sequence refers to the image sequence on which the transformation field acts.

[0069] Specifically, the transformation field is weighted decomposed, the first transformation field may be a positive deformation field, and the second deformation field may be a negative deformation field, where positive and negative represent that the adjustment directions of the pixels in the first image sequence and the pixels in the second image sequence are opposite. The sum of the absolute value of the weight corresponding to the first image sequence and the absolute value of the weight corresponding to the second image sequence may be 1. The first image sequence and the second image sequence adjust the pixel positions synchronously, which can reduce the adjustment amplitude of the pixels and ensure the overall consistency of the first scan information and the overall consistency of the second scan information. The overall consistency refers to the consistency of the overlapping area and the overlapping area.

[0070] Optionally, after obtaining the target image sequence, the target image sequence may be combined. Specifically, combining the adjusted second image sequence with the first image sequence includes: directly adding, weighted summing or subtracting the adjusted second image sequence with the first image sequence.

[0071] The adjusted second image sequence is combined with the first image sequence to obtain the corrected target image sequence. The combination methods include direct addition, weighted summation or difference. Direct addition directly adds the corresponding pixel values ​​of the adjusted second image sequence and the first image sequence, which is simple and fast. Weighted summation assigns different weights to the adjusted second image sequence and the first image sequence, and then performs weighted summation of the corresponding pixel values. Difference subtracts the adjusted second image sequence from the first image sequence, which can highlight the difference between the two image sequences. In addition, the adjusted second image sequence and the first image sequence can be decomposed using the Laplacian pyramid, and then fused at different scales, and finally reconstructed The fused image is used to retain more detail information. Alternatively, the fusion is performed based on the statistical characteristics of the adjusted second image sequence and the first image sequence, such as using the mean, median or mode, among which median fusion has a good effect on suppressing noise and enhancing edges.

[0072] Optionally, the first scanning information corresponds to the first sector information of the heart scan, and the second scanning information corresponds to the second sector information of the heart scan; or, the first scanning information corresponds to the information obtained by the high energy scanning in the dual energy scanning, and the second scanning information corresponds to the information obtained by the low energy scanning in the dual energy scanning.

[0073] The method for data inconsistency correction provided by the embodiment of the present disclosure is used to eliminate the inconsistency in the data acquisition process by using the overlapping data between different scanning information, so as to obtain a clear, continuous, and high-confidence image. For different imaging requirements, the specific implementation process will be different. For example, for multi-sector imaging, it is necessary to eliminate the inconsistency of data between different heartbeat cycles, and combine the data from different sectors to obtain an image with good time resolution. For dual-energy imaging, it is necessary to eliminate the inconsistency between high-energy and low-energy data, and use material decomposition and virtual plain scanning to obtain an image that can improve the ability to detect lesions. For cardiac multi-position imaging, it is necessary to eliminate the inconsistency of two adjacent scanning data at the overlapping position, so as to obtain a continuous image sequence. For motion artifact correction related imaging, it is necessary to eliminate the inconsistency between different phases, so as to calculate the motion curve between the two phases, and then perform motion artifact correction. Therefore, the first scanning information and the second scanning information in the embodiment of the present disclosure can respectively represent scanning information of different sectors, different energies, different positions, and different phases, and the transformation relationship between the two in the overlapping area in the scanning range is used to eliminate the inconsistency, so that the data under different scanning information can be better combined together, ensuring good image quality, and more conducive to clinical diagnosis.

[0074] Combination Figure 6 As shown, the embodiment of the present disclosure provides a device 300 for data inconsistency correction, including a processor 400 and a memory 401. Optionally, the device may also include a communication interface 402 and a bus 403. The processor 400, the communication interface 402, and the memory 401 may communicate with each other through the bus 403. The communication interface 402 may be used for information transmission. The processor 400 may call the logic instructions in the memory 401 to execute the method for data inconsistency correction of the above embodiment.

[0075] In addition, the logic instructions in the memory 401 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0076] The memory 401 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 400 executes the function application and data processing by running the program instructions / modules stored in the memory 401, that is, the method for correcting data inconsistency in the above embodiment is implemented.

[0077] The memory 401 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 401 may include a high-speed random access memory and may also include a non-volatile memory.

[0078] The embodiments of the present disclosure provide a medical imaging device, including: a medical imaging device body, and the above-mentioned device for correcting data inconsistencies. The device for correcting data inconsistencies is installed in the medical imaging device body. The installation relationship described here is not limited to placement inside the medical imaging device, but also includes installation connections with other components of the medical imaging device, including but not limited to physical connections, electrical connections, or signal transmission connections. It can be understood by those skilled in the art that the device for correcting data inconsistencies can be adapted to a feasible medical imaging device body, thereby realizing other feasible embodiments.

[0079] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned method for correcting data inconsistency.

[0080] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0081] The above description and accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent possible changes only. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the technical solutions recorded in this application. As used in the technical solutions recorded in this application, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0082] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0083] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0084] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for data inconsistency correction, characterized in that: include: Determine an overlapping area according to a scanning range of the first scanning information and the second scanning information; In the overlapping area, the first scanning information is reconstructed to obtain a first image sequence, and the second scanning information is reconstructed to obtain a second image sequence; Determining a transformation field of a second image sequence based on the first image sequence; According to the transformation field, the second image sequence, or the first image sequence and the second image sequence are adjusted to obtain a corrected target image sequence.

2. The method according to claim 1, characterized in that Determining an overlapping area according to a scanning range of the first scanning information and the second scanning information includes: Determine, according to the scanning range of the first scanning information, a first position range corresponding to the first scanning information and capable of reconstructing a complete image; Determining, according to the scanning range of the second scanning information, a second position range corresponding to the second scanning information and capable of reconstructing a complete image; An intersection of the first position range and the second position range is determined as the overlapping area.

3. The method according to claim 1, characterized in that Determining a transformation field of a second image sequence according to a first image sequence includes: Set the initial transformation field; the transformation of the initial transformation field includes translation, rotation, uniform scaling or non-uniform scaling; The initial transformation field is adjusted according to the first image sequence and the second image sequence.

4. The method according to claim 3, characterized in that According to the first image sequence and the second image sequence, the initial transformation field is adjusted, including one or more iterative operations; the iterative operations include: transforming the second image sequence using the current transformation field to obtain a transformed image sequence; Using a similarity metric to evaluate the similarity between the first image sequence and the transformed image sequence, and obtaining a similarity evaluation result; When the similarity evaluation result does not reach the similarity measurement threshold, the current transformation field is updated; The convergence condition of the iterative operation is that the similarity evaluation result reaches the similarity measurement threshold.

5. The method according to claim 4, characterized in that The similarity measure includes a similarity measure based on Euclidean distance; and the similarity between the first image sequence and the transformed image sequence is evaluated by using the similarity measure, including: calculating the Euclidean distance between the first image sequence and the transformed image sequence; When the Euclidean distance is greater than or equal to the set threshold, the current transformation field is updated; When the Euclidean distance is less than the set threshold, the iteration operation ends.

6. The method according to claim 1, characterized in that Determining a transformation field of a second image sequence according to a first image sequence includes: inputting the first image sequence and the second image sequence into a pre-trained model to obtain the transformation field; wherein the pre-trained model is obtained in the following manner: Acquire a training image pair, the training image pair comprising a reference image and a moving image; The transformation relationship from the moving image to the reference image is learned using the initial model, and the output of the initial model is the training transformation field; Transform the moving image using the training transformation field; A loss function is designed to minimize the similarity measure between the reference image and the transformed moving image, resulting in a trained pre-trained model.

7. The method according to any one of claims 1 to 6, characterized in that: According to the transformation field, the second image sequence, or the first image sequence and the second image sequence are adjusted, comprising: Using the transformation field to adjust the positions of the pixels in the second image sequence; or, Decomposing the transformation field by weights to obtain a first transformation field of the first image sequence and a second transformation layer of the second image sequence; Adjusting the positions of pixels in the first image sequence based on the first transformation field, and adjusting the positions of pixels in the second image sequence based on the second transformation field; The scope of the transformation field includes the complete image sequence, or any partial angular image corresponding to the complete image sequence.

8. The method according to any one of claims 1 to 6, characterized in that: The first scanning information and the second scanning information are information obtained by scanning at different times. During the process of obtaining the first scanning information and the second scanning information, there is movement in the target area, and the target area is the area corresponding to the first scanning information and the second scanning information.

9. A device for data inconsistency correction, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for data inconsistency correction according to any one of claims 1 to 8 when running the program instructions.

10. A medical imaging device, characterized in that: include: Medical imaging equipment body; The device for data inconsistency correction as claimed in claim 9 is installed in the body of the medical imaging device.

Images