Spectral CT imaging methods, equipment, media and products

Abstract

The present invention discloses a spectral CT imaging method, equipment, medium and product, belonging to the field of medical image processing technology. The method includes: obtaining a first image corresponding to a first energy level and a second image corresponding to a second energy level, at least one of the first image and the second image includes a target motion organ; performing intensity transformation processing on the first image to obtain a first intermediate image, the CT intensity value of the first intermediate image matches the second energy level; determining the motion field of the second image compared to the first intermediate image, and performing deformation processing on the first image based on the motion field to obtain a first target image, the first target image and the second image corresponding to the same phase of the target motion organ; determining the first substance decomposition result based on the first target image and the second image. The technical solution provided by the present invention improves the accuracy of the first substance decomposition result by indirectly improving the registration effect between the first target image and the second image.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a spectral CT imaging method, equipment, medium and product. Background Art

[0002] Currently, mid-range and low-end spectral CT systems can only perform spectral imaging using slow tube voltage switching. However, the slow tube voltage switching of CT imaging systems based on slow tube voltage switching prevents them from acquiring spatially and temporally aligned dual-energy spectral data. Consequently, accurate first-substance decomposition results cannot be determined based on the acquired dual-energy spectral data. Furthermore, this problem is exacerbated when imaging moving organs such as the heart, abdomen, and lungs.

[0003] In summary, the decomposition result of the first substance determined by the energy spectrum imaging method based on slow tube voltage switching has the problem of low accuracy. Summary of the Invention

[0004] The present invention provides a spectral CT imaging method, device, medium and product to solve the problem of low accuracy of the first substance decomposition result determined by the spectral imaging method based on slow tube voltage switching.

[0005] According to one aspect of the present invention, a spectral CT imaging method is provided, comprising:

[0006] Acquiring a first image corresponding to a first energy level and a second image corresponding to a second energy level, wherein at least one of the first image and the second image includes a target motor organ;

[0007] performing intensity transformation processing on the first image to obtain a first intermediate image, wherein a CT intensity value of the first intermediate image matches the second energy level;

[0008] determining a motion field of the second image compared to the first intermediate image, and performing deformation processing on the first image based on the motion field to obtain a first target image, wherein the first target image and the second image correspond to the same time phase of the target motor organ;

[0009] A first substance decomposition result is determined according to the first target image and the second image.

[0010] According to another aspect of the present invention, there is provided a spectral CT imaging device, comprising:

[0011] an image acquisition module, configured to acquire a first image corresponding to a first energy level and a second image corresponding to a second energy level, wherein at least one of the first image and the second image includes a target motor organ;

[0012] an intensity conversion module, configured to perform intensity conversion processing on the first image to obtain a first intermediate image, wherein a CT intensity value of the first intermediate image matches the second energy level;

[0013] a deformation module, configured to determine a motion field of the second image compared to the first intermediate image, and perform deformation processing on the first image based on the motion field to obtain a first target image, wherein the first target image and the second image correspond to the same phase of the target motor organ;

[0014] A base substance image module is used to determine a decomposition result of a first substance according to the first target image and the second image.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can perform the spectral CT imaging method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the energy spectrum CT imaging method according to any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the computer program implements the spectral CT imaging method according to any embodiment of the present invention.

[0021] The energy spectrum imaging technology solution provided by an embodiment of the present invention performs intensity transformation processing on a first image to obtain a first intermediate image, and the first intermediate image and the second image have the same CT intensity value. Since the first intermediate image and the second image have the same CT intensity value, the influence of different CT intensity values ​​on the accuracy of the motion field in the second image compared with the first intermediate image is eliminated during the process of determining the motion field in the second image compared with the first intermediate image, resulting in a higher accuracy of the motion field. Using the motion field to deform the first image to obtain a first target image, the first target image and the second image can have the same structural features. Therefore, the two can be regarded as two images acquired simultaneously at different energy levels, indirectly completing the registration between the first target image and the second image. Therefore, an accurate first substance decomposition result can be obtained based on the first target image and the second image. This effectively avoids the problem of large differences in structural features of the images corresponding to the two energy levels due to slow voltage switching, and the resulting low accuracy of the first substance decomposition result, thereby contributing to the popularization and application of energy spectrum CT imaging equipment based on slow tube voltage switching.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of a spectral CT imaging method provided according to an embodiment of the present invention;

[0025] Figure 2A A first image provided by an embodiment of the present invention;

[0026] Figure 2B A second image provided by an embodiment of the present invention;

[0027] Figure 2C A first target image provided by an embodiment of the present invention;

[0028] Figure 2D A deformed image of the first image determined by using mean square error as an image similarity measurement function in the prior art;

[0029] Figure 2E A deformed image of the first image determined by using a normalized correlation coefficient as an image similarity measurement function in the prior art;

[0030] Figure 3 A schematic diagram of the decomposition results of the first substance provided in an embodiment of the present invention;

[0031] Figure 4 Another flow chart of the spectral CT imaging method provided in an embodiment of the present invention;

[0032] Figure 5 Another flow chart of the spectral CT imaging method provided in an embodiment of the present invention;

[0033] Figure 6 A schematic diagram of a first image intensity transformation provided by an embodiment of the present invention;

[0034] Figure 7 Another flow chart of the spectral CT imaging method provided in an embodiment of the present invention;

[0035] Figure 8 A schematic diagram of determining a sports field according to an embodiment of the present invention;

[0036] Figure 9A The first intermediate images and second images corresponding to the first 50 layers of first images provided in the embodiment of the present invention;

[0037] Figure 9B The first intermediate image and the second image corresponding to the last 50 layers of the first image provided in the embodiment of the present invention;

[0038] Figure 10A The first material decomposition results corresponding to the first 50 layers of the first image provided in the embodiment of the present invention;

[0039] Figure 10B The first material decomposition results corresponding to the last 50 layers of the first image provided in the embodiment of the present invention;

[0040] Figure 11 is a flow chart of a spectral CT imaging device provided according to an embodiment of the present invention;

[0041] Figure 12 It is a structural diagram of an electronic device for implementing the energy spectrum CT imaging method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0043] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0044] Figure 1 The present invention provides a flowchart of a spectrum imaging method. This embodiment is applicable to processing a first image and a second image acquired by a spectrum CT imaging device with slow tube voltage switching for a moving organ. The method can be performed by a spectrum CT imaging device. The spectrum CT imaging device can be implemented in the form of hardware and / or software. The spectrum CT imaging device can be configured in a processor of an electronic device. Figure 1 As shown, the method includes:

[0045] S110 , acquiring a first image corresponding to a first energy level and a second image corresponding to a second energy level, wherein at least one of the first image and the second image includes a target motor organ.

[0046] The target movement organ may be a heart, a lung, a stomach, etc. The first image and the second image may both include the target movement organ, or one of the two images may include the target movement organ.

[0047] The first energy level is different from the second energy level. The first energy level can be the lower energy level of the two energy levels or the higher energy level of the two energy levels. The first energy level and the second energy level are two energy levels included in the energy level combination used by the existing target energy spectrum CT imaging device, wherein the target energy spectrum CT imaging device is an energy spectrum CT imaging device based on slow tube voltage switching.

[0048] To facilitate the description of the technical solution, the first energy level is set to be lower than the second energy level. The first image is set to correspond to the first phase of the target motor organ, and the second image is set to correspond to the second phase of the target motor organ. In a movement cycle of the target motor organ, the second phase is later than the first phase.

[0049] The existing image reconstruction method is used to determine the first image corresponding to the first energy level and the second image corresponding to the second energy level.

[0050] It is understood that if the first energy level is lower than the second energy level, then the CT intensity value of the first image corresponding to the first energy level is lower than the CT intensity value of the second image corresponding to the second energy level. The CT intensity value can be understood as the CT value of the CT image.

[0051] S120 . Perform intensity transformation processing on the first image to obtain a first intermediate image, wherein the CT intensity value of the first intermediate image matches the second energy level.

[0052] This step targets the CT intensity values ​​of the second image and performs intensity transformation on the first image to produce a first intermediate image. This transformation ensures that the first intermediate image has CT intensity values ​​that match the second energy level. Specifically, the first intermediate image is a CT scan image that simulates the T1 phase and matches the second energy level. In this way, both the first intermediate image and the second image have CT intensity values ​​that match the second energy level, but include structural features from different phases.

[0053] In one embodiment, an existing CT intensity value transformation method is used to perform intensity transformation on the first image to obtain a first intermediate image.

[0054] S130 , determining a motion field of the second image compared to the first intermediate image, and performing deformation processing on the first image based on the motion field to obtain a first target image, wherein the first target image and the second image correspond to the same phase of the target motor organ.

[0055] The motion field of the second image compared to the first intermediate image includes the displacement of the target moving organ in the second image compared to the target moving organ in the first intermediate image.

[0056] In one embodiment, the motion field of the second image compared to the first intermediate image is determined based on an existing motion field determination method.

[0057] It is understood that after the motion field is determined, if the first intermediate image is deformed based on the motion field to obtain the target image, the structural features in the target image will be identical to those in the second image, both corresponding to the second time. Since the motion field acts on structural features, the first image and the first intermediate image correspond to structural features at the same time. Therefore, when the first image is deformed based on the motion field to determine the first target image, the first target image and the second image will have identical structural features, both corresponding to the second time. Furthermore, the CT intensity value in the first target image matches the first energy level. In other words, the CT intensity value of the first target image matches the first energy level, but the structural features it includes correspond to the second time. In other words, the first target image and the second image can be considered as images acquired simultaneously at different energy levels at the T2 time phase. This achieves the goal of changing the structural features of the first image while preserving its image intensity features, and indirectly completes the registration of the first target image and the second image, with high accuracy.

[0058] Figure 2A This is the first image provided by the embodiment of the present invention. Figure 2B The second image provided by the embodiment of the present invention, Figure 2C A first target image provided by an embodiment of the present invention; Figure 2D A deformed image of the first image determined by using mean square error as an image similarity measurement function in the prior art; Figure 2E It is a deformed image of the first image determined by the prior art using the normalized correlation coefficient as the image similarity measurement function. In terms of visual effect, Figure 2C and Figure 2B have the same structural characteristics, Figure 2C and Figure 2A have the same CT intensity characteristics; and Figure 2D 、 Figure 2E The strength characteristics and Figure 2A There are significant differences, see Figure 2D and Figure 2E The arrow in the middle points to the intensity feature.

[0059] S140: Determine a decomposition result of the first substance according to the first target image and the second image.

[0060] Since the first target image and the second image correspond to structural features at the same phase and CT intensity values ​​at different energy levels, the first target image and the second image can be regarded as images at two different energy levels acquired simultaneously. Therefore, two base material images can be determined based on the first target image and the second image, such as a water-based image and an iodine-based image, a water-based image and a calcium-based image, etc.

[0061] Figure 3 This is the decomposition result of the first substance provided by the embodiment of the present invention. Figure 3The material distribution information in the is completely consistent with the structural features (see arrows), so the first material decomposition result determined by the embodiment of the present invention has higher accuracy.

[0062] The energy spectrum imaging technology solution provided by an embodiment of the present invention performs intensity transformation processing on a first image to obtain a first intermediate image, and the first intermediate image and the second image have the same CT intensity value. Since the first intermediate image and the second image have the same CT intensity value, the influence of different CT intensity values ​​on the accuracy of the motion field in the second image compared with the first intermediate image is eliminated during the process of determining the motion field in the second image compared with the first intermediate image, resulting in a higher accuracy of the motion field. Using the motion field to deform the first image to obtain a first target image, the first target image and the second image can have the same structural features. Therefore, the two can be regarded as two images acquired simultaneously at different energy levels, indirectly completing the registration between the first target image and the second image. Therefore, an accurate first substance decomposition result can be obtained based on the first target image and the second image. This effectively avoids the problem of large differences in structural features of the images corresponding to the two energy levels due to slow voltage switching, and the resulting low accuracy of the first substance decomposition result, thereby contributing to the popularization and application of energy spectrum CT imaging equipment based on slow tube voltage switching.

[0063] Figure 4 This is another flow chart of the spectral CT imaging method provided by an embodiment of the present invention. Based on the previous embodiment, this embodiment adds the determination of the material decomposition result of the image layer that does not include the target moving organ. Figure 4 As shown, the method includes:

[0064] S2101: Acquire a first initial image combination corresponding to a first energy level and a second initial image combination corresponding to a second energy level.

[0065] The scanning data collected during a single spectral CT imaging process of the target object is obtained, and image reconstruction is performed on the scanning data based on the existing spectral CT image reconstruction method to obtain a first initial image combination corresponding to the first energy level and a second initial image combination corresponding to the second energy level. It is understood that the first initial image combination and the second initial image combination have the same longitudinal scanning range, and image layers with the same layer identifier have the same longitudinal coordinates (coordinates in the head and foot direction of the target object), and both include image layers containing target motion organs and image layers not containing target motion organs. Image layers not containing target motion organs are generally distributed in front of or behind image layers containing target motion organs.

[0066] S2102: Select a first image pair from all image pairs having the same layer identifier in the first initial image combination and the second initial image combination, wherein part or all of the images in the first image pair include the target motion organ.

[0067] The layer identifier is the code of the image layer. The first initial image combination and the second initial image combination are acquired in the same head-foot orientation.

[0068] Exemplarily, if the image with layer identification 50 in the first initial image combination includes the target motion organ, and the image with layer identification 50 in the second initial image combination does not include the target motion organ, then the image pair corresponding to layer identification 50 is determined to be the first image pair.

[0069] Exemplarily, the image with the layer identifier 100 in the first initial image combination and the image with the layer identifier 100 in the second initial image combination both include the target motion organ, so the image pair corresponding to the layer identifier 100 is determined to be the first image pair.

[0070] S2103 : Using the image in each first image pair that belongs to the first initial image combination as the first image, and using the image in each first image pair that belongs to the second initial image combination as the second image.

[0071] All first images may include the target organ, or only some of them may include the target organ, while the remaining first images do not. Similarly, all second images may include the target organ, or only some of them may include the target organ, while the remaining second images do not. However, a second image corresponding to a first image that does not include the target organ definitely includes the target organ, and similarly, a first image corresponding to a second image that does not include the target organ definitely also includes the target organ.

[0072] S220 , performing intensity transformation processing on the first image to obtain a first intermediate image, wherein the CT intensity value of the first intermediate image matches the second energy level.

[0073] S230 , determining a motion field of the second image compared to the first intermediate image, and performing deformation processing on the first image based on the motion field to obtain a first target image, wherein the first target image and the second image correspond to the same phase of the target motor organ.

[0074] S240: Determine a decomposition result of the first substance according to the first target image and the second image.

[0075] In one embodiment, non-first images in the first initial image combination are used as third images, and non-second images in the second initial image combination are used as fourth images; the second substance decomposition result is determined based on the third image and the fourth image with the same layer identification; and the union of all the first substance decomposition results and all the second substance decomposition results is used as the target substance decomposition result.

[0076] It is understood that since neither the third image nor the fourth image includes the target motor organ, their structural features can be considered identical. Therefore, the second substance decomposition result can be directly determined based on the third and fourth images. The target substance decomposition result is the union of all first substance decomposition results determined based on the first target image and the second image, and all second substance decomposition results determined based on the third and fourth images.

[0077] The technical solution provided by the embodiment of the present invention selects an image pair in which at least one image includes a target motion organ from all image pairs with the same layer identification in the first initial image combination and the second initial image combination, and uses the image belonging to the first initial image combination in each first image pair as the first image, and uses the image belonging to the second initial image combination in each first image pair as the second image, accurately determining all first images that need to be motion corrected based on the second image, thereby ensuring the accuracy of the first substance decomposition result.

[0078] Figure 5 This is another flow chart of the energy spectrum CT imaging method provided by an embodiment of the present invention. This embodiment further refines the determination of the first intermediate image based on the previous embodiment. Figure 5 As shown, the method includes:

[0079] S310: Acquire a first initial image combination corresponding to a first energy level and a second initial image combination corresponding to a second energy level.

[0080] S3102: Select a first image pair from all image pairs having the same layer identifier in the first initial image combination and the second initial image combination, wherein part or all of the images in the first image pair include the target motion organ.

[0081] S3103 : Using the image in each first image pair that belongs to the first initial image combination as the first image, and using the image in each first image pair that belongs to the second initial image combination as the second image.

[0082] S320 , input the first image into a pre-trained intensity transformation model to obtain a first intermediate image, wherein the CT intensity value of the first intermediate image matches the second energy level.

[0083] like Figure 6 As shown in FIG. 1 , the first image (M(L, T1)) is input as input data μ into the pre-trained intensity transformation model, and the output data μ' of the pre-trained intensity transformation model is the first intermediate image M(H, T1). As can be seen from the figure, the CT intensity value of each pixel in the first intermediate image is higher than the CT intensity value of the corresponding pixel in the first image.

[0084] The intensity transformation model can be selected as an implicit network model. The pre-trained transformation model is based on the loss function The loss function can be selected as the two-norm, such as In one embodiment, the network depth can be selected according to the range of CT intensity values. For example, when the CT intensity value range is 0-1500HU, the network structure of the intensity transformation model is 128×128×128, with three layers in total; when the CT intensity value range is 0-2000HU, the network structure of the intensity transformation model is 128×128×128×128, with four layers in total.

[0085] In one embodiment, the training of the intensity transformation model is accomplished by the following steps:

[0086] Step a1: Select at least two image pairs that meet the static condition from all image pairs with the same layer identifier in the first initial image combination and the second initial image combination, and use each image pair in the at least two image pairs as the second image pair.

[0087] An image pair meeting the static condition requires that the relative displacement of each tissue or organ between the two images in the pair is less than a set number of pixels. In one embodiment, the set number of pixels can be selected as 3, 4, or 5, at which point the tissue or organ can be considered to be motionless or nearly motionless. This setting can be adjusted based on actual accuracy requirements.

[0088] It should be noted that skin, muscles, bones, target motor organs, and non-target motor organs are all tissue organs.

[0089] Step a2: taking the images in all the second image pairs that belong to the first initial image combination as the fifth image combination, and taking the images in all the second image pairs that belong to the second initial image combination as the sixth image combination.

[0090] Each fifth image in the fifth image combination corresponds to each sixth image in the sixth image combination in a one-to-one correspondence on the vertical coordinate plane. Because the fifth and sixth image combinations are determined based on image pairs that meet the static condition, even if the slow voltage switching speed is slow, the structural features of the corresponding image layers in the fifth and sixth image combinations can be considered identical. In this case, the CT intensity values ​​of corresponding pixels in the corresponding image layers are only related to the energy level and can therefore be used to determine training samples.

[0091] Step a3: For each fifth image in the fifth image combination, determine the pixel point combination corresponding to the current fifth image, and the CT intensity value corresponding to each pixel point in the pixel point combination in the current fifth image; determine the sixth image in the sixth image combination corresponding to the current fifth image, and the CT intensity value corresponding to each pixel point in the pixel point combination in the sixth image.

[0092] The pixel point combination is part or all of the pixel points in the current fifth image. When the pixel point combination is part of the pixel points in the current fifth image, the part of the pixel points can be determined based on a random selection method or a set area selection method. For example, all pixels within a specified range of the current fifth image are used as part of the pixel points, where the specified range can be 20×20 in the upper left corner, 30×30 in the lower right corner, etc., and can be determined according to specific circumstances in actual use.

[0093] It is understandable that, when the fifth image and the sixth image have the same pixel combination, the pixel combination can also be determined based on the sixth image; specifically, part or all of the pixels of the sixth image can be used as the pixel combination.

[0094] Step a4: Use the CT intensity value corresponding to each pixel point in the pixel point combination corresponding to the current fifth image in the current fifth image and the CT intensity value corresponding to the sixth image as training samples corresponding to the current fifth image.

[0095] Briefly, the training sample includes a coordinate combination, where each coordinate in the coordinate combination corresponds to two CT intensity values, one from the fifth image and one from the sixth image.

[0096] Step a5: Use all training samples to train the intensity conversion model until the network parameters of the intensity conversion model meet the set parameter optimization conditions, thereby obtaining a pre-trained intensity conversion model.

[0097] It can be understood that after the model training is completed, the intensity transformation model can learn the correspondence between the CT intensity value corresponding to the first energy level and the CT intensity value corresponding to the second energy level. In this way, it can determine the CT intensity value of each pixel point at the second energy level when the CT intensity value corresponding to each pixel point of the first image corresponding to the first energy level is known, so as to obtain the first intermediate image.

[0098] In one embodiment, for each target object, the training samples determined by its current fifth image combination and sixth image combination are used to complete the training of the intensity transformation model, obtain a pre-trained intensity transformation model, and then use the pre-trained intensity transformation model to perform intensity transformation on the first image; this achieves the technical effect of customizing a personalized pre-trained intensity transformation model for each target object, improves the adaptability of the pre-trained intensity transformation model relative to the first image to be processed, and improves the accuracy of the first intermediate image determined by the pre-trained intensity transformation model, thereby improving the accuracy of subsequent image processing.

[0099] S330: Determine a motion field of the second image compared to the first intermediate image, and perform deformation processing on the first image based on the motion field to obtain a first target image, wherein the first target image and the second image correspond to the same phase of the target motor organ.

[0100] S340: Determine a decomposition result of the first substance according to the first target image and the second image.

[0101] The embodiment of the present invention determines a first intermediate image corresponding to the first image through a pre-trained intensity transformation model, and makes the CT intensity value corresponding to each pixel point in the first intermediate image correspond to the second energy level, thereby achieving the technical effect of simply and quickly completing the intensity transformation of the CT intensity value of the first image.

[0102] Figure 7 This is another flow chart of the energy spectrum imaging method provided by an embodiment of the present invention. This embodiment further refines the determination of the target motion field based on the previous embodiment. Figure 7 As shown, the method includes:

[0103] S410: Acquire a first image corresponding to a first energy level and a second image corresponding to a second energy level, wherein at least one of the first image and the second image includes a target motor organ.

[0104] S420 , performing intensity transformation processing on the first image to obtain a first intermediate image, wherein the CT intensity value of the first intermediate image matches the second energy level.

[0105] S4301. Input the first intermediate image and the second image into a motion matching model to obtain a motion field of the second image compared with the first intermediate image.

[0106] The motion matching model includes an offset network and an adjustment network. The offset network is used to generate offsets for each pixel in the first intermediate image. The adjustment network is used to use the offsets corresponding to all pixels as a motion field when the deformation result of the first intermediate image corresponding to the offset meets the similarity condition with the second image. Otherwise, the offset network is controlled to adjust the offsets of each pixel in the first intermediate image until the adjusted offsets ensure that the deformation result of the first intermediate image meets the similarity condition with the second image.

[0107] S4302: Perform deformation processing on the first image based on the motion field to obtain a first target image, where the first target image and the second image correspond to the same phase of the target motion organ.

[0108] Specifically, the first loss function can be expressed as:

[0109]

[0110] Among them, L datais the similarity measurement function between the first intermediate image and the second image, is the target space transformation operator corresponding to the motion matching model. This operator acts on the first intermediate image to obtain the target image, and the target image and the second image meet the similarity constraint condition; L reg yes The regularization term, i.e., the similarity constraint term, is determined based on the Bending Energy regularization method. M(H,T1)oM2 represents the image result obtained by applying Φ2 to M(H,T1).

[0111] like Figure 8 As shown, the coordinates (x, y, z) of each pixel of the first intermediate image (M(H, T1)) are input into the offset network as input data. The output data (μ(x)) of the offset network is the offset of each pixel, specifically (x′, y′, z′). The offset of all pixels is used as the motion field of the second image compared to the first intermediate image, and then the sum of the first intermediate image and the motion field is used as the deformation result of the motion field acting on the first intermediate image.

[0112] The motion matching model is a registration network under the condition of the same energy level. It does not directly perform motion correction on the first intermediate image, but obtains the motion field by performing motion registration on the first intermediate image and the second image.

[0113] It can be understood that since the first image and the first intermediate image include the same structural features, the motion field can be used to perform motion correction on the first image. Since the first intermediate image and the second image correspond to the same energy level, the influence of the intensity feature on the accuracy of the motion field is avoided. In other words, the motion field does not include the intensity information of the image. In this way, when the motion field is used to perform motion correction on the first image, the intensity feature of the first image is completely preserved, that is, the first target image has the intensity feature corresponding to the first energy level and the structural feature corresponding to the second energy level (see Figure 2C ), which helps to improve the accuracy of the subsequent first material decomposition result determined based on the first target image and the second image.

[0114] The first image combination includes 100 layers of first images, and the second image combination includes 100 layers of second images. Sampling is performed every 10 layers to determine a first target image that is aligned with each second image.

[0115] In order to facilitate the display of image registration results, the first images of the first 50 layers are combined as a sub-image, and the first images of the last 50 layers are combined as a sub-image.

[0116] Figure 9A The first target image (D) and the second image (F) corresponding to the first 50 layers of the first image (M) provided in the embodiment of the present invention, Figure 9B The first target image (D) and the second image (F) corresponding to the last 50 layers of the first image provided in the embodiment of the present invention, Figure 9A and Figure 9B The first row is the first image (M), the second row is the first target image (D), and the third row is the second image (F). Figure 9A In the example, visually, the first target images marked as 0, 10, 20, 30 and 40 have the same structural features and different intensity features as the corresponding second images; similarly, Figure 9B , the first target images labeled 50, 60, 70, 80 and 90 have the same structural features and different intensity features as the corresponding second images.

[0117] S440: Determine a decomposition result of the first substance according to the first target image and the second image.

[0118] Figure 10A The first material decomposition results corresponding to the first 50 layers of first images provided by an embodiment of the present invention are shown in this figure. In this figure, the first and second row basis images are first material decomposition results determined based on existing technology; the third and fourth row basis images are first material decomposition results provided by an embodiment of the present invention. Clearly, the first material decomposition results corresponding to the third and fourth row basis images have higher accuracy.

[0119] Figure 10B This figure shows the first substance decomposition results corresponding to the last 50 layers of first images provided by an embodiment of the present invention. In this figure, the first and second row basis images are first substance decomposition results determined based on existing techniques, while the third and fourth row basis images are first substance decomposition results provided by an embodiment of the present invention. Clearly, the first substance decomposition results corresponding to the third and fourth row basis images have higher accuracy.

[0120] The technical solution provided by the embodiment of the present invention achieves the technical effect of quickly determining the structural feature differences between the second image and the first intermediate image by inputting the first intermediate image into a motion matching model to obtain a motion field.

[0121] Figure 11 This is a schematic diagram of the structure of the energy spectrum CT imaging device provided by the embodiment of the present invention. Figure 11 As shown, the device includes:

[0122] An image acquisition module 110 is configured to acquire a first image corresponding to a first energy level and a second image corresponding to a second energy level, wherein at least one of the first image and the second image includes a target motor organ;

[0123] an intensity conversion module 120, configured to perform intensity conversion processing on the first image to obtain a first intermediate image, wherein the CT intensity value of the first intermediate image matches the second energy level;

[0124] a deformation module 130 configured to determine a motion field of the second image compared to the first intermediate image, and to perform deformation processing on the first image based on the motion field to obtain a first target image, wherein the first target image and the second image correspond to the same phase of the target motor organ;

[0125] The base substance image module 140 is configured to determine a first substance decomposition result according to the first target image and the second image.

[0126] In one embodiment, the image acquisition module 110 is specifically configured to:

[0127] Acquire a first initial image combination corresponding to the first energy level and a second initial image combination corresponding to the second energy level;

[0128] Selecting a first image pair from all image pairs having the same layer identifier in the first initial image combination and the second initial image combination, wherein part or all of the images of the first image pair include the target motor organ;

[0129] using the image in each of the first image pairs that belongs to the first initial image combination as a first image, and using the image in each of the first image pairs that belongs to the second initial image combination as a second image;

[0130] In one embodiment, the image acquisition module 110 is further configured to:

[0131] using non-first images in the first initial image combination as third images, and using non-second images in the second initial image combination as fourth images;

[0132] The base material image module 140 is further configured to:

[0133] determining a decomposition result of the second substance according to the third image and the fourth image with the same layer identifier;

[0134] The union of all the first substance decomposition results and all the second substance decomposition results is used as the target substance decomposition result.

[0135] In one embodiment, the intensity transformation module 120 is specifically configured to:

[0136] The first image is input into a pre-trained intensity transformation model to obtain a first intermediate image.

[0137] In one embodiment, the apparatus further includes a model training module, the model training module including:

[0138] selecting at least two image pairs that meet a stationary condition from all image pairs having the same layer identifier in the first initial image combination and the second initial image combination, and using each image pair in the at least two image pairs as a second image pair;

[0139] taking the images in all the second image pairs that belong to the first initial image combination as a fifth image combination, and taking the images in all the second image pairs that belong to the second initial image combination as a sixth image combination;

[0140] determining, for each of the fifth images in the fifth image combination, a pixel combination corresponding to the current fifth image and a CT intensity value corresponding to each pixel in the pixel combination in the current fifth image; and determining, in the sixth image combination, a sixth image corresponding to the current fifth image and a CT intensity value corresponding to each pixel in the pixel combination in the sixth image;

[0141] using, for each pixel in the pixel point combination corresponding to the current fifth image, a CT intensity value corresponding to the current fifth image and a CT intensity value corresponding to the sixth image as training samples corresponding to the current fifth image;

[0142] All the training samples are used to perform model training on the intensity conversion model until the network parameters of the intensity conversion model meet the set parameter optimization conditions, thereby obtaining a pre-trained intensity conversion model.

[0143] In one embodiment, the motion matching model includes an offset network and an adjustment network, and the deformation module 130 includes a motion field unit, which is used to:

[0144] Inputting the first intermediate image and the second image into a motion matching model to obtain a motion field of the second image compared to the first intermediate image;

[0145] The offset network is used to generate an offset for each pixel in the first intermediate image; the adjustment network is used to use the offsets corresponding to all the pixel points as the motion field when the deformation result of the first intermediate image corresponding to the offset meets the similarity condition with the second image; otherwise, the offset network is controlled to adjust the offset of each pixel in the first intermediate image until the adjusted offset of each pixel point can make the deformation result of the first intermediate image meet the similarity condition with the second image.

[0146] In one embodiment, the target movement organ is the heart.

[0147] The energy spectrum imaging technology solution provided by an embodiment of the present invention performs intensity transformation processing on a first image to obtain a first intermediate image, and the first intermediate image and the second image have the same CT intensity value. Since the first intermediate image and the second image have the same CT intensity value, the influence of different CT intensity values ​​on the accuracy of the motion field in the second image compared with the first intermediate image is eliminated during the process of determining the motion field in the second image compared with the first intermediate image, resulting in a higher accuracy of the motion field. Using the motion field to deform the first image to obtain a first target image, the first target image and the second image can have the same structural features. Therefore, the two can be regarded as two images acquired simultaneously at different energy levels, indirectly completing the registration between the first target image and the second image. Therefore, an accurate first substance decomposition result can be obtained based on the first target image and the second image. This effectively avoids the problem of large differences in structural features of the images corresponding to the two energy levels due to slow voltage switching, and the resulting low accuracy of the first substance decomposition result, thereby contributing to the popularization and application of energy spectrum CT imaging equipment based on slow tube voltage switching.

[0148] The energy spectrum CT imaging device provided by the embodiment of the present invention can execute the energy spectrum CT imaging method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0149] Figure 12 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0150] like Figure 12As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0151] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0152] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the spectral CT imaging method.

[0153] In some embodiments, the spectral CT imaging method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the spectral CT imaging method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the spectral CT imaging method in any other suitable manner (e.g., via firmware).

[0154] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0155] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0156] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0157] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0158] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0159] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0160] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the energy spectrum CT imaging method provided in any embodiment of the present application.

[0161] The computer program product may be implemented by writing computer program code for performing the operations of the present invention in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0162] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0163] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A spectral CT imaging method, characterized in that: include: Acquiring a first image corresponding to a first energy level and a second image corresponding to a second energy level, including: acquiring a first initial image combination corresponding to the first energy level and a second initial image combination corresponding to the second energy level; selecting a first image pair from all image pairs having the same layer identifier in the first initial image combination and the second initial image combination, wherein part or all of the images in the first image pair include a target locomotor organ; using an image in each of the first image pairs that belongs to the first initial image combination as a first image, and using an image in each of the first image pairs that belongs to the second initial image combination as a second image, wherein at least one of the first image and the second image includes the target locomotor organ; performing intensity transformation processing on the first image to obtain a first intermediate image, wherein a CT intensity value of the first intermediate image matches the second energy level; determining a motion field of the second image compared to the first intermediate image, and performing deformation processing on the first image based on the motion field to obtain a first target image, wherein the first target image and the second image correspond to the same time phase of the target motor organ; determining a decomposition result of a first substance according to the first target image and the second image; using non-first images in the first initial image combination as third images, and using non-second images in the second initial image combination as fourth images; determining a decomposition result of the second substance according to the third image and the fourth image with the same layer identifier; The union of all the first substance decomposition results and all the second substance decomposition results is used as the target substance decomposition result.

2. The method according to claim 1, characterized in that The performing intensity transformation on the first image to obtain a first intermediate image includes: The first image is input into a pre-trained intensity transformation model to obtain a first intermediate image.

3. The method according to claim 2, characterized in that After acquiring the first initial image combination corresponding to the first energy level and the second initial image combination corresponding to the second energy level, the method further includes: selecting at least two image pairs that meet a stationary condition from all image pairs having the same layer identifier in the first initial image combination and the second initial image combination, and using each image pair in the at least two image pairs as a second image pair; taking the images in all the second image pairs that belong to the first initial image combination as a fifth image combination, and taking the images in all the second image pairs that belong to the second initial image combination as a sixth image combination; determining, for each fifth image in the fifth image combination, a pixel combination corresponding to the current fifth image and a CT intensity value corresponding to each pixel in the pixel combination in the current fifth image; and determining a sixth image in the sixth image combination corresponding to the current fifth image and a CT intensity value corresponding to each pixel in the pixel combination in the sixth image; using, for each pixel in the pixel point combination corresponding to the current fifth image, a CT intensity value corresponding to the current fifth image and a CT intensity value corresponding to the sixth image as training samples corresponding to the current fifth image; All the training samples are used to perform model training on the intensity conversion model until the network parameters of the intensity conversion model meet the set parameter optimization conditions, thereby obtaining the pre-trained intensity conversion model.

4. The method according to claim 1, wherein The motion matching model includes an offset network and an adjustment network, and determining the motion field of the second image compared to the first intermediate image includes: Inputting the first intermediate image and the second image into a motion matching model to obtain a motion field of the second image compared to the first intermediate image; The offset network is used to generate an offset for each pixel in the first intermediate image; the adjustment network is used to use the offsets corresponding to all the pixel points as the motion field when the deformation result of the first intermediate image corresponding to the offset meets the similarity condition with the second image; otherwise, the offset network is controlled to adjust the offset of each pixel in the first intermediate image until the adjusted offset of each pixel point can make the deformation result of the first intermediate image meet the similarity condition with the second image.

5. The method according to claim 1, wherein The target movement organ is the heart.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the spectral CT imaging method according to any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the spectral CT imaging method according to any one of claims 1 to 5 when executed.

8. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the spectral CT imaging method according to any one of claims 1 to 5.

Images