Sequential scanning DECT cardiac imaging method based on AIGC condition generation

By using AIGC conditional generation technology and model processing, motion-matched DECT cardiac images are directly generated, solving the motion artifact problem in sequential scanning DECT cardiac imaging and achieving efficient, low-cost, and high-precision imaging.

CN118986381AActive Publication Date: 2024-11-22SOUTHEAST UNIV

Patent Information

Application Number
CN202411062249.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-11-22
Estimated Expiration
2044-08-05

AI Technical Summary

Technical Problem

Traditional registration-based motion state matching methods are difficult to effectively solve the motion artifact problem in sequential DECT cardiac imaging, especially under the influence of organ motion caused by heartbeat, resulting in large imaging errors.

Method used

AIGC conditional generation technology is adopted, and sequential scan DECT cardiac image domain data with motion state matching is directly generated through Energy-GAN model and diffusion denoising model, avoiding complex 3D flexible registration. The generator is trained using static image layer to generate high-energy image layer, and image domain material decomposition and denoising processing are performed.

Benefits of technology

It effectively reduces imaging time, improves imaging accuracy, expands the clinical application of DECT cardiac imaging, reduces costs, and demonstrates superiority in addressing motion artifacts.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118986381A_ABST
    Figure CN118986381A_ABST
Patent Text Reader

Abstract

The invention discloses a sequential scanning DECT cardiac imaging method based on AIGC condition generation, and the method comprises the steps: carrying out the sequential scanning of the projection data of different phases and high and low energy levels of a heart through CT, and carrying out the FDK reconstruction through the projection data, and obtaining the image domain data of high and low energy levels; the method comprises the following steps: selecting a high-energy-level organ image pair and a low-energy-level organ image pair of which an image domain is in a relatively static state to train a condition to generate a network model Entry-GAN, and generating a high-energy image layer in the same motion state by using a low-energy image layer of a motion organ as an input condition of the Entry-GAN; and finally, carrying out image domain substance decomposition on the generated high-energy image and the corresponding low-energy image, and carrying out denoising on the substance decomposition image by using a pre-trained diffusion model. According to the method, sequential scanning DECT cardiac imaging is achieved, and on the premise that 3D image flexible registration is not carried out, noise generated by substance decomposition artifact image domain substance decomposition caused by heart movement is effectively reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of computer image processing, and in particular to a sequential scanning DECT cardiac imaging method based on AIGC condition generation. Background Art

[0002] In recent years, with the continuous development of medical imaging technology, CT (computed tomography) technology has become an important tool in diagnosis and treatment. CT technology obtains cross-sectional images of the body through X-ray rotation scanning at different angles, thereby helping doctors diagnose diseases and guide surgery. Traditional CT imaging technology is X-ray mixed energy imaging, which leads to its two biggest inherent defects: X-ray hardening effect and average absorption effect [1]. The former will produce beam hardening artifacts, which are more serious for objects with larger atomic weights, such as bones and iodine contrast agents; the latter will cause different substances to have similar CT values, that is, the phenomenon of foreign body co-image.

[0003] In order to overcome these shortcomings of traditional single-energy CT technology (SECT), dual-energy CT (DECT) technology came into being. DECT uses two X-ray beams of different energies to scan objects and can obtain energy characteristics of different tissues and materials. Compared with SECT, DECT can provide more accurate tissue identification capabilities, reduce the generation of metal artifacts, and improve the imaging quality of low-contrast structures. However, DECT requires the acquisition of two sets of different energy projection data that are consistent in space and time, which places higher requirements on data acquisition methods.

[0004] DECT data acquisition methods include fast KVP switching scanning, single-source multi-slice scanning, and dual-source scanning, all of which require specialized hardware, are costly, and technically difficult. In contrast, single-source sequential scanning can be implemented on any conventional SECT scanner, is less expensive, and is less technically difficult, and is mainly used for kidney stone and gout examinations. However, this method is more susceptible to the motion of the scanned object during scanning, such as changes in body position, organ motion caused by breathing and heartbeat, especially the beating of the heart, which can reach several centimeters in 1 second and is highly nonlinear and localized. Since sequential scans are obtained from different locations of the same anatomical structure, large global motion artifacts may be generated, reducing the quantitative accuracy of DECT imaging.

[0005] For cardiac data collected by sequential scanning DECT, it is necessary to match the motion state before material decomposition, which is generally achieved through image registration algorithms. According to different similarity metrics, the traditional registration algorithms currently developed mainly include three categories. The first category is the registration method based on image grayscale features. This type of method matches according to the grayscale distribution characteristics of the image, including Demons, NCC, MSE, MI, etc. The second category is the registration method based on image features, including surf, ORB, HOG, LBP, etc.; the third category is based on image registration in the transform domain, such as Fourier transform. The above algorithms measure image similarity from different perspectives. Although they can play a good effect in specific registration tasks, they all have their own limitations. For example, the Demons algorithm has the constraints of constant brightness and small motion, and does not work well when the motion amplitude is large; the NCC and MSE algorithms are based on the consistency of the grayscale features of the image, and do not work well when the grayscale values ​​of the images are very different and for multimodal registration; MI, as a global metric, only measures the statistical correlation of the grayscale values ​​between two complete images for local image alignment; HOG, surf, LBP, ORB and other image feature-based registration methods only align important points in the image and tend to ignore global information; methods based on transform domains usually require certain assumptions on the image transformation model, such as affine transformation, polynomial transformation, etc. If the transformation model does not conform to the actual situation, it may affect the accuracy and stability of the registration.

[0006] At present, for single-modality CT image registration, similarity based on CT intensity values ​​is generally used as the image similarity metric, such as NCC, MSE, MI, etc. This scheme has been proven to be feasible for the registration of CT images scanned at the same energy level. However, in DECT imaging, due to the different energy levels of the two scans, there is a large difference in the intensity values ​​of high-energy CT images and low-energy CT images, resulting in obvious CT value drift in the deformed image obtained by the single-modality CT image registration algorithm based on intensity features as the similarity metric, which amplifies the error of DECT imaging.

[0007] Therefore, the traditional motion state matching method based on registration is difficult to be directly used to solve the motion artifact problem in sequential scanning DECT cardiac imaging. With the development of AIGC technology, it is possible to directly generate the required images by conditional generation. Therefore, the present invention combines AIGC conditional generation technology with DECT technology and is committed to developing a sequential scanning DECT cardiac imaging method based on AIGC conditional generation, which solves the motion artifact problem in sequential scanning DECT cardiac imaging in a new way. Summary of the invention

[0008] In order to solve the problem of motion artifacts in sequential scanning DECT cardiac imaging, the present invention discloses a sequential scanning DECT cardiac imaging method based on AIGC conditional generation, which directly generates sequential scanning DECT cardiac image domain data with motion state matching through conditional generation, avoiding the matching of image motion state through complex 3D flexible alignment under sequential scanning DECT cardiac imaging conditions.

[0009] In order to achieve the above object, the present invention provides the following technical solutions:

[0010] A sequential scanning DECT cardiac imaging method based on AIGC condition generation comprises the following steps:

[0011] Step 1, acquiring cardiac high-energy and low-energy CT data obtained by sequential scanning, and performing FDK reconstruction on the high-energy and low-energy CT data respectively;

[0012] Step 2, separating static image layers and dynamic image layers from the high- and low-energy CT image domain data reconstructed by FDK;

[0013] Step 3, using the static low-energy image layer as the generation condition and the static high-energy image layer as the generation target, training the Energy-GAN conditional generation model;

[0014] Step 4: Use the dynamic low-energy image layer as a generation condition and input it into Energy-GAN to generate the corresponding high-energy layer;

[0015] Step 5, performing image domain material decomposition to calculate iodine and water base images according to the dynamic low-energy image layer and the generated high-energy image layer;

[0016] Step 6, using the simulated heart iodine-based and water-based images, gradually add Gaussian noise to train the diffusion denoising model;

[0017] Step 7: Input the water-based and iodine-based images in step 5 into the pre-trained denoising model for denoising.

[0018] Furthermore, in step 1, the cone-beam 3D projection algorithm in the ASTRA Toolbox is used to perform FDK analytical reconstruction.

[0019] Furthermore, in step 2, the static image layer and the dynamic image layer are separated by using an image similarity measurement function provided by the scikit-image library, which specifically includes the following process: selecting SSIM as the image similarity measure, setting a suitable threshold as the standard for distinguishing dynamic and static layers, taking the one-to-one corresponding 2D layers in the 3D high-energy level heart image and the 3D low-energy level heart image as input, comparing the SSIM values ​​of image pairs from different energy levels and the same image layer, if the SSIM values ​​are lower than the specified threshold, it is considered that the image pair has inconsistent motion states and belongs to a dynamic layer, otherwise it belongs to a static layer, and finally obtaining four image sets M(low, t1, static), M(low, t1, dynamic), M(high, t2, static), and M(high, t2, dynamic), which represent low-energy static layers, low-energy dynamic layers, high-energy static layers, and high-energy dynamic layers, respectively, wherein the motion states of M(low, t1, static) and M(high, t2, static) match, and the motion states of M(low, t1, dynamic) and M(high, t2, dynamic) do not match.

[0020] Furthermore, the step 3 specifically includes the following process:

[0021] ① The image layers corresponding to the separated static low-energy image M(low,t1,static) and static high-energy image M(high,t2,static) are concatenated along the channel direction as positive samples;

[0022] ② Input the separated static low-energy image M(low,t1,static) into the generator G, output G(M(low,t1,static)), and concatenate M(low,t1,static) and G(M(low,t1,static)) in the channel direction as a negative sample;

[0023] ③ Alternately train the generator G and the discriminator D until the loss functions of both the generator and the discriminator converge;

[0024] Furthermore, the step 4 specifically includes the following process:

[0025] The dynamic low-energy image layer is input into the trained Energy-GAN to obtain the corresponding high-energy image in the same motion state generated by the generator based on the dynamic low-energy image.

[0026] Furthermore, the step 5 specifically includes the following process:

[0027] The dynamic low-energy image layer and the corresponding generated high-energy image layer are solved by the image domain material decomposition algorithm based on matrix inversion. According to the image-based decomposition theory, the linear attenuation coefficient of the CT image is approximately the weighted sum of the two basis material images, as shown in Formula 1:

[0028]

[0029] X H,i,j represents the CT image reconstructed at different energy levels; d1 / 2 represents the base material image or decomposed image; i, j are the image pixel indices; the component matrix is ​​composed of X kH / L (k=1 or 2) element composition, Xk H / L is the linear attenuation coefficient or mass attenuation coefficient of the base material measured at high and low energies. At this time, the matrix is ​​inverted, and the process is shown in Formula 2:

[0030]

[0031] In this method, d1 and d2 represent water-based image water and iodine-based image iodine, respectively.

[0032] X H , X L They represent the dynamic low-energy image layers M(low,t1,dynamic)[slicer] and G(M(low,t1,dynamic)[slicer]) respectively, where slicer is the layer index.

[0033] Furthermore, in step 6, the simulated heart data in the XCAT phantom is used to generate a material-based image gold standard T, and Gaussian noise is gradually added to the gold standard for training the diffusion denoising model.

[0034] Furthermore, in step 7, the water-based image water and the iodine-based image iodine generated in step 5 are input into the trained diffusion denoising model to reduce noise.

[0035] Compared with the existing technology, the present invention has the following advantages and beneficial effects:

[0036] 1. The present invention applies AIGC technology to sequential scanning DECT cardiac imaging, directly generates motion state-matched cardiac dual-energy scanning image domain data, avoids the use of complex 3D flexible registration technology to correct the motion state of the initial high- and low-energy image domains, and the trained model can perform dual-energy imaging online in real time, which effectively reduces the imaging time compared to the 3D flexible registration technology.

[0037] 2. The present invention inputs the separated static low-energy image M(low, t1, static) into the generator G as a generation condition, splices the separated static high- and low-energy image pairs M(low, t1, static) and M(high, t2, static) in the channel direction and inputs them into the discriminator D as positive samples, and splices M(low, t1, static) and G(M(low, t1, static)) in the channel direction and inputs them into the discriminator as negative samples, thereby effectively changing the CT intensity distribution of M(low, t1, static) while keeping the motion state of M(low, t1, static) unchanged, so that the CT intensity distribution of G(M(low, t1, static)) is consistent with the intensity distribution of M(high, t2, static).

[0038] 3. The image denoising method based on the diffusion model implemented by the present invention has many advantages. First, it does not require a large amount of paired training data, so it is more flexible in practical applications. Second, it can approximate the posterior distribution of the clean image through the reverse diffusion process, thereby avoiding the problem of over-smoothing. Finally, it can control the degree of denoising by adjusting the number of steps of reverse diffusion to meet different needs.

[0039] 4. The sequential scanning DECT cardiac imaging method based on AIGC condition generation proposed in the present invention effectively expands the clinical application scope of ordinary CT and reduces the cost of DECT cardiac imaging. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The overall flow chart of the sequential scanning DECT cardiac imaging method based on AIGC condition generation provided by the present invention;

[0041] Figure 2 Schematic diagram of Energy-GAN, a network for generating high-energy CT images based on AIGC conditions;

[0042] Figure 3 This is a schematic diagram of the diffusion denoising model used in the present invention;

[0043] Figure 4 The high-energy image M(high, t1, dynamic) generated by Energy-GAN in the present invention and the high-energy image M'(high, t1, dynamic) after deformation of M(high, t2, dynamic) using three different registration algorithms SyNMI, Demons, and VoxelMorph, where Ground Truth is the gold standard and slicer is the layer index. The experimental results show that the scheme proposed in the present invention is superior to the registration-based method;

[0044] Figure 5 The iodine-based images obtained by the sequential scanning DECT cardiac imaging method based on AIGC conditions in the present invention and the iodine-based material images obtained by three registration-based methods SyNMI, Demons, and VoxelMorph, among which GroundTruth is the gold standard. The experimental results show that the scheme proposed in the present invention is superior to the registration-based method.

[0045] Figure 6 The water-based images are obtained by the sequential scanning DECT cardiac imaging method generated based on AIGC conditions in the present invention, and the water-based material images are obtained by three registration-based methods SyNMI, Demons, and VoxelMorph, among which GroundTruth is the gold standard. The experimental results show that the scheme proposed in the present invention is superior to the registration-based method. DETAILED DESCRIPTION

[0046] The present invention is further explained below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention. It should be noted that the words "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to directions in the accompanying drawings, and the words "inner" and "outer" refer to directions toward or away from the geometric center of a specific component, respectively.

[0047] The present embodiment provides a sequential scanning DECT cardiac imaging method based on AIGC conditional generation. First, sequential scanning DECT myocardial perfusion projection domain data of human body obtained from clinical scanning is used to perform FDK parsing and reconstruction by the cone beam three-dimensional projection algorithm in the ASTRA Toolbox to obtain image domain data with mismatched motion state; then, the static image layer and the dynamic image layer are separated by using the image similarity measurement function provided by the scikit-image library; then, the static image layer and the dynamic image layer are separated by using the image similarity measurement function provided by the scikit-image library; then, the low-energy and high-energy static image pairs M(low, t1, static) and M(high, t2, static) are used to train the conditional generation model Energy-GAN, and the low-energy dynamic image layer M(low, t1, dynamic) is input into the generator G of the trained Energy-GAN as a generation condition to generate the corresponding high-energy layer M(high, t1, dynamic) with matching motion state;

[0048] Next, M(low,t1,dynamic) and M(high,t1,dynamic) are used to perform material decomposition in the image domain, and the decomposed material-based image is input into the pre-trained diffusion denoising model for denoising; finally, the sequential scanning DECT cardiac imaging method generated based on AIGC conditions is compared with the results obtained using the traditional registration-based algorithm, and the performance of the network model is evaluated.

[0049] Specifically, the overall process of this embodiment is as shown in the attached Figure 1-4 As shown, the following steps are included:

[0050] Step 1: Obtain cardiac high- and low-energy CT data obtained by sequential scanning, and perform FDK analytical reconstruction using the cone-beam 3D projection algorithm in ASTRA Toolbox.

[0051] Step 2, using the image similarity measurement function provided by the scikit-image library to separate the static image layer and the dynamic image layer, specifically including the following process: select SSIM as the image similarity measure, set a suitable threshold as the standard for distinguishing dynamic and static layers, take the corresponding 2D layers in the 3D high-energy level heart image and the 3D low-energy level heart image as input, compare the SSIM values ​​of image pairs from different energy levels and the same image layer, if it is lower than the specified threshold, it is considered that the image pair has inconsistent motion states and belongs to a dynamic layer, otherwise it belongs to a static layer, and finally obtain four groups of image sets M(low, t1, static), M(low, t1, dynamic), M(high, t2, static), and M(high, t2, dynamic), which represent low-energy static layers, low-energy dynamic layers, high-energy static layers, and high-energy dynamic layers, respectively, where the motion states of M(low, t1, static) and M(high, t2, static) match, and the motion states of M(low, t1, dynamic) and M(high, t2, dynamic) do not match. In this implementation case, the threshold is set to 0.9.

[0052] Step 3, splice the image layers corresponding to the separated static low-energy image M(low, t1, static) and the static high-energy image M(high, t2, static) along the channel direction as positive samples. Input the separated static low-energy image M(low, t1, static) into the generator G, output G(M(low, t1, static)), splice M(low, t1, static) and G(M(low, t1, static)) in the channel direction as negative samples. Alternately train the generator G and the discriminator D until the loss functions of the generator and the discriminator converge;

[0053] Step 4: Input the dynamic low-energy image layer into the trained Energy-GAN to obtain the corresponding high-energy image in the same motion state generated by the generator based on the dynamic low-energy image. Step 5: Solve the dynamic low-energy image layer and the corresponding generated high-energy image layer using the image domain material decomposition algorithm based on matrix inversion. According to the image-based decomposition theory, the linear attenuation coefficient of the CT image is approximately the weighted sum of the two basis material images, as shown in Formula 1:

[0054]

[0055] X H,i,j represents the CT image reconstructed at different energy levels; d1 / 2 represents the base material image or the decomposed image; i and j are the pixel indices of the image x-axis and y-axis respectively; the component matrix is ​​composed of X kH / L (k=1 or 2) element composition, Xk H / L is the linear attenuation coefficient or mass attenuation coefficient of the base material measured at high and low energies. At this time, the matrix is ​​inverted, and the process is shown in Formula 2:

[0056]

[0057] In this method, d1 and d2 represent water-based image water and iodine-based image iodine, respectively.

[0058] X H , X L They represent the dynamic low-energy image layers M(low,t1,dynamic)[slicer] and G(M(low,t1,dynamic)[slicer]) respectively, where slicer is the layer index.

[0059] Step 6: Generate a material-based image gold standard T using the simulated heart data in the XCAT phantom, and gradually add Gaussian noise to the gold standard for training the diffusion denoising model.

[0060] Step 7: Input the water-based image water and the iodine-based image iodine generated in step 5 into the trained diffusion denoising model to reduce noise.

[0061] In order to verify the effect of the sequential scanning DECT cardiac imaging method based on AIGC condition generation disclosed in the present invention, a set of human CT data sets obtained by clinical scanning is used to verify the significant improvement of the method disclosed in the present invention over the traditional algorithm. Figure 5 , 6A comparison chart of the material decomposition effects obtained by using the traditional algorithm and the conditional generation algorithm of the present invention is shown. Compared with the two, the method provided by the present invention can significantly reduce the motion artifact problem caused by cardiac movement in sequential scanning DECT imaging while ensuring the quantitative accuracy of material decomposition, and the imaging effect is significantly improved, which has profound significance for conducting clinical medical research.

[0062] The technical means disclosed in the scheme of the present invention are not limited to the technical means disclosed in the above-mentioned implementation mode, but also include technical schemes composed of any combination of the above technical features.

Claims

1. A sequential scanning DECT cardiac imaging method based on AIGC condition generation, characterized in that: The following steps are involved: Step 1, acquiring cardiac high-energy and low-energy CT data obtained by sequential scanning, and performing FDK reconstruction on the high-energy and low-energy CT data respectively; Step 2, separating static image layers and dynamic image layers from the high- and low-energy CT image domain data reconstructed by FDK; Step 3, using the static low-energy image layer as the generation condition and the static high-energy image layer as the generation target, training the Energy-GAN conditional generation model; Step 4: Use the dynamic low-energy image layer as a generation condition and input it into Energy-GAN to generate the corresponding high-energy layer; Step 5, performing image domain material decomposition to calculate iodine and water base images according to the dynamic low-energy image layer and the generated high-energy image layer; Step 6, using the simulated heart iodine-based and water-based images, gradually add Gaussian noise to train the diffusion denoising model; Step 7: Input the water-based and iodine-based images in step 5 into the pre-trained denoising model for denoising.

2. The sequential scanning DECT cardiac imaging method based on AIGC condition generation according to claim 1, characterized in that: In step 1, the cone-beam 3D projection algorithm in the ASTRA Toolbox is used to perform FDK reconstruction.

3. The sequential scanning DECT cardiac imaging method based on AIGC condition generation according to claim 1, characterized in that: In step 2, the static image layer and the dynamic image layer are separated by using the image similarity measurement function provided by the scikit-image library, which specifically includes the following process: SSIM was selected as the image similarity measure, and a suitable threshold was set as the standard for distinguishing dynamic and static layers in combination with actual operations. The corresponding 2D layers in the 3D high-energy level cardiac image and the 3D low-energy level cardiac image were taken as input, and the SSIM values ​​of image pairs from different energy levels and the same image layer were compared. If the SSIM value was lower than the specified threshold, it was considered that the image pair had inconsistent motion states and belonged to a dynamic layer. Otherwise, it belonged to a static layer. Finally, four image sets M(low, t1, static), M(low, t1, dynamic), M(high, t2, static), and M(high, t2, dynamic) were obtained, representing low-energy static layer, low-energy dynamic layer, high-energy static layer, and high-energy dynamic layer, respectively. The motion states of M(low, t1, static) and M(high, t2, static) matched, while the motion states of M(low, t1, dynamic) and M(high, t2, dynamic) did not match.

4. The sequential scanning DECT cardiac imaging method based on AIGC condition generation according to claim 1, characterized in that: The step 3 specifically includes the following process: ① The image layers corresponding to the separated static low-energy image M(low,t1,static) and static high-energy image M(high,t2,static) are concatenated along the channel direction as positive samples; ② Input the separated static low-energy image M(low,t1,static) into the generator G, output G(M(low,t1,static)), and concatenate M(low,t1,static) and G(M(low,t1,static)) in the channel direction as a negative sample; ③ Alternately train the generator G and the discriminator D until the loss functions of both the generator and the discriminator converge.

5. The sequential scanning DECT cardiac imaging method based on AIGC condition generation according to claim 1, characterized in that: The step 4 specifically includes the following process: The dynamic low-energy image layer is input into the trained Energy-GAN to obtain the corresponding high-energy image in the same motion state generated by the generator based on the dynamic low-energy image.

6. The sequential scanning DECT cardiac imaging method based on AIGC condition generation according to claim 1, characterized in that: The step 5 specifically includes the following process: The dynamic low-energy image layer and the corresponding generated high-energy image layer are solved by the image domain material decomposition algorithm based on matrix inversion; according to the image-based decomposition theory, the linear attenuation coefficient of the CT image is approximately the weighted sum of the two basis material images, as shown in Formula 1: X H,i,j represents the CT image reconstructed at different energy levels; d1 / 2 represents the base material image or the decomposed image; i and j are the pixel indices of the image x-axis and y-axis respectively; the component matrix is ​​composed of X kH / L (k=1 or 2) element composition, Xk H / L is the linear attenuation coefficient or mass attenuation coefficient of the base material measured at high and low energies; at this time, the matrix is ​​inverted, and the process is shown in (2): Where d1 and d2 represent the water-based image water and the iodine-based image iodine, respectively. X H, X L They represent the dynamic low-energy image layers M(low,t1,dynamic)[slicer] and G(M(low,t1,dynamic)[slicer]) respectively, where slicer is the layer index.

7. The sequential scanning DECT cardiac imaging method based on AIGC condition generation according to claim 1, characterized in that: The step 6 specifically includes the following process: The simulated heart data in the XCAT phantom is used to generate the material-based image gold standard T, and Gaussian noise is gradually added to the gold standard for training the diffusion denoising model.

8. The sequential scanning DECT cardiac imaging method based on AIGC condition generation according to claim 1, characterized in that: The step 7 specifically includes the following process: The water-based image water and the iodine-based image iodine generated in step 5 are input into the trained diffusion denoising model to reduce noise.

Citation Information

Patent Citations

  • X-ray energy spectrum detection and reconstruction analysis method for dual-energy CT imaging

    CN107884806A

  • Image processing method and system and application thereof

    CN113506353A

  • Coronary artery microcirculation analysis system based on CT

    CN117297640A

  • Energy spectrum CT image domain dual-material decomposition method based on generative adversarial network

    CN117409096A

  • Heart CT image geometric calibration method and system based on machine learning

    CN117422647A

Cited By

  • Sparse visual angle CT reconstruction method based on conditional embedding fusion diffusion model

    CN120374781A