Simulation of X-rays from low dose CT

Abstract

Systems and methods for converting three-dimensional computed tomography (CT) data into a two-dimensional image are provided. In one embodiment, a method is provided that includes retrieving three-dimensional CT imaging data, where the three-dimensional CT imaging data includes projection data acquired from a plurality of angles about a central axis. Once three-dimensional CT imaging data is retrieved, the imaging data is processed as a three-dimensional image, and the method continues to generate a two-dimensional image by tracking rays from a simulated radiation source located outside of the three-dimensional image. The two-dimensional image is then presented to the user as simulated X-rays.

Description

Technical Field

[0001] This disclosure generally relates to systems and methods for simulating conventional X-ray images from CT data. More specifically, this disclosure relates to presenting ultra-low-dose CT data to a user as a two-dimensional image simulating an X-ray image. Background Technology

[0002] Compared to traditional planar X-ray (CXR) imaging, computed tomography (CT) imaging offers advantages. Consequently, CT imaging has replaced X-ray imaging in various clinical settings and is increasingly being used as a replacement for X-ray imaging in additional clinical settings.

[0003] This is especially true in the context of low-dose and ultra-low-dose CT imaging (ULDCT), which is currently designed to replace CXR in additional settings such as routine chest imaging in outpatient settings.

[0004] Compared to CXR, a major advantage of CT imaging is that it provides additional information, specifically three-dimensional spatial information. Furthermore, CXR has relatively low sensitivity and a high false-negative rate in many clinical scenarios. Due to the additional information associated with CT imaging, it is also better suited for various image processing and AI-based diagnostic techniques.

[0005] On the other hand, compared to traditional CT imaging, specifically ULCT imaging, CXR has higher spatial resolution and is less affected by noise.

[0006] One reason why CT imaging has not been more widely adopted in routine clinical settings is that its readout time is significantly longer than that of CXR. This is partly because radiologists are more familiar with CXR images and are therefore more comfortable reading and making diagnoses based on these traditional planar X-ray images.

[0007] However, in terms of radiologists continuing to rely on CXR images, they are giving up the advantages of CT imaging in terms of both additional information and analytical capabilities.

[0008] There is a need for a CT imaging system and method, specifically a ULDCT imaging system and method, that can present data to radiologists in a form that is easier to interpret and more likely to be adopted. There is also a need for a system in which the advantages of CT imaging are offered to radiologists in an accessible manner. Summary of the Invention

[0009] Systems and methods are provided for converting three-dimensional computed tomography (CT) data into two-dimensional images. One method includes retrieving three-dimensional CT imaging data, wherein the three-dimensional CT imaging data comprises projection data acquired from multiple angles about a central axis.

[0010] Once the 3D CT imaging data is retrieved, the imaging data is processed into a 3D image, and the method continues to generate a 2D image by tracing rays from a simulated radiation source located outside the subject in the 3D image.

[0011] Subsequently, a two-dimensional image is presented to the user as a simulated X-ray.

[0012] In some embodiments, processing the three-dimensional CT imaging data includes reconstructing the three-dimensional image using filtered backprojection. In some such embodiments, the three-dimensional CT imaging data includes ultra-low dose CT imaging data, and processing the three-dimensional CT image data also includes denoising the imaging data.

[0013] In some such embodiments, processing 3D CT imaging data also includes performing artificial intelligence (AI)-based super-resolution processing. This super-resolution processing may include deblurring.

[0014] In some embodiments, denoising imaging data may include applying a trained convolutional neural network (CNN) to the three-dimensional CT imaging data.

[0015] In some embodiments, denoising is applied to the 3D CT imaging data before reconstructing the 3D image.

[0016] In some embodiments, the method further includes processing the two-dimensional image by applying a style to the two-dimensional image before presenting the image to the user. This style may be derived from multiple X-ray images, and the style may subsequently modify the appearance of the two-dimensional image without altering its morphological content.

[0017] In some of these embodiments, the multiple X-ray images are conventional planar X-ray images.

[0018] In some embodiments, processing of three-dimensional CT imaging data includes identifying at least one physical element in the three-dimensional image and removing or masking the at least one physical element from the three-dimensional image before generating a two-dimensional image.

[0019] In some of these embodiments, the physical element is an anatomical element, such as a rib or the heart. In other embodiments, the physical element is a table or an implant.

[0020] In some embodiments, a two-dimensional image is presented to the user together with a three-dimensional image, and an indicator is incorporated into the three-dimensional image to indicate a segment of the three-dimensional image represented in the two-dimensional image.

[0021] In some embodiments, the method further includes processing the two-dimensional image before presenting it to the user. This processing may include applying denoising or super-resolution processing to the image.

[0022] In some embodiments, AI-based denoising or super-resolution processing is applied to the 2D plane in 3D CT imaging data.

[0023] In some embodiments, the three-dimensional CT imaging data includes spectral data or photon count data, and the simulated X-rays are simulated spectral X-rays or photon count X-rays.

[0024] In some embodiments, the generation of a two-dimensional image is performed by a neural network. In some such embodiments, the neural network is a trained convolutional neural network. Attached Figure Description

[0025] Figure 1 This is a schematic diagram of a system according to an embodiment of the present disclosure.

[0026] Figure 2 An exemplary imaging device according to one embodiment of the present disclosure is shown.

[0027] Figure 3 An illustrative workflow for implementing a method according to an embodiment of the present disclosure is shown.

[0028] Figure 4 This is a flowchart illustrating a method according to an embodiment of the present disclosure.

[0029] Figure 5 A ray tracing process applied to a three-dimensional image is schematically illustrated and can be used in the context of one embodiment of this disclosure.

[0030] Figures 6A to 6C An implementation of style conversion used in a method according to an embodiment of this disclosure is shown. Detailed Implementation

[0031] The description of illustrative embodiments based on the principles of this disclosure is intended to be read in conjunction with the accompanying drawings, which should be considered an integral part of the entire written description. Any references to direction or orientation in the description of embodiments of the disclosure herein are intended only for ease of description and are not intended to limit the scope of this disclosure in any way. Relative terms such as “lower,” “upper,” “horizontal,” “vertical,” “above,” “below,” “up,” “top,” and “bottom,” and their derivatives (e.g., “horizontally,” “downward,” “upward,” etc.) should be interpreted as referring to the orientation as described in the discussion or shown in the accompanying drawings. These relative terms are for ease of description only and do not require the device to be constructed or operated in a particular orientation unless expressly indicated otherwise. Unless expressly described otherwise, terms such as “attach,” “fix,” “connect,” “couple,” “interconnect,” and similar terms refer to a relationship in which structures are directly or indirectly fixed or attached to each other by intervening structures, and movable or rigid attachments or relationships. Moreover, the features and advantages of this disclosure are illustrated by reference to exemplary embodiments. Accordingly, this disclosure should not be explicitly limited to exemplary embodiments that illustrate combinations of possible, non-limiting features that may exist alone or in other combinations of features; the scope of this disclosure is defined by the appended claims.

[0032] This disclosure describes one or more best modes of carrying out this disclosure as currently contemplated. This specification is not intended to be understood in a limiting sense, but rather to provide examples of this disclosure for illustrative purposes only by reference to the accompanying drawings, to inform those skilled in the art of the advantages and construction of this disclosure. In the various views of the drawings, the same reference numerals denote the same or similar parts.

[0033] It is important to note that the disclosed embodiments are merely examples of the many advantageous uses of the inventive teachings herein. Generally, the statements made in this application's specification do not necessarily limit any of the various claims. Furthermore, some statements may apply to some inventive features but not to others. Generally, unless otherwise indicated, singular elements may be plural, and vice versa, without loss of generality.

[0034] Computed tomography (CT) and conventional planar X-ray (CXR) are both used in medical imaging. However, CT imaging, particularly ultra-low dose CT imaging (ULDCT), is designed to replace CXR in many clinical settings, such as chest imaging in routine outpatient settings.

[0035] Some of the key advantages of ULDCT imaging are readily apparent. CT imaging, including ULDCT, provides three-dimensional spatial information, which allows for sophisticated analytical techniques. Furthermore, ULDCT avoids the relatively low sensitivity and high false-negative rate associated with CXR in many clinical settings.

[0036] However, compared to CXR, ULDCT has a slower readout time, and radiologists are less familiar with and less comfortable with ULDCT. Therefore, radiologists tend to prefer being presented with more familiar CXR images and making diagnoses based on them. Thus, the methods described in this paper provide a workflow for generating artificial CXR images from ULDCT data, or images stylized to have the appearance of CXR images. These methods can be implemented or enhanced using artificial intelligence (AI) techniques, including learning algorithms in the form of neural networks (e.g., convolutional neural networks (CNNs)).

[0037] Accordingly, a method for converting 3D CT data into 2D images is provided. In this way, CXR-style images can be generated from ULDCT data and presented to radiologists. This presentation can follow analysis techniques applied to the underlying ULDCT data in either the raw or 3D image format, and can be presented to radiologists as a proxy for CXR images or within the context of a corresponding ULDCT-based image interface.

[0038] Therefore, the following can be used: Figure 1 Systems like the one shown and with the help of, for example Figure 2 Imaging devices such as the one shown generate 3D CT imaging data from ULDCT imaging data. Subsequently, it can be used... Figure 1 The system's processing equipment is used to process the retrieved data.

[0039] Figure 1 This is a schematic diagram of a system 100 according to an embodiment of the present disclosure. As shown, system 100 generally includes a processing device 110 and an imaging device 120.

[0040] Processing device 110 can apply processing routines to image or measurement data, such as projection data, received from imaging device 120. Processing device 110 may include memory 113 and processor circuitry 111. Memory 113 may store multiple instructions. Processor circuitry 111 may be coupled to memory 113 and may be configured to execute instructions. Instructions stored in memory 113 may include processing routines and data associated with the processing routines, such as machine learning algorithms and various filters for processing images.

[0041] The processing device 110 may also include an input 115 and an output 117. The input 115 may receive information from the imaging device 120, such as three-dimensional images or measurement data, such as three-dimensional CT imaging data. The output 117 may output information to a user or user interface device, such as a filtered image or a converted two-dimensional image. The output may include a monitor or display.

[0042] In some embodiments, the processing device 110 may be directly associated with the imaging device 120. In alternative embodiments, the processing device 110 may be distinct from the imaging device 120, such that the processing device 110 receives image or measurement data for processing at input 115 via a network or other interface.

[0043] In some embodiments, the imaging device 120 may include an image data processing device and a spectral or conventional CT scanning unit for generating CT projection data when scanning an object (e.g., a patient). In some embodiments, the imaging device 120 may be a conventional CT scanning unit configured to generate helical scans.

[0044] Figure 2 An exemplary imaging apparatus 200 according to one embodiment of the present disclosure is shown. It should be understood that although a CT imaging apparatus 200 is shown, and the following discussion is generally in the context of CT images, similar methods can be applied in the context of other imaging apparatuses, and images to which these methods have been applied can be acquired in a variety of ways.

[0045] In the imaging apparatus 200 according to embodiments of the present disclosure, the CT scanning unit may be adapted to perform one or more axial and / or helical scans of an object to generate CT projection data. In the imaging apparatus 200 according to embodiments of the present disclosure, the CT scanning unit may include an energy-resolved photon counting or spectral dual-layer image detector. Other detector settings may also be used to acquire spectral content. The CT scanning unit may include a radiation source that emits radiation for passing through the object when acquiring projection data.

[0046] exist Figure 2 In the example shown, a CT scanning unit 200, such as a computed tomography (CT) scanner, may include a fixed gantry 202 and a rotating gantry 204, which may be rotatably supported by the fixed gantry 202. When acquiring projection data, the rotating gantry 204 may rotate about a longitudinal axis about an examination area 206 for the object. The CT scanning unit 200 may include a support 207 for supporting a patient within the examination area 206 and is configured to allow the patient to pass through the examination area during imaging.

[0047] The CT scanning unit 200 may include a radiation source 208, such as an X-ray tube, which may be supported by a rotating gantry 204 and configured to rotate with the gantry 204. The radiation source 208 may include an anode and a cathode. A source voltage applied across the anode and cathode can accelerate electrons from the cathode to the anode. The electron flow can provide a current from the cathode to the anode, for example, to generate radiation for passing through the examination area 206.

[0048] The CT scanning unit 200 may include a detector 210. The detector 210 may be positioned relative to the radiation source 208 at an angular arc opposite the examination area 206. The detector 210 may include a one-dimensional or two-dimensional array of pixels, such as direct conversion detector pixels. The detector 210 may be adapted to detect radiation passing through the examination area 206 and to generate a signal indicating the energy of that radiation.

[0049] The CT scanning unit 200 may include generators 211 and 213. Generator 211 may generate tomographic projection data 209 based on signals from detector 210. Generator 213 may receive the tomographic projection data 209 and, in some embodiments, generate three-dimensional CT imaging data 311 of the object based on the tomographic projection data 209. In some embodiments, the tomographic projection data 209 may be provided to input 115 of processing device 110, while in other embodiments, the three-dimensional CT imaging data 311 is provided to input of processing device 110.

[0050] Figure 3 An illustrative workflow for implementing a method according to an embodiment of the present disclosure is shown. Figure 4 This is a flowchart illustrating a method according to an embodiment of the present disclosure. As shown, the method typically includes first retrieving (400) three-dimensional CT imaging data. This three-dimensional CT imaging data includes projection data of the subject acquired from multiple angles around a central axis.

[0051] Therefore, in Figure 2 In the context of the imaging device 200, the subject can be a patient positioned on the support 207, and the central axis can be an axis passing through the examination area. When acquiring three-dimensional CT imaging data from the imaging device 200, the rotating gantry 204 can then rotate about the subject's central axis to acquire projection data from various angles.

[0052] Once acquired, the three-dimensional CT imaging data 311 is reconstructed (410) into a three-dimensional image 300 for processing. Subsequently, the three-dimensional CT imaging data 311 is processed (420) into a three-dimensional image 300.

[0053] It should be understood that although reconstruction (at 410) and processing (at 420) are indicated as different processes, reconstruction itself may be the actual processing of 3D CT imaging data into a 3D image. Similarly, reconstruction can be part of such processing. This reconstruction (at 410) can be performed using standard reconstruction techniques, such as filtered backprojection.

[0054] like Figure 3 As shown, the process may include denoising 310, which may utilize a neural network or other artificial intelligence-based learning algorithm. In the example shown, denoising 310 utilizes a convolutional neural network (CNN) previously trained on an appropriate image. This denoising process 310 can be used, for example, in noisy CT imaging, as is the case with ULDCT images. Subsequently, the denoising process may produce a denoised or partially denoised 3D image 320.

[0055] The described denoising process 310 can be a process of incorporating features that allow it to be well generalized to different contrasts, anatomical structures, reconstruction filters, and noise levels. This denoising process 310 can compensate for the inherently high noise levels in ULDCT images.

[0056] In the example shown, the processing of the 3D CT image (at 420) may also include performing super-resolution processing 330. As in the case of denoising processing 310, super-resolution processing 330 may be performed using AI-based learning algorithms, such as CNNs. In some embodiments, super-resolution processing 330 may include deblurring the image. Subsequently, super-resolution processing 330 may produce a higher-resolution 3D image 340.

[0057] Super-resolution processing 330 typically interpolates images to a smaller voxel size while preserving or enhancing perceived image sharpness. AI-based super-resolution processing 330 can be trained on real CT images (including ULDCT images) or more general image materials (such as natural high-resolution photographs).

[0058] In the illustrated embodiment, denoising process 310 and super-resolution process 330 are applied sequentially. However, it should be understood that these two processes can be combined into a single neural network (e.g., a CNN). Furthermore, although both processes 310 and 330 are shown as being applied to the 3D image 300, in some embodiments, these processes can be applied directly to the 3D CT imaging data prior to reconstruction (at 410). Additionally, in some embodiments, one or both processes 310 and 330 can be applied to a 2D plane in the 3D CT imaging dataset perpendicular to the projection direction to generate the 2D image discussed below.

[0059] In some embodiments, the process may further include identifying (430) at least one physical element in the three-dimensional image. Once identified (at 430), the physical element may be removed from or masked (435) from the three-dimensional image. By removing or masking (435) the element before generating the two-dimensional image, such a physical element may be removed from the simulated X-ray generated from the CT imaging data.

[0060] The identified physical feature (at 430) can be an anatomical feature, such as one or more ribs or the heart. For example, by removing such an anatomical feature from the simulated X-ray, other anatomical features of interest to the radiologist reviewing the image may be more easily seen, and the simulated X-ray can show a cross-section of the patient's chest cavity without interfering with the ribs.

[0061] Alternatively, the identified physical element (at 430) can be a table 207 or an implant. As in the imaging apparatus 200 discussed above, CT imaging data is typically acquired from a patient lying on a table or other support 207. Conversely, conventional planar X-rays are typically acquired from a standing patient. Accordingly, by removing the support 207, the simulated X-ray can appear more natural to the radiologist reviewing the images. Similarly, removing an implant can provide a better view of the patient's anatomy.

[0062] In some embodiments, physical features can be weighted rather than removed (at 430). Similarly, different segments of the 3D image 300 can be weighted differently.

[0063] After processing the three-dimensional CT imaging data (at 420), the method continues to generate a two-dimensional image 350 by tracing (440) rays from a simulated radiation source located outside the subject in the three-dimensional image. For example, this ray tracing processing can be implemented by implementing the Siddons-Jacobs ray tracing algorithm.

[0064] Figure 5A ray tracing process (440) is illustrated for performing ray tracing on a 3D image 300 to generate a 2D image 350. The ray tracing process can then be performed in such a manner that the processing of X-rays 345 is simulated by propagating incident X-ray photons from a simulated radiation source 500 through the reconstructed 3D image 300. The generation of the 2D image 350 can be achieved using a neural network (e.g., a CNN), and in this case, the CNN can be combined with one or more of the denoising, super-resolution, or style transfer processes discussed elsewhere in this document. Such a neural network can be a generative adversarial network (GAN). In this embodiment, many or all of the steps described herein can be combined into a single network, which is then fed CT volumetric data and outputs a simulated CXR projection.

[0065] In some embodiments, the projection angle or orientation of the ray tracing process (440) can be adjusted to improve the resulting two-dimensional image 350. Similarly, the weights of physical elements in the three-dimensional image 300 can be adjusted to improve the resulting two-dimensional image 350.

[0066] Once a two-dimensional image 350 has been generated, in some embodiments, an optional style transfer process (450) can be applied, wherein a style is applied to the two-dimensional image. In this embodiment, the applied style (at 450) can be derived from multiple X-ray images (460), such as conventional planar X-ray images, and can be applied using an AI algorithm 360 (e.g., CNN). This style changes the appearance of the two-dimensional image but does not alter the morphological content of the underlying image. This process will be discussed in more detail below with reference to Figure 6, and this process can be used to generate a second two-dimensional image 370 in the "style" of conventional X-rays.

[0067] In some embodiments, following the ray tracing process (at 440), further processing may be applied to the two-dimensional image (470). This processing may include denoising or super-resolution processing applied to the image, and may be applied instead of additionally to the three-dimensional image.

[0068] Following any processing (at 470), the two-dimensional image 350 or stylized image 370 can be presented to a user (480), such as a radiologist. This presentation (at 480) can include presenting the image as if it were a conventional planar X-ray, or it can include incorporating the two-dimensional image 350 or stylized image 370 into a user interface having a three-dimensional image 300. For example, in some embodiments, the two-dimensional image 350 or stylized image 370 can be presented to the user along with the three-dimensional image 300 and an indicator incorporated into the three-dimensional image indicating the segment of the three-dimensional image represented in the two-dimensional image. Accordingly, the two-dimensional image 350 or stylized image 370 can be presented as a cross-sectional view of the three-dimensional image 300, wherein the three-dimensional image contextualizes the cross-section. Subsequently, the two-dimensional image 350 or stylized image 370 can be used as an avatar to guide ULDCT readings, and AI feedback can be projected onto the two-dimensional image to help the radiologist quickly identify problem areas for detailed examination and reporting of the original ULDCT image.

[0069] In some embodiments, three-dimensional CT imaging data may include spectral data. In such embodiments, simulated X-rays can similarly simulate spectral X-rays. Similarly, this method can be applied to photon-counting or phase-shrinking CT datasets, and the photon-counting or phase-shrinking CT datasets can subsequently be reflected in the resulting two-dimensional images.

[0070] Similarly, although the method is described in the context of CT data, specifically ULDCT data, a similar method can be applied to magnetic resonance (MR) image data by applying MR-CT image translation and subsequently applying the described method steps.

[0071] Figures 6A to 6C The implementation of style transfer used in the method of this disclosure is illustrated. As shown in the figure, a set of "style images," for example... Figure 6A As shown, this can be used to define a specific style for an image. Subsequently, an artificial intelligence algorithm, such as a CNN, can be trained to apply the style derived from the "style image" to the received image.

[0072] Accordingly, when such as Figure 6B When an image like the one shown is received by an AI algorithm, it can be re-rendered and output in the style of a "styled image," such as... Figure 6C As shown. In the example shown, the style may be derived from a specific artist, in this case Paul Klee, and applied to a general portrait.

[0073] In the embodiments discussed herein, the "style image" used to train the AI ​​algorithm can be, for example, a conventional X-ray (CXR) image. In this way, a 2D image 350 generated from the ULDCT 3D image 300 can be converted to look more like a CXR image. This stylized image 370 can then be used in practice. It should be understood that style transfer does not change the morphological content of the image, but only its appearance. Thus, the described style transfer is a conservative technique.

[0074] Many of the steps described in this paper can be implemented as AI methods such as CNNs. For example, these methods can be used to achieve effects of varying intensities to allow for different levels of denoising or super-resolution.

[0075] The methods according to this disclosure can be executed on a computer as a computer-implemented method, or in dedicated hardware, or a combination of both. Executable code for the methods according to this disclosure can be stored on a computer program product. Examples of computer program products include memory devices, optical storage devices, integrated circuits, servers, online software, etc. Preferably, the computer program product may include non-transient program code stored on a computer-readable medium for performing the methods according to this disclosure when the program product is executed on a computer. In one embodiment, the computer program may include computer program code adapted to perform all steps of the methods according to this disclosure when the computer program is run on a computer. The computer program may be embodied on a computer-readable medium.

[0076] Although this disclosure has been described in detail with respect to several described embodiments and has some particularity, it is not intended to limit this disclosure to any such details or embodiments or any particular embodiment, but rather to be interpreted with reference to the appended claims in order to provide the broadest possible interpretation of these claims in accordance with the prior art, thereby effectively covering the intended scope of this disclosure.

[0077] All examples and conditional language described herein are intended for pedagogical purposes to aid the reader in understanding the principles of this disclosure and the concepts contributed by the inventors to further the development of the art, and should be construed as not being limited to these specifically described examples and conditions. Furthermore, all statements herein describing the principles, aspects, and embodiments of this disclosure, as well as specific examples thereof, are intended to cover structural and functional equivalents. Moreover, such equivalents include those currently known as well as those developed in the future, i.e., any element developed that performs the same function, regardless of its structure.

Claims

1. A method for converting three-dimensional computed tomography (CT) data into a two-dimensional image, comprising: Retrieving three-dimensional CT imaging data, the three-dimensional CT imaging data comprising projection data acquired from a plurality of angles around a central axis; Processing the three-dimensional CT imaging data into a three-dimensional image; generating a two-dimensional image by tracing rays from a simulated radiation source located external to a subject of the three-dimensional image; as well as The two-dimensional image is presented to the user as a simulated X-ray.

2. The method according to claim 1, characterized in that Processing the three-dimensional CT imaging data includes reconstructing the three-dimensional image using filtered back projection.

3. The method according to claim 2, characterized in that The three-dimensional CT imaging data includes ultra-low-dose CT imaging data, and processing the three-dimensional CT imaging data includes denoising the imaging data.

4. The method according to claim 3, characterized in that: Processing the three-dimensional CT imaging data also includes performing AI-based super-resolution processing.

5. The method according to claim 4, characterized in that The super-resolution processing includes a deblurring process.

6. The method according to claim 3, characterized in that Denoising the imaging data includes applying a trained convolutional neural network (CNN) to the three-dimensional CT imaging data.

7. The method according to claim 2, characterized in that A denoising process is applied to the three-dimensional CT imaging data prior to reconstructing the three-dimensional image.

8. The method according to claim 1, characterized in that The method also includes processing the two-dimensional image by applying a style to the two-dimensional image before presenting the two-dimensional image to the user, the style being derived from a plurality of X-ray images and modifying the appearance of the two-dimensional image without modifying the morphological content of the two-dimensional image.

9. The method according to claim 8, characterized in that The plurality of X-ray images are conventional planar X-ray images.

10. The method according to claim 1, characterized in that Processing the three-dimensional CT imaging data includes identifying at least one physical element in the three-dimensional image and removing or masking the at least one physical element from the three-dimensional image before generating the two-dimensional image.

11. The method according to claim 10, characterized in that The at least one physical element is an anatomical element.

12. The method according to claim 1, characterized in that The two-dimensional image is presented to the user along with the three-dimensional image, and an indicator is incorporated into the three-dimensional image to indicate a section of the three-dimensional image that is represented in the two-dimensional image.

13. The method according to claim 1, characterized in that The method also includes processing the two-dimensional image before presenting the two-dimensional image to the user, processing the two-dimensional image including applying a denoising or super-resolution process to the image.

14. The method according to claim 1, characterized in that The method also includes performing AI-based denoising or super-resolution processing in 2D planes in the three-dimensional CT imaging data.

15. The method according to claim 1, characterized in that The three-dimensional CT imaging data includes spectral data or photon counting data, and the simulated X-ray is a simulated spectral X-ray or a photon counting X-ray.

16. The method according to claim 1, characterized in that Generating the two-dimensional image is performed by a neural network.

17. A system for converting three-dimensional computed tomography (CT) data into two-dimensional images, comprising: a memory storing a plurality of instructions; as well as a processor circuit coupled to the memory and configured to execute the plurality of instructions to: Retrieving three-dimensional CT imaging data, the three-dimensional CT imaging data comprising projection data acquired from a plurality of angles around a central axis; Processing the three-dimensional CT imaging data into a three-dimensional image; generating a two-dimensional image by tracing rays from a simulated radiation source located external to a subject of the three-dimensional image; as well as The two-dimensional image is presented to the user as a simulated X-ray.

18. A non-transitory computer readable medium for storing executable instructions causing a method to be performed to convert three-dimensional computed tomography (CT) data into a two-dimensional image, the method comprising: Retrieving three-dimensional CT imaging data, the three-dimensional CT imaging data comprising projection data acquired from a plurality of angles around a central axis; Processing the three-dimensional CT imaging data into a three-dimensional image; generating a two-dimensional image by tracing rays from a simulated radiation source located external to a subject of the three-dimensional image; as well as The two-dimensional image is presented to the user as a simulated X-ray.

Images