X-ray Simulation from Low-dose CT

Abstract

A system and method for converting three-dimensional computed tomography (CT) data into two-dimensional images are provided. Such a method includes obtaining three-dimensional CT imaging data, which includes projection data obtained from a plurality of angles centered around a central axis. Once the three-dimensional CT imaging data is obtained, the three-dimensional CT imaging data is processed as a three-dimensional image, and the method proceeds to generate a two-dimensional image by ray tracing X-rays from a simulated radiation source outside the three-dimensional image. The two-dimensional image is then presented to the user as the simulated X-rays.

Description

Technical Field

[0001] The present disclosure generally relates to systems and methods for simulating conventional X-ray images from CT data. In particular, the present disclosure relates to presenting ultra-low dose CT data to a user as a two-dimensional image simulating an X-ray image.

Background Art

[0002] Computed tomography (CT) imaging offers advantages over conventional planar X-ray (CXR) imaging. Thus, CT imaging has replaced X-ray imaging in various clinical situations and is being increasingly adopted in additional clinical situations in place of such X-ray imaging.

[0003] This is particularly true for low-dose and ultra-low-dose CT imaging (ULDCT), which is intended to replace CXR in additional situations such as routine chest imaging in the outpatient setting today.

Summary of the Invention

Problems to be Solved by the Invention

[0004] One of the main advantages of CT imaging over CXR is that CT provides additional information, particularly three-dimensional spatial information. Also, CXR has a relatively low sensitivity and a high false negative rate in many clinical scenarios. CT imaging is also more suitable for various image processing and AI-based diagnostic techniques due to the additional information associated with it.

[0005] On the other hand, CXR has a higher spatial resolution and is less affected by noise than conventional CT imaging and particularly ULCT imaging.

[0006] One reason why CT imaging has not been more widely adopted in routine clinical settings is that the reading time for CT imaging is substantially longer than that for CXR. This is partly because radiologists are more familiar with CXR images and thus have a more comfortable basis for reading and diagnosing such conventional planar X-ray images.

[0007] However, as long as radiologists continue to rely on CXR images, they are foregoing the advantages of both the additional information and the analytical capabilities of CT images.

[0008] There is a need for CT imaging systems and methods, particularly ULDCT imaging systems and methods, that can present data to radiologists in a form that is more easily interpretable and more likely to be adopted. Further, there is a need for a system that can make the advantages of CT imaging available to radiologists in an easy-to-understand and accessible manner.

Means for Solving the Problems

[0009] A system and method for converting three-dimensional computed tomography (CT) data into two-dimensional images are provided. Such a method includes acquiring three-dimensional CT imaging data, which includes projection data acquired from a plurality of angles centered around a central axis.

[0010] Once the three-dimensional CT imaging data is acquired, the imaging data is processed as a three-dimensional image, and the method proceeds to generate a two-dimensional image by tracing rays from a simulated radiation source outside the object of the three-dimensional image.

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

[0012] In some embodiments, the processing of three-dimensional CT imaging data includes reconstructing a three-dimensional image using filtered backprojection. In some such embodiments, the three-dimensional CT imaging data has ultra-low dose CT imaging data, and processing the three-dimensional CT imaging data further includes removing noise from the imaging data.

[0013] In some such embodiments, processing the three-dimensional CT imaging data further includes performing artificial intelligence (AI)-based super-resolution processing. Such super-resolution processing can include deblurring processing.

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

[0015] In some embodiments, a noise removal process is applied to the three-dimensional CT imaging data before reconstructing the three-dimensional image.

[0016] In some embodiments, the method further includes processing a two-dimensional image before presenting the image to the user by applying a style to the two-dimensional image. Such a style can be derived from a plurality of X-ray images, and such a style changes the appearance of the two-dimensional image but does not change the morphological content of the two-dimensional image.

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

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

[0019] In some such 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, the 2D image is presented to the user using the 3D image, and an indicator is incorporated into the 3D image that indicates a segment of the 3D image represented in the 2D image.

[0021] In some embodiments, the method further includes processing the 2D image before presenting the 2D image to the user. Such processing can include applying noise removal or super-resolution processing to the image.

[0022] In some embodiments, AI-based noise removal or super-resolution processing is applied to the 2D planes within the 3D CT imaging data.

[0023] In some embodiments, the 3D CT imaging data includes spectral data or photon counting data, and the simulated X-rays are simulated spectral X-rays or photon counting X-rays.

[0024] In some embodiments, the generation of the 2D image is performed by a neural network. In some such embodiments, the neural network is a trained convolutional neural network.

Brief Description of the Drawings

[0025]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6A

Figure 6B

Figure 6C

Embodiments for Carrying Out the Invention

[0026] The description of exemplary embodiments in accordance with the principles of the present disclosure is intended to be read in conjunction with the accompanying drawings, which are to be regarded as a part of the entire specification. In the description of the embodiments of the disclosure disclosed herein, references to directions or orientations are for convenience of description only and are not intended to limit the scope of the disclosure in any way. Relative meaning differentials such as "lower", "upper", "horizontal", "vertical direction", "above", "below", "on", "under", "over", "beneath", and "underneath" (e.g., "horizontal", "lower", "upper", etc.) should be construed to refer to the orientation as then described or as shown in the drawings under discussion. These relative meanings are for convenience of description only and do not require the device to be constructed or operated in a particular orientation unless explicitly shown as such. Terms such as "attached", "affixed", "connected", "coupled", "interconnected", and the like, unless explicitly stated otherwise, refer to a relationship where structures are fixed or attached to each other directly or indirectly through intervening structures and through both movable or rigid attachments or relationships. Further, the features and advantages of the present disclosure are illustrated by reference to the exemplified embodiments. Accordingly, the present disclosure should not be explicitly limited to such exemplary embodiments showing some possible non-limiting combinations of several possible features that may exist alone or in combination with other features, and the scope of the present disclosure is defined by the claims appended hereto.

[0027] The present disclosure describes the best mode(s) contemplated for carrying out the present disclosure as presently conceived. This description is not intended to be understood in a limiting sense, but rather is presented for illustrative purposes only by reference to the accompanying drawings to advise those skilled in the art of the advantages and configurations of the present disclosure. In the various views of the drawings, like reference numerals indicate like or similar parts.

[0028] It is important to note that the disclosed embodiments are merely illustrative of many beneficial uses of the innovative teachings herein. Generally, the descriptions made in the specification of this application do not necessarily limit any of the various claimed disclosures. Further, some descriptions may be applicable to some features of some inventions but not to others. Generally, unless otherwise specified, a single component may be plural without losing generality, and vice versa.

[0029] Both computed tomography (CT) and conventional planar X-ray (CXR) are used in medical imaging. However, CT imaging, especially ultra-low dose CT imaging (ULDCT), is aimed at replacing CXR in many clinical situations, such as chest imaging in routine outpatient settings.

[0030] Some of the main advantages of ULDCT images are immediately apparent. CT imaging, including ULDCT, provides three-dimensional spatial information that enables advanced analysis techniques. Further, ULDCT avoids the relatively low sensitivity and high false negative rate associated with CXR in many clinical scenarios.

[0031] However, ULDCT has a slower reading time than CXR, and radiologists are less familiar with and less comfortable with ULDCT. Therefore, radiologists prefer to present more familiar CXR images and make diagnoses based on them. Accordingly, the methods described herein provide a workflow for generating artificial CXR images or images stylistically transformed to have the appearance of CXR images from ULDCT data. Such methods can be implemented or enhanced using artificial intelligence (AI) techniques, including the use of learning algorithms in the form of neural networks such as convolutional neural networks (CNNs).

[0032] Accordingly, a method for converting three-dimensional CT data into two-dimensional images is provided. In this way, CXR-style images can be generated from ULDCT data and presented to a radiologist. Such presentation can follow the implementation of analysis techniques for the underlying ULDCT data, either in a raw image format or a three-dimensional image format, and can be presented to the radiologist as a surrogate for a CXR image or in the context of a corresponding ULDCT-based image interface.

[0033] Accordingly, ULDCT imaging data can be generated as three-dimensional CT imaging data by an imaging device as shown in FIG. 2 using a system as shown in FIG. 1. The acquired data can then be processed using the processing device of the system of FIG. 1.

[0034] FIG. 1 is a schematic diagram of a system 100 according to an embodiment of the present disclosure. As shown, system 100 typically includes a processing device 110 and an imaging device 120.

[0035] The processing device 110 can apply processing routines to images or measurement data such as projection data received from the imaging device 120. The processing device 110 can include a memory 113 and a processor circuit 111. The memory 113 can store a plurality of instructions. The processor circuit 111 can be coupled to the memory 113 and configured to execute the instructions. The instructions stored in the memory 113 can include processing routines, data related to the processing routines such as machine learning algorithms, and various filters for processing images.

[0036] The processing device 110 can further have an input 115 and an output 117. The input unit 115 can receive information such as measurement data like a three-dimensional image or three-dimensional CT imaging data from the imaging device 120. The output unit 117 can output information such as a filtered image or a converted two-dimensional image to the user or a user interface device. The output unit can also have a monitor or a display.

[0037] In some embodiments, the processing device 110 can be directly related to the imaging device 120. In an alternative embodiment, the processing device 110 may be separate from the imaging device 120, and the processing device 110 can receive an image or measurement data for processing via a network or other interface at the input unit 115.

[0038] In some embodiments, the imaging device 120 can have an image data processing device and a spectral CT scan unit or a conventional CT scan unit that generates CT projection data when scanning a subject (e.g., a patient). In some embodiments, the imaging device 120 may be a conventional CT scan unit configured to perform helical scanning.

[0039] FIG. 2 shows an exemplary imaging device 200 according to an embodiment of the present disclosure. A CT imaging device 200 is shown, and the following description generally relates to the context of CT images, but the same methods can be applied in the context of other imaging devices, and it will be understood that the images to which these methods can be applied can be acquired in a wide variety of ways.

[0040] In the imaging device 200 according to an embodiment of the present disclosure, the CT scan unit can be adapted to perform one or more axial scans and / or helical scans of the subject to generate CT projection data. In the imaging device 200 according to an embodiment of the present disclosure, the CT scan unit can have an energy-resolved photon counting or spectral dual-layer image detector. Spectral content can be acquired using other detector setups. The CT scan unit can have a radiation source that emits radiation traversing the subject when acquiring projection data.

[0041] In the example shown in FIG. 2, the CT scan unit 200, for example a computed tomography (CT) scanner, can have a stationary gantry 202 and a rotating gantry 204 that can be rotatably supported by the stationary gantry 202. The rotating gantry 204 can rotate about the longitudinal axis around the examination region 206 of the subject when acquiring projection data. The CT scan unit 200 can have a support 207 for supporting the patient in the examination region 206 and is configured to pass the patient through the examination region during the imaging process.

[0042] The CT scan unit 200 can have a radiation source 208, such as an X-ray tube, that is supported by and configured to rotate with the rotating gantry 204. The radiation source 208 can have an anode and a cathode. The source voltage applied between the anode and the cathode can accelerate electrons from the cathode to the anode. The flow of electrons can provide a flow of current from the cathode to the anode to generate radiation traversing the examination region 206.

[0043] The CT scan unit 200 can have a detector 210. The detector 210 can define an angled arc on the opposite side of the examination region 206 from the radiation source 208. The detector 210 can have a one - or two - dimensional array of pixels, such as direct - conversion detector pixels. The detector 210 can be adapted to detect radiation traversing the examination region 206 and generate a signal indicative of its energy.

[0044] The CT scan unit 200 can have generators 211 and 213. The generator 211 can generate tomographic projection data 209 based on signals from the detector 210. The generator 213 can 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 can be provided to the input section 115 of the processing device 110, and in other embodiments, the three - dimensional CT imaging data 311 can be provided to the input of the processing device.

[0045] FIG. 3 shows a schematic workflow for implementing a method according to an embodiment of the present disclosure. FIG. 4 is a flowchart showing a method according to an embodiment of the present disclosure. As shown, the method typically first includes acquiring three - dimensional CT imaging data (400). Such three - dimensional CT imaging data includes projection data of the object acquired from a plurality of angles about a central axis.

[0046] Thus, in the context of the imaging device 200 of FIG. 2, the object can be a patient on the support 207, and the central axis can be an axis passing through the examination region. When three - dimensional CT imaging data is acquired from the imaging device 200, the rotating gantry 204 can rotate around the central axis of the object, thereby enabling the acquisition of projection data from various angles.

[0047] Once the three-dimensional CT imaging data 311 is acquired, it is reconstructed as a three-dimensional image 300 for processing (410). Next, the three-dimensional CT imaging data 311 is processed as the three-dimensional image 300 (420).

[0048] Although the reconstruction (410) and the processing (420) are shown as separate processes, it should be understood that the reconstruction itself can be the actual processing of the three-dimensional CT imaging data as a three-dimensional image. Similarly, the reconstruction may be part of such processing. Such a reconstruction (410) can be by using standard reconstruction techniques such as filtered backprojection.

[0049] As shown in FIG. 3, the processing can include, for example, noise removal 310 by a neural network or other artificial intelligence-based learning algorithm. In the illustrated example, the noise removal 310 is by a convolutional neural network (CNN) previously trained on a suitable image. Such noise removal processing 310 can be utilized, for example, when the CT imaging data is noisy as in the case of ULDCT images. The noise removal processing can then provide a noise-removed or partially noise-removed three-dimensional image 320.

[0050] The noise removal processing 310 described can be a process that incorporates features that enable it to generalize well for different contrasts, anatomical structures, reconstruction filters, and noise levels. Such a noise removal process 310 can compensate for the high noise level inherent in ULDCT images.

[0051] In the illustrated example, the processing (420) of the 3D CT image can further include the implementation of the super-resolution processing 330. Similar to the case of the noise removal process 310, the super-resolution processing 330 can use an AI-based learning algorithm such as a CNN. In some embodiments, the super-resolution processing 330 can include blurring removal of the image. Then, the super-resolution processing 330 can result in a higher-resolution 3D image 340.

[0052] Typically, the super-resolution processing 330 interpolates the image to a smaller voxel size while maintaining or improving the perceived image sharpness. The AI-based super-resolution processing 330 can be trained with either actual CT images including ULDCT images or more general image materials such as natural high-resolution photos.

[0053] In the illustrated embodiment, both the noise removal process 310 and the super-resolution processing 330 are applied in sequence. However, it will be understood that both processes can be incorporated into a single neural network such as a CNN. Further, although both processes 310, 330 are shown to be applied to the 3D image 300, in some embodiments, the processing may be applied directly to the 3D CT imaging data before reconstruction (at 410). Further, in some embodiments, one or both of the processes 310, 330 can be applied on a 2D plane within the 3D CT imaging data set perpendicular to the projection direction used to generate the 2D images described below.

[0054] In some embodiments, the processing can further include identifying (430) at least one physical element within the 3D image. Once the physical element is identified (430), it can be removed or masked (435) from the 3D image. By removing or masking the physical element (435) prior to the generation of the 2D image, such physical elements can be removed from the simulated X-rays generated from the CT imaging data.

[0055] (In 430), the physical element identified may be one or more anatomical elements such as ribs or the heart. By removing such anatomical elements from the simulated X-ray, other anatomical elements of interest to the radiologist viewing the image become more visible, and the simulated X-ray can, for example, display a cross-section of the patient's chest cavity without the interfering ribs.

[0056] Alternatively, (in 430), the physical element identified may be the table 207 or an implant. CT imaging data is typically acquired from a patient lying on a table or other support 207, such as the imaging device 200 described above. In contrast, conventional planar X-rays are often acquired from a standing patient. Thus, by removing the support 207, the simulated X-ray may appear more natural to the radiologist viewing the image. Similarly, removing the implant can provide a better view of the patient's anatomical structure.

[0057] In some embodiments, rather than removing the physical element identified (in 430), the physical element can instead be weighted. Similarly, different sections of the 3D image 300 may be weighted differently.

[0058] Following the processing (420) of the 3D CT imaging data, the method proceeds to generate a 2D image 350 by tracing rays from a simulated radiation source outside the object of the 3D image (440). Such ray tracing processing can be performed, for example, by implementing the Siddon-Jacobs ray tracing algorithm.

[0059] FIG. 5 shows the implementation of a ray tracing process (440) on a 3D image 300 to generate a 2D image 350. The ray tracing process can then proceed by simulating the processing of X-rays (345) 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 may also be via a neural network such as a CNN, in which case the CNN can incorporate one or more of the noise removal, super-resolution, or style conversion processes discussed elsewhere in this specification. Such a neural network can be a generative adversarial network (GAN). In such embodiments, many or all of the steps described herein can be incorporated into a single network, whereby CT volume data is provided to the network and a simulated CXR projection is output.

[0060] In some embodiments, the projection angle or orientation of the ray tracing process (440) can be adjusted to improve the resulting 2D image 350. Similarly, the weighting of physical elements within the 3D image 300 can be adjusted to improve the resulting 2D image 350.

[0061] Once the 2D image 350 is generated, in some embodiments, an optional style conversion process (450) can be applied to apply a style to the 2D image. In such embodiments, the style applied (at 450) can be derived from a plurality of X-ray images (460) such as a conventional planar X-ray image and can also be applied by an AI algorithm 360 such as a CNN. Such a style does not change the morphological content of the underlying image that changes the appearance of the 2D image. Such a process is described in more detail below with reference to FIG. 6 and can be used to generate a second 2D image 370 in the “style” of a conventional X-ray.

[0062] In some embodiments, following the ray tracing process (440), additional processing can be applied to the two-dimensional image (470). Such processing can include noise removal or super-resolution processing applied to the image, and can be performed instead of, or in addition to, the application of such processing to the three-dimensional image.

[0063] Following any processing (470), the two-dimensional image 350 or the style-converted image 370 can be presented (480) to a user, such as a radiologist. Such presentation (480) may include presenting the image as if it were a conventional planar X-ray, or it may include incorporating the two-dimensional image 350 or the style-converted image 370 into a user interface with the three-dimensional image 300. For example, in some embodiments, the two-dimensional image 350 or the style-converted image 370 can be presented to the user together with the three-dimensional image 300 and with indicators incorporated into the three-dimensional image that indicate segments of the three-dimensional image represented within the two-dimensional image. Thus, the two-dimensional image 350 or the style-converted image 370 can be presented as a sectional view of the three-dimensional image 300 with the three-dimensional image contextualizing the section. The two-dimensional image 350 or the style-converted image 370 can then be used as an avatar to guide the reading of the ULDCT image, and AI feedback can be projected onto the two-dimensional image to assist the radiologist in quickly identifying the problem area and scrutinizing and reporting in detail on the original ULDCT image.

[0064] In some embodiments, the three-dimensional CT imaging data can include spectral data. In such embodiments, the simulated X-rays can similarly simulate spectral X-rays. Similarly, the method can be applied to photon-counting or phase-contrast CT data sets and can then be reflected in the resulting two-dimensional images.

[0065] Similarly, although the method is described in the context of CT data, particularly ULDCT data, a similar method can be applied to magnetic resonance (MR) image data by applying MR-CT image conversion and then applying the method steps described subsequently.

[0066] Figures 6A - 6C illustrate an example implementation of style conversion used in the method of the present disclosure. As shown, a set of "style images" such as those shown in Figure 6A can be used to define a particular style of an image. Then, an AI algorithm such as a CNN can be trained to apply the style derived from the "style image" to an input image.

[0067] Thus, when an image such as that shown in Figure 6B is input by an AI algorithm, the image can be re - rendered and output in the style of the "style image" as shown in Figure 6C. In the illustrated example, the style is derived from a particular artist, in this case Paul Klee, and can be applied to a general portrait.

[0068] In the embodiments described herein, the "style image" used to train the AI algorithm may be, for example, a conventional X - ray (CXR) image. In this way, the 2D image 350 generated from the ULDCT 3D image 300 can be converted to look more like a CXR image. Such a style - converted image 370 can then be actually used. Note that the style conversion changes only the appearance of the image without changing its morphological content. Thus, the described style conversion is a conservative technique.

[0069] Many of the method steps described herein can be implemented as AI methods such as CNNs. Such methods can be used with various effect intensities, for example, to enable different noise removal levels or super - resolution levels.

[0070] The method according to the present disclosure can be implemented on a computer as a computer-implemented method, or in dedicated hardware, or in a combination of both. The executable code of the method according to the present disclosure may be stored in 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 can include non-transitory program code stored on a computer-readable medium for executing the method according to the present disclosure when the program product is executed on a computer. In one embodiment, the computer program can include computer program code adapted to execute all steps of the method according to the present disclosure when the computer program is executed on a computer. The computer program can be embodied on a computer-readable medium.

[0071] The present disclosure has been described at some length and in some detail with respect to several described embodiments, but should not be limited to any such details or embodiments or any particular embodiment, and should be construed with reference to the appended claims so as to provide the broadest possible interpretation of the prior art and thus effectively encompass the intended scope of the present disclosure.

[0072] All examples and conditional statements recited herein are for the educational purpose of helping the reader understand the principles of the present disclosure and the concepts contributed by the inventors of this application to advance the art, and should not be construed as limited to such specifically recited examples and conditions. Further, all descriptions in this specification of the principles, aspects, and embodiments of the present disclosure, and of the specific examples thereof listed herein, are intended to encompass both structural and functional equivalents thereof. Moreover, such equivalents are intended to include both currently known equivalents and equivalents developed in the future, i.e., any components developed that perform the same function regardless of structure.

Claims

1. A method for converting 3D computed tomography (CT) data into a 2D image, A step of acquiring 3D CT imaging data, wherein the 3D CT imaging data includes projection data acquired from multiple angles around the central axis. The steps include processing the aforementioned 3D CT imaging data as a 3D image, The steps include generating a two-dimensional image by ray tracing X-rays from a simulated radiation source outside the object of the three-dimensional image, The steps include presenting the two-dimensional image to the user as a simulated X-ray, It has, The two-dimensional image is presented to the user together with the three-dimensional image, and an indicator showing the segments of the three-dimensional image represented in the two-dimensional image is incorporated into the three-dimensional image. method.

2. The method according to claim 1, wherein the step of processing the three-dimensional CT imaging data includes reconstructing the three-dimensional image using a filtered back projection.

3. The method according to claim 2, wherein the three-dimensional CT imaging data includes ultra-low dose CT imaging data, and the step of processing the three-dimensional CT imaging data includes denoising the imaging data.

4. The method according to claim 3, wherein the step of processing the three-dimensional CT imaging data further comprises performing AI-based super-resolution processing.

5. The method according to claim 4, wherein the super-resolution processing includes a blur removal process.

6. The method according to claim 3, wherein 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, wherein a noise reduction process is applied to the three-dimensional CT imaging data before reconstructing the three-dimensional image.

8. The method according to claim 1, further comprising the step of processing the two-dimensional image by applying a style to the two-dimensional image before presenting the two-dimensional image to the user, wherein the style is derived from a plurality of X-ray images, and the style alters the appearance of the two-dimensional image but does not alter the morphological content of the two-dimensional image.

9. The method according to claim 8, wherein the plurality of X-ray images are conventional planar X-ray images.

10. The method according to claim 1, wherein the step of 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, wherein the at least one physical element is an anatomical element.

12. The method according to claim 1, further comprising the step of processing the two-dimensional image before presenting the two-dimensional image to the user, wherein the processing of the two-dimensional image includes applying denoising or super-resolution processing to the two-dimensional image.

13. The method according to claim 1, further comprising the step of performing AI-based noise reduction or super-resolution processing in a 2D plane within the 3D CT imaging data.

14. The method according to claim 1, wherein the three-dimensional CT imaging data has spectral data or photon counting data, and the simulated X-rays are simulated spectral X-rays or photon counting X-rays.

15. The method according to claim 1, wherein the generation of the two-dimensional image is performed by a neural network.

16. A system for converting three-dimensional computed tomography (CT) data into a two-dimensional image, Memory that stores multiple instructions, A processor circuit coupled to the memory and configured to execute the plurality of instructions, The processor circuit has, A step of acquiring 3D CT imaging data, wherein the 3D CT imaging data includes projection data acquired from multiple angles around the central axis. The steps include processing the aforementioned 3D CT imaging data as a 3D image, The steps include generating a two-dimensional image by ray tracing X-rays from a simulated radiation source outside the object of the three-dimensional image, The steps include presenting the two-dimensional image to the user as a simulated X-ray, Configured to perform, The two-dimensional image is presented to the user together with the three-dimensional image, and an indicator showing the segments of the three-dimensional image represented in the two-dimensional image is incorporated into the three-dimensional image. system.

17. A non-temporary computer-readable medium for storing executable instructions, wherein the executable instructions are instructions for performing a method for converting three-dimensional computed tomography (CT) data into a two-dimensional image, the method being: A step of acquiring 3D CT imaging data, wherein the 3D CT imaging data includes projection data acquired from multiple angles around the central axis. The steps include processing the aforementioned 3D CT imaging data as a 3D image, The steps include generating a two-dimensional image by ray tracing X-rays from a simulated radiation source outside the object of the three-dimensional image, The steps include presenting the two-dimensional image to the user as a simulated X-ray, It has, The two-dimensional image is presented to the user together with the three-dimensional image, and an indicator showing the segments of the three-dimensional image represented in the two-dimensional image is incorporated into the three-dimensional image. Non-temporary computer-readable media.

Images