X-ray computed tomography apparatus, information processing system, information processing method, and non-transitory computer readable medium

Abstract

This disclosure relates to an X-ray computed tomography (CT) apparatus, an information processing system, an information processing method, and a non-transient computer-readable medium. The X-ray computed tomography (CT) apparatus includes: an X-ray tube configured to irradiate X-rays; a detector configured to detect X-rays irradiated by the X-ray tube and penetrating a subject; a reconstruction processing unit configured to reconstruct imaging data output from the detector and generate CT image data and material breakdown image data; a first inference unit configured to perform inference on the material breakdown image data; a second inference unit configured to perform inference on the CT image data; a third inference unit configured to perform inference on the composite image data; a selection unit configured to select the inference result of the third inference unit if the inference result of the first inference unit differs from the inference result of the second inference unit; and a display control unit configured to display the selected inference result.

Description

Technical Field

[0001] This disclosure relates to an X-ray computed tomography (CT) apparatus equipped with photon counting CT functionality, an information processing system, an information processing method, and a non-transient computer-readable medium. Background Technology

[0002] An X-ray computed tomography (CT) device equipped with photon-counting CT functionality counts each incident X-ray and measures its energy to obtain an X-ray spectrum. Using this spectrum, the X-ray CT device can identify substances within the examined body and generate decomposition image data. Furthermore, the X-ray CT device equipped with photon-counting CT functionality can reconstruct CT image data (integral image data) (e.g., Japanese Patent Application Laid-Open No. 2018-175866).

[0003] On the other hand, inference tasks performed by neural networks include classification tasks that categorize image data into different types and detection tasks that detect what is captured in which location within the image data.

[0004] The inference results can vary depending on whether the inference task is performed on material decomposition image data obtained from an X-ray CT device equipped with photon counting CT capabilities or on CT image data (integrated image data). Summary of the Invention

[0005] This disclosure is intended to show appropriate inference results.

[0006] An X-ray CT apparatus according to an embodiment of the present disclosure includes: an X-ray tube configured to irradiate X-rays; a detector configured to detect X-rays irradiated by the X-ray tube and penetrating a subject; a reconstruction processing unit configured to reconstruct imaging data output by the detector and generate CT image data and material breakdown image data; a first inference unit configured to perform inference on the material breakdown image data; a second inference unit configured to perform inference on the CT image data; a third inference unit configured to perform inference on synthetic image data composed of the CT image data and the material breakdown image data; a selection unit configured to select the inference result of the third inference unit if the inference result of the first inference unit differs from the inference result of the second inference unit; and a display control unit configured to display the inference result of the selected third inference unit.

[0007] An information processing system according to an embodiment of the present disclosure includes: a first inference unit configured to perform inference on matter decomposition image data, the matter decomposition image data being generated by reconstructing imaging data output by a detector; a second inference unit configured to perform inference on image data, the image data being generated by reconstructing the imaging data output by the detector; a third inference unit configured to perform inference on synthetic image data, the synthetic image data being composed of the image data and the matter decomposition image data; a selection unit configured to select the inference result of the third inference unit when the inference result of the first inference unit differs from the inference result of the second inference unit; and a display control unit configured to display the inference result of the selected third inference unit.

[0008] The information processing method according to embodiments of the present disclosure includes: performing inference on material decomposition image data, the material decomposition image data being generated by reconstructing imaging data output by a detector; performing inference on image data, the image data being generated by reconstructing the imaging data output by the detector; selecting an inference result obtained by performing inference on synthetic image data, the synthetic image data being composed of the image data and the material decomposition image data, when the inference result obtained by performing inference on the material decomposition image data is different from the inference result obtained by performing inference on the image data; and displaying the selected inference result.

[0009] An X-ray CT apparatus according to an embodiment of the present disclosure includes: an X-ray tube configured to irradiate X-rays; a detector configured to detect X-rays irradiated by the X-ray tube and penetrating a subject; a reconstruction processing unit configured to reconstruct imaging data output by the detector and generate CT image data and material breakdown image data; a first inference unit configured to perform inference on the material breakdown image data; a second inference unit configured to perform inference on the CT image data; and a third inference unit configured to perform inference on synthetic image data, the synthetic image data being composed of the CT image data and the material breakdown image data. The system comprises: a decomposed image data component; an image analysis unit configured to analyze the decomposed image data and obtain content information of a predetermined substance or content information of a predetermined lesion included in the decomposed image data; a selection unit configured to select at least one of the inference results of the first inference unit, the inference result of the second inference unit, and the inference result of the third inference unit based on the content information of the predetermined substance or the content information of the predetermined lesion included in the decomposed image data; and a display control unit configured to display the selected inference result.

[0010] An information processing system according to an embodiment of the present disclosure includes: a first inference unit configured to perform inference on substance decomposition image data, the substance decomposition image data being generated by reconstructing imaging data output by a detector; a second inference unit configured to perform inference on image data, the image data being generated by reconstructing the imaging data output by the detector; a third inference unit configured to perform inference on synthetic image data, the synthetic image data being composed of the image data and the substance decomposition image data; an image analysis unit configured to analyze the substance decomposition image data and obtain content information of a predetermined substance included in the substance decomposition image data or content information of a predetermined lesion included in the substance decomposition image data; a selection unit configured to select at least one of the inference result of the first inference unit, the inference result of the second inference unit, and the inference result of the third inference unit based on the content information of the predetermined substance included in the substance decomposition image data or the content information of the predetermined lesion included in the substance decomposition image data; and a display control unit configured to display the selected inference result.

[0011] The information processing method according to embodiments of this disclosure includes: analyzing material decomposition image data and obtaining content information of a predetermined substance or content information of a predetermined lesion included in the material decomposition image data, wherein the material decomposition image data is generated by reconstructing imaging data output by a detector; and performing inference on at least one of the material decomposition image data, image data, and synthetic image data based on the content information of the predetermined substance or the content information of the predetermined lesion included in the material decomposition image data, and displaying the inference result, wherein the synthetic image data is composed of the material decomposition image data and the image data.

[0012] An X-ray CT apparatus according to an embodiment of the present disclosure includes: an X-ray tube configured to irradiate X-rays; a detector configured to detect X-rays irradiated by the X-ray tube and penetrating a subject; a reconstruction processing unit configured to reconstruct imaging data output by the detector and generate CT image data and material breakdown image data; a first inference unit configured to perform inference on the material breakdown image data; a second inference unit configured to perform inference on the CT image data; a third inference unit configured to perform inference on synthetic image data composed of the CT image data and the material breakdown image data; and a selection unit configured to select at least one of the inference result of the first inference unit, the inference result of the second inference unit, and the inference result of the third inference unit according to an examination order.

[0013] An information processing system according to an embodiment of the present disclosure includes: a first inference unit configured to perform inference on material decomposition image data, the material decomposition image data being generated by reconstructing imaging data output by a detector; a second inference unit configured to perform inference on image data, the image data being generated by reconstructing the imaging data output by the detector; a third inference unit configured to perform inference on synthetic image data, the synthetic image data being composed of the image data and the material decomposition image data; a selection unit configured to select at least one of the inference result of the first inference unit, the inference result of the second inference unit, and the inference result of the third inference unit according to a checklist; and a display control unit configured to display the selected inference result.

[0014] The information processing method according to embodiments of the present disclosure includes: generating image data, material breakdown image data, and synthetic image data, wherein the image data and the material breakdown image data are based on X-rays irradiated by an X-ray tube and penetrating a subject, and the synthetic image data is composed of the image data and the material breakdown image data; and performing inference on at least one of the material breakdown image data, the image data, and the synthetic image data composed of the image data and the material breakdown image data according to an examination form, and displaying the inference result.

[0015] Further features of this disclosure will become clear from the following description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0016] Figure 1 This is a diagram illustrating an example configuration of an X-ray computed tomography (CT) apparatus according to an embodiment of the present disclosure.

[0017] Figure 2 This is a diagram illustrating an example of the peripheral configuration of the inference unit of an X-ray CT apparatus according to an embodiment of the present disclosure.

[0018] Figure 3 This is a diagram illustrating a display mode of a display unit in an X-ray CT apparatus according to an embodiment of the present disclosure.

[0019] Figure 4 This is a diagram illustrating a display mode of a display unit in an X-ray CT apparatus according to an embodiment of the present disclosure.

[0020] Figure 5 This is a flowchart illustrating an example operation of an X-ray CT apparatus according to an embodiment of the present disclosure.

[0021] Figure 6 This is a diagram illustrating an example of the peripheral configuration of the inference unit of an X-ray CT apparatus according to an embodiment of the present disclosure.

[0022] Figure 7 This is a flowchart illustrating an example operation of an X-ray CT apparatus according to an embodiment of the present disclosure. Detailed Implementation

[0023] In the following description, a non-transient computer-readable medium for X-ray computed tomography (CT) apparatus, information processing system, information processing method, and stored program according to embodiments will be described with reference to the accompanying drawings. Parts indicated by the same reference numerals perform similar operations, and repeated descriptions will be omitted as appropriate. Embodiments will be described below with reference to the accompanying drawings.

[0024] Reference Figures 1 to 5A first embodiment of this disclosure will be described. Reference will be made to... Figure 1 An example configuration of an X-ray CT apparatus according to a first embodiment is described. Figure 1 The X-ray CT apparatus 1 shown includes a platform device (stand) 10, a bed device 30, and a control console device 40. In an embodiment, the rotation axis direction of the rotating frame 13 in a non-tilted state or the longitudinal direction of the top plate 33 of the bed device 30 is defined as the Z-axis direction, the axis direction orthogonal to the Z-axis direction and horizontal to the ground is defined as the X-axis direction, and the axis direction orthogonal to the Z-axis direction and perpendicular to the ground is defined as the Y-axis direction.

[0025] For example, platform device 10 and bed device 30 are installed in a CT examination room, and console device 40 is installed in a control room adjacent to the CT examination room. Console device 40 does not necessarily need to be installed in a control room. For example, console device 40 can be installed in a room where platform device 10 and bed device 30 are installed. In any case, platform device 10, bed device 30, and console device 40 are connected to each other via wired or wireless means to enable communication.

[0026] Platform device 10 is a scanning device configured to perform X-ray CT imaging on a subject P. Platform device 10 includes an X-ray tube 11, a detector 12, a rotating frame 13, an X-ray high-voltage device 14, a control device 15, a wedge 16, a collimator 17, and a data acquisition device 18 (hereinafter also referred to as a data acquisition system (DAS)).

[0027] For ease of description, only a portion of the configuration is shown here.

[0028] X-ray tube 11 is a vacuum tube that generates X-rays by irradiating thermionic electrons from the cathode (filament) toward the anode (target) with a high voltage applied from X-ray high-voltage device 14 and a filament current supplied. Specifically, the X-rays are generated as a result of thermionic electrons colliding with the target. For example, X-ray tube 11 could be a rotating anode X-ray tube that generates X-rays by irradiating thermionic electrons toward a rotating anode. The X-rays generated by X-ray tube 11 are shaped into a cone shape via, for example, collimator 17 and irradiated onto the subject P. X-ray tube 11 is an example of an X-ray generating unit.

[0029] Detector 12 detects X-rays irradiated by X-ray tube 11 and penetrating the subject P, and outputs a signal corresponding to the X-ray dose to DAS 18. Detector 12 includes, for example, multiple rows of X-ray detection elements, in each of these rows arranged along an arc in the channel direction centered on the focal point of X-ray tube 11. Detector 12 has, for example, a row structure in which the multiple rows of X-ray detection elements are arranged in the slice direction (row direction), and in each of these rows, multiple X-ray detection elements are arranged in the channel direction. Detector 12 is a photon counting detector. The reconstruction processing unit can reconstruct CT image data (integrated image data) with a high S / N ratio by counting the number of photons of X-rays penetrating the subject P using the photon counting detector.

[0030] Depending on the method used to perform measurements on the converted signal for the DAS18, the detector 12 can be classified as either an energy integration function or a photon counting function. The energy integration function integrates the energy of X-rays penetrating the subject P over a given time period, thereby measuring the total energy of the X-rays passing through during that time period. The photon counting function measures the number of X-ray photons included in the X-rays penetrating the subject P for each of multiple energy bands (also called energy intervals or simply intervals). This allows for the performance of matter decomposition based on the imaging data obtained for each energy band. Here, the imaging mode that performs matter decomposition is called the matter decomposition mode (matter decomposition image mode), and the imaging mode that does not perform matter decomposition is called the non-matter decomposition mode (integration image mode).

[0031] The rotating frame 13 supports the X-ray generating unit and the X-ray detection unit so that they can rotate about the rotation axis Z. Specifically, the rotating frame 13 is an annular frame that supports the X-ray tube 11 and the detector 12 so that they are opposite each other and rotated by the control device 15. The rotating frame 13 is rotatably supported by a fixed frame (not shown) made of a metal such as aluminum. Specifically, the rotating frame 13 is connected to the edge portion of the fixed frame via bearings. The rotating frame 13 receives power from the drive mechanism of the control device 15 and rotates about the rotation axis Z at a constant angular velocity.

[0032] In addition to the X-ray tube 11 and detector 12, the rotating frame 13 also includes and supports the X-ray high-voltage device 14 and the DAS 18. The rotating frame 13 is housed in a generally cylindrical housing having an opening (hole) 19 that serves as an imaging space. The opening 19 is substantially aligned with the field of view (FOV). The central axis of the opening 19 is aligned with the rotation axis Z of the rotating frame 13. Imaging data generated by the DAS 18 is transmitted, for example via optical communication, from a transmitter including a light-emitting diode (LED) to a receiver including a photodiode (not shown) provided in the non-rotating part (fixed frame) of the platform device 10, and then to the console device 40. The method of transmitting imaging data from the rotating frame 13 to the non-rotating part of the platform device 10 is not limited to optical communication, and any non-contact data transmission method may be used.

[0033] The X-ray high-voltage device 14 includes circuitry such as a transformer and rectifier, a high-voltage generator having the function of generating a high voltage to be applied to the X-ray tube 11 and a filament current to be supplied to the X-ray tube 11, and an X-ray controller that controls the output voltage according to the X-rays irradiated by the X-ray tube 11. The high-voltage generator can be a transformer solution or an inverter solution. The X-ray high-voltage device 14 can be provided in the rotating frame 13 or on the fixed frame side of the platform device 10.

[0034] The control device 15 includes processing circuitry such as a central processing unit (CPU) and a drive mechanism such as a motor or actuator. As hardware resources, the processing circuitry includes a processor such as a CPU or microprocessor unit (MPU) and a memory such as read-only memory (ROM) or random access memory (RAM). The control device 15 can be implemented using an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), another complex programmable logic device (CPLD), or a simple programmable logic device (SPLD). The control device 15 controls the X-ray high-voltage equipment 14, DAS 18, etc., according to instructions from the console device 40. The processor implements the above control by reading and executing programs stored in memory.

[0035] The wedge 16 is a filter used to adjust the dose of X-rays irradiated by the X-ray tube 11.

[0036] Specifically, the wedge 16 is a filter that allows X-rays irradiated by the X-ray tube 11 to pass through and attenuate, resulting in a predetermined distribution of X-rays irradiated from the X-ray tube 11 onto the subject P. For example, the wedge 16 (wedge filter or bowtie filter) is a filter obtained by treating aluminum to have a predetermined target angle and a predetermined thickness.

[0037] Collimator 17 is a lead plate or the like used to limit the irradiation range of X-rays penetrating the wedge 16, and has a slit depending on the combination of multiple lead plates or the like. Collimator 17 can be referred to as X-ray aperture.

[0038] The DAS18 generates digital data (also called imaging data) for each of multiple energy bands, indicating the count values ​​of X-ray photons detected by detector 12. The imaging data is a dataset of count values ​​identified by the channel number, row number, view number indicating the acquired view (projection angle), and energy band number of the X-ray detection element that serves as the generation source. The DAS18 is implemented, for example, by an application-specific integrated circuit (ASIC) having circuitry capable of generating imaging data. The imaging data is transmitted to console device 40.

[0039] The bed device 30 is a device on which the subject P to be scanned is placed and moved, and includes a base 31, a bed drive device 32, a top plate 33, and a support frame 34. The base 31 is a housing that supports the support frame 34 so that it can move in the vertical direction.

[0040] The bed drive device 32 is a motor or actuator that moves the top plate 33, on which the subject P is placed, in the longitudinal direction of the top plate 33. The bed drive device 32 moves the top plate 33 under the control of the console device 40 or the control device 15. For example, the bed drive device 32 moves the top plate 33 in a direction orthogonal to the subject P, such that the body axis of the subject P placed on the top plate 33 is aligned with the central axis of the opening of the rotating frame 13. The bed drive device 32 can move the top plate 33 in the direction of the body axis of the subject P according to X-ray CT imaging performed using the platform device 10. The bed drive device 32 generates power by being driven at a rotational speed corresponding to the duty cycle, etc., of the drive signal from the control device 15. The bed drive device 32 is implemented, for example, by a motor such as a direct drive motor or a servo motor.

[0041] The top plate 33 provided on the upper surface of the support frame 34 is the plate on which the subject P is to be placed. In addition to the top plate 33, the bed drive device 32 can also move the support frame 34 in the longitudinal direction of the top plate 33.

[0042] The console device 40 includes a memory 41, a display unit 42, an operation unit 43, and a processing circuit 44. Data communication between the memory 41, the display unit 42, the operation unit 43, and the processing circuit 44 is performed via a bus. Although the console device 40 is described as a separate entity from the platform device 10, the console device 40 or some of its constituent elements may be included in the platform device 10.

[0043] Memory 41 is a storage device that stores various types of information, such as hard disk drives (HDDs), solid-state drives (SSDs), or integrated circuit storage devices.

[0044] Memory 41 stores, for example, imaging data and reconstructed image data. Memory 41 is not limited to HDD or SSD, but can be a drive device that reads and writes various information from and to portable storage media such as CDs, DVDs, or flash memory, or semiconductor storage elements such as random access memory (RAM). The storage area of ​​memory 41 can be located within the X-ray CT apparatus 1 or in an external storage device connected via a network. For example, memory 41 stores CT images and data for displaying those images. Memory 41 also stores control programs according to an embodiment.

[0045] Display unit 42 displays various information. For example, display unit 42 outputs medical images (CT images) generated by processing circuit 44 and a graphical user interface (GUI) for receiving various operations from the operator. As display unit 42, for example, a liquid crystal display (LCD) unit, a cathode ray tube (CRT) display unit, an organic electroluminescent display (OELD) unit, a plasma display unit, or any other display unit can be appropriately used. Display unit 42 can be provided in platform device 10. Display unit 42 can be desktop type or can be composed of a tablet terminal or the like capable of wireless communication with the main body of console device 40.

[0046] The operation unit 43 receives various input operations from the operator, converts the received input operations into electrical signals, and outputs the electrical signals to the processing circuit 44. For example, the operation unit 43 receives from the operator acquisition conditions for acquiring imaging data, reconstruction conditions for reconstructing CT images, and image processing conditions for generating post-processed images from the CT images. As the operation unit 43, for example, a mouse, keyboard, trackball, switch, button, joystick, touchpad, or touch panel display unit can be appropriately used. In embodiments, the operation unit 43 is not limited to units including physical operation components such as a mouse, keyboard, trackball, switch, button, joystick, touchpad, or touch panel display unit. For example, in an example of the operation unit 43, an electrical signal processing circuit is also included, which receives electrical signals corresponding to the input operations from an external input device provided separately from the device and outputs the electrical signals to the processing circuit 44. The operation unit 43 can be provided in the platform device 10. The operation unit 43 can be composed of a tablet terminal or the like capable of wirelessly communicating with the main body of the console device 40.

[0047] The processing circuit 44 controls the operation of the entire X-ray CT apparatus 1 based on the electrical signals of the input operation output from the operation unit 43. For example, as hardware resources, the processing circuit 44 includes a processor such as a CPU, MPU, or graphics processing unit (GPU) and a memory such as ROM or RAM. The processing circuit 44 implements the control unit 441, reconstruction processing unit 442, image analysis unit 443, inference unit 444, selection unit 445, and display control unit 446 by executing programs loaded in the memory. Each function (control unit 441, reconstruction processing unit 442, image analysis unit 443, inference unit 444, selection unit 445, and display control unit 446) is not necessarily implemented by a single processing circuit. Multiple independent processors can be combined to form a processing circuit, and each processor can execute programs to implement its respective function.

[0048] The control unit 441 operates the control processing circuit 44 according to the input received from the operator via the operation unit 43. Specifically, the control unit 441 reads the control program stored in the memory 41, loads the control program into the memory in the processing circuit 44, and controls each unit of the X-ray CT apparatus 1 according to the loaded control program. The control unit 441 performs preprocessing on the imaging data output from the DAS 18, such as logarithmic transformation processing, offset correction processing, inter-channel sensitivity correction processing, or beam hardening correction, thereby generating preprocessed imaging data.

[0049] The reconstruction processing unit 442 has the function of generating CT image data based on the imaging data output by the detector 12 (DAS18). The reconstruction processing unit 442 reconstructs the CT image data by, for example, performing backprojection processing on the imaging data stored in the memory 41. The backprojection processing can be, for example, a backprojection processing based on the filtered backprojection (FBP) method. The reconstruction processing unit 442 can perform the reconstruction processing by, for example, using successive approximations. The reconstruction processing unit 442 generates CT image data by performing various image processing on the CT image data. The reconstruction processing unit 442 stores the reconstructed CT image data and the CT image data generated by the various image processing in the memory 41.

[0050] The reconstruction processing unit 442 calculates energy integral data by using the sum of the counts (total value) of each energy range or the sum of the product of the representative value of the energy range and the count (which is a signal obtained by the photon counting detector 12). The reconstruction processing unit 442 is able to reconstruct CT image data (integrated image data) by using the energy integral data.

[0051] As an application of the photon-counting X-ray CT apparatus 1, there exists a technique for determining the type, quantity, density, etc., of substances included in a subject P by utilizing the fact that each substance has different X-ray absorption characteristics. This is called substance decomposition. For example, the reconstruction processing unit 442 is capable of performing substance decomposition on imaging data and acquiring substance decomposition information. The reconstruction processing unit 442 is also capable of reconstructing substance decomposition image data indicating substance decomposition using the substance decomposition information as a result of substance decomposition.

[0052] For example, the imaging data generated from the counting results obtained by the photon-counting X-ray CT apparatus 1 includes information about the energy spectrum of X-rays that attenuate as a result of penetrating the subject P. Therefore, the reconstruction processing unit 442 is able to reconstruct material decomposition image data, for example, obtained by imaging specific energy components.

[0053] Image analysis unit 443 analyzes material decomposition image data. By analyzing the material decomposition image data, image analysis unit 443 can obtain the amount of predetermined material included in the material decomposition image data, or the amount of predetermined lesions included in the material decomposition image data.

[0054] The inference unit 444 is capable of performing inference on material decomposition image data. The inference unit 444 is also capable of performing inference on CT image data (integral image data). Furthermore, the inference unit 444 is capable of performing inference on synthetic image data composed of material decomposition image data and CT image data (integral image data). Therefore, the inference unit 444 is capable of performing inference on each of the material decomposition image data, the CT image data, and the synthetic image data composed of the material decomposition image data and the CT image data.

[0055] Specifically, such as Figure 2 As shown, the inference unit 444 includes a first inference unit 450, a second inference unit 451, and a third inference unit 452. The first inference unit 450 performs inference on the material decomposition image data using a neural network. The second inference unit 451 performs inference on the CT image data using a neural network. The third inference unit 452 performs inference on the composite image data composed of the material decomposition image data and the CT image data using a neural network.

[0056] The first inference unit 450 obtains teaching data in advance. The teaching data is determined based on the inference task or classification objective performed by the neural network.

[0057] Examples of inference tasks performed by neural networks include classification tasks that categorize substances in decomposed image data, detection tasks that identify which substance is present in which location within the decomposed image data, and segmentation tasks that extract target regions from the decomposed image data. The decomposed image data used as teaching data is different from CT image data (integral image data).

[0058] When training a neural network to perform a classification task, the first inference unit 450 obtains teaching data including a pair of material breakdown image data and a correct answer label, which is a label indicating the target material present in the material breakdown image data.

[0059] On the other hand, when training the neural network to perform the detection task, the first inference unit 450 obtains teaching data on the material decomposition image data, including a pair of regions of interest (ROIs) and a correct answer image with a correct answer label. The regions of interest (ROIs) indicate the location of the target material present in the material decomposition image data, and the correct answer label is a label indicating the target.

[0060] When training the neural network to perform the segmentation task, the first inference unit 450 obtains a pair of teaching data for the material decomposition image data, which includes the positional information of the pixels of the target material and the correct answer image with the correct answer label, the target material being present in the material decomposition image data, and the correct answer label being a label indicating the target material.

[0061] Similarly, the second inference unit 451 receives teaching data in advance. The teaching data is determined based on the inference task or classification objective performed by the neural network.

[0062] Examples of inference tasks performed by neural networks include classification tasks that categorize CT image data (integral image data), detection tasks that detect which element exists in which location within CT image data, and segmentation tasks that extract target regions from CT image data.

[0063] When training a neural network to perform a classification task, the second inference unit 451 obtains teaching data including a pair of CT image data and a correct answer label, which is a label indicating a target present in the CT image data.

[0064] On the other hand, when training the neural network that performs the detection task, the second inference unit 451 obtains teaching data on the CT image data, including a pair of regions of interest (ROIs) and a correct answer image with a correct answer label. The regions of interest (ROIs) indicate the location of the target in the CT image data, and the correct answer label is a label indicating the target.

[0065] When training the neural network to perform the segmentation task, the second inference unit 451 obtains teaching data from CT image data, including the positional information of a pair of target pixels and a correct answer image with a correct answer label, the target being present in the CT image data, and the correct answer label being a label indicating the target.

[0066] An image combining unit 447 is included in the processing circuit 44. The image combining unit 447 combines material decomposition image data and CT image data (integrated image data). Specifically, the image combining unit 447 performs registration of the material decomposition image data and CT image data based on characteristic portions of the material decomposition image data and CT image data, thereby combining the material decomposition image data and CT image data. Registration of the material decomposition image data and CT image data can be performed for each slice.

[0067] The third inference unit 452, which performs inference on synthetic image data composed of material decomposition image data and CT image data (integrated image data), obtains teaching data in advance. The teaching data is determined based on the inference task or classification objective performed by the neural network.

[0068] Examples of inference tasks performed by neural networks include classification tasks that categorize synthetic image data consisting of material breakdown image data and CT image data (integral image data), detection tasks that detect which exists in which location within synthetic image data, and segmentation tasks that extract target regions from synthetic image data.

[0069] When training a neural network to perform a classification task, the third inference unit 452 obtains teaching data including a pair of synthetic image data and correct answer labels. The synthetic image data consists of material decomposition image data and CT image data (integral image data), and the correct answer labels are labels indicating the targets present in the synthetic image data.

[0070] On the other hand, when training the neural network that performs the detection task, the third inference unit 452 obtains teaching data for the synthetic image data composed of material decomposition image data and CT image data (integral image data), including a pair of regions of interest (ROIs) and a correct answer image with a correct answer label. The regions of interest (ROIs) indicate the location of the target present in the synthetic image data, and the correct answer label is a label indicating the target.

[0071] When training the neural network to perform the segmentation task, the third inference unit 452 obtains teaching data from the synthetic image data composed of material decomposition image data and CT image data (integrated image data), including the positional information of a pair of target pixels and a correct answer image with a correct answer label, the target being present in the synthetic image data, and the correct answer label being a label indicating the target.

[0072] Selection unit 445 selects at least one of the following: the inference result of a first inference unit 450 that performs inference on material decomposition image data, the inference result of a second inference unit 451 that performs inference on CT image data (integral image data), and the inference result of a third inference unit 452 that performs inference on synthetic image data composed of material decomposition image data and CT image data (integral image data).

[0073] That is, the selection unit 445 can select which of the following should be displayed on the display unit 42: the inference result of the first inference unit 450 that performs inference on the material decomposition image data, the inference result of the second inference unit 451 that performs inference on the CT image data (integral image data), and the inference result of the third inference unit 452 that performs inference on the composite image data composed of the material decomposition image data and the CT image data (integral image data).

[0074] Selection unit 445 can also select at least one of the inference results of first inference unit 450, second inference unit 451, and third inference unit 452 based on the examination form. Specifically, if the examination form includes an examination of the breast (calcification examination), selection unit 445 selects the inference result of third inference unit 452, which performs inference on synthetic image data composed of material breakdown image data including calcium information and CT image data (integrated image data). Alternatively, selection unit 445 can select the inference result of first inference unit 450, which performs inference on material breakdown image data including calcium information.

[0075] When the examination form includes an examination using contrast agents (iodine test), selection unit 445 selects the inference result of third inference unit 452, which performs inference on synthetic image data composed of material decomposition image data including iodine information and CT image data (integrated image data). Alternatively, selection unit 445 may select the inference result of first inference unit 450, which performs inference on material decomposition image data including iodine information. Furthermore, when the examination form includes an examination regarding the presence / absence of metal (stent) (metal test), selection unit 445 selects the inference result of third inference unit 452, which performs inference on synthetic image data composed of material decomposition image data including metal (stent) information and CT image data (integrated image data). Alternatively, selection unit 445 may select the inference result of first inference unit 450, which performs inference on material decomposition image data including metal (stent) information.

[0076] That is, when the examination form includes a predetermined first examination (calcification examination, iodine examination, metal examination, etc.), the selection unit 445 selects the inference result of the third inference unit 452, which performs inference on the synthetic image data composed of material decomposition image data and CT image data (integrated image data). Alternatively, the selection unit 445 can select the inference result of the first inference unit 450, which performs inference on the material decomposition image data.

[0077] The synthetic image data, composed of material decomposition image data and CT image data, has a larger information content than the material decomposition image data. Therefore, the selection unit 445 selects the inference result of the third inference unit 452, which performs inference on the synthetic image data (integrated image data), over the inference result of the first inference unit 450.

[0078] If the examination order does not include a predetermined first examination, the selection unit 445 selects the inference result of the second inference unit 451 that performs inference on the CT image data (integrated image data). If the examination order includes, for example, an examination about nodules, the selection unit 445 selects the inference result of the second inference unit 451 that performs inference on the CT image data (integrated image data). If the examination order includes an examination that cannot be performed using only material decomposition image data, the selection unit 445 selects the inference result of the second inference unit 451 that performs inference on the CT image data (integrated image data).

[0079] When the examination form includes a predetermined second examination (an examination related to breast cancer (calcification examination and tumor examination)), the inference results of the first inference unit 450, which performs inference on material breakdown image data including calcium information, and the inference results of the second inference unit 451, which performs inference on CT image data (integral image data), are necessary. The second examination differs from the first examination. Therefore, the selection unit 445 selects both the inference results of the first inference unit 450, which performs inference on material breakdown image data including calcium information, and the inference results of the second inference unit 451, which performs inference on CT image data (integral image data).

[0080] The display control unit 446 controls the display unit 42 to display information about the progress status or processing results of each function or process of the processing circuit 44. The display control unit 446 causes the display unit 42 to display the inference result selected by the selection unit 445.

[0081] Figure 3The illustration shows a display mode of the display unit 42 in an X-ray CT apparatus 1 according to an embodiment of the present disclosure. In response to the inference result of a third inference unit 452 performing inference on synthetic image data composed of material decomposition image data and CT image data (integrated image data), a selection unit 445 selects, as shown... Figure 3 As shown, composite image data 300, consisting of material decomposition image data and CT image data, is displayed on display unit 42. Display unit 42 can display material decomposition image data.

[0082] Display unit 42 displays composite image data 300 composed of material decomposition image data and CT image data (integrated image data). Display unit 42 displays images obtained by combining corresponding slice images of material decomposition image data and CT image data.

[0083] In response to the third inference unit 452 detecting a predetermined substance (calcium, iodine, metal, etc.) in the composite image data 300 composed of substance decomposition image data and CT image data (integrated image data), region information 302 and substance name information 304 regarding the predetermined substance are displayed. The operator can identify which substance is present at which location from the region information 302 and substance name information 304 regarding the predetermined substance. In response to the third inference unit 452 detecting a predetermined lesion in the composite image data 300 composed of substance decomposition image data and CT image data (integrated image data), the display control unit 446 causes the display unit 42 to display region information 305 and lesion name information 307 regarding the lesion.

[0084] The display control unit 446 can also enable the display unit 42 to display information 306 indicating that the third inference unit 452 has performed inference on the composite image data 300 composed of material decomposition image data and CT image data (integrated image data). The operator can identify that the composite image data 300 composed of material decomposition image data and CT image data (integrated image data) has been used to infer region information 302 and substance name information 304 regarding a predetermined substance. Therefore, the operator can identify which substance exists in which location. The operator can also identify that the composite image data 300 composed of material decomposition image data and CT image data (integrated image data) has been used to infer region information 305 and lesion name information 307 regarding a lesion. Therefore, the operator can identify which lesion exists in which location.

[0085] When the inference result of the first inference unit 450, which performs inference on material decomposition image data, differs from the inference result of the second inference unit 451, which performs inference on CT image data (integrated image data), the display control unit 446 can enable the display unit 42 to display information indicating that the inference results are different from each other.

[0086] When the inference result of the first inference unit 450 performing the classification task differs from the inference result of the second inference unit 451 performing the classification task, the display control unit 446 can cause the display unit 42 to display classification information indicating that the inference results are different. When the inference result of the first inference unit 450 performing the detection task differs from the inference result of the second inference unit 451 performing the detection task, the display control unit 446 can cause the display unit 42 to display detection information (region information) indicating that the inference results are different.

[0087] Figure 4 The illustration shows a display mode of the display unit 42 in an X-ray CT apparatus 1 according to an embodiment of the present disclosure. In response to the inference result of the second inference unit 451 performing inference on CT image data (integrated image data) being selected by the selection unit 445, as... Figure 4 As shown, CT image data 301 is displayed on display unit 42.

[0088] Display unit 42 displays CT image data 301. CT image data 301 is a slice image of three-dimensional volume data. In response to the second inference unit 451 detecting a predetermined lesion (nodule, tumor, etc.) in the CT image data 301, display control unit 446 causes display unit 42 to display region information 308 and lesion name information 310 regarding the predetermined lesion. The operator can identify which lesion exists in which location from the region information 308 and lesion name information 310 regarding the predetermined lesion.

[0089] The display control unit 446 can also enable the display unit 42 to display information 312 indicating that the second inference unit 451 has performed inference on the CT image data 301. The operator can recognize that the CT image data 301 has been used for inference.

[0090] Although console device 40 has been described as a device that performs multiple functions by a single console, the multiple functions can be performed by different consoles.

[0091] When the inference result of the first inference unit 450, which performs inference on material decomposition image data, differs from the inference result of the second inference unit 451, which performs inference on CT image data (integrated image data), the display control unit 446 can cause the display unit 42 to display information indicating that the inference results are different from each other. When the inference result of the first inference unit 450 differs from the inference result of the second inference unit 451, the display control unit 446 can cause the display unit 42 to display classification information or detection information (region information) indicating that the inference results are different from each other.

[0092] Next, the operation of the X-ray CT apparatus 1 according to an embodiment of the present disclosure will be described. Figure 5 This is a flowchart illustrating an example operation of the X-ray CT apparatus 1.

[0093] S100: Perform a scan to perform X-ray CT imaging on the subject P. X-ray CT imaging is performed, wherein X-rays are generated by X-ray tube 11, and X-ray tube 11 and detector 12 rotate about rotation axis Z (subject P).

[0094] S102: Detector 12 detects X-rays that penetrate the subject P and obtains imaging data as a signal about the subject P. The imaging data is obtained by bundling multiple detection data from a predetermined number of detection elements in a spatial unit. The imaging data generated from the counting results obtained by detector 12 includes information about the energy of the X-rays that attenuate as a result of penetrating the subject P.

[0095] S104: The reconstruction processing unit 442 generates CT image data (integrated image data) based on the imaging data output by the detector 12. The reconstruction processing unit 442 is capable of reconstructing image data, for example, specific energy components.

[0096] S106: The reconstruction processing unit 442 performs material decomposition on the imaging data output by the detector 12, and reconstructs the material decomposition image data using the results of the material decomposition. The reconstruction processing unit 442 generates the material decomposition image data.

[0097] S108: Image combination unit 447 combines material decomposition image data and CT image data (integrated image data). Specifically, image combination unit 447 performs registration of material decomposition image data and CT image data based on feature portions of material decomposition image data and CT image data, and combines material decomposition image data and CT image data.

[0098] S110: The first inference unit 450 performs inference on the material decomposition image data and obtains the inference result. The second inference unit 451 performs inference on the CT image data (integral image data) and obtains the inference result. The third inference unit 452 performs inference on the composite image data composed of the material decomposition image data and the CT image data (integral image data) and obtains the inference result.

[0099] S112: Selection unit 445 selects at least one of the following: the inference result of the first inference unit 450 that performs inference on the material decomposition image data, the inference result of the second inference unit 451 that performs inference on the CT image data (integral image data), and the inference result of the third inference unit 452 that performs inference on the composite image data composed of the material decomposition image data and the CT image data (integral image data).

[0100] S114: Selection unit 445 outputs the selected inference result to display control unit 446. Display control unit 446 causes display unit 42 to display the inference result of third inference unit 452 and the composite image data 300 composed of material decomposition image data and CT image data (integrated image data), such as... Figure 3 As shown in the image.

[0101] If the inference result of the third inference unit 452 includes a predetermined substance (calcium, iodine, metal, etc.), the display control unit 446 causes the display unit 42 to display area information 302 and substance name information 304 related to the predetermined substance. If the inference result of the third inference unit 452 includes a lesion, the display control unit 446 causes the display unit 42 to display area information 305 and lesion name information 307 related to the lesion.

[0102] Selection unit 445 can select both the inference result of the first inference unit 450 that performs inference on the material decomposition image data and the inference result of the second inference unit 451 that performs inference on the CT image data (integrated image data). In this case, selection unit 445 outputs the inference result of the first inference unit 450 and the inference result of the second inference unit 451 to display control unit 446. Display control unit 446 enables display unit 42 to display the composite image data composed of material decomposition image data and CT image data, the inference result of the first inference unit 450, and the inference result of the second inference unit 451 on the same screen.

[0103] The inference result of the second inference unit 451 can be output to the display control unit 446. The display control unit 446 causes the display unit 42 to display the inference result of the second inference unit 451 and the CT image data 301, such as... Figure 4 As shown in the diagram, the display control unit 446 enables the display unit 42 to display CT image data 301 and the inference results of the second inference unit 451 on the same screen. If the inference results of the second inference unit 451 include a lesion, the display control unit 446 causes the display unit 42 to display area information 308 and lesion name information 310 related to the lesion.

[0104] As described above, the inference unit 444 includes a first inference unit 450 that performs inference on material decomposition image data using a neural network, a second inference unit 451 that performs inference on CT image data using a neural network, and a third inference unit 452 that performs inference on synthetic image data composed of material decomposition image data and CT image data (integrated image data).

[0105] If the inference result obtained by performing inference on synthetic image data composed of material decomposition image data and CT image data (integrated image data), or on material decomposition image data, includes information about a specific material, the selection unit 445 selects the inference result obtained by performing inference on synthetic image data composed of material decomposition image data and CT image data (integrated image data), or on material decomposition image data. If the inference result obtained by performing inference on CT image data (integrated image data) includes information about a specific lesion, the selection unit 445 selects the inference result obtained by performing inference on CT image data (integrated image data).

[0106] If the inference result obtained by performing inference on the material decomposition image data includes information about a specific substance and the inference result obtained by performing inference on the CT image data (integral image data) includes information about a specific lesion, the selection unit 445 selects the inference result obtained by performing inference on the material decomposition image data and the inference result obtained by performing inference on the CT image data (integral image data).

[0107] like Figure 5 As shown, in S110, the first inference unit 450 performs inference on the material decomposition image data and obtains an inference result. The second inference unit 451 performs inference on the CT image data (integral image data) and obtains an inference result. The third inference unit 452 performs inference on the composite image data composed of the material decomposition image data and the CT image data (integral image data) and obtains an inference result.

[0108] The control unit 441 is capable of comparing the inference results of the first inference unit 450 obtained by performing inference on material decomposition image data, the inference results of the second inference unit 451 obtained by performing inference on CT image data (integral image data), and the inference results of the third inference unit 452 obtained by performing inference on synthetic image data composed of material decomposition image data and CT image data (integral image data) with each other, calculating comparison information of the inference results, and displaying the comparison information. The comparison information of the inference results indicates whether the inference results of the first inference unit 450 obtained by performing inference on material decomposition image data, the inference results of the second inference unit 451 obtained by performing inference on CT image data (integral image data), and the inference results of the third inference unit 452 obtained by performing inference on synthetic image data composed of material decomposition image data and CT image data (integral image data) match each other.

[0109] For example, if the inference result of the first inference unit 450 obtained by performing inference on material decomposition image data matches the inference result of the second inference unit 451 obtained by performing inference on CT image data (integral image data), the selection unit 445 selects either the inference result of the first inference unit 450 obtained by performing inference on material decomposition image data or the inference result of the second inference unit 451 obtained by performing inference on CT image data (integral image data). The display control unit 446 can cause the display unit 42 to display information indicating that the inference result of the first inference unit 450 obtained by performing inference on material decomposition image data matches the inference result of the second inference unit 451 obtained by performing inference on CT image data (integral image data).

[0110] If the inference result of the first inference unit 450 obtained by performing inference on the material decomposition image data differs from the inference result of the second inference unit 451 obtained by performing inference on the CT image data (integral image data), there is a possibility that the material decomposition affects the inference result. Therefore, the selection unit 445 selects the inference result of the third inference unit 452 obtained by performing inference on the composite image data composed of the material decomposition image data and the CT image data (integral image data). The display control unit 446 causes the display unit 42 to display the inference result of the third inference unit 452 obtained by performing inference on the composite image data composed of the material decomposition image data and the CT image data (integral image data), as well as the composite image data 300, such as... Figure 3 As shown in the image.

[0111] If the inference result of the first inference unit 450 obtained by performing inference on the material decomposition image data differs from the inference result of the second inference unit 451 obtained by performing inference on the CT image data (integral image data), the selection unit 445 can select either the inference result of the first inference unit 450 obtained by performing inference on the material decomposition image data or the inference result of the second inference unit 451 obtained by performing inference on the CT image data (integral image data). The display control unit 446 can cause the display unit 42 to display information indicating that the inference result of the first inference unit 450 obtained by performing inference on the material decomposition image data differs from the inference result of the second inference unit 451 obtained by performing inference on the CT image data (integral image data).

[0112] The display control unit 446 can perform emphasis display on areas where the inference result of the first inference unit 450 obtained by inference from material decomposition image data differs from the inference result of the second inference unit 451 obtained by inference from CT image data (integral image data). Emphasis display includes methods such as box display and highlighting. The display control unit 446 is capable of performing display such that areas where the inference result of the first inference unit 450 obtained by inference from material decomposition image data differs from the inference result of the second inference unit 451 obtained by inference from CT image data (integral image data) can be distinguished.

[0113] The display control unit 446 enables the display unit 42 to display, on the composite image data composed of material decomposition image data and CT image data (integrated image data), the inference results of the first inference unit 450 obtained by performing inference on the material decomposition image data and the inference results of the second inference unit 451 obtained by performing inference on the CT image data (integrated image data). The operator can identify which detection information differs from each inference result (detection information).

[0114] As described above, the X-ray CT apparatus according to this embodiment includes: an X-ray tube 11 configured to irradiate X-rays; a detector 12 configured to detect X-rays irradiated by the X-ray tube 11 and penetrating the subject; a reconstruction processing unit 442 configured to reconstruct the imaging data output by the detector 12 and generate CT image data and material breakdown image data; a first inference unit 450 configured to perform inference on the material breakdown image data; a second inference unit 451 configured to perform inference on the CT image data; a third inference unit 452 configured to perform inference on composite image data composed of CT image data and material breakdown image data; a selection unit 445 configured to select the inference result of the third inference unit 452 when the inference result of the first inference unit 450 is different from the inference result of the second inference unit 451; and a display control unit 446 configured to display the inference result of the selected third inference unit 452. If the inference result of the first inference unit 450 is the same as the inference result of the second inference unit 451, the display control unit 446 displays either the inference result of the first inference unit 450 or the inference result of the second inference unit 451.

[0115] Therefore, the X-ray CT apparatus according to this embodiment can display appropriate inference results based on the status of multiple inference results.

[0116] The detector does not necessarily have to be from an X-ray CT device. A detector from an X-ray imaging device can be used.

[0117] The information processing system according to this embodiment includes: a first inference unit 450 configured to perform inference on matter decomposition image data generated by reconstructing imaging data output by a detector; a second inference unit 451 configured to perform inference on image data generated by reconstructing imaging data output by a detector; a third inference unit 452 configured to perform inference on synthetic image data composed of image data and matter decomposition image data; a selection unit 445 configured to select the inference result of the third inference unit 452 when the inference result of the first inference unit 450 is different from the inference result of the second inference unit 451; and a display control unit 446 configured to display the inference result of the selected third inference unit 452.

[0118] The information processing method according to this embodiment includes: performing inference on material decomposition image data generated by reconstructing imaging data output by a detector; performing inference on image data generated by reconstructing imaging data output by a detector; selecting the inference result obtained by performing inference on synthetic image data composed of image data and material decomposition image data when the inference result obtained when performing inference on the material decomposition image data is different from the inference result obtained when performing inference on the image data; and displaying the selected inference result.

[0119] Next, a second embodiment of this disclosure will be described. The second embodiment differs from the first embodiment in that the selection unit 445 selects at least one of a first inference unit 450 that performs inference on matter decomposition image data, a second inference unit 451 that performs inference on CT image data (integrated image data), and a third inference unit 452 that performs inference on synthetic image data composed of CT image data and matter decomposition image data. In this embodiment, the differences from the first embodiment will be primarily described.

[0120] When material decomposition image data is selected as the inference target, selection unit 445 selects either first inference unit 450 or third inference unit 452. First inference unit 450 performs inference on the material decomposition image data. Third inference unit 452 performs inference on composite image data composed of CT image data and material decomposition image data. When material decomposition image data is not selected as the inference target, selection unit 445 selects second inference unit 451. Second inference unit 451 performs inference on CT image data (integrated image data).

[0121] The reconstruction processing unit 442 has the function of generating CT image data (integrated image data) based on the imaging data output by the detector 12. The display control unit 446 causes the display unit 42 to display the CT image data. The reconstruction processing unit 442 also has the function of performing material decomposition on the imaging data output by the detector 12 and reconstructing material decomposition image data using the results of the material decomposition. The display control unit 446 enables the display unit 42 to display the material decomposition image data.

[0122] Selection unit 445 determines whether to select material decomposition image data as the inference target. If material decomposition image data is selected as the inference target, third inference unit 452 performs inference on the composite image data composed of CT image data and material decomposition image data, and obtains the inference result. First inference unit 450 can perform inference on the material decomposition image data and obtain the inference result. Third inference unit 452 or first inference unit 450 outputs the inference result of third inference unit 452 or first inference unit 450 to display control unit 446.

[0123] Next, we will refer to Figure 6 and Figure 7 A third embodiment of this disclosure is described. The third embodiment differs from the first and second embodiments in that it provides an image analysis unit 443 that analyzes material decomposition image data and obtains information on the content of predetermined substances or predetermined lesions included in the material decomposition image data. A selection unit 445 selects the inference result of a third inference unit 452 that performs inference on the synthetic image data composed of CT image data and material decomposition image data based on the content information of the predetermined substances or predetermined lesions included in the material decomposition image data. In this embodiment, the differences from the first and second embodiments will be primarily described.

[0124] like Figure 6 As shown, the reconstruction processing unit 442 has the function of generating CT image data (integrated image data) based on the imaging data output by the detector 12. The display control unit 446 causes the display unit 42 to display the CT image data. The reconstruction processing unit 442 performs material decomposition on the imaging data output by the detector 12 and reconstructs material decomposition image data using the results of the material decomposition. The display control unit 446 enables the display unit 42 to display the material decomposition image data.

[0125] Image analysis unit 443 analyzes the substance decomposition image data. Image analysis unit 443 is capable of analyzing the substance decomposition image data and obtaining the type and amount of substances included in the substance decomposition image data. That is, image analysis unit 443 obtains the content information of predetermined substances included in the substance decomposition image data. Selection unit 445 is capable of selecting an inference target based on the analysis results of image analysis unit 443 (i.e., based on the content information of predetermined substances included in the substance decomposition image data). In other words, selection unit 445 selects at least one of the following based on the analysis results of image analysis unit 443 (i.e., based on the content information of predetermined substances included in the substance decomposition image data): a first inference unit 450 performing inference on the substance decomposition image data, a second inference unit 451 performing inference on CT image data (integrated image data), and a third inference unit 452 performing inference on synthetic image data composed of CT image data and substance decomposition image data.

[0126] The predetermined substance is any one of calcium, water, iodine, etc. Image analysis unit 443 can obtain, for example, the percentage of calcium included in the substance decomposition image data as content information of the predetermined substance in the substance decomposition image data. Image analysis unit 443 can also determine whether calcium is included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more). If calcium is included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more), selection unit 445 selects a third inference unit 452 to perform inference on the composite image data composed of CT image data and substance decomposition image data. Selection unit 445 can select a first inference unit 450 to perform inference on the substance decomposition image data.

[0127] In the absence of calcium being included in the material decomposition image data at a predetermined ratio or more (at a predetermined content or more), selection unit 445 selects a second inference unit 451 to perform inference on the CT image data (integral image data).

[0128] Image analysis unit 443 can obtain, for example, the percentage of water included in the substance decomposition image data as information on the content of a predetermined substance in the substance decomposition image data. Water corresponds to, for example, blood, lymph, etc. Image analysis unit 443 can also determine whether water is included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more). If water is included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more), selection unit 445 selects a third inference unit 452 to perform inference on the composite image data composed of CT image data and substance decomposition image data. Selection unit 445 can select a first inference unit 450 to perform inference on the substance decomposition image data. If water is not included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more), selection unit 445 selects a second inference unit 451 to perform inference on the CT image data (integrated image data).

[0129] Image analysis unit 443 can obtain, for example, the percentage of iodine included in the substance decomposition image data as information on the content of a predetermined substance in the substance decomposition image data. Image analysis unit 443 can also determine whether iodine is included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more). If iodine is included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more), selection unit 445 selects a third inference unit 452 to perform inference on the composite image data composed of CT image data and substance decomposition image data. Selection unit 445 can select a first inference unit 450 to perform inference on the substance decomposition image data. If iodine is not included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more), selection unit 445 selects a second inference unit 451 to perform inference on the CT image data (integrated image data).

[0130] That is, if a predetermined substance is included in the material decomposition image data at a predetermined ratio or more, the selection unit 445 selects the third inference unit 452. The third inference unit 452 is selected preferentially over the first inference unit 450. If the predetermined substance is not included in the material decomposition image data at a predetermined ratio or more, the selection unit 445 selects the second inference unit 451.

[0131] A setting unit (operation unit 43) can be provided for setting the type of substance to be analyzed by the image analysis unit 443. The operator can select the type of substance to be analyzed by the image analysis unit 443 via the setting unit. For example, the operator selects calcium as the substance to be analyzed by the image analysis unit 443 via the setting unit. If calcium is included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more), the selection unit 445 selects a third inference unit 452 to perform inference on the composite image data composed of CT image data and substance decomposition image data. If calcium is not included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more), the selection unit 445 selects a second inference unit 451 to perform inference on the CT image data (integrated image data).

[0132] As the substance to be analyzed by the image analysis unit 443, the operator selects, for example, iodine via the setting unit. If iodine is included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more), the selection unit 445 selects a third inference unit 452 to perform inference on the composite image data composed of CT image data and substance decomposition image data. If iodine is not included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more), the selection unit 445 selects a second inference unit 451 to perform inference on the CT image data (integrated image data).

[0133] As substances and lesions to be analyzed by the image analysis unit 443, the operator can select, for example, calcium and tumor via the setting unit. If the substance (calcium) is included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more), or if the lesion (tumor) is included in the substance decomposition image data at a predetermined ratio or more (at a predetermined content or more), the selection unit 445 selects a third inference unit 452 to perform inference on the synthetic image data composed of CT image data and substance decomposition image data.

[0134] Next, the operation of the X-ray CT apparatus 1 according to an embodiment of the present disclosure will be described. Figure 7 This is a flowchart illustrating an example operation of the X-ray CT apparatus 1.

[0135] S100 to S108 and Figure 5 Since the description is the same as in the text, it will be omitted.

[0136] S200: Image analysis unit 443 analyzes the substance decomposition image data. Image analysis unit 443 analyzes the substance decomposition image data and is able to obtain the type and quantity of substances included in the substance decomposition image data, or the type and quantity of lesions included in the substance decomposition image data. That is, image analysis unit 443 obtains the content information of predetermined substances included in the substance decomposition image data or the content information of predetermined lesions included in the substance decomposition image data.

[0137] S202: Selection unit 445 selects an inference target based on the analysis results of image analysis unit 443 (i.e., the content information of a predetermined substance included in the substance decomposition image data or the content information of a predetermined lesion included in the substance decomposition image data). Selection unit 445 selects at least one of the following: a first inference unit 450 that performs inference on substance decomposition image data, a second inference unit 451 that performs inference on CT image data (integrated image data), and a third inference unit 452 that performs inference on synthetic image data composed of CT image data and substance decomposition image data.

[0138] S204: The selected inference unit outputs its inference result to the display control unit 446. The display control unit 446 causes the display unit 42 to display the inference result of the selected inference unit and the synthesized image data 300. The display control unit 446 can also cause the display unit 42 to display the analysis result of the image analysis unit 443. Specifically, the display control unit 446 can cause the display unit 42 to display the content information of a predetermined substance included in the substance decomposition image data or the content information of a predetermined lesion included in the substance decomposition image data.

[0139] As described above, the X-ray CT apparatus according to this embodiment includes: an X-ray tube 11 configured to irradiate X-rays; a detector 12 configured to detect X-rays irradiated by the X-ray tube 11 and penetrating the subject; a reconstruction processing unit 442 configured to reconstruct imaging data output by the detector 12 and generate CT image data and material breakdown image data; a first inference unit 450 configured to perform inference on the material breakdown image data; a second inference unit 451 configured to perform inference on the CT image data; and a third inference unit 452 configured to perform inference on the CT image data and material breakdown image data. The image analysis unit 443 is configured to analyze the material decomposition image data and obtain information on the content of a predetermined substance or the content of a predetermined lesion included in the material decomposition image data; the selection unit 445 is configured to select a third inference unit 452 based on the information on the content of a predetermined substance or the content of a predetermined lesion included in the material decomposition image data; and the display control unit 446 is configured to display the inference result of the selected third inference unit 452. Therefore, the operator can confirm the inference result corresponding to the material decomposition image data.

[0140] The detector does not necessarily have to be from an X-ray CT device. A detector from an X-ray imaging device can be used.

[0141] The information processing system according to this embodiment includes: a first inference unit 450 configured to perform inference on material decomposition image data generated by reconstructing imaging data output from a detector; a second inference unit 451 configured to perform inference on image data generated by reconstructing imaging data output from a detector; a third inference unit 452 configured to perform inference on synthetic image data composed of image data and material decomposition image data; an image analysis unit 443 configured to analyze the material decomposition image data and obtain information on the content of a predetermined substance or the content of a predetermined lesion included in the material decomposition image data; a selection unit 445 configured to select the third inference unit 452 based on the information on the content of a predetermined substance or the content of a predetermined lesion included in the material decomposition image data; and a display control unit 446 configured to display the inference result of the selected third inference unit 452.

[0142] The information processing method according to this embodiment includes: analyzing material decomposition image data generated by reconstructing imaging data output by a detector, and obtaining content information of a predetermined substance or content information of a predetermined lesion included in the material decomposition image data; performing inference on synthetic image data composed of image data and material decomposition image data based on the content information of the predetermined substance or content information of the predetermined lesion included in the material decomposition image data, and displaying the inference result.

[0143] The computer program that implements the functions of the above embodiments can be supplied to a computer via a network or a memory (storage medium), and the computer program can be executed by a processor (not shown). The computer program causes the computer to perform the above information processing method. That is, the computer program is a program for implementing the functions of an information processing system by a computer. The memory stores the computer program.

[0144] Other embodiments

[0145] Embodiments of this disclosure can also be implemented by a computer of a system or apparatus that reads and executes computer-executable instructions (e.g., one or more programs) recorded on a storage medium (which may also be more fully referred to as a 'non-transient computer-readable storage medium') to perform one or more functions of the above embodiments and / or includes one or more circuits (e.g., application-specific integrated circuits (ASICs)) for performing one or more functions of the above embodiments, and by a method performed by a computer of the system or apparatus by, for example, reading and executing computer-executable instructions from the storage medium to perform one or more functions of the above embodiments and / or controlling one or more circuits to perform one or more functions of the above embodiments. The computer may include one or more processors (e.g., a central processing unit (CPU), a microprocessor unit (MPU)) and may include separate computers or networks of separate processors to read and execute computer-executable instructions. The computer-executable instructions may be provided to the computer, for example, from a network or storage medium. The storage medium may include, for example, a hard disk, random access memory (RAM), read-only memory (ROM), storage devices for distributed computing systems, optical discs (such as CDs, DVDs, or Blu-ray discs). TM One or more of the following: flash memory devices, memory cards, etc.

[0146] The embodiments of the present invention can also be implemented by providing software (programs) that perform the functions of the above embodiments to a system or device via a network or various storage media, and the computer or central processing unit (CPU) or microprocessor unit (MPU) of the system or device reads out and executes the program.

[0147] While this disclosure has been described with reference to exemplary embodiments, it is to be understood that this disclosure is not limited to the disclosed exemplary embodiments. The scope of the appended claims is to be given the broadest interpretation in order to cover all such modifications and equivalent structures and functions.

Claims

1. An X-ray computed tomography (CT) device, comprising: X-ray tube, the X-ray tube being configured to irradiate X-rays; A detector configured to detect X-rays irradiated by the X-ray tube and penetrating the subject; A reconstruction processing unit is configured to reconstruct the imaging data output by the detector and generate CT image data and material decomposition image data; A first inference unit is configured to perform inference on the substance decomposition image data; A second inference unit is configured to perform inference on the CT image data; A third inference unit is configured to perform inference on synthetic image data, which consists of the CT image data and the substance decomposition image data. The selection unit is configured to select the inference result of the third inference unit when the inference result of the first inference unit is different from the inference result of the second inference unit; as well as The display control unit is configured to display the inference result of the selected third inference unit.

2. The X-ray computed tomography (CT) apparatus according to claim 1, wherein the display control unit is configured to display either the inference result of the first inference unit or the inference result of the second inference unit when the inference result of the first inference unit is the same as the inference result of the second inference unit.

3. The X-ray computed tomography (CT) apparatus according to claim 1, wherein the CT image data is integral image data.

4. The X-ray computed tomography (CT) apparatus of claim 1, wherein the display control unit is configured to display region information and substance name information about the predetermined substance in response to the first inference unit detecting a predetermined substance in the substance decomposition image data.

5. The X-ray computed tomography (CT) apparatus of claim 1, wherein the display control unit is configured to display information indicating that inference has been performed on the composite image data consisting of the CT image data and the material breakdown image data.

6. The X-ray computed tomography (CT) apparatus of claim 1, wherein the display control unit is configured to display region information and lesion name information about the predetermined lesion in response to the second inference unit detecting a predetermined lesion in the CT image data.

7. The X-ray computed tomography (CT) apparatus of claim 1, wherein the display control unit is configured to display information indicating that inference has been performed on the CT image data.

8. An X-ray computed tomography (CT) device, comprising: X-ray tube, the X-ray tube being configured to irradiate X-rays; A detector configured to detect X-rays irradiated by the X-ray tube and penetrating the subject; A reconstruction processing unit is configured to reconstruct the imaging data output by the detector and generate CT image data and material decomposition image data; A first inference unit is configured to perform inference on the substance decomposition image data; A second inference unit is configured to perform inference on the CT image data; A third inference unit is configured to perform inference on synthetic image data, which consists of the CT image data and the substance decomposition image data. An image analysis unit is configured to analyze the substance decomposition image data and obtain information on the content of a predetermined substance included in the substance decomposition image data or information on the content of a predetermined lesion included in the substance decomposition image data. The selection unit is configured to select at least one of the inference results of the first inference unit, the inference result of the second inference unit, and the inference result of the third inference unit based on the content information of the predetermined substance included in the substance decomposition image data or the content information of the predetermined lesion included in the substance decomposition image data. as well as The display control unit is configured to display the selected inference result.

9. The X-ray computed tomography (CT) apparatus of claim 8, wherein the predetermined substance is any one of calcium, water, and iodine.

10. The X-ray computed tomography (CT) apparatus of claim 8, wherein the selection unit is configured to select the third inference unit when the predetermined substance is included in the substance decomposition image data at a predetermined ratio or more.

11. The X-ray computed tomography (CT) apparatus of claim 8, wherein the selection unit is configured to select the second inference unit when the predetermined substance is not included in the substance decomposition image data at a predetermined ratio or more.

12. The X-ray computed tomography (CT) apparatus of claim 8, further comprising a setting unit configured to set the type of substance to be analyzed by the image analysis unit.

13. An X-ray computed tomography (CT) device, comprising: X-ray tube, the X-ray tube being configured to irradiate X-rays; A detector configured to detect X-rays irradiated by the X-ray tube and penetrating the subject; A reconstruction processing unit is configured to reconstruct the imaging data output by the detector and generate CT image data and material decomposition image data; A first inference unit is configured to perform inference on the substance decomposition image data; A second inference unit is configured to perform inference on the CT image data; A third inference unit is configured to perform inference on synthetic image data, which consists of the CT image data and the substance decomposition image data. as well as The selection unit is configured to select at least one of the inference results of the first inference unit, the inference results of the second inference unit, and the inference results of the third inference unit according to the checklist.

14. An information processing system, comprising: A first inference unit is configured to perform inference on matter decomposition image data, which is generated by reconstructing imaging data output by a detector. A second inference unit is configured to perform inference on image data generated by reconstructing the imaging data output by the detector; A third inference unit is configured to perform inference on synthetic image data, which consists of the image data and the substance decomposition image data. The selection unit is configured to select the inference result of the third inference unit when the inference result of the first inference unit is different from the inference result of the second inference unit; as well as The display control unit is configured to display the inference result of the selected third inference unit.

15. An information processing method, comprising: Inference is performed on material decomposition image data, which is generated by reconstructing imaging data output by a detector; Inference is performed on image data, which is generated by reconstructing the imaging data output by the detector; If the inference result obtained from the inference of the substance decomposition image data differs from the inference result obtained from the inference of the image data, the inference result obtained by performing inference on the synthetic image data, which consists of the image data and the substance decomposition image data, shall be selected. as well as The selected inference result is displayed.

16. A non-transient computer-readable medium storing a program for causing a computer to perform the information processing method according to claim 15.

Images