X-ray CT apparatus, information processing system, information processing method, and program

Abstract

To provide an X-ray CT apparatus for displaying an appropriate inference result.SOLUTION: The X-ray CT apparatus includes: an X-ray tube 11 for emitting X-rays; a detector 12 for detecting the X-rays emitted from the X-ray tube 11 and transmitted through a subject; a reconfiguration processing unit 442 for reconfiguring imaging data output by the detector 12 and generating CT image data and substance discrimination image data; a first inference unit 450 for performing inference to the subject discrimination image data; a second inference unit 451 for performing inference to the CT image data; a third inference unit 452 for performing inference to composite image data obtained by synthesizing the CT image data and the subject discrimination image data; a selection unit for selecting 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 for displaying the selected inference result of the third inference unit 452.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an X-ray CT apparatus equipped with a photon-counting CT function, an information processing system, an information processing method, and a program. [Background technology]

[0002] An X-ray CT device equipped with a photon-counting CT (Computed Tomography) function counts individual incident X-rays and measures the energy of the incident X-rays to obtain an X-ray spectrum. From the obtained X-ray spectrum, the material contained in the subject can be identified and material decomposition image data can be generated. In addition, an X-ray CT device equipped with a photon-counting CT function can reconstruct CT image data (integral image data) (for example, Patent Document 1).

[0003] Meanwhile, inference tasks performed by neural networks include classification tasks, such as classifying image data into classes, and detection tasks, such as detecting what is captured in what position in the image data. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2018-175866 A Summary of the Invention [Problem to be solved by the invention]

[0005] Inference results may differ depending on whether an inference task is performed on material decomposition image data acquired by an X-ray CT device equipped with a photon counting CT function or on CT image data (integral image data). The present invention aims to display appropriate inference results.

[0006] However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problems. Problems corresponding to the effects of each configuration shown in the embodiments described later may also be positioned as other problems. [Means for solving the problem]

[0007] In order to achieve the object of the present invention, the X-ray CT device of the present invention comprises an X-ray tube that irradiates X-rays, a detector that detects X-rays irradiated from the X-ray tube and transmitted through a subject, a reconstruction processing unit that reconstructs the shooting data output by the detector and generates CT image data and material decomposition image data, a first inference unit that performs inference on the material decomposition image data, a second inference unit that performs inference on the CT image data, a third inference unit that performs inference on combined image data combining the CT image data and the material decomposition image data, a selection unit that selects the inference result of the third inference unit when the inference result of the first inference unit and the inference result of the second inference unit are different inference results, and a display control unit that displays the selected inference result of the third inference unit.

[0008] The information processing system of the present invention includes a first inference unit that performs inference on material decomposition image data generated by reconstructing the shooting data output by the detector of the X-ray CT device, a second inference unit that performs inference on CT image data generated by reconstructing the shooting data output by the detector of the X-ray CT device, a third inference unit that performs inference on combined image data combining the CT image data and the material decomposition image data, a selection unit that selects the inference result of the third inference unit when the inference result of the first inference unit and the inference result of the second inference unit are different inference results, and a display control unit that displays the selected inference result of the third inference unit.

[0009] The information processing method of the present invention includes a step of performing inference on material decomposition image data generated by reconstructing the shooting data output by the detector of the X-ray CT device, a step of performing inference on CT image data generated by reconstructing the shooting data output by the detector of the X-ray CT device, and if the respective inference results differ, a step of selecting an inference result performed on composite image data obtained by combining the CT image data and the material decomposition image data, and a step of displaying the selected inference result.

[0010] The X-ray CT apparatus of the present invention includes an X-ray tube that irradiates X-rays, a detector that detects X-rays irradiated from the X-ray tube and transmitted through a subject, a reconstruction processing unit that reconstructs the shooting data output by the detector and generates CT image data and material decomposition image data, a first inference unit that performs inference on the material decomposition image data, a second inference unit that performs inference on the CT image data, a third inference unit that performs inference on combined image data obtained by combining the CT image data and the material decomposition image data, an image analysis unit that analyzes the material decomposition image data and acquires content information of a specified substance or content information of a specified lesion contained in the material decomposition image data, a selection unit that selects 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 a specified substance or the content information of a specified lesion contained in the material decomposition image data, and a display control unit that displays the selected inference result.

[0011] The information processing system of the present invention includes a first inference unit that performs inference on material decomposition image data generated by reconstructing the shooting data output by the detector of the X-ray CT device, a second inference unit that performs inference on CT image data generated by reconstructing the shooting data output by the detector of the X-ray CT device, a third inference unit that performs inference on combined image data obtained by combining the CT image data and the material decomposition image data, an image analysis unit that analyzes the material decomposition image data and acquires content information of a specified substance or content information of a specified lesion contained in the material decomposition image data, a selection unit that selects 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 a specified substance or the content information of a specified lesion contained in the material decomposition image data, and a display control unit that displays the selected inference result.

[0012] The information processing method of the present invention includes the steps of analyzing material decomposition image data generated by reconstructing the imaging data output by the detector of the X-ray CT device, and acquiring information on the content of a specified substance or the content of a specified lesion contained in the material decomposition image data, and performing inference on at least one of the material decomposition image data, the CT image data, and composite image data obtained by combining the CT image data and the material decomposition image data, based on the information on the content of a specified substance or the information on the content of a specified lesion contained in the material decomposition image data, and displaying the inference result.

[0013] The X-ray CT apparatus of the present invention comprises an X-ray tube that irradiates X-rays, a detector that detects X-rays irradiated from the X-ray tube and transmitted through a subject, a reconstruction processing unit that reconstructs the shooting data output by the detector and generates CT image data and material decomposition image data, a first inference unit that performs inference on the material decomposition image data, a second inference unit that performs inference on the CT image data, a third inference unit that performs inference on combined image data combining the CT image data and the material decomposition image data, and a selection unit that selects 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 an examination order.

[0014] The information processing system of the present invention includes a first inference unit that performs inference on material decomposition image data generated by reconstructing the imaging data output by the detector of the X-ray CT device, a second inference unit that performs inference on CT image data generated by reconstructing the imaging data output by the detector of the X-ray CT device, a third inference unit that performs inference on combined image data combining the CT image data and the material decomposition image data, a selection unit that selects 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 an examination order, and a display control unit that displays the selected inference result.

[0015] The information processing method of the present invention includes the steps of generating CT image data based on X-rays irradiated from an X-ray tube and transmitted through a subject, material decomposition image data, and composite image data combining the CT image data and the material decomposition image data, and performing inference on at least one of the material decomposition image data, the CT image data, and the composite image data combining the CT image data and the material decomposition image data based on an examination order, and displaying the inference result. Effect of the Invention

[0016] According to the present invention, it is possible to display appropriate inference results. [Brief description of the drawings]

[0017] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of an X-ray CT apparatus according to the present invention. [Diagram 2] FIG. 2 is a diagram showing an example of the peripheral configuration of an inference unit of the X-ray CT apparatus of the present invention. [Diagram 3] FIG. 2 is a diagram showing one display form of the display unit in the X-ray CT apparatus of the present invention. [Figure 4] FIG. 2 is a diagram showing one display form of the display unit in the X-ray CT apparatus of the present invention. [Diagram 5] 4 is a flowchart showing an example of the operation of the X-ray CT apparatus of the present invention. [Figure 6] FIG. 2 is a diagram showing an example of the peripheral configuration of an inference unit of the X-ray CT apparatus of the present invention. [Figure 7]4 is a flowchart showing an example of the operation of the X-ray CT apparatus of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] Hereinafter, an X-ray CT apparatus, an information processing system, an information processing method, and a program according to an embodiment will be described with reference to the drawings. Note that parts with the same reference numerals perform the same operations, and redundant explanations will be omitted as appropriate. Hereinafter, an embodiment will be described with reference to the drawings.

[0019] A first embodiment of the present invention will be described with reference to Figs. 1 to 5. An example of the configuration of an X-ray CT apparatus according to the first embodiment will be described with reference to Fig. 1. The X-ray CT apparatus 1 shown in Fig. 1 includes a gantry 10, a bed apparatus 30, and a console apparatus 40. In the embodiment, the rotation axis of the rotating frame 13 in a non-tilted state or the longitudinal direction of a top plate 33 of the bed apparatus 30 is defined as the Z-axis direction, the axial direction perpendicular to the Z-axis direction and horizontal to the floor surface is defined as the X-axis direction, and the axial direction perpendicular to the Z-axis direction and perpendicular to the floor surface is defined as the Y-axis direction.

[0020] For example, the gantry device 10 and the bed device 30 are installed in a CT examination room, and the console device 40 is installed in a control room adjacent to the CT examination room. The console device 40 does not necessarily have to be installed in the control room. For example, the console device 40 may be installed in the same room as the gantry device 10 and the bed device 30. In any case, the gantry device 10, the bed device 30, and the console device 40 are connected to each other by wire or wirelessly so that they can communicate with each other.

[0021] The gantry device 10 is a scanning device having a configuration for performing X-ray CT imaging of the subject P. The gantry 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 DAS (Data Acquisition System)). For convenience of explanation, only a part of the configuration is shown here.

[0022] The X-ray tube 11 is a vacuum tube that generates X-rays by irradiating thermoelectrons from a cathode (filament) to an anode (target) by application of a high voltage from the X-ray high voltage device 14 and supply of a filament current. Specifically, X-rays are generated by the thermoelectrons colliding with the target. For example, the X-ray tube 11 may be a rotating anode type X-ray tube that generates X-rays by irradiating a rotating anode with thermoelectrons. The X-rays generated by the X-ray tube 11 are shaped into a cone beam via a collimator 17, for example, and irradiated to the subject P. The X-ray tube 11 is an example of an X-ray generating unit.

[0023] The detector 12 detects X-rays irradiated from the X-ray tube 11 and transmitted through the subject P, and outputs a signal corresponding to the X-ray dose to the DAS 18. The detector 12 has, for example, a plurality of X-ray detection element rows in which a plurality of X-ray detection elements are arranged in the channel direction along one arc centered on the focal point of the X-ray tube 11. The detector 12 has, for example, a row structure in which a plurality of X-ray detection element rows in which a plurality of X-ray detection elements are arranged in the channel direction are arranged in the slice direction (row direction). The detector 12 is a photon-counting detector. The reconstruction processing unit can also reconstruct CT image data (integral image data) with a high S / N ratio by counting photons of the X-rays transmitted through the subject P using the photon-counting detector.

[0024] The detector 12 can be classified into an energy integration function and a photon counting function according to the measurement method performed by the DAS 18 on the converted signal. In the energy integration function, the energy of the X-rays transmitted through the subject P is integrated over a certain period of time to measure the total energy of the X-rays transmitted over a certain period of time. In the photon counting function, the number of X-ray photons contained in the X-rays transmitted through the subject P is measured by dividing them into multiple energy bands (also called energy bins or simply bins). This makes it possible to perform material fractionation based on the imaging data obtained for each energy band. Here, the imaging mode when material fractionation is performed is called the material fractionation mode (material decomposition image mode), and the imaging mode when material fractionation is not performed is called the non-material decomposition mode (integral image mode).

[0025] The rotating frame 13 supports the X-ray generating unit and the X-ray detecting unit rotatably around a rotation axis Z. Specifically, the rotating frame 13 is an annular frame that supports the X-ray tube 11 and the detector 12 facing each other and rotates the X-ray tube 11 and the detector 12 by a control device 15. The rotating frame 13 is rotatably supported by a fixed frame (not shown) made of a metal such as aluminum. More specifically, the rotating frame 13 is connected to an edge of the fixed frame via a bearing. The rotating frame 13 receives power from a drive mechanism of the control device 15 and rotates around the rotation axis Z at a constant angular velocity.

[0026] The rotating frame 13 further includes and supports the X-ray high voltage device 14 and the DAS 18 in addition to the X-ray tube 11 and the detector 12. The rotating frame 13 is housed in a substantially cylindrical housing in which an opening (bore) 19 forming an imaging space is formed. The opening substantially coincides with the FOV. The central axis of the opening coincides with the rotation axis Z of the rotating frame 13. The imaging data generated by the DAS 18 is transmitted, for example, from a transmitter having a light-emitting diode (LED) to a receiver (not shown) having a photodiode provided in a non-rotating part (fixed frame) of the gantry 10 by optical communication, and is then transferred to the console device 40. The method of transmitting the imaging data from the rotating frame 13 to the non-rotating part of the gantry 10 is not limited to optical communication, and any method of non-contact data transmission may be used.

[0027] The X-ray high voltage device 14 has electric circuits such as a transformer and a rectifier, and includes a high voltage generator having a 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 control device that controls an output voltage according to the X-rays irradiated by the X-ray tube 11. The high voltage generator may be of a transformer type or an inverter type. The X-ray high voltage device 14 may be provided on the rotating frame 13, or on the fixed frame side of the gantry device 10.

[0028] The control device 15 has a processing circuit having a CPU (Central Processing Unit) and the like, and a driving mechanism for a motor, an actuator, and the like. The processing circuit has a processor such as a CPU or an MPU (Micro Processing Unit) and a memory such as a ROM (Read Only Memory) or a RAM (Random Access Memory) as hardware resources. The control device 15 may also be realized by 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 device 14, the DAS 18, and the like according to commands from the console device 40. The processor realizes the above control by reading and executing a program stored in the memory.

[0029] The wedge 16 is a filter for adjusting the amount of X-rays irradiated from the X-ray tube 11. Specifically, the wedge 16 is a filter that transmits and attenuates the X-rays irradiated from the X-ray tube 11 so that the X-rays irradiated from the X-ray tube 11 to the subject P have a predetermined distribution. For example, the wedge 16 (wedge filter, bow-tie filter) is a filter made of processed aluminum so as to have a predetermined target angle and a predetermined thickness.

[0030] The collimator 17 is a lead plate or the like for narrowing down the irradiation range of the X-rays transmitted through the wedge 16, and a slit is formed by combining a plurality of lead plates or the like. The collimator 17 may also be called an X-ray aperture.

[0031] The DAS 18 generates digital data (also called imaging data) indicating count values ​​of X-ray photons detected by the detector 12 for each of a plurality of energy bands. The imaging data is a set of count value data identified by the channel number of the X-ray detection element that generated the data, the row number, the view number indicating the collected view (projection angle), and the energy bin number. The DAS 18 is realized, for example, by an ASIC (Application Specific Integrated Circuit) equipped with circuit elements capable of generating imaging data. The imaging data is transferred to the console device 40.

[0032] The bed device 30 is a device for placing and moving a subject P to be scanned, and includes a base 31, a bed driving device 32, a top board 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.

[0033] The bed driving device 32 is a motor or actuator that moves the tabletop 33 on which the subject P is placed in the longitudinal direction of the tabletop 33. The bed driving device 32 moves the tabletop 33 under the control of the console device 40 or the control device 15. For example, the bed driving device 32 moves the tabletop 33 in a direction perpendicular to the subject P so that the body axis of the subject P placed on the tabletop 33 coincides with the central axis of the opening of the rotating frame 13. The bed driving device 32 may also move the tabletop 33 along the body axis direction of the subject P in accordance with X-ray CT imaging performed using the gantry device 10. The bed driving device 32 generates power by driving at a rotation speed according to the duty ratio of a drive signal from the control device 15. The bed driving device 32 is realized by a motor such as a direct drive motor or a servo motor.

[0034] The tabletop 33 provided on the upper surface of the support frame 34 is a plate on which the subject P is placed. The bed driving device 32 may move the support frame 34 in the longitudinal direction of the tabletop 33 in addition to the tabletop 33.

[0035] The console device 40 has 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. Note that, although the console device 40 will be described as being separate from the gantry device 10, the gantry device 10 may include the console device 40 or some of the components of the console device 40.

[0036] The memory 41 is a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or an integrated circuit storage device that stores various information. The memory 41 stores, for example, imaging data and reconstructed image data. In addition to the HDD or SSD, the memory 41 may be a drive device that reads and writes various information between a portable storage medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a flash memory, or a semiconductor memory element such as a RAM (Random Access Memory). The storage area of ​​the memory 41 may be in the X-ray CT device 1 or in an external storage device connected via a network. For example, the memory 41 stores data of a CT image and a display image. The memory 41 also stores a control program according to the embodiment.

[0037] The display unit 42 displays various information. For example, the display unit 42 outputs medical images (CT images) generated by the processing circuit 44 and a GUI (Graphical User Interface) for receiving various operations from an operator. For example, a liquid crystal display (LCD), a cathode ray tube (CRT), an organic electroluminescence display (OELD), a plasma display, or any other display unit can be used as appropriate as the display unit 42. The display unit 42 may be provided on the gantry device 10. The display unit 42 may be a desktop type, or may be configured as a tablet terminal capable of wireless communication with the console device 40 main body.

[0038] 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 collection conditions for collecting imaging data, reconstruction conditions for reconstructing a CT image, image processing conditions for generating a post-processed image from a CT image, and the like. As the operation unit 43, for example, a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touchpad, a touch panel display unit, and the like can be used as appropriate. In the embodiment, the operation unit 43 is not limited to a device having physical operation parts such as a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touchpad, and a touch panel display unit. For example, an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs the electrical signal to the processing circuit 44 is also included in the example of the operation unit 43. The operation unit 43 may be provided in the gantry device 10. The operation unit 43 may also be configured with a tablet terminal or the like capable of wireless communication with the console device 40 main body.

[0039] The processing circuitry 44 controls the operation of the entire X-ray CT apparatus 1 in response to an electrical signal of an input operation output from the operation unit 43. For example, the processing circuitry 44 has a processor such as a CPU, MPU, or GPU (Graphics Processing Unit) and a memory such as a ROM or RAM as hardware resources. The processing circuitry 44 executes a control unit 441, a reconstruction processing unit 442, an image analysis unit 443, an inference unit 444, a selection unit 225, and a display control unit 446 by a processor that executes a program expanded in the memory. Note that each function (the control unit 441, the reconstruction processing unit 442, the image analysis unit 443, the inference unit 444, the selection unit 225, and the display control unit 446) is not limited to being realized by a single processing circuit. A processing circuit may be configured by combining a plurality of independent processors, and each processor may execute a program to realize each function.

[0040] The control unit 441 controls each function of the processing circuit 44 based on an input operation received from an operator via the operation unit 43. Specifically, the control unit 441 reads out a control program stored in the memory 41, expands it on the memory in the processing circuit 44, and controls each unit of the X-ray CT apparatus 1 according to the expanded control program. In addition, the control unit 441 generates imaging data by performing pre-processing such as logarithmic conversion processing, offset correction processing, sensitivity correction processing between channels, and beam hardening correction on the imaging data output from the DAS 18.

[0041] The reconstruction processing unit 442 has a function of generating CT image data based on the imaging data output by the detector 12 (DAS 18). The reconstruction processing unit 442 reconstructs CT image data by, for example, backprojection processing of the imaging data stored in the memory circuitry 35. An example of the backprojection processing is backprojection processing by a Filtered Back Projection (FBP) method. The reconstruction processing unit 442 may perform the reconstruction processing by, for example, an iterative approximation method. The reconstruction processing unit 442 also 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 various image processing in the memory 41.

[0042] The reconstruction processor 442 also calculates energy integral data by the sum of the counts (total value) of each energy bin, or the sum of the products of the representative values ​​and counts of the energy bins, which are signals obtained by the photon-counting detector 12. The reconstruction processor 442 can also reconstruct CT image data (integral image data) by using the energy integral data.

[0043] Furthermore, as an application of the photon-counting X-ray CT apparatus 1, there is a technique for discriminating the type, abundance, density, etc. of the material contained in the subject P by utilizing the fact that the X-ray absorption characteristics differ for each material. This is called material decomposition. For example, the reconstruction processing unit 442 can perform material decomposition on the imaging data and obtain material decomposition information. Furthermore, the reconstruction processing unit 442 can reconstruct material decomposition image data indicating the material decomposition using the material decomposition information that is the result of the material decomposition.

[0044] For example, imaging data generated from counting results obtained by the photon-counting X-ray CT device 1 contains information on the energy spectrum of X-rays attenuated by passing through the subject P. Therefore, the reconstruction processing unit 442 can reconstruct material decomposition image data in which, for example, a specific energy component is visualized.

[0045] The image analysis unit 443 analyzes the material decomposition image data. By analyzing the material decomposition image data, it is possible to obtain the extent to which a predetermined material is contained in the material decomposition image data and the extent to which a predetermined lesion is contained in the material decomposition image data.

[0046] The inference unit 444 can perform inference on the material decomposition image data. The inference unit 444 can perform inference on the CT image data (integral image data). Furthermore, the inference unit 444 can perform inference on the composite image data of the material decomposition image data and the CT image data (integral image data). Therefore, the inference unit 444 can perform inference on each of the material decomposition image data, the CT image data, and the composite image data of the material decomposition image data and the CT image data.

[0047] Specifically, as shown in FIG. 2, the inference unit 444 has a first inference unit 450 that uses a neural network to perform inference on material decomposition image data, a second inference unit 451 that uses a neural network to perform inference on CT image data, and a third inference unit 452 that uses a neural network to perform inference on composite image data of the material decomposition image data and the CT image data.

[0048] The first inference unit 450 acquires training data in advance. The training data is determined according to the inference task performed by the neural network and the target of classification.

[0049] Inference tasks performed by neural networks include a classification task to classify the classes of material decomposition image data, a detection task to detect which material is captured at which position in the material decomposition image data, a segmentation task to extract a target region from the material decomposition image data, etc. The material decomposition image data used as training data is material decomposition image data different from CT image data (integral image data).

[0050] When training a neural network to perform a classification task, the first inference unit 450 acquires training data that pairs material decomposition image data with ground truth labels, which are labels that indicate the material objects captured in the material decomposition image data.

[0051] On the other hand, when training a neural network to perform a detection task, the first inference unit 450 obtains training data for the material decomposition image data that pairs an ROI (Region Of Interest), which indicates the position of a material target reflected in the material decomposition image data, with a correct answer image to which a correct answer label, which is a label indicating the target, has been assigned.

[0052] When training a neural network to perform a segmentation task, the first inference unit 450 obtains training data for the material decomposition image data, which pairs position information of pixels of material objects captured in the material decomposition image data with a correct image to which a correct label, which is a label indicating the material object, has been assigned.

[0053] Similarly, the second inference unit 451 acquires training data in advance. The training data is determined according to the inference task performed by the neural network and the target of classification.

[0054] Inference tasks performed by neural networks include classification tasks to classify the classes of CT image data (integral image data), detection tasks to detect what is captured in what position in the CT image data, and segmentation tasks to extract target areas from the CT image data.

[0055] When training a neural network that performs a classification task, the second inference unit 451 acquires training data that pairs CT image data with a correct answer label that is a label indicating an object that appears in the CT image data.

[0056] On the other hand, when training a neural network to perform a detection task, the second inference unit 451 acquires training data for the CT image data that pairs an ROI (Region Of Interest) indicating the position of an object captured in the CT image data with a correct image to which a correct label, which is a label indicating the object, has been assigned.

[0057] When training a neural network to perform a segmentation task, the second inference unit 451 acquires training data for the CT image data that pairs position information of pixels of a target that appears in the CT image data with a correct image to which a correct label, which is a label indicating the target, has been assigned.

[0058] The image synthesis unit 447 is included in the processing circuitry 44. The image synthesis unit 447 synthesizes the material decomposition image data and the CT image data (integral image data). Specifically, the image synthesis unit 447 aligns the material decomposition image data and the CT image data based on feature portions in the material decomposition image data and the CT image data, and synthesizes the material decomposition image data and the CT image data. The material decomposition image data and the CT image data may be aligned for each slice.

[0059] The third inference unit 452, which performs inference on the composite image data of the material decomposition image data and the CT image data (integral image data), acquires training data in advance. The training data is determined according to the inference task performed by the neural network and the target of classification.

[0060] Inference tasks performed by neural networks include the classification task of classifying the class of composite image data of material decomposition image data and CT image data (integral image data), the detection task of detecting what is captured in which position of the composite image data, and the segmentation task of extracting target areas from the composite image data.

[0061] When training a neural network to perform a classification task, the third inference unit 452 acquires training data that pairs composite image data of material decomposition image data and CT image data (integral image data) with a correct answer label, which is a label indicating an object captured in the composite image data.

[0062] On the other hand, when training a neural network to perform a detection task, the third inference unit 452 obtains training data for the composite image data of material decomposition image data and CT image data (integral image data), which pairs a ROI (Region Of Interest) indicating the position of an object captured in the composite image data with a correct image to which a correct label, which is a label indicating the object, has been assigned.

[0063] When training a neural network to perform a segmentation task, the third inference unit 452 obtains training data for the composite image data of material decomposition image data and CT image data (integral image data), which pairs position information of pixels of targets captured in the composite image data with a correct image to which a correct label, which is a label indicating the target, has been assigned.

[0064] The selection unit 445 selects at least one of the inference results of the first inference unit 450 which performs inference on material decomposition image data, the inference results of the second inference unit 451 which performs inference on CT image data (integral image data), and the inference results of the third inference unit 452 which performs inference on composite image data of the material decomposition image data and the CT image data (integral image data).

[0065] In other words, the selection unit 445 can select whether to display at least one of the inference results of the first inference unit 450, which performs inference on material decomposition image data, the inference results of the second inference unit 451, which performs inference on CT image data (integral image data), and the inference results of the third inference unit 452, which performs inference on composite image data of the material decomposition image data and the CT image data (integral image data), on the display unit 42.

[0066] The selection unit 445 can also select at least one of the inference result of the first inference unit 450, the inference result of the second inference unit 451, and the inference result of the third inference unit 452 according to the examination order. Specifically, when the examination order includes an examination on the mammary gland (calcification examination), the selection unit 445 selects the inference result of the third inference unit 452 that infers on the composite image data of the material decomposition image data including calcium information and the CT image data (integral image data). Note that the selection unit 445 may select the inference result of the first inference unit 450 that infers the material decomposition image data including calcium information.

[0067] When the examination order includes an examination using a contrast agent (iodine examination), the selection unit 445 selects the inference result of the third inference unit 452 that performs inference on the composite image data of material decomposition image data including iodine information and CT image data (integral image data). The selection unit 445 may select the inference result of the first inference unit 450 that performs inference on material decomposition image data including iodine information. Furthermore, when the examination order includes an examination regarding the presence or absence of a metal (stent) (metal examination), the selection unit 445 selects the inference result of the third inference unit 452 that performs inference on the composite image data of material decomposition image data including metal (stent) information and CT image data (integral image data). The selection unit 445 selects the inference result of the first inference unit 450 that performs inference on material decomposition image data including metal (stent) information.

[0068] That is, when the examination order 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 that performs inference on the composite image data of the material decomposition image data and the CT image data (integral image data). Note that the selection unit 445 may select the inference result of the first inference unit 450 that performs inference on the material decomposition image data.

[0069] Since the composite image data of material decomposition image data and CT image data (integral image data) contains more information than the material decomposition image data, the selection unit 445 selects the inference result of the third inference unit 452, which makes inference on the composite image data of the material decomposition image data and CT image data (integral image data), in preference to the inference result of the first inference unit 450.

[0070] When 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 CT image data (integral image data). When the examination order includes, for example, an examination related to a nodule, the selection unit 445 selects the inference result of the second inference unit 451 that performs inference on CT image data (integral image data). When 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 CT image data (integral image data).

[0071] Furthermore, when the examination order includes a predetermined second examination (examination related to breast cancer (calcification examination and tumor examination)), the inference result of the first inference unit 450, which infers material decomposition image data including calcium information, and the inference result of the second inference unit 451, which performs inference on CT image data (integral image data), are required. The second examination is different from the first examination. Therefore, the selection unit 445 selects both the inference result of the first inference unit 450, which infers material decomposition image data including calcium information, and the inference result of the second inference unit 451, which performs inference on CT image data (integral image data).

[0072] The display control unit 446 controls the display unit 42 to display information on the process or 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.

[0073] Fig. 3 shows one display form of the display unit 42 in the X-ray CT apparatus 1 of the present invention. When the selection unit 445 selects the inference result of the third inference unit 452 that performs inference on the composite image data of the material decomposition image data and the CT image data (integral image data), the composite image data 300 of the material decomposition image data and the CT image data is displayed on the display unit 42 as shown in Fig. 3. The display unit 42 may also display the material decomposition image data.

[0074] The display unit 42 displays the composite image data 300 of the material decomposition image data and the CT image data (integral image data). The display unit 42 displays an image obtained by combining the slice images of the material decomposition image data and the CT image data.

[0075] When the third inference unit 452 detects a predetermined substance (calcium, iodine, metal, etc.) in the combined image data 300 of the material decomposition image data and CT image data (integral image data), it displays region information 302 related to the predetermined substance and information 304 on the substance name. The operator can recognize which substance exists at which position from the region information 302 related to the predetermined substance and information 304 on the substance name. When the third inference unit 452 detects a predetermined lesion in the combined image data 300 of the material decomposition image data and CT image data (integral image data), the display control unit 446 displays region information 305 related to the lesion and information 307 on the lesion name.

[0076] The display control unit 446 can also display information 306 indicating that the third inference unit 452 has performed inference on the composite image data 300 of the material decomposition image data and the CT image data (integral image data). The operator can recognize that the composite image data 300 of the material decomposition image data and the CT image data (integral image data) has been used for inference of the region information 302 related to a predetermined material and the information 304 on the material name. Therefore, the operator can recognize which material exists at which position. The operator can recognize that the composite image data 300 of the material decomposition image data and the CT image data (integral image data) has been used for inference of the region information 305 related to a lesion and the information 307 on the lesion name. Therefore, the operator can recognize which lesion exists at which position.

[0077] When the inference result of the first inference unit 450 that infers material decomposition image data differs from the inference result of the second inference unit 451 that performs inference on CT image data (integral image data), the display control unit 446 can display information indicating that the inference results are different.

[0078] 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 display classification information with different inference results. 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 display detection information (area information) with different inference results.

[0079] 4 shows one display form of the display unit 42 in the X-ray CT apparatus 1 of the present invention. When the selection unit 445 selects an inference result of the second inference unit 451 that performs inference on CT image data (integral image data), the CT image data 301 is displayed as shown in FIG.

[0080] The display unit 42 displays CT image data 301. The CT image data 301 is a slice image of three-dimensional volume data. When the second inference unit 451 detects a predetermined lesion (nodule, tumor, etc.) in the CT image data 301, the display control unit 446 displays region information 308 related to the predetermined lesion and information 310 on the lesion name. The operator can recognize which lesion exists at which position from the region information 308 related to the predetermined lesion and information 310 on the lesion name.

[0081] In addition, the display control unit 446 can also display information 312 indicating that inference has been made by the second inference unit 451 for the CT image data 301. The operator can recognize that the CT image data 301 has been used for inference.

[0082] Although the console device 40 has been described as a single console that executes multiple functions, multiple functions may be executed by separate consoles.

[0083] When the inference result of the first inference unit 450 that infers the material decomposition image data differs from the inference result of the second inference unit 451 that performs inference on the CT image data (integral image data), the display control unit 446 can display information indicating that the inference results are different. 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 display classification information and detection information (region information) with different inference results.

[0084] Next, an operation of the X-ray CT apparatus 1 of the present invention will be described below.

[0085] S100: A scan is performed to perform X-ray CT imaging of the subject P. While X-rays are generated by the X-ray tube 11, the X-ray tube 11 and the detector 12 are rotated around the rotation axis Z (subject P) to perform X-ray CT imaging.

[0086] S102: The detector 12 detects the X-rays transmitted through the subject P, and obtains imaging data, which is a signal related to the subject P. The imaging data is detection data obtained by bundling detection data from a predetermined number of detection elements in spatial units. In addition, the imaging data generated from the counting results obtained by the detector 12 includes information on the energy of the X-rays attenuated by transmitting through the subject P.

[0087] S104: The reconstruction processing unit 442 generates CT image data (integral image data) based on the imaging data output by the detector 12. The reconstruction processing unit 442 can reconstruct image data of, for example, a specific energy component.

[0088] S106: 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 result of the material decomposition. The reconstruction processing unit 442 generates material decomposition image data.

[0089] S108: The image synthesis unit 447 synthesizes the material decomposition image data and the CT image data (integral image data). Specifically, based on the characteristic parts in the material decomposition image data and the CT image data, the image synthesis unit 447 aligns the material decomposition image data and the CT image data, and synthesizes the material decomposition image data and the CT image data.

[0090] 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 of the material decomposition image data and the CT image data (integral image data) and obtains the inference result.

[0091] S110: The selection unit 445 selects at least one of the inference results of the first inference unit 450, which performs inference on material decomposition image data, the inference result of the second inference unit 451, which performs inference on CT image data (integral image data), and the inference result of the third inference unit 452, which performs inference on composite image data of the material decomposition image data and the CT image data (integral image data).

[0092] S112: The selection unit 445 outputs the selected 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 third inference unit 452 and the composite image data 300 of the material decomposition image data and the CT image data (integral image data), as shown in FIG.

[0093] When the inference result of the third inference unit 452 includes a predetermined substance (calcium, iodine, metal, etc.), the display control unit 446 displays region information 302 related to the predetermined substance and substance name information 304. When the inference result of the third inference unit 452 includes a lesion, the display control unit 446 displays region information 305 related to the lesion and lesion name information 307.

[0094] The selection unit 445 may select both the inference result of the first inference unit 450 that infers material decomposition image data and the inference result of the second inference unit 451 that performs inference on CT image data (integral image data). In this case, the selection unit 445 outputs the inference result of the first inference unit 450 and the inference result of the second inference unit 451 to the display control unit 446. The display control unit 446 can also display the composite image data of the material decomposition image data and the 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.

[0095] The inference result of the second inference unit 451 can also be output to the display control unit 446. As shown in Fig. 4, 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. The display control unit 446 can also cause the CT image data 301 and the inference result of the second inference unit 451 to be displayed on the same screen. When the inference result of the second inference unit 451 includes a lesion area, the display control unit 446 causes region information 308 relating to the lesion and information 310 on the name of the lesion to be displayed.

[0096] As described above, the inference unit 444 has a first inference unit 450 that uses a neural network to perform inference on material decomposition image data, a second inference unit 451 that uses a neural network to perform inference on CT image data, and a third inference unit 452 that performs inference on composite image data of the material decomposition image data and the CT image data (integral image data).

[0097] When the combined image data of the material decomposition image data and the CT image data (integral image data), or the inference result obtained by performing inference on the material decomposition image data, contains information about a specific material, the selection unit 445 selects the combined image data of the material decomposition image data and the CT image data (integral image data), or the inference result obtained by performing inference on the material decomposition image data.When the inference result obtained by performing inference on the CT image data (integral image data) contains information about a specific lesion, the selection unit 445 selects the inference result obtained by performing inference on the CT image data (integral image data).

[0098] When the inference result performed on the material decomposition image data includes information about a specific material, and when the inference result performed on the CT image data (integral image data) includes information about a specific lesion, the selection unit 445 selects the inference result performed on the material decomposition image data and the inference result performed on the CT image data (integral image data).

[0099] 5, 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 of the material decomposition image data and the CT image data (integral image data) and obtains an inference result.

[0100] Therefore, the control unit 441 can compare the inference result of the first inference unit 450 that performed inference on the material decomposition image data, the inference result of the second inference unit 451 that performed inference on the CT image data (integral image data), and the inference result of the third inference unit 452 that performed inference on the composite image data of the material decomposition image data and the CT image data (integral image data), calculate comparison information of the inference results, and display them. The comparison information of the inference results indicates whether or not the inference result of the first inference unit 450 that performed inference on the material decomposition image data, the inference result of the second inference unit 451 that performed inference on the CT image data (integral image data), and the inference result of the third inference unit 452 that performed inference on the composite image data of the material decomposition image data and the CT image data (integral image data) match.

[0101] For example, when the inference result of the first inference unit 450 that performed inference on the material decomposition image data and the inference result of the second inference unit 451 that performed inference on the CT image data (integral image data) match, the selection unit 445 selects either the inference result of the first inference unit 450 that performed inference on the material decomposition image data or the inference result of the second inference unit 451 that performed inference on the CT image data (integral image data). The display control unit 446 may cause the display unit 42 to display that the inference result of the first inference unit 450 that performed inference on the material decomposition image data and the inference result of the second inference unit 451 that performed inference on the CT image data (integral image data) match.

[0102] When the inference result of the first inference unit 450, which performed inference on the material decomposition image data, differs from the inference result of the second inference unit 451, which performed inference on the CT image data (integral image data), there is a possibility that the inference result is influenced by material decomposition, so the selection unit 445 selects the inference result of the third inference unit 452, which performed inference on the composite image data 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, which performed inference on the composite image data of the material decomposition image data and the CT image data (integral image data), and the composite image data 300, as shown in FIG.

[0103] When the inference result of the first inference unit 450 that performed inference on the material decomposition image data differs from the inference result of the second inference unit 451 that performed inference on the CT image data (integral image data), the selection unit 445 may select the inference result of the first inference unit 450 that performed inference on the material decomposition image data and the inference result of the second inference unit 451 that performed inference on the CT image data (integral image data). Furthermore, the display control unit 446 may display information that the inference result of the first inference unit 450 that performed inference on the material decomposition image data differs from the inference result of the second inference unit 451 that performed inference on the CT image data (integral image data).

[0104] The display control unit 446 may highlight an area where the inference result of the first inference unit 450 that performed inference on the material decomposition image data differs from the inference result of the second inference unit 451 that performed inference on the CT image data (integral image data). The highlighting is a frame display, a highlight display, or the like. The display control unit 446 can display an area where the inference result of the first inference unit 450 that performed inference on the material decomposition image data differs from the inference result of the second inference unit 451 that performed inference on the CT image data (integral image data) so that the area can be distinguished.

[0105] The display control unit 446 may display, on the composite image data consisting of the material decomposition image data and the CT image data (integral image data), the inference result of the first inference unit 450 that performed inference on the material decomposition image data and the inference result of the second inference unit 451 that performed inference on the CT image data (integral image data). The operator can recognize which detection information is different from each inference result (detection information).

[0106] As described above, the X-ray CT apparatus of this embodiment includes the X-ray tube 11 for irradiating X-rays, the detector 12 for detecting the X-rays irradiated from the X-ray tube 11 and transmitted through the subject, the reconstruction processing unit 442 for reconstructing the imaging data output by the detector 12 to generate CT image data and material decomposition image data, the first inference unit 450 for making an inference on the material decomposition image data, the second inference unit 451 for making an inference on the CT image data, the third inference unit 452 for making an inference on the composite image data obtained by combining the CT image data and the material decomposition image data, a selection unit for selecting the inference result of the third inference unit 452 when the inference result of the first inference unit 450 and the inference result of the second inference unit 451 are different inference results, and a display control unit 446 for displaying the selected inference result of the third inference unit 452. When the inference result of the first inference unit 450 and the inference result of the second inference unit 451 are the same inference result, 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.

[0107] Therefore, according to the X-ray CT apparatus of this embodiment, it is possible to display an appropriate inference result depending on the status of a plurality of inference results.

[0108] The information processing system of the present invention includes a first inference unit 450 that performs inference on material decomposition image data generated by reconstructing the shooting data output by the detector of the X-ray CT device, a second inference unit 451 that performs inference on CT image data generated by reconstructing the shooting data output by the detector of the X-ray CT device, a third inference unit 452 that performs inference on combined image data obtained by combining the CT image data and the material decomposition image data, a selection unit that selects the inference result of the third inference unit 452 when the inference result of the first inference unit 450 and the inference result of the second inference unit 451 are different inference results, and a display control unit 446 that displays the selected inference result of the third inference unit 452.

[0109] The information processing method of the present invention includes a step of performing inference on material decomposition image data generated by reconstructing the shooting data output by the detector of the X-ray CT device, a step of performing inference on CT image data generated by reconstructing the shooting data output by the detector of the X-ray CT device, and if the respective inference results differ, a step of selecting an inference result performed on composite image data obtained by combining the CT image data and the material decomposition image data, and a step of displaying the selected inference result.

[0110] Next, a second embodiment of the present invention will be described. The difference from the first embodiment is that the selection unit 445 selects at least one of a first inference unit 450 that performs inference on material decomposition image data, a second inference unit 451 that performs inference on CT image data (integral image data), and a third inference unit 452 that performs inference on combined image data obtained by combining the CT image data and the material decomposition image data. In this embodiment, the differences from the first embodiment will be mainly described.

[0111] When the selection unit 445 selects the material decomposition image data as the target of inference, the selection unit 445 selects the first inference unit 450 or the third inference unit 452. Then, the first inference unit 450 performs inference on the material decomposition image data. The third inference unit 452 performs inference on the composite image data obtained by combining the CT image data and the material decomposition image data. When the material decomposition image data is not the target of inference, the selection unit 445 selects the second inference unit 451. The second inference unit 451 performs inference on the CT image data (integral image data).

[0112] The reconstruction processing unit 442 has a function of generating CT image data (integral 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 a function of performing material decomposition on the imaging data output by the detector 12 and reconstructing material decomposition image data using the material decomposition result. The display control unit 446 can also cause the display unit 42 to display the material decomposition image data.

[0113] The selection unit 445 selects whether or not to use the material decomposition image data as the target of inference. When the material decomposition image data is selected as the target of inference, the third inference unit 452 performs inference on the composite image data obtained by combining the CT image data and the material decomposition image data, and acquires the inference result. The first inference unit 450 may perform inference on the material decomposition image data, and acquire the inference result. The third inference unit 452 or the first inference unit 450 outputs the inference result of the third inference unit 452 or the inference result of the first inference unit 450 to the display control unit 446.

[0114] Next, a third embodiment of the present invention will be described with reference to Figs. 6 and 7. The third embodiment differs from the first and second embodiments in that an image analysis unit 443 is provided that analyzes material decomposition image data and acquires content information of a predetermined substance or a predetermined lesion contained in the material decomposition image data, and a selection unit 445 selects an inference result of a third inference unit 452 that performs inference on combined image data obtained by combining CT image data and material decomposition image data, based on the content information of a predetermined substance or a predetermined lesion contained in the material decomposition image data. In this embodiment, the differences from the first and second embodiments will be mainly described.

[0115] 6, the reconstruction processing unit 442 has a function of generating CT image data (integral 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 result of the material decomposition. The display control unit 446 can also cause the display unit 42 to display the material decomposition image data.

[0116] The image analysis unit 443 analyzes the material decomposition image data. The image analysis unit 443 can analyze the material decomposition image data and obtain what and to what extent of material is contained in the material decomposition image data. That is, the image analysis unit 443 obtains content information of a predetermined material contained in the material decomposition image data. The selection unit 445 can select an object of inference based on the analysis result of the image analysis unit 443, i.e., the content information of a predetermined material contained in the material decomposition image data. In other words, based on the analysis result of the image analysis unit 443, i.e., the content information of a predetermined material contained in the material decomposition image data, at least one of the first inference unit 450 that performs inference on the material decomposition image data, the second inference unit 451 that performs inference on the CT image data (integral image data), and the third inference unit 452 that performs inference on the composite image data obtained by combining the CT image data and the material decomposition image data is selected.

[0117] The predetermined substance is any one of calcium, water, iodine, etc. The image analysis unit 443 can analyze, for example, what percentage of calcium is contained in the material decomposition image data as the content information of the predetermined substance in the material decomposition image data. The image analysis unit 443 can also determine whether or not calcium is contained in the material decomposition image data at a predetermined rate or more (a predetermined content rate or more). When calcium is contained in the material decomposition image data at a predetermined rate or more (a predetermined content rate or more), the selection unit 445 selects the third inference unit 452 that performs inference on the composite image data obtained by combining the CT image data and the material decomposition image data. The selection unit 445 may select the first inference unit 450 that performs inference on the material decomposition image data. When calcium is not contained in the material decomposition image data at a predetermined rate or more (a predetermined content rate or more), the selection unit 445 selects the second inference unit 451 that performs inference on the CT image data (integral image data).

[0118] The image analysis unit 443 can analyze, for example, what percentage of water is contained as information on the content of a specific material in the material decomposition image data. Water corresponds to, for example, blood, lymph, etc. The image analysis unit 443 can also determine whether or not the material decomposition image data contains water at a specific rate or more (a specific content rate or more). When the material decomposition image data contains water at a specific rate or more (a specific content rate or more), the selection unit 445 selects the third inference unit 452 that performs inference on the composite image data obtained by combining the CT image data and the material decomposition image data. It is to be noted that the selection unit 445 may select the first inference unit 450 that performs inference on the material decomposition image data. When the material decomposition image data does not contain water at a specific rate or more (a specific content rate or more), the selection unit 445 selects the second inference unit 451 that performs inference on the CT image data (integral image data).

[0119] Furthermore, the image analysis unit 443 can analyze, for example, what percentage of iodine is contained as information on the content of a predetermined material in the material decomposition image data. The image analysis unit 443 can also determine whether or not the material decomposition image data contains iodine at a predetermined rate or more (predetermined content rate or more). When the material decomposition image data contains iodine at a predetermined rate or more (predetermined content rate or more), the selection unit 445 selects the third inference unit 452 that performs inference on the composite image data obtained by combining the CT image data and the material decomposition image data. It is to be noted that the selection unit 445 may select the first inference unit 450 that performs inference on the material decomposition image data. When the material decomposition image data does not contain iodine at a predetermined rate or more (predetermined content rate or more), the selection unit 445 selects the second inference unit 451 that performs inference on the CT image data (integral image data).

[0120] In other words, when the material decomposition image data contains a predetermined material 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. When the material decomposition image data does not contain a predetermined material at a predetermined ratio or more, the selection unit 445 selects the second inference unit 451.

[0121] In addition, a setting unit (operation unit 43) for setting the type of material to be analyzed by the image analysis unit 443 may also be provided. The operator can select the type of material to be analyzed by the image analysis unit 443 via the setting unit. The operator selects, for example, calcium via the setting unit as the material to be analyzed by the image analysis unit 443. When the material decomposition image data contains calcium at a predetermined rate or more (a predetermined content rate or more), the selection unit 445 selects the third inference unit 452 that performs inference on the composite image data obtained by combining the CT image data and the material decomposition image data. When the material decomposition image data does not contain calcium at a predetermined rate or more (a predetermined content rate or more), the selection unit 445 selects the second inference unit 451 that performs inference on the CT image data (integral image data).

[0122] The operator selects, for example, iodine via the setting unit as a material to be analyzed by the image analysis unit 443. When the material decomposition image data contains iodine at a predetermined rate or more (a predetermined content rate or more), the selection unit 445 selects the third inference unit 452 that performs inference on the composite image data obtained by combining the CT image data and the material decomposition image data. When the material decomposition image data does not contain iodine at a predetermined rate or more (a predetermined content rate or more), the selection unit 445 selects the second inference unit 451 that performs inference on the CT image data (integral image data).

[0123] The operator can also select, for example, calcium and a tumor via the setting unit as the material and lesion to be analyzed by the image analysis unit 443. When the material decomposition image data contains a material (calcium) at a predetermined ratio or more (a predetermined content rate or more), or when the material decomposition image data contains a lesion (tumor) at a predetermined ratio or more (a predetermined content rate or more), the selection unit 445 selects a third inference unit 452 that performs inference on the composite image data obtained by combining the CT image data and the material decomposition image data.

[0124] Next, an operation of the X-ray CT apparatus 1 of the present invention will be described below.

[0125] S100 to S108 are the same as those in FIG. 5, and therefore the description will be omitted.

[0126] S200: The image analysis unit 443 analyzes the material decomposition image data. The image analysis unit 443 analyzes the material decomposition image data, and can acquire what materials are contained and to what extent, and what lesions are contained and to what extent, in the material decomposition image data. That is, the image analysis unit 443 acquires information on the content of a predetermined material or information on the content of a predetermined lesion contained in the material decomposition image data.

[0127] S202: The selection unit 445 selects an inference target based on the analysis result of the image analysis unit 443, i.e., the content information of a predetermined material or the content information of a predetermined lesion included in the material decomposition image data. The selection unit 445 selects at least one of a first inference unit 450 that performs inference on the material decomposition image data, a second inference unit 451 that performs inference on the CT image data (integral image data), and a third inference unit 452 that performs inference on combined image data obtained by combining the CT image data and the material decomposition image data.

[0128] S204: The selected inference unit outputs the inference result of the inference unit 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 composite image data 300, as shown in FIG. 3. 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 display the content information of a predetermined material and the content information of a predetermined lesion in the material decomposition image data on the display unit 42.

[0129] As described above, the X-ray CT apparatus of this embodiment includes the X-ray tube 11 for irradiating X-rays, the detector 12 for detecting the X-rays irradiated from the X-ray tube 11 and transmitted through the subject, the reconstruction processing unit 442 for reconstructing the imaging data output by the detector 12 to generate CT image data and material decomposition image data, the first inference unit 450 for performing inference on the material decomposition image data, the second inference unit 451 for performing inference on the CT image data, the third inference unit 452 for performing inference on composite image data obtained by combining the CT image data and the material decomposition image data, the image analysis unit 443 for analyzing the material decomposition image data and acquiring information on the content of a predetermined substance or the content of a predetermined lesion contained in the material decomposition image data, the selection unit 445 for selecting the third inference unit 452 based on the information on the content of a predetermined substance or the content of a predetermined lesion contained in the material decomposition image data, and the display control unit 446 for displaying 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.

[0130] The information processing system of this embodiment includes a first inference unit 450 that performs inference on material decomposition image data generated by reconstructing the imaging data output by the detector of the X-ray CT device, a second inference unit 451 that performs inference on CT image data generated by reconstructing the imaging data output by the detector of the X-ray CT device, a third inference unit 452 that performs inference on composite image data obtained by combining the CT image data and the material decomposition image data, an image analysis unit 443 that analyzes the material decomposition image data and obtains information on the content of a predetermined substance or the content of a predetermined lesion contained in the material decomposition image data, a selection unit 445 that selects the third inference unit 452 based on the information on the content of a predetermined substance or the content of a predetermined lesion contained in the material decomposition image data, and a display control unit 446 that displays the inference result of the selected third inference unit 452.

[0131] The information processing method of this embodiment includes the steps of: analyzing material decomposition image data generated by reconstructing the imaging data output by the detector of the X-ray CT device, and acquiring content information of a predetermined substance or content information of a predetermined lesion contained in the material decomposition image data; and performing inference on composite image data obtained by combining the CT image data and the material decomposition image data, based on the content information of a predetermined substance or content information of a predetermined lesion contained in the material decomposition image data, and displaying the inference result.

[0132] A computer program for realizing the functions of the above-described embodiments can be supplied to a computer via a network or memory (not shown), and the computer program can be executed by a processor (not shown). This is a computer program for causing a computer to execute the above-described information processing method. In other words, the computer program is a program for causing a computer to realize the functions of an information processing system. The memory stores the computer program. [Explanation of symbols]

[0133] 1 X-ray CT device 10. Gantry 11 X-ray tube 12 Detector 30 Sleeping device 40 Console device 42 Display section 43 Operation section 44 Processing circuit 441 Control Unit 442 Reconstruction Processing Unit 443 Image Analysis Unit 444 Reasoning part 445 Selection Section 446 Display control section 450 First Reasoning Part 451 Second Reasoning Part 452 Third reasoning part

Claims

1. an X-ray tube that emits X-rays; a detector that detects X-rays emitted from the X-ray tube and transmitted through the subject; a reconstruction processing unit that reconstructs the imaging data output by the detector and generates CT image data and material decomposition image data; a first inference unit that performs inference on the material decomposition image data, a second inference unit that performs inference on the CT image data, and a third inference unit that performs inference on composite image data obtained by combining the CT image data and the material decomposition image data; a selection unit that selects 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; and a display control unit that displays the inference result selected by the selection unit.

2. An X-ray CT device as described in Claim 1, characterized in that the selection unit selects the inference result of the third inference unit when the inference result of the first inference unit and the inference result of the second inference unit are different inference results.

3. The X-ray CT device described in claim 2, characterized in that the display control unit displays 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 and the inference result of the second inference unit are the same inference result.

4. 2. The X-ray CT apparatus according to claim 1, wherein the CT image data is integral image data.

5. 2. The X-ray CT apparatus according to claim 1, wherein, when the first inference unit detects a predetermined material in the material decomposition image data, the display control unit displays region information and material name information relating to the predetermined material.

6. 3. The X-ray CT apparatus according to claim 2, wherein the display control unit displays information indicating an inference made for the composite image data.

7. The X-ray CT device according to claim 1, characterized in that, when the second inference unit detects a specified lesion in the CT image data, the display control unit displays area information and lesion name information relating to the specified lesion.

8. 8. The X-ray CT apparatus according to claim 7, wherein the display control unit displays information indicating an inference made on the CT image data.

9. an image analysis unit that analyzes the material decomposition image data and acquires content information of a predetermined substance or content information of a predetermined lesion included in the material decomposition image data, 2. The X-ray CT device according to claim 1, wherein the selection unit selects at least one of the inference results of the first inference unit, the second inference unit, and the third inference unit based on content information of a predetermined substance or content information of a predetermined lesion included in the material decomposition image data.

10. 10. The X-ray CT apparatus according to claim 9, wherein the predetermined substance is any one of calcium, water, and iodine.

11. 10. The X-ray CT apparatus according to claim 9, wherein the selection unit selects the third inference unit when the material decomposition image data contains a predetermined material at a predetermined rate or more.

12. 10. The X-ray CT apparatus according to claim 9, wherein the selection unit selects the second inference unit when the material decomposition image data does not contain a predetermined material at a predetermined rate or more.

13. 10. The X-ray CT apparatus according to claim 9, further comprising a setting unit for setting the type of material to be analyzed by the image analysis unit.

14. An X-ray CT device as described in Claim 1, characterized in that the selection unit selects 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 based on an examination order.

15. a first inference unit that performs inference on material decomposition image data generated by reconstructing imaging data output by a detector of the X-ray CT device; a second inference unit that performs inference on CT image data generated by reconstructing imaging data output by a detector of the X-ray CT device; a third inference unit that performs inference on composite image data obtained by combining the CT image data and the material decomposition image data; a selection unit that selects 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; An information processing system comprising: a display control unit that displays the inference result selected by the selection unit.

16. a first inference step of performing inference on material decomposition image data generated by reconstructing imaging data output by a detector of the X-ray CT device; a second inference step of performing inference on CT image data generated by reconstructing the imaging data output by the detector of the X-ray CT device; a third inference step of performing inference on composite image data obtained by combining the CT image data and the material decomposition image data; selecting at least one of an inference result of the first inference step, an inference result of the second inference step, and an inference result of the third inference step; and a step of displaying the selected inference result.

17. A program for causing a computer to execute the information processing method according to claim 16.

Images