JP7242255B2 - X-ray CT device and detector unit - Google Patents

Description

Embodiments of the present invention relate to X-ray CT apparatus and detector units.

Response characteristics of a detector used in an X-ray CT apparatus include afterglow characteristics, charge sharing, and pile-up, and a plurality of these response characteristics occur simultaneously. Therefore, for example, when image reconstruction is performed using the output from a photon counting detector, it is necessary to correct the response characteristics of the detector.
In the correction processing of the plurality of response characteristics, a model is constructed according to each characteristic, a correction coefficient is calculated, and a value obtained by correcting the response characteristics is obtained from the acquired detector output.
However, since the plurality of response characteristics occur as a series of responses in a temporally related manner, it is very difficult to perform simultaneous correction, that is, to determine the response function and perform correction.

U.S. Pat. No. 9,833,202 U.S. Pat. No. 9,854,656 U.S. Patent Application Publication No. 2018/0192977

A problem to be solved by the present invention is to perform highly accurate correction.

The X-ray CT apparatus according to this embodiment includes an acquisition section and a correction section. The acquisition unit acquires a plurality of signals corresponding to a plurality of views including the correction target view, obtained by the same detector element. A correction unit corrects response characteristics of a detector including the detection element with respect to the signal corresponding to the correction target view based on the plurality of signals.

FIG. 1 is a block diagram showing an X-ray CT apparatus according to this embodiment. FIG. 2 is a diagram showing a method of generating a trained model according to this embodiment. FIG. 3 is a diagram showing the concept of model learning according to this embodiment. FIG. 4 is a diagram showing the concept of using a trained model according to this embodiment. FIG. 5 is a diagram showing a first input example of input data for a trained model at the time of use according to the present embodiment. FIG. 6 is a diagram showing a first input example of input data to the trained model when one time has passed from FIG. 5 . FIG. 7 is a diagram showing a second input example of input data for a trained model when using according to the present embodiment. FIG. 8 is a diagram showing a second input example of the input data to the trained model one time ahead from FIG.

An X-ray CT (Computed Tomography) apparatus and a detector unit according to this embodiment will be described below with reference to the drawings. In the following embodiments, it is assumed that parts denoted by the same reference numerals perform the same operations, and overlapping descriptions will be omitted as appropriate. An embodiment will be described below with reference to the drawings.

An X-ray CT apparatus according to this embodiment will be described below with reference to the block diagram of FIG. The X-ray CT apparatus 1 shown in FIG. 1 has a gantry device 10, a bed device 30, and a console device 40 that realizes processing of the X-ray CT device. In FIG. 1, a plurality of gantry devices 10 are depicted for convenience of explanation.

In this embodiment, the rotation axis of the rotating frame 13 in the non-tilt state or the longitudinal direction of the top plate 33 of the bed apparatus 30 is the Z-axis direction, and the axial direction perpendicular to the Z-axis direction and horizontal to the floor surface is are defined as the X-axis direction, the axis direction perpendicular to the Z-axis direction, and the Y-axis direction as the axis direction perpendicular to the floor surface.

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. Note that 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 together with 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 by wire or wirelessly so as to be able to communicate with each other.

The gantry device 10 is a scanning device having a configuration for X-ray CT imaging of the subject P. As shown in FIG. The gantry 10 includes an X-ray tube 11, an X-ray 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 , DAS (Data Acquisition System) 18).

The X-ray tube 11 is a vacuum tube that generates X-rays by irradiating thermal electrons from a cathode (filament) to an anode (target) by applying a high voltage and supplying a filament current from an X-ray high voltage device 14. is. Specifically, X-rays are generated by thermal electrons colliding with a target. For example, the X-ray tube 11 is a rotating anode type X-ray tube that generates X-rays by irradiating a rotating anode with thermal electrons. The X-rays generated by the X-ray tube 11 are shaped into a cone beam through, for example, a collimator 17 and irradiated onto the subject P. FIG.

In this embodiment, the X-ray detector 12 is assumed to be a photon counting type detector and a general X-ray detector, that is, an integrating type detector.

When the X-ray detector 12 is a photon-counting detector, it detects X-rays emitted from the X-ray tube 11 and passing through the subject P in units of photons. The X-ray detector 12 has, for example, a plurality of X-ray detection element arrays in which a plurality of X-ray detection elements are arranged in the channel direction along one circular arc centering on the focal point of the X-ray tube 11 . The X-ray detector 12 has, for example, a row structure in which a plurality of X-ray detection element rows each having a plurality of X-ray detection elements arranged in the channel direction are arranged in the slice direction (row direction).

Specifically, the X-ray detector 12 is, for example, an indirect conversion type detector having a grid, a scintillator array, and a photosensor array. The X-ray detector 12 is an example of a detection section.
The scintillator array has a plurality of scintillators. The scintillator converts incident X-rays into photons of a number corresponding to the intensity of the incident X-rays.
The grid has an X-ray shielding plate arranged on the surface of the scintillator array on the X-ray incident side and having a function of absorbing scattered X-rays. Note that the grid may also be called a collimator (one-dimensional collimator or two-dimensional collimator).
The optical sensor array has the function of amplifying the light received from the scintillator, converting it into an electrical signal, and generating an output signal (energy signal) having a peak value corresponding to the energy of the incident X-rays. It has an optical sensor such as a multiplier tube (photomultiplier: PMT). The generated energy signal is output to DAS 18 .

On the other hand, when the X-ray detector 12 is an integral detector, it detects X-rays emitted from the X-ray tube 11 and passed through the subject P, and outputs an electrical signal corresponding to the X-ray dose to the DAS 18. Output. The scintillator array has a plurality of scintillators. The scintillator has a scintillator crystal that outputs incident X-rays as light with an amount of photons corresponding to the incident X-rays. The photosensor array has a function of amplifying the light received from the scintillator and converting it into an electric signal, and has photosensors such as photomultiplier tubes (PMTs), for example.
Although the X-ray detector 12 described above is assumed to be an indirect conversion type detector, it may be a direct conversion type detector having a semiconductor element that converts incident X-rays into electrical signals. .

Rotating frame 13 supports the X-ray generator (X-ray tube 11, wedge 16 and collimator 17) and X-ray detector 12 so as to be rotatable about the rotation axis. Specifically, the rotating frame 13 is an annular frame that supports the X-ray tube 11 and the X-ray detector 12 so as to face each other and rotates the X-ray tube 11 and the X-ray detector 12 by means of a control device 15, which will be described later. is. The rotating frame 13 is rotatably supported by a fixed frame (not shown) made of metal such as aluminum. Specifically, the rotating frame 13 is connected to the edges of the stationary frame via bearings. The rotating frame 13 receives power from the drive mechanism of the control device 15 and rotates around the rotation axis Z at a constant angular velocity.

In addition to the X-ray tube 11 and the X-ray detector 12, the rotating frame 13 further includes an X-ray high-voltage device 14 and a DAS 18 to support them. Such a rotating frame 13 is accommodated in a substantially cylindrical housing in which an opening (bore) 19 forming an imaging space is formed. The aperture approximately matches the FOV. The central axis of the opening coincides with the rotational axis Z of the rotating frame 13 . The imaging data generated by the DAS 18 is provided in a non-rotating portion (for example, a fixed frame, not shown in FIG. 1) of the gantry device by optical communication from a transmitter having a light emitting diode (LED), for example. It is transmitted to a receiver (not shown) having a photodiode and forwarded to the console device 40 . Note that the method of transmitting photographed data from the rotating frame to the non-rotating portion of the gantry device is not limited to the above-described optical communication, and any method of non-contact data transmission may be adopted.

The X-ray high voltage device 14 has electric circuits such as a transformer and a rectifier, and has 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. It has a generating device and an X-ray control device for controlling the output voltage according to the X-rays emitted by the X-ray tube 11 . The high voltage generator may be of a transformer type or an inverter type. Note that the X-ray high-voltage device 14 may be provided on a rotating frame 13 to be described later, or may be provided on a fixed frame (not shown) side of the gantry device 10 .

The control device 15 has a processing circuit having a CPU (Central Processing Unit) and the like, and drive mechanisms such as motors and actuators. The processing circuit has, as hardware resources, 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). In addition, the control device 15 includes an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), and other complex programmable logic devices (Complex Programmable Logic Device: CPLD ), which may be implemented by a Simple Programmable Logic Device (SPLD). The control device 15 controls the X-ray high-voltage device 14, the DAS 18, etc. according to commands from the console device 40. FIG. The processor implements the control by reading and implementing the program stored in the memory.

The control device 15 also has a function of receiving an input signal from an input interface 43 (described later) attached to the console device 40 or the gantry device 10 and controlling the operations of the gantry device 10 and the bed device 30 . For example, the control device 15 receives an input signal and performs control to rotate the rotating frame 13 , control to tilt the gantry device 10 , and control to operate the bed device 30 and the tabletop 33 . The control for tilting the gantry device 10 is performed by the control device 15 rotating the frame about an axis parallel to the X-axis direction based on inclination angle (tilt angle) information input by the input interface 43 attached to the gantry device 10 . It is realized by rotating 13. Also, the control device 15 may be provided in the gantry device 10 or may be provided in the console device 40 . It should be noted that the control device 15 may be configured so as to directly incorporate the program into the circuit of the processor instead of storing the program in the memory. In this case, the processor implements the above control by reading and executing a program incorporated in the circuit.

Wedge 16 is a filter for adjusting the dose of X-rays emitted from X-ray tube 11 . Specifically, the wedge 16 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. It is a filter that For example, the wedge 16 (wedge filter, bow-tie filter) is a filter processed from aluminum to have a predetermined target angle and a predetermined thickness.

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. Note that the collimator 17 may also be called an X-ray diaphragm.

The DAS 18 is implemented by, for example, an ASIC (Application Specific Integrated Circuit) equipped with circuit elements capable of generating imaging data. DAS 18 and X-ray detector 12 constitute a detector unit.
When the X-ray detector 12 is a photon counting detector, the DAS 18 converts digital data (hereinafter also referred to as spectrum data) indicating the count of X-rays detected by the X-ray detector 12 into a plurality of energy bands ( Hereafter, it is generated for each energy bin or simply bin). Spectral data is a set of count value data identified by the channel number of the detector element from which it was generated, the row number, the view number indicating the acquired view (also called projection angle), and the energy bin number. Spectral data is transferred to the console device 40 .

On the other hand, when the X-ray detector 12 is an integrating detector, the DAS 18 reads an electrical signal from the X-ray detector 12 and, based on the read electrical signal, detects X-rays detected by the X-ray detector 12. Generate projection data, which is digital data about dose. The projection data is a set of data indicating the channel number and row number of the X-ray detection element from which it was generated, the view number indicating the acquired view (also called projection angle), and the integral value of the detected X-ray dose. be.
For example, DAS 18 includes preamplifiers, variable amplifiers, integrators and A/D converters for each sensing element. The preamplifier amplifies the electrical signal from the connected detection element with a predetermined gain. A variable amplifier amplifies the electrical signal from the preamplifier with a variable gain. An integrator circuit integrates the electrical signal from the preamplifier over one view period to generate an integrated signal. The crest value of the integral signal corresponds to the X-ray dose value detected by the connection-source detection element over one view period. The A/D converter analog-to-digital converts the integration signal from the integration circuit to generate projection data. Hereinafter, when spectral data and projection data are not distinguished from each other, they are referred to as imaging data.

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 as to be vertically movable.
The bed driving device 32 is a motor or actuator that moves the table 33 on which the subject P is placed in the longitudinal direction of the table 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 top plate 33 in a direction orthogonal to the subject P so that the body axis of the subject P placed on the top plate 33 coincides with the central axis of the opening of the rotating frame 13 . do. Further, the bed driving device 32 may move the top board 33 along the body axis direction of the subject P according to the X-ray CT imaging performed using the gantry device 10 . The bed drive device 32 generates power by driving at a rotational speed according to the duty ratio of the drive signal from the control device 15 and the like. The bed driving device 32 is realized by a motor such as a direct drive motor or a servo motor, for example.

A top plate 33 provided on the upper surface of the support frame 34 is a plate on which the subject P is placed. Note that the bed driving device 32 may move the support frame 34 in the longitudinal direction of the top plate 33 in addition to the top plate 33 .

The console device 40 has a memory 41 , a display 42 , an input interface 43 and a processing circuit 44 . Data communication between the memory 41, the display 42, the input interface 43, and the processing circuit 44 is performed via a bus (BUS). Note that the console device 40 is described as being separate from the gantry device 10 , but the console device 40 or a part of each component of the console device 40 may be included in the gantry device 10 .

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, photographed data and reconstructed image data. The memory 41 can be connected to portable storage media such as CDs (Compact Discs), DVDs (Digital Versatile Discs), flash memories, semiconductor memory devices such as RAMs (Random Access Memory), etc., in addition to HDDs and SSDs. It may also be a driving device that reads and writes various information with. Also, the storage area of the memory 41 may be in the X-ray CT apparatus 1 or in an external storage device connected via a network. For example, the memory 41 stores data of CT images and display images. The memory 41 also stores a control program according to this embodiment.

The display 42 displays various information. For example, the display 42 outputs a medical image (CT image) generated by the processing circuit 44, a GUI (Graphical User Interface) for accepting various operations from the operator, and the like. For example, the display 42 may be, for example, a liquid crystal display (LCD: Liquid Crystal Display), a CRT (Cathode Ray Tube) display, an organic EL display (OELD: Organic Electro Luminescence Display), a plasma display, or any other arbitrary display. , is enabled. Also, the display 42 may be provided on the gantry device 10 . The display 42 may be of a desktop type, or may be configured by a tablet terminal capable of wireless communication with the main body of the console device 40, or the like.

The input interface 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 input interface 43 receives from the operator acquisition conditions for acquiring imaging data, reconstruction conditions for reconstructing CT images, image processing conditions for generating post-processed images from CT images, and the like. . As the input interface 43, for example, a mouse, keyboard, trackball, switch, button, joystick, touch pad, touch panel display, etc. can be used as appropriate. In addition, in the present embodiment, the input interface 43 is not limited to physical operation components such as a mouse, keyboard, trackball, switch, button, joystick, touch pad, and touch panel display. For example, the input interface 43 includes 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. . The input interface 43 may be provided on the gantry device 10 . Also, the input interface 43 may be composed of a tablet terminal or the like capable of wireless communication with the main body of the console device 40 .

The processing circuit 44 controls the operation of the entire X-ray CT apparatus 1 according to the electric signal of the input operation output from the input interface 43 . For example, the processing circuit 44 has, as hardware resources, processors such as a CPU, MPU, and GPU (Graphics Processing Unit), and memories such as a ROM and a RAM. The processing circuit 44 executes a system control function 441 , an acquisition function 442 , a selection function 443 , a correction function 444 , a reconstruction processing function 445 and a display control function 446 by means of a processor that executes programs developed in memory. Each function (the system control function 441, the acquisition function 442, the selection function 443, the correction function 444, the reconstruction processing function 445, and the display control function 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 function may be realized by each processor executing a program.

The system control function 441 controls each function of the processing circuit 44 based on input operations received from the operator via the input interface 43 . Specifically, the system control function 441 reads the control program stored in the memory 41, develops it on the memory in the processing circuit 44, and controls each part of the X-ray CT apparatus 1 according to the developed control program. . For example, the processing circuit 44 controls each function of the processing circuit 44 based on an input operation received from the operator via the input interface 43 . For example, the system control function 441 acquires a two-dimensional positioning image of the subject P for determining the scan range, imaging conditions, and the like. A positioning image is also called a scanogram or a scout image. The system control function 441 is an example of a system control unit.

Acquisition function 442 acquires multiple signals at each detector element of x-ray detector 12 corresponding to multiple views obtained with the same detector element. The multiple views include a correction target view, which is a view to be corrected. A plurality of signals corresponding to a plurality of views represent historical data of signal values over time. Acquisition function 442 is an example of an acquisition unit.
When a trained model generated for each X-ray condition is generated, the selection function 443 refers to the trained model generated for each X-ray condition, and selects an X-axis when acquiring the signal of the view to be processed. Select a trained model that corresponds to the line condition.

The correction function 444 corrects the response characteristics of the X-ray detector 12 including the detection elements for the signals corresponding to the correction target view based on the multiple signals acquired by the acquisition function 442 . For example, the correction function 444 receives a plurality of signals and adjusts the response of the X-ray detector 12 with respect to the signal corresponding to the correction target view according to a learned model that outputs a signal in which the response characteristics of the X-ray detector 12 are corrected. Generates a signal with corrected characteristics. In the present embodiment, “a signal whose response characteristics of the X-ray detector have been corrected” means a signal estimated to be output from an X-ray detector whose response characteristics have been corrected. The correction function 444 is an example of a processing unit.
The reconstruction processing function 445 performs reconstruction processing using a filtered back projection method (FBP method: Filtered Back Projection), an iterative reconstruction method, etc. on the imaging data corrected by the correction function 444, and performs CT. Generate image data.
The display control function 446 controls the display 42 so as to display information on the progress or results of each function or process of the processing circuit 44 .

The processing circuit 44 also performs scan control processing and image processing.
The scan control process is a process of controlling various operations related to X-ray scanning, such as causing the X-ray high-voltage device 14 to supply a high voltage and causing the X-ray tube 11 to emit X-rays.

Image processing converts CT image data generated by the reconstruction processing function 445 into tomographic image data or three-dimensional image data of an arbitrary cross section based on input operations received from the operator via the input interface 43. is. Note that the generation of the three-dimensional image data may be directly performed by the reconstruction processing function 445 .

The processing circuit 44 is not limited to being included in the console device 40, and may be included in an integrated server that collectively processes data acquired by a plurality of medical image diagnostic apparatuses.
Although the console device 40 has been described as executing a plurality of functions with a single console, the plurality of functions may be executed by separate consoles. For example, the functions of the processing circuit 44 such as the acquisition function 442 and the correction function 444 may be distributed.

Next, a method of generating a trained model used by the correction function 444 will be described with reference to FIG.
FIG. 2 is a block diagram showing an example of a medical information processing system that generates trained models. The medical information processing system shown in FIG. 2 includes an X-ray CT apparatus 1 , a learning data storage device 20 and a model learning device 22 .

The learning data storage device 20 stores learning data including multiple learning samples. For example, the learning data storage device 20 is a computer with a built-in mass storage device. The learning data storage device 20 may also be a mass storage device communicatively connected to a computer via a cable or communication network. As the storage device, an HDD, an SSD, an integrated circuit storage device, or the like can be used as appropriate.

The model learning device 22 generates a trained model 411 by causing the model to perform machine learning according to a model learning program based on the learning data stored in the learning data storage device 20 . In the present embodiment, neural networks, deep learning, especially recurrent neural networks (RNNs) capable of handling time-series data, LSTMs (Long Short-Term Memory), etc., are assumed as machine learning algorithms. However, it is not limited to this, and other machine learning algorithms such as Hidden Markov Model (HMM) may be used. RNNs have loops in internal intermediate layers, called hidden layers, that allow information to persist until processing at a later time. Also, LSTM is a network that can learn long-term information dependencies better than RNN. The model learning device 22 is a computer such as a workstation having a processor such as CPU and GPU.

The model learning device 22 and the learning data storage device 20 may be communicably connected via a cable or a communication network. Also, the learning data storage device 20 may be installed in the model learning device 22 . In these cases, learning data is supplied from the learning data storage device 20 to the model learning device 22 . Note that the model learning device 22 and the learning data storage device 20 do not have to be communicably connected. In this case, the learning data is supplied from the learning data storage device 20 to the model learning device 22 via the portable storage medium storing the learning data.

The X-ray CT apparatus 1 and the model learning apparatus 22 may be communicably connected via a cable or a communication network. A trained model 411 generated by the model learning device 22 is supplied to the X-ray CT apparatus 1 and the trained model 411 is stored in the memory 41 . Note that the X-ray CT apparatus 1 and the model learning apparatus 22 do not necessarily have to be communicably connected. In this case, the trained model 411 is supplied from the model learning device 22 to the X-ray CT apparatus 1 via a portable storage medium or the like in which the trained model 411 is stored.

Note that the trained model 411 can also be said to be a parameterized synthetic function obtained by synthesizing a plurality of functions. A parameterized composite function is defined by a combination of multiple adjustable functions and parameters. A trained model can be any parameterized composite function that meets the above requirements.

Note that the trained model 411 according to the present embodiment is generated by subjecting a multi-layered network (simply referred to as a model) before machine learning to machine learning using an algorithm that handles time-series data represented by RNN or LSTM. . Not limited to RNN and LSTM, the trained model 411 may be generated by learning a model using the machine learning algorithm described above.

Next, the concept of model learning by the model learning device 22 will be described with reference to FIG.
The model learning device 22 machine-learns the multi-layered network 410 using the learning data. In order to correct the response characteristics of each detection element of the X-ray detector 12, learning data is created for each detection element. Also, the response characteristics of the X-ray detector 12 change depending on the X-ray conditions. For example, when the value of the tube current is large, the number of photons detected by the detection element increases compared to when the value of the tube current is small, and the pile-up characteristic changes according to the value of the tube current. Therefore, the model learning device 22 learns the model including the X-ray conditions.

In the following example, the X-ray detector 12 is a photon-counting detector, and multiple signals as input data are spectral data for multiple views obtained by one detector element for each view. assume. Note that the plurality of signals as input data are integrated values of signals detected by the detection elements when the X-ray detector 12 is of the integral type.

When learning the model, for example, at the time of shipment from the factory, the spectrum data 61 of a plurality of views in which the subject P was actually imaged and the X-ray conditions 63 at the time of imaging are used as input data, and the X-ray conditions 63 at the time of imaging are set. Learning data obtained by using one ideal spectrum data 65 simulated as correct data (output data) is used. The model learning device 22 trains the multi-layered network 410 using the learning data to generate a trained model 411 . The X-ray conditions 63 include, for example, tube voltage (kV), tube current (mA), view rate, filter information, and collimator information. Note that the learned model 411 may be updated when the X-ray CT apparatus 1 is repaired or software is updated.

As the subject P, a phantom, a deceased patient, a living animal, or a dead animal may be used in addition to a patient, a healthy person, or the like.

When imaging the subject P and collecting input data, materials (air, water, elements) and thickness are taken into consideration as transmission conditions. In particular, when the subject P is a phantom, it is desirable to use a phantom such as an elliptical cylinder in which the thickness of the subject through which the X-ray path passes varies as the rotating frame 13 rotates.
In addition, when learning the model, it is also possible to learn the variation for each energy band. For example, the spectrum data 61 is obtained by applying a filter made of a metal with a relatively small atomic number that affects the low energy side. Furthermore, spectral data 51 is obtained by applying a filter made of metal (Pb, w) having a large atomic number that affects the high energy side, that is, attenuates high energy components. After that, the acquired spectrum data 61 may be learned according to the X-ray conditions 63 .

The ideal spectrum data 65 is assumed by the simulation to be imaging data that has passed through the subject P, so it is not affected by the response characteristics of the X-ray detector 12 .
On the other hand, spectrum data 61 obtained by actually imaging the subject P is affected by multiple response characteristics of the X-ray detector 12 . Spectral data 61 is affected by interactions between these multiple response characteristics. The multiple response characteristics are temporally dependent, in other words time-varying. The response characteristics of the X-ray detector 12 include, for example, charge sharing characteristics, afterglow characteristics (afterglow characteristics), and pile-up characteristics. The charge sharing characteristic is a characteristic that the charge generated by the incident X-ray spreads over adjacent detection elements depending on the incident angle of the incident X-ray. The afterglow characteristic is a characteristic related to decay time in which an image captured at a previous time also remains in an image captured at the next time. The pile-up characteristic is a characteristic that depends on the short interval between incident photons on the detection element.

In the present embodiment, the multi-view spectrum data 61 is learned as input data, so that the response characteristics can be appropriately corrected without the need to separate and correct the above-described interaction and temporal dependence of the plurality of response characteristics. can be done.

Also, the spectrum data 61 of a plurality of views used as input data is input data together with the spectra of a plurality of views before in terms of time as history data. The number of spectral data, ie the number of views, is determined based on the X-ray conditions, the subject P, the rotational speed of the rotating frame 13 and the decay time for the X-ray detector 12 . For example, the maximum number of views acquired when the rotating frame 13 rotates once may be appropriately designed to be less than or equal to the maximum number of views. As a design guideline, for example, considering the afterglow characteristics, the number of views acquired from the time when a certain view is captured until the time when the afterglow component generated at the time of the view becomes equal to or less than a threshold is The number of views (the number of spectral data) used for input data may be used.

The "decay time" in the afterglow characteristics is the fluorescence decay time of the scintillator when the X-ray detector 12 is of the indirect conversion type. On the other hand, when the X-ray detector 12 is of the direct conversion type, the "attenuation time" in the afterglow characteristics is the time it takes for the charge to return from a non-uniform state to a uniform state.

Next, the concept of using the trained model 411 machine-learned in FIG. 3 will be described with reference to FIG.
When the learned model 411 is used, the correction function 444 causes the processing circuit 44 to input a plurality of spectral data 67 to be processed that have been captured using the X-ray CT apparatus 1 and the X-ray conditions 63 at the time of imaging as input data. Input to the trained model 411 . The learned model 411 outputs corrected spectral data 69 in which the response characteristics of the X-ray detector 12 are corrected according to the input spectral data 67 . The corrected spectral data 69 is spectral data in which components dependent on response characteristics related to signal deterioration are reduced from the input data. In other words, the corrected spectral data 69 is spectral data estimated to be generated by the X-ray detector 12 and DAS 18 having ideal response characteristics.

Next, a first input example of input data to the trained model 411 at the time of use will be described with reference to FIGS. 5 and 6. FIG.
FIG. 5 shows an example of using the trained model 411 at a certain point in time. The spectrum data assumed in the present embodiment are represented by count value data divided for each energy band (bin). The example of FIG. 5 assumes an RNN as the trained model 411 , and the trained model 411 has an input layer 4111 , an intermediate layer 4113 and an output layer 4115 . As input data, spectrum data of 3 views that are two views back from the current time (T) and X-ray conditions at the time of imaging are used. Each spectral data is represented by three bins.

In the first input example, three spectral data are input to the trained model 411 at once. That is, spectral data 51 at time (T), spectral data 52 at time (T-1), and spectral data 53 at time (T-2) are input to trained model 411 at once.

Also, as shown in FIG. 5 , the count value of each bin of each spectral data is input to each node of the input layer 4111 of the trained model 411 . Specifically, the count values of three bins E(1), E(2) and E(3) of the spectrum data 51 are input data E(1,T), input data E(2,T) and input data E(3, T) to the nodes of the input layer 4111, respectively. Spectral data 52 and spectral data 53 are similarly input to the node.

In the trained model 411 , processing is executed by the intermediate layer 4113 that receives data from the input layer 4111 and outputs data to the output layer 4115 . The output layer 4115 outputs corrected spectrum data obtained by correcting the response characteristic of the X-ray detector 12 for the spectrum data at time (T).

Next, FIG. 6 shows the case where the spectrum data in the next view is processed one time ahead. When one time advances, three spectrum data advanced one time series are input. That is, the spectral data 55 at the time (T+1), the spectral data 51 at the time (T), and the spectral data 52 at the time (T-1) are input to the trained model 411 at once. The trained model 411 performs the same processing as in FIG. 5, and the output layer 4115 outputs corrected spectral data obtained by correcting the response characteristics of the X-ray detector 12 for the spectral data at time (T+1).

Next, a second input example of input data to the trained model 411 at the time of use will be described with reference to FIGS. 7 and 8. FIG.
In the second input example, spectral data are input to the trained model one by one in chronological order.

In the trained model 411 , the process is executed after spectral data for the same number of views at the time of learning is accumulated, and corrected spectral data is output from the trained model 411 . Therefore, for example, when spectral data for three views are used as input data for learning data during learning, spectral data for three views may be input at once only for the initial input when using the trained model 411. However, spectral data may be input in chronological order, and corrected spectral data may not be output from the learned model until spectral data for three views are accumulated.

In FIG. 7, the spectral data at time (T-2) and the spectral data at time (T-1) have already been input to the trained model 411 (not shown), and then the spectral data at time (T). is input.

When the spectral data at time (T) is input, from the learned model 411 based on the input data of spectral data for three views together with the spectral data at time (T-2) and time (T-1) Corrected spectral data is output.

Next, FIG. 8 shows a case where the spectrum data in the next view is processed one time ahead. When one hour has passed, the spectrum data 55 at time (T+1) is input to the learned model 411 . Spectral data 52 at time (T−1) and spectral data 51 at time (T) have already been input to trained model 411 . Therefore, based on the three spectral data at time (T−1), time (T), and time (T+1), intermediate layer 4113 performs the same processing as in FIG. Corrected spectral data 54 obtained by correcting the response characteristic of the X-ray detector 12 is output.

In the above example, a trained model that outputs corrected spectrum data in which the detector response is corrected according to the X-ray conditions is assumed by learning including the X-ray conditions. A trained model may be generated. In this case, when using a trained model, the selection function 443 causes the processing circuitry 44 to select a trained model according to the X-ray conditions when the subject P is measured, ie when the signal of the target view is acquired. The correction function 444 causes the processing circuit 44 to output corrected spectral data obtained by correcting the response characteristics included in the spectral data according to the learned model corresponding to the X-ray condition selected by the selection function 443 .

In the above example, the spectrum data at the current time is input to the learned model 411, and the spectrum data at the current time whose response characteristics are corrected is output. Data obtained by correcting the response characteristics of the spectrum data at the previous time may be output. Specifically, the trained model 411 receives, for example, three spectral data at time (T-2), time (T-1), and time T, and the time (T-1 ) may be designed to output data whose response characteristics have been corrected.

In the above example, the processing circuit 44 executes the acquisition function 442, the selection function 443 and the correction function 444. However, this is not limitative, and the processing circuit for executing the acquisition function 442, the selection function 443 and the correction function 444 in the DAS 18. may include That is, the detector unit, not the console device 40, may correct the response characteristics of the X-ray detector 12 using the processing circuit.

According to the first embodiment described above, it is possible to input history data including time-series information as a plurality of signals from the X-ray detector, and output signals in which the response characteristics of the X-ray detector are corrected. As a result, it is possible to perform quick and highly accurate correction processing without constructing a complicated model that takes into account the time-series interaction between response characteristics, and the reliability of subsequent CT image reconstruction and spectral image reconstruction. can improve sexuality.

In addition, according to the X-ray CT apparatus according to the present embodiment, by using a trained model, mutual correction between response characteristics can be performed without individually correcting charge sharing characteristics, afterglow characteristics, and pile-up characteristics. Appropriate correction of response characteristics can be performed including effects. Therefore, a CT image with improved image quality (contrast, noise) can be generated. Therefore, it is possible to obtain a high-quality image while suppressing costs.
In addition, since it is not necessary to separately perform the response characteristic correction processing by software, the calculation time for the response characteristic correction processing by software can be omitted, and the overall calculation time for the processing can be shortened. As a result, efficiency of processing can be improved.

The X-ray CT apparatus includes a Rotate/Rotate-Type (3rd generation CT) in which the X-ray tube and detector are rotated around the subject P as a unit, and a large number of X-ray detectors arrayed in a ring. There are various types such as Stationary/Rotate-Type (4th generation CT) in which the element is fixed and only the X-ray tube rotates around the subject P, and any type can be applied to this embodiment.

Note that hardware for generating X-rays is not limited to the X-ray tube 11 . For example, in place of the X-ray tube 11, a focus coil for converging the electron beam generated from the electron gun, a deflection coil for electromagnetic deflection, and the deflected electron beam surrounding the half circumference of the subject P collide with each other to emit X-rays. X-rays may be generated using a fifth generation system including a target ring to be generated.

Furthermore, in the present embodiment, both a single-tube type X-ray CT apparatus and a so-called multi-tube type X-ray CT apparatus in which a plurality of pairs of X-ray tubes and detectors are mounted on a rotating ring can be used. Applicable.

In addition, each function according to the embodiment can also be realized by installing a program for executing the above processing in a computer such as a workstation and deploying them on the memory. At this time, the program that allows the computer to execute the above method can be distributed by being stored in a storage medium such as a magnetic disk (hard disk, etc.), optical disk (CD-ROM, DVD, etc.), semiconductor memory, or the like. .

While several embodiments of the invention have been described, these embodiments have been presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, as well as the scope of the invention described in the claims and equivalents thereof.

Reference Signs List 1 X-ray CT apparatus 10 Mounting device 11 X-ray tube 12 X-ray detector 13 Rotating frame 14 X-ray high voltage device 15 Control device 16 Wedge 17 Collimator 18 Data acquisition device (DAS)
19 aperture (bore)
20 learning data storage device 22 model learning device 30 bed device 31 base 32 bed driving device 33 table top 34 support frame 40 console device 41 memory 42 display 43 input interface 44 processing circuit 51, 52, 53, 55, 61, 67 spectrum Data 54, 69 Corrected spectral data 63 X-ray conditions 65 Ideal spectral data 410 Multilayered network 411 Trained model 441 System control function 442 Acquisition function 443 Selection function 444 Correction function 445 Reconstruction processing function 446 Display control function 4111 Input layer 4113 Intermediate layer 4115 output layer

Claims (11)

an acquisition unit that acquires a plurality of signals corresponding to a plurality of views including a correction target view obtained by the same detection element;
A signal obtained by correcting the response characteristics of the detector with respect to the signal of the correction target view according to a trained model that receives the plurality of signals and outputs a signal obtained by correcting the response characteristics of the detector including the detection element. a correction unit to generate;
An X-ray CT apparatus comprising: 2. The method according to claim 1 , further comprising a selection unit that refers to learned models generated for each X-ray condition and selects a learned model corresponding to the X-ray condition when acquiring the signal of the correction target view. of the X-ray CT apparatus. 3. The X-ray CT apparatus according to claim 1 , wherein said trained model is generated by learning using RNN (Recurrent Neural Network) or LSTM (Long Short-Term Memory). 4. The X of any one of claims 1 to 3, wherein the number of views is determined based on X-ray conditions, subject, rotation speed of a rotating frame and decay time for the detector. Line CT device. 5. The X-ray CT apparatus according to claim 4 , wherein said decay time is fluorescence decay time of a scintillator when said detector is of indirect conversion type. 5. The X-ray CT apparatus according to claim 4 , wherein said decay time is the time for the charge to return from a non-uniform state to a uniform state when said detector is of the direct conversion type. The plurality of signals are integrated values of signals detected by a detection element when the detector is an integrating detector, and are detected by a detection element when the detector is a photon counting detector. 7. The X-ray CT apparatus according to any one of claims 1 to 6 , which is a count value for each bin of the signal. The acquisition unit captures an image of a subject under a given X-ray condition, and includes input data for learning, which are a plurality of signals corresponding to a plurality of views acquired by the detection element, and the given X-ray condition. 8. The X-ray CT according to any one of claims 1 to 7, wherein the correct data for learning, which is the signal transmitted through the subject acquired by the simulation in , is acquired as learning data. Device. an acquisition unit that acquires a plurality of signals corresponding to a plurality of views including a correction target view obtained by the same detection element;
a correction unit that corrects, based on the plurality of signals, the response characteristics of a detector including the detection element for the signal corresponding to the correction target view;
the number of views is determined based on x-ray conditions, a subject, a rotation rate of a rotating frame and a decay time for the detector;
X-ray CT equipment. an acquisition unit that acquires a plurality of signals corresponding to a plurality of views including a correction target view obtained by the same detection element;
a correction unit that corrects, based on the plurality of signals, the response characteristics of a detector including the detection element for the signal corresponding to the correction target view;
The acquisition unit captures an image of a subject under a given X-ray condition, and includes input data for learning, which are a plurality of signals corresponding to a plurality of views acquired by the detection element, and the given X-ray condition. Acquiring the correct data for learning, which is the signal transmitted through the subject acquired by the simulation in , as learning data;
X-ray CT equipment. a detector including a plurality of detector elements for detecting X-rays;
an acquisition unit that acquires a plurality of signals corresponding to a plurality of views including a correction target view obtained by the same detection element;
A signal obtained by correcting the response characteristics of the detector with respect to the signal of the correction target view according to a trained model that receives the plurality of signals and outputs a signal obtained by correcting the response characteristics of the detector including the detection element. a correction unit to generate;
A detector unit comprising:

Images