JP2021010623A - X-ray ct system and medical processing device - Google Patents

Abstract

To generate high quality CT image data.SOLUTION: An X-ray CT system includes a scan part and a processing part. After collecting a first projection data set by radiating an X-ray in a first range along a body axial direction of a subject, the scan part collects a second projection data set by radiating an X-ray in a second range narrower than the first range along the body axial direction. On the basis of at least a part of the first projection data set or first image data based on the at least a part of the first projection data set, and the second projection data set or second image data based on the second projection data set, the processing part generates a third projection data set or third image data by inputting the first projection data set or the first image data, and the second projection data set or the second image data into a learned model that generates the third projection data set or the third image data of higher quality than the second production data set or the second image data.SELECTED DRAWING: Figure 3

Description

Embodiments of the present invention relate to X-ray CT systems and medical processing devices.

The CT image data collected by the X-ray CT (Computed Tomography) scanner may include noise and image artifacts due to various factors. Specifically, projection data is lost or noise is included in the projection data due to factors such as the body movement of the subject, fluctuations in the output from the X-ray tube, and attenuation of X-rays according to the body thickness of the subject. The reconstructed CT image data may contain noise and image artifacts due to the loss.

In order to improve the quality of CT image data, it has been proposed to correct the projection data set used for the reconstruction process and the reconstructed CT image data by AI (Artificial Intelligence). Here, in order to properly perform the correction by AI, it is preferable that learning based on more information is performed.

Japanese Unexamined Patent Publication No. 2012-130667 International Publication No. 2017/141958 JP-A-2017-86903

The problem to be solved by the present invention is to generate high quality CT image data.

The X-ray CT system of the embodiment includes a scanning unit and a processing unit. The scanning unit executes a first scan for collecting a first projection data set by irradiating a first range along the body axis direction of the subject with X-rays, and after the first scan, the body. A second scan is performed to collect the second projection data set by irradiating a second area along the axial direction, which is narrower than the first area, with X-rays. The processing unit has a first image data based on at least a part of the first projection data set or at least a part of the first projection data set, and a second based on the second projection data set or the second projection data set. The first projection data for a trained model that generates the third projection data set or the third image data, which is of higher quality than the second projection data set or the second image data, based on the image data. By inputting the set or the first image data and the second projection data set or the second image data, the third projection data set or the third image data is generated.

FIG. 1 is a block diagram showing an example of the configuration of the X-ray CT system according to the first embodiment. FIG. 2 is a diagram for explaining a trained model generation process according to the first embodiment. FIG. 3 is a diagram showing a usage example of the trained model according to the first embodiment. FIG. 4 is a flowchart for explaining a series of processes of the X-ray CT system according to the first embodiment. FIG. 5 is a block diagram showing an example of the configuration of the medical information processing system according to the third embodiment.

Hereinafter, embodiments of the X-ray CT system and the medical processing apparatus will be described in detail with reference to the accompanying drawings. The X-ray CT system and the medical processing apparatus according to the present application are not limited to the embodiments shown below.

(First Embodiment)
First, the configuration of the X-ray CT system 10 according to the first embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing an example of the configuration of the X-ray CT system 10 according to the first embodiment. As shown in FIG. 1, the X-ray CT system 10 includes a gantry device 110, a sleeper device 130, and a console device 140. The X-ray CT system 10 is also called an X-ray CT apparatus or an X-ray CT scanner.

In FIG. 1, the rotation axis of the rotation frame 113 in the non-tilt state or the longitudinal direction of the top plate 133 of the sleeper device 130 is the Z-axis direction. Further, the axial direction orthogonal to the Z-axis direction and horizontal to the floor surface is defined as the X-axis direction. Further, the axial direction orthogonal to the Z-axis direction and perpendicular to the floor surface is defined as the Y-axis direction. Note that FIG. 1 is a drawing of the gantry device 110 from a plurality of directions for the sake of explanation, and shows a case where the X-ray CT system 10 has one gantry device 110.

The gantry device 110 includes an X-ray tube 111, an X-ray detector 112, a rotating frame 113, an X-ray high voltage device 114, a control device 115, a wedge 116, a collimator 117, and a DAS 118.

The X-ray tube 111 is a vacuum tube having a cathode (filament) that generates thermoelectrons and an anode (target) that generates X-rays upon collision of thermions. The X-ray tube 111 generates X-rays to irradiate the subject P1 by irradiating thermions from the cathode toward the anode by applying a high voltage from the X-ray high voltage device 114.

The X-ray detector 112 detects the X-rays irradiated from the X-ray tube 111 and passed through the subject P1, and outputs a signal corresponding to the detected X-ray dose to the DAS 118. The X-ray detector 112 has, for example, a plurality of detection element sequences in which a plurality of detection elements are arranged in a channel direction (channel direction) along one arc centered on the focal point of the X-ray tube 111. The X-ray detector 112 has, for example, a structure in which a plurality of detection element sequences in which a plurality of detection elements are arranged in the channel direction are arranged in a row direction (slice direction, row direction).

For example, the X-ray detector 112 is an indirect conversion type detector having a grid, a scintillator array, and an optical sensor array. The scintillator array has a plurality of scintillators. The scintillator has a scintillator crystal that outputs a photon amount of light according to the incident X dose. The grid is arranged on the surface of the scintillator array on the X-ray incident side and has an X-ray shield plate that absorbs scattered X-rays. The grid may also be called a collimator (one-dimensional collimator or two-dimensional collimator). The optical sensor array has a function of converting into an electric signal according to the amount of light from the scintillator, and has, for example, an optical sensor such as a photodiode. The X-ray detector 112 may be a direct conversion type detector having a semiconductor element that converts incident X-rays into an electric signal.

The rotating frame 113 is an annular frame that supports the X-ray tube 111 and the X-ray detector 112 so as to face each other, and rotates the X-ray tube 111 and the X-ray detector 112 by the control device 115. For example, the rotating frame 113 is a casting made of aluminum. In addition to the X-ray tube 111 and the X-ray detector 112, the rotating frame 113 can further support an X-ray high voltage device 114, a wedge 116, a collimator 117, a DAS 118, and the like. Further, the rotating frame 113 can further support various configurations (not shown in FIG. 1). In the following, in the gantry device 110, the rotating frame 113 and the portion that rotates and moves together with the rotating frame 113 are also referred to as a rotating portion.

The X-ray high-voltage device 114 has an electric circuit such as a transformer and a rectifier, and has a high-voltage generator that generates a high voltage applied to the X-ray tube 111 and an X-ray that is generated by the X-ray tube 111. It has an X-ray control device that controls the output voltage according to the above. The high voltage generator may be a transformer type or an inverter type. The X-ray high voltage device 114 may be provided on the rotating frame 113, or may be provided on a fixed frame (not shown).

The control device 115 includes a processing circuit having a CPU (Central Processing Unit) and the like, and a drive mechanism such as a motor and an actuator. The control device 115 receives the input signal from the input interface 143 and controls the operation of the gantry device 110 and the sleeper device 130. For example, the control device 115 controls the rotation of the rotating frame 113, the tilt of the gantry device 110, the operation of the sleeper device 130, and the like. As an example, the control device 115 rotates the rotating frame 113 about an axis parallel to the X-axis direction based on the input tilt angle (tilt angle) information as a control for tilting the gantry device 110. The control device 115 may be provided in the gantry device 110 or in the console device 140.

The wedge 116 is an X-ray filter for adjusting the X-ray dose emitted from the X-ray tube 111. Specifically, the wedge 116 is an X-ray filter that attenuates the X-rays emitted from the X-ray tube 111 so that the X-rays emitted from the X-ray tube 111 to the subject P1 have a predetermined distribution. Is. For example, the wedge 116 is a wedge filter or a bow-tie filter, and is manufactured by processing aluminum or the like so as to have a predetermined target angle and a predetermined thickness.

The collimator 117 is a lead plate or the like for narrowing the irradiation range of X-rays transmitted through the wedge 116, and a slit is formed by a combination of a plurality of lead plates or the like. The collimator 117 may be called an X-ray diaphragm. Further, in FIG. 1, the case where the wedge 116 is arranged between the X-ray tube 111 and the collimator 117 is shown, but the case where the collimator 117 is arranged between the X-ray tube 111 and the wedge 116. May be good. In this case, the wedge 116 is irradiated from the X-ray tube 111, and the X-ray whose irradiation range is limited by the collimator 117 is transmitted and attenuated.

The DAS 118 collects X-ray signals detected by each detection element included in the X-ray detector 112. For example, the DAS 118 has an amplifier that amplifies an electric signal output from each detection element and an A / D converter that converts the electric signal into a digital signal, and generates detection data. DAS118 is realized by, for example, a processor.

The data generated by the DAS 118 is transmitted from a transmitter having a light emitting diode (LED) provided on the rotating frame 113 by optical communication to a non-rotating portion (for example, a fixed frame, etc.) of the gantry device 110. Is transmitted to a receiver having a light diode provided in (not shown in the above) and transferred to the console device 140. Here, the non-rotating portion is, for example, a fixed frame that rotatably supports the rotating frame 113. The method of transmitting data from the rotating frame 113 to the non-rotating portion of the gantry device 110 is not limited to optical communication, and any non-contact data transmission method may be adopted, and the contact-type data transmission method may be used. You may adopt it.

The sleeper device 130 is a device for placing and moving the subject P1 to be scanned, and has a base 131, a sleeper drive device 132, a top plate 133, and a support frame 134. The base 131 is a housing that supports the support frame 134 so as to be movable in the vertical direction. The sleeper drive device 132 is a drive mechanism for moving the top plate 133 on which the subject P1 is placed in the long axis direction of the top plate 133, and includes a motor, an actuator, and the like. The top plate 133 provided on the upper surface of the support frame 134 is a plate on which the subject P1 is placed. In addition to the top plate 133, the sleeper drive device 132 may move the support frame 134 in the long axis direction of the top plate 133.

The console device 140 has a memory 141, a display 142, an input interface 143, and a processing circuit 144. Although the console device 140 will be described as a separate body from the gantry device 110, the gantry device 110 may include a part of each component of the console device 140 or the console device 140.

The memory 141 is realized by, for example, a RAM (Random Access Memory), a semiconductor memory element such as a flash memory, a hard disk, an optical disk, or the like. For example, the memory 141 stores various data collected by performing a scan on the subject P1. Further, for example, the memory 141 stores a program for the circuit included in the X-ray CT system 10 to realize its function. The memory 141 may be realized by a server group (cloud) connected to the X-ray CT system 10 via a network.

The display 142 displays various information. For example, the display 142 displays a CT image for display generated by the processing circuit 144, and displays a GUI (Graphical User Interface) or the like for receiving various operations from the user. For example, the display 142 is a liquid crystal display or a CRT (Cathode Ray Tube) display. The display 142 may be a desktop type, or may be composed of a tablet terminal or the like capable of wireless communication with the console device 140 main body.

The input interface 143 receives various input operations from the user, converts the received input operations into an electric signal, and outputs the received input operations to the processing circuit 144. For example, the input interface 143 receives from the user reconstruction conditions for reconstructing CT image data, image processing conditions for generating a CT image for display from CT image data, and the like. For example, the input interface 143 includes a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touch pad for performing input operations by touching an operation surface, a touch screen in which a display screen and a touch pad are integrated, and an optical sensor. It is realized by the non-contact input circuit, voice input circuit, etc. used. The input interface 143 may be provided on the gantry device 110. Further, the input interface 143 may be composed of a tablet terminal or the like capable of wireless communication with the console device 140 main body. Further, the input interface 143 is not limited to the one provided with physical operating parts such as a mouse and a keyboard. For example, an electric signal processing circuit that receives an electric signal corresponding to an input operation from an external input device provided separately from the console device 140 and outputs the electric signal to the processing circuit 144 is also an example of the input interface 143. included.

The processing circuit 144 controls the operation of the entire X-ray CT system 10 by executing the scanning function 144a, the processing function 144b, and the control function 144c. The scanning function 144a is an example of a scanning unit. The processing function 144b is an example of a processing unit.

For example, the processing circuit 144 executes a scan on the subject P1 by reading a program corresponding to the scan function 144a from the memory 141 and executing the program. For example, the scan function 144a executes various scans such as positioning imaging and main scan on the subject P1.

Here, the positioning imaging may be performed in two dimensions or in three dimensions. In this embodiment, a case of performing two-dimensional positioning imaging will be described as an example. In this case, the scanning function 144a does not rotate the position of the X-ray tube 111 around the subject P1, but at least one of the position of the X-ray tube 111 and the subject P1 is in the body axis direction of the subject P1 (FIG. 1). Positioning imaging is performed while moving along the Z-axis direction shown in (1).

For example, the scan function 144a fixes the position of the X-ray tube 111 at a predetermined rotation angle, and irradiates the subject P1 with X-rays from the X-ray tube 111 while moving the top plate 133 in the Z-axis direction. .. Further, while the positioning imaging is executed by the scan function 144a, the DAS 118 collects X-ray signals from each detection element in the X-ray detector 112 and generates detection data. Further, the scan function 144a performs preprocessing on the detection data output from DAS118. For example, the scan function 144a performs preprocessing such as logarithmic conversion processing, offset correction processing, sensitivity correction processing between channels, and beam hardening correction on the detection data output from DAS118. The data after pretreatment is also described as raw data. In addition, the detection data before the pretreatment and the raw data after the pretreatment are collectively referred to as projection data.

That is, the scanning function 144a fixes the position of the X-ray tube 111 at a predetermined rotation angle, and irradiates the subject P1 with X-rays from the X-ray tube 111 while moving the top plate 133 in the Z-axis direction. As a result, projection data is collected for each of the plurality of positions of the subject P1 in the body axis direction. In the following, a plurality of projection data will be collectively referred to as a projection data set. That is, the scan function 144a collects the projection data set by performing positioning imaging.

Further, the processing circuit 144 generates image data based on the scan result by reading the program corresponding to the processing function 144b from the memory 141 and executing the program. For example, the processing function 144b generates positioning image data based on the projection data set collected by the positioning imaging. The positioning image data may be referred to as a scanno image data or a scout image data.

Further, the main scan may be executed by, for example, a conventional scan method, a helical scan method, or a step-and-shoot method.

When the main scan is executed by the conventional scan method, the scan function 144a does not move the position of the X-ray tube 111 and the subject P1 along the body axis direction, and moves the position of the X-ray tube 111 around the subject P1. Perform this scan while rotating with. For example, the scanning function 144a irradiates the subject P1 with X-rays from the X-ray tube 111 while rotating the X-ray tube 111 around the subject P1 with the top plate 133 stopped.

When the main scan is executed by the helical scan method, the scan function 144a moves the position of the X-ray tube 111 and the subject P1 along the body axis direction, and moves the position of the X-ray tube 111 to the subject P1. Perform this scan while rotating around the. For example, the scanning function 144a causes the top plate 133 to move in the Z-axis direction and irradiates the subject P1 with X-rays from the X-ray tube 111 while rotating the X-ray tube 111 around the subject P1. ..

When the main scan is executed by the step-and-shoot method, the scan function 144a first moves the position of the X-ray tube 111 and the subject P1 along the body axis direction, and first shifts the position of the X-ray tube 111 to the subject P1. Perform this scan while rotating around the. For example, the scanning function 144a irradiates the subject P1 with X-rays from the X-ray tube 111 while rotating the X-ray tube 111 around the subject P1 with the top plate 133 stopped. Next, the scanning function 144a moves the top plate 133 in the Z-axis direction in a state where the irradiation of X-rays from the X-ray tube 111 is stopped. Then, the scanning function 144a re-irradiates the subject P1 with X-rays from the X-ray tube 111 while rotating the X-ray tube 111 around the subject P1 with the top plate 133 stopped.

While this scan is performed by the scan function 144a, the DAS 118 collects X-ray signals from each detection element in the X-ray detector 112 and generates detection data. Further, the scan function 144a performs preprocessing such as logarithmic conversion processing, offset correction processing, sensitivity correction processing between channels, and beam hardening correction on the detection data output from DAS118.

That is, the scan function 144a collects projection data for each of a plurality of irradiation directions (views) by irradiating the subject P1 with X-rays while rotating the position of the X-ray tube 111 around the subject P1. .. That is, the scan function 144a collects the projection data set by executing the main scan.

In addition, the processing function 144b generates CT image data (volume data) based on the projection data set collected by this scan. For example, the processing function 144b generates CT image data by performing reconstruction processing using a filter correction back projection method, a successive approximation reconstruction method, a successive approximation applied reconstruction method, or the like based on a projection data set. .. In addition, the processing function 144b can also generate CT image data by performing reconstruction processing by AI. For example, the processing function 144b generates CT image data by a DLR (Deep Learning Reconnection) method.

Here, the processing function 144b corrects the CT image data. Specifically, the processing function 144b corrects the CT image data by inputting the positioning image data collected by the positioning imaging and the CT image data collected by the main scan into the trained model M1. .. The correction using the trained model M1 will be described later.

Further, the processing circuit 144 controls the display on the display 142 by reading the program corresponding to the control function 144c from the memory 141 and executing the program. For example, the control function 144c converts the positioning image data and the CT image data generated by the processing function 144b into a display image by a known method. As an example, the control function 144c converts CT image data into tomographic image data of an arbitrary cross section, three-dimensional image data, or the like based on an input operation or the like received from a user via the input interface 143. Then, the control function 144c causes the converted display image to be displayed on the display 142. Further, the control function 144c transmits various data via the network. As an example, the control function 144c transmits the positioning image data and the CT image data generated by the processing function 144b to an image storage device (not shown) for storage.

In the X-ray CT system 10 shown in FIG. 1, each processing function is stored in the memory 141 in the form of a program that can be executed by a computer. The processing circuit 144 is a processor that realizes a function corresponding to each program by reading a program from the memory 141 and executing the program. In other words, the processing circuit 144 in the state where the program is read has a function corresponding to the read program.

Although it has been described in FIG. 1 that the scan function 144a, the processing function 144b, and the control function 144c are realized by a single processing circuit 144, the processing circuit 144 is configured by combining a plurality of independent processors. , Each processor may realize the function by executing the program. Further, each processing function of the processing circuit 144 may be appropriately distributed or integrated into a single or a plurality of processing circuits.

Further, the processing circuit 144 may realize the function by utilizing the processor of the external device connected via the network. For example, the processing circuit 144 reads a program corresponding to each function from the memory 141 and executes it, and also uses a server group (cloud) connected to the X-ray CT system 10 via a network as a computational resource. Each function shown in FIG. 1 is realized.

The configuration example of the X-ray CT system 10 has been described above. Under such a configuration, the processing circuit 144 in the X-ray CT system 10 improves the quality of CT image data by the processing described in detail below.

First, the processing function 144b generates the trained model M1 and stores it in the memory 141. That is, the processing function 144b performs the generation processing of the trained model M1 prior to the positioning imaging and the main scan of the subject P1. Hereinafter, the process of generating the trained model M1 by the processing function 144b will be described with reference to FIG. FIG. 2 is a diagram for explaining the generation process of the trained model M1 according to the first embodiment.

The image data C11, the image data C12, and the image data C13 shown in FIG. 2 are image data collected by scanning the subject P1, the subject P2 different from the subject P1, the phantom imitating the human body, and the like. The image data C11, the image data C12, and the image data C13 may be the image data collected by the X-ray CT system 10 or the image data collected by another system. In the following, as an example, the image data C11, the image data C12, and the image data C13 will be collected by scanning the subject P2 with the X-ray CT system 10.

For example, the X-ray CT system 10 collects image data C11 by performing scan A11 on the subject P2. As an example, first, the scanning function 144a fixes the position of the X-ray tube 111 at a predetermined rotation angle, and moves the top plate 133 in the Z-axis direction from the X-ray tube 111 to the subject P2. By irradiating with X-rays, projection data is collected for each of a plurality of positions of the subject P2 in the body axis direction. Hereinafter, the plurality of projection data collected by the scan A11 will be referred to as a projection data set B11. Then, the processing function 144b generates the image data C11 shown in FIG. 2 based on the collected projection data set B11. That is, the image data C11 is two-dimensional image data collected by a two-dimensional scan. As an example, the image data C11 is the positioning image data collected by the positioning imaging in the inspection of the subject P2.

Further, for example, the X-ray CT system 10 collects image data C12 by executing scan A12 on the subject P2. As an example, first, the scan function 144a irradiates the subject P2 with X-rays having a dose of X1 while rotating the X-ray tube 111 around the subject P2 to project data for each of the plurality of views. To collect. Hereinafter, the plurality of projection data collected by the scan A12 will be referred to as a projection data set B12. Then, the processing function 144b generates the image data C12 shown in FIG. 2 by executing the reconstruction process based on the collected projection data set B12. That is, the image data C12 is three-dimensional image data collected by a three-dimensional scan. As an example, the image data C12 is the CT image data collected by this scan in the test for the subject P2.

Further, for example, the X-ray CT system 10 collects image data C13 by executing scan A13 on the subject P2. As an example, first, the scan function 144a irradiates the subject P2 with X-rays having a dose of X2 while rotating the X-ray tube 111 around the subject P2, thereby projecting data for each of the plurality of views. To collect. Here, the dose X2 is a higher dose than the dose X1. Hereinafter, the plurality of projection data collected by the scan A13 will be referred to as a projection data set B13. Then, the processing function 144b generates the image data C13 shown in FIG. 2 by executing the reconstruction process based on the collected projection data set B13. That is, the image data C13 is three-dimensional image data collected by a three-dimensional scan. As an example, the image data C13 is the CT image data collected by this scan in the test for the subject P2.

Further, the image data C13 is image data collected by using a high dose of X-rays as compared with the image data C12. That is, the image data C13 is high quality image data collected by using a high dose of X-rays. For example, in the image data C13, artifacts and noise are reduced as compared with the image data C12.

The processing function 144b generates the trained model M1 by executing machine learning using the image data C11 and the image data C12 shown in FIG. 2 as input side data and the image data C13 as output side data. Here, the trained model M1 can be configured by, for example, a neural network (Neural Network).

A neural network is a network that has a structure in which adjacent layers arranged in layers are connected and information propagates from the input layer side to the output layer side. For example, the processing function 144b generates a trained model M1 by performing deep learning on a multi-layer neural network using image data C11, image data C12, and image data C13. The multi-layer neural network is composed of, for example, an input layer, a plurality of intermediate layers (hidden layers), and an output layer.

As an example, the processing function 144b inputs the image data C11 and the image data C12 as input side data to the neural network. Here, in the neural network, information is propagated while being coupled only between adjacent layers in one direction from the input layer side to the output layer side, and the image data estimated from the image data C13 is output from the output layer. .. That is, in the neural network, processing for improving the quality of the image data C12 is performed, and the image data in which the image data C13 having a higher quality than the image data C12 is estimated is output from the output layer. A neural network in which information propagates in one direction from the input layer side to the output layer side is also called a convolutional neural network (CNN).

The processing function 144b generates the trained model M1 by adjusting the parameters of the neural network so that the neural network can output a preferable result when the input side data is input. For example, the processing function 144b adjusts the parameters of the neural network by using a function (error function) representing the proximity between the image data.

As an example, the processing function 144b calculates an error function E1 indicating the proximity between the image data C13 and the image data estimated by the neural network. Further, the processing function 144b calculates an error function E2 indicating consistency between the image data C11 and the image data estimated by the neural network. For example, the processing function 144b generates two-dimensional image data C14 by forward-projecting the image data estimated by the neural network according to the X-ray irradiation direction when the image data C11 is collected. Further, the processing function 144b calculates an error function E2 indicating the proximity between the image data for the generated image data C14 and the image data C11.

Further, the processing function 144b adjusts the parameters of the neural network so that the calculated error function becomes the minimum. For example, the processing function 144b adjusts the parameters of the neural network so that the sum of the error function E1 and the error function E2 is minimized. As a result, the processing function 144b accepts the input of the two-dimensional image data and the three-dimensional image data, and generates a trained model M1 functionalized to improve the quality of the input three-dimensional image data. To do. Further, the processing function 144b stores the generated trained model M1 in the memory 141.

Then, when the scan for the subject P1 is executed, the processing function 144b reads the learned model M1 from the memory 141, and the quality of the CT image data collected from the subject P1 is used by using the read learned model M1. To improve. Hereinafter, the scan performed on the subject P1 and the correction processing of the CT image data using the trained model M1 will be described with reference to FIG. FIG. 3 is a diagram showing a usage example of the trained model M1 according to the first embodiment.

First, the scan function 144a executes the scan A21. Specifically, as shown in FIG. 3, the scanning function 144a does not rotate the position of the X-ray tube 111 around the subject P1, but makes the position of the X-ray tube 111 relative to the subject P1. The subject P1 is irradiated with X-rays while being moved. As a result, the scanning function 144a irradiates the range R1 along the body axis direction of the subject P1 with X-rays and collects the projection data set B21. For example, the scanning function 144a fixes the position of the X-ray tube 111 at a predetermined rotation angle, moves the top plate 133 in the Z-axis direction, and collects the projection data set B21. Further, the processing function 144b generates two-dimensional image data C21 based on the projection data set B21 collected by the scan A21.

The scan A21 is an example of the first scan. The range R1 is an example of the first range. The projection data set B21 is an example of the first projection data set. Further, the image data C21 is an example of the first image data. The processing function 144b may generate the image data C21 by using the entire projection data set B21, or may generate the image data C21 by using a part of the projection data set B21.

Next, the control function 144c causes the display 142 to display a reference image based on the image data C21. Further, the control function 144c sets the range R2, which is the scan range of the scan A22, by accepting an input operation from the user who has referred to the reference image. The scan A22 is an example of the second scan. The range R2 is an example of the second range.

As described above, the range R2 is generated based on at least a portion of the projection data set B21 and is set by manipulating the positioning image data displayed on the display 142. That is, the scan A21 is a positioning image for setting the range R2. Therefore, the range R1 of the scan A21 is preferably set to a relatively wide area so as to include the organ to be diagnosed and the like. Since the range R2 is set in the range R1, it is usually narrower than the range R1 as shown in FIG.

Next, the scan function 144a executes the scan A22 with respect to the range R2 set in the reference image. Specifically, as shown in FIG. 3, the scanning function 144a irradiates the subject P1 with X-rays while rotating the position of the X-ray tube 111 around the subject P1. As a result, the scanning function 144a irradiates the range R2 along the body axis direction of the subject P1 with X-rays and collects the projection data set B22. For example, the scan function 144a collects the projection data set B22 by performing a conventional scan, a helical scan, a step-and-shoot scan, or the like. The projection data set B22 is an example of the second projection data set.

Further, the processing function 144b generates three-dimensional image data C22 based on the projection data set B22 collected by the scan A22. The image data C22 is an example of the second image data. For example, the processing function 144b executes reconstruction processing such as a filter correction back projection method, a successive approximation reconstruction method, a successive approximation applied reconstruction method, and a DLR method based on the projection data set B22, thereby performing a three-dimensional image. Data C22 is reconstructed. That is, the scan A22 is a main scan for collecting CT image data (volume data).

The scan function 144a may be executed in synchronization with the scan A21 and the scan A22 according to the heartbeat or the respiratory cycle of the subject P1. That is, the scan function 144a may be executed in synchronization with the scan A21 and the scan A22 so that the position shift between the scan A21 and the scan A22 does not occur due to the periodic movement due to the heartbeat or the respiration.

For example, the scan function 144a acquires the electrocardiographic waveform of the subject P1 in parallel with the scan A21 and the scan A22. For example, the scan function 144a acquires the electrocardiographic waveform of the subject P1 by an electrocardiograph attached to the subject P1. Then, the scan function 144a executes the scan A22 so that the phase of the electrocardiographic waveform in the scan A22 matches the electrocardiographic waveform in the scan A21.

Further, for example, the scan function 144a acquires the respiratory waveform of the subject P1 in parallel with the scan A21 and the scan A22. For example, the scan function 144a acquires the respiratory waveform of the subject P1 by the respiratory sensor. As an example, the scan function 144a acquires a respiration waveform using a laser generator and a receiver as a respiration sensor. Specifically, the scan function 144a processes the signal of the reflected light from the abdominal surface of the subject P1 and uses the laser generator and the laser generator based on the time from the laser irradiation to the reception of the reflected light or the phase change of the reflected light signal. The respiratory waveform is acquired by repeatedly calculating the distance from the abdominal surface of the subject in real time. The example of the respiration sensor is not limited to this, and the scan function 144a uses, for example, a pressure sensor attached to the abdomen of the subject P1 or an optical camera for photographing the subject P1 to capture the respiration waveform. It does not matter if it is acquired. Then, the scan function 144a executes the scan A22 so that the phase of the respiratory waveform in the scan A22 matches the respiratory waveform in the scan A21.

Further, the processing function 144b may align the projection data set B21 collected by the scan A21 with the projection data set B22 collected by the scan A22. Alternatively, the processing function 144b may align the image data C21 collected by the scan A21 with the image data C22 collected by the scan A22. As a result, the processing function 144b can reduce the influence of the body movement of the subject P1 that occurs between the scan A21 and the scan A22.

Next, the processing function 144b evaluates the quality of the image data C22. For example, the processing function 144b evaluates the quality of the image data C22 by calculating the signal-to-noise ratio (signal-noise ratio) for the image data C22 and comparing the signal-to-noise ratio with the threshold value. Further, for example, the control function 144c generates a display image based on the image data C22 and displays it on the display 142. Then, the processing function 144b accepts an input for evaluation regarding the quality of the image data C22 from the user who has referred to the display image.

Next, the processing function 144b determines whether or not to perform the correction processing of the image data C22 according to the evaluation result of the quality of the image data C22. That is, when the quality of the image data C22 is sufficiently high, the processing function 144b may omit the correction processing described later and end the processing. In the following, a case where the correction processing of the image data C22 is performed will be described.

When performing the correction processing of the image data C22, the processing function 144b inputs the image data C21 and the image data C22 to the trained model M1 read from the memory 141. As a result, the trained model M1 outputs image data C23 having a higher quality than the image data C22, as shown in FIG. That is, the trained model M1 generates the image data C23 shown in FIG. 3 by correcting the image data C22 while maintaining consistency with the image data C21. The image data C23 is an example of the third image data.

The processing function 144b may input all of the image data C21 or only a part of the trained model M1. For example, the processing function 144b may input only the portion of the image data C21 included in the range R2 into the trained model M1. In other words, the processing function 144b inputs image data C21 based on at least a part of the projection data set B21 collected from the range R1 into the trained model M1.

Then, the control function 144c causes the display 142 to display a display image based on the image data C23. For example, the control function 144c first executes a rendering process for the image data C23. Here, as an example of the rendering process, there is a process of generating a two-dimensional image of an arbitrary cross section from the image data C23 by the cross section reconstruction method (MPR: Multi Planar Reconnection). In addition, as another example of the rendering process, a two-dimensional image reflecting three-dimensional information is generated from the image data C23 by a volume rendering process or a maximum value projection method (MIP). Processing to be done is mentioned. Then, the control function 144c causes the display 142 to display the display image generated by the rendering process.

Next, an example of the processing procedure by the X-ray CT system 10 will be described with reference to FIG. FIG. 4 is a flowchart for explaining a series of processes of the X-ray CT system 10 according to the first embodiment.

Step S101 and step S106 correspond to the scanning function 144a. Step S102, step S107, step S108, step S109, step S110 and step S111 correspond to the processing function 144b. Step S103, step S104, step S105 and step S112 correspond to the control function 144c.

First, the processing circuit 144 executes the scan A21 on the subject P1 and collects the projection data set B21 (step S101). Next, the processing circuit 144 generates image data C21 based on the projection data set B21 (step S102). Next, the processing circuit 144 generates a reference image by performing rendering processing on the image data C21 (step S103), and displays the generated reference image on the display 142 (step S104).

Here, the processing circuit 144 determines whether or not the scan range has been set by the user who referred to the reference image (step S105), and if the scan range has not been set, the processing circuit 144 enters a standby state (step S105 negative). .. On the other hand, when the scan range is set (step S105 affirmative), the processing circuit 144 executes the scan A22 for the scan range set in the reference image and collects the projection data set B22 (step S106). Next, the processing circuit 144 generates image data C22 based on the projection data set B22 (step S107).

Next, the processing circuit 144 evaluates the quality of the image data C22 (step S108), and determines whether or not to perform correction processing on the image data C22 according to the evaluation result (step S109). When performing the correction process (affirmation in step S109), the processing circuit 144 inputs the image data C21 and the image data C22 to the trained model M1 (step S110), and generates the image data C23 (step S111).

Then, the processing circuit 144 generates a display image and displays it on the display 142 (step S112), and ends the processing. When the image data C23 has been generated, the processing circuit 144 causes the display 142 to display the display image based on the image data C23 in step S112. On the other hand, when the correction process is not performed (denial in step S109), the processing circuit 144 causes the display 142 to display the display image based on the image data C22 in step S112.

The above-mentioned steps S108 and S109 may be omitted. That is, regardless of the quality of the image data C22, the processing circuit 144 may input the image data C21 and the image data C22 to the trained model M1 to generate the image data C23.

As described above, according to the first embodiment, the scan function 144a executes the scan A21 for collecting the projection data set B21 by irradiating the range R1 along the body axis direction of the subject P1 with X-rays. To do. Further, the scan function 144a executes the scan A22 for collecting the projection data set B22 by irradiating the range R2 along the body axis direction of the subject P1 with X-rays after the scan A21. Further, the processing function 144b is better than the image data C22 by inputting the image data C21 based on at least a part of the projection data set B21 and the image data C22 based on the projection data set B22 to the trained model M1. Generates image data C23 with a high value. That is, the X-ray CT system 10 according to the first embodiment can generate image data C23, which is CT image data of higher quality than image data C22.

In particular, the X-ray CT system 10 generates image data C23 based on image data C21 as well as image data C22. That is, in the X-ray CT system 10, since additional anatomical information can be obtained from the image data C21, more appropriate correction processing is performed as compared with the case where only the image data C22 is used, and the image data. The quality of C23 can be further improved.

Further, the X-ray CT system 10 sets the range R2 in the scan A22 based on the result of the scan A21 and improves the quality of the CT image data. That is, the X-ray CT system 10 can make the exposure of the subject P1 by the scan A21 more meaningful. The scan A21 is a positioning image for setting the range R2 in the scan A22. That is, the scan A21 is executed before the scan A22 in the normal processing flow, and does not complicate the processing flow.

(Second Embodiment)
In the first embodiment described above, a case where high-quality CT image data is generated by inputting image data C21 and image data C22 into the trained model M1 has been described. On the other hand, in the second embodiment, a case where high quality CT image data is generated by inputting the projection data set B21 and the projection data set B22 into the trained model M2 described later will be described.

The X-ray CT system 10 according to the second embodiment has the same configuration as the X-ray CT system 10 according to the first embodiment shown in FIG. Hereinafter, the points described in the first embodiment are designated by the same reference numerals as those in FIG. 1, and the description thereof will be omitted.

First, the processing function 144b generates the trained model M2 and stores it in the memory 141. For example, the processing function 144b acquires the projection data set B11, the projection data set B12, and the projection data set B13 as training data used to generate the trained model M2.

For example, the scan function 144a fixes the position of the X-ray tube 111 at a predetermined rotation angle, and irradiates the subject P2 with X-rays from the X-ray tube 111 while moving the top plate 133 in the Z-axis direction. , Collect projection data set B11. Further, the scan function 144a collects the projection data set B12 by irradiating the subject P2 with X-rays having a dose of X1 while rotating the X-ray tube 111 around the subject P2. Further, the scan function 144a collects the projection data set B13 by irradiating the subject P2 with X-rays having a dose X2 higher than the dose X1 while rotating the X-ray tube 111 around the subject P2. That is, the projection data set B13 is a higher quality projection data set than the projection data set B12.

Then, the processing function 144b generates the trained model M2 by executing machine learning using the projection data set B11 and the projection data set B12 as input side data and the projection data set B13 as output side data. Here, the trained model M2 can be configured by, for example, a neural network. For example, the processing function 144b generates a trained model M2 by performing deep learning on a multi-layer neural network using the projection data set B11, the projection data set B12, and the projection data set B13.

As an example, the processing function 144b inputs the projection data set B11 and the projection data set B12 as input side data to the neural network. Here, in the neural network, information propagates while being coupled only between adjacent layers in one direction from the input layer side to the output layer side, and the projection data set estimated from the projection data set B13 is output from the output layer. Will be done. That is, in the neural network, processing for improving the quality of the projection data set B12 is performed, and the projection data set that estimates the projection data set B13 having a higher quality than the projection data set B12 is output from the output layer.

The processing function 144b generates the trained model M2 by adjusting the parameters of the neural network so that the neural network can output a preferable result when the input side data is input. For example, the processing function 144b adjusts the parameters of the neural network using an error function that represents the proximity between the projected datasets.

As an example, the processing function 144b calculates an error function E3 indicating the proximity between the projection data set B13 and the projection data set estimated by the neural network. The processing function 144b also calculates an error function E4 that indicates the consistency between the projection data set B11 and the image data estimated by the neural network. Then, the processing function 144b adjusts the parameters of the neural network so that the calculated error function becomes the minimum. For example, the processing function 144b adjusts the parameters of the neural network so that the sum of the error function E3 and the error function E4 is minimized. As a result, the processing function 144b is a trained model functionalized to accept the input of the 2D projection data set and the 3D projection data set and improve the quality of the input 3D projection data set. Generate M2. Further, the processing function 144b stores the generated trained model M2 in the memory 141.

Then, when the scan for the subject P1 is executed, the processing function 144b reads the trained model M2 from the memory 141, and the quality of the projection data set collected from the subject P1 is used by using the read trained model M2. And thus the quality of CT image data based on the projection dataset.

For example, the scan function 144a first executes the scan A21 shown in FIG. 3 and collects the projection data set B21. The processing function 144b also generates image data C21 based on the projection data set B21 collected by scan A21. Next, the control function 144c sets the range R2, which is the scan range of the scan A22, by accepting an input operation from the user who has referred to the reference image based on the image data C21. Next, the scan function 144a executes the scan A22 on the range R2 set in the reference image and collects the projection data set B22.

The processing function 144b then evaluates the quality of the projection data set B22. For example, the processing function 144b evaluates the quality of the projection data set B22 by calculating the signal-to-noise ratio for the projection data set B22 and comparing the signal-to-noise ratio with the threshold value. Further, for example, the control function 144c causes the display 142 to display an image (for example, a synogram) based on the projection data set B22. Then, the processing function 144b accepts an input for evaluation of the quality of the projection data set B22 from the user who has referred to the image based on the projection data set B22.

Next, the processing function 144b determines whether or not to perform the correction processing of the projection data set B22 according to the evaluation result of the quality of the projection data set B22. That is, when the quality of the projection data set B22 is sufficiently high, the processing function 144b may omit the correction processing described later. In this case, the processing function 144b can reconstruct the high quality image data C22 based on the projection data set B22. The process of determining whether or not to perform the correction process of the projection data set B22 may be omitted as appropriate.

When performing the correction processing of the projection data set B22, the processing function 144b inputs the projection data set B21 and the projection data set B22 to the trained model M2 read from the memory 141. As a result, the trained model M2 outputs a projection data set B23 having a higher quality than the projection data set B22. That is, the trained model M2 generates the projection data set B23 by correcting the projection data set B22 while maintaining consistency with the projection data set B21. The projection data set B23 is an example of the third projection data set.

The processing function 144b may input the entire projection data set B21 or only a part of the trained model M2. For example, the processing function 144b may input only the portion of the projection data set B21 included in the range R2 into the trained model M2. In other words, the processing function 144b inputs at least a part of the projection data set B21 collected from the range R1 into the trained model M2.

Further, the processing function 144b generates three-dimensional image data C24 based on the projection data set B23 generated by using the trained model M2. For example, the processing function 144b executes reconstruction processing such as a filter correction back projection method, a successive approximation reconstruction method, a successive approximation applied reconstruction method, and a DLR method based on the projection data set B23, thereby performing a three-dimensional image. Data C24 is reconstructed. Here, the image data C24 is generated based on the high-quality projection data set B23, and is a high-quality CT image data as compared with the image data C22 and the like generated based on the projection data set B22. is there. Further, the control function 144c generates a display image based on the image data C24 and displays it on the display 142.

As described above, according to the second embodiment, the scan function 144a executes the scan A21 for collecting the projection data set B21 by irradiating the range R1 along the body axis direction of the subject P1 with X-rays. To do. Further, the scan function 144a executes the scan A22 for collecting the projection data set B22 by irradiating the range R2 along the body axis direction of the subject P1 with X-rays after the scan A21. Further, the processing function 144b generates a projection data set B23 having a higher quality than the projection data set B22 by inputting at least a part of the projection data set B21 and the projection data set B22 to the trained model M1. .. Then, the X-ray CT system 10 according to the second embodiment can generate image data C24, which is high-quality CT image data, based on the projection data set B23.

In particular, the X-ray CT system 10 generates a projection data set B23 based on the projection data set B21 as well as the projection data set B22. That is, in the X-ray CT system 10, since additional anatomical information can be obtained from the projection data set B21, more appropriate correction processing is performed as compared with the case where only the projection data set B22 is used. The quality of the projection data set B23 can be further improved. As a result, the X-ray CT system 10 can further improve the quality of the image data C24 based on the projection data set B23.

(Third Embodiment)
By the way, although the first and second embodiments have been described so far, various different embodiments may be implemented in addition to the above-described embodiments.

For example, the user has been described as setting the range R2 which is the scan range of the scan A22, but the embodiment is not limited to this. For example, the control function 144c may automatically set the range R2 by analyzing the image data C21 or the reference image generated based on the image data C21 and extracting the organ or the like to be diagnosed.

Further, in the above-described embodiment, the case where the positioning imaging is performed in two dimensions has been described. However, the embodiment is not limited to this, and the X-ray CT system 10 may be a case where positioning imaging is performed in three dimensions.

When the positioning imaging is executed in three dimensions, the processing function 144b first executes machine learning using the three-dimensional positioning image data instead of the two-dimensional positioning image data to generate a trained model. For example, the processing function 144b performs machine learning using the image data C15 collected by performing three-dimensional positioning imaging on the subject P2 and the image data C12 and the image data C13 shown in FIG. 2 as training data. By executing it, a trained model M3 is generated.

For example, the X-ray CT system 10 collects image data C15 by performing scan A15 on subject P2. As an example, first, the scan function 144a irradiates the subject P2 with X-rays from the X-ray tube 111 while rotating the X-ray tube 111 around the subject P2, thereby displaying a plurality of views. Collect projection data for each. Hereinafter, the plurality of projection data collected by the scan A15 will be referred to as a projection data set B15. Then, the processing function 144b generates the image data C15 by executing the reconstruction process based on the collected projection data set B15. That is, the image data C15 is three-dimensional image data collected by a three-dimensional scan. For example, the image data C15 is positioning image data for setting the scan range of the scan A12 and the scan A13.

Further, the scan function 144a executes the scan A12 by irradiating the subject P2 with X-rays having a dose of X1 while rotating the X-ray tube 111 around the subject P2, and collects the projection data set B12. Further, the processing function 144b generates the image data C12 by executing the reconstruction process based on the projection data set B12. Further, the scan function 144a executes the scan A13 by irradiating the subject P2 with X-rays having a dose X2 higher than the dose X1 while rotating the X-ray tube 111 around the subject P2, and the projection data set. Collect B13. Further, the processing function 144b generates the image data C13 by executing the reconstruction process based on the projection data set B13. That is, the image data C13 is higher quality image data than the image data C12.

Then, the processing function 144b generates the trained model M3 by executing machine learning with the image data C15 and the image data C12 as the input side data and the image data C13 as the output side data. Here, the trained model M3 can be configured by, for example, a neural network. For example, the processing function 144b generates a trained model M3 by performing deep learning on a multi-layer neural network using image data C15, image data C12, and image data C13.

As an example, the processing function 144b inputs the image data C15 and the image data C12 as input side data to the neural network. Here, in the neural network, information is propagated while being coupled only between adjacent layers in one direction from the input layer side to the output layer side, and the image data estimated from the image data C13 is output from the output layer. .. That is, in the neural network, processing for improving the quality of the image data C12 is performed, and the image data in which the image data C13 having a higher quality than the image data C12 is estimated is output from the output layer.

The processing function 144b generates the trained model M3 by adjusting the parameters of the neural network so that the neural network can output a preferable result when the input side data is input. For example, the processing function 144b adjusts the parameters of the neural network by using an error function representing the proximity between the image data.

As an example, the processing function 144b calculates an error function E5 indicating the proximity between the image data C13 and the image data estimated by the neural network. Further, the processing function 144b calculates an error function E6 indicating the closeness between the image data C15 and the image data estimated by the neural network. Then, the processing function 144b adjusts the parameters of the neural network so that the calculated error function becomes the minimum. For example, the processing function 144b adjusts the parameters of the neural network so that the sum of the error function E5 and the error function E6 is minimized. As a result, the processing function 144b accepts the input of the first image data collected in the three-dimensional positioning imaging and the second image data collected in the three-dimensional main scan, and the quality of the input second image data. Generates a trained model M3 that is functionalized to improve. Further, the processing function 144b stores the generated trained model M3 in the memory 141.

Then, when the scan for the subject P1 is executed, the processing function 144b reads the learned model M3 from the memory 141, and the quality of the CT image data collected from the subject P1 is used by using the read learned model M3. To improve.

For example, the scan function 144a first collects image data C25 by executing scan A25 on the subject P1. As an example, first, the scanning function 144a irradiates the subject P1 with X-rays from the X-ray tube 111 while rotating the X-ray tube 111 around the subject P1 to obtain a plurality of views. Collect projection data for each. Hereinafter, the plurality of projection data collected by the scan A25 will be referred to as a projection data set B25. For example, the scan function 144a collects the projection data set B25 by irradiating the range R1 shown in FIG. 3 with X-rays. Then, the processing function 144b generates the image data C25 by executing the reconstruction process based on the collected projection data set B25. That is, the image data C25 is three-dimensional image data collected by a three-dimensional scan.

The scan A25 is an example of the first scan. The projection data set B25 is an example of the first projection data set. Further, the image data C25 is an example of the first image data.

Next, the control function 144c sets the range R2, which is the scan range of the scan A22, by accepting an input operation from the user who has referred to the reference image based on the image data C25. That is, the image data C25 is positioning image data for setting the scan range of the scan A22. Next, the scan function 144a executes the scan A22 on the range R2 set in the reference image and collects the projection data set B22. In addition, the processing function 144b generates image data C22 based on the projection data set B22.

Next, the processing function 144b evaluates the quality of the image data C22. Next, the processing function 144b determines whether or not to perform the correction processing of the image data C22 according to the evaluation result of the quality of the image data C22. That is, when the quality of the image data C22 is sufficiently high, the processing function 144b may omit the correction processing described later. The process of determining whether or not to perform the correction process of the image data C22 may be omitted as appropriate.

When performing the correction processing of the image data C22, the processing function 144b inputs the image data C25 and the image data C22 to the trained model M3 read from the memory 141. As a result, the trained model M3 outputs the image data C26 having a higher quality than the image data C22. That is, the trained model M3 generates the image data C26 by correcting the image data C22 while maintaining the consistency with the image data C25. The image data C26 is an example of the third image data.

The processing function 144b may input all of the image data C25 or only a part of the trained model M3. For example, the processing function 144b may input only the portion of the image data C25 included in the range R2 into the trained model M3. In other words, the processing function 144b inputs image data C25 based on at least a part of the projection data set B25 collected from the range R1 into the trained model M3.

To give another example, the processing function 144b uses the projection data set B15, the projection data set B12, and the projection data set B13 collected by performing three-dimensional positioning imaging on the subject P2 as training data. The trained model M4 is generated by executing machine learning.

For example, the scan function 144a executes the scan A15 by irradiating the subject P2 with X-rays while rotating the X-ray tube 111 around the subject P2, and collects the projection data set B15. Further, the scan function 144a executes the scan A12 by irradiating the subject P2 with X-rays having a dose of X1 while rotating the X-ray tube 111 around the subject P2, and collects the projection data set B12. Further, the scan function 144a executes the scan A13 by irradiating the subject P2 with X-rays having a dose X2 higher than the dose X1 while rotating the X-ray tube 111 around the subject P2, and the projection data set. Collect B13. That is, the projection data set B13 is a higher quality projection data set than the projection data set B12.

Then, the processing function 144b generates the trained model M4 by executing machine learning using the projection data set B15 and the projection data set B12 as input side data and the projection data set B13 as output side data. Here, the trained model M4 can be configured by, for example, a neural network. For example, the processing function 144b generates a trained model M4 by performing deep learning on a multi-layer neural network using the projection data set B15, the projection data set B12, and the projection data set B13.

As an example, the processing function 144b inputs the projection data set B15 and the projection data set B12 as input side data to the neural network. Here, in the neural network, information propagates while being coupled only between adjacent layers in one direction from the input layer side to the output layer side, and the projection data set estimated from the projection data set B13 is output from the output layer. Will be done. That is, in the neural network, processing for improving the quality of the projection data set B12 is performed, and the projection data set that estimates the projection data set B13 having a higher quality than the projection data set B12 is output from the output layer.

The processing function 144b generates the trained model M4 by adjusting the parameters of the neural network so that the neural network can output a preferable result when the input side data is input. For example, the processing function 144b adjusts the parameters of the neural network using an error function that represents the proximity between the projected datasets.

As an example, the processing function 144b calculates an error function E7 indicating the proximity between the projection data set B13 and the projection data set estimated by the neural network. In addition, the processing function 144b calculates an error function E8 indicating the proximity between the projection data set B15 and the image data estimated by the neural network. Then, the processing function 144b adjusts the parameters of the neural network so that the calculated error function becomes the minimum. For example, the processing function 144b adjusts the parameters of the neural network so that the sum of the error function E7 and the error function E8 is minimized. As a result, the processing function 144b receives the input of the first projection data set collected in the three-dimensional positioning imaging and the second projection data set collected in the three-dimensional main scan, and the input second projection data. Generate a trained model M4 that is functionalized to improve the quality of the set. Further, the processing function 144b stores the generated trained model M4 in the memory 141.

Then, when the scan for the subject P1 is executed, the processing function 144b reads the trained model M4 from the memory 141, and the quality of the projection data set collected from the subject P1 is used by using the read trained model M4. And thus the quality of CT image data based on the projection dataset.

For example, the scan function 144a first collects the projection data set B25 by performing scan A25 on subject P1. For example, the scan function 144a collects the projection data set B25 by irradiating the range R1 shown in FIG. 3 with X-rays. In addition, the processing function 144b generates image data C25 by executing a reconstruction process based on the collected projection data set B25.

Next, the control function 144c sets the range R2, which is the scan range of the scan A22, by accepting an input operation from the user who has referred to the reference image based on the image data C25. Next, the scan function 144a executes the scan A22 on the range R2 set in the reference image and collects the projection data set B22.

The processing function 144b then evaluates the quality of the projection data set B22. Further, the processing function 144b determines whether or not to perform the correction processing of the projection data set B22 according to the evaluation result of the quality of the projection data set B22. That is, when the quality of the projection data set B22 is sufficiently high, the processing function 144b may omit the correction processing described later. In this case, the processing function 144b can reconstruct the high quality image data C22 based on the projection data set B22. The process of determining whether or not to perform the correction process of the projection data set B22 may be omitted as appropriate.

When performing the correction processing of the projection data set B22, the processing function 144b inputs the projection data set B25 and the projection data set B22 to the trained model M4 read from the memory 141. As a result, the trained model M4 outputs a projection data set B26 having a higher quality than the projection data set B22. That is, the trained model M4 generates the projection data set B26 by correcting the projection data set B22 while maintaining consistency with the projection data set B25. The projection data set B26 is an example of the third projection data set. Further, the processing function 144b reconstructs the image data C27, which is high-quality CT image data, based on the projection data set B26 generated by using the trained model M4.

The processing function 144b may input the entire projection data set B25 or only a part of the trained model M4. For example, the processing function 144b may input only the portion of the projection data set B25 included in the range R2 into the trained model M4. In other words, the processing function 144b inputs at least a part of the projection data set B25 collected from the range R1 into the trained model M4.

Further, although the trained models M1 to M4 have been described as being configured by the neural network, the processing function 144b may generate the trained models M1 to M4 by a machine learning method other than the neural network. Further, although the processing function 144b has been described as generating the trained models M1 to M4, the trained models M1 to M4 may be generated by another device.

Further, although the X-ray CT system 10 has been described as performing the correction processing of the projection data set or the CT image data, the embodiment is not limited to this. For example, the correction process may be executed in another device different from the X-ray CT system 10. Hereinafter, this point will be described by taking the medical information processing system 1 shown in FIG. 5 as an example. FIG. 5 is a block diagram showing an example of the configuration of the medical information processing system 1 according to the fifth embodiment. The medical information processing system 1 includes an X-ray CT system 10 and a medical processing device 20 that executes correction processing.

As shown in FIG. 5, the X-ray CT system 10 and the medical processing device 20 are connected to each other via a network NW. Here, the place where the X-ray CT system 10 and the medical processing device 20 are installed is arbitrary as long as it can be connected via the network NW. For example, the medical processing device 20 may be installed in a hospital different from the X-ray CT system 10. That is, the network NW may be configured by a local network closed in the hospital, or may be a network via the Internet. Further, although one X-ray CT system 10 is shown in FIG. 5, the medical information processing system 1 may include a plurality of X-ray CT systems 10.

The medical processing device 20 is realized by a computer device such as a workstation. For example, the medical processing apparatus 20 has a memory 21, a display 22, an input interface 23, and a processing circuit 24, as shown in FIG.

The memory 21 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, a hard disk, an optical disk, or the like. For example, the memory 21 stores various data transmitted from the X-ray CT system 10. Further, for example, the memory 21 stores a program for the circuit included in the medical processing device 20 to realize its function. The memory 21 may be realized by a server group (cloud) connected to the medical processing device 20 via the network NW.

The display 22 displays various information. For example, the display 22 displays a CT image for display generated by the processing circuit 24, and displays a GUI or the like for receiving various operations from the user. For example, the display 22 is a liquid crystal display or a CRT display. The display 22 may be a desktop type, or may be composed of a tablet terminal or the like capable of wireless communication with the main body of the medical processing device 20.

The input interface 23 receives various input operations from the user, converts the received input operations into electric signals, and outputs the received input operations to the processing circuit 24. For example, the input interface 23 receives from the user reconstruction conditions for reconstructing CT image data, image processing conditions for generating a CT image for display from CT image data, and the like. For example, the input interface 23 includes a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touch pad for performing input operations by touching an operation surface, a touch screen in which a display screen and a touch pad are integrated, and an optical sensor. It is realized by the non-contact input circuit, voice input circuit, etc. used. The input interface 23 may be composed of a tablet terminal or the like capable of wireless communication with the main body of the medical processing device 20. Further, the input interface 23 is not limited to one provided with physical operation parts such as a mouse and a keyboard. For example, an example of the input interface 23 is an electric signal processing circuit that receives an electric signal corresponding to an input operation from an external input device provided separately from the medical processing device 20 and outputs the electric signal to the processing circuit 24. include.

The processing circuit 24 controls the operation of the entire medical processing device 20 by executing the processing function 24a and the control function 24b. The processing function 24a is an example of a processing unit. The processing by the processing circuit 24 will be described later.

In the medical processing device 20 shown in FIG. 5, each processing function is stored in the memory 21 in the form of a program that can be executed by a computer. The processing circuit 24 is a processor that realizes a function corresponding to each program by reading a program from the memory 21 and executing the program. In other words, the processing circuit 24 in the state where the program is read has a function corresponding to the read program.

Although it has been described in FIG. 5 that the processing function 24a and the control function 24b are realized by a single processing circuit 24, a plurality of independent processors are combined to form the processing circuit 24, and each processor is programmed. The function may be realized by executing. Further, each processing function of the processing circuit 24 may be realized by being appropriately distributed or integrated into a single or a plurality of processing circuits.

Further, the processing circuit 24 may realize the function by utilizing the processor of the external device connected via the network NW. For example, the processing circuit 24 reads a program corresponding to each function from the memory 21 and executes it, and also uses a server group (cloud) connected to the medical processing device 20 via a network NW as a computational resource. Each function shown in FIG. 5 is realized.

For example, first, the scan function 144a in the X-ray CT system 10 executes a first scan for collecting a first projection data set by irradiating a range R1 along the body axis direction of the subject P1 with X-rays. .. Further, the scan function 144a collects the second projection data set by irradiating the range R2 narrower than the range R1 along the body axis direction of the subject P1 with X-rays after the first scan. Perform a scan.

The processing function 144b also generates first image data based on at least a part of the first projection data set and second image data based on the second projection data set. Next, the control function 144c transmits the first image data and the second image data to the medical processing device 20 via the network NW. Alternatively, the control function 144c transmits the first projection data set and the second projection data set to the medical processing apparatus 20. Next, the processing function 24a generates first image data based on at least a part of the first projection data set and second image data based on the second projection data set.

Then, the processing function 24a executes the correction processing for the second image data. For example, the processing function 24a generates third image data having a higher quality than the second image data by inputting the first image data and the second image data into the trained model M1 or the trained model M3 described above. To do. The processing function 24a may evaluate the quality of the second image data prior to the correction processing and determine whether or not to generate the third image data according to the evaluation result.

To give another example, the control function 144c transmits the first projection data set and the second projection data set to the medical processing apparatus 20. Then, the processing function 24a executes the correction processing for the second projection data set. For example, the processing function 24a inputs at least a part of the first projection data set and the second projection data set into the trained model M2 or the trained model M4 described above, so that the quality is higher than that of the second projection data set. Generate a high third projection dataset. The processing function 24a may evaluate the quality of the second projection data set prior to the correction processing and determine whether or not to generate the third projection data set according to the evaluation result.

Then, the processing function 24a reconstructs the third image data, which is higher in quality than the CT image data based on the second projection data set, based on the third projection data set. Alternatively, the control function 24b transmits the third projection data set to the X-ray CT system 10 via the network NW. In this case, the processing function 144b reconstructs the third image data based on the third projection data set.

The term "processor" used in the above description refers to, for example, a CPU, a GPU (Graphics Processing Unit), an integrated circuit for a specific application (Application Specific Integrated Circuit: ASIC), a programmable logic device (for example, a simple programmable logic device (for example, a simple programmable logic device)). It means a circuit such as a Simple Programmable Logic Device (SPLD), a composite programmable logic device (Complex Programmable Logic Device: CPLD), and a field programmable gate array (Field Programmable Gate Array: FPGA). The processor realizes the function by reading and executing the program stored in the memory 141 or the memory 21.

Note that, in FIG. 1, a single memory 141 has been described as storing a program corresponding to each processing function of the processing circuit 144. Further, in FIG. 5, it has been described that a single memory 21 stores a program corresponding to each processing function of the processing circuit 24. However, the embodiment is not limited to this. For example, a plurality of memories 141 may be distributed and arranged, and the processing circuit 144 may be configured to read a corresponding program from the individual memories 141. Similarly, a plurality of memories 21 may be distributed and arranged, and the processing circuit 24 may be configured to read a corresponding program from the individual memories 21. Further, instead of storing the program in the memory 141 or the memory 21, the program may be directly incorporated in the circuit of the processor. In this case, the processor realizes the function by reading and executing the program embedded in the circuit.

Each component of each device according to the above-described embodiment is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically distributed in arbitrary units according to various loads and usage conditions. It can be integrated and configured. Further, each processing function performed by each device may be realized by a CPU and a program analyzed and executed by the CPU, or may be realized as hardware by wired logic.

Further, the processing method described in the above-described embodiment can be realized by executing a processing program prepared in advance on a computer such as a personal computer or a workstation. This processing program can be distributed via a network such as the Internet. Further, this processing program is recorded on a non-transient recording medium such as a hard disk, flexible disk (FD), CD-ROM, MO, or DVD that can be read by a computer, and is executed by being read from the recording medium by the computer. You can also do it.

According to at least one embodiment described above, high quality CT image data can be generated.

Although some embodiments of the present invention have been described, these embodiments are presented as examples 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 changes can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, as well as in the scope of the invention described in the claims and the equivalent scope thereof.

1 Medical information processing system 10 X-ray CT system 110 Standing device 140 Console device 144 Processing circuit 144a Scan function 144b Processing function 144c Control function 20 Medical processing device 24 Processing circuit 24a Processing function 24b Control function

Claims (7)

A first scan is performed to collect the first projection data set by irradiating the first area along the body axis direction of the subject with X-rays, and after the first scan, along the body axis direction. In addition, a scanning unit that executes a second scan that collects a second projection data set by irradiating a second range narrower than the first range with X-rays.
The first image data based on at least a part of the first projection data set or at least a part of the first projection data set, and the second image data based on the second projection data set or the second projection data set. For a trained model that produces a third projection data set or a third image data that is of higher quality than the second projection data set or the second image data, the first projection data set or the first A processing unit that generates the third projection data set or the third image data by inputting one image data and the second projection data set or the second image data.
X-ray CT system equipped with. The scanning unit collects the first projection data set while moving at least one of the position of the X-ray tube that generates X-rays and the subject along the body axis direction, and the position of the X-ray tube. The X-ray CT system according to claim 1, wherein the second projection data set is collected while rotating the subject around the subject. The X-ray CT system according to claim 2, wherein the scanning unit collects the first projection data set without rotating the position of the X-ray tube around the subject. The X-ray CT system according to claim 2 or 3, wherein the scanning unit collects the second projection data set without moving the position of the X-ray tube and the subject along the body axis direction. The processing unit evaluates the quality of the second projection data set or the second image data, and determines whether or not to generate the third projection data set or the third image data according to the evaluation result. , The X-ray CT system according to any one of claims 1 to 4. The second range is defined in any one of claims 1 to 5, which is generated based on at least a part of the first projection data set and is set by an operation on the positioning image data displayed on the display unit. The described X-ray CT system. A first based on at least a portion of the first projection data set or at least a portion of the first projection data set collected by a first scan that irradiates a first area along the body axis of the subject with X-rays. The second projection data set or the second scan collected after the first scan by irradiating the image data with X-rays into a second range narrower than the first range along the body axis direction. For a second image data based on a projection data set and a trained model that produces a third projection data set or a third image data of higher quality than the second projection data set or the second image data based on. The process of generating the third projection data set or the third image data by inputting the first projection data set or the first image data and the second projection data set or the second image data. A medical processing device equipped with a part.

Images