JP2021010727A - X-ray ct system and medical processing device - Google Patents

Abstract

To improve accuracy of material discrimination.SOLUTION: An X-ray CT system includes a scan part and a processing part. The scan part executes a first scan for collecting a first subject data set corresponding to first X-ray energy by radiating an X-ray onto a first area of the subject, and a second scan for, after the first scan, collecting a second subject data set corresponding to second X-ray energy by radiating an X-ray onto a second area included in the first area, and a third subject data set corresponding to third X-ray energy different from the second X-ray energy. The processing part executes material discrimination on the basis of a fourth subject data set acquired on the basis of the first subject data set, and one of the second and third subject data sets, and the other of the second and third subject data sets by using a plurality of reference materials.SELECTED DRAWING: Figure 2

Description

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

Based on the projection data corresponding to two or more types of X-ray energies collected by an X-ray CT (Computed Tomography) scanner, there is a technology to discriminate the object by multiple reference substances and display the result as an image. .. When two types of X-ray energy are used, this technique is called dual energy (DE), and it is possible to discriminate substances using two types of reference substances.

For example, dual energy technology makes it possible to discriminate substances such as kidney stones, fat, soft tissue, and bone in the body of a subject. In addition, according to the dual energy technique, it is possible to determine whether the kidney stone in the body of the subject is a calcium type stone or a uric acid type stone.

Here, the projection data collected by the X-ray CT scanner may include noise and artifacts due to various factors. In particular, when the physique of the subject is large, X-rays are likely to be attenuated, and the quality of the projected data is significantly deteriorated. Here, although the quality of the projected data can be improved by using high-energy and high-dose X-rays, the exposure dose of the subject increases. In addition, when the energy of X-rays on the low energy side in dual energy is increased, there is a concern that the accuracy of substance discrimination may be lowered due to the small energy difference.

Japanese Unexamined Patent Publication No. 04-347143 Japanese Unexamined Patent Publication No. 2005-143948 Japanese Unexamined Patent Publication No. 08-294485 Japanese Unexamined Patent Publication No. 2008-229161

The problem to be solved by the present invention is to improve the accuracy of substance discrimination.

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 subject data set corresponding to the first X-ray energy by irradiating the first region of the subject with X-rays, and the first scan is performed. After the scan, the second region included in the first region is irradiated with X-rays to obtain a second subject data set corresponding to the second X-ray energy and the second X-ray energy. Performs a second scan that collects a third subject data set corresponding to a different third X-ray energy. The processing unit includes a fourth subject data set obtained based on the first subject data set and one of the second and third subject data sets, and the second and third subject data. Material discrimination is performed by a plurality of reference substances based on the other of the set.

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 showing an example of processing of the X-ray CT system according to the first embodiment. FIG. 3 is a diagram for explaining the correction process of the projection data set according to the first embodiment. FIG. 4A is a diagram for explaining the segmentation according to the first embodiment. FIG. 4B is a diagram for explaining the segmentation according to the first embodiment. FIG. 4C is a diagram for explaining the segmentation according to the first embodiment. FIG. 5 is a flowchart for explaining a series of processes of the X-ray CT system according to the first embodiment. FIG. 6 is a block diagram showing an example of the configuration of the medical information processing system according to the second 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, or displays an image showing the result of substance discrimination. Further, for example, the display 142 displays a GUI (Graphical User Interface) 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 supplies a high voltage to the X-ray tube 111 by controlling the X-ray high voltage device 114. As a result, the X-ray tube 111 generates X-rays to irradiate the subject P1. Further, the scanning function 144a moves the subject P1 into the photographing port of the gantry device 110 by controlling the sleeper driving device 132. Further, the scanning function 144a controls the distribution of X-rays applied to the subject P1 by adjusting the position of the wedge 116 and the opening degree and position of the collimator 117. Further, the scan function 144a rotates the rotating portion by controlling the control device 115. Further, while the scan is executed by the scan function 144a, the DAS 118 collects an X-ray signal 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.

Further, the processing circuit 144 generates image data based on the projection data after the preprocessing by reading the program corresponding to the processing function 144b from the memory 141 and executing the program. For example, the processing function 144b performs CT image data (volume data) by performing reconstruction processing on the projection data using a filter correction back projection method, a successive approximation reconstruction method, a successive approximation applied reconstruction method, or the like. To generate. In addition, the processing function 144b can also perform reconstruction processing by AI (Artificial Intelligence) to generate CT image data. For example, the processing function 144b generates CT image data by a DLR (Deep Learning Reconnection) method. Further, the processing function 144b performs substance discrimination by a plurality of reference substances based on the projection data. The processing function 144b may perform substance discrimination at a stage before the reconstruction process (projection data stage), or may perform substance discrimination at the stage after the reconstruction process (CT image data stage). May be done. The discrimination process by the processing function 144b 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 displays the CT image data generated by the processing function 144b by a known method based on an input operation received from the user via the input interface 143 (a fault of an arbitrary cross section). Convert to image data, 3D image data, etc.). Then, the control function 144c causes the converted CT image for display to be displayed on the display 142. Further, for example, the control function 144c causes the display 142 to display an image showing the result of substance discrimination by the processing function 144b. Further, the control function 144c transmits various data via the network. As an example, the control function 144c transmits the CT image data generated by the processing function 144b and an image showing the result of substance discrimination 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. Hereinafter, the processing performed by the X-ray CT system 10 will be described in detail.

First, the process performed by the X-ray CT system 10 will be described with reference to FIG. In FIG. 2, a case where the kV switching type scan A12 is executed and the substance is discriminated by two kinds of reference substances will be described. FIG. 2 is a diagram showing an example of processing of the X-ray CT system 10 according to the first embodiment.

As shown in FIG. 2, the scan function 144a first executes the scan A11. Specifically, as shown in FIG. 2, the scan function 144a rotates the X-ray focal position around the subject P1 while energetizing the energy E11 with respect to the range R1 along the body axis direction of the subject P1. By irradiating with X-rays, projection data is collected for each of a plurality of irradiation directions (views). 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 B11 corresponding to the energy E11 by irradiating the range R1 with X-rays. For example, the scan function 144a collects the projection data set B11 by performing a conventional scan, a helical scan, a step-and-shoot scan, or the like. Further, the processing function 144b reconstructs the three-dimensional image data C11 based on the projection data set B11 collected by the scan A11.

The scan A11 is an example of the first scan. Further, the range R1 is an example of the first range or the first region. The energy E11 is an example of the first X-ray energy. The projection data set B11 is an example of the first projection data set and the first subject data set. Further, the image data C11 is an example of the first image data.

Next, the control function 144c generates a reference image by executing a rendering process on the image data C11, and displays the generated reference image on the display 142. 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 C11 by a cross section reconstruction method (MPR: Multi Planar Reconnection). Further, as another example of the rendering process, a two-dimensional image reflecting three-dimensional information is generated from the image data C11 by a volume rendering (Volume Rendering) process or a maximum value projection method (MIP). Processing to be done is mentioned. Further, the control function 144c sets the range R2, which is the scan range of the scan A12, by accepting an input operation from the user who has referred to the reference image. The scan A12 is an example of the second scan. Further, the range R2 is an example of a second range or a second region.

That is, the scan A11 is a positioning image for setting the range R2, and the image data C11 is the positioning image data used for setting the range R2. Therefore, it is preferable that the range R1 of the scan A11 is set to a relatively wide area so as to include the organ to be diagnosed and the like. Further, since the range R2 is set in the range R1, it is usually a range narrower than the range R1 as shown in FIG. In other words, the range R2 is a range included in the range R1. The positioning image data may be referred to as a scanno image data, a scanogram, or a scout image data. Further, the image data C11, which is a three-dimensional scanogram, is also described as a 3D scanogram.

Next, the scan function 144a executes the scan A12 with respect to the range R2 set in the reference image. Specifically, the scan function 144a changes the energy of the X-rays emitted from the X-ray tube 111 to the subject P1 between the energies E12 and the energies E13 for each one or a plurality of views. Perform scan A12. As a result, the scanning function 144a collects the projection data set B12 corresponding to the energy E12 and the projection data set B13 corresponding to the energy E13.

The energy E12 is an example of the second X-ray energy. The projection data set B12 is an example of the second projection data set and the second subject data set. The energy E13 is an example of the third X-ray energy. The projection data set B13 is an example of a third projection data set and a third subject data set. Here, the energy E12 is smaller than the energy E13. Further, the energy E11 may be an energy different from the energy E12 and the energy E13, or may be the same energy as any of the energy E12 and the energy E13.

Next, the processing function 144b generates the projection data set B14 corresponding to the energy E12 based on the projection data set B11. Further, the processing function 144b corrects the projection data set B12 based on the projection data set B14 to generate the projection data set B16 corresponding to the energy E12. That is, the processing function 144b generates the projection data set B16 based on the projection data set B12 and the projection data set B14. The projection data set B14 is an example of a fourth projection data set, and the projection data set B16 is an example of a sixth projection data set and a fourth subject data set. The generation processing of the projection data set B14 and the projection data set B16 will be described later.

Then, the processing function 144b executes substance discrimination by two kinds of reference substances based on the projection data set B16 corresponding to the energy E12 and the projection data set B13 corresponding to the energy E13, and generates a substance discrimination image. ..

As an example, the processing function 144b uses the projection data set B16 and the projection data set B13 to separate two reference materials existing within the range R2. Specifically, the processing function 144b obtains the distribution of the line attenuation coefficient for each of the projection data set B16 and the projection data set B13, and for each position (each pixel) of the line attenuation coefficient, the simultaneous equations of the following equation (1) By solving, the mixing amount and mixing ratio of the two reference substances at each position are calculated.

Here, "μ (E1)" indicates the line attenuation coefficient of each position in the monochromatic X-ray energy "E1", and "μ (E2)" indicates the line attenuation coefficient of each position in the monochromatic X-ray energy "E2". .. Further, "μα (E)" indicates a linear attenuation coefficient of the reference substance α, and "μβ (E)" indicates a linear attenuation coefficient of the reference substance β. Further, "cα" indicates the mixed amount of the reference substance α, and "cβ" indicates the mixed amount of the reference substance β. The linear attenuation coefficient for each energy of each reference substance is known. For example, the processing function 144b substitutes two kinds of reference substances "α, β" by substituting the energy E11 for "E1" and substituting the energy E12 for "E2" to solve the simultaneous equations of the equation (1). Perform substance discrimination.

Then, the processing function 144b generates an image showing the result of substance discrimination. For example, the processing function 144b generates a substance discrimination image for each reference substance. As an example, the processing function 144b generates a substance discrimination image in which the reference substance α is emphasized and a substance discrimination image in which the reference substance β is emphasized, respectively. Further, the processing function 144b performs a weighting calculation process based on the mixing ratio of each reference substance using a plurality of substance discrimination images generated for each reference substance, thereby performing a virtual monochromatic X-ray image (monochromematic) at a predetermined energy. It is also possible to generate various images such as (also referred to as an image), a density image, and an effective atomic number image. Further, the control function 144c causes the display 142 to display an image showing the results of these substance discriminations.

Although it has been described that the substance is discriminated before the reconstitution treatment is performed, the treatment function 144b may perform the substance discrimination at the stage after the reconstitution treatment is performed. That is, the processing function 144b may perform material discrimination by solving the simultaneous equations of the equation (1) for each pixel of the projection data set B16 and the projection data set B13, or the CT image data and the CT image data based on the projection data set B16. Material discrimination may be performed by solving the simultaneous equations of the equation (1) for each pixel of the CT image data based on the projection data set B13.

Further, although the above equation (1) has been described with "μ" as the linear attenuation coefficient and "c" as the mixing amount, the embodiment is not limited to this. For example, the processing function 144b may solve the equation (1) with "μ" in each substance as the mass attenuation coefficient and "c" as the density.

Next, the generation processing of the projection data set B14 and the projection data set B16 will be described in more detail with reference to FIG. Specifically, as shown in FIG. 3, the X-ray CT system 10 generates a projection data set B14 from the projection data set B11 collected by the scan A11 and projects the projection data set B12 collected by the scan A12. The projected data set B16 is generated by making corrections using the data set B14. That is, FIG. 3 is a diagram for explaining the correction process of the projection data set B12 according to the first embodiment.

More specifically, the scan function 144a first executes scan A11 and collects the projection data set B11 corresponding to energy E11. Here, the projection data set B11 can be represented as data having axes in the channel direction and the view direction, as shown in FIG. Further, since the scan A11 is performed using X-rays of a single energy (energy E11), the projection data set B11 is the data of the energy E11 for any view. That is, the scan A11 is a single energy scan using X-rays of energy E11.

Although the description is omitted in FIG. 3, the projection data set B11 is three-dimensional data including the body axis direction (Z-axis direction) of the subject P1. For example, the projection dataset B11 has a matrix size of "P" in the channel direction, "Q" in the view direction, and "R" in the body axis direction.

Next, the processing function 144b executes a reconstruction process based on the projection data set B11 to generate three-dimensional image data C11. Here, the image data C11 is three-dimensional data showing the distribution of CT values (unit: HU).

Next, the processing function 144b segmentes the image data C11 according to the CT value. Specifically, the processing function 144b classifies each pixel in the image data C11 into air, water, soft tissue, bone, and the like according to the CT value. The CT value is a value proportional to the X-ray absorption coefficient. That is, the processing function 144b segmentes the image data C11 according to the X-ray absorption coefficient.

Here, the segmentation of the image data C11 by the processing function 144b will be described in more detail with reference to FIGS. 4A, 4B and 4C. 4A, 4B and 4C are diagrams for explaining the segmentation according to the first embodiment.

FIG. 4A shows the segmented image data C11. For example, the processing function 144b classifies each of the pixels in the image data C11 into any of tissues such as air, water, soft tissue, and bone. Here, different tissues each exhibit different attenuation factors. For example, as shown in FIG. 4B, even when X-rays of the same energy E11 are irradiated, the attenuation coefficient is different between bone and soft tissue. That is, “μbone (E11) ≠ μsoft tissue (E11)”. Also, different X-ray energies show different attenuation factors. Further, for example, as shown in FIG. 4C, even when the same tissue “bone” is irradiated with X-rays, the attenuation coefficient is different between the X-rays of energy E11 and the X-rays of energy E12. That is, “μbone (E11) ≠ μbone (E12)”. Although the segmentation has been described for each pixel, the processing function 144b may perform the segmentation for each pixel group in which a plurality of pixels are bundled.

Next, the processing function 144b generates the projection data set B14 by forward-projecting the image data C11 according to the energy E12. That is, since the attenuation coefficient for each energy of each tissue is known, the processing function 144b forward-projects the image data C11 segmented for each tissue according to the energy E12, and the projection data collected by the energy E12. The set can be simulated to generate the projection data set B14. That is, the projection data set B11 is the projection data set actually collected by the scan A11, whereas the projection data set B14 is the simulated projection data set. For example, the processing function 144b generates the projection data set B14 by calculating the attenuation of the X-rays that occur when the X-rays of energy E12 pass through various tissues.

Next, the processing function 144b resamples the projection data set B14. That is, where the projection data set B14 generated by forward projection has the same “P × Q × R” matrix as the projection data set B11, the matrix of the projection data set B14 and the projection data set collected by the scan A12. It may be different from the matrix of. Therefore, the processing function 144b resamples the projection data set B14 so as to align the matrix of the projection data set B14 with the matrix of the projection data set collected by the scan A12.

For example, the projection dataset collected by scan A12 has a "PxMxN" matrix. That is, since the matrix size in the channel direction does not usually change, the projection data set collected by the scan A12 has a matrix size of "P" in the channel direction, like the projection data set B14. On the other hand, the matrix size in the view direction and the body axis direction can change from scan to scan. For example, the projection dataset B14 has a matrix size of "Q" in the view direction and "R" in the body axis direction, whereas the projection dataset collected by scan A12 has a matrix size of "M" in the view direction and the body axis. It has a matrix size of "N" in the direction. Therefore, the processing function 144b performs resampling so that the matrix of the projection data set B14 is “P × M × N”.

Next, the processing function 144b processes the projection data set B14 into a sparse state. Specifically, the processing function 144b processes the projection data set B14 generated by forward projection so that the projection data set B12 corresponding to the energy E12 is in the same sparse state as the projection data set B12, and the sparse projection data is processed. Generate set B14.

That is, as shown in FIG. 3, the projection data set collected by the scan A12 is a projection data set in which a plurality of energies (energy E12 and energy E13) are mixed. Here, the projection data set B12 separated from the projection data set collected by the scan A12 becomes sparse data in which the data corresponding to the view of the energy E13 is missing. Therefore, the processing function 144b processes the projection data set B14 so as to have a sparse state similar to that of the projection data set B12.

Note that FIG. 3 is just an example, and the processing flow can be changed as appropriate. For example, the processing function 144b may first process the projection data set B14 into a sparse state, and then perform resampling from “P × Q × R” to “P × M × N”. Further, for example, the processing function 144b may resample the projection data set B11 and then reconstruct the image data C11. Further, for example, the processing function 144b may perform segmentation after resampling the image data C11. Further, for example, the processing function 144b may perform forward projection after resampling the segmented image data C11. Further, in FIG. 3, it has been described that full data that is not sparse is generated by forward projection and then processed to generate sparse data. However, the processing function 144b generates sparse data by forward projection. You may.

As described above, the processing function 144b forward-projects the image data C11 to generate the projection data set B14, and further performs various processing on the projection data set B14. For example, the processing function 144b aligns the matrix with the projection data set B12 and processes the projection data set B14 into the same sparse state as the projection data set B12. That is, the processing function 144b processes the projection data set B14 so as to have the same data format as the projection data set B12.

Next, the processing function 144b blends the projection data set B14 and the projection data set B12 to generate the projection data set B16. For example, the processing function 144b aligns the projection data set B14 and the projection data set B12, and weights and adds the projection data set B14 and the projection data set B12 at a predetermined ratio to obtain the projection data set B16. Generate. In other words, the processing function 144b corrects the projection data set B12 by the projection data set B14 to generate the projection data set B16.

Alternatively, the processing function 144b may correct the projection data set B12 based on the projection data set B14 by AI. As an example, the processing function 144b pre-generates a trained model M1 functionalized to receive input from two projection datasets collected from the same object and output a high quality projection dataset. And store it in the memory 141. Then, when the scan A11 and the scan A12 are executed, the processing function 144b inputs the projection data set B14 and the projection data set B12 to the trained model M1 read from the memory 141, so that the projection data set B16 To generate.

Hereinafter, an example of the generation process of the trained model M1 will be described. First, the processing function 144b acquires a set of projection data sets collected from the same object as training data. Hereinafter, as an example of the training data, a set of the projection data set B21, the projection data set B22, and the projection data set B23 will be described. For example, the projection data set B21, the projection data set B22, and the projection data set B23 are collected by performing three scans on the subject P1, the subject P2 different from the subject P1, the phantom imitating the human body, and the like. .. Also, the projection dataset B23 is a high quality projection dataset collected using high doses of X-rays as compared to the projection dataset B21 and the projection dataset B22. The projection data set B21, the projection data set B22, and the projection data set B23 may be collected in the X-ray CT system 10 or in another system.

For example, the processing function 144b generates the trained model M1 by executing machine learning using the projection data set B21 and the projection data set B22 as input side data and the high quality projection data set B23 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 executing deep learning (deep learning) on a multi-layer neural network using the above-mentioned training data. 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 projection data set B21 and the projection data set B22 into the neural network as input side data. 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 B23 is output from the output layer. Will be done.

For example, in a neural network, the projection data set B21 and the projection data set B22 are aligned, and the weights of the projection data set B21 and the projection data set B22 are determined to determine the projection data set B21 and the projection data set B22. Is blended. The weights of the projection data set B21 and the projection data set B22 may be determined for each pixel. Then, the projection data set that estimates the high-quality projection data set B23 is output from the output layer of the neural network. 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 projection data sets.

As an example, the processing function 144b calculates an error function indicating the proximity between the projection data set B23 and the projection data set 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. As a result, the processing function 144b generates a trained model M1 functionalized to receive inputs of two projection datasets collected from the same object and output a high quality projection dataset. Further, the processing function 144b stores the generated trained model M1 in the memory 141.

The trained model M1 may be functionalized to further preprocess the blending of the two input projection data sets. For example, the trained model M1 resamples at least one of the two input projection data sets when the matrices of the two input projection data sets are different. Further, for example, the trained model M1 processes so that when one of the two input projection data sets has sparse data, the other projection data set has the same sparse data.

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

After generating the projection data set B16 based on the projection data set B12 and the projection data set B14, the processing function 144b is based on the projection data set B16 corresponding to the energy E12 and the projection data set B13 corresponding to the energy E13. 2. Perform material discrimination based on two types of reference substances.

For example, the processing function 144b first interpolates the data of the missing portion of each projection data set. That is, since both the projection data set B16 and the projection data set B13 are sparse data, the processing function 144b interpolates the data of the respective missing portions to obtain full data. Examples of interpolation processing by the processing function 144b include linear interpolation, Lagrange interpolation, and sigmoid. Then, the processing function 144b executes substance discrimination based on the projection data set B16 and the projection data set B13 in the state of full data. For example, the treatment function 144b can separate kidney stones from soft tissue by treatment of substance discrimination.

Further, the processing function 144b produces an image showing the result of substance discrimination. For example, the processing function 144b generates a substance discrimination image in which "calcium" is emphasized and a substance discrimination image in which "water" is emphasized, respectively. The processing function 144b can also generate various images such as a monochrome matic image, a density image, and an effective atomic number image at a predetermined energy. Further, the control function 144c causes the display 142 to display an image showing the result of substance discrimination.

In FIG. 3, the processing function 144b may perform interpolation processing tailing of a missing portion on the projection data set B12 before blending the projection data set B14 and the projection data set B12. That is, the processing function 144b may omit the process of processing the projection data set B14 into sparse data, and may blend the projection data set B14 and the projection data set B12 in the state of full data.

Further, in FIG. 3, it has been described that the matrix of the projection data set collected by the scan A11 and the projection data set collected by the scan A12 are different, but the scan function 144a has the same matrix of the projection data set. Scan A11 and Scan A12 may be performed so as to be. In this case, the processing function 144b can omit the resampling process.

Further, when the energy E11 and the energy E12 have the same energy, the scanning function 144a may omit the processing of reconstruction, segmentation, and forward projection. That is, when the energy E11 and the energy E12 have the same energy, the scan function 144a can also correct the projection data set B12 by using the projection data set B11 collected by the scan A11 as it is.

Next, an example of the processing procedure by the X-ray CT system 10 will be described with reference to FIG. FIG. 5 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 S107 correspond to the scanning function 144a. Step S102, step S103, step S108 and step S109 correspond to the processing function 144b. Step S104, step S105, step S106 and step S110 correspond to the control function 144c.

First, the processing circuit 144 executes the scan A11 by irradiating the range R1 along the body axis direction of the subject P1 with X-rays, and collects the projection data set B11 corresponding to the energy E11 (step S101). Next, the processing circuit 144 executes reconstruction processing on the projection data set B11 to generate image data C11 (step S102).

Next, the processing circuit 144 generates the projection data set B14 corresponding to the energy E12 based on the projection data set B11 (step S103). Specifically, the processing circuit 144 segments the image data C11 based on the projection data set B11 according to the X-ray absorption coefficient, and forward-projects the segmented image data C11 according to the energy E12 to form a projection data set. Generate B14.

Further, the processing circuit 144 generates a reference image by performing rendering processing on the image data C11 (step S104), and displays the generated reference image on the display 142 (step S105). Here, the processing circuit 144 determines whether or not the range R2, which is the scan range of the scan A12, has been set by the user who referred to the reference image (step S106), and waits if the scan range is not set. It becomes a state (step S106 negation).

On the other hand, when the scan range is set (affirmation in step S106), the processing circuit 144 executes the scan A12 for the scan range set in the reference image (step S107). Specifically, the processing circuit 144 irradiates the range R2 along the body axis direction of the subject P1 with X-rays, thereby irradiating the projection data set B12 corresponding to the energy E12 and the projection data set B13 corresponding to the energy E13. To collect.

Next, the processing circuit 144 generates the projection data set B16 corresponding to the energy E12 based on the projection data set B12 and the projection data set B14 (step S108). Next, the processing circuit 144 discriminates substances with two types of reference substances based on the projection data set B16 corresponding to the energy E12 and the projection data set B13 corresponding to the energy E13 (step S109). Then, the processing circuit 144 displays a substance discrimination image showing the result of the substance discrimination on the display 142 (step S110), and ends the processing.

The order in which step S103 and step S104, step S105, step S106, and step S107 are performed is arbitrary, and may be performed in parallel.

Further, in FIG. 3, the scan A12 has been described as changing the X-ray energy for each view, but the scan function 144a may change the X-ray energy for each of a plurality of views.

Further, in FIG. 3, the scan A12 is described as having dual energies (energy E12 and energy E13), but the scan function 144a is a multi-energy scan using X-rays of three or more kinds of energies as the scan A12. May be executed. In this case, the processing circuit 144 can discriminate substances with three or more kinds of reference substances.

As described above, according to the first embodiment, the scan function 144a collects the projection data set B11 corresponding to the energy E11 by irradiating the range R1 along the body axis direction of the subject P1 with X-rays. Scan A11 is executed. Further, the scan function 144a collects the projection data set B12 corresponding to the energy E12 and the projection data set B13 corresponding to the energy E13 by irradiating the range R2 along the body axis direction of the subject P1 with X-rays. Execute scan A12. The processing function 144b also generates a projection data set B14 corresponding to the energy E12 based on the projection data set B11. In addition, the processing function 144b discriminates substances with a plurality of reference substances based on the projection data set B14, the projection data set B12, and the projection data set B13. Therefore, the X-ray CT system 10 according to the first embodiment can improve the accuracy of substance discrimination.

In particular, the projection data set B12, which is the data on the low energy side, is often of lower quality than the projection data set B13, which is the data on the high energy side. Here, the X-ray CT system 10 can correct the projection data set B12 based on the projection data set B14 to improve the quality of the data on the low energy side. As a result, the X-ray CT system 10 can improve the accuracy of substance discrimination based on the data on the low energy side and the data on the high energy side.

Further, the processing function 144b generates image data C11 based on the projection data set B11, segments the image data C11 according to the X-ray absorption coefficient, and forward-projects the segmented image data C11 according to the energy E12. To generate the projection data set B14. Here, at least a part of the noise contained in the projection data set B11 is removed in the process of reconstruction and forward projection. That is, the projection data set B14 has less noise than the projection data set B11. Therefore, the X-ray CT system 10 accurately corrects the projection data set B12 by generating the projection data set B14, as compared with the case where the projection data set B11 is used as it is to correct the projection data set B12. Can be done.

Further, the scan A11 is a positioning scan for executing the scan A12, and is included in a general processing flow. That is, even if the scan A11 is executed, it does not complicate the processing flow and does not increase the exposure dose of the subject P1.

Further, the X-ray CT system 10 uses the result of the scan A11 for the positioning of the scan A12 and also for the processing of substance discrimination. That is, the X-ray CT system 10 can make the exposure of the subject P1 by the scan A11 more meaningful.

(Second Embodiment)
By the way, although the first embodiment has been described so far, it may be implemented in various different forms other than the above-described embodiment.

For example, in the above-described embodiment, only the projection data set B12 of the projection data set B12 and the projection data set B13 collected by the scan A12 is corrected based on the projection data set B11 collected by the scan A11. explained. However, the embodiment is not limited to this, and the processing function 144b may correct the projection data set B13 based on the projection data set B11.

For example, the processing function 144b first generates image data C11 based on the projection data set B11, and then segments the image data C11 according to the X-ray absorption coefficient. Next, the processing function 144b generates the projection data set B15 by forward-projecting the segmented image data C11 according to the energy E13. The projection data set B15 is an example of a fifth projection data set.

Next, the processing function 144b generates a projection data set B17 corresponding to the energy E13 based on the projection data set B13 and the projection data set B15. That is, the processing function 144b generates the projection data set B17 by correcting the projection data set B13 based on the projection data set B15. For example, the processing function 144b generates the projection data set B17 by inputting the projection data set B13 and the projection data set B15 to the trained model M1. The projection data set B17 is an example of the seventh projection data set and the fourth subject data set. Then, the processing function 144b performs material discrimination based on the projection data set B12 corresponding to the energy E12 and the projection data set B17 corresponding to the energy E13.

Although the projection data set B13, which is the data on the high energy side, is generally of high quality, noise may be included in the projection data set B13 when the physique of the subject P1 is large. In addition, artifacts may occur in the projection data set B13 due to various factors such as a discharge phenomenon occurring in the X-ray tube 111 and the body movement of the subject P1. On the other hand, the processing function 144b can correct the projection data set B13 based on the projection data set B11 collected by the scan A11.

Alternatively, the processing function 144b can correct both the projection data set B12 and the projection data set B13 based on the projection data set B11 collected by the scan A11.

For example, the processing function 144b first generates image data C11 based on the projection data set B11, and then segments the image data C11 according to the X-ray absorption coefficient. Next, the processing function 144b generates a projection data set B14 by forward-projecting the segmented image data C11 according to the energy E12. Further, the processing function 144b generates a projection data set B15 by forward-projecting the segmented image data C11 according to the energy E13.

Next, the processing function 144b generates a projection data set B16 corresponding to the energy E12 based on the projection data set B12 and the projection data set B14. For example, the processing function 144b generates the projection data set B16 by inputting the projection data set B12 and the projection data set B14 into the trained model M1. Further, the processing function 144b generates a projection data set B17 corresponding to the energy E13 based on the projection data set B13 and the projection data set B15. For example, the processing function 144b generates the projection data set B17 by inputting the projection data set B13 and the projection data set B15 into the trained model M1. Then, the processing function 144b discriminates substances based on the projection data set B16 corresponding to the energy E12 and the projection data set B17 corresponding to the energy E13.

Further, in the above-described embodiment, it has been described that the projection data set B14 and the projection data set B15 are generated from the projection data set B11 by the processing of reconstruction, segmentation, and forward projection. However, the embodiment is not limited to this.

For example, the processing function 144b can also generate the projection data set B14 and the projection data set B15 from the projection data set B11 by the scaling process. Here, the scaling process is a process of generating data of different energies based on the change in the amount of X-ray transmission according to the energy of the X-ray. For example, the processing function 144b multiplies the projection data set B11 by a coefficient corresponding to the difference between the energy E11 and the energy E12 to obtain the amount of X-ray transmission in the projection data set B11 and the X-ray energy is the energy E12. The projected data set B14 corresponding to the energy E12 is generated by approximating the amount of X-ray transmission in the case. Further, for example, the processing function 144b multiplies the projection data set B11 by a coefficient corresponding to the difference between the energy E11 and the energy E13 to obtain the amount of X-ray transmission in the projection data set B11 and the X-ray energy is the energy E13. The projection data set B15 corresponding to the energy E13 is generated by approximating the amount of X-ray transmission in the case of.

Further, in the above-described embodiment, the user sets the range R2 which is the scan range of the scan A12, 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 C11 or the reference image generated based on the image data C11 and extracting the organ or the like to be diagnosed.

Further, in the above-described embodiment, the scan A11 has been described as a positioning scan for setting the range R2 which is the scan range of the scan A12, but the embodiment is not limited thereto. For example, scan A11 may be a scan performed on a different day than scan A12. Further, the scan A11 may be a scan executed after the scan A12.

Further, in the above-described embodiment, the case where the projection data set B12 and the projection data set B13 are collected by executing the scan A12 of the kV switching method has been described. However, the embodiment is not limited to this.

For example, the scan function 144a may execute the scan A13 of the laminated detector method (also referred to as the dual layer method) instead of the scan A12. In this case, the X-ray CT system 10 includes a stacked detector as the X-ray detector 112. For example, the X-ray detector 112 is composed of a first layer 112a and a second layer 112b, and spectroscopically detects X-rays emitted from an X-ray tube 111. Then, the scan function 144a collects the projection data set B12 based on the detection result of the first layer 112a and the projection data set B13 based on the detection result of the second layer 112b by executing the scan A13. Can be done.

Further, for example, the scan function 144a may execute the dual source scan A14 instead of the scan A12 or the scan A13. In this case, the X-ray CT system 10 includes an X-ray tube 1111 and an X-ray tube 1112 as the X-ray tube 111. Further, the X-ray CT system 10 uses the X-ray detector 112 as an X-ray detector 1121 for detecting X-rays emitted from the X-ray tube 1111 and an X-ray detector for detecting the X-rays emitted from the X-ray tube 1112. It is provided with a line detector 1122. Then, the scan function 144a collects the projection data set B12 based on the detection result of the X-ray detector 1121 and the projection data set B13 based on the detection result of the X-ray detector 1122 by executing the scan A14. Can be done.

Further, for example, the scan function 144a may execute the split type scan A15 instead of the scan A12, the scan A13, or the scan A14. In this case, the X-ray CT system 10 includes a wedge 116 as a filter that divides the X-rays emitted from the X-ray tube 111 into a plurality of X-rays having different energies.

As an example, the X-ray CT system 10 includes an X-ray filter 116a and an X-ray filter 116b as wedges 116. The X-ray filter 116a and the X-ray filter 116b are different in material, thickness, and the like, and divide X-rays having the same energy into a plurality of X-rays having different energies. In this case, the scan function 144a attenuates the X-rays emitted from the X-ray tube 111 to the energy E12 by the X-ray filter 116a and attenuates the X-rays to the energy E13 by the X-ray filter 116b, and executes the scan A15. More specifically, the scanning function 144a refers to the X-ray filter 116a and the X-ray filter 116b in a state where the X-ray filter 116a and the X-ray filter 116b are arranged in the Z-axis direction (column direction) shown in FIG. X-rays are irradiated from the X-ray tube 111. As a result, the scan function 144a executes the scan A15 in a state where the X-rays of the energy E12 and the X-rays of the energy E13 are distributed in the column direction, and corresponds to the projection data set B12 and the energy E13 corresponding to the energy E12. The projection data set B13 and can be collected.

To give another example, the X-ray CT system 10 includes only the X-ray filter 116c as the wedge 116. For example, the scan function 144a irradiates the X-rays of the energy E13 from the X-ray tube 111, attenuates a part of the X-rays to the energy E12 by the X-ray filter 116c, and executes the scan A15. More specifically, the scanning function 144a attenuates X-rays in a predetermined range in the column direction from energy E13 to energy E12 by the X-ray filter 116b, and irradiates the subject P1. The X-rays that have not been attenuated by the X-ray filter 116b are irradiated to the subject P1 with the energy E13. As a result, the scan function 144a executes the scan A15 in a state where the X-rays of the energy E12 and the X-rays of the energy E13 are distributed in the column direction, and corresponds to the projection data set B12 and the energy E13 corresponding to the energy E12. The projection data set B13 and can be collected.

Since the projection data set B12 and the projection data set B13 collected by the dual layer method, the dual source method, or the split method are not sparse data, the processing function 144b interpolates the projection data set B12 and the projection data set B13. It is not necessary to perform processing or process the projection data set B14 and the projection data set B15 based on the projection data set B11 into sparse data.

Further, in the above-described embodiment, the projection data set B12 and the projection data set B13 have been described as correction targets. That is, in the above-described embodiment, the case where the correction is performed in the projection data area has been described. However, the embodiment is not limited to this. For example, the processing function 144b may perform correction in the image area.

For example, the processing function 144b reconstructs the three-dimensional image data C11 corresponding to the energy E11 based on the projection data set B11 collected by the scan A11. Further, the processing function 144b reconstructs the three-dimensional image data C12 corresponding to the energy E12 based on the projection data set B12 collected by the scan A12. Further, the processing function 144b reconstructs the three-dimensional image data C13 corresponding to the energy E13 based on the projection data set B13 collected by the scan A12. Here, the image data C11 is an example of the first subject data set. Further, the image data C12 is an example of the second subject data set. Further, the image data C13 is an example of the third subject data set.

Next, the processing function 144b corrects at least one of the image data C12 and the image data C13 based on the image data C11. Here, even if the image data C11 corresponds to an X-ray energy different from that of the image data C12 and the image data C13, it has valuable information regarding the X-ray attenuation and the anatomical structure in the subject P1. There is. Therefore, the processing function 144b can improve the quality of the reconstructed image such as the image data C12 and the image data C13 based on the image data C11. Then, the processing function 144b executes the substance discrimination process based on the image data C12 and the image data C13 in which at least one of them is corrected.

When the correction is performed in the image area, the processing function 144b can omit the above-mentioned generation processing of the projection data set B14 and the projection data set B15. That is, the processing function 144b can omit the processing of simulating the projection data set of another energy.

Further, the correction process in the image region described above can be realized by a machine learning method. For example, the processing function 144b has been trained to receive input of image data based on the first scan and image data based on the second scan and correct the image data based on the second scan. The model M2 is generated in advance and stored in the memory 141. Further, when the scan A11 and the scan A12 are executed, the processing function 144b inputs the image data C11 based on the scan A11 and the image data C12 based on the scan A12 to the trained model M2 read from the memory 141. By doing so, the image data C12'corrected from the image data C12 is generated. Then, the processing function 144b executes the substance discrimination process based on the image data C12'corresponding to the energy E12 and the image data C13 corresponding to the energy E13. Here, the image data C12'is an example of a fourth subject data set. That is, the processing function 144b discriminates substances based on the fourth subject data set obtained based on the first subject data set and the second subject data set and the third subject data set. Execute the processing of.

Alternatively, the processing function 144b generates image data C13'corrected image data C13 by inputting image data C11 based on scan A11 and image data C13 based on scan A12 into the trained model M2. To do. Then, the processing function 144b executes the substance discrimination process based on the image data C12 corresponding to the energy E12 and the image data C13'corresponding to the energy E13. Here, the image data C13'is an example of a fourth subject data set. That is, the processing function 144b discriminates substances based on the fourth subject data set obtained based on the first subject data set and the third subject data set and the second subject data set. Execute the processing of.

Alternatively, the processing function 144b uses the trained model M2 to generate both the image data C12'corrected by the image data C12 and the image data C13' corrected by the image data C13. Then, the processing function 144b executes the substance discrimination process based on the image data C12'corresponding to the energy E12 and the image data C13' corresponding to the energy E13. That is, the processing function 144b includes a fourth subject data set, a first subject data set, and a third subject data obtained based on the first subject data set and the second subject data set. The substance discrimination process is performed based on the fourth subject data set obtained based on the set.

The trained model M2 can be configured in the same manner as the trained model M1. For example, the trained model M2 can be constructed by a neural network. As an example, the processing function 144b generates a trained model M2 by executing deep learning on a multi-layer neural network. Here, the type of the neural network is not particularly limited, and may be a convolutional neural network (CNN), or another type such as a fully connected neural network or a recursive neural network (RNN). It may be a neural network of. Alternatively, the processing function 144b may generate the trained model M2 by a machine learning method other than the neural network. Further, the processing function 144b may acquire and use the trained model M2 generated by another device without performing the generation processing of the trained model M2.

Further, it has been described so far that the projection data set B12 corresponding to the energy E12 and the projection data set B13 corresponding to the energy E13 are collected in the second scan. However, the embodiment is not limited to this. For example, the scan function 144a may collect only one of the projection data set B12 and the projection data set B13 in the second scan. In this case, the processing function 144b corrects either the projection data set B12 or the projection data set B13 based on the projection data set B11, and high-quality CT image data based on the corrected projection data set. Can be reconstructed. Alternatively, the processing function 144b reconstructs either the image data C12 reconstructed from the projection data set B12 or the image data C13 reconstructed from the projection data set B13 based on the image data C11 reconstructed from the projection data set B11. It can be corrected and the quality can be improved.

Further, although the substance discrimination has been described as being performed by the X-ray CT system 10, the embodiment is not limited to this. For example, substance discrimination may be performed 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. 6 as an example. FIG. 6 is a block diagram showing an example of the configuration of the medical information processing system 1 according to the second embodiment. The medical information processing system 1 includes an X-ray CT system 10 and a medical processing device 20 that performs substance discrimination.

As shown in FIG. 6, 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. 6, 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 an image showing the result of substance discrimination by the processing circuit 24, or displays a GUI or the like for accepting 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. 6, 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. 6 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. 6 is realized.

For example, first, the scan function 144a in the X-ray CT system 10 irradiates the range R1 along the body axis direction of the subject P1 with X-rays to execute the scan A11, and displays the projection data set B11 corresponding to the energy E11. collect. Further, the scan function 144a irradiates the range R2 along the body axis direction of the subject P1 with X-rays to execute the scan A12, and executes the scan A12, and the projection data set B12 corresponding to the energy E12 and the projection data corresponding to the energy E13. Collect set B13. The scan function 144a may execute the dual layer type scan A13, the dual source type scan A14, or the split type scan A15 instead of the kV switching type scan A12. Further, the control function 144c transmits the projection data set B11, the projection data set B12, and the projection data set B13 to the medical processing apparatus 20 via the network NW.

Next, the processing function 24a in the medical processing apparatus 20 generates at least one of the projection data set B14 corresponding to the energy E12 and the projection data set B15 corresponding to the energy E13 based on the projection data set B11. Further, the processing function 24a discriminates substances based on at least one of the projection data set B14 and the projection data set B15 and the projection data set B12 and the projection data set B13.

For example, the processing function 24a generates a projection data set B16 corresponding to the energy E12 based on the projection data set B12 and the projection data set B14, and discriminates substances based on the projection data set B16 and the projection data set B13. Further, for example, the processing function 24a generates a projection data set B17 corresponding to the energy E13 based on the projection data set B13 and the projection data set B15, and discriminates substances based on the projection data set B12 and the projection data set B17. Do it. Further, for example, the processing function 24a generates a projection data set B16 based on the projection data set B12 and the projection data set B14, generates a projection data set B17 based on the projection data set B13 and the projection data set B15, and projects the projection data set B17. Material discrimination is performed based on the data set B16 and the projection data set B17.

In addition, the control function 24b causes the display 22 to display an image showing the result of substance discrimination by the processing function 24a. Alternatively, the control function 24b transmits an image showing the result of substance discrimination to the X-ray CT system 10. In this case, the control function 144c in the X-ray CT system 10 causes the display 142 to display an image showing the result of substance discrimination.

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. 6, 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, the accuracy of substance discrimination can be improved.

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 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 (15)

A first scan is performed to collect a first subject data set corresponding to the first X-ray energy by irradiating the first region of the subject with X-rays, and after the first scan. A third region different from the second subject data set corresponding to the second X-ray energy and the second X-ray energy by irradiating the second region included in the first region with X-rays. A scanning unit that executes a second scan that collects a third subject data set corresponding to the X-ray energy of
A fourth subject data set obtained based on the first subject data set and one of the second and third subject data sets, and the other of the second and third subject data sets. An X-ray CT system equipped with a processing unit that discriminates substances based on a plurality of reference substances. The scanning unit
The first scan is performed by irradiating the first region along the body axis direction of the subject with X-rays, and the first projection data set is collected as the first subject data set. And
After the first scan, the second scan is performed by irradiating a second region narrower than the first region along the body axis direction with X-rays to perform the second scan. A second projection data set is collected as the sample data set, and a third projection data set is collected as the third subject data set.
The processing unit
Based on the first projection data set, at least one of the fourth projection data set corresponding to the second X-ray energy and the fifth projection data set corresponding to the third X-ray energy Generate and
The fourth subject data set obtained based on one of the fourth projection data set, the second projection data set, the fifth projection data set, and the third projection data set, and the said. The X-ray CT system according to claim 1, wherein the substance discrimination is performed based on the other of the second and third projection data sets. The X-ray CT system according to claim 1 or 2, wherein the first X-ray energy is different from the second X-ray energy and the third X-ray energy. The second X-ray energy is smaller than the third X-ray energy,
The processing unit
Based on the first projection data set, the fourth projection data set corresponding to the second X-ray energy is generated.
Based on the second projection data set and the fourth projection data set, a sixth projection data set corresponding to the second X-ray energy is generated.
The X-ray CT system according to claim 2, wherein the substance discrimination is performed based on the third projection data set and the sixth projection data set. The processing unit
Based on the first projection data set, the fourth projection data set corresponding to the second X-ray energy and the fifth projection data set corresponding to the third X-ray energy are generated.
Based on the second projection data set and the fourth projection data set, a sixth projection data set corresponding to the second X-ray energy is generated.
Based on the third projection data set and the fifth projection data set, a seventh projection data set corresponding to the third X-ray energy is generated.
The X-ray CT system according to claim 2, wherein the substance discrimination is performed based on the sixth projection data set and the seventh projection data set. The processing unit generates three-dimensional first image data based on the first projection data set, segments the first image data according to the X-ray absorption coefficient, and segments the first image data. The X-ray CT system according to claim 4, wherein the fourth projection data set is generated by forward-projecting according to the second X-ray energy. The processing unit generates three-dimensional first image data based on the first projection data set, segments the first image data according to the X-ray absorption coefficient, and segments the first image data. The fourth projection data set is generated by forward projection according to the second X-ray energy, and the segmented first image data is forward-projected according to the third X-ray energy. The X-ray CT system according to claim 5, which produces a fifth projection data set. The processing unit receives the input of two projection data sets collected from the same object and outputs a high-quality projection data set to the trained model, the fourth projection data set. The X-ray CT system according to claim 4 or 6, wherein the sixth projection data set is generated by inputting the second projection data set and the second projection data set. The processing unit receives the input of two projection data sets collected from the same object and outputs a high-quality projection data set to the trained model, the fourth projection data set. And the second projection data set are input to generate the sixth projection data set, and the fifth projection data set and the third projection data set are input to generate the seventh projection data set. The X-ray CT system according to claim 5 or 7, which produces a projection data set. The scanning unit executes the second scan by changing the X-ray energy between the second X-ray energy and the third X-ray energy for each one or a plurality of views. , The X-ray CT system according to any one of claims 1 to 9. The scanning unit irradiates the X-ray of the second X-ray energy from the first X-ray tube and irradiates the X-ray of the third X-ray energy from the second X-ray tube. The X-ray CT system according to any one of claims 1 to 9, wherein the second scan is performed. The scanning unit has a laminated X-ray detection having a first layer for detecting X-rays of the second X-ray energy and a second layer for detecting X-rays of the third X-ray energy. The X-ray CT system according to any one of claims 1 to 9, wherein the second scan is performed using a device. The scanning unit includes a first X-ray filter that attenuates transmitted X-rays to the second X-ray energy, and a second X-ray filter that attenuates transmitted X-rays to the third X-ray energy. The X-ray CT system according to any one of claims 1 to 9, wherein the second scan is performed using the X-ray CT system. The scanning unit attenuates a part of the X-rays applied to the subject by using an X-ray filter that attenuates the transmitted X-rays from the second X-ray energy to the third X-ray energy. The X-ray CT system according to any one of claims 1 to 9, wherein the second scan is performed. Performed after the first scan with the first subject dataset corresponding to the first X-ray energy collected by irradiating the first region of the subject with X-rays in the first scan. The second subject data set corresponding to the second X-ray energy collected by irradiating the second region included in the first region with X-rays in the second scan and the second region. A fourth subject data set obtained based on one of a third subject data sets corresponding to a third X-ray energy different from the X-ray energy, and the second and third subject data sets. A medical processing apparatus provided with a processing unit that discriminates substances based on a plurality of reference substances based on the other.

Images