Medical information processing method, medical information processing apparatus, and medical image processing apparatus

Abstract

To create a medical image with improved contract.SOLUTION: A medical information processing method creates a high contrast image with higher contrast than that of a second medical image acquired by a second medical image diagnostic device by applying conversion processing to a first medical image having first contrast in a region of interest imaged by a first medical image diagnostic device. The medical information processing method creates a pseudo-second medical image having second contrast lower than the first contrast in the region of interest, which is an image pseudo-reproducing the second medical image, by applying image processing to the high contrast image. A model is learned with the pseudo-second medical image as input data, and with the high contrast image as teacher data, and a learned model is created.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The embodiments disclosed in this specification and the drawings relate to a medical information processing method, a medical information processing apparatus, and a medical image processing apparatus.

Background Art

[0002] Conventionally, in the medical image diagnosis of brain tissue, diagnosis using CT (Computed Tomography) images and MR (Magnetic Resonance) images has become widespread. Here, although the contrast on the images of the white matter and gray matter of the brain has been improved by image processing such as noise reduction and contrast enhancement processing in CT images, it does not reach the contrast of MR images. Particularly at the emergency site, etc., imaging takes time, and further, when a metal is embedded in the patient, the need for image acquisition by an X-ray CT apparatus that can perform imaging in a shorter time is higher than that of an MRI apparatus that cannot perform imaging, and a CT image with improved tissue contrast is desired.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to generate a medical image with improved contrast. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problems. The problems corresponding to the respective effects of each configuration shown in the embodiments described later can also be regarded as other problems.

Means for Solving the Problems

[0005] The medical information processing method according to this embodiment applies a conversion process to a first medical image having a first contrast in a region of interest, which is taken by a first medical image diagnostic apparatus, to generate a high-contrast image having a higher contrast than a second medical image obtained by a second medical image diagnostic apparatus. By applying an image process to the high-contrast image, a pseudo-second medical image is generated which is an image that pseudo-reproduces the second medical image and has a second contrast lower than the first contrast in the region of interest. Using the pseudo-second medical image as input data and the high-contrast image as teacher data, a model is learned to generate a learned model.

Brief Description of Drawings

[0006]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Modes for Carrying Out the Invention

[0007] Hereinafter, a medical information processing method, a medical information processing apparatus, and a medical image processing apparatus according to this embodiment will be described with reference to the drawings. In the following embodiments, parts denoted by the same reference numerals perform the same operations, and overlapping descriptions will be omitted as appropriate. Hereinafter, one embodiment will be described with reference to the drawings.

[0008] (First Embodiment) The medical information processing apparatus according to the first embodiment will be described with reference to the block diagram of FIG. 1. The medical information processing apparatus 1 according to the first embodiment includes a memory 11, a processing circuit 13, an input interface 15, and a communication interface 17.

[0009] The memory 11 is a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or an integrated circuit memory device that stores various types of information. In addition to HDDs, SSDs, etc., the memory 11 may also be a drive device that reads and writes various types of information to and from portable storage media such as CDs (Compact Discs), DVDs (Digital Versatile Discs), flash memories, and semiconductor memory elements such as RAMs (Random Access Memories). Further, the storage area of the memory 11 may be within the medical information processing apparatus 1 or within an external storage device connected by a network. The memory 11 is assumed to store learning data, a learned model, various types of medical data (raw data, projection data, intermediate data such as sinograms, etc.), and various types of medical images (reconstructed images, CT (Computed Tomography) images, MR (Magnetic Resonance) images, ultrasonic images, PET (Positron Emission Tomography) images, SPECT (Single photon emission computed tomography), etc.). Note that the learning data, the learned model, the medical data, and the medical images, etc., may be stored externally. When the learning data, the learned model, the medical data, and the medical images, etc., are stored externally, it is sufficient that the processing circuit 13 can refer to them.

[0010] The processing circuit 13 includes, for example, as hardware resources, a processor such as a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), and a memory such as a ROM (Read Only Memory) and a RAM. The processing circuit 13 may also be implemented by an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), other Complex Programmable Logic Devices (CPLDs), or Simple Programmable Logic Devices (SPLDs). The processing circuit 13 executes an acquisition function 131, a teacher image generation function 132, an input image generation function 133, a model learning function 134, a model execution function 135, and a display control function 136 by a processor that executes a program deployed in the memory. Note that each function (acquisition function 131, teacher image generation function 132, input image generation function 133, model learning function 134, model execution function 135, and display control function 136) is not limited to being realized by a single processing circuit. It is also acceptable to configure the processing circuit 13 by combining a plurality of independent processors, and each function is realized by each processor executing a program.

[0011] The processing circuit 13 acquires, by the acquisition function 131, a first medical image having a first contrast in a region of interest, which is taken by the first medical imaging diagnostic apparatus. In other words, the first medical image is a medical image obtained by a first imaging modality, which is an imaging method used in the first medical imaging diagnostic apparatus. The first contrast is the contrast between tissues in the region of interest depicted in the first medical image.

[0012] The processing circuit 13, by applying a conversion process to the first medical image using the teacher image generation function 132, generates a high-contrast image with higher contrast than the second medical image obtained by the second medical image diagnostic apparatus. In other words, by applying a conversion process to the first medical image to convert the image obtained by the first imaging modality into an image equivalent to the second imaging modality, which is the imaging method used by the second medical image diagnostic apparatus, the second medical image is obtained. The teacher image generation function 132 is an example of a first generation unit. The second medical image diagnostic apparatus is assumed to be an apparatus that can capture a medical image with higher tissue contrast in the region of interest than the first medical image diagnostic apparatus.

[0013] The processing circuit 13, by applying image processing to the high-contrast image using the input image generation function 133, generates a pseudo-second medical image that pseudo-reproduces the second medical image and has a second contrast lower than the first contrast in the region of interest. The image processing is assumed to be at least a process that reduces (degrades) the contrast of the image, such as a contrast reduction process and a noise addition process.

[0014] The processing circuit 13, using the pseudo-second medical image as input data and the high-contrast image as teacher data, learns (trains) a learning model and generates a learned model. The generated learned model can improve the contrast of the image obtained by the second imaging modality. As the learning model assumed in this embodiment, a neural network, a deep neural network, a deep convolutional neural network (DCNN), etc. are assumed. Note that, without being limited to this, any model that can learn some features from the learning data may be used.

[0015] The processing circuit 13, by means of the model execution function 135, applies the learned model to the second medical image acquired from the second medical imaging device, and outputs a high-contrast image with improved contrast of the second medical image. Note that, for example, when the learned model is stored in the memory 11, the learned model may be referred to from the memory 11, or when the learned model is stored in an external device, the model execution function 135 may refer to the external device.

[0016] The processing circuit 13, by means of the display control function 136, controls the output of the image so that the high-contrast image is displayed on the display or on a screen via a projector.

[0017] The input interface 15 receives various input operations from the user, and outputs signals based on the received input operations to the memory 11, the processing circuit 13, the communication interface 17, and the like. For example, a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touch pad, a touch panel display, etc. can be used as appropriate. Note that in this embodiment, the input interface 15 is not limited to one including physical operation components such as a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touch pad, and a touch panel display. For example, a processing circuit that receives a signal corresponding to an input operation from an external input device provided separately from the apparatus and outputs this signal to the processing circuit 13 is also included in the examples of the input interface 15. The communication interface 17 is a wireless or wired interface for communicating with the outside, and since a general interface may be used, the description here is omitted.

[0018] Note that the configuration including the memory 11, the acquisition function 131, the model execution function 135, the processing circuit 13 including the display control function 136, the input interface 15, and the communication interface 17 is also called a medical image processing apparatus. The medical information processing apparatus 1 and the medical image processing apparatus according to the first embodiment may be implemented in a computer such as a workstation having a general-purpose processor such as a CPU or a GPU, or a processor configured specifically for machine learning, or may be mounted on a server such as a PACS. Alternatively, it may be mounted on various medical image diagnostic apparatuses such as a CT apparatus. Also, each of the above-described functions (acquisition function 131, teacher image generation function 132, input image generation function 133, model learning function 134, model execution function 135, and display control function 136) may be executed by separate devices, and the above-described processing may be realized by connecting the devices so as to be communicable.

[0019] Next, the concept during the learning of the model by the model learning function 134 will be described with reference to FIG. 2. During the learning of the model, the network model 21 is learned using learning data. As shown in FIG. 2, the network model 21 is learned using learning data in which a high-contrast image generated from a first medical image is used as teacher data (correct data), and a pseudo-second medical image generated from the high-contrast image is used as input data, and a learned model 23 is generated. Next, a specific example during the model learning by the model learning function 134 will be described with reference to FIG. 3.

[0020] FIG. 3 is a conceptual diagram showing a case where a learned model is generated using learning data related to an MR image of a subject's head as a specific example during the learning of the learned model. Here, an MRI apparatus is assumed as the first medical image diagnostic apparatus, and an X-ray CT apparatus is assumed as the second medical image diagnostic apparatus. Also, the MR image is the first medical image, and the pseudo-CT image is the pseudo-second medical image.

[0021] The MR image 31 is an MR image when a region including the white matter and gray matter of the brain is set as the region of interest, and it is assumed to be an image with high contrast between tissues of white matter and gray matter, such as a FLAIR (Fluid attenuated inversion recovery) image.

[0022] By performing a conversion process from an MR image to a CT image, a high-contrast CT image 32 is generated that, although it is an image simulating a CT image, maintains the contrast of the MR image 31 to some extent and has a higher contrast than a general CT image. For image conversion processing between medical images taken with different medical imaging diagnostic devices, such as the conversion from an MR image to a CT image, general image conversion processing may be used. That is, any method may be used as long as it is an image conversion that can be converted into an image corresponding to an image taken with a different imaging modality, which is a different image imaging method. The high-contrast CT image 32 has lower contrast regarding the white matter and gray matter regions than the MR image 31. On the other hand, it is assumed that the high-contrast CT image 32 has a higher contrast than a CT image actually taken by an X-ray CT device. Also, it is assumed that the shapes of the anatomical structures depicted in the high-contrast CT image 32 and the MR image 31 are substantially the same. The pseudo-CT image 33 is generated by performing image processing on the high-contrast CT image 32. That is, since a general CT image has lower contrast of white matter and gray matter than the contrast of an MR image, image processing is performed on the high-contrast CT image 32 that simulates a CT image so as to be closer to an actual CT image. Specifically, the processing circuit 13 by the input image generation function 133 performs a contrast reduction process and a noise addition process on the high-contrast CT image 32. For the contrast reduction process, for example, filter processing may be performed so that the contrast of the entire image becomes lower. Also, for the noise addition process, for example, a process of adding noise so as to include granular noise peculiar to a CT image may be performed.

[0023] As described above, a plurality of pieces of learning data in which the pseudo CT image 33 and the high-contrast CT image 32 are paired are prepared and stored in, for example, the memory 11. The processing circuit 13 by the model learning function 134 iteratively learns the network model 21 using the pseudo CT image 33 as input data and the high-contrast CT image 32 as teacher data, thereby generating a learned model. The learning method of the network model 21 may be a learning method in general machine learning, such as calculating an error between the output image from the network model 21 and the high-contrast CT image 32 which is the teacher data, and learning the parameters of the network model using the error backpropagation method so that the error function regarding the error becomes minimum. Thereby, the network model 21 can be learned so that a high-contrast CT image having the contrast of the tissue in the region of interest comparable to that of the MR image can be reproduced from the CT image.

[0024] Note that if the MR image 31 is collected, the conversion into the high-contrast CT image 32 and the pseudo CT image 33 is easy. Therefore, since it is not necessary to collect the CT image corresponding to the MR image in a pair, the learning data can be prepared easily and efficiently. Also, when generating the high-contrast CT image 32 and the pseudo CT image 33 from the MR image 31, images assuming a plurality of types of image reconstruction processes may be generated and used as learning data. For example, as the image reconstruction method, there is image reconstruction processing using the filtered back projection method (FBP method) or the successive approximation reconstruction method, etc. When using the learned model, it is unknown what type of image reconstruction process the input CT image has undergone. Therefore, in order to support various image reconstruction processes, for example, the processing circuit 13, by means of the input image generation function 133, generates, from a single high-contrast CT image 32, a pseudo CT image 33 assuming image reconstruction by the FBP method and a pseudo CT image 33 assuming image reconstruction by the successive approximation reconstruction method. For example, the pseudo CT image 33 of the successive approximation reconstruction method has a different noise pattern such as the amount of noise and the type of noise compared to the pseudo CT image 33 of the FBP method. By adding a noise pattern for successive approximation reconstruction to the high-contrast CT image 32, a pseudo CT image 33 for successive approximation reconstruction can be generated, and by adding a noise pattern for FBP reconstruction, a pseudo CT image 33 for FBP reconstruction can be generated. In this way, by generating pseudo CT images 33 assuming multiple types of image reconstruction processes, a more general-purpose learned model 23 can be generated.

[0025] Also, the MR image 31 that is the source of the training data may include not only MR images of specific types of diseases but also MR images of various cases and MR images of normal states of healthy subjects. Thereby, training data rich in variations can be prepared, and a more general-purpose learned model 23 can be generated.

[0026] Next, the concept when using the learned model 23 will be described with reference to FIG. 4. When using the learned model 23, the learned model 23 is applied to the CT image actually taken by the X-ray CT apparatus. That is, the processing circuit 13, by means of the model execution function 135, inputs the CT image actually taken to the learned model 23, and a high-contrast CT image with improved contrast of the CT image is output from the learned model 23.

[0027] Note that, as the high-contrast image, a contrast-enhanced image obtained by performing contrast enhancement processing on a CT image taken with an X-ray CT apparatus by setting a high tube current value (mAs) may be used. Since contrast enhancement processing effectively acts on a CT image taken by setting a high tube current value, learning data using the contrast-enhanced image as teacher data and the taken CT image as input data may be used.

[0028] In the above example, the head was assumed as the imaging target site, but it is not limited to this, and the abdomen, spinal cord, limbs, joints, etc. may be used as the imaging target site. By setting the imaging target site as a site with a higher contrast of tissue, more benefits can be obtained.

[0029] Note that when assuming a plurality of imaging target sites, a learned model is generated for each imaging target site. For example, if the imaging target site is the head, a learned model may be generated using learning data including a high-contrast image generated from an MR image related to the head and a corresponding pseudo CT image. Also, if it is the abdomen, a learned model may be generated using learning data including a high-contrast image generated from an MR image related to the abdomen and a corresponding pseudo CT image.

[0030] Also, not limited to MR images, a high-contrast image may be generated based on a PET image obtained by a PET apparatus. The PET image is used, for example, 18 to measure the sugar metabolism of tissues using a glucose analog such as 18F-FDG (fluorodeoxyglucose) for diagnosis of the presence and malignancy of tumors. Therefore, since the contrast of tumors is higher than that of CT images, a high-contrast image (for example, a fusion image obtained by superimposing a PET image and a CT image) is generated from the PET image with the tumor part as the region of interest, and a pseudo CT image corresponding to the high-contrast image is generated and used as learning data, so that a learned model can be generated in the same manner as in the case of MR images. By applying the learned model to the taken CT image, a fusion image with improved contrast regarding tumors can be generated. Note that the present invention is not limited to PET images, and SPECT images obtained by an SPECT apparatus may also be used.

[0031] According to the first embodiment described above, a high-contrast image having a higher contrast than the second medical image is generated from the first medical image having a high contrast, and by performing image processing on the high-contrast image, an image that pseudo-reproduces the second medical image and has a lower contrast than the high-contrast image, i.e., a pseudo-second medical image, is generated. A learned model is generated by using the pseudo-second medical image as input data and the high-contrast image as teacher data to train the model. By applying the learned model to the actually captured second medical image, a medical image with improved contrast compared to the second medical image can be generated. (Second Embodiment) In the second embodiment, an X-ray CT apparatus will be described as an example of a medical image diagnostic apparatus including the functions of the processing circuit 13 of the medical image processing apparatus according to the first embodiment.

[0032] Hereinafter, the X-ray CT apparatus according to the present embodiment will be described with reference to the block diagram of FIG. 5. The X-ray CT apparatus 2 shown in FIG. 5 includes a gantry apparatus 70, a couch apparatus 50, and a console apparatus 40 that realizes the processing of the X-ray CT apparatus. In FIG. 5, for convenience of explanation, the gantry apparatus 70 is drawn a plurality of times.

[0033] Note that the X-ray CT apparatus 2 and the control method according to the present embodiment will be described by taking a horizontal type X-ray CT apparatus as an example, but the present invention can be similarly applied to a standing type X-ray CT apparatus. Further, the present invention can be similarly applied to an X-ray CT apparatus that can scan a subject in both standing and horizontal positions according to the scan mode.

[0034] In the present embodiment, the longitudinal direction of the rotation axis of the rotation frame 73 in the non-tilt state is defined as the Z axis, the direction orthogonal to the Z axis and toward the support column that supports the rotation frame 73 from the rotation center is defined as the X axis, and the direction orthogonal to the Z axis and the X axis is defined as the Y axis.

[0035] For example, the gantry device 70 and the bed device 50 are installed in the CT examination room, and the console device 40 is installed in the control room adjacent to the CT examination room. Note that the console device 40 does not necessarily have to be installed in the control room. For example, the console device 40 may be installed in the same room as the gantry device 70 and the bed device 50. In any case, the gantry device 70, the bed device 50, and the console device 40 are connected to each other by wire or wirelessly so as to be able to communicate with each other.

[0036] The gantry device 70 is a scanning device having a configuration for X-ray CT imaging of the subject P. The gantry device 70 includes an X-ray tube 71, an X-ray detector 72, a rotating frame 73, an X-ray high-voltage device 74, a control device 75, a wedge 76, a collimator 77, and a data acquisition device 78 (hereinafter also referred to as a DAS (Data Acquisition System) 78).

[0037] The X-ray tube 71 is a vacuum tube that generates X-rays by irradiating thermoelectrons from the cathode (filament) toward the anode (target) by applying a high voltage from the X-ray high-voltage device 74 and supplying a filament current. Specifically, X-rays are generated when the thermoelectrons collide with the target. For example, the X-ray tube 71 includes a rotating anode type X-ray tube that generates X-rays by irradiating the rotating anode with thermoelectrons. The X-rays generated by the X-ray tube 71 are shaped into a cone beam shape through, for example, the collimator 77 and irradiated onto the subject P.

[0038] The X-ray detector 72 detects the X-rays irradiated from the X-ray tube 71 and passing through the subject P. The X-ray detector 72 has, for example, a plurality of X-ray detector element arrays in which a plurality of X-ray detector elements are arranged in the channel direction along an arc centered on the focal point of the X-ray tube 71. The X-ray detector 72 has, for example, a column structure in which a plurality of X-ray detector element arrays in which a plurality of X-ray detector elements are arranged in the channel direction are arranged in the slice direction (column direction, row direction).

[0039] The X-ray detector 72 is specifically, for example, an indirect conversion type detector having a grid, a scintillator array, and a photosensor array. The X-ray detector 72 can be assumed to be either a general integration type detector or a photon counting type detector. The X-ray detector 72 is an example of a detection unit.

[0040] The case where the X-ray detector 72 is an integration type detector will be described. The scintillator array has a plurality of scintillators. The scintillator has a scintillator crystal that outputs light in an amount of photons corresponding to the incident X-ray dose. The grid is disposed on the X-ray incident side surface of the scintillator array and has an X-ray shielding plate having a function of absorbing scattered X-rays. Note that the grid may also be called a collimator (one-dimensional collimator or two-dimensional collimator). The photosensor array has a function of amplifying the light received from the scintillator and converting it into an electrical signal, and has a photosensor such as a photomultiplier tube (PMT).

[0041] Next, the case where the X-ray detector 72 is a photon counting type detector will be described. The scintillator converts the incident X-ray into a number of photons corresponding to the intensity of the incident X-ray. The photosensor array has a function of amplifying the light received from the scintillator and converting it into an electrical signal, and generating an output signal (energy signal) having a pulse height value corresponding to the energy of the incident X-ray. Note that the X-ray detector 72 may be a direct conversion type detector having a semiconductor element that converts the incident X-ray into an electrical signal.

[0042] The rotating frame 73 is an annular frame that oppositely supports the X-ray tube 71 and the X-ray detector 72, and rotates the X-ray tube 71 and the X-ray detector 72 by a control device 75 described later. Note that the rotating frame 73 further supports an X-ray high voltage device 74 and a DAS 78 in addition to the X-ray tube 71 and the X-ray detector 72.

[0043] The rotating frame 73 is rotatably supported by a fixed frame (not shown) made of a metal such as aluminum. Specifically, the rotating frame 73 is connected to the edge of the fixed frame via a bearing. The rotating frame 73 receives power from the drive mechanism of the control device 75 and rotates at a constant angular velocity around the rotation axis Z.

[0044] The rotating frame 73 is rotatably supported by a non-rotating part of the gantry device (for example, a fixed frame; illustration in FIG. 1 is omitted). The rotation mechanism includes, for example, a motor that generates a rotational driving force and a bearing that transmits the rotational driving force to the rotating frame 73 to cause rotation. The motor is provided, for example, on the non-rotating part, and the bearing is physically connected to the rotating frame 73 and the motor, and the rotating frame rotates according to the rotational force of the motor.

[0045] A non-contact or contact communication circuit is provided on each of the rotating frame 73 and the non-rotating part, whereby communication is performed between the unit supported by the rotating frame 73 and the non-rotating part or an external device of the gantry device 70. For example, when optical communication is adopted as the non-contact communication method, the detection data generated by the DAS 78 is transmitted by optical communication from a transmitter having a light-emitting diode (LED) provided on the rotating frame 73 to a receiver having a photodiode provided on the non-rotating part of the gantry device, and is further transferred from the non-rotating part to the console device 40 by the transmitter. In addition to this, as the communication method, in addition to non-contact data transmission such as capacitive coupling and radio wave methods, a contact data transmission method using a slip ring and an electrode brush may also be adopted.

[0046] The X-ray high voltage device 74 has an electric circuit such as a transformer and a rectifier, and is a high voltage generating device having a function of generating a high voltage applied to the X-ray tube 71 and a filament current supplied to the X-ray tube 71, and an X-ray control device that controls the output voltage according to the X-ray irradiated by the X-ray tube 71. The high voltage generating device may be of a transformer type or an inverter type. Note that the X-ray high voltage device 74 may be provided on the rotating frame 73 described later, or may be provided on the fixed frame (not shown) side of the gantry device 70.

[0047] The control device 75 has a processing circuit having a CPU or the like, and a drive mechanism such as a motor and an actuator. The processing circuit has, as hardware resources, a processor such as a CPU or an MPU, and a memory such as a ROM and a RAM. Further, the control device 75 may be realized by an ASIC, an FPGA, other CPLDs, or SPLDs. The control device 75 controls the X-ray high voltage device 74, the DAS 78, etc. according to commands from the console device 40. The processor realizes the above control by reading out a program stored in the memory.

[0048] In addition, the control device 75 has a function of receiving an input signal from an input interface 43 (to be described later), which is attached to the console device 40 or the gantry device 70, and controlling the operations of the gantry device 70 and the bed device 50. For example, the control device 75 performs control to rotate the rotating frame 73 upon receiving the input signal, control to tilt the gantry device 70, and control to operate the bed device 50 and the top plate 53. The control to tilt the gantry device 70 is realized by the control device 75 rotating the rotating frame 73 about an axis parallel to the X-axis direction based on the inclination angle (tilt angle) information input by the input interface 43 attached to the gantry device 70. Further, the control device 75 may be provided in the gantry device 70 or may be provided in the console device 40. Note that the control device 75 may be configured to directly incorporate the program into the circuit of the processor instead of storing the program in the memory. In this case, the processor realizes the above control by reading and executing the program incorporated in the circuit.

[0049] The wedge 76 is a filter for adjusting the X-ray dose irradiated from the X-ray tube 71. Specifically, the wedge 76 is a filter that transmits and attenuates the X-rays irradiated from the X-ray tube 71 so that the X-rays irradiated from the X-ray tube 71 to the subject P have a predetermined distribution. For example, the wedge 76 (wedge filter, bow-tie filter) is a filter formed by processing aluminum to have a predetermined target angle and a predetermined thickness.

[0050] The collimator 77 is a plurality of aperture vanes (also referred to as blades) for narrowing down the irradiation range of the X-rays that have passed through the wedge 76, and forms a slit (also referred to as an aperture) by combining the plurality of aperture vanes. The aperture vanes are formed of a material with high X-ray shielding ability, such as a lead plate. Note that the collimator 77 may sometimes be referred to as an X-ray aperture.

[0051] When the X-ray detector 72 is an integrating detector, the DAS 78 reads an electrical signal from the X-ray detector 72 and generates digital data (hereinafter also referred to as detection data) regarding the dose of X-rays detected by the X-ray detector 72 based on the read electrical signal. The detection data is a set of data indicating the channel number of the generating X-ray detection element, the column number, the view number indicating the collected view (also referred to as the projection angle), and the integrated value of the dose of the detected X-rays.

[0052] Also, when the X-ray detector 72 is a photon counting type detector, the DAS 78 reads an energy signal from the X-ray detector 72 and generates detection data indicating the count of X-rays detected by the X-ray detector 72 for each of a plurality of energy bands (energy bins) based on the read energy signal. The detection data is a set of data indicating the channel number of the generating detector pixel, the column number, the view number indicating the collected view, and the count value identified by the energy bin number. The DAS 78 is realized, for example, by an ASIC (Application Specific Integrated Circuit) equipped with circuit elements capable of generating detection data.

[0053] The bed device 50 is a device for placing and moving a subject P to be scanned, and includes a base 51, a bed driving device 52, a top plate 53, and a support frame 54. The base 51 is a housing that supports the support frame 54 so as to be movable in the vertical direction. The bed driving device 52 is a motor or actuator that moves the top plate 53 on which the subject P is placed in the longitudinal axis direction of the top plate 53. The bed driving device 52 moves the top plate 53 according to the control by the console device 40 or the control by the control device 75. For example, the bed driving device 52 moves the top plate 53 in a direction orthogonal to the subject P so that the body axis of the subject P placed on the top plate 53 coincides with the central axis of the opening of the rotary frame 73. Further, the bed driving device 52 may move the top plate 53 along the body axis direction of the subject P according to the X-ray CT imaging performed using the gantry device 70. The bed driving device 52 generates power by driving at a rotational speed according to the duty ratio etc. of the drive signal from the control device 75. The bed driving device 52 is realized by, for example, a motor such as a direct drive motor or a servo motor.

[0054] The top plate 53 provided on the upper surface of the support frame 54 is a plate on which the subject P is placed. Note that the bed driving device 52 may move the support frame 54 in the longitudinal axis direction of the top plate 53 in addition to the top plate 53.

[0055] The console device 40 includes a memory 41, a display 42, an input interface 43, and a processing circuit 44. Data communication between the memory 41, the display 42, the input interface 43, and the processing circuit 44 is performed via a bus (BUS). Note that although the console device 40 is described as a separate body from the gantry device 70, the gantry device 70 may include the console device 40 or a part of each component of the console device 40.

[0056] The memory 41 is a storage device such as an HDD, SSD, or integrated circuit memory device that stores various types of information. The memory 41 stores, for example, the learned model for each imaging target site shown in the first embodiment, the projection data described later, and the reconstructed image data. In addition to HDDs, SSDs, etc., the memory 41 may also be a drive device that reads and writes various types of information to and from portable storage media such as CDs, DVDs, flash memories, and semiconductor memory elements such as RAMs. Further, the storage area of the memory 41 may be within the X-ray CT apparatus 2 or within an external storage device connected via a network. For example, the memory 41 stores data of CT images and display images. The memory 41 also stores the control program according to the present embodiment.

[0057] The display 42 displays various types of information. For example, the display 42 outputs a medical image (CT image) generated by the processing circuit 44 and a GUI (Graphical User Interface) for receiving various operations from the operator. For example, as the display 42, for example, a liquid crystal display (LCD), a CRT (Cathode Ray Tube) display, an organic EL display (OELD), a plasma display, or any other display can be appropriately used. Further, the display 42 may be provided on the gantry device 70. Also, the display 42 may be a desktop type or may be configured by a tablet terminal or the like that can communicate wirelessly with the console device 40 main body.

[0058] The input interface 43 receives various input operations from the operator, converts the received input operations into electrical signals, and outputs them to the processing circuit 44. For example, the input interface 43 receives from the operator collection conditions when collecting imaging data, reconstruction conditions when reconstructing CT images, image processing conditions when generating post-processing images from CT images, and the like. As the input interface 43, for example, a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touch pad, a touch panel display, etc. can be appropriately used. Note that in the present embodiment, the input interface 43 is not limited to one including physical operation components such as a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touch pad, and a touch panel display. For example, an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the apparatus and outputs this electrical signal to the processing circuit 44 is also included in the example of the input interface 43. The input interface 43 may be provided on the gantry device 70. Alternatively, the input interface 43 may be configured by a tablet terminal or the like that can communicate wirelessly with the console device 40 main body.

[0059] The processing circuit 44 controls the operation of the entire X-ray CT apparatus 2 according to the electrical signal of the input operation output from the input interface 43. For example, as hardware resources, the processing circuit 44 has a processor such as a CPU, an MPU, or a GPU and a memory such as a ROM or a RAM. Similar to the processing circuit 13 according to the first embodiment, the processing circuit 44 executes a system control function 441, a pre-processing function 442, an acquisition function 131, a model execution function 135, and a display control function 136 by a processor that executes a program developed in the memory. Note that each function is not limited to being realized by a single processing circuit. A processing circuit may be configured by combining a plurality of independent processors, and each function may be realized by each processor executing a program. Note that the acquisition function 131, the acquisition function 131, the model execution function 135, and the display control function 136 are not described because they perform the same operations as in the first embodiment.

[0060] The system control function 441 controls each function of the processing circuit 44 based on the input operation received from the operator via the input interface 43. Specifically, the system control function 441 reads out the control program stored in the memory 41 and expands it onto the memory in the processing circuit 44, and controls each part of the X-ray CT apparatus 2 according to the expanded control program. For example, the processing circuit 44 controls each function of the processing circuit 44 based on the input operation received from the operator via the input interface 43. For example, the system control function 441 acquires a two-dimensional positioning image of the subject P for determining the scan range, imaging conditions, etc.

[0061] The preprocessing function 442 generates data obtained by performing preprocessing such as logarithmic conversion processing, offset correction processing, sensitivity correction processing between channels, and beam hardening correction on the detection data output from the DAS 78. Note that the data before preprocessing (detection data) and the data after preprocessing are collectively referred to as projection data.

[0062] Note that the processing circuit 44 also performs scan control processing, image processing, and display control processing. The scan control processing is a process of controlling various operations related to X-ray scanning, such as supplying high voltage to the X-ray high voltage device 74 and irradiating the X-ray tube 71 with X-rays. The image processing is an image reconstruction process of converting CT image data into tomographic image data or three-dimensional image data of an arbitrary cross-section based on the input operation received from the operator via the input interface 43.

[0063] The processing circuit 44 may be included not only in the console device 40 but also in an integrated server that collectively processes data acquired by a plurality of medical image diagnostic devices. Note that although the console device 40 has been described as executing a plurality of functions with a single console, it may be configured such that a plurality of consoles execute the plurality of functions. For example, the functions of the processing circuit 44 such as the acquisition function 131 and the model execution function 135 may be distributed.

[0064] According to the second embodiment described above, by applying to the CT image taken by the X-ray CT apparatus to the learned model, a high-contrast image with higher contrast in the region of interest than the CT image can be generated.

[0065] Note that the X-ray CT apparatus 2 has various types such as Rotate / Rotate-Type (third-generation CT) in which the X-ray tube and the detector rotate around the subject P integrally, and Stationary / Rotate-Type (fourth-generation CT) in which a large number of X-ray detection elements arrayed in a ring are fixed and only the X-ray tube rotates around the subject P. Any type can be applied to this embodiment.

[0066] Furthermore, in this embodiment, it is applicable to a single-tube X-ray CT apparatus and also to a so-called multi-tube X-ray CT apparatus in which a plurality of pairs of the X-ray tube and the detector are mounted on a rotating ring.

[0067] In addition, each function according to the embodiment can also be realized by installing a program for executing the above processing in a computer such as a workstation and expanding these on the memory. At this time, the program that can cause the computer to execute the above method can also be stored and distributed in a storage medium such as a magnetic disk (such as a hard disk), an optical disk (such as a CD-ROM, DVD), or a semiconductor memory.

[0068] According to at least one embodiment described above, a medical image with improved contrast can be generated.

[0069] Although some embodiments have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, changes, and combinations of embodiments can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, as well as in the invention described in the claims and the scope equivalent thereto.

Explanation of Reference Numerals

[0070] 1 Medical information processing device 2 X-ray CT device 11, 41 Memory 13, 44 Processing circuit 15, 43 Input interface 17 Communication interface 23 Trained model 31 MR image 32 High-contrast CT image 33 Virtual CT image 40 Console device 41 Memory 42 Display 44 Processing circuit 50 Bed device 51 Base 52 Bed driving device 53 Top plate 54 Support frame 70 Gantry device 71 X-ray tube 72 X-ray detector 73 Rotating frame 74 X-ray high-voltage device 75 Control device 76 Wedge 77 Collimator 78 Data acquisition device 131 Acquisition function 132 Teacher image generation function 133 Input image generation function 134 Model learning function 135 Model execution function 136 represents the control function 441 System control function 442 Pretreatment function

Claims

1. By applying a conversion process to a first medical image having a first contrast in a region of interest, which is captured by a first medical imaging diagnostic device, a high-contrast image having a higher contrast than a second medical image obtained by a second medical imaging diagnostic device is generated. By applying an image process to the high-contrast image, an image that pseudo-reproduces the second medical image is generated, which has a second contrast lower than the first contrast in the region of interest, i.e., a pseudo-second medical image is generated. Using the pseudo-second medical image as input data and the high-contrast image as teacher data, a model is trained to generate a trained model. A medical information processing method.

2. The first medical image is an MR (Magnetic Resonance) image or a PET (Positron Emission Tomography) image, and the second medical image is a CT (Computed Tomography) image. The medical information processing method according to Claim 1.

3. The image process is a process related to noise addition and contrast reduction to the high-contrast image. The medical information processing method according to Claim 1 or Claim 2.

4. The high-contrast image and the pseudo-second medical image are images reproduced assuming a plurality of types of image reconstruction processes. The medical information processing method according to any one of Claims 1 to 3.

5. The first contrast and the second contrast are contrasts between a plurality of tissues included in the region of interest. The medical information processing method according to any one of Claims 1 to 4.

6. By applying a conversion process for converting an image obtained by a first imaging modality into an image equivalent to a second imaging modality to a first medical image obtained by the first imaging modality, a second medical image used for training a machine learning model is obtained. By applying an image process to the second medical image, a third medical image having a lower contrast than the second medical image and used for training a machine learning model is obtained. By training a machine learning model based on the second medical image and the third medical image, a trained model for improving the contrast of an image obtained by the second imaging modality is generated. A medical information processing method.

7. A first generation unit that generates a high-contrast image with higher contrast than a second medical image obtained by a second medical imaging device by applying a conversion process to a first medical image having a first contrast in a region of interest captured by a first medical imaging device; A second generation unit that generates a pseudo-second medical image, which is an image that pseudo-reproduces the second medical image and has a second contrast lower than the first contrast in the region of interest, by applying image processing to the high-contrast image; A learning unit that uses the pseudo-second medical image as input data and the high-contrast image as teacher data to train a model and generate a trained model; A medical information processing device comprising the above.

8. An acquisition unit that acquires a first medical image captured by a first medical imaging device; An execution unit that uses the medical image as input data and applies a trained model trained with an image having improved contrast in the region of interest of the medical image as teacher data to the first medical image, thereby generating a high-contrast image with higher contrast than a first contrast in the region of interest of the first medical image; Comprising: The trained model: Is generated by training a model using, as teacher data, a high-contrast image generated from a second medical image captured by a second medical imaging device having a second contrast higher than the first contrast, And using, as input data, a pseudo-second medical image, which is an image that pseudo-reproduces the first medical image by performing image processing on the high-contrast image; A medical image processing device.

9. Applying a conversion process to a first medical image having a first contrast in a region of interest captured by a first medical imaging device to generate a high-contrast image with higher contrast than a second medical image obtained by a second medical imaging device, Applying image processing to the high-contrast image to generate a pseudo-second medical image, which is an image that pseudo-reproduces the second medical image and has a second contrast lower than the high-contrast image in the region of interest, Using the pseudo-second medical image as input data and the high-contrast image as teacher data to train a model and generate a trained model; A medical information processing method.

Images