Medical image generation device, medical image generation method, and program

Abstract

To reduce the radiation exposure of the subject. [Solution] The medical image generation apparatus of the embodiment comprises an acquisition unit and a generation unit. The acquisition unit acquires first image data of a subject in a first posture and direction information relating to a second pair of subject directions in which gravity acts on the subject in the first posture is different from the first pair of subject directions relative to the subject in the first posture. The generation unit generates estimated image data that is estimated to have been taken of the subject based on the first image data and the direction information.

Description

Technical Field

[0001] The embodiments disclosed in this specification and the drawings relate to a medical image generation device, a medical image generation method, and a program.

Background Art

[0002] Conventionally, as X-ray CT devices, there are a general X-ray CT device for imaging a subject in a supine position and a standing X-ray CT device for imaging a subject in a standing position, which generate supine X-ray images and standing X-ray images, respectively. Physicians, for example, perform examinations while looking at either the supine X-ray image or the standing X-ray image depending on the position of the organ or lesion of interest.

[0003] Since the supine X-ray image and the standing X-ray image are generated by an X-ray CT device and a standing X-ray CT device, respectively, for example, when preparing the supine X-ray image and the standing X-ray image, the subject will be exposed to radiation each time it is imaged by the X-ray CT device and the standing X-ray CT device. Therefore, the radiation exposure of the subject tends to increase.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] The problem to be solved by the embodiments disclosed in this specification and the drawings is to reduce the radiation exposure of the subject. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problems. It is also possible to position the problems corresponding to the respective effects of each configuration shown in the embodiments described later as other problems.

Means for Solving the Problems

[0006] The medical image generation apparatus of the embodiment comprises an acquisition unit and a generation unit. The acquisition unit acquires first image data of a subject in a first posture and direction information relating to a second pair of subject directions in which gravity acts on the subject in the first posture is different from the first pair of subject directions relative to the subject in the first posture. The generation unit generates estimated image data that is estimated to have been taken of the subject, based on the first image data and the direction information. [Brief explanation of the drawing]

[0007] [Figure 1] A diagram showing an example of the configuration of a hospital system 1 including a medical image generation device 100 of the embodiment. [Figure 2] A diagram showing an example of a medical image generation device 100. [Figure 3] A diagram showing an example of the contents of the training data DB151. [Figure 4] A diagram illustrating the process of generating training data. [Figure 5] A flowchart showing an example of processing in the medical image generation device 100. [Figure 6] A diagram showing an example of an X-ray CT apparatus 200 according to the second embodiment. [Figure 7] A diagram illustrating the processing flow as the first modified example. [Figure 8] A diagram illustrating the processing flow in the second modified example. [Figure 9] A diagram illustrating the processing flow in the third modified example. [Figure 10] A diagram illustrating the processing flow in the fourth modified example. [Figure 11] A diagram illustrating the processing flow in the fifth modified example. [Modes for carrying out the invention]

[0008] The following describes the embodiment of the medical image generation apparatus, medical image generation method, and program with reference to the drawings.

[0009] (First embodiment) Figure 1 shows an example of the configuration of a hospital system 1 including a medical image generation device 100 of the embodiment. The hospital system 1 of the embodiment includes, for example, a Hospital Information System (HIS) 10, a Radiology Information System (RIS) 20, a medical image diagnostic device (modality) 30, a Picture Archiving and Communication System (PACS) 40, and a medical image generation device 100. The HIS 10, RIS 20, modality 30, and PACS 40 can communicate with each other via a network NW.

[0010] HIS10 is a computer system that provides operational support within hospitals. Specifically, HIS10 has various subsystems. These subsystems include, for example, an electronic medical record system, a medical accounting system, an appointment scheduling system, a patient registration system, and an admission / discharge management system.

[0011] HIS10 includes, for example, computers such as server devices and client terminals equipped with a processor such as a CPU (Central Processing Unit), memory such as ROM (Read Only Memory) and RAM (Random Access Memory), a display, an input interface, and a communication interface.

[0012] The user uses the electronic medical record system included in HIS10 to input and retrieve patient information. The user issues imaging examination orders to HIS10. HIS10 then transfers the order information corresponding to the imaging examination order to other systems such as RIS20 and the medical image generation device 100.

[0013] RIS20 is a computer system that provides business support in the imaging diagnosis department. In addition to reservation management of imaging examination orders in cooperation with HIS10, RIS20 also performs reservation information linkage to examination equipment and management of examination information. RIS20 includes computers such as server devices and client terminals that have a processor such as a CPU, memories such as ROM and RAM, a display, an input interface, and a communication interface.

[0014] Modality 30 executes imaging (shooting) according to shooting conditions (shooting protocols) determined based on, for example, imaging examination instructions. Examples of Modality 30 include an X-ray computed tomography (X-ray CT) device, an X-ray diagnostic device, a magnetic resonance imaging device, an ultrasonic diagnostic device, a nuclear medicine diagnostic device, etc. Medical images include, for example, radiation images, magnetic resonance images, and ultrasonic images. Modality 30 is operated by an operator such as a doctor (radiologist) or a radiological technologist. The medical images (image data) generated by the imaging of Modality 30 are transmitted to PACS40. Medical images include planar images and three-dimensional images (volume images). In an embodiment, as Modality 30, for example, an X-ray CT device and a standing X-ray CT device are used.

[0015] PACS40 is a computer system that receives medical images transmitted by Modality 30 etc. and stores them in a database. PACS40 transmits (transfers) the medical images stored in the database in response to a request from a client. PACS40 includes a server computer that includes a processor such as a CPU, memories such as ROM and RAM, a display, an input interface, and a communication interface.

[0016] FIG. 2 is a configuration diagram showing an example of the medical image generation device 100. The medical image generation device 100 includes, for example, a communication interface 110, an input interface 120, a display 130, a processing circuit 140, and a memory 150. The communication interface 110 communicates with external devices such as HIS 10, RIS 20, modality 30, PACS 40, etc. via a network NW such as a LAN (Local Area Network). The communication interface 110 includes, for example, a communication interface such as a NIC (Network Interface Card).

[0017] The input interface 120 receives various input operations from a user such as a doctor, converts the received input operations into electrical signals, and outputs them to the processing circuit 140. The input interface 120 generates, for example, information corresponding to the input operation when an input operation is performed by the user. The input interface 120 outputs the generated information corresponding to the input operation to the processing circuit 140.

[0018] The information corresponding to the input operation includes, for example, an estimated image generation instruction, a gravity-free image generation instruction, and a posture designation instruction. The estimated image generation instruction is an instruction for causing the medical image generation device 100 to generate an estimated image (estimated image data) by converting a captured image (captured image data) captured in the first posture into an estimated image captured in the second posture. The user may want to view a medical image when the subject P captured in the first posture is captured in the second posture for reasons such as the need for diagnosis. In this case, the user inputs an estimated image generation instruction to cause the medical image generation device 100 to generate an estimated image.

[0019] The gravity-free image generation instruction is an instruction for causing the medical image generation device 100 to generate a gravity-free image. The user may want to view medical images when the subject P is captured in a plurality of different second postures. In this case, first, a gravity-free image in which the influence of gravity is excluded is generated from the captured image, and an estimated image is generated in the medical image generation device 100 by designating the direction with respect to the subject, which is the direction with respect to the subject, in the gravity-free image.

[0020] The posture specification instruction is an instruction that specifies the second posture of the subject P in the estimated image. Users may want to see an estimated image in which gravity acts in a specific direction relative to the subject. In this case, the user inputs a posture estimation instruction that specifies a specific direction relative to the subject, causing the medical image generation device 100 to generate an estimated image. The posture specification instruction may be, for example, an instruction that specifies the posture of the subject, such as standing, lying down (supine, prone, or lateral).

[0021] When an estimated image generation instruction, a zero-gravity image generation instruction, and a posture specification instruction are input to the input interface 120, it generates estimated image generation information, zero-gravity image generation information, and posture specification information, respectively, and outputs them to the processing circuit 140. The posture specification information includes directional information regarding the direction to the subject when the posture specified by the posture specification instruction (second posture) is in place.

[0022] The input interface 120 includes, for example, a mouse, keyboard, trackball, switch, button, joystick, touch panel, etc. The input interface 120 may also be a user interface that accepts audio input, such as a microphone. The input interface 120 may also have a display function as a display 130, such as a touch panel.

[0023] In this specification, the term "input interface" is not limited to those equipped with physical operating components such as a mouse or keyboard. For example, an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device located separately from the device and outputs this electrical signal to a control circuit is also included as an example of an input interface.

[0024] The display 130 is a display unit that displays various types of information. For example, the display 130 displays images generated by the processing circuit 140, or a GUI (Graphical User Interface) for receiving various input operations from the user. For example, the display 130 may be an LCD (Liquid Crystal Display), a CRT (Cathode Ray Tube) display, or an organic EL (Electro Luminescence) display.

[0025] The processing circuit 140 includes, for example, an acquisition function 141 and a generation function 142. The acquisition function 141 includes, for example, an imaging information acquisition function 161 and a training data reading function 162. The generation function 142 includes, for example, a zero-gravity image generation function 171, a gravity direction transformation function 172, and an estimated image generation function 173. The processing circuit 140 realizes these functions, for example, by a hardware processor (computer) executing a program stored in memory 150.

[0026] Hardware processors refer to circuits such as CPUs, GPUs (Graphics Processing Units), Application Specific Integrated Circuits (ASICs), programmable logic devices (e.g., Simple Programmable Logic Devices (SPLDs) or Complex Programmable Logic Devices (CPLDs)), and Field Programmable Gate Arrays (FPGAs).

[0027] Instead of storing the program in memory 150, the system may be configured to directly incorporate the program into the hardware processor's circuitry. In this case, the hardware processor performs its function by reading and executing the program incorporated into the circuitry. The program may be stored in memory 150 beforehand, or it may be stored on a non-temporary storage medium such as a DVD or CD-ROM, and installed from the non-temporary storage medium to memory 150 when the non-temporary storage medium is mounted on the drive device (not shown) of the medical image generation device 100.

[0028] A hardware processor is not limited to being a single circuit; it may also be composed of multiple independent circuits combined to perform various functions. Alternatively, multiple components may be integrated into a single hardware processor to perform various functions.

[0029] Memory 150 can be implemented by semiconductor memory elements such as RAM and flash memory, hard disks, and optical discs. These non-transient storage media may also be implemented by other storage devices connected via a communication network, such as NAS (Network Attached Storage) or external storage server devices. Memory 150 may also include non-transient storage media such as ROM (Read Only Memory) and registers.

[0030] Memory 150 stores the training data database (hereinafter referred to as DB) 151. The training data DB 151 is a database containing multiple training data. The training data is, for example, data generated by training using a large number of sample images obtained by imaging subject P or other subjects in the past, such as AI (Artificial Intelligence) training.

[0031] The sample images include, for example, first and second image data previously acquired by modality 30, particularly an X-ray CT scanner. The first image data is image data of a subject in a first posture, and the second image data is image data of a subject in a second posture different from the first posture. The sample images may also be multiple images of a single subject taken at different times, multiple images of multiple subjects taken at the same or different times, or multiple images including these.

[0032] Figure 3 shows an example of the contents of the training data DB151. The training data DB151 stores, for example, the first to twelfth training data. The first to twelfth training data are data that converts the medical image before conversion (hereinafter referred to as the pre-conversion medical image) to the medical image after conversion (hereinafter referred to as the post-conversion medical image). In the following explanation, the dimensions of the CT image (2D or 3D) will be indicated in parentheses. For example, a 3D CT image will be written as a CT (3D) image.

[0033] For example, the first training data is data that converts standing general X-ray (2D) images to supine CT (3D) images. The second training data is data that converts supine CT (3D) images to standing general X-ray (2D) images. The third training data is data that converts standing general X-ray (2D) images to supine high-resolution (3D) CT images. The fourth training data is data that converts supine high-resolution (3D) CT images to standing general X-ray (2D) images.

[0034] High-resolution (3D) supine CT images are images with higher resolution than supine (3D) CT images. The third and fourth training data are data used to generate estimated images so that the level of detail (resolution) of the displayed medical image is higher or lower depending on the posture of the subject.

[0035] The fifth training data set is data that converts standing general X-ray (2D) images to standing CT (3D) images. The sixth training data set is data that converts standing CT (3D) images to standing general X-ray (2D) images. The seventh training data set is data that converts supine CT (3D) images to supine high-resolution (3D) CT images. The eighth training data set is data that converts supine high-resolution (3D) CT images to supine CT (3D) images.

[0036] The supine position includes the supine position where the subject lies on their back, the prone position where the subject lies face down, and the lateral position where the subject faces sideways. The supine CT high-resolution (3D) images and supine CT (3D) images in the 7th and 8th training data sets are data acquired from subjects in different supine positions (hereinafter referred to as heterosupine positions).

[0037] The 9th training data is data that converts supine (3D) CT images to upright (3D) CT images. The 10th training data is data that converts upright (3D) CT images to supine (3D) CT images. The 11th training data is data that converts supine high-resolution (3D) CT images to upright (3D) CT images. The 12th training data is data that converts upright (3D) CT images to supine high-resolution (3D) CT images.

[0038] Standing general X-ray (2D) images are 2D images generated by imaging a standing subject with a standing X-ray CT scanner. Supine CT (3D) images are 3D images generated by imaging a supine subject with an X-ray CT scanner. Supine high-resolution (3D) CT images are 3D images generated by imaging a supine subject with an X-ray CT scanner and then performing high-resolution processing (high-density processing). These are 3D images generated by imaging a standing subject with a standing X-ray CT scanner.

[0039] The first to twelfth training data sets all contain information about the posture of subject P when the subject P was imaged, such as standing and lying down (supine, prone, and lateral). The information about the posture of subject P included in the first to twelfth training data sets, for example, information about posture such as standing and lying down, is an example of directional information related to the direction relative to the subject.

[0040] Figure 4 illustrates the process of generating training data. For example, the first and second training data are generated by inputting standing general X-ray (2D) images and supine CT (3D) images as sample images into the AI ​​training device. The third and fourth training data are generated by inputting standing general X-ray (2D) images and supine high-resolution CT (3D) images as sample images into the AI ​​training device.

[0041] The fifth and sixth training data are generated by inputting standing general X-ray (2D) images and standing CT (3D) images as sample images into the AI ​​training device. The seventh and eighth training data are generated by inputting supine CT (3D) images and supine high-resolution CT (3D) images as sample images into the AI ​​training device.

[0042] The 9th and 10th training data are generated by inputting supine (3D) CT images and standing (3D) CT images as sample images into the AI ​​training device. The 11th and 12th training data are generated by inputting supine high-resolution (3D) CT images and standing (3D) CT images as sample images into the AI ​​training device.

[0043] The acquisition function 141 in the processing circuit 140 acquires, by means of the imaging information acquisition function 161, a first image (first image data) of a subject in a first posture and directional information relating to a second subject direction in which gravity acts on the subject in the first posture is different from the first subject direction relative to the subject in the first posture. The first posture includes, for example, standing and lying down (supine, prone, and lateral). The first image data includes, for example, standing CT (3D) images and lying down CT (3D) images.

[0044] The acquisition function 141 further acquires imaging-related image data, such as training data, related to the second image (second image data) captured of a subject in a second posture different from the first posture, using the training data reading function 162. The second posture includes, for example, standing and lying down (supine, prone, lateral), and is, for example, the lying down posture when the first posture is standing. The imaging-related image data is, for example, training data used when converting the first image to the second image. The training data reading function 162 reads and acquires training data from among multiple training data contained in the training data DB 151 stored in the memory 150. The acquisition function 141 is an example of an acquisition unit.

[0045] The generation function 142 generates estimated image data, which is estimated to be of a subject, based on the first captured image data and orientation information. The generation function 142 generates estimated image data, which is estimated to be of a subject in a second orientation, where the gravitational force acting on the subject is in the second direction relative to the subject. The generation function 142 is an example of a generation unit.

[0046] In generating estimated image data, the generation function 142 generates, for example, zero-gravity image data by using the zero-gravity image generation function 171 to capture subject P in a zero-gravity state where gravity acting on subject P is removed, based on the first captured image data acquired by the imaging information acquisition function 161. The zero-gravity image generation function 171 estimates the gravity acting on various parts of subject P, such as organs, in the first captured image data.

[0047] The zero-gravity image generation function 171 generates zero-gravity image data by identifying the shape of each part of subject P after removing the estimated gravity from each part of subject P contained in the first captured image data. The zero-gravity image generation function 171 is an example of a zero-gravity image generation unit. The zero-gravity image generation function 171 may also generate zero-gravity image data by inputting the first captured image data of subject P to a trained model that has been trained using the first captured image data before gravity removal and the zero-gravity image data as training data.

[0048] The generation function 142 uses the gravity direction conversion function 172 to convert the direction of gravity acting on the subject in the first image data. The gravity direction conversion function 172, for example, converts and sets the direction of gravity acting on the subject when the first image data was acquired to a direction based on the posture specification instruction specified as estimated image data.

[0049] The gravity direction conversion function 172 converts and sets the direction of gravity acting on subject P by adding a direction based on direction information acquired by the imaging information acquisition function 161 as the direction of gravity acting on subject P in the zero-gravity image generated by the zero-gravity image generation function 171. The gravity direction conversion function 172 is an example of a gravity direction conversion unit. The generation function 142 may also be configured to convert and set the direction of gravity acting on subject P in the gravity direction conversion function 172 without generating a zero-gravity image by the zero-gravity image generation function 171.

[0050] The estimated image generation function 173 generates an estimated image from the zero-gravity image data generated by the zero-gravity image generation function 171, by capturing an image of subject P in a direction relative to the subject, which is set by the gravity direction conversion function 172.

[0051] Next, the processing in the medical image generation device 100 will be described. Figure 5 is a flowchart showing an example of the processing in the medical image generation device 100. The flowchart shown in Figure 5 starts, for example, when the user inputs an estimated image generation instruction into the input interface 120, and the input interface 120 outputs the estimated image generation information to the processing circuit 140. When the user inputs a specified image generation instruction, they also input a posture specification instruction and, if necessary, a zero-gravity image generation instruction.

[0052] The medical image generation device 100, having received estimated image generation information, first acquires captured images of the subject P using the imaging information acquisition function 161 in the acquisition function 141 (step S101). The imaging information acquisition function 161 acquires captured images transmitted by modality 30 or PACS 40. The imaging information acquisition function 161 stores the acquired captured images (hereinafter referred to as acquired images) in memory 150. Memory 150 may store, for example, multiple acquired images of the subject P taken in the past. Among the multiple acquired images, there may be images in which the subject P was photographed in a different posture than the posture of the subject P when the captured images were taken.

[0053] Next, the zero-gravity image generation function 171 determines whether or not it has acquired zero-gravity image generation information output by the input interface 120 (step S103). If it determines that it has acquired zero-gravity image generation information, the zero-gravity image generation function 171 generates a zero-gravity image based on the captured image (step S105). The zero-gravity image generation function 171 stores the generated zero-gravity image in the memory 150. If it determines that it has not acquired a zero-gravity image generation instruction, the zero-gravity image generation function 171 skips the process in step S105 and proceeds to step S107.

[0054] Next, the imaging information acquisition function 161 acquires attitude specification information output by the input interface 120 (step S107), and acquires direction information included in the acquired attitude specification information. Subsequently, the gravity direction conversion function 172 determines whether or not a weightless image has been generated by the weightless image generation function 171 (step S109).

[0055] If it is determined that a weightless image has been generated, the gravity direction conversion function 172 sets the direction of gravity acting on the subject P to the direction corresponding to the direction information obtained by the imaging information acquisition function 161. The direction corresponding to the direction information is, for example, the direction from the abdomen to the back of the subject P if the subject P is in a supine position, and the direction from the head to the legs of the subject P if the subject P is in an upright position.

[0056] Next, the estimated image generation function 173 generates an estimated image based on the weightless image generated by the weightless image generation function 171 and the direction corresponding to the direction information set by the gravity direction conversion function 172 (step S111). Subsequently, the estimated image generation function 173 displays the generated estimated image on the display 130 (step S113). In this way, the medical image generation device 100 completes the process shown in Figure 5.

[0057] Suppose in step S109 it is determined that no zero-gravity image has been generated. In this case, the gravity direction conversion function 172 determines whether or not it can generate an estimated image based on the acquired images stored in memory 150 (step S115). If it is determined that an estimated image can be generated based on the acquired images, the gravity direction conversion function 172 sets the direction of gravity acting on subject P to the direction corresponding to the direction information acquired by the imaging information acquisition function 161.

[0058] The estimated image generation function 173 reads an acquired image from the memory 150 that is oriented according to the gravity acting on the subject P, based on the gravity direction conversion function 172 (step S117). Next, the estimated image generation function 173 generates an estimated image based on the acquired image obtained by the imaging information acquisition function 161 and the acquired image read from the memory 150 (step S119). Next, the estimated image generation function 173 displays the generated estimated image on the display 130 (step S113). In this way, the medical image generation device 100 completes the process shown in Figure 5.

[0059] Suppose in step S115 it is determined that an estimated image cannot be generated based on the acquired image. In this case, the training data reading function 162 identifies and reads training data for generating an estimated image from the training data DB 151 in memory 150 based on the directional information contained in the captured image and the directional information acquired by the imaging information acquisition function 161 (step S121). For example, if the directional information contained in the captured image is supine and the directional information acquired by the imaging information acquisition function 161 is standing, the training data reading function 162 reads the ninth training data from the training data DB 151.

[0060] Next, the estimated image generation function 173 generates an estimated image based on the captured image acquired by the imaging information acquisition function 161 and the training data read out by the training data readout function 162 (step S123). Subsequently, the estimated image generation function 173 displays the generated estimated image on the display 130 (step S113). In this way, the medical image generation device 100 completes the process shown in Figure 5.

[0061] The medical image generation device 100 of the first embodiment generates estimated images of subject P in different postures from captured images of subject P. Therefore, for example, if a doctor or other professional wants to see images of subject P in a different posture after capturing images of subject P, it is not necessary to capture new images of subject P in a different posture. Consequently, the radiation exposure of subject P can be reduced.

[0062] Furthermore, the medical image generation device 100 of the first embodiment generates a weightless image by removing the gravity acting on the subject from the captured image, and generates estimated images of the subject P in different postures based on the weightless image. In this case, since the weightless image is generated in advance, the computational load on the medical image generation device when generating the estimated images can be reduced.

[0063] (Second embodiment) Next, a second embodiment will be described. In the first embodiment, the medical image generation device 100 is provided independently of the modality 30, but functions equivalent to those of the medical image generation device 100 may be installed in the modality 30, for example, an X-ray CT scanner or an upright X-ray CT scanner.

[0064] In the second embodiment, an example in which the X-ray CT apparatus is equipped with functions equivalent to those of the medical image generation apparatus 100 will be described. Figure 6 is a configuration diagram showing an example of the X-ray CT apparatus 200 of the second embodiment. The X-ray CT apparatus 200 includes, for example, a pedestal 210, a patient bed 230, and a console 240.

[0065] In Figure 6, for explanatory purposes, both a view of the frame device 210 from the Z-axis direction and a view from the X-axis direction are shown, but in reality, there is only one frame device 210. In the first embodiment, the rotation axis of the rotating frame 217 in the non-tilted state or the longitudinal direction of the top plate 233 of the bed device 230 is defined as the Z-axis direction, the axis perpendicular to the Z-axis direction and horizontal to the floor surface is defined as the X-axis direction, and the direction perpendicular to the Z-axis direction and perpendicular to the floor surface is defined as the Y-axis direction.

[0066] The rigging device 210 includes, for example, an X-ray tube 211, a wedge 212, a collimator 213, an X-ray high-voltage device 214, an X-ray detector 215, a data acquisition system (hereinafter referred to as DAS) 216, a rotating frame 217, and a control device 218.

[0067] The X-ray tube 211 generates X-rays by irradiating thermionic electrons from the cathode (filament) to the anode (target) when a high voltage is applied from the X-ray high-voltage device 214. The X-ray tube 211 includes a vacuum tube. For example, the X-ray tube 211 is a rotating anode type X-ray tube that generates X-rays by irradiating a rotating anode with thermionic electrons.

[0068] The wedge 212 is a filter used to adjust the amount of X-rays irradiated from the X-ray tube 211 onto the subject P being imaged. The wedge 212 attenuates the X-rays that pass through it so that the distribution of the X-ray dose irradiated from the X-ray tube 211 onto the subject P becomes a predetermined distribution. The wedge 212 is also called a wedge filter or bow-tie filter. The wedge 212 is made, for example, from aluminum that has been processed to have a predetermined target angle and thickness.

[0069] The collimator 213 is a mechanism for narrowing the irradiation area of ​​X-rays that have passed through the wedge 212. The collimator 213 narrows the irradiation area of ​​X-rays by forming a slit, for example, by combining multiple lead plates. The collimator 213 is sometimes called an X-ray diaphragm. The narrowing range of the collimator 213 may be mechanically driveable.

[0070] The X-ray high-voltage device 214 includes, for example, a high-voltage generator and an X-ray control device. The high-voltage generator has an electrical circuit including a transformer and a rectifier, and generates a high voltage to be applied to the X-ray tube 211. The X-ray control device controls the output voltage of the high-voltage generator according to the amount of X-rays to be generated in the X-ray tube 211. The high-voltage generator may perform voltage boosting using the transformer described above, or it may perform voltage boosting using an inverter. The X-ray high-voltage device 214 may be installed on the rotating frame 217, or it may be installed on the side of the fixed frame (not shown) of the mounting device 210.

[0071] The X-ray detector 215 detects the intensity of X-rays generated by the X-ray tube 211 and incident after passing through the subject P. The X-ray detector 215 outputs an electrical signal (or optical signal, etc.) corresponding to the detected X-ray intensity to the DAS 216. The X-ray detector 215 has, for example, multiple rows of X-ray detection elements. Each of the multiple rows of X-ray detection elements has multiple X-ray detection elements arranged in the channel direction along an arc centered on the focal point of the X-ray tube 211. The multiple rows of X-ray detection elements are arranged in the slice direction (row direction).

[0072] The X-ray detector 215 is an indirect type detector having, for example, a grid, a scintillator array, and a photosensor array. The scintillator array has multiple scintillators. Each scintillator has a scintillator crystal. The scintillator crystal emits light in an amount corresponding to the intensity of the incident X-rays.

[0073] The grid is positioned on the X-ray incident surface of the scintillator array and has an X-ray shielding plate that absorbs scattered X-rays. The grid is sometimes called a collimator (one-dimensional collimator or two-dimensional collimator). The optical sensor array has optical sensors such as photomultipliers (PMTs). The optical sensor array outputs an electrical signal corresponding to the amount of light emitted by the scintillator. The X-ray detector 215 may be a direct conversion type detector having a semiconductor element that converts incident X-rays into an electrical signal.

[0074] The DAS216 includes, for example, an amplifier, an integrator, and an A / D converter. The amplifier amplifies the electrical signals output by each X-ray detection element of the X-ray detector 215. The integrator integrates the amplified electrical signals over the viewing period. The A / D converter converts the electrical signals showing the integration result into a digital signal. The DAS216 outputs detection data based on the digital signal to the console device 240.

[0075] The rotating frame 217 is an annular member that supports the X-ray tube 211, wedge 212, and collimator 213 opposite the X-ray detector 215. The rotating frame 217 is an annular member having two circular sides with a circular opening in the center, an inner surface connecting the inner circles of the two sides, and an outer surface connecting the outer circles of the two sides. The two sides of the rotating frame 217 are flat, while the inner and outer surfaces are curved.

[0076] The rotating frame 217 is supported by a fixed frame (not shown) so as to be rotatable around the subject P introduced inside. The rotating frame 217 further supports the DAS 216. Detection data output by the DAS 216 is transmitted by optical communication from a transmitter having a light-emitting diode (LED) provided on the rotating frame 217 to a receiver having a photodiode provided on the non-rotating part (e.g., the fixed frame) of the mounting device 210, and is then transferred by the receiver to the console device 240. Note that the method of transmitting detection data from the rotating frame 217 to the non-rotating part is not limited to the optical communication method described above, but any non-contact transmission method may be used. The rotating frame 217 is not limited to an annular member, but may be an arm-like member, as long as it can support and rotate the X-ray tube 211 or the like.

[0077] The X-ray CT scanner 200 is, for example, a Rotate / Rotate-Type X-ray CT scanner (third-generation CT) in which both the X-ray tube 211 and the X-ray detector 215 are supported by a rotating frame 217 and rotate around the subject P. However, it is not limited to this, and may also be a Stationary / Rotate-Type X-ray CT scanner (fourth-generation CT) in which a plurality of X-ray detection elements arranged in a ring shape are fixed to a fixed frame and the X-ray tube 211 rotates around the subject P.

[0078] The control device 218 includes, for example, a processing circuit having a processor such as a CPU (Central Processing Unit), and a drive mechanism including a motor and an actuator. The processing circuit realizes these functions, for example, by having a hardware processor execute a program stored in a memory device (storage circuit).

[0079] The control device 218 can, for example, rotate the rotating frame 217, tilt the base of the rigging device 210, move the top plate 233 of the patient bed device 230 up and down, or emit (expose) X-rays from the X-ray tube 211. The control device 218 may be installed on the rigging device 210 or on the console device 240.

[0080] The bed device 230 is a device that places the subject P to be scanned onto, moves it, and introduces it into the rotating frame 217 of the stand device 210. The bed device 230 comprises, for example, a base 231, a bed vertical movement device 232, and a top plate 233. The base 231 includes a housing that supports the support frame on which the subject P is placed so as to be movable in the vertical direction (Y-axis direction). The top plate 233 is an example of a bed.

[0081] The console device 240 includes, for example, a memory 241, a display 242, an input interface 243, and a processing circuit 250. In the first embodiment, the console device 240 is described separately from the mounting device 210, but the mounting device 210 may include some or all of the components of the console device 240.

[0082] Memory 241 can be implemented using, for example, semiconductor memory elements such as RAM (Random Access Memory) or flash memory, a hard disk, or an optical disc. Memory 241 stores, for example, detection data, projection data, reconstructed image data, and CT image data. This data may be stored not in memory 241 (or in addition to memory 241) but in an external memory that the X-ray CT apparatus 200 can communicate with. The external memory is controlled by a cloud server that manages the external memory, for example, by accepting read and write requests from the cloud server.

[0083] Memory 241 stores, for example, the training data DB 151 stored in the memory 150 of the medical image generation device 100 in the first embodiment. Memory 241 may also store a training data DB containing fewer training data than the training data included in the training data DB 151 shown in Figure 3. In this case, the training data DB may include, for example, the second training data, the seventh training data, and the ninth training data, which are training data related to supine CT (3D). If the X-ray CT device 200 is capable of high-resolution processing, it may further include the fourth training data, the eighth training data, and the eleventh training data.

[0084] The display 242 displays various types of information. For example, the display 242 displays medical images (CT images) generated by the processing circuit 250, or GUI (Graphical User Interface) images that accept various operations from operators such as doctors and technicians. The display 242 can be, for example, a liquid crystal display, a CRT (Cathode Ray Tube), or an organic EL (Electroluminescence) display. The display 242 may be mounted on the stand device 210. The display 242 may be a desktop type, or it may be a display device (for example, a tablet terminal) that can communicate wirelessly with the main unit of the console device 240.

[0085] The input interface 243 receives various input operations from the operator and outputs an electrical signal indicating the content of the received input operation to the processing circuit 250.

[0086] The processing circuit 250 controls the overall operation of the X-ray CT apparatus 200. The processing circuit 250 includes, for example, a control function 251, a preprocessing function 252, a reconstruction processing function 253, an image processing function 254, an image generation function 255, and a display control function 256. The processing circuit 250 realizes these functions, for example, by having a hardware processor execute a program stored in a memory device (storage circuit).

[0087] Each component of the console device 240 or the processing circuit 250 may be distributed and implemented by multiple hardware components. The processing circuit 250 may not be implemented in the same configuration as the console device 240, but rather by a processing unit that can communicate with the console device 240. The processing unit may be, for example, a workstation connected to one X-ray CT scanner, or a device (e.g., a cloud server) connected to multiple X-ray CT scanners that performs processing equivalent to that of the processing circuit 250 described below in a batch. Each function included in the processing circuit 250 may be distributed across multiple circuits, or it may be made available by launching application software stored in memory 241.

[0088] The control function 251 controls various functions of the processing circuit 250 based on input operations received by the input interface 243. For example, the control function 251 controls the X-ray high-voltage device 214, DAS 216, control device 218, and bed vertical movement device 232 to perform data collection processing of detection data in the support structure 210.

[0089] The preprocessing function 252 performs preprocessing on the detection data output by the DAS216, such as logarithmic transformation, offset correction, inter-channel sensitivity correction, and beam hardening correction, to generate projection data, and stores the generated projection data in the memory 241.

[0090] The reconstruction processing function 253 performs reconstruction processing on the projection data generated by the preprocessing function 252, such as a filtered back projection method or an iterative reconstruction method, to generate reconstructed image data for generating CT image data, and stores the generated reconstructed image data in the memory 241.

[0091] The image processing function 254 generates medical image data such as three-dimensional data and cross-sectional image data by converting the reconstructed image data into three-dimensional image data or cross-sectional image data of an arbitrary cross-section using a known method, based on the input operation received by the input interface 243. The conversion to three-dimensional image data may be performed by the preprocessing function 252.

[0092] The image generation function 255 has the same functions as the acquisition function 141 and generation function 142 provided in the processing circuit 140 of the medical image generation device 100 described in the first embodiment. The image generation function 255 acquires the medical image data generated by the image processing function 254 as captured image data. Similar to the first embodiment, the image generation function 255 generates a zero-gravity image, stores and uses acquired images, and reads and uses training data stored in the memory 241 to generate an estimated image.

[0093] The display control function 256 displays the medical image data generated by the image processing function 254 and the estimated image generated by the image generation function 255 on the display 242. The display control function 256 indicates that the estimated image generated by the image generation function 255 may be, for example, an upright image, or a supine image in which the posture of the subject is different from that of the medical image data generated by the image generation function 255.

[0094] The X-ray CT scanner 200 of the second embodiment provides the same effects and advantages as the medical image generation device 100 of the first embodiment. Furthermore, in the X-ray CT scanner 200 of the second embodiment, users such as doctors can view medical images of a standing subject P while imaging a supine subject P. Therefore, efficiency can be increased when performing tasks while viewing the X-ray CT scanner 200.

[0095] As an example of imaging a subject in a first posture and displaying an estimated medical image of the subject in a second posture, in addition to the example shown in the second embodiment in which an X-ray CT scanner 200 images a subject in a supine position and displays a medical image of a subject in an upright position, other forms of processing are also possible. These examples are described below as modified versions. In the following description, an X-ray CT scanner that images a subject in a supine position will be referred to as a supine CT scanner, and an X-ray CT scanner that images a subject in an upright position will be referred to as an upright CT scanner.

[0096] (First variation) Figure 7 is a diagram illustrating the processing flow as a first modified example. In the first modified example, the supine CT scanner or the upright CT scanner is equipped with functions equivalent to, for example, the acquisition function 141 and the generation function 142 provided in the processing circuit 140 of the medical image generation device 100 of the first embodiment.

[0097] In the first modification, a subject is imaged using a supine or upright CT scanner to obtain a supine CT image (3D) or upright CT image (3D) of the subject in a supine or upright position. Then, a weightless state image is generated based on the acquired image. The supine or upright CT scanner changes the subject's posture in the generated weightless state image (changes the direction relative to the subject) and generates an upright CT image (3D) or supine CT image (3D) as an estimated image. The supine or upright CT scanner displays the generated estimated image on a display.

[0098] In the first modified example, a supine CT scanner or an upright CT scanner can display estimated images of a standing subject or an estimated image of a supine subject, respectively. In this process, the subject is exposed to radiation only once, when acquiring the supine CT image (3D) or the upright CT image (3D), and the estimated images, the upright CT image (3D) or supine CT image (3D), can be generated without any radiation exposure to the subject. Therefore, the subject's radiation exposure can be reduced.

[0099] (Second variation) Figure 8 is a diagram illustrating the processing flow in the second modified example. In the second modified example, the supine CT scanner is equipped with functions equivalent to, for example, the acquisition function 141 and the generation function 142 provided in the processing circuit 140 of the medical image generation device 100 in the first embodiment. In the second modified example, as a function equivalent to the generation function 142, the supine CT scanner is equipped with a function that generates a medical image (estimated image) of a standing subject based on medical images (acquired images) of multiple subjects in different supine positions.

[0100] In the second modification, the supine CT scanner generates supine CT images (3D), prone CT images (3D), and lateral CT images (3D) of the subject in different supine positions, for example, supine, prone, and lateral. Based on the supine CT images (3D), prone CT images (3D), and lateral CT images (3D), the supine CT scanner acquires image generation information for generating upright CT images (3D) based on the supine organ position information, prone organ position information, and lateral organ position information obtained from the supine CT images (3D), prone CT images (3D), and lateral CT images (3D).

[0101] The supine organ position information is information about the position of each point of organs, such as the lungs and stomach, in a subject in a supine position. The prone organ position information is information about the position of each point of organs in a subject in a prone position. The lateral organ position information is information about the position of each point of organs in a subject in a lateral position. The supine CT scanner generates an estimated upright CT image (3D) based on the supine CT image (3D), prone CT image (3D), and lateral CT image (3D) organ position information in the supine, prone, and lateral positions. The supine CT scanner displays the generated upright CT image (3D) on a display.

[0102] In the second modification, a supine CT scanner can display an estimated image of a standing subject. In this process, the subject is exposed to radiation only when acquiring supine CT images (3D), prone CT images (3D), and lateral CT images (3D), while the estimated standing CT image (3D) can be generated without any radiation exposure to the subject. Therefore, the subject's radiation exposure can be reduced.

[0103] (Third variation) Figure 9 is a diagram illustrating the processing flow in the third modified example. In the third modified example, the supine CT scanner is equipped with functions equivalent to, for example, the acquisition function 141 and the generation function 142 provided in the processing circuit 140 of the medical image generation device 100 in the first embodiment. In the third modified example, as a function equivalent to the generation function 142, the supine CT scanner is equipped with a function that generates a medical image (estimated image) of a standing subject based on a supine CT image (3D) and the 9th training data.

[0104] In the third modification, the subject is imaged using a supine CT scanner to acquire a supine CT image (3D), and the ninth training data is read and acquired from memory 241. The generation function 142 generates an upright CT image (3D) as an estimated image of the upright subject based on the acquired supine CT image (3D) and the ninth training data. The supine CT scanner displays the generated upright CT image (3D) on the display.

[0105] In the third modification, a supine CT scanner can display an estimated image of a standing subject. In this process, the subject is exposed to radiation only once when the supine CT image (3D) is acquired, and the estimated standing CT image (3D) can be generated without any radiation exposure to the subject. Therefore, the subject's radiation exposure can be reduced.

[0106] (Fourth variation) Figure 10 is a diagram illustrating the processing flow in the fourth modified example. In the fourth modified example, the standing CT scanner includes functions equivalent to, for example, the acquisition function 141 and the generation function 142 provided in the processing circuit 140 of the medical image generation device 100 in the first embodiment. In the fourth modified example, as a function equivalent to the generation function 142, the standing CT scanner includes a function that generates a medical image (estimated image) of a supine subject based on a standing CT image (3D) and the 10th training data.

[0107] In the fourth modification, the subject is imaged using a standing CT scanner to acquire a standing CT image (3D), and the 10th training data is read and acquired from memory 241. The generation function 142 generates a supine CT image (3D) as an estimated image of the subject in a supine position based on the acquired standing CT image (3D) and the 10th training data. The standing CT scanner displays the generated supine CT image (3D) on a display.

[0108] In the fourth modification, an estimated image of a supine subject can be displayed on an upright CT scanner. In this process, the subject is exposed to radiation only once when the upright CT image (3D) is acquired, and the supine CT image (3D) which serves as the estimated image can be generated without any radiation exposure to the subject. Therefore, the subject's radiation exposure can be reduced.

[0109] (Fifth variation) Figure 11 is a diagram illustrating the processing flow in the fifth modified example. In the fifth modified example, the supine CT scanner is equipped with functions equivalent to, for example, the acquisition function 141 and the generation function 142 provided in the processing circuit 140 of the medical image generation device 100 in the first embodiment. In the fifth modified example, as a function equivalent to the generation function 142, the supine CT scanner is equipped with a function that generates a medical image (estimated image) of a standing subject based on a supine CT image (3D) and the fifth training data.

[0110] In the fifth modification, the subject is imaged using a supine CT scanner to acquire a supine CT image (3D), and the fifth training data is read from memory 241 and acquired. The generation function 142 generates an upright CT image (3D) as an estimated image of the upright subject based on the acquired supine CT image (3D) and the fifth training data. The supine CT scanner displays the generated upright CT image (3D) on the display.

[0111] In the fifth modification, a supine CT scanner can display an estimated image of a standing subject. In this process, the subject is exposed to radiation only once when the supine CT image (3D) is acquired, and the estimated standing CT image (3D) can be generated without any radiation exposure to the subject. Therefore, the subject's radiation exposure can be reduced.

[0112] (Other variations) In the embodiments and modifications described above, the captured images do not involve a temporal element, but the captured images may include a temporal element. For example, the CT scanner may continuously image the subject for a certain period of time, for example, between 5 seconds and 5 minutes. In such captured images with a temporal element, for example, a zero-gravity image may be generated, and a transformed image may be generated based on the zero-gravity image, or an estimated image may be generated from the captured image.

[0113] According to at least one embodiment described above, the medical information processing device includes an acquisition unit that acquires first image data of a subject in a first posture and direction information relating to a second pair of subject directions in which gravity acts on the subject in the first posture is different from the first pair of subject directions relative to the subject in the first posture, and a generation unit that generates estimated image data estimated to be of the subject based on the first image data and the direction information, thereby reducing the exposure of the subject to radiation.

[0114] While several embodiments have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0115] 1. Hospital Systems 30 Medical imaging equipment (modalities) 100 Medical Image Generation Devices 110 Communication Interface 120 Input Interfaces 130 displays 140 Processing Circuits 141 Acquisition function 142 Generation function 150 Storage section 150 memory 151 Training Data Database 161 Image Information Acquisition Function 162 Training Data Retrieval Function 171. Zero-gravity image generation function 172 Gravity Direction Change Function 173 Estimated Image Generation Function 200 X-ray CT device 210 Mounting device 211 X-ray tube 212 Wedge 213 Collimator 214 X-ray high-voltage equipment 215 X-ray detector 216 DAS 217 rotation frames 218 Control device 230 Bed equipment 231 Base 232 Bed elevation / lowering device 233 Top plate 240 Console Device 241 memory 242 displays 243 Input Interfaces 250 processing circuits 251 Control Functions 252 Preprocessing Functions 253 Reconstruction Processing Function 254 Image Processing Functions 255 Image generation function 256 Display control function NW Network P Subject

Claims

1. An acquisition unit that acquires first image data of a subject in a first posture and direction information relating to a second pair of subject directions in which gravity acts on the subject in the first posture is different from the first pair of subject directions relative to the subject in the first posture, The system comprises a generation unit that generates estimated image data estimated to be of the subject, based on the first image data and the direction information, Medical image generation device.

2. The acquisition unit further acquires imaging-related image data relating to the second imaging image data obtained by imaging the subject in a second posture different from the first posture, The generation unit generates estimated image data which is estimated to be an image of the subject in a second posture in which gravity acting on the subject is in the second direction relative to the subject. A medical image generation apparatus according to claim 1.

3. The generation unit includes a zero-gravity image generation unit that generates zero-gravity image data of the subject in the first posture, based on the first captured image data, in a zero-gravity state where gravity acting on the subject is removed. A medical image generation apparatus according to claim 1.

4. The generation unit further includes a gravity direction conversion unit that converts the direction of gravity acting on the subject when the first image data is captured to the direction of gravity acting on the subject in the estimated image data. A medical image generation apparatus according to claim 1.

5. The generation unit converts the first image data into a state in which gravity acting on the subject is removed when the first image data is captured, and in the zero-gravity image data in which gravity acting on the subject is removed. The system further includes a gravity direction conversion unit that converts the state in the zero-gravity image data where gravity acting on the subject is removed to a state in which gravity acts on the subject in a direction different from the direction in which gravity acts on the subject in the estimated image data. The medical image generation apparatus according to claim 3.

6. One of the positions, lying down or standing, is the first posture, and the other is the second posture. The medical image generation apparatus according to claim 2.

7. The first and second postures are, respectively, supine, prone, or lateral. The medical image generation apparatus according to claim 2.

8. The aforementioned imaging-related image data includes training data generated by learning training using the first imaging image data and the second imaging image data. The medical image generation apparatus according to claim 2.

9. The generation unit generates estimated image data with a resolution different from the resolution of the first captured image data. The medical image generation apparatus according to claim 1.

10. Computers First image data obtained by capturing a subject in a first posture and direction information relating to a second pair of subject directions in which the direction in which gravity acts on the subject in the first posture is different from the first pair of subject directions relative to the subject in the first posture are acquired. Based on the first image data and the orientation information, estimated image data is generated that is estimated to be of the subject being imaged. Medical image generation method.

11. On the computer, First image data obtained by capturing a subject in a first posture and direction information relating to a second pair of subject directions in which the direction in which gravity acts on the subject in the first posture is different from the first pair of subject directions relative to the subject in the first posture are acquired. Based on the first image data and the orientation information, the system generates estimated image data that is estimated to be of the subject. program.

Images