Control method and x-ray CT device

Abstract

To reduce the radiation exposure of radiation-sensitive organs.SOLUTION: A control method comprises: performing a positioning CT (Computed Tomography) scan of a 3D region of a head of a subject by controlling a CT gantry with an X-ray source and an X-ray detector both rotatably supported, so as to produce image data; detecting anatomical landmarks for identifying a tilt plane by inputting cross-sectional image data of the 3D region generated from the image data to a trained model, where the tilt surface is for avoiding irradiation of the lenses of the subject during a diagnostic CT scan; determining a tilt angle of the CT gantry based on the anatomical landmarks and the tilt plane; and performing a diagnostic CT scan of the subject by controlling the CT gantry tilted at the determined tilt angle.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The embodiments disclosed in this specification and the drawings relate to a control method and an X-ray CT apparatus.

[0002] FIELD OF THE DISCLOSURE

[0002] Embodiments described herein relate generally to X-ray Computed Tomography (CT) devices and methods, and more particularly to X-ray CT devices and methods with automatic gantry tilt for eye protection. [Background technology]

[0003] An X-ray CT scanner is a medical imaging diagnostic device that acquires projection data of a subject placed on a table from multiple angles by rotating an X-ray source at high speed relative to the subject. X-ray CT scanners generate two-dimensional and / or three-dimensional CT images by reconstructing the multiple projection data acquired from each angle.

[0004] In a scan mode called helical scan, the relative positional relationship between the X-ray source and the subject is changed while the X-ray source is continuously rotated, and projection data of the subject's entire body can be obtained in one scan. When imaging a subject using an X-ray CT device, the subject is generally placed on the table so that the subject's body axis (i.e., the direction from head to foot) is aligned with the longitudinal direction of the table (i.e., the z-axis direction of the device coordinate system described below), and the table is moved in the z-axis direction while scanning is performed.

[0005] In examinations using X-ray CT devices, a prescan (positioning CT scan) is performed to obtain projection data of a scanogram or scout image before the main scan (diagnostic CT scan) to obtain projection data of medical images for image diagnosis. A scanogram or scout image is an image obtained with a low radiation dose before the main scan in order to determine the imaging conditions of the main scan, such as the radiation dose and imaging range, and has the function of assisting in centering and positioning of the subject and selecting the anatomical target for the next CT scan.

[0006] However, traditional 2D scanograms usually only provide LR and AP radiographic views. Therefore, scanograms have limitations such as poor visualization of soft-tissue organs and suboptimal tube current modulation. Meanwhile, in recent years, ultra-low-dose 3D scanograms have shown advantages in overcoming the limitations of 2D scanograms (e.g., better soft-tissue resolution and organ-based modulation) by providing complete 3D anatomical information while maintaining a sufficiently low dose (<1 mGy).

[0007] Radiation exposure of the ocular lens during head and neck CT scans may increase the subject's risk of developing cataracts and opacities. See Nikupaavo, U. et al., Lens Dose in Routine Head CT: Comparison of Different Optimization Methods With Anthropomorphic Phantoms. AJR 2015; 204:117-123, and Mosher, E. et al., Lens Dose Reduction by Patient Posture Modification During Neck CT. AJR 2018; 210:1111-1117. Radiation exposure of the lens and radiosensitive tissues can be reduced by using technical solutions such as Organ-Based Tube Current Modulation (OBTCM), local external shielding, and optimization of the gantry tilt angle. Studies have shown that gantry tilt is an effective way to reduce direct radiation exposure of the eye's lens in CT brain scans without compromising imaging quality. See also Mussmann, B. et al., Organ-based tube current modulation in chest CT. A comparison of three vendors. Radiography 2021 Feb; 27(1):1-7. X-ray CT devices sometimes include gantry tilt capabilities in their systems to allow for reduction of direct radiation exposure of the subject's lens in routine brain scans.

[0008] Gantry tilt or subject positioning (head tilt) is part of basic CT technician training, and while tilt has been shown to help reduce dose exposure to the crystalline lens, compliance in many clinical settings has been generally low over the years. See Filice, R., Lens Identification to Prevent Radiation-Induced Cataracts Using Convolutional Neural Networks. Journal of Digital Imaging (2019) 32:644-650, and Deshpande, H. et al., Deep Learning for the Detection of Landmarks in Head CT Images and Automatic Quality Assessment. Proc. SPIE 11596, Medical Imaging 2021: Image Processing, 115960N (15 February 2021); doi: 10.1117 / 12.2581810. A retrospective study from Georgetown University Hospital found that only about 10% of head CT exams were compliant with lens protection guidance. This is probably because the positioning technique requires manual manipulation with a laser marker (and / or 2D scanogram) to exclude the crystalline lens, which can be challenging and somewhat subjective. Moreover, the adjustment process of the gantry tilt is relatively time-consuming compared to the total CT acquisition time. Also, subject movement after positioning may cause unwanted exposure of the crystalline lens.

[0009] Therefore, there is a need for a technology that automatically sets imaging conditions for automating subject positioning and gantry tilt CT head examinations so as to provide appropriate lens protection and improve throughput for all subjects. [Prior art documents] [Non-patent literature]

[0010] [Non-Patent Document 1] Nikupaavo, U. et al., Lens Dose in Routine Head CT: Comparison of Different Optimization Methods With Anthropomorphic Phantoms. AJR 2015; 204:117-123. [Non-Patent Document 2] Mosher, E. et al., Lens Dose Reduction by Patient Posture Modification During Neck CT. AJR 2018; 210:1111-1117. [Non-Patent Document 3] Mussmann, B. et al., Organ-based tube current modulation in chest CT. A comparison of three vendors. Radiography 2021 Feb; 27(1):1-7. [Non-Patent Document 4] Filice, R., Lens Identification to Prevent Radiation-Induced Cataracts Using Convolutional Neural Networks. Journal of Digital Imaging (2019) 32:644-650. [Non-Patent Document 5] Deshpande, H. et al., Deep Learning for the Detection of Landmarks in Head CT Images and Automatic Quality Assessment. Proc. SPIE 11596, Medical Imaging 2021: Image Processing, 115960N (15 February 2021); doi: 10.1117 / 12.2581810. Summary of the Invention [Problem to be solved by the invention]

[0011] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to reduce exposure of organs with high radiation sensitivity. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems. [Means for solving the problem]

[0012] A control method according to an embodiment includes controlling a CT (Computed Tomography) gantry that rotatably supports an X-ray source and an X-ray detector, performing a positioning CT scan of a three-dimensional region of a subject's head to generate image data, inputting cross-sectional image data of the three-dimensional region generated from the image data into a learned model to detect anatomical landmarks that identify a tilt plane for avoiding irradiation of the subject's crystalline lens during a diagnostic CT scan, determining a tilt angle of the CT gantry based on the anatomical landmarks and the tilt plane, and controlling the CT gantry tilted at the determined tilt angle to perform the diagnostic CT scan of the subject. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is an overall block diagram showing the configuration of an X-ray CT apparatus in the first embodiment. [Diagram 2] FIG. 2 is a schematic side view for explaining a tilt mechanism of the X-ray CT apparatus of the first embodiment. [Diagram 3] FIG. 3 is a block diagram of a processing circuit in the X-ray CT apparatus of the first embodiment. [Figure 4A] FIG. 4A is a schematic diagram showing biomarkers and tilt lines in the first to fourth embodiments of the present method. [Figure 4B]FIG. 4B is a schematic diagram showing biomarkers and tilt lines in the first to fourth embodiments of the present method. [Figure 4C] FIG. 4C shows the shift of the analyte in the first to fourth embodiments of the present method. [Figure 4D] FIG. 4D shows the shift of the analyte in the first to fourth embodiments of the present method. [Figure 5A] FIG. 5A is a flowchart according to this embodiment. [Figure 5B] FIG. 5B is a flowchart according to this embodiment. [Figure 5C] FIG. 5C is a flowchart according to this embodiment. [Figure 5D] FIG. 5D is a flow chart according to this embodiment. [Figure 6] FIG. 6 is a diagram illustrating a neural network in the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating training of a neural network in the first embodiment. [Figure 8] FIG. 8 is a flow chart of a modification of the method for controlling a CT scan according to the first embodiment. [Figure 9] FIG. 9 shows three X-ray head CT images labeled with biomarkers, tilt planes, and estimated tilt planes. [Figure 10] FIG. 10 shows the labeled tilt planes and the estimated tilt planes. [Figure 11] FIG. 11 is a diagram of the phantom used to obtain the images shown in FIGS. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] An embodiment according to the present disclosure relates to a method for controlling a computed tomography (CT) scan, including performing a scout CT scan (positioning CT scan for acquiring scanogram or scout image projection data) of a 3D region of a head of a subject to be examined using a CT gantry that rotatably supports both an X-ray source and an X-ray detector to generate image data. Cross-sectional image data of the 3D region generated from the image data is input to a trained machine learning model to detect anatomical landmarks to identify tilt planes positioned to avoid exposure to the subject's crystalline lens during a subsequent diagnostic CT scan. A tilt angle of the CT gantry is determined based on the detected anatomical landmarks. A diagnostic CT scan of the subject is performed using the tilted CT gantry at the determined tilt angle.

[0015] The scout CT scan and the diagnostic CT scan may be performed sequentially in one scanning operation. In another embodiment, performing the scout CT scan includes increasing the x-ray dose for a particular view acquisition having a particular rotational position to identify the OMBL.

[0016] The tilt plane may be defined using the subject's Orbitomeatal Base Line (OMBL) or may be defined using the subject's supraorbital ridge and opisthotonus.

[0017] Another embodiment of a method for controlling a CT scan includes performing a scout CT scan of a three-dimensional (3D) region of a subject to be examined using a CT gantry that rotatably supports both an x-ray source and an x-ray detector to generate image data. Identifying anatomical landmarks in the image data by inputting cross-sectional image data of the 3D region generated from the image data into a trained machine learning model. Determining a tilt angle of the CT gantry based on the identified anatomical landmarks, and performing a diagnostic CT scan of the subject using the CT gantry tilted at the determined tilt angle.

[0018] Yet another embodiment according to the present disclosure relates to an X-ray CT device having a gantry, an X-ray source and an X-ray detector mounted on the gantry, and a memory storing a trained model configured to detect anatomical landmarks, and including a processing circuit configured to instruct the device to perform a scout CT scan (positioning CT scan) of a three-dimensional (3D) region of a subject to be examined to generate image data, input the image data to the trained model to detect anatomical landmarks, determine a tilt angle of the CT gantry based on the detected anatomical landmarks, and perform a diagnostic CT scan of the subject using the CT gantry tilted at the determined tilt angle.

[0019] Hereinafter, the X-ray CT apparatus of each embodiment will be described with reference to the accompanying drawings.

[0020] Since the imaging range differs depending on the sex and / or body type of the subject, it is preferable to set the imaging range appropriately for each subject. A conventional method for setting imaging conditions uses various template images in which anatomical landmarks (hereinafter abbreviated as AL) stored in a database are extracted.

[0021] Each template image has an imaging range defined according to an anatomical region. Therefore, it is possible to determine the imaging range of the subject by performing coordinate transformation on the imaging range defined in the template image based on the AL extracted from the scano image and the AL of the template image.

[0022] An X-ray CT apparatus can image a subject in one of various scan modes such as a helical scan and a rotational scan. For example, a variable helical pitch scan (hereinafter referred to as a vHP scan) is known as one of the scan modes of an X-ray CT apparatus. In a vHP scan, a wide range is imaged while switching the imaging conditions for each predetermined imaging range.

[0023] When imaging the whole body with a vHP scan, an ECG-gated scan is performed in an imaging range including the heart. In an ECG-gated scan, imaging conditions are set so that projection data is acquired in a cardiac phase in which the influence of the heartbeat is small in one cycle of the heartbeat. In other words, projection data of a predetermined cardiac phase required for image reconstruction is acquired over multiple heartbeats. Thus, in an imaging range including the heart in a vHP scan, the table movement speed is set to be slower than other imaging ranges not including the heart.

[0024] If the table movement speed is slow, the subject is exposed to X-rays for a longer period, increasing the subject's X-ray exposure. However, if the table movement exceeds the width of the X-ray beam in the slice direction during one cardiac cycle, the reconstructed cardiac CT image will contain missing parts in the Z-axis direction.

[0025] For the above reasons, the inventors have devised an innovative configuration that automatically sets the imaging range as narrow as possible within a range that maintains satisfactory image quality from the diagnostic point of view. With this configuration, it is possible to reduce the total radiation dose in the entire imaging by minimizing the imaging range exposed to a large dose of X-rays under conditions that maintain satisfactory image quality for the acquired CT images.

[0026] Hereinafter, an embodiment of an X-ray CT apparatus having a configuration for setting the imaging range by the above method will be described.

[0027] (First embodiment) 1 is an overall block diagram showing the configuration of an X-ray CT apparatus 1 in the first embodiment. The X-ray CT apparatus 1 shown in FIG.

[0028] The scanner 11 is installed in an examination room and acquires projection data of a subject P. The console 12 is installed in an operation room (control room) adjacent to the examination room and generates a CT image by reconstructing the projection data input from the scanner 11.

[0029] The scanner 11 includes a rotating body 25, a table driving device 31, a high-voltage power supply 41, an aperture driving device 42, a rotation driving device 43, a tilt controller 44, a scan controller 45, and a communication device 46. For example, the communication device 46 may be a speaker / microphone for communicating with the subject.

[0030] The rotating body 25 is a frame (i.e., a housing) configured to rotatably support the X-ray tube 21, the X-ray detector 23, and a cooler (not shown) described below, and is fixed to the base 27 by a fixed base (not shown). Under the control of the scan controller 45, the rotation drive device 43 rotates the rotating body 25 about a rotation axis parallel to the z-axis of the apparatus coordinate system.

[0031] As an example, the x-axis, y-axis, and z-axis of the apparatus coordinate system are defined as follows: the vertical direction is defined as the y-axis direction, the z-axis direction is defined as a direction perpendicular to the y-axis and parallel to the horizontal movement direction of the table (i.e., the longitudinal direction), and the x-axis direction is defined as a direction perpendicular to both the y-axis and the z-axis. In this embodiment, unless otherwise specified, it is assumed that the subject P is placed on the table so that the body axis direction coincides with the z-axis direction.

[0032] The rotating body 25 and the fixed base are tilted in the z-axis direction of the device coordinate system by a tilt mechanism 26 provided between the fixed base and base 27. The tilt mechanism 26 is equipped with a tilt bearing (not shown). The rotating body 25 and the fixed base rotate together around the tilt bearing. Under the control of the scan controller 45, the tilt mechanism 26 tilts the rotating body 25 in accordance with a control signal input from the tilt controller 44. The tilt operation of the rotating body 25 will be described in detail below with reference to FIG. 2.

[0033] The rotating body 25 includes an opening. The table driving device 31 moves the table 30 on which the subject P is placed into the opening of the rotating body 25 during imaging, and moves the table 30 to the outside of the opening after imaging is completed. Here, as an example, the negative direction of the z axis is defined as the movement direction of the table 30 from the outside of the opening to the inside of the opening. In other words, the positive direction of the z axis is defined as the movement direction of the table 30 from the inside of the opening to the outside of the opening. The support base 32 is installed on the floor surface so as to support the table 30.

[0034] The table driving device 31 includes a table moving motor and a table moving mechanism (not shown). Under the control of the scan controller 45, the table driving device 31 moves the table 30 up and down along the y-axis direction and moves the table 30 horizontally in the z-axis direction.

[0035] The table moving mechanism is, for example, a rack and pinion mechanism. The table 30 moves along a rack meshing with a pinion (gear) by the rotational force of the pinion generated by a table moving motor. Furthermore, the table driving device 31 includes a stepping motor (not shown), and transmits position control information such as the current position of the table 30 detected by the stepping motor and the amount of movement of the table 30 to the scan controller 45.

[0036] The rotating body 25 includes an X-ray tube 21 , an X-ray optical system 22 , an X-ray detector 23 , and a data acquisition system (DAS) 24 .

[0037] The X-ray tube 21 generates an electron beam from its cathode in response to a tube voltage supplied from a high-voltage power supply 41, and generates X-rays by colliding the electron beam with a metal target (i.e., its anode). The X-rays generated by the X-ray tube 21 are emitted toward the X-ray detector 23. Under the control of a scan controller 45, the X-ray tube 21 is supplied with power required for X-ray emission.

[0038] Under the control of the scan controller 45, the X-ray optical system 22 controls the irradiation range of the X-rays irradiated to the subject P based on a control signal from the aperture driving device 42. The X-ray optical system 22 includes various control devices configured to control irradiation conditions such as the dose, irradiation range, shape, and radiation quality of the X-ray beam. Specifically, the X-ray optical system 22 includes, for example, a wedge filter and a collimator. The wedge filter is a convex lens-shaped filter made of a lightweight metal such as aluminum, and adjusts the dose of the X-rays generated by the X-ray tube 21. The collimator is a slit for narrowing down the irradiation range of the X-rays, and the dose of the X-rays is controlled and adjusted by the wedge filter.

[0039] As an example of the X-ray detector 23, the X-ray detector 23 may be a two-dimensional array type detector in which a large number of detection elements are arranged in a matrix along the X-axis direction (i.e., the channel direction) and the slice direction. The X-ray detector 23 detects X-rays emitted from the X-ray tube 21. The slice direction is perpendicular to the channel direction. Here, as an example, the slice direction is the rotation axis direction of the rotor 25, and coincides with the Z-axis direction when the rotor 25 is not tilted, that is, when the tilt angle described below is 0 degrees. Furthermore, the channel direction coincides with the X-axis direction regardless of the tilt state of the rotor 25.

[0040] The two-dimensional array detector is also called a multi-slice detector. When the X-ray detector 23 is a multi-slice detector, it is possible to scan a three-dimensional area having a width in the slice direction by rotating the rotor 25 360 degrees or 180+α degrees. A three-dimensional scanogram or scout image can be obtained using the two-dimensional array detector.

[0041] The DAS 24 includes an amplifier and an A / D (analog / digital) converter (not shown), amplifies the signal of the transmission data of X-rays detected by each detection element of the X-ray detector 23, and converts the amplified transmission data into a digital signal. The DAS 24 transmits projection data generated based on the transmission data detected by the X-ray detector 23 to the scan controller 45 via a data transfer device (not shown).

[0042] The console 12 of the X-ray CT apparatus 1 is configured based on a computer and can communicate with external devices via a network such as a LAN (Local Area Network). The console 12 is configured with hardware such as a processing circuit 51, a memory 52, an input interface 53, and a display 55.

[0043] The processing circuit 51 is connected to each of the hardware components constituting the console 12 via a bus serving as a transmission path for common signals. Note that the console 12 may include a memory media drive in some cases.

[0044] The processing circuit 51 may be configured as dedicated hardware, or may be configured to realize various functions by software processing of a built-in processor. Here, as an example, a case where the processing circuit 51 realizes various functions by software processing of the processor will be described.

[0045] The above-mentioned term "processor" refers to circuits such as a dedicated or general-purpose CPU, a dedicated or general-purpose GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device, and a Field Programmable Gate Array (FPGA). Examples of the above-mentioned programmable logic device include a Simple Programmable Logic Device (SPLD) and a Complex Programmable Logic Device (CPLD). The processing circuit 51 realizes various functions by reading a program stored in the memory 52 and executing the program. Additionally or alternatively, the processing circuit 51 realizes various functions by reading a program stored in its own processor and executing the program.

[0046] Furthermore, the processing circuit 51 may be composed of a single processor, or may be composed of a combination of multiple processors independent of each other. In the latter case, multiple memories 52 corresponding to the respective processors may be provided, and the programs executed by each processor may be stored in the memories 52 corresponding to the processors. As a further modification, one memory 52 may collectively store all the programs corresponding to the respective functions of the multiple processors. The memory 52 is a storage medium including an external storage device such as an HDD (Hard Disk Drive) and an optical disk device in addition to a RAM (Random Access Memory) and a ROM (Read Only Memory). The memory 52 stores image data, data required for executing the programs, and various programs (including application programs and an operating system) executed by the processing circuit 51. Furthermore, the memory 52 can store a program for controlling the operating system. Furthermore, the memory 52 may store a program of a GUI (Graphical User Interface) that supports input from an input interface 53.

[0047] The input interface 53 is composed of input devices such as a keyboard, a mouse, a joystick, and a trackball. The input interface 53 accepts input from a user via the input devices. When at least one input device is operated by an operator, the input interface 53 generates an input signal according to the operation and outputs the input signal to the processing circuit 51.

[0048] The display 55 is a display device such as a liquid crystal display panel, a plasma display panel, an organic EL (Electro Luminescence) panel, etc. Under the control of the processing circuitry 51, the display 55 displays imaging conditions and images such as a scanogram.

[0049] FIG. 2 is a schematic side view of the X-ray CT device 1 of the first embodiment for explaining the tilt mechanism. FIG. 2 is a side view of the scanner 11 viewed from the x-axis direction with the rotor 25 tilted. The dashed-dotted line L1 in FIG. 2 is a straight line that is parallel to the y-axis and passes through the center of the tilt mechanism 26. The dashed-dotted line L2 is a straight line on the yz plane and passes through the center of the tilt mechanism 26. The tilt angle θ is defined as the angle between the dashed-dotted line L1 and the dashed-dotted line L2.

[0050] 2, the case where the rotating body 25 tilts in the negative direction along the z axis (i.e., tilting backward) has been described, but in some cases, the rotating body 25 can also tilt in the positive direction along the z axis (i.e., tilting forward). When tilting backward is defined as the positive tilt direction and tilting forward is defined as the negative tilt direction, the rotating body 25 is tilted in the positive tilt direction or negative tilt direction within a predetermined angle range so that the reference angle position of the rotating body 25 is a tilt angle of 0 degrees where the dashed dotted line L2 and the dashed dotted line L1 coincide with each other.

[0051] The details of the processing circuit 51 are shown in FIG. 3. The processing circuit 51 includes a scan controller function 60, an image reconstruction function 61, a deep convolutional neural network (DCNN) 62, and a tilt plane generation function 63. Each of these functions may be a program stored in a memory and executed by a processor, or may be hardwired to the processor. The scan controller function 60 is an example of a generation unit and a control unit. The DCNN 62 is an example of a detection unit and an example of a learned model (a trained machine learning model). The tilt plane generation function 63 is an example of a determination unit.

[0052] The DCNN 62, described in more detail below, extracts and outputs points ((x,y,z) coordinates) in the 3D scanogram volume that correspond to the desired biomarkers. The DCNN 62 may also output scan lines or planes. In one embodiment, the centers of the supraorbital ridges of the left and right eyes and the centers of the ear canals are extracted and denoted P1-P3, respectively. The three points P1-P3 define the desired scan plane. The supraorbital ridge points P1-P2 may be determined using the mean or center of the orbit. Other points such as the inner plate of the posterior edge of the foramen magnum, or the opisthoton of the occipital bone (OO) may be extracted to define the scan plane. In another embodiment, if the subject has implants or has had head surgery, the location or area of ​​the implants or surgery may be used as biomarkers if irradiation of these locations needs to be avoided during diagnostic scanning.

[0053] FIG. 4A and FIG. 4B show, as an example, biomarkers, tilt planes, and tilt lines. FIG. 4A is a frontal skull view in which the supraorbital ridge points P1-P2 are identified. The line L3 between the points is in the scan plane. The OMBL is shown in FIG. 4B as a tilt line L4 defined by one of the supraorbital ridge points P1-P2 and point P3 of the ear canal. The tilt plane is defined by three points P1-P3 (or two lines L3-L4). Line L5 shows the tilt plane defined by points P1-P2 and a point corresponding to the opisthotonus (OO) of the occipital bone. Either plane can be used to determine the angle of the tilt plane.

[0054] FIG. 5A is a flowchart showing a method according to the first embodiment. In the X-ray CT apparatus 1, a subject is placed and positioned in the scanner 11 (step 70), and a 3D scanogram is obtained (step 71). The processing circuit 51 inputs the 3D scanogram into the DCNN 62 to detect biomarkers from the 3D scanogram (step 72). In the case of head CT, the points defined as the opisthoton of the occipital bone, the external auditory canal, and the centers of the supraorbital ridges of the left and right eyes can be biomarkers. See also, for example, American Association of Physicists in Medicine, Adult routine head CT protocols version 2.0 (2016). To avoid or reduce exposure of the eye's lens, the scan angle can be parallel to a line made by the infraorbital ridge and the inner plate of the posterior edge of the foramen magnum. In one embodiment, the supraorbital ridge and the center of the external auditory canal are used to identify the orbitomeatal base line (OMBL).

[0055] The processing circuitry 51 executes a tilt plane generation function 63 to generate a tilt plane from the biomarker-derived coordinates of the scanogram. The orientation of the tilt plane relative to the mechanical axis is determined by the tilt plane generation function 63. The scan controller function 60 generates instructions to the scan controller 45 to control the tilt controller 44 to move the gantry to an appropriate angle, and, if necessary, to the table drive device 31 to position the subject in an appropriate position, to perform a CT scan at the determined gantry tilt angle and table position to obtain a desired head image while minimizing exposure of the crystalline lens. The gantry tilt angle is preferably determined from a plane defined by the biomarkers, as described above.

[0056] Returning to FIG. 5A, a tilt plane is generated by the processing circuitry in step 73 using the detected biomarkers. The processing circuitry instructs the tilt controller 44 to tilt the gantry in step 74. The processing circuitry can also move the subject, if necessary, in step 75 by sending instructions to the table drive device 31 to position the subject in the appropriate position in the z-direction. A diagnostic CT scan of the subject is then performed in step 75. The scout CT scan and diagnostic CT scan can be part of one overall scanning operation to improve workflow and ensure that safety protocols for lens protection are followed.

[0057] It is also clear that the angles of the lines L3 and L4 may change due to the positioning and post-positioning movement of the subject. In the line L3, if the subject's head is displaced to the left or right from the desired position, the determined scan plane may expose one of the lenses to radiation during the diagnostic scan. This is because the gantry is only configured to tilt about an axis in the x direction (see FIG. 2). The gantry in FIG. 2 is not configured to tilt about an axis in the yz plane. In a second embodiment shown in FIG. 5B, the X-ray CT device 1 includes a capability to correct the positioning of the subject.

[0058] FIG. 4C illustrates a head shift and includes an exposure line EL based on the subject's position. In the figure, the subject is exposed above EL. Processing circuitry 51 can determine EL from the subject's positioning and machine geometry. With the amount of shift illustrated in FIG. 4C, the subject's right lens may be exposed.

[0059] Steps 70-74 are the same as the method of FIG. 5A. After step 74, a check for head tilt is performed in step 77A. In one embodiment, the angle of line L3 in the xz plane with respect to the x-axis, as determined by DCNN 62, is compared to a desired range by processing circuitry 51. If the angle of line L3 is greater than a determined number of degrees from the y-axis, a warning or alert is provided to the operator on display 55 in step 77B. In another embodiment, processing circuitry 51 can determine a distance orthogonal to EL between P1 or P2 and EL. If this distance is equal to or greater than a threshold, such as a few mm, a warning or alert is again provided. FIG. 4D illustrates a shift of the head as the subject moves from a desired chin-up position, including an exposure line EL based on the subject's position. In the figure, the subject is exposed above EL. Processing circuitry 51 can determine EL from the subject's positioning and the geometry of the machine. With the amount of shift shown in FIG. 4D, the subject's crystalline lens may be exposed. By ascertaining the angle between L4 and L5, or by determining the distance between P2 and EL perpendicular to EL, a warning or alarm can be given in a manner similar to that described above in FIG. 4C.

[0060] The operator can communicate with the subject using the communication device 46 (speaker / microphone) to reposition the subject in step 77C. If the operator desires, another 3D scanogram can be taken in step 77D to ensure the subject is in the proper position. This process can be repeated as necessary. If necessary, the subject can be moved to the proper z-position in step 75 and a diagnostic scan is performed as in the first embodiment in step 76.

[0061] 5C and 5D show third and fourth embodiments of the method according to the present disclosure. In these embodiments, the gantry is fixed at the L1 position and does not tilt. For the method of FIG. 5C, the subject is positioned in step 70, typically with the chin tucked, to place the head at a desired angle so that the crystalline lens is not irradiated. Steps 71 and 72 described above are performed. Using the biomarkers, the processing circuitry 51 determines the appropriate z-position, if necessary, in step 75, and the subject is scanned in step 76. The method shown in FIG. 5D is similar to the method of FIG. 5B, except that steps 73 and 74 are omitted as in the third embodiment.

[0062] FIG. 6 shows an example of DCNN62. Other neural network structures are also possible. A multi-layer network is a network in which multiple layers are arranged so that only adjacent layers are connected, and information propagates in one direction from the input layer side to the output layer side. In FIG. 6, DCNN62 has an input layer (I=1), inner layers I=2 to I=L-1, and an output layer I=L. Other configurations are also possible. Scano image data is expressed as x1 to x N The input data is fed to the units in the input layer, represented as I = L. The data is processed in the inner layers and an output is generated in the output layer I = L. Each layer is given appropriate weights and biases to detect the biomarkers.

[0063] The weights and biases are determined by the training process shown in Figure 7. The training process of DCNN is designed to map the training inputs X to the desired targets Y, as shown in the figure above. This training process can be described as solving the following optimization problem:

[0064]

number

[0065] where Θ is the set of parameters of the neural network to be optimized, N is the total number of training instances in the training process, f is the neural network to be optimized, x i is the i-th element of the training input, y i is the i-th element of the training target. By solving this optimization problem, we find the optimal network parameters Θ such that the difference Δ between the network output and the target biomarker Y (e.g., it can be MAE (Mean Absolute Error), MSE (Mean Squared Error), GDL (Generalized Dice Loss), Dice loss, cross entropy, etc.) is minimized. * can be sought.

[0066] In FIG. 7, a 3D scanogram 80 is input to a DCNN 81, and a biomarker 82 is generated as the output of the DCNN 81. Target biomarkers 83 (such as the supraorbital ridge and the center of the ear canal) are prepared and input to a loss function 84 to obtain the difference between the generated target biomarker and the ground truth target biomarker. An optimizer 85 adjusts the weights and biases of the DCNN 81 to adjust Θ so that the difference between the output biomarker and the target biomarker is minimized. We collected a training group consisting of 48 manually labeled brain CT scans to obtain the coordinates of three landmarks: the opisthotonus (OO) of the occipital bone and a point defined as the approximate center of the supraorbital ridge of the left and right eyes (LE and RE). A test group consisting of 12 brain CT and 8 real 3D scanogram datasets also had the coordinates manually labeled as the ground truth. The images were preprocessed by downscaling (x4) and bone thresholding (HU 300-1900 was set as 1, other features were set as 0). The results are shown in Figure 9. The left, middle, and right views show the biomarker points determined by DCNN for LE, OO, and RE, respectively. The horizontal lines at the bottom of each view are the mechanical axes and the resulting tilt angles (θ) of the planes shown for reference. The estimated tilt planes are shown as dashed lines, and the labeled tilt planes are shown as solid lines. Table 1 below shows the pixel data results for 12 sets of brain CT data with dFOV=240mm or 320mm, pitch 0.5mm. The estimated biomarker points and tilt planes match well with the manually labeled points and planes with good accuracy.

[0067] [Table 1]

[0068] We also performed tests using 3D scanogram data. We used 8 datasets with dFOV=500mm and 1mm pitch. The image data was downsampled (2x) with cropped images of 256x256 pixels. The results are shown in Fig. 10 for LE, OO and RE. The estimated tilt planes are shown in dashed lines and the labelled tilt planes in solid lines. Again, the predicted tilt planes match well with the planes of manually labelled points. Table 2 below shows the results for pixel data.

[0069] [Table 2]

[0070] The results in Tables 1 and 2 and Figures 9 and 10 show that the device can accurately estimate the tilt plane (and tilt angle) for safely performing diagnostic head CT scans to avoid unnecessary exposure to the crystalline lens.

[0071] The images shown in FIGS. 9 and 10 were obtained using the phantom shown in FIG.

[0072] (Modification) In a variation of the embodiment, two modes of 3D scout scanning are used. In the first mode, the OMBL (or another line) is not detected and a scout scan is performed at the normal 3D scanogram dose. The mode is switched to the second mode at a higher scanogram dose to detect the OMBL. As a second modification, in a particular view acquisition during the 3D scanogram operation, the dose is increased at a particular rotational position during the 3D scan for the detection of the OMBL. This is shown in FIG. 8.

[0073] The method and system according to the present disclosure has the advantage of an automated gantry tilt workflow, which will accelerate the overall subject throughput compared to time-consuming manual tilt. It is envisioned that the method and system will ensure the application of a phaco-protective gantry tilt protocol and reduce the risk of human error for estimating the tilt angle. Compared to the conventional gantry tilt approach, the proposed method and system according to the present disclosure does not change the current workflow and does not require additional CT scans for positioning and gantry tilt angle calculation, since the 3D scout scan and diagnostic scan are performed seamlessly.

[0074] According to at least one of the embodiments described above, it is possible to reduce exposure of organs that are highly sensitive to radiation.

[0075] Although some embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents as described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0076] 1 X-ray CT device 11 Scanner 60 Scan Controller Function 61 Image reconstruction function 62 DCNN 63 Tilt surface generation function

Claims

1. Controlling a CT (Computed Tomography) gantry that rotatably supports an X-ray source and an X-ray detector, and performing a positioning CT scan of a three-dimensional region of the subject's head to generate image data; inputting cross-sectional image data of the three-dimensional region generated from the image data into a trained model to detect anatomical landmarks that identify tilt planes to avoid irradiation of the subject's crystalline lens during a diagnostic CT scan; determining a tilt angle of the CT gantry based on the anatomical landmarks and the tilt plane; controlling the CT gantry tilted at the determined tilt angle to perform the diagnostic CT scan of the subject; A control method comprising:

2. The method of claim 1 , wherein the positioning CT scan and the diagnostic CT scan are performed consecutively in a single scanning operation.

3. The control method according to claim 1 , wherein the positioning CT scan is performed with increasing X-ray doses of specific views having specific rotational positions to identify the tilt plane.

4. The control method according to claim 1 , wherein the tilt plane is determined based on an orbitomeatal line of the subject.

5. The control method according to claim 1 , wherein the determination of the tilt plane includes determining the tilt plane based on the supraorbital ridge and opisthotonus of the subject.

6. The method of claim 1 , further comprising determining a position of the subject's head based on the anatomical landmarks.

7. determining a position of the subject on a movable table relative to the CT gantry with respect to a scan plane of the tilted CT gantry; moving the subject so that a desired scan plane through the subject's head coincides with the scan plane of the tilted CT gantry; The control method of claim 1 , further comprising:

8. Determine the tilt plane line passing through the supraorbital ridges of the left and right eyes, determining whether the angle of the line is within a set angle relative to one of the mechanical axes of the CT gantry; generating a signal indicating that the angle of the line is not within the set angle; The control method of claim 1 , further comprising:

9. Controlling a CT gantry that rotatably supports an X-ray source and an X-ray detector, and performing a positioning CT scan of a three-dimensional region of the subject to generate image data; Identifying anatomical landmarks in the image data by inputting the image data into a trained model; determining a tilt angle of the CT gantry based on the anatomical landmarks; controlling the CT gantry tilted at the tilt angle to perform a diagnostic CT scan of the subject; A control method comprising:

10. The control method of claim 9 , wherein the positioning CT scan and the diagnostic CT scan are performed consecutively in a single scanning operation.

11. generating anatomical lines based on the anatomical landmarks; determining the tilt angle based on the anatomical line; tilting the CT gantry based on the tilt angle; The control method of claim 9 , comprising:

12. The method of claim 11 , wherein the anatomical line is the orbitomeatal line.

13. The positioning CT scan includes: a first scan configured for a scan plan that involves detection of the orbitomeatal line or a second scan configured for a scan plan that does not involve detection of the orbitomeatal line; the first scan is performed at a higher x-ray dose than the second scan; The control method according to claim 9.

14. a CT gantry that rotatably supports an X-ray source and an X-ray detector; A generating unit that performs a positioning CT scan of a three-dimensional region of a subject to generate image data; A detection unit that detects anatomical landmarks by inputting the image data to a trained model; a determination unit that determines a tilt angle of the CT gantry based on the anatomical landmark; a control unit that controls the CT gantry tilted at the tilt angle to perform a diagnostic CT scan of the subject; An X-ray CT apparatus comprising:

15. The generation unit executes, as the positioning CT scan, a first scan configured for a scan plan including detection of an orbital ear canal line, or a second scan configured for a scan plan not including detection of the orbital ear canal line; the first scan is performed at a higher x-ray dose than the second scan; The X-ray CT apparatus according to claim 14.

16. The X-ray CT apparatus according to claim 14 , wherein the positioning CT scan and the diagnostic CT scan are performed consecutively in a single scanning operation.

17. The determination unit generates an anatomical line based on the anatomical landmark, and determines the tilt angle based on the generated anatomical line; The control unit tilts the CT gantry based on the tilt angle. The X-ray CT apparatus according to claim 14.

18. The X-ray CT apparatus according to claim 14 , wherein the determination unit determines the tilt angle based on an orbitomeatal line of the subject.

19. The X-ray CT apparatus according to claim 14 , wherein the determination unit determines the tilt angle based on a supraorbital ridge and an opisthoton of the subject.

Images