阅读说明：本技术 磁共振成像装置、方法以及存储介质 (Magnetic resonance imaging apparatus, method and storage medium ) 是由 宝珠山裕 松永奈美 京谷勉辅 于 2021-05-12 设计创作，主要内容包括：实施方式的磁共振成像装置具备线圈和处理器,该线圈接收由于高频磁场的影响而从被检体发出的磁共振信号。处理器从与包含被检体的前列腺在内的范围对应并基于磁共振信号的定位用的磁共振图像中,检测出被检体的股骨头、骨盆、关节唇、耻骨结合、尿道以及前列腺尖部中的至少一个组织。处理器基于检测出的组织,决定被检体的前列腺的诊断用的磁共振图像的摄像中的摄像对象区域。(The magnetic resonance imaging apparatus of an embodiment includes a coil that receives a magnetic resonance signal emitted from a subject due to the influence of a high-frequency magnetic field, and a processor. The processor detects at least one tissue of a femoral head, a pelvis, an articular lip, a pubic junction, a urethra, and a prostatic apex of a subject from a magnetic resonance image for localization based on a magnetic resonance signal corresponding to a range including a prostate of the subject. The processor determines an imaging target region in imaging a magnetic resonance image for diagnosing a prostate of a subject based on the detected tissue.)

1. A magnetic resonance imaging apparatus includes:

a detection unit that detects at least one tissue of a femoral head, a pelvis, an articular lip, a pubic junction, a urethra, and a prostatic apical portion of a subject from a magnetic resonance image for positioning obtained by imaging a range including a prostate of the subject; and

and a determination unit configured to determine an imaging target region in imaging a magnetic resonance image for diagnosis of a prostate of the subject based on the detected tissue.

2. The magnetic resonance imaging apparatus according to claim 1,

the diagnostic magnetic resonance image is a two-dimensional magnetic resonance image,

the determination unit determines at least one of a slice direction, a slice center, a slice width, and a rotation amount in an in-plane direction of an imaging cross section in imaging the two-dimensional magnetic resonance image.

3. The magnetic resonance imaging apparatus according to claim 2,

the two-dimensional magnetic resonance image comprises an axial image,

the detection unit detects 2 femoral heads of the subject from the magnetic resonance image for positioning,

the determination unit determines a direction perpendicular to a line segment passing through the upper end portion of each of the 2 femoral heads as a slice direction in imaging of the axial image.

4. The magnetic resonance imaging apparatus according to claim 3,

the detection unit further detects pubic symphysis of the subject from the magnetic resonance image for localization,

the determination unit determines a slice width in imaging of the axial image based on the positions of the 2 femoral heads and the position of pubic junction.

5. The magnetic resonance imaging apparatus according to claim 3 or 4,

the detection unit further detects a plurality of articular lips of the subject from the magnetic resonance image for positioning,

the determination unit determines a rotation amount in the in-plane direction in the imaging of the axial image based on the plurality of joint lips.

6. The magnetic resonance imaging apparatus according to any one of claims 2 to 5,

the two-dimensional magnetic resonance image comprises a sagittal image,

the detection unit detects a plurality of articular lips of the subject from the magnetic resonance image for positioning,

the determination unit determines the midpoint of each of 2 line segments connecting 2 articular lips facing each other in the width direction of the body of the subject, and determines a direction perpendicular to a line segment connecting the determined 2 midpoints as a slice direction in imaging the sagittal image.

7. The magnetic resonance imaging apparatus according to claim 6,

the detection unit detects the pelvis of the subject from the magnetic resonance image for positioning,

the determination unit determines the slice width in imaging the sagittal image based on the feature points on the pelvis.

8. The magnetic resonance imaging apparatus according to claim 6,

the detection unit further detects the prostate of the subject from the magnetic resonance image for positioning,

the determination unit determines the slice center in the imaging of the sagittal image as a position where the slice center passes through the detected center of the prostate.

9. The magnetic resonance imaging apparatus according to claim 8,

the detection unit further detects pubic symphysis of the subject from the magnetic resonance image for localization,

and a determination unit configured to correct the position of the slice center based on the detected position of the pubic symphysis when the slice center determined based on the detected position of the prostate is separated from the detected position of the pubic symphysis by a predetermined distance or more.

10. The magnetic resonance imaging apparatus according to claim 2,

the two-dimensional magnetic resonance image comprises a coronal image,

the detection unit detects a plurality of articular lips of the subject from the magnetic resonance image for positioning,

the determination unit determines the midpoint of each of 2 line segments connecting 2 articular lips facing each other in the front-rear direction of the body of the subject, and determines a direction perpendicular to a line segment connecting the determined 2 midpoints as a slice direction in imaging the coronal image.

11. The magnetic resonance imaging apparatus according to claim 10,

the detection unit further detects pubic symphysis of the subject from the magnetic resonance image for localization,

the determination unit determines a slice width of the coronal image based on a position of the pubic bone in a front-back direction of the body of the subject.

12. The magnetic resonance imaging apparatus according to claim 2,

the two-dimensional magnetic resonance image comprises an axial image,

the detection unit detects the urethra and the prostatic apical part of the subject from the magnetic resonance image for positioning,

the determination unit obtains a line segment connecting the starting position of the urethra of the subject and the prostatic apex, and determines a direction parallel to the line segment as a slice direction in the axial image capturing.

13. The magnetic resonance imaging apparatus according to claim 2,

the two-dimensional magnetic resonance image comprises a coronal image,

the detection unit detects the urethra and the prostatic apical part of the subject from the magnetic resonance image for positioning,

the determination unit obtains a line segment connecting the starting position of the urethra of the subject and the prostatic apex, and determines a direction perpendicular to the line segment as a slice direction in imaging the coronal image.

14. The magnetic resonance imaging apparatus according to any one of claims 1 to 13,

the diagnostic imaging apparatus further includes an imaging processing unit that executes processing for imaging the diagnostic magnetic resonance image based on the imaging target region determined by the determination unit.

15. The magnetic resonance imaging apparatus according to any one of claims 1 to 13,

the image processing apparatus further includes a display control unit that causes a display unit to display an image representing the imaging target region determined by the determination unit.

16. The magnetic resonance imaging apparatus according to claim 1,

the detection unit detects at least one tissue of a femoral head, a pelvis, an articular lip, a pubic junction, a urethra, and a prostatic apical portion of the subject depicted in the magnetic resonance image for positioning by inputting the magnetic resonance image for positioning into a learned model obtained by learning a magnetic resonance image in association with an image region in which at least one of the femoral head, the pelvis, the articular lip, the pubic junction, the urethra, and the prostatic apical portion is depicted on the magnetic resonance image.

17. A method, comprising:

a detection step of detecting at least one tissue of a femoral head, a pelvis, an articular lip, a pubic junction, a urethra, and a prostatic apex of a subject from a magnetic resonance image for positioning obtained by imaging a range including a prostate of the subject; and

a determination step of determining an imaging target region in imaging a magnetic resonance image for diagnosis of a prostate of the subject based on the detected tissue.

18. A storage medium that stores, non-temporarily, a program that causes a computer to execute:

a detection step of detecting at least one tissue of a femoral head, a pelvis, an articular lip, a pubic junction, a urethra, and a prostatic apex of a subject from a magnetic resonance image for positioning obtained by imaging a range including a prostate of the subject; and

a determination step of determining an imaging target region in imaging a magnetic resonance image for diagnosis of a prostate of the subject based on the detected tissue.

Technical Field

Embodiments disclosed in the present specification and drawings relate to a magnetic resonance imaging apparatus, a method, and a storage medium.

Background

Conventionally, in a Magnetic Resonance Imaging (MRI) apparatus, before Imaging an image for diagnosis of a subject, a user may manually set an Imaging target region of the image for diagnosis on a positioning image obtained by preparation scan Imaging. The process of setting the imaging target region for main imaging in this way is called positioning.

Disclosure of Invention

A magnetic resonance imaging apparatus according to an embodiment includes a coil that receives a magnetic resonance signal emitted from a subject under the influence of a high-frequency magnetic field, and a processor. The processor detects at least one tissue of a femoral head, a pelvis, an articular lip, a pubic junction, a urethra, and a prostatic apex of a subject from a magnetic resonance image for localization based on a magnetic resonance signal corresponding to a range including a prostate of the subject. The processor determines an imaging target region in imaging a magnetic resonance image for diagnosing a prostate of a subject based on the detected tissue.

Drawings

Fig. 1 is a block diagram showing an example of a magnetic resonance imaging apparatus according to a first embodiment.

Fig. 2 is a diagram illustrating an example of the learned model according to the first embodiment.

Fig. 3 is a diagram illustrating an example of an imaging target region when a two-dimensional axial (axial) image is imaged according to the first embodiment.

Fig. 4 is a diagram illustrating an example of rotation in the in-plane direction of the imaging cross section in the first embodiment.

Fig. 5 is a diagram illustrating an example of a method for determining the slice direction of an axial image according to the first embodiment.

Fig. 6 is a diagram showing an example of a method for determining the top end of a slice in an axial image according to the first embodiment.

Fig. 7 is a diagram showing an example of a method for determining the slice lower end of the axial image according to the first embodiment.

Fig. 8 is a diagram showing an example of a method for determining the amount of rotation in the in-plane direction of the axial image according to the first embodiment.

Fig. 9 is a diagram illustrating an example of a method for determining a slice direction in a sagittal (sagittal) image and a coronal (coronal) image according to the first embodiment.

Fig. 10 is a diagram showing an example of a method for determining the slice center in imaging a sagittal image according to the first embodiment.

Fig. 11 is a diagram showing an example of a method for determining a slice width in imaging a sagittal image according to the first embodiment.

Fig. 12 is a flowchart showing an example of the flow of the positioning process according to the first embodiment.

Fig. 13 is a diagram showing an example of a method for determining the slice direction of a coronal image and an axial image according to the second embodiment.

Detailed Description

Embodiments of a magnetic resonance imaging apparatus, a magnetic resonance imaging method, and a storage medium will be described in detail below with reference to the drawings.

The magnetic resonance imaging apparatus of an embodiment includes a coil that receives a magnetic resonance signal emitted from a subject due to the influence of a high-frequency magnetic field, and a processor. The processor detects at least one tissue of a femoral head (femoral head), a pelvis, an articular lip, a pubic junction, a urethra, and a prostatic apex of a subject from a magnetic resonance image for localization based on a magnetic resonance signal corresponding to a range of a prostate including the subject. The processor determines an imaging target region in imaging a magnetic resonance image for diagnosing a prostate of a subject based on the detected tissue.

Fig. 1 is a block diagram showing an example of a Magnetic Resonance Imaging (MRI) apparatus 100 according to an embodiment. As shown in fig. 1, the magnetic resonance imaging apparatus 100 includes a static field magnet 101, a static field power supply (not shown), a gradient coil 103, a gradient power supply 104, a bed 105, a bed control circuit 106, a transmission coil 107, a transmission circuit 108, a reception coil 109, a reception circuit 110, a sequence control circuit 120, and a computer system 130.

The configuration shown in fig. 1 is merely an example. For example, the sequence control circuit 120 and the computer system 130 may be combined or separated as appropriate. In addition, the subject P (e.g., a human body) is not included in the magnetic resonance imaging apparatus 100.

The X-axis, Y-axis, and Z-axis shown in fig. 1 constitute an apparatus coordinate system unique to the magnetic resonance imaging apparatus 100. For example, the Z-axis direction is set along the magnetic flux of the static magnetic field generated by the static magnetic field magnet 101 so as to coincide with the axial direction of the cylinder of the gradient coil 103. The Z-axis direction is the same direction as the longitudinal direction of the bed 105, and the head-to-tail direction of the subject P placed on the bed 105. The X-axis direction is set along a horizontal direction orthogonal to the Z-axis direction. The Y-axis direction is set along the vertical direction orthogonal to the Z-axis direction.

The static magnetic field magnet 101 is a magnet formed in a hollow substantially cylindrical shape, and generates a static magnetic field in an internal space. The static field magnet 101 is, for example, a superconducting magnet, and is excited by receiving a current from a static field power supply. The static magnetic field power supply supplies a current to the static magnetic field magnet 101. As another example, the static magnetic field magnet 101 may be a permanent magnet, and in this case, the magnetic resonance imaging apparatus 100 may not include a static magnetic field power supply. Alternatively, the static magnetic field power supply may be provided separately from the magnetic resonance imaging apparatus 100.

The gradient coil 103 is a coil formed in a hollow substantially cylindrical shape, and is disposed inside the static field magnet 101. The gradient coil 103 is formed by combining 3 coils corresponding to the respective orthogonal X, Y and Z axes, and the 3 coils generate a gradient magnetic field whose magnetic field strength changes along the respective axes X, Y and Z by receiving supply of current from the gradient magnetic field power supply 104. The gradient magnetic field power supply 104 supplies a current to the gradient magnetic field coil 103 under the control of the sequence control circuit 120.

The bed 105 includes a top plate (couchtop)105a on which the subject P is placed, and the top plate 105a is inserted into the imaging port with the subject P such as a patient placed thereon under the control of the bed control circuit 106. The bed control circuit 106 drives the bed 105 to move the top plate 105a in the longitudinal direction and the vertical direction under the control of the computer system 130.

The transmission coil 107 applies a radio-frequency magnetic field to excite an arbitrary region of the subject P. The transmission coil 107 is, for example, a main body (wheel body) type coil that surrounds the entire body of the subject P. The transmission coil 107 receives the RF pulse from the transmission circuit 108, generates a radio frequency magnetic field, and applies the radio frequency magnetic field to the subject P. The transmission circuit 108 supplies an RF pulse to the transmission coil 107 under the control of the sequence control circuit 120.

The receiving coil 109 is disposed inside the gradient coil 103, and receives a magnetic resonance signal (hereinafter, referred to as an mr (magnetic resonance) signal) emitted from the subject P due to the influence of the radio frequency magnetic field. Upon receiving the MR signal, the receiving coil 109 outputs the received MR signal to the receiving circuit 110.

In fig. 1, the receiving coil 109 is provided separately from the transmitting coil 107, but this is an example and is not limited to this configuration. For example, the receiving coil 109 may also serve as the transmitting coil 107. Hereinafter, the transmitting coil 107 and the receiving coil 109 will be collectively referred to as simply coils.

The receiving circuit 110 performs analog-to-digital (AD) conversion on the analog MR signal output from the receiving coil 109 to generate MR data. In addition, the receiving circuit 110 transmits the generated MR data to the sequence control circuit 120. The AD conversion may be performed in the receiving coil 109. In addition to the AD conversion, the reception circuit 110 can perform arbitrary signal processing.

The sequence control circuit 120 drives the gradient magnetic field power supply 104, the transmission circuit 108, and the reception circuit 110 based on the sequence information transmitted from the computer system 130, thereby performing imaging of the subject P.

Here, the order information is information defining a procedure for performing image capturing. The sequence information defines the intensity of the current supplied to the gradient magnetic field coil 103 by the gradient magnetic field power supply 104, the timing of supplying the current, the intensity of the RF pulse supplied to the transmission coil 107 by the transmission circuit 108, the timing of applying the RF pulse, the timing of detecting the MR signal by the reception circuit 110, and the like. The order information differs according to the range of the region that becomes the imaging target in the body of the subject P.

The sequence control circuit 120 may be implemented by a processor, or may be implemented by a mixture of software and hardware.

Further, as a result of the sequence control circuit 120 driving the gradient magnetic field power supply 104, the transmission circuit 108, and the reception circuit 110 to image the subject P, when the MR data is received from the reception circuit 110, the received MR data is transferred to the computer system 130.

The computer system 130 performs overall control of the magnetic resonance imaging apparatus 100, generation of MR images, and the like. As shown in fig. 1, the computer system 130 includes an NW (network) interface 131, a storage circuit 132, a processing circuit 133, an input interface 134, and a display 135.

The NW interface 131 communicates with the sequence control circuit 120 and the couch control circuit 106. For example, the NW interface 131 sends the sequence information to the sequence control circuit 120. Further, the NW interface 131 receives MR data from the sequence control circuit 120.

The storage circuit 132 stores MR data received by the NW interface 131, k-space data arranged in k-space by a processing circuit 133 described later, image data generated by the processing circuit 133, and the like. The Memory circuit 132 is, for example, a semiconductor Memory element such as a RAM (Random Access Memory) or a flash Memory, a hard disk, an optical disk, or the like.

The input interface 134 receives various instructions and information inputs from an operator. The input interface 134 is implemented by, for example, a trackball, a switch button, a mouse, a keyboard, a touch panel that performs an input operation by touching an operation surface, a touch panel in which a display screen and a touch panel are integrated, a non-contact input circuit using an optical sensor, an audio input circuit, and the like. The input interface is connected to the processing circuit 133, converts an input operation received from an operator into an electric signal, and outputs the electric signal to the processing circuit 133. In this specification, the input interface is not limited to an interface including a physical operation member such as a mouse or a keyboard. For example, a processing circuit that receives an electric signal corresponding to an input operation from an external input device provided separately from the computer system 130 and outputs the electric signal to the control circuit is also included in the input interface.

The display 135 displays a gui (graphical User interface) for accepting input of imaging conditions, a magnetic resonance image generated by the processing circuit 133, and the like under the control of the processing circuit 133. The display 135 is a display device such as a liquid crystal display. The display 135 is an example of a display unit.

The processing circuit 133 controls the entire magnetic resonance imaging apparatus 100. More specifically, the processing circuit 133 includes, as an example, an imaging processing function 133a, a detection function 133b, a determination function 133c, a display control function 133d, and a reception function 133 e. The image pickup processing function 133a is an example of an image pickup processing section. The detection function 133b is an example of a detection unit. The determination function 133c is a part of the determination section. The display control function 133d is an example of a display control unit. The receiving function 133e is an example of a receiving unit.

Here, for example, the respective processing functions of the imaging processing function 133a, the detection function 133b, the determination function 133c, the display control function 133d, and the reception function 133e, which are components of the processing circuit 133, are stored in the storage circuit 132 as programs executable by a computer. The processing circuit 133 is a processor. For example, the processing circuit 133 reads out and executes programs from the storage circuit 132 to realize functions corresponding to the respective programs. In other words, the processing circuit 133 in which the respective programs are read has the respective functions shown in the processing circuit 133 in fig. 1. In fig. 1, the processing functions performed by the imaging processing function 133a, the detection function 133b, the determination function 133c, the display control function 133d, and the reception function 133e have been described as being implemented by a single processor, but the processing circuit 133 may be configured by combining a plurality of independent processors, and each processor may implement the functions by executing a program. In fig. 1, although the description has been given with respect to the case where the single memory circuit 132 stores data corresponding to each processing function, the following configuration may be adopted: the plurality of memory circuits are arranged in a distributed manner, and the processing circuit 133 reads out a corresponding program from the individual memory circuits.

The imaging processing function 133a controls each unit of the magnetic resonance imaging apparatus 100 to perform imaging of a magnetic resonance image. For example, the imaging processing function 133a executes generation of sequence information, acquisition of MR data, generation of k-space data, and generation of a magnetic resonance image.

More specifically, the imaging processing function 133a generates sequence information defining the imaging sequence based on the type of the magnetic resonance image to be imaged and the imaging target region, and transmits the generated sequence information to the sequence control circuit 120 via the NW interface 131. The sequence control circuit 120 executes various pulse sequences (pulse sequences) based on the sequence information generated by the image pickup processing function 133 a.

In addition, the imaging processing function 133a collects MR data converted from MR signals emitted from the subject P by executing various pulse sequences from the sequence control circuit 120 via the NW interface 131. The imaging processing function 133a arranges the acquired MR data in accordance with the phase encoding amount and the frequency encoding amount given by the gradient magnetic field. MR data arranged in k-space is referred to as k-space data. The k-space data is stored in the storage circuit 132.

The imaging processing function 133a generates a magnetic resonance image based on the k-space data stored in the storage circuit 132. For example, the imaging processing function 133a generates a magnetic resonance image by performing reconstruction processing such as fourier transform on k-space data. The imaging processing function 133a stores the generated magnetic resonance image in the storage circuit 132, for example.

In the present embodiment, the imaging processing function 133a performs imaging of a magnetic resonance image for positioning before the main imaging. The magnetic resonance image for positioning is also called a Locator image (Locator) or a Scout image (Scout), and is an image used for positioning of an imaging cross section in main imaging. The main imaging is imaging of a magnetic resonance image for diagnosis.

In the present embodiment, the magnetic resonance image for positioning is a magnetic resonance image obtained by imaging a range of the prostate including the subject P. In other words, the magnetic resonance image for positioning corresponds to a range including the prostate of the subject P and is based on the magnetic resonance signal received by the receiving coil 109. The magnetic resonance image for localization may be a three-dimensional image or a two-dimensional multi-slice image. The magnetic resonance image for localization may have a smaller number of pixels than the magnetic resonance image for diagnosis, and may be a rough image.

Alternatively, the magnetic resonance image for localization may be a high-resolution three-dimensional magnetic resonance image. In this case, the three-dimensional magnetic resonance image for diagnosis may also be used as the magnetic resonance image for localization.

In the present embodiment, the diagnostic magnetic resonance image imaged by the main imaging is a two-dimensional magnetic resonance image used for diagnosis of the prostate of the subject P. More specifically, in the present embodiment, three diagnostic two-dimensional magnetic resonance images, i.e., an Axial (Axial) image (body Axial cross-sectional image), a Sagittal (Sagittal) image (Sagittal cross-sectional image), and a Coronal (Coronal) image (Coronal cross-sectional image), are imaged in the main imaging. In addition, the magnetic resonance image for diagnosis may not include all of the axial image, the sagittal image, and the coronal image, as long as at least one of them is included.

The imaging target region in imaging a two-dimensional magnetic resonance image for diagnosis is determined by a determination function 133c described later. The imaging processing function 133a generates order information based on the imaging target region determined by the determining function 133c, and executes main imaging. When the position, size, inclination, or the like of the imaging target region 70 determined by the determination function 133c is changed by the user, the imaging processing function 133a generates order information based on the changed imaging target region 70, and executes main imaging.

The detection function 133b detects at least one tissue of the femoral head, pelvis, articular lip, pubic junction, urethra, and prostatic apex of the subject P from a magnetic resonance image for positioning obtained by imaging a range including the prostate of the subject P.

In the present embodiment, the detection function 133b detects the femoral head, pelvis, labia articularis, and pubic symphysis of the subject P. The femoral head, pelvis, labia articularis, and pubic symphysis are bones located around the prostate. In the present embodiment, both of the hard bone and the cartilage are simply referred to as bone.

The detection target is not limited to this. The detection function 133b may detect all of the femoral head, pelvis, labia articularis, pubic symphysis, urethra, and prostatic apical part of the subject P, or may detect only one of them, for example. In addition, when a plurality of parts of the femoral head, pelvis, labia articularis, pubic symphysis, urethra, and prostatic apex of the subject P are detected, it is not necessary to detect all of them. That is, the detection function 133b detects at least one of the femoral head, pelvis, labia articularis, pubic junction, urethra, and prostatic apex of the subject P, for example.

As a method of detecting a tissue such as a femoral head from a magnetic resonance image for positioning, for example, a method of image processing such as template matching can be employed. In this case, the storage circuit 132 stores template images of the femoral head, pelvis, labia, pubic symphysis, urethra, and prostatic apex, for example. The detection function 133b detects an image region in which the tissue to be detected is drawn on the magnetic resonance image 80 for positioning, based on the template image read from the storage circuit 132.

The method of detecting a tissue such as a femoral head from a magnetic resonance image for positioning is not limited to template matching. For example, the detection function 133b can employ a method based on deep learning or other machine learning as a method of detecting a tissue such as a femoral head from a magnetic resonance image for positioning. In this case, the detection function 133b inputs the magnetic resonance image for positioning to the learned model stored in the storage circuit 132, thereby detecting at least one tissue of the femoral head, pelvis, labia, pubic junction, urethra, and prostatic apical part of the subject P from the magnetic resonance image for positioning.

The learned model is a model obtained by learning a magnetic resonance image in association with an image region in which at least one of the femoral head, pelvis, labia, pubic symphysis, urethra, and prostatic apical part is depicted on the magnetic resonance image. The learned model is generated by a deep learning or other machine learning based approach. The magnetic resonance image used for learning by the learned model is referred to as a magnetic resonance image for learning.

Fig. 2 is a diagram illustrating an example of the learned model 90 according to the present embodiment. As shown in fig. 2, the detection function 133b inputs the magnetic resonance image 80 for positioning to the learned model 90. Then, the learned model 90 outputs, as a detection result, an image region in which the femoral head, pelvis, articular lip, and pubic symphysis are depicted on the magnetic resonance image 80 for positioning.

In the example shown in fig. 2, the learned model 90 outputs coordinates on the magnetic resonance image 80 for positioning of image regions 801a and 801b in which femoral heads are drawn, an image region 802 in which a pelvis is drawn, image regions 803a to 803d in which the relevant labia are drawn, and an image region 804 in which pubic symphysis is drawn. In fig. 2, the image regions 801a, 801b, 802, 803a to 803d, and 804 are shown as rectangles for explanation, but the learned model 90 may output coordinates of pixels included in the image regions 801a, 801b, 802, 803a to 803d, and 804 on the magnetic resonance image 80 for positioning, for example.

In fig. 2, the magnetic resonance image 80 for positioning is displayed as a coronal image, but the learned model 90 detects image regions 801a, 801b, 802, 803a to 803d, and 804 from cross sections in other directions of the magnetic resonance image 80 for positioning. The learned model 90 may output an image region in which the urethra and the prostatic apical portion are depicted on the magnetic resonance image 80 for positioning.

The detection function 133b detects the prostate of the subject P from the magnetic resonance image 80 for positioning obtained by imaging a range including the prostate of the subject P. The detection function 133b can also use a method of image processing such as template matching for prostate detection. For example, the memory circuit 132 is configured to store a template image of the prostate. The detection function 133b detects an image region in which the prostate is depicted on the magnetic resonance image 80 for positioning, based on the template image read out from the storage circuit 132.

Alternatively, the detection function 133b may detect the prostate using the learned model. The learned model 90 used for detecting the femoral head and the like may further have a function of detecting the prostate, or another learned model for detecting the prostate may be used.

The detection function 133b sends the detection result of the tissue around the prostate, such as the femoral head, and the prostate to the determination function 133 c.

Returning to fig. 1, the determination function 133c determines an imaging target region in imaging a magnetic resonance image for diagnosis based on at least one tissue of the femoral head, pelvis, articular lip, pubic junction, urethra, and prostatic tip of the subject P detected by the detection function 133 b. In the present embodiment, the determination function 133c determines the imaging target region in imaging the magnetic resonance image for diagnosis based on the femoral head, pelvis, labia articularis, and pubic symphysis of the subject P detected by the detection function 133 b. As described above, in the present embodiment, the magnetic resonance images for diagnosis are three two-dimensional magnetic resonance images, i.e., an axial image, a sagittal image, and a coronal image.

The imaging target region in the axial image, the sagittal image, and the coronal image is determined by the slice direction, the slice center, the slice width, and the amount of rotation in the in-plane direction of the imaging section. The determining function 133c determines at least one of a slice direction, a slice center, a slice width, and a rotation amount in an in-plane direction of an imaging cross section in imaging of a magnetic resonance image for diagnosis. The determination function 133c of the present embodiment determines all of the slice direction, slice center, slice width, and amount of rotation in the in-plane direction of the imaging cross section. The determining function 133c may determine only some of them.

Fig. 3 is a diagram illustrating an example of the imaging target region 70 in imaging the two-dimensional axial image according to the present embodiment. The direction of the X, Y, Z axis shown in fig. 3 indicates the direction of the X, Y, Z axis when the subject P is placed on the couch 105 shown in fig. 1.

The imaging target region 70 is also referred to as a slice. As shown in fig. 3, a direction perpendicular to the plane of the imaging target region 70 is referred to as a slice direction. In the axial image, the slice direction is a direction along the head-tail direction of the subject P.

The slice width 701 is the thickness of the imaging target region 70. The slice width 701 is also referred to as slice coverage (slice coverage). The slice center 702 is the center in the width direction of the imaging target region 70.

Fig. 4 is a diagram illustrating an example of rotation in the in-plane direction of the imaging cross section in the present embodiment. The in-plane direction of the imaging cross section is a planar direction horizontal to the plane of the imaging target region 70. The amount of rotation in the in-plane direction of the imaging section is the amount of rotation of the imaging target region 70 in the XY plane defined by the X axis and the Y axis in fig. 3. The rotation amount of the imaging target region 70 in the XY plane may be represented by, for example, an angle formed by the Y-axis direction of the magnetic resonance imaging apparatus 100 and a side in the longitudinal direction of the imaging target region 70, an angle formed by the X-axis direction of the magnetic resonance imaging apparatus 100 and a side in the lateral direction of the imaging target region 70, or the like.

In fig. 3 and 4, the axial image is taken as an example, but the imaging target region 70 is also defined by the slice direction, the slice center, the slice width, and the amount of rotation in the in-plane direction of the imaging cross section at the time of imaging the sagittal image and the coronal image.

Fig. 5 is a diagram illustrating an example of a method for determining the slice direction of an axial image according to the present embodiment. Fig. 5 illustrates a coronal cross-section of a magnetic resonance image 80 for localization. As shown in fig. 5, the determining function 133c determines a direction perpendicular to a line segment 600 through which the upper end portions 60a and 60b of the 2 femoral heads on the magnetic resonance image 80 for positioning detected by the detecting function 133b pass, as a slice direction in imaging of the axial image.

The determination function 133c determines the slice width 701 and the slice center 702 of the axial image based on the positions of the 2 femoral heads and the positions of the pubic symphysis detected by the detection function 133 b.

Fig. 6 is a diagram illustrating an example of a method for determining the slice upper end 711a of the axial image according to the present embodiment. Fig. 7 is a diagram illustrating an example of a method for determining the slice lower end 711b of the axial image according to the present embodiment. The interval between the slice upper end 711a and the slice lower end 711b is the slice width 701. Fig. 6 illustrates a coronal cross-section of a magnetic resonance image 80 for localization. In addition, fig. 7 illustrates a sagittal section of the magnetic resonance image 80 for positioning.

The determination function 133c determines the slice upper end 711a based on the positions of the 2 femoral heads. As an example, as shown in fig. 6, the determining function 133c determines a segment obtained by moving a segment 600 passing through the upper ends 60a and 60b of the 2 femoral heads in parallel by a first distance 701a toward the head of the subject P as a slice upper end 711 a. The first distance 701a is, for example, 20mm, but is not limited thereto.

The determination function 133c determines the slice lower end 711b based on the position of pubic junction. As an example, the determining function 133c determines a line segment separated by a second distance 701b from the pubic junction lower end 61 toward the leg portion side of the subject P as a slice lower end 711b, as shown in fig. 7. The second distance 701b is, for example, 10mm, but is not limited thereto. In fig. 7, the line segment 600 and the slice upper end 711a are not described, but the slice lower end 711b is parallel to the line segment 600 and the slice upper end 711 a.

The middle between the slice upper end 711a and the slice lower end 711b is the slice center 702 in imaging of the axial image.

In fig. 7, an example in which the pubic symphysis is used as a reference of the slice lower end 711b in imaging of the axial image is described, but the pubic symphysis is also used for other purposes. For example, the determining function 133c may determine the slice width 701 in imaging of the coronal image based on the position of pubic symphysis in the anteroposterior direction of the body of the subject P.

The determining function 133c determines the amount of rotation in the in-plane direction of the imaging cross section based on the 4 articular lips detected by the detecting function 133 b. There may be a deviation in the X-axis, Y-axis, or Z-axis direction of the magnetic resonance imaging apparatus 100 from the width direction, the front-back direction, or the body axis direction of the subject P depicted in the magnetic resonance image 80 for positioning. For example, the determining function 133c may determine a direction perpendicular to a line segment connecting 2 joint lips located at positions facing each other in the width direction of the body of the subject P as the body axis direction of the subject P, and determine the amount of rotation in the in-plane direction of the imaging cross section so that the body axis direction coincides with the Z axis direction of the magnetic resonance image 80 for positioning.

The method of determining the amount of rotation in the in-plane direction of the imaging cross section is not limited to this. Fig. 8 is a diagram illustrating an example of a method for determining the amount of rotation in the in-plane direction of an axial image according to the present embodiment. In fig. 8, a body axis cross section of a magnetic resonance image 80 for localization is illustrated. The articular lips 62a and 62b shown in fig. 8 are articular lips on the front surface side of the subject P. The articular lips 62c and 62d are the articular lips on the back side of the subject P. The articular lips 62a to 62d are detected by the detecting function 133 b.

For example, the determination function 133c obtains the midpoint 63a of a line segment 621a connecting the articular lip 62a and the articular lip 62b facing each other in the body width direction of the subject P. The determination function 133c obtains the midpoint 63b of a line segment 621b connecting the articular lip 62c and the articular lip 62d facing each other in the body width direction of the subject P. The determining function 133c obtains a midpoint 63c of a line segment 621c connecting the articular lip 62a and the articular lip 62c facing each other in the front-rear direction of the body of the subject P. The determining function 133c obtains the midpoint 63d of a line segment 621d connecting the articular lip 62b and the articular lip 62d facing each other in the front-rear direction of the body of the subject P.

Then, for example, the determination function 133c obtains a line segment 601 passing through the midpoint 63a and the midpoint 63 b. The determining function 133c obtains a line segment 602 passing through the midpoint 63c and the midpoint 63 d. The determining function 133c obtains the amount of rotation in the in-plane direction of the axial image, for example, such that the longitudinal direction of the imaging target region 70 is parallel to the line segment 601. Alternatively, the determining function 133c may determine the amount of rotation in the in-plane direction of the axial image so that the horizontal direction of the imaging target region 70 is parallel to the line segment 602.

The determination function 133c determines the slice directions of the sagittal image and the coronal image for diagnosis based on the positions of the articular lips 62a to 62d on the magnetic resonance image 80 for positioning detected by the detection function 133 b.

Fig. 9 is a diagram showing an example of a method for determining the slice direction in the sagittal image and the coronal image according to the present embodiment. In fig. 9, a body axis cross section of a magnetic resonance image 80 for localization is illustrated.

The determination function 133c obtains the midpoint 63a of a line segment 621a connecting the articular lip 62a and the articular lip 62b facing each other in the width direction of the body of the subject P. The determination function 133c obtains the midpoint 63b of a line segment 621b connecting the articular lip 62c and the articular lip 62d facing each other in the body width direction of the subject P. The determining function 133c obtains a midpoint 63c of a line segment 621c connecting the articular lip 62a and the articular lip 62c facing each other in the front-rear direction of the body of the subject P. The determining function 133c obtains the midpoint 63d of a line segment 621d connecting the articular lip 62b and the articular lip 62d facing each other in the front-rear direction of the body of the subject P.

Then, the determining function 133c obtains a line segment 601 passing through the midpoint 63a and the midpoint 63 b. The determining function 133c obtains a line segment 602 passing through the midpoint 63c and the midpoint 63 d.

The determination function 133c determines a direction perpendicular to the line segment 601 as a slice direction in imaging of a sagittal image for diagnosis. The determining function 133c determines a direction perpendicular to the line segment 602 as a slice direction in imaging of the coronal image for diagnosis.

The determination function 133c determines the slice center 702 as a position where the center of the prostate detected by the detection function 133b passes. Further, the determining function 133c corrects the position of the slice center 702 based on the detected position of the pubic symphysis when the slice center 702 determined based on the detected position of the prostate is separated from the position of the pubic symphysis of the subject P detected by the detecting function 133b by a predetermined distance or more. The predetermined distance is not particularly limited, and may be set by an engineer or the like or may be predetermined.

Normally, when the detected position of the prostate is correct, the center of the prostate in the width direction of the subject P and the center of the pubic symphysis in the width direction of the subject P substantially coincide, but when the detection function 133b erroneously detects the position of the prostate, the slice center 702 determined based on the detected position of the prostate may be separated from the position of the pubic symphysis of the subject P detected by the detection function 133b by a predetermined distance or more.

Fig. 10 is a diagram illustrating an example of a method of determining a slice center in imaging a sagittal image according to the present embodiment. In fig. 10, a body axis cross section of a magnetic resonance image 80 for localization is illustrated. The determination function 133c corrects the position of the slice center 702 such that the slice center 702 is located at the position of the end 64a on the front side of the subject P and the end 64b on the back side of the subject P, which have passed the pubic junction drawn on the magnetic resonance image 80 for positioning.

The process of correcting the slice center 702 is not essential, and the determination function 133c may use the slice center 702 with the center of the prostate as a reference.

The determination function 133c determines the slice width 701 in imaging of a sagittal image based on the feature points on the pelvis of the subject P detected by the detection function 133 b.

Fig. 11 is a diagram illustrating an example of a method for determining a slice width 701 in imaging a sagittal image according to this embodiment. In fig. 11, a body axis cross section of a magnetic resonance image 80 for localization is illustrated.

The characteristic points 65a and 65c shown in fig. 11 are located on the inner side of the pelvis and correspond to the gaps between the bones. The feature points 65b and 65d are convex portions located on the inner side of the pelvis. The characteristic points 65a and 65c are located on the front surface side of the subject P, and the characteristic points 65b and 65d are located on the back surface side of the subject P.

The prostate is located between the characteristic points 65a and 65d and the characteristic points 65c and 65b of the pelvis, and the characteristic points 65c and 65b are located at positions facing the characteristic points 65a and 65d, respectively, across the spine. Therefore, the determination function 133c can set the imaging target region 70 in the imaging of the sagittal image so as to include the prostate of the subject P by setting the slice width 701 so that the imaging target region 70 includes the gaps between the characteristic points 65a and 65d of the pelvis and the characteristic points 65c and 65 b.

For example, the determining function 133c determines the narrowest slice width 701 of the slice widths 701 in which all the feature points 65a to 65d are included in the imaging target region 70, as the slice width 701 in imaging a sagittal image for diagnosis.

The determination condition of the slice width 701 is not limited to this. For example, the determination function 133c may set the slice width 701 so that the contour lines of both side surfaces of the imaging target region 70 pass through all of the feature points 65a to 65 d. For example, the determination function 133c may set the slice width 701 so that the total of the distances between the contour lines on both side surfaces of the imaging target region 70 and the feature points 65a to 65d is the smallest.

The characteristic points on the pelvis that are the reference of the slice width 701 are not limited to the characteristic points 65a to 65d shown in fig. 11, and other characteristic points may be used as the reference as long as they are easily detected on the magnetic resonance image 80 for positioning.

The determination function 133c transmits the determination results of the slice direction, slice center, slice width, and rotation amount in the in-plane direction of the imaging section in imaging of the axial image, sagittal image, and coronal image for diagnosis to the imaging processing function 133 a.

Returning to fig. 1, the display control function 133d causes the display 135 to display an image showing the imaging target region 70 determined by the determination function 133 c. For example, the display control function 133d causes the display 135 to display an image in which the imaging target region 70 in the imaging of the axial image, the sagittal image, and the coronal image for diagnosis is superimposed on the magnetic resonance image 80 for positioning. The display mode is not limited to this.

The display control function 133d causes the display 135 to display a diagnostic magnetic resonance image captured by the main imaging after the main imaging by the imaging processing function 133a is executed.

The reception function 133e receives various operations performed by the user via the input interface 134. More specifically, the receiving function 133e receives a user operation for changing the slice direction, slice center, slice width, and amount of rotation in the in-plane direction of the imaging target region 70 determined by the determining function 133 c. For example, the reception function 133e may receive, as an operation for changing the slice direction, the slice center, the slice width, and the amount of rotation in the in-plane direction of the imaging cross section, an operation of a user for changing the position, size, inclination, or the like of the imaging target region 70 displayed on the display 135.

The reception function 133e receives an operation by the user for instructing completion of positioning. For example, the reception function 133e receives, as an operation for instructing completion of positioning, an operation of a user clicking an imaging start button displayed on the display 135 with a mouse or the like. The imaging start button may be provided in the magnetic resonance imaging apparatus 100 as a physical button, instead of an image.

In the above description, an example has been described in which the "processor" reads out a program corresponding to each function from the memory circuit and executes the program, but the embodiment is not limited to this. The term "processor" refers to, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a Programmable Logic Device (e.g., a Simple Programmable Logic Device (SPLD)), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)). In the case where the processor is, for example, a CPU, the processor reads out and executes a program stored in the storage circuit to realize a function. On the other hand, in the case where the processor is an ASIC, the functions are directly incorporated into the circuit of the processor as a logic circuit, instead of storing a program in a memory circuit. Note that each processor of the present embodiment is not limited to a single circuit configuration for each processor, and may be configured by combining a plurality of independent circuits to configure one processor to realize the functions thereof. Further, a plurality of components in fig. 1 may be integrated into one processor to realize the functions thereof.

Next, a flow of the positioning process executed in the magnetic resonance imaging apparatus 100 of the present embodiment configured as described above will be described.

Fig. 12 is a flowchart showing an example of the flow of the positioning process according to the present embodiment. As a premise of this flowchart, the subject P is placed on the top plate 105a, and the top plate 105a is inserted into the imaging port.

First, the imaging processing function 133a images the magnetic resonance image 80 for positioning (S1).

Then, the detection function 133b detects the prostate from the captured magnetic resonance image 80 for positioning by image processing such as template matching or a learned model (S2).

The detection function 133b detects bones around the prostate (femoral head, pelvis, articular lip, and pubic symphysis) from the captured magnetic resonance image 80 for positioning by image processing such as template matching or the learned model 90 (S3).

Then, the determination function 133c determines the slice direction, slice center, slice width, and amount of rotation in the in-plane direction of the imaging cross section in the main imaging based on the position on the magnetic resonance image 80 for positioning the tissue detected by the detection function 133b (S4).

Next, the display control function 133d causes the display 135 to display the result of the positioning by the decision function 133c (S5). Specifically, the display control function 133d causes the display 135 to display the image indicating the imaging target region 70 determined by the determination function 133 c.

The reception function 133e then determines whether or not an operation by the user for changing the slice direction, slice center, slice width, or amount of rotation in the in-plane direction of the imaging target region 70 determined by the determination function 133c has been received (S6).

When it is determined that the user has accepted the operation to change the slice direction, the slice center, the slice width, or the amount of rotation in the in-plane direction of the imaging section (yes at S6), the accepting function 133e changes the slice direction, the slice center, the slice width, or the amount of rotation in the in-plane direction of the imaging section in accordance with the accepted change operation (S7).

Then, the reception function 133e determines whether or not a positioning completion operation by the user has been received (S8). If the receiving function 133e determines that the user has not received an operation to change the slice direction, the slice center, the slice width, or the amount of rotation in the in-plane direction of the imaging cross section (no at S6), the process proceeds to S8.

If it is determined that the user has not accepted the positioning completion operation (no in S8), the reception function 133e returns to the process of S6.

When determining that the positioning completion operation by the user has been accepted (yes at S8), the acceptance function 133e notifies the imaging processing function 133a of the completion of the positioning.

In this case, the imaging processing function 133a captures a magnetic resonance image for diagnosis based on the imaging target region 70 determined by the determining function 133c (S9). In S8, when the user changes the slice direction, slice center, slice width, or amount of rotation in the in-plane direction of the imaging target region 70, the imaging processing function 133a captures a magnetic resonance image for diagnosis based on the changed imaging target region 70. Further, the function of receiving a change of the imaging target region 70 by the user may not be provided, and the imaging processing function 133a may directly use the imaging target region 70 determined by the determining function 133 c. When the function of accepting a change of the imaging target region 70 by the user is not provided, the image indicating the imaging target region 70 determined by the determination function 133c may not be displayed on the display 135. The imaging processing function 133a stores the imaged diagnostic magnetic resonance image in the storage circuit 132.

Then, the display control function 133d causes the display 135 to display the diagnostic magnetic resonance image imaged by the imaging processing function 133a (S10). Here, the processing of the flowchart ends.

As described above, the magnetic resonance imaging apparatus 100 according to the present embodiment detects at least one tissue of the femoral head, pelvis, labia, pubic symphysis, urethra, and prostatic apical part of the subject P from the magnetic resonance image 80 for positioning, and determines the imaging target region 70 in imaging the magnetic resonance image for diagnosis based on the detected tissue. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, since it is possible to reduce the number of trial and error operations for positioning performed by the user such as an engineer on the magnetic resonance image 80 for positioning, it is possible to reduce the workload of the positioning operation performed by the user at the time of MR imaging of the prostate.

In addition, according to the magnetic resonance imaging apparatus 100 of the present embodiment, since the reference of positioning is unified, even when MR imaging of the subject P is performed a plurality of times, imaging can be easily performed at the same position as in the previous imaging, as compared with the case where the user manually performs the positioning work. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, the reproducibility of positioning can be improved.

More specifically, the magnetic resonance imaging apparatus 100 according to the present embodiment determines at least one of a slice direction, a slice center, a slice width, and a rotation amount in an in-plane direction of an imaging cross section in imaging a two-dimensional magnetic resonance image for diagnosis. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, the workload of positioning by the user can be reduced with respect to at least one of the slice direction, the slice center, the slice width, and the amount of rotation in the in-plane direction of the imaging cross section.

The magnetic resonance imaging apparatus 100 of the present embodiment determines a direction perpendicular to a line segment 600 passing through the upper ends 60a and 60b of the 2 femoral heads of the subject P as a slice direction in imaging an axial image for diagnosis. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, it is possible to set a slice direction suitable for imaging an axial image for diagnosing the prostate.

The magnetic resonance imaging apparatus 100 according to the present embodiment determines the slice width in imaging the axial image for diagnosis based on the position of the 2 femoral heads and the position of pubic junction of the subject P. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, the slice width 701 suitable for imaging an axial image for diagnosing the prostate can be set.

The magnetic resonance imaging apparatus 100 of the present embodiment determines the amount of rotation in the in-plane direction of the imaging cross section of the imaging target region 70 in imaging the axial image for diagnosis based on the plurality of articular lips 62a to 62d of the subject P. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, it is possible to set the rotation amount in the in-plane direction of the imaging cross section suitable for imaging the axial image for diagnosis of the prostate.

The magnetic resonance imaging apparatus 100 of the present embodiment obtains a midpoint 63a of a line segment 621a connecting the joint lip 62a and the joint lip 62b facing each other in the width direction of the body of the subject P among the plurality of joint lips 62a to 62d of the subject P, and a midpoint 63b of a line segment 621b connecting the joint lip 62c and the joint lip 62 d. The magnetic resonance imaging apparatus 100 determines a direction perpendicular to a line segment 601 connecting the calculated 2 middle points 63a and 63b as a slice direction in imaging a sagittal image for diagnosis. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, it is possible to set a slice direction suitable for imaging a sagittal image for diagnosis of the prostate.

The magnetic resonance imaging apparatus 100 of the present embodiment determines the slice width 701 in imaging a sagittal image for diagnosis of the prostate based on the characteristic points 65a to 65d on the pelvis of the subject P. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, the slice width 701 suitable for imaging a sagittal image for diagnosis of the prostate can be set.

In the magnetic resonance imaging apparatus 100 according to the present embodiment, the slice center 702 in imaging a sagittal image for diagnosis of the prostate is determined to be a position passing through the center of the prostate of the subject P. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, the slice center 702 suitable for imaging a sagittal image for diagnosis of the prostate can be set.

In addition, the magnetic resonance imaging apparatus 100 according to the present embodiment corrects the position of the slice center 702 based on the detected position of the pubic symphysis when the slice center 702 determined based on the detected position of the prostate is separated from the detected position of the pubic symphysis by a predetermined distance or more. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, the slice center 702 suitable for imaging a sagittal image for diagnosis of the prostate can be set with higher accuracy.

The magnetic resonance imaging apparatus 100 of the present embodiment obtains a midpoint 63c of a line segment 621c connecting the joint lip 62a and the joint lip 62c facing each other along the front-rear direction of the body of the subject P, and a midpoint 63d of a line segment 621d connecting the joint lip 62b and the joint lip 62d, among the plurality of joint lips 62a to 62d of the subject P. The magnetic resonance imaging apparatus 100 determines a direction perpendicular to a line segment 602 connecting the calculated 2 middle points 63c and 63d as a slice direction in imaging of the diagnostic coronal image. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, it is possible to set a slice direction suitable for imaging a coronal image for diagnosis of the prostate.

The magnetic resonance imaging apparatus 100 according to the present embodiment determines the slice width 701 of the coronal image based on the position of pubic symphysis in the anterior-posterior direction of the body of the subject P. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, the slice width 701 suitable for imaging a coronal image for diagnosis of the prostate can be set.

The magnetic resonance imaging apparatus 100 according to the present embodiment takes a diagnostic magnetic resonance image based on the imaging target region 70 determined based on the tissue detected from the magnetic resonance image 80 for positioning. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, the imaging target region 70 suitable for imaging the prostate of the subject P can be imaged in the main imaging.

In the magnetic resonance imaging apparatus 100 according to the present embodiment, an image representing the imaging target region 70 determined based on the tissue detected from the magnetic resonance image 80 for positioning is displayed on the display 135. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, the user can confirm the result of the positioning performed automatically.

The magnetic resonance imaging apparatus 100 according to the present embodiment is configured to detect at least one tissue of the femoral head, pelvis, joint lip, pubic junction, urethra, and prostatic apical part of the subject P depicted in the magnetic resonance image 80 for localization by inputting the magnetic resonance image 80 for localization to the learned model 90. Therefore, according to the magnetic resonance imaging apparatus 100 of the present embodiment, these tissues drawn in the magnetic resonance image 80 for positioning can be detected with high accuracy.

The learned model 90 in the present embodiment is a "self-learning model" including an internal algorithm for further updating the learned model 90 by obtaining feedback of the estimation result from the user. For example, when the user changes the slice direction, the slice center, the slice width, or the amount of rotation in the in-plane direction of the imaging cross section, the learned model 90 may update the internal algorithm of the learned model 90 according to the change.

The learned model 90 may be generated by a device other than the magnetic resonance imaging device 100 and input to the magnetic resonance imaging device 100. The processing circuit 133 of the magnetic resonance imaging apparatus 100 may further include a learning function of generating the learned model 90.

The learned model 90 may be constructed by an integrated circuit such as ASIC or FPGA. Instead of the learned model 90, a mathematical expression model, a lookup table, a database, or the like may be applied.

The learned model 90 or template image used for the detection process may be stored in a storage device outside the magnetic resonance imaging apparatus 100.

(second embodiment)

In the first embodiment described above, the determination function 133c of the magnetic resonance imaging apparatus 100 performs the positioning based on the femoral head, pelvis, labrum, pubic symphysis, urethra, and prostatic apical part of the subject P detected from the magnetic resonance image 80 for positioning. In this second embodiment, the decision function 133c of the magnetic resonance imaging apparatus 100 is also positioned based on the urethra and the prostatic cusp.

The configuration of the magnetic resonance imaging apparatus 100 according to the present embodiment is the same as that of the first embodiment described with reference to fig. 1. The processing circuit 133 of the magnetic resonance imaging apparatus 100 according to the present embodiment includes an imaging processing function 133a, a detection function 133b, a determination function 133c, a display control function 133d, and a reception function 133e, as in the first embodiment. The image pickup processing function 133a, the display control function 133d, and the reception function 133e of the present embodiment have the same functions as those of the first embodiment.

The detection function 133b of the present embodiment detects the urethra and the prostatic apical part of the subject P from the magnetic resonance image 80 for positioning, in addition to the functions of the first embodiment.

The determination function 133c of the present embodiment determines the slice direction in imaging the axial image for diagnosis and the coronal image for diagnosis based on the urethra and the prostatic apical part of the subject P detected by the detection function 133b, in addition to the functions of the first embodiment.

Fig. 13 is a diagram showing an example of a method for determining the slice direction of the coronal image and the axial image according to the present embodiment. In fig. 13, a sagittal section of a magnetic resonance image 80 for localization is illustrated.

As shown in fig. 13, the determining function 133c obtains a line segment 603 connecting the urethral canal start position 66 and the prostatic cusp 67 of the subject P in the sagittal section of the magnetic resonance image 80 for positioning.

The determining function 133c determines a direction parallel to the line segment 603 as a slice direction in imaging of the axial image for diagnosis. The determining function 133c determines a direction perpendicular to the line segment 603 as a slice direction in imaging of the coronal image for diagnosis.

As described above, according to the magnetic resonance imaging apparatus 100 of the present embodiment, the slice direction in imaging the axial direction image for diagnosis and the coronal image for diagnosis is determined based on the urethra and the apical area of the prostate of the subject P, and thus, the slice position of the axial direction image for diagnosis and the coronal image for diagnosis suitable for diagnosis of the prostate can be further determined while the effects of the first embodiment are provided.

(modification example)

In the first and second embodiments described above, the magnetic resonance imaging apparatus 100 executes the positioning process, but a part or all of the positioning process may be executed by an apparatus other than the magnetic resonance imaging apparatus 100. For example, another information processing apparatus connected to the magnetic resonance imaging apparatus 100 via a network or the like may have the detection function 133b or the determination function 133 c.

In the first and second embodiments described above, the display control function 133d causes the display 135 to display an image representing the imaging target region 70, but may be displayed on another display connected to the magnetic resonance imaging apparatus 100 via a network or the like. In this case, the other display is an example of the display unit.

In the first and second embodiments described above, the learned model 90 is stored in the storage circuit 132, but the learned model 90 may be incorporated in the detection function 133 b.

According to at least one embodiment described above, the workload of the positioning operation by the user at the time of MR imaging of the prostate can be reduced.

Several embodiments have been described, but these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in other various manners, and various omissions, substitutions, changes, and combinations of the embodiments can be made without departing from the scope of the invention. These embodiments and modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and the equivalent scope thereof.

While several embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. Indeed, the novel embodiments described herein may be embodied in a variety of other forms; furthermore, various omissions, substitutions, and changes in the form of the embodiments described herein may be made without departing from the spirit of the invention. The appended claims and their equivalents are intended to cover such embodiments and modifications as fall within the true scope and spirit of the invention.