Medical Image Processing Apparatus and Medical Image Processing Program

Abstract

To support imaging at an imaging position corresponding to a position of an image acquired in the past.SOLUTION: A medical image processing device comprises: an extraction unit; a selection unit; and a determination unit. The extraction unit extracts landmarks from a reference image and a plurality of candidate images. The selection unit selects at least one candidate image from the plurality of candidate images on the basis of the similarity between the landmark of the reference image and the landmarks of the plurality of candidate images. The determination unit determines an imaging position where a medical image diagnostic device performs imaging on the basis of the at least one candidate image selected by the selection unit.SELECTED DRAWING: Figure 1

Description

Technical Field

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

[0002] Conventionally, in a follow-up examination performed by observing over time, changes in the observation target are examined. Therefore, a technique capable of acquiring an image at a position similar to the position of an image acquired in the past has been demanded.

[0003] Also, in a Magnetic Resonance Imaging (MRI) apparatus, for example, a technique for detecting an intervertebral disc and determining a position for acquiring a cross-sectional image is known.

[0004] However, in the conventional techniques exemplified, the intervertebral disc is detected, and it has not been possible to determine a position similar to the position of an image acquired in the past. Therefore, it has not been possible to acquire an image at a position corresponding to the position of an image acquired in the past.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to assist imaging at an imaging position corresponding to the position of an image acquired in the past. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problems. It is also possible to position, as other problems, the problems corresponding to the respective effects by each configuration shown in the embodiments described later.

Means for Solving the Problems

[0007] The medical image processing apparatus according to the embodiment includes an extraction unit, a selection unit, and a determination unit , an acquisition unit and and is provided with. The extraction unit extracts landmarks from a reference image and a plurality of candidate images. The selection unit selects at least one candidate image from the plurality of candidate images based on the similarity between the landmarks of the reference image and the landmarks of the plurality of candidate images. The determination unit determines an imaging position to be imaged by a medical image diagnostic apparatus based on at least one candidate image selected by the selection unit. wherein the similarity exceeds a threshold value If there is no candidate image with the similarity exceeding the threshold value, the acquisition unit acquires a plurality of the candidate images generated under different conditions. Then, the extraction unit extracts the landmark from the plurality of candidate images generated under different conditions acquired by the acquisition unit. The selection unit selects at least one candidate image from the plurality of candidate images based on the similarity between the landmark of the reference image and the landmark of each of the plurality of candidate images generated under different conditions. The determination unit determines the imaging position based on at least one candidate image selected by the selection unit.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Mode for Carrying Out the Invention

[0009] Hereinafter, with reference to the drawings, a medical image processing apparatus and a medical image processing program according to the present embodiment will be described. In the following embodiments, portions denoted by the same reference numerals perform the same operations, and duplicate descriptions will be omitted as appropriate.

[0010] (This Embodiment) FIG. 1 is a block diagram showing an example of the configuration of a magnetic resonance imaging apparatus 10 according to the present embodiment. The magnetic resonance imaging apparatus 10 includes a static magnetic field magnet 101, a static magnetic field power supply (not shown), a gradient magnetic field coil 103, a gradient magnetic field 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.

[0011] The X-axis, Y-axis, and Z-axis shown in FIG. 1 constitute a device coordinate system unique to the magnetic resonance imaging apparatus 10. For example, the Z-axis direction coincides with the axial direction of the cylinder of the gradient magnetic field coil 103 and is set along the magnetic flux of the static magnetic field generated by the static magnetic field magnet 101. Also, the Z-axis direction is the same as the longitudinal direction of the couch 105 and is also the same as the head-tail direction of the subject P placed on the couch 105. Further, the X-axis direction is set along the horizontal direction orthogonal to the Z-axis direction. The Y-axis direction is set along the vertical direction orthogonal to the Z-axis direction.

[0012] Note that the configuration shown in FIG. 1 is merely an example. For example, each part in the sequence control circuit 120 and the computer system 130 may be appropriately integrated or separated. Note that the subject P (for example, a human body) is not included in the magnetic resonance imaging apparatus 10.

[0013] The static magnetic field magnet 101 is a magnet formed in a hollow substantially cylindrical shape and generates a static magnetic field in the internal space. The static magnetic field magnet 101 is, for example, a superconducting magnet or the like and is excited by receiving a current supply from a static magnetic field power source. The static magnetic field power source 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 10 may not include a static magnetic field power source. Also, the static magnetic field power source may be provided separately from the magnetic resonance imaging apparatus 10.

[0014] The gradient magnetic field coil 103 is a coil formed in a hollow substantially cylindrical shape and is disposed inside the static magnetic field magnet 101. The gradient magnetic field coil 103 is formed by combining three coils corresponding to the X, Y, and Z axes orthogonal to each other, and these three coils receive individual current supplies from the gradient magnetic field power source 104 to generate a gradient magnetic field in which the magnetic field strength changes along the X, Y, and Z axes. Also, the gradient magnetic field power source 104 supplies a current to the gradient magnetic field coil 103 under the control of the sequence control circuit 120.

[0015] The examination table 105 is provided with a top plate 105a on which the subject P is placed, and under the control of the examination table control circuit 106, the top plate 105a is inserted into the imaging oral cavity with the subject P such as a patient placed thereon. The examination table control circuit 106 drives the examination table 105 to move the top plate 105a in the longitudinal direction and the vertical direction under the control of the computer system 130.

[0016] The transmission coil 107 excites an arbitrary region of the subject P by applying a high-frequency magnetic field. The transmission coil 107 is, for example, a whole body type coil that surrounds the entire body of the subject P. The transmission coil 107 receives the supply of RF pulses from the transmission circuit 108, generates a high-frequency magnetic field, and applies the high-frequency magnetic field to the subject P. The transmission circuit 108 supplies RF pulses to the transmission coil 107 under the control of the sequence control circuit 120.

[0017] The reception coil 109 is disposed inside the gradient magnetic field 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 high-frequency magnetic field. When the reception coil 109 receives the MR signal, the received MR signal is output to the reception circuit 110.

[0018] In FIG. 1, the reception coil 109 is provided separately from the transmission coil 107, but this is an example and is not limited to this configuration. For example, a configuration in which the reception coil 109 is also used as the transmission coil 107 may be adopted.

[0019] The reception circuit 110 performs analog-digital (AD) conversion on the analog MR signal output from the reception coil 109 to generate MR data. Further, the reception circuit 110 transmits the generated MR data to the sequence control circuit 120. Regarding the AD conversion, it may be performed within the reception coil 109. Further, the reception circuit 110 can perform arbitrary signal processing other than the AD conversion.

[0020] The sequence control circuit 120 performs imaging of the subject P by driving 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. The sequence information is information that defines the procedure for performing imaging. The sequence information includes, for example, the strength of the current supplied by the gradient magnetic field power supply 104 to the gradient magnetic field coil 103 and the timing of supplying the current, the strength of the RF pulse supplied by the transmission circuit 108 to the transmission coil 107 and the timing of applying the RF pulse, the timing at which the reception circuit 110 detects the MR signal, and the like. The sequence control circuit 120 may be realized by a processor, or may be realized by a combination of software and hardware.

[0021] When the sequence control circuit 120 drives the gradient magnetic field power supply 104, the transmission circuit 108, and the reception circuit 110 to image the subject P and receives MR data from the reception circuit 110, the received MR data is transferred to the computer system 130.

[0022] The computer system 130 performs overall control of the magnetic resonance imaging apparatus 10 and generation of MR images. As shown in FIG. 1, the computer system 130 includes a NW (network) interface 131, a storage circuit 132, an input interface 133, a display 134, and a processing circuit 135. For example, the computer system 130 is a computer.

[0023] The NW interface 131 communicates with the sequence control circuit 120 and the bed control circuit 106. For example, the NW interface 131 transmits sequence information to the sequence control circuit 120. Also, the NW interface 131 receives MR data from the sequence control circuit 120.

[0024] The memory circuit 132 stores MR data received by the NW interface 131, k-space data arranged in k-space by the processing circuit 135 described later, image data generated by the processing circuit 135, and the like. The memory circuit 132 is, for example, a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, a hard disk, or an optical disk.

[0025] The input interface 133 receives various instructions and information inputs from the operator. The input interface 133 is realized, for example, by a trackball, a switch button, a mouse, a keyboard, a touch pad that performs an input operation by touching the operation surface, a touch screen in which the display screen and the touch pad are integrated, a non-contact input circuit using an optical sensor, and an audio input circuit. The input interface 133 is connected to the processing circuit 135, converts the input operation received from the operator into an electrical signal, and outputs it to the processing circuit 135. Note that in this specification, the input interface 133 is not limited to those having physical operation components such as a mouse and a keyboard. For example, an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the computer system 130 and outputs this electrical signal to the control circuit is also included in the example of the input interface 133.

[0026] Under the control of the processing circuit 135, the display 134 displays a GUI (Graphical User Interface) for receiving input of imaging conditions and magnetic resonance images generated by the processing circuit 135. The display 134 is, for example, a display device such as a liquid crystal display.

[0027] The processing circuit 135 controls the operation of the entire magnetic resonance imaging apparatus 10. The processing circuit 135 has, for example, a reference image acquisition function 135a, a candidate image acquisition function 135b, a landmark extraction function 135c, a similarity calculation function 135d, a matching image selection function 135e, and a setting function 135f. In the embodiment, each processing function performed by the reference image acquisition function 135a, the candidate image acquisition function 135b, the landmark extraction function 135c, the similarity calculation function 135d, the matching image selection function 135e, and the setting function 135f is stored in the storage circuit 132 in the form of a program executable by a computer. The processing circuit 135 is a processor that reads out and executes the program from the storage circuit 132 to realize the functions corresponding to the respective programs. In other words, the processing circuit 135 in the state of having read out each program will have each function shown in the processing circuit 135 of FIG. 1. The program is an example of a medical image processing program.

[0028] In FIG. 1, it has been described that the reference image acquisition function 135a, the candidate image acquisition function 135b, the landmark extraction function 135c, the similarity calculation function 135d, the matching image selection function 135e, and the setting function 135f are realized by a single processor. However, it is also possible to configure the processing circuit 135 by combining a plurality of independent processors, and each processor realizes the function by executing a program. Further, in FIG. 1, it has been described that a single storage circuit such as the storage circuit 132 stores the programs corresponding to the respective processing functions. However, it is also possible to arrange a plurality of storage circuits in a distributed manner, and the processing circuit 135 reads out the corresponding program from an individual storage circuit.

[0029] The term "processor" used in the above description means, for example, a CPU (Central Processing Unit), a GPU (Graphical Processing Unit), or a circuit such as an application specific integrated circuit (ASIC), a programmable logic device (for example, a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)). The processor realizes its functions by reading and executing the program stored in the storage circuit 132. Instead of storing the program in the storage circuit 132, it may be configured to directly incorporate the program into the circuit of the processor. In this case, the processor realizes its functions by reading and executing the program incorporated into the circuit.

[0030] Here, an overview of the computer system 130 will be described. FIG. 2 is a diagram showing an example of an overview of the processing executed by the computer system 130 according to the present embodiment.

[0031] The computer system 130 extracts landmarks, which are characteristic regions of an image, from each of a reference image captured in the past and a plurality of candidate images captured by pilot scanning. Further, the computer system 130 calculates the degree of similarity between the landmarks of the reference image and the landmarks of the candidate images. This is executed by the computer system 130 for each of the landmarks of the plurality of candidate images. The plurality of candidate images are, for example, a plurality of images having different slice positions from each other.

[0032] The computer system 130 selects at least one candidate image as a matching image captured at an imaging position that matches the imaging position of the reference image based on the similarity between the landmarks of the reference image and the landmarks of the plurality of candidate images. Then, the computer system 130 applies the settings for capturing the matching image to the imaging plan for capturing the MR image. In other words, the computer system 130 applies to the sequence information to capture an image at the imaging position specified by the matching image. Thereby, the magnetic resonance imaging apparatus 10 executes imaging at the imaging position corresponding to the reference image.

[0033] Next, the functions of the computer system 130 will be described in detail.

[0034] The reference image acquisition function 135a acquires a reference image. The reference image is a reference image and is an image captured in the past. For example, the reference image acquisition function 135a acquires an MR image captured in the past. The computer system 130 extracts candidate images captured at imaging positions corresponding to the imaging position of the reference image.

[0035] The candidate image acquisition function 135b acquires candidate images. The candidate images are images to be compared and are candidate images for the matching image captured at the imaging position corresponding to the reference image. For example, the candidate images are images captured by a pilot scan. The pilot scan is, for example, a scan for acquiring a low-resolution MR image to determine the imaging region, a scan for acquiring sensitivity information of the receiving coil 109, a scan for acquiring information for correcting the non-uniformity of the MR image, and the like. Also, the matching image is at least one candidate image selected from a plurality of candidate images.

[0036] Also, it is common for the candidate image to be an image including the same subject P as the subject P included in the reference image. However, the candidate image may not include the same subject P as the subject P included in the reference image. For example, the reference image or the candidate image may be an image of a pseudo subject.

[0037] Further, when the reference image and the candidate image are MR images, they may be images with different objects to be emphasized. That is, the reference image and the candidate image may have different image types. For example, either the reference image or the candidate image may be a T1-weighted image, and the other may be a T2-weighted image.

[0038] Further, the candidate image is not limited to the captured image, and may be an image formed by calculation from any candidate image. Note that the computer system 130 may use k-space data without using an image, and may compare landmarks extracted from the k-space data using various known methods with the k-space data serving as the basis of the reference image and the k-space data serving as the basis of the candidate image. Further, the computer system 130 may compare the reference image and the candidate image from which the landmarks are extracted after returning them to the k-space data.

[0039] Further, one of the reference image and the candidate image may be a high-resolution image with high resolution, and the other may be a low-resolution image with low resolution. In this case, the reference image acquisition function 135a or the candidate image acquisition function 135b may perform image processing for converting the low-resolution image into a high-resolution image. Alternatively, the reference image acquisition function 135a or the candidate image acquisition function 135b may perform image processing for converting the high-resolution image into a low-resolution image. Then, the computer system 130 may perform extraction of landmarks, calculation of similarity, and selection of a matching image on the image subjected to the image processing. When the computer system 130 converts the image into a low-resolution image, the processing time required for extraction of landmarks, calculation of similarity, and selection of a matching image can be shortened.

[0040] Further, the computer system 130 may generate a low-resolution image from a high-resolution image by an algorithm of machine learning such as CycleGAN (Generative Adversarial Network). Furthermore, the reference image and the candidate image are not limited to images with high or low resolution, and may be images with high or low contrast. Also in this case, the computer system 130 may convert the high or low contrast by image processing.

[0041] The landmark extraction function 135c extracts landmarks from a reference image and a plurality of candidate images. The landmark extraction function 135c is an example of an extraction unit. More specifically, the landmark extraction function 135c extracts landmarks from a reference image which is an MR image captured in the past and a candidate image which is a pilot image captured at a low resolution to determine an imaging region. A landmark is a characteristic region included in the reference image and the candidate images. For example, a landmark may be an anatomical feature point or a characteristic pattern such as a fold of the brain. Note that the landmark extraction function 135c may extract landmarks from an arbitrary cross-section or may extract landmarks from a three-dimensional volume.

[0042] Here, compared with normal structures, a tumor is likely to change in shape and size over time. For example, a tumor may not be similar even if it is the same tumor when compared after a certain period has elapsed. Therefore, the landmark extraction function 135c extracts landmarks from regions other than regions of abnormal structures such as tumors. That is, the landmark extraction function 135c extracts landmarks from regions outside the region of interest. The region of interest is a region that medical staff such as doctors focus on in follow-up observations. For example, the region of interest is a region where there is an abnormal structure such as a tumor.

[0043] For example, the landmark extraction function 135c compares a database that has collected normal examples of the main structures of the target site with each structure extracted from the reference image to identify normal regions. Then, the landmark extraction function 135c extracts landmarks from the normal regions. Thereby, the landmark extraction function 135c extracts landmarks from regions outside the region of interest.

[0044] The similarity calculation function 135d calculates the similarity between the landmarks extracted from the reference image and each of the landmarks extracted from a plurality of candidate images. The similarity is the degree to which the landmarks extracted from the reference image and the landmarks extracted from the candidate image are similar.

[0045] More specifically, the similarity calculation function 135d extracts a first feature amount indicating the shape and size of the landmark extracted from the reference image. Also, the similarity calculation function 135d extracts a second feature amount indicating the shape and size of the landmark extracted from the candidate image. Then, the similarity calculation function 135d calculates the similarity by comparing the first feature amount and the second feature amount. Further, the similarity calculation function 135d executes the same process for each landmark extracted from a plurality of candidate images. Thereby, the similarity calculation function 135d calculates the similarity for each landmark extracted from each of the plurality of candidate images.

[0046] The matching image selection function 135e selects at least one candidate image from the plurality of candidate images based on the similarity between the landmarks of the reference image and the landmarks of the plurality of candidate images. The matching image selection function 135e is an example of a selection unit. More specifically, the matching image selection function 135e selects a matching image captured at an imaging position that matches the imaging position of the reference image based on the similarity between the landmarks of the reference image and the landmarks of the plurality of candidate images. For example, the matching image selection function 135e selects a candidate image with a similarity of 95 percent or more as the matching image.

[0047] Here, there may be a case where a plurality of candidate images with a similarity exceeding the threshold are detected. In this case, the compatible image selection function 135e selects the candidate image with the highest similarity as the compatible image. For example, the compatible image selection function 135e converts the first feature amount extracted from the landmark extraction of the reference image into vector information. Also, the compatible image selection function 135e converts the second feature amount extracted from the landmarks of the candidate image into vector information. Further, the compatible image selection function 135e calculates the similarity based on the cosine similarity between the vector information converted from the first feature amount and the vector information converted from the second feature amount. Then, the compatible image selection function 135e selects the candidate image with the second feature amount having the highest similarity as the compatible image.

[0048] The compatible image selection function 135e may select a compatible image using a pre-trained model such as a CNN (Convolutional Neural Network). For example, the compatible image selection function 135e may select a compatible image using a pre-trained model that converts the landmarks of the reference image and the candidate image into vector information and calculates the similarity based on the cosine similarity.

[0049] Also, there may be a case where no candidate image with a similarity exceeding the threshold is detected. When there is no candidate image with a similarity exceeding the threshold, the candidate image acquisition function 135b acquires a plurality of candidate images generated under different conditions. For example, the candidate image acquisition function 135b acquires candidate images generated under conditions where the values of parameters related to image quality such as TE, TR, or resolution are different. The candidate image acquisition function 135b is an example of an acquisition unit. The landmark extraction function 135c extracts landmarks from a plurality of candidate images generated under different conditions acquired by the candidate image acquisition function 135b. The similarity calculation function 135d calculates the similarity between the landmarks extracted from the reference image and the landmarks of each of the plurality of candidate images generated under different conditions. Then, the compatible image selection function 135e selects at least one candidate image from the plurality of candidate images based on the similarity between the landmarks of the reference image and the landmarks of the plurality of candidate images generated under different conditions.

[0050] The computer system 130 repeatedly executes the above-described compatible image selection process until a candidate image with a similarity exceeding the threshold is detected. Thereby, the computer system 130 selects a candidate image whose similarity exceeds the threshold.

[0051] Also, when repeatedly executing the compatible image selection process, the computer system 130 may receive an input specifying the conditions for generating candidate images. In this case, the computer system 130 may receive an input specifying conditions from the user each time, or may receive an input specifying a plurality of conditions collectively.

[0052] Also, when repeatedly executing the compatible image selection process, the computer system 130 may limit the range for searching for compatible images. That is, the computer system 130 may limit the candidate images to be searched among a plurality of candidate images. Specifically, the computer system 130 may limit the search range in the slice direction for searching for a compatible image. For example, the computer system 130 designates the search range based on the similarity. The landmark extraction function 135c extracts landmarks from a plurality of candidate images within the search range determined based on the similarity. The similarity calculation function 135d calculates the similarity between the landmarks extracted from the reference image and each of the landmarks extracted from the plurality of candidate images in the search range. The compatible image selection function 135e selects at least one candidate image from the plurality of candidate images based on the similarity between the landmarks of the reference image and the landmarks of the plurality of candidate images within the search range. That is, the compatible image selection function 135e selects a compatible image based on the similarity. In this way, the computer system 130 can reduce the time required for searching for a compatible image by limiting the range for searching for a compatible image.

[0053] In addition, when the computer system 130 designates a specific range as the search range from candidate images with high similarity, the specific range may be a fixed range or a calculated range. For example, the computer system 130 mathematically expresses the landmark extraction method and the similarity calculation method using a cost function. Then, the computer system 130 may calculate the search range by performing particle swarm optimization with the parameter to be changed as the slice direction. For example, the computer system 130 may align the reference image and a plurality of candidate images and limit the search range based on the position of the most similar candidate image. The computer system 130 may narrow the search range as the similarity increases. That is, the landmark extraction function 135c extracts landmarks from a plurality of candidate images within a search range that narrows as the similarity increases. The landmark extraction function 135c can extract landmarks with less processing time as the search range is narrowed. In addition, the computer system 130 may determine the search range for a plurality of cross-sections acquired in advance, or may determine the search range for a three-dimensional volume and cut out a cross-section of the determined range.

[0054] The setting function 135f determines the imaging position imaged by a medical imaging device such as the magnetic resonance imaging device 10 based on at least one candidate image selected by the compatible image selection function 135e. The setting function 135f is an example of a determination unit. In other words, the setting function 135f applies to the sequence information so as to image the image at the imaging position specified by the compatible image selected by the compatible image selection function 135e.

[0055] More specifically, the setting function 135f extracts the settings at the time of imaging for the compatible image selected by the compatible image selection function 135e. Then, the setting function 135f reflects the settings at the time of imaging the compatible image in the settings of the MR image. Thereby, the setting function 135f sets the conditions for imaging at the imaging position of the compatible image.

[0056] Next, various processes executed by the computer system 130 will be described.

[0057] FIG. 3 is a flowchart showing an example of the imaging position determination process executed by the computer system 130 according to the present embodiment. The imaging position determination process is a process of determining the imaging position to be imaged by the magnetic resonance imaging apparatus 10 based on the landmarks of the reference image.

[0058] The reference image acquisition function 135a acquires a reference image that is an MR image captured in the past (step S1).

[0059] The candidate image acquisition function 135b acquires a plurality of candidate images that are MR images captured by pilot scanning (step S2).

[0060] The landmark extraction function 135c extracts landmarks from each of the reference image and the plurality of candidate images (step S3).

[0061] The similarity calculation function 135d calculates the similarity between the landmarks of the reference image and the landmarks of each of the plurality of candidate images for each of the plurality of candidate images (step S4).

[0062] The matching image selection function 135e determines whether there is a candidate image with a similarity exceeding a threshold value (step S5).

[0063] When there is no candidate image with a similarity exceeding the threshold value (step S5; No), the matching image selection function 135e acquires a candidate image captured under conditions different from the candidate images in step S2 (step S6).

[0064] When there is a candidate image with a similarity exceeding the threshold value (step S5; Yes), the matching image selection function 135e selects a matching image based on the similarity between the landmarks of the reference image and the landmarks of each of the plurality of candidate images (step S7). That is, the matching image selection function 135e selects a candidate image with a similarity exceeding the threshold value as the matching image.

[0065] The setting function 135f applies the setting for imaging the imaging position specified by the matching image to the plan for imaging the MR image of the subject P (step S8). More specifically, the setting function 135f extracts, for example, landmarks or other features from the matching image and determines the imaging position based on the extracted landmarks or features. That is, the setting function 135f applies the setting for imaging the imaging position specified by the matching image to the sequence information.

[0066] As described above, the computer system 130 ends the imaging position determination process.

[0067] As described above, the computer system 130 according to the present embodiment extracts landmarks from the reference image and the plurality of candidate images. Further, the computer system 130 selects a matching image from the plurality of candidate images based on the similarity between the landmarks of the reference image and the landmarks of the plurality of candidate images. The computer system 130 determines the imaging position to be imaged by the magnetic resonance imaging apparatus 10 based on the matching image. Therefore, the computer system 130 can assist imaging at the imaging position corresponding to the position of the image acquired in the past. Thereby, the magnetic resonance imaging apparatus 10 can acquire an MR image of the imaging position corresponding to the position of the image acquired in the past. Therefore, the computer system 130 can improve the diagnostic accuracy when performing high-precision image overlay in follow-up observation, diagnosis using fusion images, etc.

[0068] (Modification 1) In the present embodiment, it has been described that the reference image acquisition function 135a acquires a reference image such as an MR image imaged in the past. However, as long as the reference image acquisition function 135a can extract landmarks, it is not limited to MR images, and it may acquire a CT image imaged by an X-ray CT apparatus as a reference image, or may acquire a PET (Positron Emission computed Tomography) image imaged by a PET apparatus as a reference image, or may acquire an image imaged by other apparatuses as a reference image.

[0069] Furthermore, when the reference image acquisition function 135a acquires an image captured by a device other than the magnetic resonance imaging apparatus 10, it may acquire the image subjected to image processing as a reference image. Similarly, when the candidate image acquisition function 135b acquires an image captured by a device other than the magnetic resonance imaging apparatus 10, it may acquire a plurality of images subjected to image processing as a plurality of candidate images. In this case, the landmark extraction function 135c extracts landmarks from the reference image and the plurality of candidate images, at least one of which has been subjected to image processing. The conforming image selection function 135e selects a conforming image based on the similarity between the landmarks of the reference image and the landmarks of the plurality of candidate images. Then, the setting function 135f determines the imaging position at which the magnetic resonance imaging apparatus 10 captures an image based on the conforming image selected by the conforming image selection function 135e. For example, the candidate image acquisition function 135b may acquire a PET image obtained by an integrated PET / MRI apparatus as a candidate image.

[0070] (Modification 2) The computer system 130 may display an image of a camera provided on the ceiling of the room in which the magnetic resonance imaging apparatus 10 is arranged on the display 134 or the like. Here, if the posture of the subject P when the reference image is captured is significantly different from the posture of the subject P when the candidate image is captured, the computer system 130 cannot select a conforming image. Therefore, the computer system 130 displays the image of the posture of the subject P when the reference image is captured by the camera and the image of the posture of the subject P when the candidate image is captured by the camera. As a result, medical staff such as technicians can recognize the difference in postures and thus can correct the posture of the subject P.

[0071] (Modification 3) The computer system 130 may not be able to select a matching image when the similarity between the landmarks of the reference image and the landmarks of the candidate image is low. In such a case, the landmark extraction function 135c may transform the coordinates indicating the positions of the landmarks by affine transformation. That is, the landmark extraction function 135c may newly extract landmarks by transforming the coordinates indicating the positions of the landmarks of the candidate image.

[0072] Specifically, the landmark extraction function 135c may perform translation, enlargement, reduction, rotation, or shear on the landmarks of the candidate image. The similarity calculation function 135d calculates the similarity between the landmarks of the reference image and the landmarks whose coordinates have been changed by affine transformation. Then, the matching image selection function 135e selects at least one candidate image based on the similarity between the landmarks of the reference image and the newly extracted landmarks from the candidate image. That is, the matching image selection function 135e selects a matching image. In this way, the landmark extraction function 135c makes it easier to extract landmarks whose similarity exceeds the threshold by transforming the coordinates of the landmarks. That is, the computer system 130 can select a matching image in a shorter time. Note that the computer system 130 may reflect the result of the affine transformation in the shooting position. Also, instead of reflecting the affine transformation in the shooting position, the computer system 130 may perform an image deformation process corresponding to the affine transformation on the matching image to generate a new matching image.

[0073] (Modification Example 4) Also, the computer system 130 has been described as being provided in the magnetic resonance imaging apparatus 10. However, the computer system 130 may be a device separate from the magnetic resonance imaging apparatus 10. For example, the computer system 130 may be an information processing device such as a personal computer or a server device. In this case, the reference image acquisition function 135a and the candidate image acquisition function 135b acquire a reference image and a plurality of candidate images from a medical image diagnostic device such as the magnetic resonance imaging apparatus 10. Also, the setting function 135f transmits the imaging position determined based on at least one candidate image selected by the conforming image selection function 135e to the medical image diagnostic device. Alternatively, the setting function 135f transmits the sequence information for imaging the image at the determined imaging position to the medical image diagnostic device.

[0074] According to at least one embodiment or the like described above, it is possible to assist imaging at an imaging position corresponding to the position of an image acquired in the past.

[0075] Although several embodiments have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, changes, and combinations of embodiments can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, as well as in the invention described in the claims and its equivalent scope.

Description of Reference Numerals

[0076] 10 Magnetic Resonance Imaging Apparatus 101 Static Magnetic Field Magnet 103 Gradient Magnetic Field Coil 104 Gradient Magnetic Field Power Supply 105 Bed 105a Top Plate 106 Bed Control Circuit 107 Transmission Coil 108 Transmission Circuit 109 Reception Coil 110 Reception Circuit 120 Sequence control circuit 130 Computer system 131 NW (Network) interface 132 Memory circuit 133 Input interface 134 Display 135 Processing circuit 135a Reference image acquisition function 135b Candidate image acquisition function 135c Landmark extraction function 135d Similarity calculation function 135e Conforming image selection function 135f Setting function P Subject

Claims

1. An extraction unit that extracts landmarks from a reference image and a plurality of candidate images, A selection unit that selects at least one of the candidate images whose similarity exceeds a threshold from the plurality of candidate images based on the similarity between the landmark of the reference image and the landmarks of the plurality of candidate images, A determination unit that determines an imaging position to be imaged by a medical imaging diagnostic apparatus based on at least one candidate image selected by the selection unit, An acquisition unit that acquires a plurality of candidate images generated under different conditions when there is no candidate image with a similarity exceeding the threshold, Comprising, The extraction unit extracts the landmark from a plurality of candidate images generated under different conditions acquired by the acquisition unit, The selection unit selects at least one candidate image from the plurality of candidate images based on the similarity between the landmark of the reference image and the landmarks of each of the plurality of candidate images generated under different conditions, The determination unit determines the imaging position based on at least one candidate image selected by the selection unit, A medical image processing apparatus.

2. The extraction unit extracts the landmark from an area other than the region of interest included in the reference image and the candidate image, The medical image processing apparatus according to Claim 1.

3. The region of interest is a tumor, The medical image processing apparatus according to Claim 2.

4. The acquisition unit acquires a plurality of candidate images generated under the different conditions with values of parameters related to imaging, The medical image processing apparatus according to any one of Claims 1 to 3.

5. The extraction unit extracts the landmark from a plurality of candidate images within a search range determined based on the similarity, The selection unit selects at least one candidate image from the plurality of candidate images based on the similarity between the landmark of the reference image and the landmarks of the plurality of candidate images within the search range, The medical image processing apparatus according to any one of Claims 1 to 4.

6. The extraction unit extracts the landmark from a plurality of candidate images within a search range that narrows as the similarity increases, The medical image processing apparatus according to Claim 5.

7. The extraction unit newly extracts a landmark by converting coordinates indicating each position of the landmark of the candidate image, The selection unit selects at least one of the candidate images based on the similarity between the landmark of the reference image and the landmark newly extracted from the candidate image. The medical image processing apparatus according to any one of claims 1 to 6.

8. The extraction unit extracts the landmark from the reference image subjected to image processing on at least one of them and a plurality of the candidate images. The medical image processing apparatus according to any one of claims 1 to 7.

9. The extraction unit extracts the landmark from the reference image which is an MR image captured in the past and the candidate image which is a pilot image captured at a low resolution to determine the imaging region. The medical image processing apparatus according to any one of claims 1 to 8.

10. On a computer, extract a landmark from a reference image and a plurality of candidate images, select at least one of the candidate images whose similarity exceeds a threshold from the plurality of candidate images based on the similarity between the landmark of the reference image and the landmarks of the plurality of candidate images, determine the imaging position to be imaged by the medical image diagnostic apparatus based on at least one of the selected candidate images, when there is no candidate image with the similarity exceeding the threshold, acquire a plurality of the candidate images generated under different conditions, to realize, extract the landmark from the plurality of candidate images generated under different conditions acquired, select at least one of the candidate images from the plurality of candidate images based on the similarity between the landmark of the reference image and each of the landmarks of the plurality of candidate images generated under different conditions, determine the imaging position based on at least one of the selected candidate images, A medical image processing program.

Images