JP7246864B2 - Image processing device, magnetic resonance imaging device and image processing program - Google Patents

Description

TECHNICAL FIELD Embodiments of the present invention relate to an image processing apparatus, a magnetic resonance imaging apparatus, and an image processing program.

Conventionally, a technique is known in which an MR image captured by a magnetic resonance imaging (MRI) apparatus and arbitrary parameter values are used to computationally generate a calculated image of an arbitrary image type after imaging. there is The technique of generating a calculated image in this way can perform an inspection in a shorter time than when generating an image while actually collecting data, and it is possible to set parameter values after the fact. There is an advantage.

JP 2013-192057 A JP 2016-225862 A

A problem to be solved by the present invention is to provide an image processing apparatus, a magnetic resonance imaging apparatus, and an image processing program capable of obtaining a calculated image suitable for diagnosis.

An image processing apparatus according to an embodiment includes an acquisition unit, a division unit, a setting unit, and a generation unit. The acquisition unit acquires an MR image of the brain captured by the magnetic resonance imaging apparatus. The division unit divides the brain region in the MR image acquired by the acquisition unit into a plurality of regions. The setting unit sets the parameter values used to generate the calculated image so that the contrast relationship between the regions included in the plurality of regions in the calculated brain image generated by synthetic MRI is a predetermined relationship. set. A generation unit generates the calculated image by the synthetic MRI using the MR image acquired by the acquisition unit and the parameter values set by the setting unit.

FIG. 1 is a diagram illustrating a configuration example of an image processing apparatus according to the first embodiment. FIG. 2 is a diagram showing an example of a plurality of brain regions according to the first embodiment. 3 is a diagram illustrating an example of a contrast ratio table stored by a storage circuit according to the first embodiment; FIG. 4 is a diagram illustrating an example of a parameter range table stored by a storage circuit according to the first embodiment; FIG. FIG. 5 is a diagram showing a specific example of a calculated image generated by the image processing apparatus according to the first embodiment. FIG. 6 is a diagram showing a specific example of a calculated image generated by the image processing apparatus according to the first embodiment. FIG. 7 is a flowchart illustrating a processing procedure for generating a calculated image performed by the image processing apparatus according to the first embodiment. FIG. 8 is a diagram showing an example of the effects of the first embodiment. FIG. 9 is a diagram showing a configuration example of an image processing apparatus according to the second embodiment. FIG. 10 is a diagram showing an example of a disease-related region table stored by a storage circuit according to the second embodiment. FIG. 11 is a flowchart showing a processing procedure for updating a disease-related region table performed by the image processing apparatus according to the second embodiment. FIG. 12 is a flow chart showing a processing procedure for generating a calculated image performed by the image processing apparatus according to the second embodiment. FIG. 13 is a diagram showing a configuration example of an MRI apparatus according to the third embodiment. FIG. 14 is a diagram showing a configuration example of an MRI apparatus according to the fourth embodiment.

Hereinafter, an image processing apparatus, a magnetic resonance imaging apparatus, and an image processing program according to embodiments will be described in detail with reference to the drawings.

(First embodiment)
FIG. 1 is a diagram illustrating a configuration example of an image processing apparatus according to the first embodiment. For example, as shown in FIG. 1, in this embodiment, an MRI apparatus 100, an image storage apparatus 200, and an image processing apparatus 300 are connected via a network 400 so as to be communicable.

The MRI apparatus 100 acquires image data of a subject using magnetic resonance phenomena. Specifically, the MRI apparatus 100 acquires magnetic resonance data from a subject by executing various imaging sequences based on imaging conditions set by an operator. The MRI apparatus 100 generates two-dimensional or three-dimensional image data (MR image) by performing image processing such as Fourier transform processing on the collected magnetic resonance data.

The image storage device 200 stores image data acquired by the MRI apparatus 100 . Specifically, the image storage apparatus 200 acquires image data from the MRI apparatus 100 via the network 400 and stores the acquired image data in a storage circuit provided inside or outside the apparatus. For example, the image storage device 200 is realized by computer equipment such as a server device.

The image processing device 300 processes image data acquired by the MRI device 100 . Specifically, the image processing apparatus 300 acquires image data from the MRI apparatus 100 or the image storage apparatus 200 via the network 400 and stores it in a storage circuit provided inside or outside the apparatus. The image processing apparatus 300 also performs various image processing on the acquired image data, and displays the image data before or after the image processing on a display or the like. For example, the image processing apparatus 300 is implemented by computer equipment such as a workstation.

Specifically, the image processing apparatus 300 includes a network (NW) interface 310 , a storage circuit 320 , an input interface 330 , a display 340 and a processing circuit 350 .

The NW interface 310 controls transmission and communication of various data exchanged between the image processing apparatus 300 and another apparatus connected via the network 400 . Specifically, the NW interface 310 is connected to the processing circuit 350, converts the image data output from the processing circuit 350 into a format conforming to a predetermined communication protocol, and transmits the data to the MRI apparatus 100 or the image storage apparatus 200. . The NW interface 310 also outputs image data received from the MRI apparatus 100 or the image storage apparatus 200 to the processing circuit 350 . For example, the NW interface 310 is implemented by a network card, network adapter, NIC (Network Interface Controller), or the like.

The storage circuit 320 stores various data. Specifically, the storage circuit 320 is connected to the processing circuit 350 and stores input image data according to a command sent from the processing circuit 350, or transfers the stored image data to the processing circuit 350. Output. For example, the storage circuit 320 is implemented by a semiconductor memory device such as a RAM (Random Access Memory) or flash memory, a hard disk, an optical disk, or the like.

The input interface 330 receives input operations of various instructions and various information from the operator. Specifically, the input interface 330 is connected to the processing circuit 350, converts an input operation received from the operator into an electrical signal, and outputs the electrical signal to the control circuit. For example, the input interface 330 includes a trackball for setting a region of interest (ROI), a switch button, a mouse, a keyboard, a touch pad for performing an input operation by touching an operation surface, a display screen and a touch panel. It is realized by a touch screen integrated with a pad, a non-contact input interface using an optical sensor, a voice input interface, or the like. In this specification, the input interface 330 is not limited to having physical operation parts such as a mouse and a keyboard. For example, the input interface 330 also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs the electrical signal to the control circuit.

The display 340 displays various information and various images. Specifically, the display 340 is connected to the processing circuitry 350 and displays images in various formats based on the image data output from the processing circuitry 350 . For example, the display 340 is realized by a liquid crystal monitor, a CRT (Cathode Ray Tube) monitor, a touch panel, or the like.

The processing circuit 350 controls each component included in the image processing apparatus 300 according to an input operation received from an operator via the input interface 330 . Specifically, the processing circuit 350 causes the storage circuit 320 to store the image data output from the NW interface 310 . The processing circuit 350 also displays the image data read from the storage circuit 320 on the display 340 . For example, processing circuitry 350 is implemented by a processor.

With such a configuration, the image processing apparatus 300 according to the present embodiment uses an MR image captured by the MRI apparatus 100 and arbitrary parameter values to calculate an arbitrary image type after imaging. It has the ability to generate images. Here, the image type is, for example, a T1 weighted (T1W) image, a T2 weighted (T2W) image, a FLAIR (Fluid Attenuation Inversion Recovery) image, or the like.

For example, the image processing apparatus 300 has a function of generating a calculated image (synthetic MRI image) by synthetic MRI. Specifically, the image processing apparatus 300 uses MR images captured while changing TI (Inversion Time), TE (Echo Time), FA (Flip Angle), etc., to obtain a theoretical expression of the signal value of the MR image. Tissue quantitative values such as T1 value, T2 value, PD (Proton Density) value, etc. are derived by the simulation and curve fitting used. Then, the image processing apparatus 300 generates a calculated image of an arbitrary image type with arbitrary TI, TE, and TR (Repetition Time) parameter values based on the derived tissue quantitative values. For example, the image processing apparatus 300 acquires T1 transition curves from multiple TI images, and derives T1 values and PD values from the curves. Also, for example, the image processing apparatus 300 derives the T2 value from a plurality of TE images, and generates a calculated image of an arbitrary image type based on these quantitative values.

Synthetic MRI can generate computed images of any image type by quantifying T1 values, T2 values, and proton densities. In addition, with synthetic MRI, even when obtaining a different type of calculated image, there is no need to perform imaging again. In addition, in Synthetic MRI, parameter values such as TR, TE, and TI can be freely adjusted even after a calculated image has been generated. can do.

The image processing apparatus 300 according to this embodiment is configured to obtain a calculated image suitable for diagnosis.

Here, in general, the purpose of using such a calculated image is to obtain an image with the same contrast as the MR image that has been conventionally obtained by imaging, thereby shortening the time required for examination using the MR image. is to shorten For this purpose, a calculated image is often generated with the same parameter values as the imaging. may not be the same. In this case, in order to obtain a calculated image with a desired contrast, the parameter values are adjusted while checking the contrast of the calculated image one by one, and this adjustment may not shorten the inspection time.

For this reason, the image processing apparatus 300 according to the present embodiment automatically sets parameter values for obtaining a calculated image having the same contrast as an MR image, which has conventionally been obtained by imaging, thereby shortening the examination time. It is designed so that it can be shortened.

Specifically, in the present embodiment, the storage circuit 320 stores information indicating a known contrast ratio corresponding to each image type, with respect to contrast between regions included in a plurality of brain regions, for each image type. . Note that the storage circuit 320 in this embodiment is an example of a storage unit.

Here, a plurality of regions of the brain (also called parcels) are, for example, regions of the brain divided by anatomical structure, function, and the like.

FIG. 2 is a diagram showing an example of a plurality of brain regions according to the first embodiment. For example, as shown in FIG. 2, brain regions are defined by dividing them step by step into a plurality of levels, and the lower the level, the finer the division unit. For example, in the example shown in FIG. 2, each level is expressed as level-n (n=0, 1, 2, 3, 4, 5, . . . ), and the higher the n, the lower the level. Note that FIG. 2 illustrates only levels -3 to -5.

For example, level -0 indicates the whole brain area. Further, for example, "limbic system" at level-3 and "limbic system" at level-4 have the same region names, but different sizes. For example, the "limbic system" at level-3 is the unit commonly referred to as the "limbic system". And at level -4, the "limbic system" at level -3 is divided into "cingulate gyrus", "amygdala", "hippocampus" and other areas, and here "other areas" are , defined as the “limbic system”.

In the example shown in FIG. 2, the "limbic system" at level -4 is divided into "parahippocampal gyrus" and "entorhinal cortex" at level -5, and the "cingulate gyrus" at level -4 is divided into level - 5 is divided into the "posterior cingulate gyrus" (not shown), etc., and the "amygdala" and "hippocampus" at level -4 are each divided into one or more regions (not shown) at level -5. .

In this way, for example, when brain regions are divided into different units for each level, each individual region unit at each level can be one of the plurality of brain regions referred to in the present application. For example, level-3 "limbic system", level-4 "limbic system", level-4 "hippocampus", and level-5 "parahippocampal gyrus" can each be one area. .

For example, a plurality of brain regions referred to in this application are defined in units of regions at any one level (for example, the lowest level). Alternatively, the multiple regions of the brain referred to in the present application are, for example, "parahippocampal gyrus" and "entorhinal cortex" at level -5, and "cingulate gyrus", "amygdala" and "hippocampus" at level -4. As such, it may be defined by combining units of regions at different levels.

Based on such a plurality of brain regions, the memory circuit 320 stores, for each image type, information indicating a known contrast ratio for the contrast between regions included in the plurality of brain regions corresponding to the image type. Remember.

FIG. 3 is a diagram showing an example of a contrast ratio table stored by the storage circuit 320 according to the first embodiment. For example, as shown in FIG. 3, the storage circuit 320 stores, for each image type, a contrast ratio table that associates the image type with known contrast ratios corresponding to each of a plurality of brain regions.

For example, "T1W", "T2W" and "FLAIR" shown in FIG. 3 respectively indicate image types, "T1W" indicates a T1W image, "T2W" indicates a T2W image, and "FLAIR" indicates a FLAIR image. showing the image. In addition, "GM", "WM" and "CSF" shown in FIG. 3 indicate regions of the brain, respectively. Matter), and "CSF" indicates the CerebroSpinal Fluid area.

For example, the example shown in FIG. 3 indicates that the known contrast ratio for T1W images is gray matter:white matter:cerebrospinal fluid=1:1.05:0.1. The example shown in FIG. 3 also indicates that the known contrast ratio corresponding to the T2W image is gray matter:white matter:cerebrospinal fluid=2.52:1:3. The example shown in FIG. 3 also indicates that the known contrast ratio corresponding to the FLAIR image is gray matter:white matter:cerebrospinal fluid=2.1:1:0.1.

Furthermore, in the present embodiment, the storage circuit 320 stores information defining the range of parameter values, which is a condition for setting the parameter values used to generate the calculated image, for each image type.

FIG. 4 is a diagram showing an example of a parameter range table stored by the storage circuit 320 according to the first embodiment. For example, as shown in FIG. 4, the storage circuit 320 stores, for each image type, a parameter range in which an image type, an imaging method, and a parameter value range for each of a plurality of parameters used for generating a calculated image are associated with each other. memorize the table.

For example, "T1W", "T2W", and "FLAIR" shown in FIG. 4 respectively indicate image types, "T1W" indicates a T1W image, "T2W" indicates a T2W image, and "FLAIR" indicates a FLAIR image. showing the image. In addition, "SE" and "IR" shown in FIG. 4 each indicate an imaging method, "SE" indicates a spin echo (SE) method, and "IR" indicates an inversion recovery (IR ) shows the law. In addition, "TR", "TE" and "TI" shown in FIG. 4 each indicate a plurality of parameters used for generating a calculated image, respectively, "TR" indicates TR, "TE" indicates TE and "TI" indicates TI.

For example, the example shown in FIG. 4 indicates that the range of TR is 100-1000 and the range of TE is 1-50 corresponding to the T1W image and SE method. Also, for example, in the example shown in FIG. 4, the TR range corresponding to the T2W image and the SE method is 3000-10000, and the TE range is 80-120. Further, for example, in the example shown in FIG. 4, the TR range corresponding to the FLAIR image and the IR method is 3000-10000, the TE range is 80-120, and the TI range is 2300-3500. showing.

Here, for example, the range of each parameter value set in the parameter range table includes, for each image type, general parameter values used when MR images of the same image type are captured by conventional imaging. range is set. This makes it possible to set parameter values for generating calculated images within the range of parameter values commonly used in the medical field, and to generate calculated images in line with common sense in the medical field. become.

Further, in this embodiment, the processing circuit 350 has an acquisition function 351 , a division function 352 , a setting function 353 and a generation function 354 . Note that the dividing function 352 in this embodiment is an example of a dividing unit. Also, the setting function 353 in this embodiment is an example of a setting unit. Also, the generation function 354 in this embodiment is an example of a generation unit. Note that the division unit, the setting unit, and the generation unit in this specification may be implemented by a mixture of hardware such as circuits and software.

The acquisition function 351 acquires an input image of the subject's brain from the MRI apparatus 100 or the image storage apparatus 200 .

Specifically, the acquisition function 351 uses a plurality of MR images captured by the MRI apparatus 100 while changing parameter values that affect the contrast of the image, such as TI, TE, and FA, and the MR images. A plurality of quantitative images such as the derived T1 map image, T2 map image, and PD image are obtained as input images. For example, the acquisition function 351 acquires a T1W image captured by the MRI apparatus 100 using an MP2RAGE (Magnetization Prepared 2 Rapid Gradient Echo) sequence and a T1 map image derived from the T1W image. Alternatively, for example, the acquisition function 351 acquires, as an input image, one MR image obtained by a sequence capable of storing the changes in one image while changing TI, TE, FA, etc. good too.

The segmentation function 352 segments the brain region in the input image of the brain into multiple regions.

Specifically, the division function 352 uses the MR image acquired by the acquisition function 351 as an input image and divides the brain region in the input image into a plurality of regions. For example, the division function 352 uses a T1W image captured by the MRI apparatus 100 using the MP2RAGE sequence as an input image, and divides the brain region in the input image into a plurality of regions.

Here, for example, the division function 352 divides the brain region in the input image into a plurality of regions (also called parcellation) as illustrated in FIG. )do.

The setting function 353 generates a calculated image of the brain so that the contrast relationship between regions included in the plurality of brain regions divided by the division function 352 is a predetermined relation in the generated calculated image of the brain. Sets the parameter value used for

Specifically, the setting function 353 is used to generate a calculated image so that a contrast relationship between regions included in a plurality of regions in a calculated brain image generated by synthetic MRI is a predetermined relation. Set parameter values.

Here, in the present embodiment, the setting function 353 sets the contrast between regions included in the plurality of brain regions divided by the division function 352 to a known contrast ratio corresponding to the image type designated by the operator. Set the parameter values used to generate the calculated image so that

Specifically, the setting function 353 receives designation of image type from the operator via the input interface 330 . For example, the setting function 353 displays buttons indicating each image type on the display 340 for a plurality of predetermined image types, and accepts an operation of selecting one of the buttons from the operator. Accept designation.

After that, the setting function 353 refers to the contrast ratio table stored in the storage circuit 320 to obtain a known contrast ratio corresponding to the specified image type. Then, the setting function 353 sets the parameter values used for generating the calculated image so that the contrast between the regions included in the plurality of regions divided by the dividing function 352 becomes the acquired contrast ratio.

At this time, the setting function 353 refers to the parameter range table stored in the storage circuit 320 to obtain the parameter value range corresponding to the designated image type. Then, the setting function 353 is used to generate the calculated image so that the contrast ratio between the regions included in the plurality of regions is closest to the contrast ratio obtained from the contrast ratio table within the range of the obtained parameter values. Sets the parameter value to be used.

For example, if TE, TR and TI are the parameter values of TE, TR and TI used to generate a calculated image, the combination of these parameter values is represented by a set θ as follows.

θ={TR, TE, TI}

The ranges of parameter values for TE, TR, and TI set in the parameter range table are expressed as follows.

TR _min <TR < TR _max , TE _min < TE < TE _max , TI _min < TI < TI _max

Then, for example, when the number of brain regions set in the contrast ratio table is N, the contrast ratio between regions in the calculated image derived from the parameter values of the set θ is as follows for each region is represented by a vector C _θ consisting of the contrast ratios of

C _θ = (c1 _θ , c2 _θ , c3 _θ , . . . cN _θ )

Also, the contrast ratio between regions set in the contrast ratio table is represented by a vector C _DB consisting of the contrast ratio for each region as follows.

_CDB = ( _c1DB , _c2DB , _c3DB , ... _cNDB )

In this case, the setting function 353 uses the function D(·) representing the distance between the vectors to calculate the distance D(C _θ −C _DB ) between the vector C _θ and the vector C _DB as shown below. A search is made for a combination θ _optimized of TE, TR, and TI that minimizes .

θ _optimized = argmin _θ D (C _θ −C _DB )

Specifically, the setting function 353 sequentially derives the vector _Cθ and the vector _CDB while individually and sequentially changing TE, TR, and TI within the range of parameter values obtained from the parameter range table, and further , derive the distance D (C _θ −C _DB ) between the vector C _θ and the vector C _DB . The setting function 353 then specifies, as θ _optimized , the combination of TE, TR, and TI when the distance D (C _θ −C _DB ) is minimized.

Note that, for example, when changing each parameter value, the setting function 353 does not necessarily have to change all the values within the parameter value range acquired from the parameter range table. For example, the setting function 353 sets, as initial values, the parameter values that are normally used when an MR image is captured, and while sequentially changing the parameter values so as to gradually deviate from the initial values, the vector C _θ and the vector C D(C _θ −C _{DB )} is derived. Then, the setting function 353 ends the processing when the distance D (C _θ −C _DB ) becomes smaller than a predetermined threshold, and specifies the combination of TE, TR, and TI at that time as θ _optimized . .

After that, the setting function 353 sets the parameter values of TE, TR, and TI at the identified θ _optimized as parameter values used for generating the calculated image. This automatically sets the parameter values used to generate the computational image such that the contrast between regions contained in multiple brain regions is a known contrast ratio corresponding to the specified image type. .

The generation function 354 generates a calculated image using the input image acquired by the acquisition function 351 and the parameter values set by the setting function 353 .

Specifically, the generation function 354 uses the quantitative image acquired by the acquisition function 351 and the parameter values set by the setting function 353 to generate a calculated image by synthetic MRI. For example, the generation function 354 uses the T1 map image derived from the T1W image captured by the MRI apparatus 100 using the MP2RAGE sequence and the parameter values set by the setting function 353 to generate the calculated image. Alternatively, for example, the generation function 354 generates a calculated image using one MR image holding changes in TI, TE, FA, etc., acquired by the acquisition function 351 and parameter values set by the setting function 353. may be generated.

The generation function 354 then displays the generated calculated image on the display 340 .

5 and 6 are diagrams showing specific examples of calculated images generated by the image processing apparatus 300 according to the first embodiment. 5 and 6 show, as an example, a case where a FLAIR image calculation image is generated.

Here, FIG. 5(a) shows an example of known contrast ratios corresponding to FLAIR images set in the contrast ratio table. Also, FIG. 5(b) shows the desired FLAIR image. FIG. 5(c) shows an example of a calculated image generated before the parameter values are automatically set according to this embodiment. Further, (d) of FIG. 5 shows an example of a calculated image generated after automatic setting of parameter values according to the present embodiment.

For example, as shown in (a) of FIG. 5, in the contrast ratio table, the known contrast ratio corresponding to the FLAIR image was set as gray matter: white matter: cerebrospinal fluid = 2.1: 1: 0. do. Then, the desired FLAIR image shown in FIG. 5(b) is shown in FIG. FLAIR images obtained with the indicated contrast ratios. This FLAIR image is, for example, a FLAIR image suitable for interpretation, a FLAIR image captured in the past with the same subject, or the like.

Here, for example, as shown in FIG. 5C, when the calculated image is generated in the state before the automatic setting of the parameter values according to the present embodiment, the same parameters as the desired FLAIR image Even if values are used, they do not always give a calculated image with the same contrast as the desired FLAIR image due to errors in the T1, T2 and PD values that occur during data acquisition.

On the other hand, for example, as shown in (d) of FIG. 5, when the calculation image is generated after the automatic setting of the parameter values according to the present embodiment, the gray matter region (GM), The same contrast as the desired FLAIR image is achieved for areas of white matter (WM) and areas of cerebrospinal fluid (CSF).

At this time, for example, as shown in FIG. A difference in contrast occurs between the surroundings where the T1 value, T2 value, and PD value derived based on the TI parameter values are reflected. As a result, an abnormal site can be detected in a calculated image in the same manner as in reading a normal FLAIR image.

Also, FIG. 6(a), like FIG. 5(a), shows an example of known contrast ratios corresponding to FLAIR images set in the contrast ratio table. Here, (b) of FIG. 6 shows the TI, the gray matter area (GM), the white matter area (WM), the cerebrospinal fluid area (CSF), and the abnormal site when TR=8000. shows the relationship with the signal value in each region (T2_lesion). FIG. 6(c) shows the relationship between TE and signal values in each region when TR=8000 and TI=2900. Further, (d) of FIG. 6 shows the relationship between TE and the signal value in each region when TR=8000 and TI=2580.

For example, as shown in (b) to (d) of FIG. 6, the signal value in each region varies depending on the measured T1 value, T2 value and PD value, so some variation is inevitable for each measurement. occurs in In other words, the desired contrast cannot be obtained with fixed parameter values.

Here, for example, as shown in (a) of FIG. 6, in the contrast ratio table, the known contrast ratio corresponding to the FLAIR image is set as gray matter: white matter: cerebrospinal fluid = 2.1: 1: 0 Suppose it was done. In this case, for example, as shown in FIG. 6B, in the automatic setting of parameter values according to the present embodiment, as a result of changing TI with TR=8000, automatic setting of parameter values is performed. Assume that TI=2900 before becomes TI=2580 after automatic setting of parameter values.

At this time, for example, as shown in FIG. The difference between the signal value in the site area (T2 lesion) and the signal values in the gray matter area (GM) and the white matter area (WM) becomes smaller (see, for example, signal values when TE=80).

On the other hand, for example, as shown in FIG. 6(d), when TE is changed with TR=8000 and TI=2580, the signal value in the cerebrospinal fluid region (CSF) becomes 0. , the difference between the signal value in the region of the abnormal site (T2 lesion) and the signal values in the gray matter region (GM) and the white matter region (WM) increases (see, for example, the signal value when TE = 80 ).

In this way, by automatically setting the parameter values used to generate the calculated image based on the known contrast ratio corresponding to the specified image type, the image essentially desired (FLAIR image in this example) gives the same computed image as At this time, for example, as shown in (c) and (d) of FIG. , T2 value and PD value are reflected in the surroundings, resulting in a difference in contrast. As a result, an abnormal site can be detected in a calculated image in the same manner as in reading a normal FLAIR image.

Thus, in this embodiment, in the calculated image, the contrast ratio of the gray matter area (GM), the white matter area (WM), and the cerebrospinal fluid area (CSF) is set to be the same as that of the desired FLAIR image. can improve the contrast ratio between the abnormal site and its surroundings in the calculated image. This is different from normal gain adjustment.

Each function of the processing circuit 350 has been described above. For example, in this embodiment, each processing function performed by the acquisition function 351, the division function 352, the setting function 353, and the generation function 354 is stored in the storage circuit 320 in the form of a computer-executable program. The processing circuit 350 is a processor that implements a function corresponding to each program by reading the program from the storage circuit 320 and executing the program. In other words, the processing circuit with each program read has each function shown in the processing circuit 350 of FIG.

Note that FIG. 1 shows an example in which the processing functions performed by the acquisition function 351, the division function 352, the setting function 353, and the generation function 354 are realized by a single processing circuit 350, but the embodiment is similar to this. is not limited to For example, the processing circuit 350 may be configured by combining a plurality of independent processors, and each function may be realized by each processor executing a program. Moreover, each processing function of the processing circuit 350 may be appropriately distributed or integrated in a single or a plurality of processing circuits and implemented. Further, in the above-described first embodiment, the single memory circuit 320 stores the programs corresponding to the respective processing functions. A configuration in which the corresponding programs are read from individual storage circuits may be used.

FIG. 7 is a flow chart showing a processing procedure for generating a calculated image performed by the image processing apparatus 300 according to the first embodiment. For example, as shown in FIG. 7, in the image processing apparatus 300 according to the present embodiment, the acquisition function 351 first acquires an input image of the subject's brain from the MRI apparatus 100 or the image storage apparatus 200 (step S101). .

After that, the division function 352 divides the brain region in the input image of the brain into a plurality of regions (step S102).

Also, the setting function 353 receives designation of the image type from the operator via the input interface 330 (step S103). After that, the setting function 353 refers to the contrast ratio table stored in the storage circuit 320 and obtains a known contrast ratio corresponding to the designated image type (step S104).

Then, the setting function 353 sets the parameter values for generating the calculated image so that the contrast between the regions included in the plurality of regions divided by the dividing function 352 becomes the obtained contrast ratio (step S105).

After that, the generating function 354 generates a calculated image using the parameter values set by the setting function 353 (step S106), and displays the generated calculated image on the display 340 (step S107).

Here, step S101 is realized, for example, by causing the processing circuit 350 to call a predetermined program corresponding to the acquisition function 351 from the storage circuit 320 and execute it. Further, step S102 is realized, for example, by causing the processing circuit 350 to call a predetermined program corresponding to the division function 352 from the storage circuit 320 and execute it. Further, steps S103 to S105 are realized by, for example, the processing circuit 350 calling a predetermined program corresponding to the setting function 353 from the storage circuit 320 and executing the program. Further, steps S106 and S107 are realized by, for example, the processing circuit 350 calling a predetermined program corresponding to the generation function 354 from the storage circuit 320 and executing the program.

Note that in FIG. 7, the division function 352 divides the brain region into a plurality of regions (step S102), and the setting function 353 receives the designation of the image type from the operator and uses a known image corresponding to the designated image type. from the contrast ratio table (steps S103 and S104) may be performed in the opposite order or may be performed in parallel.

As described above, according to the first embodiment, based on the quantitative image, the desired image type, and the contrast ratio between regions, a calculated image having the same contrast as the MR image conventionally obtained by imaging can be set automatically with the parameter values obtained. This eliminates the need for parameter adjustment and shortens the inspection time. Also, the workflow can be improved by automatically setting the parameters of the computed image.

In addition, according to the first embodiment, a calculated image is generated in which the contrast ratio between regions is optimized to a specific contrast ratio. the values will be the same. On the other hand, for other regions, if there is no change, the brightness value will be the same, but if there is a change, the brightness value will be different, so follow-up observation can be easily performed. become able to.

FIG. 8 is a diagram showing an example of the effects of the first embodiment. Here, (a) of FIG. 8 shows an example of a past calculated image generated by the image processing apparatus 300 according to the present embodiment, and (b) of FIG. 8 shows an example of the image processing according to the present embodiment. An example of a current calculated image produced by the device 300 is shown.

As described above, in the first embodiment, a calculated image is generated according to the contrast ratio set in the contrast ratio table. Therefore, for example, the gray matter area (GM), the white matter area (WM), and the cerebrospinal fluid area (CSF) in each calculation image shown in FIGS. Without change, the luminance value in each region is the same. On the other hand, for example, as shown in (a) and (b) of FIG. , the contrast of the abnormal region A becomes different.

Thus, according to the first embodiment, a calculated image suitable for diagnosis can be obtained.

In the above-described first embodiment, the setting function 353 refers to the contrast ratio table stored in the storage circuit 320 and acquires a known contrast ratio corresponding to the designated image type. Although described, embodiments are not so limited. For example, the setting function 353 may refer to previously captured MR images or previously generated calculated images to obtain a known contrast ratio corresponding to the designated image type.

In this case, if the parameter value is derived using the contrast ratio of the region of the abnormal site in the image captured in the past, the brightness value of most regions in the generated calculated image will be different from the past image. I will put it away. Therefore, the setting function 353 does not use the contrast ratio of the region of the abnormal site for deriving the parameter value.

For example, the setting function 353 derives a parameter value based on the contrast ratio between each region for each combination of multiple different regions included in previously captured images. Then, the setting function 353 regards values that are greatly different among the derived parameter values as outliers, and adopts values that are the same as optimum parameter values.

For example, the contrast ratio between gray matter regions (GM) and white matter regions (WM) in historical images is 1:3 and the derived parameter values are TE=a, TR=b, Suppose TI=c. Also, the contrast ratio between the area of gray matter (GM) and the area of cerebrospinal fluid (CSF) in the previous image was 1:0.1, and the parameter values derived therefrom were TE=x, Suppose that TR=y and TI=z. In addition, the contrast ratio between the area of the thalamus (Thalamus) and the area of cerebrospinal fluid (CSF) in the past image was 1:0.1, and the parameter values derived therefrom were TE = x, TR = y and TI = z.

In this case, for example, the setting function 353 considers the parameter value derived from the contrast ratio between the gray matter area (GM) and the white matter area (WM) to be an outlier, and the gray matter area (GM ) and the area of cerebrospinal fluid (CSF), and the contrast ratio between the area of the thalamus (Thalamus) and the area of cerebrospinal fluid (CSF) as the optimal parameter adopted as a value.

Further, in the first embodiment described above, an example in which the operator designates the image type has been described, but the embodiment is not limited to this. For example, the type of image to be processed may be specified in advance and stored in the storage circuit 320 . In this case, for example, the setting function 353 determines that the contrast between regions included in the plurality of brain regions divided by the division function 352 is equal to the known contrast ratio corresponding to the image type stored by the storage circuit 320. Set the parameter values used to generate the calculated image so that

Note that the number of image types stored in the storage circuit 320 may be plural. In that case, the setting function 353 sets parameter values used for generating calculated images for all image types stored in the storage circuit 320 . Then, for example, the generation function 354 generates calculated images for all image types stored in the storage circuit 320 and displays the generated calculated images on the display 340 in sequence or simultaneously.

In the above-described first embodiment, the setting function 353 refers to the contrast ratio table and the parameter range table stored in the storage circuit 320 to set the parameter values used for generating the calculated image. has been described, the embodiments are not limited to this.

For example, the setting function 353 uses a trained model obtained by machine learning using a learning data set of correct values for the parameter values used to generate the quantitative image, the image type, and the calculated image, and sets the parameter value may be set.

For example, the setting function 353 uses deep learning as a machine learning technique.

In this case, for example, the setting function 353 sets a large number of quantitative images such as T1 map images, T2 map images, and PD images, image types such as T1W images, T2W images, and FLAIR images, and each image from each quantitative image. A trained model is generated by deep learning using correct values for parameter values such as TR, TE, and TI used when generating a type of calculated image as a learning data set.

Here, as the correct value for the parameter value, for example, the value actually set as the appropriate parameter value by the doctor when the calculated image was used in the past diagnosis is used. Alternatively, as the correct value for the parameter value, for example, a value actually set using the above-described contrast ratio table and parameter range table is used.

In this way, by using a trained model obtained by deep learning, compared to the case of setting parameter values by referring to the contrast ratio table and the parameter range table as described above, the parameter values can be set.

Note that the machine learning method used by the setting function 353 is not limited to deep learning, and other methods may be used.

For example, the setting function 353 may use non-linear discriminant analysis, Support Vector Machine (SVM), Random Forest, Naive Bayes, etc. as machine learning methods.

Here, the support vector machine is a statistical technique that constructs a two-class pattern classifier using linear input elements. A support vector machine is a statistical technique that learns the parameters of linear input elements based on the criterion of obtaining a margin-maximizing hyperplane that maximizes the distance to each data point from training data. Also, random forest is a statistical technique that performs ensemble learning using a large number of decision trees learned from randomly sampled training data. Naive Bayes is a statistical method for learning using Bayes' theorem.

In either method, it is possible to generate a trained model by inputting a large number of training data sets corresponding to correct values, and use the generated learning model to estimate the parameter values used to generate the calculated image. It is possible.

Further, in the above-described first embodiment, an example in which the setting function 353 sets the parameter values so that the contrast between regions included in the plurality of regions divided by the division function 352 has a known contrast ratio. , the regions targeted here do not necessarily have to be all the regions divided by the dividing function 352 .

For example, the setting function 353 accepts from the operator an operation to designate at least one of the plurality of regions divided by the division function 352, and removes the designated region from the plurality of regions and Set the parameter values so that the contrast between is a known relationship.

In this case, for example, the setting function 358 displays the MR image of the brain used as the input image by the division function 352 on the display 340 and, via the input interface 330, an arbitrary position on the displayed MR image. Accepts the specified operation from the operator. Then, the setting function 358 specifies a region including the position specified by the operator from among the plurality of brain regions obtained from the input image, and targets the remaining regions excluding the specified region. Set the parameter values so that the contrast between is a known relationship.

In this way, by excluding the region specified by the operator, the region where an abnormal site such as a tumor occurs or the region where artifacts are likely to occur ( For example, surrounding areas of blood vessels, etc.) can be excluded, and parameter values can be set to obtain a calculated image with the same contrast as the MR image obtained by imaging with higher accuracy.

Further, in the above-described first embodiment, the setting function 353 sets the parameter values so that the contrast between regions included in a plurality of brain regions is a known contrast ratio corresponding to the designated image type. Although an example of setting has been described, the embodiment is not limited to this. For example, the setting function 353 may set the parameter values used to generate the calculated image such that the contrast between the specified disease-related region and other regions is enhanced. Therefore, an example of such a case will be described below as a second embodiment.

(Second embodiment)
FIG. 9 is a diagram showing a configuration example of an image processing apparatus according to the second embodiment. In the second embodiment, the points different from the first embodiment will be mainly described, and the same reference numerals will be given to the constituent elements that play the same role as the constituent elements shown in FIG. detailed description is omitted. For example, as shown in FIG. 9, in this embodiment, an MRI apparatus 100, an image storage apparatus 200, and an image processing apparatus 1300 are connected via a network 400 so as to be communicable.

The image processing device 1300 processes image data acquired by the MRI device 100 . Specifically, the image processing apparatus 1300 acquires image data from the MRI apparatus 100 or the image storage apparatus 200 via the network 400 and stores it in a storage circuit provided inside or outside the apparatus. The image processing apparatus 1300 also performs various image processing on the acquired image data, and displays the image data before or after image processing on a display or the like. For example, the image processing apparatus 1300 is implemented by computer equipment such as a workstation.

Specifically, the image processing device 1300 includes a NW interface 310 , a memory circuit 1320 , an input interface 330 , a display 340 and a processing circuit 1350 .

The storage circuit 1320 stores various data. Specifically, the storage circuit 1320 is connected to the processing circuit 1350 and stores input image data according to a command sent from the processing circuit 1350, or transfers the stored image data to the processing circuit 1350. Output. For example, the storage circuit 1320 is realized by a semiconductor memory device such as a RAM or flash memory, a hard disk, an optical disk, or the like.

The processing circuit 1350 controls each component included in the image processing apparatus 1300 according to an input operation received from the operator via the input interface 330 . Specifically, the processing circuit 1350 causes the storage circuit 1320 to store the image data output from the NW interface 310 . The processing circuit 1350 also displays the image data read from the storage circuit 320 on the display 340 . For example, processing circuitry 1350 is implemented by a processor.

With such a configuration, the image processing apparatus 1300 according to the present embodiment uses the MR image captured by the MRI apparatus 100 and arbitrary parameter values to calculate an arbitrary image type after imaging. It has the ability to generate images. Here, the image type is, for example, a T1W image, a T2W image, a FLAIR image, or the like.

For example, the image processing device 1300 has a function of generating a calculated image by synthetic MRI, like the image processing device 300 described in the first embodiment.

The image processing apparatus 1300 according to this embodiment is configured to obtain a calculated image suitable for diagnosis.

Here, for example, if, as is generally done, simply obtaining a calculated image with the same parameter values as for imaging, the diagnostic utility value of a calculated contrast image that has not been captured conventionally is overlooked. It is possible.

For this reason, the image processing apparatus 1300 according to the present embodiment automatically sets parameter values for obtaining a contrast calculated image that makes it easy to visually distinguish a target region, thereby enabling diagnostic use. It is configured so that it is possible to obtain computational images of high value.

Specifically, in this embodiment, the memory circuit 1320 stores information indicating disease-related regions among a plurality of brain regions for each disease. Note that the memory circuit 1320 in this embodiment is an example of a memory unit.

FIG. 10 is a diagram showing an example of a disease-related region table stored by the storage circuit 1320 according to the second embodiment. For example, as shown in FIG. 10, the memory circuit 1320 stores a disease-related region table that associates, for each disease, brain regions related to the disease and degrees of association between the region and the disease.

For example, the example shown in FIG. 10 shows a disease-related region table related to Alzheimer's disease, and "region #2", "region #3" and "region #8" shown in FIG. 10 respectively indicate brain regions. there is For example, in the example shown in FIG. 10, the degree of association between Alzheimer's disease and region #2 is "2", the degree of association between Alzheimer's disease and region #3 is "5", and the degree of association between Alzheimer's disease and region #8 is is "4". The degree of relevance here may be set, for example, based on a p-value obtained from literature, or may be set based on the number of times the information is referred to when a doctor makes a diagnosis.

Also, in this embodiment, the processing circuit 1350 has an acquisition function 351 , a division function 352 , a setting function 1353 , a generation function 354 and an update function 1355 . Note that the dividing function 352 in this embodiment is an example of a dividing unit. Also, the setting function 1353 in this embodiment is an example of a setting unit. Also, the generation function 354 in this embodiment is an example of a generation unit. Also, the update function 1355 in this embodiment is an example of an update unit. Note that the dividing unit, setting unit, generating unit, and updating unit in this specification may be implemented by a mixture of hardware such as circuits and software.

The setting function 1353 sets parameter values used for generating a calculated image of the brain so that the regions included in the brain regions divided by the dividing function 352 have a predetermined contrast relationship.

Specifically, the setting function 1353 is used to generate a calculated image so that a contrast relationship between regions included in a plurality of regions in a calculated brain image generated by synthetic MRI is a predetermined relation. Set parameter values.

Here, in the present embodiment, the setting function 1353 refers to the disease-related region table stored in the storage circuit 1320, identifies a disease-related region designated by the operator, The parameter values used to generate the calculated image are set so that the contrast between regions is emphasized.

For example, the setting function 1353 sets the parameter values used to generate the calculated image such that the contrast between the designated disease-related region and the regions surrounding the region is enhanced.

Specifically, the setting function 1353 receives designation of disease from the operator via the input interface 330 . For example, the setting function 1353 displays a list listing each disease on the display 340 for a plurality of predetermined diseases, and receives an operation from the operator to select a disease from the displayed list. Accept designation.

After that, the setting function 1353 refers to the disease-related region table stored in the storage circuit 1320 to identify the designated disease-related region. For example, the setting function 1353 identifies, as a processing target area, the area of the brain set in the disease-related area table that has the highest degree of association with the designated disease.

Then, the setting function 1353 generates a calculated image so that the contrast ratio between the specified region and the regions around the specified region is maximized within a predetermined range determined in advance for each parameter value. Sets the parameter value used for

For example, if TE, TR, and TI are the parameter values of TE, TR, and TI used to generate the calculated image, combinations of these parameter values are represented by a set θ as shown below.

θ={TR, TE, TI}

Further, the predetermined parameter value ranges for TE, TR and TI are expressed as follows. Here, it is desirable that the range of each parameter value is set sufficiently wide.

TR _min <TR < TR _max , TE _min < TE < TE _max , TI _min < TI < TI _max

Then, for example, if the number of brain regions divided by the dividing function 352 is N, the contrast ratio between the specified region and other regions in the calculated image derived from the parameter values of the set θ is as follows: , represented by a vector C _θ consisting of the contrast ratio for each region.

C _θ = (c1 _θ , c2 _θ , c3 _θ , . . . cN _θ )

Also, the contrast ratio between the area around the designated area and other areas is represented by a vector C _PERI consisting of the contrast ratio for each area, as shown below.

C _PERI = (c1 _PERI , c2 _PERI , c3 _PERI , ... cN _PERI )

In this case, the setting function 1353 calculates the distance D (C _θ −C _PERI ) between the vector C _θ and the vector C _PERI using the function D(·) representing the distance between the vectors, as shown below. A search is made for a combination θ _optimized of TE, TR, and TI that maximizes .

θ _optimized = argmax _θ D(C _θ −C _PERI )

Specifically, the setting function 1353 sequentially derives the vector C _θ and the vector C _PERI while individually and sequentially changing TE, TR, and TI within a predetermined range. Derive the distance D (C _θ −C _DB ) between _θ and the vector C _DB . Then, the setting function 1353 specifies the combination of TE, TR, and TI when the distance D (C _θ −C _DB ) is maximized as θ _optimized .

Note that, for example, when changing each parameter value, the setting function 1353 does not necessarily have to change all the values within the parameter value range acquired from the parameter range table. For example, the setting function 1353 sets the parameter values that are normally used when an MR image is captured as initial values, and sequentially changes the parameter values so as to gradually deviate from the initial values, while setting vector C _θ and vector C Derive the distance D (C _θ −C _PERI ) to _PERI . Then, the setting function 1353 ends the processing when the distance D (C _θ −C _PERI ) becomes a value greater than a predetermined threshold, and identifies the combination of TE, TR, and TI at that time as θ _optimized . .

After that, the setting function 1353 sets the parameter values of TE, TR, and TI at the identified θ _optimized as parameter values used for generating the calculated image. Thereby, the parameter values used to generate the calculated image are automatically set such that the contrast between the designated disease-related region and the regions surrounding the region is enhanced.

The update function 1355 updates the information indicating the disease-related region stored in the storage circuit 1320 in accordance with the operator's operation.

Specifically, the update function 1355 updates the disease-related region table stored in the storage circuit 1320 in accordance with the operator's operation.

For example, the update function 1355 displays an image representing a plurality of regions divided by the division function 352 on the display 340, and receives an operation from an operator such as a doctor based on the result of interpretation of the displayed image.

Then, the update function 1355 updates the disease-related region table according to the operation received from the operator. For example, the update function 1355 changes or deletes set brain regions or adds new brain regions in the disease-related region table for a specific disease. Alternatively, for example, the update function 1355 registers a disease-related region table for a new disease in the memory circuit 1320 or deletes a disease-related region table for a specific disease from the memory circuit 1320.

In this way, the update function 1355 updates the disease-related region table stored in the storage circuit 1320 in accordance with the operator's operation, for example, based on the results of image interpretation performed by a plurality of doctors. It becomes possible to accumulate information indicating disease-related regions.

Each function of the processing circuit 1350 has been described above. For example, in this embodiment, each processing function performed by the acquisition function 351, the division function 352, the setting function 1353, the generation function 354, and the update function 1355 is stored in the storage circuit 1320 in the form of a computer-executable program. ing. The processing circuit 1350 is a processor that reads a program from the storage circuit 1320 and executes it, thereby realizing a function corresponding to each program. In other words, the processing circuit with each program read has each function shown in the processing circuit 1350 of FIG.

Note that FIG. 9 shows an example in which the processing functions performed by the acquisition function 351, the division function 352, the setting function 1353, the generation function 354, and the update function 1355 are implemented by a single processing circuit 1350. Embodiments are not limited to this. For example, the processing circuit 1350 may be configured by combining a plurality of independent processors, and each function may be realized by executing a program by each processor. Moreover, each processing function of the processing circuit 1350 may be appropriately distributed or integrated in a single or a plurality of processing circuits and implemented. Further, in the above-described first embodiment, the single memory circuit 1320 stores the programs corresponding to the respective processing functions. A configuration in which the corresponding programs are read from individual storage circuits may be used.

FIG. 11 is a flowchart showing a processing procedure for updating the disease-related region table performed by the image processing apparatus 1300 according to the second embodiment. For example, as shown in FIG. 11, in the image processing apparatus 1300 according to the present embodiment, the acquisition function 351 first acquires an input image of the subject's brain from the MRI apparatus 100 or the image storage apparatus 200 (step S201). . At this time, for example, the acquisition function 351 acquires a T1W image captured by the MRI apparatus 100 using an MPRAGE (Magnetization Prepared Rapid Gradient Echo) sequence.

After that, the division function 352 divides the brain region in the input image of the brain into a plurality of regions (step S202).

Then, the updating function 1355 displays on the display 340 an image showing a plurality of regions divided by the dividing function 352 (step S203), and an operator such as a doctor performs an operation based on the result of interpretation of the displayed image. Accept (step S204). After that, the update function 1355 updates the information (disease-related region table) indicating the region related to the disease according to the received operation (step S205).

Here, step S201 is realized, for example, by causing the processing circuit 1350 to call a predetermined program corresponding to the acquisition function 351 from the storage circuit 1320 and execute it. Further, step S202 is realized, for example, by causing the processing circuit 1350 to call a predetermined program corresponding to the division function 352 from the storage circuit 1320 and execute it. Further, steps S203 to S205 are implemented by, for example, the processing circuit 1350 calling a predetermined program corresponding to the update function 1355 from the storage circuit 1320 and executing the program.

Although an example in which the update function 1355 displays an image for interpretation has been described here, the embodiment is not limited to this. For example, the setting function 1353 in this embodiment sets parameter values in the same manner as the setting function 353 described in the first embodiment, and the generation function 354 uses the set parameter values to generate a calculated image for interpretation. may be generated.

FIG. 12 is a flow chart showing a processing procedure for generating a calculated image performed by the image processing apparatus 1300 according to the second embodiment. For example, as shown in FIG. 12, in the image processing apparatus 1300 according to the present embodiment, the acquisition function 351 first acquires an input image of the subject's brain from the MRI apparatus 100 or the image storage apparatus 200 (step S301). .

A segmentation function 352 then segments the brain region in the input image of the brain into multiple regions (step S302).

Also, the setting function 1353 receives designation of a disease from the operator via the input interface 330 (step S303). After that, the setting function 1353 refers to the disease-related region table stored in the storage circuit 1320 to identify the designated disease-related region (step S304).

Then, the setting function 1353 sets the parameter values for generating the calculation image so that the contrast ratio between the identified region and the regions surrounding the region is emphasized (step S305).

After that, the generating function 354 generates a calculated image using the parameter values set by the setting function 1353 (step S306), and displays the generated calculated image on the display 340 (step S307). Note that the calculated image displayed here may be an image without a specific name, such as a T1W image, a T2W image, a FLAIR image, or the like.

Here, step S301 is realized, for example, by causing the processing circuit 1350 to call a predetermined program corresponding to the acquisition function 351 from the storage circuit 1320 and execute it. Further, step S302 is realized, for example, by causing the processing circuit 1350 to call a predetermined program corresponding to the division function 352 from the storage circuit 1320 and execute it. Further, steps S303 to S305 are realized by, for example, the processing circuit 1350 calling a predetermined program corresponding to the setting function 1353 from the storage circuit 1320 and executing the program. Further, steps S306 and S307 are realized by, for example, the processing circuit 1350 calling a predetermined program corresponding to the generation function 354 from the storage circuit 1320 and executing it.

In FIG. 12, the dividing function 352 divides the brain region into a plurality of regions (step S302), and the setting function 1353 receives designation of a disease from the operator and identifies a region related to the designated disease. The execution order of the processing (steps S303 and S304) may be reversed, or may be executed in parallel.

As described above, according to the second embodiment, based on the information of the disease and the region associated with the disease, the parameter values yield a computed image of contrast such that the regions of interest are visually distinguishable. can be set automatically. As a result, a calculated image with high diagnostic utility value can be obtained. Also, it becomes easier for the doctor to interpret the disease-related region on the calculated image.

In addition, for example, it is now possible to generate a contrast calculated image that clearly shows the abnormal region that was qualitatively interpreted by a skilled doctor, so that even an unskilled doctor can interpret the abnormal region. Become. Also, pixel values obtained from the generated calculated image may be defined as an Imaging biomarker. Also, the workflow can be improved by automatically setting the parameters of the computed image.

Thus, according to the second embodiment, a calculated image suitable for diagnosis can be obtained.

In the second embodiment described above, an example in which the storage circuit 1320 stores disease-related regions one by one in the disease-related region table has been described, but the embodiment is not limited to this. For example, the memory circuit 1320 may store information indicating a combination of at least two regions associated with each disease. In this case, for example, the setting function 1353 refers to the information stored in the storage circuit 1320 to specify a combination of regions related to the specified disease, and the contrast between the regions included in the specified combination is Set the parameters used to generate the computational image as emphasized.

Further, in the above-described second embodiment, the setting function 1353 specifies, as the processing target region, the region with the highest degree of association with the specified disease among the brain regions set in the disease-related region table. Although the example of the case of doing is described, the embodiment is not limited to this. For example, the setting function 1353 may process a plurality of brain regions set in the disease-related region table. In this case, for example, the setting function 1353 derives the distance D(C _θ −C _DB ) between the vector C _θ and the vector C _DB for all regions, among which the distance D(C _θ − The combination of TE, TR, and TI when C _DB ) is maximized is specified as θ _optimized . Further, when a plurality of regions are to be processed in this way, the setting function 1353 performs weighting according to the degree of association set in the disease-related region table when setting parameters for each region. can be

In addition, in the above-described second embodiment, an example was described in which the setting function 1353 refers to the disease-related region table stored in the storage circuit 1320 to specify a designated disease-related region. , the embodiment is not limited to this. For example, the setting function 1353 receives an operation from the operator to designate a disease-related region among a plurality of brain regions, and the contrast between the region designated by the operator and other regions is emphasized. You may set the parameter value as follows: At this time, the number of areas received from the operator may be one or plural.

Also, in the second embodiment described above, an example in which a disease is specified by the operator has been described, but the embodiment is not limited to this. For example, a disease to be processed may be specified in advance and stored in the storage circuit 1320 . In this case, for example, the setting function 1353 refers to the disease-related region table stored in the storage circuit 1320 to specify a disease-related region stored by the storage circuit 1320, The parameter values used to generate the calculated image are set so that the contrast between regions is emphasized.

Note that the number of diseases stored in the storage circuit 1320 may be plural. In that case, the setting function 1353 sets parameter values used for generating calculated images for all diseases stored in the storage circuit 1320 . Then, for example, the generation function 354 generates calculated images for all the diseases stored in the storage circuit 1320, and displays the generated calculated images on the display 340 sequentially or simultaneously.

Further, in the above-described second embodiment, the setting function 1353 sets the parameter values used for generating the calculated image so that the contrast between the specified disease-related region and other regions is enhanced. An example of setting has been described, but the degree of contrast enhancement may be changed.

For example, the setting function 1353 accepts an operation to specify the degree of contrast enhancement from the operator, and the contrast between the specified disease-related region and other regions is enhanced at the specified degree of enhancement. , set the parameter value.

In this case, for example, the setting function 1353 receives an operation of inputting a value indicating the degree of emphasis from the operator via the input interface 330 . Alternatively, for example, the setting function 1353 receives an operation from the operator to select one level from a plurality of pre-determined levels of emphasis, such as high, medium, and low.

This allows the operator to adjust the degree of emphasis of the region associated with the disease, thereby facilitating interpretation.

The image processing apparatuses according to the first and second embodiments have been described above. Here, for example, in the first and second embodiments described above, when the setting function derives the optimum parameter values for generating the calculated image, the derived parameter values are stored as presets in the storage circuit. You may do so. In this case, for example, the generation function later reuses the parameter values stored as presets to generate the calculated image.

Further, in the first and second embodiments described above, an example in which synthetic MRI is used as a technique for generating a calculated image has been described, but embodiments are not limited to this. For example, instead of Synthetic MRI, MR fingerprinting may be used. In MR fingerprinting, tissue quantitative values such as T1 values, T2 values, PD (Proton Density) values, etc. are derived by comparison with a database and simulation based on estimation.

Further, in the first and second embodiments described above, an example in which the technique disclosed by the present application is applied to an image processing apparatus has been described, but the embodiment is not limited to this. For example, the technology disclosed by the present application can also be applied to an MRI apparatus. Therefore, the embodiments of the MRI apparatus will be described below as third and fourth embodiments.

(Third embodiment)
FIG. 13 is a diagram showing a configuration example of the MRI apparatus 100 according to the third embodiment. For example, as shown in FIG. 13, the MRI apparatus 100 according to the present embodiment includes a static magnetic field magnet 1, a gradient magnetic field coil 2, a gradient magnetic field power supply 3, a transmission coil 4, a transmission circuit 5, a reception coil 6, a reception circuit 7, It has a pedestal 8, a bed 9, an input interface 10, a display 11, a memory circuit 12, and processing circuits 13-16.

The static magnetic field magnet 1 is formed in a hollow, substantially cylindrical shape (including one having an elliptical cross section perpendicular to the central axis of the cylinder), and generates a static magnetic field in the inner space. For example, the static magnetic field magnet 1 has a substantially cylindrical cooling container and a magnet such as a superconducting magnet immersed in a coolant (for example, liquid helium) filled in the cooling container. ing. Here, for example, the static magnetic field magnet 1 may use a permanent magnet to generate a static magnetic field. Further, for example, the static magnetic field magnet 1 is not formed in a substantially cylindrical shape, but has a so-called open type configuration in which a pair of magnets are arranged so as to face each other across an imaging space in which the subject S is arranged. may have

The gradient magnetic field coil 2 is formed in a hollow, substantially cylindrical shape (including one having an elliptical cross section perpendicular to the central axis of the cylinder), and is arranged inside the static magnetic field magnet 1 . The gradient magnetic field coil 2 includes three coils that generate gradient magnetic fields along mutually orthogonal x-, y-, and z-axes. Here, the x-axis, y-axis, and z-axis constitute an apparatus coordinate system unique to the MRI apparatus 100 . For example, the x-axis direction is set horizontally and the y-axis direction is set vertically. Also, the direction of the z-axis is set to be the same as the direction of the magnetic flux of the static magnetic field generated by the static magnetic field magnet 1 .

The gradient magnetic field power supply 3 supplies a current to each of the three coils included in the gradient magnetic field coil 2 to generate gradient magnetic fields along the x-, y-, and z-axes in the space inside the gradient magnetic field coil 2. generate. Gradient magnetic fields can be generated along the readout direction, the phase encoding direction, and the slice direction by appropriately generating gradient magnetic fields along the x-, y-, and z-axes, respectively.

Here, axes along each of the readout direction, phase encoding direction, and slice direction constitute a logical coordinate system for defining a slice region or volume region to be imaged. Hereinafter, the gradient magnetic field along the readout direction is called the readout gradient magnetic field, the gradient magnetic field along the phase encode direction is called the phase encode gradient magnetic field, and the gradient magnetic field along the slice direction is called the slice gradient magnetic field. .

Each gradient magnetic field is superimposed on the static magnetic field generated by the static magnetic field magnet 1 and used to give spatial position information to MR (Magnetic Resonance) signals. Specifically, the readout gradient magnetic field changes the frequency of the MR signal according to the position in the readout direction, thereby imparting positional information along the readout direction to the MR signal. Also, the phase-encoding gradient magnetic field changes the phase of the MR signal along the phase-encoding direction, thereby imparting positional information in the phase-encoding direction to the MR signal. When the imaging region is a slice region, the slice gradient magnetic field is used to determine the direction, thickness, and number of slice regions. By changing the phase of the MR signal using the MR signal, positional information along the slice direction is added to the MR signal.

The transmission coil 4 is an RF coil that applies an RF magnetic field to an imaging space in which the subject S is placed based on an RF (Radio Frequency) pulse signal output from the transmission circuit 5 . Specifically, the transmission coil 4 is formed in a hollow, substantially cylindrical shape (including one having an elliptical cross section perpendicular to the central axis of the cylinder), and is arranged inside the gradient magnetic field coil 2. . Based on the RF pulse signal output from the transmission circuit 5 , the transmission coil 4 applies an RF magnetic field to the imaging space formed in the space inside the transmission coil 4 .

The transmission circuit 5 outputs an RF pulse signal corresponding to the Larmor frequency to the transmission coil 4 .

The receiving coil 6 is an RF coil that receives MR signals emitted from the subject S. For example, the receiving coil 6 is attached to the subject S placed inside the transmitting coil 4 and receives MR signals emitted from the subject S under the influence of the RF magnetic field applied by the transmitting coil 4 . The receiving coil 6 then outputs the received MR signal to the receiving circuit 7 . For example, as the receiving coil 6, a dedicated coil is used for each region to be imaged. Here, the dedicated coils are, for example, a receiving coil for the head, a receiving coil for the neck, a receiving coil for the shoulder, a receiving coil for the chest, a receiving coil for the abdomen, a receiving coil for the lower extremities, and a spine. receiving coil, etc.

The receiving circuit 7 generates MR signal data based on the MR signal output from the receiving coil 6 and outputs the generated MR signal data to the processing circuit 14 .

Here, an example in which the transmission coil 4 applies an RF magnetic field and the reception coil 6 receives an MR signal will be described, but the form of each RF coil is not limited to this. For example, the transmission coil 4 may further have a reception function for receiving MR signals, and the reception coil 6 may further have a transmission function for applying an RF magnetic field. If the transmission coil 4 has a reception function, the reception circuit 7 also generates MR signal data from the MR signals received by the transmission coil 4 . Moreover, when the receiving coil 6 has a transmitting function, the transmitting circuit 5 also outputs the RF pulse signal to the receiving coil 6 .

The pedestal 8 accommodates the static magnetic field magnet 1 , the gradient magnetic field coil 2 and the transmission coil 4 . Specifically, the pedestal 8 has a cylindrical hollow bore B, and the static magnetic field magnet 1, the gradient magnetic field coil 2, and the transmission coil 4 are arranged so as to surround the bore B. , a static magnetic field magnet 1, a gradient magnetic field coil 2 and a transmission coil 4, respectively. Here, the space inside the bore B in the gantry 8 becomes an imaging space in which the subject S is arranged when the subject S is imaged.

The bed 9 has a top board 9a on which the subject S is placed. For example, the bed 9 is installed so that its longitudinal direction is parallel to the central axis of the static magnetic field magnet 1 .

The input interface 10 receives input operations of various instructions and various information from the operator. Specifically, the input interface 10 is connected to the processing circuit 16, converts an input operation received from the operator into an electric signal, and outputs the electric signal to the control circuit. For example, the input interface 10 includes a trackball for setting a region of interest (ROI), a switch button, a mouse, a keyboard, a touch pad for performing an input operation by touching an operation surface, a display screen and a touch panel. It is realized by a touch screen integrated with a pad, a non-contact input interface using an optical sensor, a voice input interface, or the like. In this specification, the input interface 10 is not limited to having physical operation parts such as a mouse and a keyboard. For example, the input interface 10 also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs the electrical signal to the control circuit.

The display 11 displays various information and various images. Specifically, the display 11 is connected to the processing circuit 16, converts various information and image data sent from the processing circuit 16 into electrical signals for display, and outputs the electrical signals. For example, the display 11 is realized by a liquid crystal monitor, a CRT (Cathode Ray Tube) monitor, a touch panel, or the like.

The storage circuit 12 stores various data. Specifically, the memory circuit 12 stores MR signal data and image data. For example, the storage circuit 12 is realized by a RAM (Random Access Memory), a semiconductor memory device such as a flash memory, a hard disk, an optical disk, or the like.

The processing circuit 13 has a bed control function 13a. For example, the processing circuitry 13 is implemented by a processor. The bed control function 13 a is connected to the bed 9 and outputs control electric signals to the bed 9 to control the operation of the bed 9 . For example, the bed control function 13a receives an instruction from the operator via the input interface 10 to move the tabletop 9a in the longitudinal direction, the vertical direction, or the horizontal direction, and moves the tabletop 9a according to the received instruction. The driving mechanism of the top plate 9a of the bed 9 is operated.

The processing circuit 14 has an execution function 14a. The execution function 14a drives the gradient magnetic field power supply 3, the transmission circuit 5, and the reception circuit 7 based on the sequence execution data output from the processing circuit 16, thereby acquiring MR signal data. Here, the sequence execution data is information defining a pulse sequence indicating a procedure for acquiring MR signal data. Specifically, the sequence execution data includes the timing and strength of the current supplied by the gradient magnetic field power supply 3 to the gradient magnetic field coil 2, the strength of the RF pulse signal supplied to the transmission coil 4 by the transmission circuit 5, and the This information defines the supply timing, the detection timing for detecting the MR signal by the receiving circuit 7, and the like. For example, processing circuitry 14 is implemented by a processor.

The executing function 14 a also receives MR signal data from the receiving circuit 7 as a result of executing various pulse sequences, and stores the received MR signal data in the storage circuit 12 . Note that the set of MR signal data received by executive function 14a is arranged two-dimensionally or three-dimensionally according to the positional information imparted by the readout magnetic field gradient, phase-encoding magnetic field gradient, and slice magnetic field gradient described above. Thus, it is stored in the storage circuit 12 as data forming the k-space.

The processing circuitry 15 generates an image based on the MR signal data stored in the storage circuitry 12 . Specifically, the processing circuit 15 reads the MR signal data stored in the storage circuit 12 by the execution function 14a, and performs post-processing, ie, reconstruction processing such as Fourier transform, on the read MR signal data to generate an image. do. The processing circuit 15 also causes the storage circuit 12 to store the image data of the generated image. For example, the processing circuitry 15 is implemented by a processor.

The processing circuit 16 has a main control function 16a. The main control function 16 a performs overall control of the MRI apparatus 100 by controlling each component of the MRI apparatus 100 . For example, the main control function 16a receives input of various parameters relating to the pulse sequence from the operator via the input interface 10, and generates sequence execution data based on the received parameters. The main control function 16a then transmits the generated sequence execution data to the processing circuit 14 to execute various pulse sequences. Further, for example, the main control function 16 a reads image data of an image requested by the operator from the storage circuit 12 and outputs the read image to the display 11 . For example, processing circuitry 16 is implemented by a processor.

With such a configuration, the MRI apparatus 100 according to the present embodiment has a function of computationally generating a calculated image of an arbitrary image type after imaging using an MR image and arbitrary parameter values. Here, the image type is, for example, a T1W image, a T2W image, a FLAIR image, or the like.

For example, the MRI apparatus 100 has a function of generating calculated images by synthetic MRI, like the image processing apparatus described in the first embodiment.

The MRI apparatus 100 according to this embodiment is configured to obtain a calculated image suitable for diagnosis.

Specifically, in the present embodiment, the memory circuit 12 stores, for each image type, the contrast between regions included in a plurality of brain regions in the same manner as the memory circuit 320 described in the first embodiment. Store information indicating known contrast ratios corresponding to image types. Note that the memory circuit 12 in the present embodiment is an example of a memory unit.

Furthermore, in the present embodiment, the storage circuit 12, like the storage circuit 320 described in the first embodiment, stores parameters that are conditions for setting parameter values used for generating a calculated image for each image type. Stores information that defines a range of values.

Further, in this embodiment, the processing circuit 15 has an acquisition function 15a, a division function 15b, a setting function 15c, and a generation function 15d. Note that the dividing function 15b in this embodiment is an example of a dividing unit. Also, the setting function 15c in this embodiment is an example of a setting unit. Also, the generation function 15d in this embodiment is an example of a generation unit. Note that the division unit, the setting unit, and the generation unit in this specification may be implemented by a mixture of hardware such as circuits and software.

The acquisition function 15a has the same function as the acquisition function 351 described in the first embodiment. However, in the first embodiment, the acquisition function 351 acquires the input image from the MRI apparatus 100 or the image storage apparatus 200, whereas the acquisition function 15a according to the present embodiment acquires the image of the subject from the storage circuit 12. An MR image of the brain is acquired as an input image.

The division function 15b has the same function as the division function 352 described in the first embodiment. Also, the setting function 15c has the same function as the setting function 353 described in the first embodiment. Also, the generation function 15d has the same function as the generation function 354 described in the first embodiment.

Here, in this embodiment, the input interface 10 and the display 11 respectively correspond to the input interface 330 and the display 340 described in the first embodiment.

Each function of the processing circuit 15 has been described above. For example, in the present embodiment, each processing function performed by the acquisition function 15a, the division function 15b, the setting function 15c, and the generation function 15d is stored in the storage circuit 12 in the form of a computer-executable program. The processing circuit 15 is a processor that implements a function corresponding to each program by reading out and executing the program from the storage circuit 12 . In other words, the processing circuit with each program read has each function shown in the processing circuit 15 of FIG.

Note that FIG. 13 shows an example in which the processing functions performed by the acquisition function 15a, the division function 15b, the setting function 15c, and the generation function 15d are realized by a single processing circuit 15, but the embodiment is similar to this. is not limited to For example, the processing circuit 15 may be configured by combining a plurality of independent processors, and each function may be realized by each processor executing a program. Moreover, each processing function of the processing circuit 15 may be appropriately distributed or integrated in a single or a plurality of processing circuits and implemented. Further, in the above-described third embodiment, the single memory circuit 12 stores the programs corresponding to the respective processing functions. The corresponding program may be read out from the storage circuit.

With such a configuration, according to the third embodiment, the same effects as those of the first embodiment can be obtained. That is, according to the third embodiment, the inspection time can be shortened by automatically setting the parameter values for obtaining the calculated image with the same contrast as the MR image, which has conventionally been obtained by imaging.

Thus, according to the third embodiment, a calculated image suitable for diagnosis can be obtained.

(Fourth embodiment)
FIG. 14 is a diagram showing a configuration example of the MRI apparatus 100 according to the fourth embodiment. In the fourth embodiment, the points different from the third embodiment will be mainly described, and constituent elements that play the same role as the constituent elements shown in FIG. detailed description is omitted. For example, as shown in FIG. 14, the MRI apparatus 100 according to the present embodiment includes a static magnetic field magnet 1, a gradient magnetic field coil 2, a gradient magnetic field power supply 3, a transmission coil 4, a transmission circuit 5, a reception coil 6, a reception circuit 7, A pedestal 8, a bed 9, an input interface 10, a display 11, a memory circuit 112, and processing circuits 13, 14, 115 and 16 are provided.

The storage circuit 112 stores various data. Specifically, the memory circuit 112 stores MR signal data and image data. For example, the storage circuit 112 is realized by a RAM (Random Access Memory), a semiconductor memory device such as a flash memory, a hard disk, an optical disk, or the like.

Processing circuitry 115 generates an image based on the MR signal data stored in storage circuitry 112 . Specifically, the processing circuit 115 reads the MR signal data stored in the storage circuit 112 by the execution function 14a, and performs post-processing, ie, reconstruction processing such as Fourier transform, on the read MR signal data to generate an image. do. The processing circuit 115 also causes the storage circuit 112 to store the image data of the generated image. For example, processing circuitry 115 is implemented by a processor.

With such a configuration, the MRI apparatus 100 according to the present embodiment has a function of computationally generating a calculated image of an arbitrary image type after imaging using an MR image and arbitrary parameter values. Here, the image type is, for example, a T1W image, a T2W image, a FLAIR image, or the like.

For example, the MRI apparatus 100 has a function of generating calculated images by synthetic MRI, like the image processing apparatus described in the second embodiment.

The MRI apparatus 100 according to this embodiment is configured to obtain a calculated image suitable for diagnosis.

Specifically, in the present embodiment, the memory circuit 112 stores, for each disease, information indicating a disease-related region among a plurality of brain regions, similarly to the memory circuit 1320 described in the second embodiment. memorize Note that the memory circuit 1320 in this embodiment is an example of a memory unit.

Further, in this embodiment, the processing circuit 115 has an acquisition function 15a, a division function 15b, a setting function 115c, a generation function 15d, and an update function 115e. Note that the dividing function 15b in this embodiment is an example of a dividing unit. Also, the setting function 115c in this embodiment is an example of a setting unit. Also, the generation function 15d in this embodiment is an example of a generation unit. Also, the update function 115e in this embodiment is an example of an update unit. Note that the dividing unit, setting unit, generating unit, and updating unit in this specification may be implemented by a mixture of hardware such as circuits and software.

The setting function 115c has the same function as the setting function 1353 described in the second embodiment. Also, the update function 115e has the same function as the update function 1355 described in the second embodiment.

Here, in this embodiment, the input interface 10 and the display 11 respectively correspond to the input interface 330 and the display 340 described in the second embodiment.

Each function of the processing circuit 115 has been described above. For example, in the present embodiment, each processing function performed by the acquisition function 15a, the division function 15b, the setting function 115c, the generation function 15d, and the update function 115e is stored in the storage circuit 112 in the form of a computer-executable program. ing. The processing circuit 115 is a processor that implements a function corresponding to each program by reading out and executing the program from the storage circuit 112 . In other words, the processing circuit with each program read has each function shown in the processing circuit 115 of FIG.

Note that FIG. 14 shows an example in which the processing functions performed by the acquisition function 15a, the division function 15b, the setting function 115c, the generation function 15d, and the update function 15e are realized by a single processing circuit 115. Embodiments are not limited to this. For example, the processing circuit 115 may be configured by combining a plurality of independent processors, and each function may be realized by executing a program by each processor. Moreover, each processing function of the processing circuit 115 may be appropriately distributed or integrated in a single or a plurality of processing circuits and implemented. Further, in the above-described first embodiment, the single memory circuit 112 stores the programs corresponding to the respective processing functions. The corresponding program may be read out from the storage circuit.

With such a configuration, according to the fourth embodiment, the same effects as those of the second embodiment can be obtained. That is, according to the fourth embodiment, by automatically setting the parameter values for obtaining a calculated image with a contrast that makes it easy to visually distinguish the target region, a calculated image with high diagnostic utility value can be obtained. Obtainable.

Thus, according to the fourth embodiment, a calculated image suitable for diagnosis can be obtained.

In each of the above-described embodiments, an example in which an image of the brain is targeted has been described. It is possible to apply In that case, for example, in each embodiment, the division function uses a template that divides the region of the target part based on the anatomical structure, function, etc., and fits the template to the input image. A region of the target part in the input image is divided into a plurality of regions. Alternatively, the division unit divides the region of the target part in the input image into a plurality of regions using various segmentation (region division) techniques.

Further, in each of the above-described embodiments, an example in which MR images are used has been described, but the embodiments are not limited to this. For example, even when using medical images captured by other image diagnostic equipment such as X-ray CT (Computed Tomography) equipment, ultrasonic diagnostic equipment, and X-ray diagnostic equipment, the same is true for image processing equipment and medical image diagnostic equipment. Embodiments are possible.

Further, the term "processor" used in the description of each embodiment described above is, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an application specific integrated circuit (ASIC). , programmable logic devices (e.g., Simple Programmable Logic Devices (SPLDs), Complex Programmable Logic Devices (CPLDs), and Field Programmable Gate Arrays (FPGAs)), etc. means Here, instead of storing the program in the memory circuit, the program may be configured to be directly embedded in the circuit of the processor. In this case, the processor implements its functions by reading and executing the program embedded in the circuit. Further, each processor of the present embodiment is not limited to being configured as a single circuit for each processor, and may be configured as one processor by combining a plurality of independent circuits to realize its function. good.

Here, the program executed by the processor is pre-installed in a ROM (Read Only Memory), a storage circuit, or the like and provided. This program is a file in a format that can be installed in these devices or in a format that can be executed, such as CD (Compact Disk)-ROM, FD (Flexible Disk), CD-R (Recordable), DVD (Digital Versatile Disk), etc. may be provided on a computer readable storage medium. Also, this program may be provided or distributed by being stored on a computer connected to a network such as the Internet and downloaded via the network. For example, this program is composed of modules including each functional unit described above. As actual hardware, the CPU reads out a program from a storage medium such as a ROM and executes it, so that each module is loaded onto the main storage device and generated on the main storage device.

According to at least one embodiment described above, a calculated image suitable for diagnosis can be obtained.

While several embodiments of the invention have been described, these embodiments have been 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, and modifications can be made without departing from the scope of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, as well as the scope of the invention described in the claims and equivalents thereof.

300, 1300 image processing device 350, 1350 processing circuit 351 acquisition function 352 division function 353, 1353 setting function 354 generation function 1355 update function

Claims (15)

an acquisition unit that acquires an MR image of the subject's brain captured by a magnetic resonance imaging device;
a division unit that divides the brain region in the MR image acquired by the acquisition unit into a plurality of regions;
a storage unit that stores information indicating a region related to the disease among the plurality of regions for each disease;
The parameter values used to generate the calculated image of the brain by synthetic MRI, the contrast relationship between the regions included in the plurality of regions in the calculated image, the image type of the calculated image or the subject A setting unit that sets a predetermined relationship for the disease of
a generation unit that generates the calculated image by the synthetic MRI using the quantitative image derived from the MR image acquired by the acquisition unit and the parameter values set by the setting unit;
with
The setting unit refers to the information stored in the storage unit, specifies a region related to the specified disease, and performs the set parameter values,
Image processing device. The storage unit stores information indicating a combination of at least two regions related to the disease for each disease,
The setting unit refers to the information stored in the storage unit, identifies a combination of regions related to the specified disease, and enhances the contrast between regions included in the identified combination. setting the parameter value;
The image processing apparatus according to claim 1 . an acquisition unit that acquires an MR image of the brain captured by a magnetic resonance imaging device;
a division unit that divides the brain region in the MR image acquired by the acquisition unit into a plurality of regions;
a storage unit that stores information indicating a region related to the disease among the plurality of regions for each disease;
A setting unit that sets parameter values used to generate the calculated image so that the contrast relationship between regions included in the plurality of regions in the calculated brain image generated by synthetic MRI is a predetermined relation. and,
A generation unit that generates the calculated image by the synthetic MRI using the quantitative image derived from the MR image acquired by the acquisition unit and the parameter value set by the setting unit,
The storage unit stores information indicating a combination of at least two regions related to the disease for each disease,
The setting unit refers to the information stored in the storage unit, specifies a combination of regions related to the specified disease, and performs the set parameter values,
Image processing device. further comprising an updating unit that updates information indicating the region related to the disease in response to an operation by an operator;
The image processing apparatus according to claim 1 , 2 or 3 . an acquisition unit that acquires an MR image of the subject's brain captured by a magnetic resonance imaging device;
a division unit that divides the brain region in the MR image acquired by the acquisition unit into a plurality of regions;
The parameter values used to generate the calculated image of the brain by synthetic MRI, the contrast relationship between the regions included in the plurality of regions in the calculated image, the image type of the calculated image or the subject A setting unit that sets a predetermined relationship for the disease of
a generation unit that generates the calculated image by the synthetic MRI using the quantitative image derived from the MR image acquired by the acquisition unit and the parameter values set by the setting unit;
with
The setting unit receives an operation from the operator to designate a disease-related region among the plurality of regions, and the contrast between the region designated by the operator and other regions is emphasized, setting the parameter value;
Image processing device. The setting unit sets the parameter value such that the contrast between the designated disease-related region and regions surrounding the region is emphasized.
The image processing device according to any one of claims 1 to 5 . an acquisition unit that acquires an MR image of the brain captured by a magnetic resonance imaging device;
a division unit that divides the brain region in the MR image acquired by the acquisition unit into a plurality of regions;
a storage unit that stores information indicating a region related to the disease among the plurality of regions for each disease;
A setting unit that sets parameter values used to generate the calculated image so that the contrast relationship between regions included in the plurality of regions in the calculated brain image generated by synthetic MRI is a predetermined relation. and,
A generation unit that generates the calculated image by the synthetic MRI using the quantitative image derived from the MR image acquired by the acquisition unit and the parameter value set by the setting unit,
The setting unit refers to the information stored in the storage unit, identifies a region associated with the specified disease, and enhances the contrast between the identified region and regions surrounding the region. setting the parameter value as
Image processing device. The setting unit receives an operation from an operator to designate a degree of contrast enhancement, and sets the parameter value so that the contrast between the specified region and the other region is emphasized at the designated degree of emphasis. to set the
The image processing apparatus according to claim 1 or 2 . The acquisition unit acquires a T1-weighted image captured by the magnetic resonance imaging apparatus using an MP2RAGE (Magnetization Prepared 2 Rapid Gradient Echo) sequence and a T1 map image derived from the T1-weighted image,
The dividing unit uses the T1-weighted image to divide the brain region into the plurality of regions,
The generating unit generates the calculated image using the T1 map image and the parameter value.
The image processing device according to any one of claims 1 to 8 . an acquisition unit that acquires an input image of the brain;
a division unit that divides the brain region in the input image acquired by the acquisition unit into a plurality of regions;
a storage unit that stores information indicating a region related to the disease among the plurality of regions for each disease;
a setting unit that sets parameter values used for generating the calculated image so that contrast relationships between regions included in the plurality of regions in the calculated brain image to be generated have a predetermined relationship;
a generation unit that generates the calculated image using the input image acquired by the acquisition unit and the parameter values set by the setting unit;
The storage unit stores information indicating a combination of at least two regions related to the disease for each disease,
The setting unit refers to the information stored in the storage unit, specifies a combination of regions related to the specified disease, and performs the set parameter values,
Image processing device. an acquisition unit that acquires an input image of the brain;
a division unit that divides the brain region in the input image acquired by the acquisition unit into a plurality of regions;
a storage unit that stores information indicating a region related to the disease among the plurality of regions for each disease;
a setting unit that sets parameter values used for generating the calculated image so that contrast relationships between regions included in the plurality of regions in the calculated brain image to be generated have a predetermined relationship;
a generation unit that generates the calculated image using the input image acquired by the acquisition unit and the parameter values set by the setting unit;
The setting unit refers to the information stored in the storage unit, identifies a region associated with the specified disease, and enhances the contrast between the identified region and regions surrounding the region. setting the parameter value as
Image processing device. a dividing unit that divides a region of the brain in an MR image of the brain into a plurality of regions;
a storage unit that stores information indicating a region related to the disease among the plurality of regions for each disease;
A setting unit that sets parameter values used to generate the calculated image so that the contrast relationship between regions included in the plurality of regions in the calculated brain image generated by synthetic MRI is a predetermined relation. and,
A generation unit that generates the calculated image by the synthetic MRI using the quantitative image derived from the MR image and the parameter value set by the setting unit,
The storage unit stores information indicating a combination of at least two regions related to the disease for each disease,
The setting unit refers to the information stored in the storage unit, specifies a combination of regions related to the specified disease, and performs the set parameter values,
Magnetic resonance imaging equipment. a dividing unit that divides a region of the brain in an MR image of the brain into a plurality of regions;
a storage unit that stores information indicating a region related to the disease among the plurality of regions for each disease;
A setting unit that sets parameter values used to generate the calculated image so that the contrast relationship between regions included in the plurality of regions in the calculated brain image generated by synthetic MRI is a predetermined relation. and,
A generation unit that generates the calculated image by the synthetic MRI using the quantitative image derived from the MR image and the parameter value set by the setting unit,
The setting unit refers to the information stored in the storage unit, identifies a region associated with the specified disease, and enhances the contrast between the identified region and regions surrounding the region. setting the parameter value as
Magnetic resonance imaging equipment. Acquiring an MR image of the brain imaged by a magnetic resonance imaging device,
dividing a region of the brain in an acquired MR image into a plurality of regions;
setting parameter values used to generate the calculated image so that the contrast relationship between regions included in the plurality of regions in the calculated image of the brain generated by synthetic MRI is a predetermined relationship;
generating the calculated image by the synthetic MRI using the quantitative image derived from the acquired MR image and the set parameter values;
let the computer do
referring to a storage unit storing information indicating a combination of at least two regions related to the disease among the plurality of regions for each disease, and identifying a combination of regions related to the designated disease; setting the parameter value such that the contrast between regions included in the combined combination is enhanced;
Image processing program. Acquiring an MR image of the brain imaged by a magnetic resonance imaging device,
dividing a region of the brain in an acquired MR image into a plurality of regions;
setting parameter values used to generate the calculated image so that the contrast relationship between regions included in the plurality of regions in the calculated image of the brain generated by synthetic MRI is a predetermined relationship;
generating the calculated image by the synthetic MRI using the quantitative image derived from the acquired MR image and the set parameter values;
let the computer do
For each disease, referring to a storage unit that stores information indicating a region related to the disease among the plurality of regions, a region related to the specified disease is specified, and the specified region and the region setting the parameter value such that the contrast between surrounding areas is enhanced;
Image processing program.

Images