JP6843669B2 - Medical image processing equipment, medical image processing methods, and medical image processing programs - Google Patents

Description

Embodiments of the present invention relate to a medical image processing apparatus, a medical image processing method, and a medical image processing program.

The medical image processing apparatus can appropriately perform image processing and display a medical image generated by a modality species such as CT (Computed Tomography) and MR (Magnetic Resonance). When a plurality of medical images are comparatively interpreted by an image reader, the medical image processing apparatus displays a plurality of medical images acquired under a plurality of imaging conditions (for example, non-contrast and contrast) with a single modality species. May be done. In that case, the medical image processing apparatus can align a plurality of medical images by using the coordinate information included in the DICOM (Digital Imaging and Communication in Medicine) information. This is because a plurality of medical images generated by a single modality species are generally generated by the same examination (study), so that the positions of the patients on the top plate can be considered to be almost the same.

In addition, it may not be possible to simply align the medical image using the coordinate information included in the DICOM information. The case is, for example, a case of displaying a plurality of medical images acquired in each of a plurality of modality species. When the medical image processing apparatus displays a plurality of medical images acquired in a plurality of modality species, for example, a CT image and an MR image, the CT image is analyzed by performing image analysis and anatomically identifying the same position. And the MR image are aligned. Since CT images and MR images are generally generated by different examinations, the position of the patient on the top plate differs depending on the position of the patient and which of Head_First and Foot_First is adopted. is there.

Here, consider a case where the medical image processing apparatus displays a plurality of medical images obtained by each modality type under a plurality of imaging conditions, which are related to a plurality of modality species. Specifically, the CT / non-contrast image and the CT / contrast image acquired under the imaging conditions "non-contrast" and "contrast" of the modality type "CT", and the imaging condition "T1" and the imaging condition "T1" of the modality type "MR", respectively. This is a case where the medical image processing apparatus displays the MR / T1 image and the MR / T2 image acquired in “T2”, respectively. In that case, the medical image processing apparatus uses the coordinate information included in the DICOM information as described above to align the CT / non-contrast image and the CT / contrast image, and to position the MR / T1 image and the MR / T2 image. Each can be matched.

However, although the alignment between a plurality of modality species is performed by image analysis as described above, the target of the alignment is a combination of CT / non-contrast image and MR / T1 image, and CT / non-contrast image and MR. There are four possible combinations: a combination of T2 images, a combination of CT / contrast image and MR / T1 image, and a combination of CT / contrast image and MR / T2 image. Therefore, the medical image processing apparatus must select an appropriate combination as the alignment target.

As described above, since the alignment between a plurality of modality species is performed by image analysis, the alignment accuracy changes depending on which combination is selected as the alignment target.

Japanese Unexamined Patent Publication No. 2010-063514

An object to be solved by the present invention is to provide a medical image processing apparatus, a medical image processing method, and a medical image processing program capable of efficiently selecting an arbitrary combination from a plurality of combinations of image types.

The medical image processing apparatus according to the present embodiment acquires a plurality of medical images belonging to a plurality of image types and a plurality of alignment accuracy corresponding to a plurality of combinations of the plurality of image types from a storage unit. It has means and a selection means for selecting a predetermined combination corresponding to a predetermined alignment accuracy from the plurality of combinations.

The schematic diagram which shows the structural example of the medical image processing apparatus which concerns on this embodiment. The block diagram which shows the function of the medical image processing apparatus which concerns on this embodiment. The figure which shows the operation of the medical image processing apparatus which concerns on this embodiment as a flowchart. The figure which shows an example of the correspondence table which the storage circuit stores in advance in the medical image processing apparatus which concerns on this embodiment. (A) is a diagram showing an example of m medical images belonging to m image types in the medical image processing apparatus according to the present embodiment, and (B) is a diagram showing an example of m medical images belonging to the m image types, and (B) is the medical image processing apparatus according to the present embodiment. The figure which shows the example of m medical image sets belonging to m image types. FIG. 6 is a conceptual diagram for explaining r combinations extracted from n combinations of image types in the medical image processing apparatus according to the present embodiment. In the medical image processing apparatus according to the present embodiment, the figure which shows the combination of r kinds of image types acquired from the correspondence table of FIG. 4 and the alignment accuracy of r corresponding pieces as a table. (A) and (B) are conceptual diagrams for explaining the alignment of steps ST7 and ST8 of FIG. 3 in the medical image processing apparatus according to the present embodiment. The figure which shows the display example of two medical images at the time of performing comparative interpretation in the medical image processing apparatus which concerns on this embodiment. The figure which shows the display example of two medical images at the time of performing comparative interpretation in the medical image processing apparatus which concerns on this embodiment. The figure which shows the 1st modification of the correspondence table shown in FIG. 4 in the medical image processing apparatus which concerns on this embodiment. The figure which shows the 2nd modification of the correspondence table shown in FIG. 4 in the medical image processing apparatus which concerns on this embodiment. The figure which shows the 3rd modification of the correspondence table shown in FIG. 4 in the medical image processing apparatus which concerns on this embodiment. The figure which shows the 4th modification of the correspondence table shown in FIG. 4 in the medical image processing apparatus which concerns on this embodiment.

The medical image processing apparatus, the medical image processing method, and the medical image processing program according to the present embodiment will be described with reference to the accompanying drawings.

FIG. 1 is a schematic view showing a configuration example of a medical image processing apparatus according to the present embodiment.

FIG. 1 shows a medical image processing device 1 according to the present embodiment. The medical image processing device 1 is a medical image management device (image server), a workstation, an image interpretation terminal, or the like, and is provided on a medical image system connected via a network. The medical image processing device 1 may be an offline device.

The medical image processing device 1 includes a control unit (for example, a processing circuit) 11, a storage unit (for example, a storage circuit) 12, an input unit (for example, an input circuit) 13, a display unit (for example, a display) 14, and a communication unit (for example). For example, a communication control circuit) 15 is provided.

The processing circuit 11 means a processing circuit such as a dedicated or general-purpose CPU (Central Processing Unit) or MPU (Micro Processor Unit), an application specific integrated circuit (ASIC), and a programmable logic device. To do. Examples of the programmable logic device include a simple programmable logic device (SPLD: Simple Programmable Logic Device), a compound programmable logic device (CPLD: Complex Programmable Logic Device), and a field programmable gate array (FPGA: Field Programmable Gate Array). The circuit can be mentioned. The processing circuit 11 realizes a function described later by reading and executing a program stored in the storage circuit 12 or directly incorporated in the processing circuit 11.

Further, the processing circuit 11 may be composed of a single processing circuit or a combination of a plurality of independent processing circuits. In the latter case, the plurality of storage circuits 12 may store programs corresponding to the functions of the plurality of processing circuits, respectively, or one storage circuit 12 may store programs corresponding to the functions of the plurality of processing circuits. It may be something to remember.

The storage circuit 12 is composed of a semiconductor memory element such as a RAM (Random Access Memory) and a flash memory (Flash Memory), a hard disk, an optical disk, and the like. The storage circuit 12 may be composed of a portable medium such as a USB (Universal Serial Bus) memory and a DVD (Digital Video Disk). The storage circuit 12 stores various processing programs (including an OS (Operating System) and the like in addition to the application program) used in the processing circuit 11, data necessary for executing the program, and image data. In addition, the OS may include a GUI (Graphical User Interface) that makes extensive use of graphics for displaying information on the display 14 to an operator such as an image reader and allows basic operations to be performed by an input circuit 13.

Further, the storage circuit 12 stores each medical image to which DICOM information is attached and a correspondence table (shown in FIG. 4) showing the relationship between the combination of image types and the alignment accuracy.

The input circuit 13 is a circuit for inputting a signal from an input device that can be operated by an operator, and here, it is assumed that the input device itself is also included in the input circuit 13. Input devices include pointing devices (eg, mice), keyboards, various buttons, and the like. When the input device is operated by the operator, the input circuit 13 generates an input signal corresponding to the operation and outputs the input signal to the processing circuit 11. The medical image processing device 1 may include a touch panel in which the input device is integrally configured with the display 14.

The display 14 is a display device such as a liquid crystal display panel, a plasma display panel, and an organic EL (Electro Luminescence) panel. The display 14 displays a tomographic image generated under the control of the processing circuit 11 and an image on which information on the degree of influence is superimposed.

The communication control circuit 15 is composed of connectors that meet the parallel connection specifications and the serial connection specifications. The communication control circuit 15 has a function of performing communication control according to each standard and being able to connect to a network through a telephone line, whereby the medical image processing device 1 can be connected to the network.

FIG. 2 is a block diagram showing the functions of the medical image processing device 1.

When the processing circuit 11 executes the program, the medical image processing apparatus 1 has the acquisition means (for example, acquisition function) 11A, the selection means (for example, selection function) 11B, and the alignment means (for example, alignment function) 11C. Functions as. All or part of the functions 11A to 11C may be provided in the medical image processing device 1 as hardware such as an ASIC.

The acquisition function 11A includes a function of acquiring m medical images belonging to m (m = 2, 3, ...) Image types from the storage circuit 12. As another example, the acquisition function 11A may acquire m medical images from an external storage circuit (not shown) of the medical image processing device 1 via the communication control circuit 15. The image type includes at least a modality type (study type) which is a parameter capable of classifying a medical image by DICOM information. Preferably, the image type includes, in addition to the modality type, an imaging condition (series type) which is a parameter capable of classifying a medical image based on DICOM information. That is, the m medical images belonging to the m image types are (1) m medical images belonging to different modality species (for example, CT image and MR image), or (2) the same modality species. There are cases where m medical images (for example, CT / non-contrast images and CT / contrast images) belong to different imaging conditions, and (3) m medical images which are a combination thereof. Hereinafter, the case of (3) above will be described.

In addition to the modality type and imaging conditions, parameters that can classify medical images based on DICOM information can be added to the image type. For example, the image type can include information such as an imaging site and an imaging date and time, which are parameters that can classify medical images based on DICOM information.

Further, the acquisition function 11A includes a function of acquiring n alignment accuracy corresponding to each of n combinations of m image types from the storage circuit 12. As another example, the acquisition function 11A may acquire n alignment accuracy from an external storage circuit (not shown) of the medical image processing device 1 via the communication control circuit 15. Here, n is represented by _m C _2.

The selection function 11B selects a predetermined combination corresponding to a predetermined alignment accuracy from the n alignment accuracy acquired by the acquisition function 11A from the combination of n image types acquired by the acquisition function 11A. Including functions.

For example, the selection function 11B displays the n alignment accuracy acquired by the acquisition function 11A and the n combinations corresponding to the n alignment accuracy on the display 14 in association with each other. According to the instruction input from the input circuit 13 by the operation of, a predetermined combination corresponding to a predetermined alignment accuracy is selected. As another example, the selection function 11B is displayed on an external display (not shown) of the medical image processing apparatus 1 in association with n alignment accuracy and n combinations via the communication control circuit 15. A predetermined combination corresponding to a predetermined alignment accuracy is selected according to an instruction input from an external input circuit (not shown) of the medical image processing device 1 via the communication control circuit 15 by the operation of the operator. Alternatively, the selection function 11B selects the maximum alignment accuracy from the n alignment accuracy acquired by the acquisition function 11A, and selects the combination corresponding to the maximum alignment accuracy as a predetermined combination.

The alignment function 11C has a function of extracting two medical images belonging to two image types corresponding to a predetermined combination selected by the selection function 11B from a plurality of medical images acquired by the acquisition function 11A. Including. The alignment function 11C includes a function of aligning the two extracted medical images.

The specific operations of the functions 11A to 11C will be described later with reference to FIGS. 3 to 10.

FIG. 3 is a diagram showing the operation of the medical image processing device 1 as a flowchart.

First, the storage circuit 12 of the medical image processing device 1 stores in advance a correspondence table showing the relationship between the combination of image types and the alignment accuracy.

FIG. 4 is a diagram showing an example of a correspondence table stored in advance by the storage circuit 12 in the medical image processing device 1.

FIG. 4 shows 6 combinations out of 10 combinations for 5 image types. That is, in FIG. 4, the combination between the same modality species is omitted. Further, FIG. 4 shows the alignment accuracy (for example, the score out of 100 points) corresponding to each of the six combinations. Here, the alignment accuracy is quantified by the operator by performing alignment on a plurality of medical images having different image types in advance by image analysis and comparing the two medical images after the alignment. It is a thing.

Further, as shown in FIG. 4, the alignment accuracy "100" is associated with the combination of the image type "CT / contrast" and the image type "MR / T1". Here, the imaging condition "T1" is an imaging condition for collecting an image having a contrast that emphasizes the difference in the vertical relaxation time (T1) between tissues. Further, the alignment accuracy "90" is associated with the combination of the image type "CT / non-contrast" and the image type "MR / T2". Here, the imaging condition "T2" is an imaging condition for collecting an image having contrast that emphasizes the difference in lateral relaxation time (T2) between tissues. Further, the alignment accuracy "80" is associated with the combination of the image type "CT / contrast" and the image type "MR / DWI (Diffusion Weighted Image)". Here, the imaging condition "DWI" is an imaging condition for collecting an image in which the diffusion effect is emphasized. The relationship between the other combinations and the alignment accuracy is as shown in the figure.

The alignment accuracy corresponding to each combination may be set for each medical institution such as a hospital, or may be set for each operator.

Returning to the description of FIG. 3, the acquisition function 11A has m image types for a predetermined patient stored in advance in the storage circuit 12 when a plurality of medical images are comparatively read by an operator such as an image reader. Acquire m medical images belonging to (step ST1). The acquisition function 11A is used for medical purposes according to the patient ID (Identification) related to a predetermined patient, which is the information included in the DICOM information, the modality type, the imaging condition, the imaging site, the imaging date and time, etc., which are the information included in the DICOM information. The search range of images can be limited.

FIG. 5A is a diagram showing an example of m medical images belonging to m image types in the medical image processing apparatus 1.

FIG. 5 (A) shows 4 (m = 4) medical images belonging to 4 (m = 4) image types for a given patient A. The four medical images include two CT images corresponding to the modality type "CT" and two MR images corresponding to the modality type "MR".

The two CT images are a CT / non-contrast image acquired by the image type "CT / non-contrast" which is the modality type "CT" and the imaging condition "non-contrast", and the modality type "CT" and the imaging condition. Includes CT / contrast images acquired by the image type "CT / contrast" which is "contrast". The two MR images are an MR / T1 image acquired by the image type "MR / T1" having the modality type "MR" and the imaging condition "T1", and the modality type "MR" and the imaging condition "DWI". Includes MR / DWI images acquired by the image type "MR / DWI". Although the CT image and the MR image will be described here, the present invention is not limited to that case. For example, an ultrasonic image generated by an ultrasonic device, a nuclear medicine image generated by a nuclear medicine device such as PET (Positron Emission Tomography), or the like may be used.

The number of medical images belonging to each image type is not limited to one as shown in FIG. 5 (A). In other words, there is one CT / non-contrast image in the image type "CT / non-contrast", one CT / contrast image in the image type "CT / contrast", and the image type "MR / T1". It is not limited to the case where one MR / T1 image is present in the image type and one MR / DWI image is present in the image type “MR / DWI”. There may be a case where a plurality of medical images are present in at least one image type of the plurality of image types. FIG. 5B, which is an example thereof, is a diagram showing an example of m medical image sets belonging to m image types in the medical image processing apparatus 1.

FIG. 5B shows a set of 4 (m = 4) medical images belonging to 4 (m = 4) image types for a given patient A. Each medical image set includes a plurality of medical images as a plurality of slice images. Hereinafter, unless otherwise specified, the case of FIG. 5A will be described.

Returning to the description of FIG. 3, the acquisition function 11A acquires n combinations of m image types acquired in step ST1 (step ST2). Here, n is represented by _m C _2. The acquisition function 11A extracts r (r ≦ n) combinations from the n combinations of image types acquired in step ST2 (step ST3). r is defined when excluding a combination of image species related to the same modality species.

FIG. 6 is a conceptual diagram for explaining r combinations extracted from n combinations of image types in the medical image processing apparatus 1.

FIG. 6 shows 6 (n = 6) combinations for 4 (m = 4) image types. Further, in order to exclude combinations of image types related to the same modality species, 4 (r = 4) combinations are extracted from the combinations of 6 image types. Needless to say, as long as the correspondence table shown in FIG. 4 includes a combination of the same modality species, the case of r = n may be used.

Returning to the description of FIG. 3, the acquisition function 11A corresponds to each of the r combinations of image types extracted in step ST3 from the correspondence table (shown in FIG. 4) stored in advance in the storage circuit 12. Acquire the alignment accuracy of the pieces (step ST4).

FIG. 7 is a diagram showing as a table the combinations of r types of image types acquired from the correspondence table of FIG. 4 and the corresponding r alignment accuracy in the medical image processing apparatus 1.

FIG. 7 shows 4 (r = 4) combinations of image types obtained from the correspondence table shown in FIG. 4 for a given patient. FIG. 7 shows a combination of the image type “CT / contrast” and the image type “MR / T1”, a combination of the image type “CT / contrast” and the image type “MR / DWI”, and the image type “CT / non-contrast”. And the combination of the image type "MR / T1" and the combination of the image type "CT / non-contrast" and the image type "MR / DWI" are shown.

Further, FIG. 7 shows the alignment accuracy of four pieces corresponding to each of the four combinations between the modality types “CT” and “MR” in the correspondence table shown in FIG. Specifically, FIG. 7 shows the alignment accuracy "100" corresponding to the combination of the image type "CT / contrast" and the image type "MR / T1", and the image type "CT / contrast" and the image type "MR / T1". Alignment accuracy "80" corresponding to the combination of "DWI", alignment accuracy "70" corresponding to the combination of image type "CT / non-contrast" and image type "MR / T1", and image type "CT / non-contrast" The alignment accuracy "50" corresponding to the combination of "contrast" and the image type "MR / DWI" is shown.

Returning to the description of FIG. 3, the selection function 11B corresponds to a predetermined alignment accuracy among the r alignment accuracy acquired in step ST4 from the combination of r kinds of image types extracted in step ST3. A predetermined combination is selected (step ST5).

For example, in step ST5, the selection function 11B displays the table shown in FIG. 7 on the display 14, and according to the instruction input from the input circuit 13 by the operation of the operator, a predetermined combination corresponding to a predetermined alignment accuracy is obtained. select. Alternatively, the selection function 11B selects the maximum alignment accuracy from the table shown in FIG. 7, and selects a combination of image types corresponding to the maximum alignment accuracy as a predetermined combination.

The alignment function 11C extracts two medical images corresponding to a predetermined combination selected in step ST5 from the m medical images acquired in step ST1 as alignment targets (step ST6). The alignment function 11C aligns the two medical images extracted in step ST6 by performing image analysis and anatomically identifying the same position (step ST7). This is because the two medical images generated by different examinations cannot be simply aligned with the medical images using the coordinate information included in the DICOM information.

The alignment function 11C uses the coordinate information included in the DICOM information to align the medical image related to the same modality type as each medical image extracted in step ST6 with each medical image extracted in step ST6. (Step ST8). This is because medical images generated by the same modality species are generated by the same examination.

8 (A) and 8 (B) are conceptual diagrams for explaining the alignment of steps ST7 and ST8 of FIG. 3 in the medical image processing apparatus 1. Note that FIG. 8 (A) is based on FIG. 5 (A), and FIG. 8 (B) is based on FIG. 5 (B).

Based on FIG. 7, it is assumed that the combination of the image type "CT / contrast" and the image type "MR / T1", which has the maximum alignment accuracy, is selected. In that case, as shown in FIG. 8A, the alignment function 11C includes a CT / contrast image corresponding to the image type “CT / contrast” and an MR / T1 image corresponding to the image type “MR / T1”. (Step ST7 shown in FIG. 3).

Further, as shown in FIG. 8A, the alignment function 11C aligns the CT / contrast image after alignment with the CT / non-contrast image corresponding to the image type “CT / non-contrast”. (Step ST8 shown in FIG. 3). Further, as shown in FIG. 8A, the alignment function 11C aligns the MR / T1 image after alignment with the MR / DWI image corresponding to the image type “MR / DWI” (FIG. FIG. Step ST8 shown in 3.

When FIG. 5 (B) is adopted instead of FIG. 5 (A), that is, there are a plurality of CT / contrast images in the image type "CT / contrast", and a plurality of CT / contrast images are present in the image type "MR / T1". When an MR / T1 image is present, the alignment function 11C has an image selected from a plurality of CT / contrast images as shown in FIG. 8 (B) and an image selected from a plurality of CT / contrast images and as shown in FIG. 8 (B). Alignment is performed with a plurality of MR / T1 images (step ST7 shown in FIG. 3). That is, the alignment function 11C determines which of the plurality of MR / T1 images matches the image selected from the plurality of CT / contrast images by image analysis. As a result, the alignment function 11C can align the plurality of CT / contrast images with the plurality of MR / T1 images.

Alternatively, when the alignment function 11C is adopted in FIG. 5 (B), the alignment function 11C includes an image selected from a plurality of CT / contrast images shown in FIG. 8 (B) and a plurality of images shown in FIG. 8 (B). It is generated from volume data based on MR / T1 images (hereinafter referred to as "MR / T1 volume data"), and alignment is performed between the selected image and a plurality of MPR (Multi-Planar Reconstruction) images having substantially parallel cross sections. (Step ST7 shown in FIG. 3). That is, the alignment function 11C determines which of the plurality of MPR images matches the image selected from the plurality of CT / contrast images by image analysis. As a result, the plurality of CT / contrast images will be aligned with the MR / T1 volume data. The alignment function 11C may align volume data based on a plurality of CT / contrast images (hereinafter referred to as “CT / contrast volume data”) with a plurality of MR / T1 images. The CT / contrast volume data and the MR / T1 volume data may be aligned.

Returning to the description of FIG. 3, the alignment function 11C causes the two medical images after alignment to be displayed on the display 14 (step ST9).

9 and 10 are diagrams showing a display example of two medical images when performing comparative image interpretation in the medical image processing device 1.

FIG. 9 shows a CT / contrast image and an MR / T1 image that are displayed in parallel when comparative interpretation is performed and have the same patient ID and imaging site but different imaging dates and times. FIG. 10 shows a CT / contrast image and an MR / T1 image having the same patient ID and imaging site but different imaging dates and times, which are superimposed and displayed when performing comparative image interpretation. By displaying the medical image that has been aligned with high alignment accuracy in this way, the efficiency and accuracy of the comparative interpretation of the image reader are improved.

Further, in the case shown in FIG. 8B, that is, when there are a plurality of CT / contrast images in the image type "CT / contrast" and a plurality of MR / T1 images are present in the image type "MR / T1". It is preferable that the alignment function 11C aligns a plurality of CT / contrast images with MR / T1 volume data. In that case, the alignment function 11C parallelizes or parallels the CT / contrast image selected from the plurality of CT / contrast images after the alignment and the MPR image having almost the same cross section as the selected image based on the MR / T1 volume data. Overlapping display. It should be noted that the alignment function 11C may be used to align the CT / contrast volume data with a plurality of MR / T1 images, or the CT / contrast volume data with the MR / T1 volume data. Needless to say.

As described above, according to the medical image processing apparatus 1, 4 (r = 4) shown in FIG. 7 regarding 4 (m = 4) image types shown in FIG. 5 (A) (or FIG. 5 (B)). From the individual combinations, a combination with high alignment accuracy can be efficiently selected. Further, according to the medical image processing apparatus 1, as shown in FIGS. 9 and 10, by displaying two medical images that have been aligned with high alignment accuracy, the efficiency of comparative interpretation of the image reader is achieved. And accuracy can be improved.

(First modification)
The correspondence table stored in advance in the storage circuit 12 is not limited to the correspondence table shown in FIG. For example, the acquisition function 11A may update the alignment accuracy of the correspondence table by feedback from an operator such as an image reader via the input circuit 13. In that case, the alignment accuracy corresponding to each combination may be updated for each medical institution such as a hospital, or may be updated for each operator.

FIG. 11 is a diagram showing a first modification of the correspondence table shown in FIG. 4 in the medical image processing device 1.

As shown in FIG. 11, the alignment accuracy "80" corresponding to the combination of the image type "CT / contrast" and the image type "MR / DWI" has been updated to "95". As a result, the order of the positioning accuracy corresponding to the combination of the image type "CT / contrast" and the image type "MR / DWI" is raised by one.

According to the first modification of the medical image processing device 1, in addition to the effect of the medical image processing device 1 described above, by updating the alignment accuracy of the correspondence table, it is possible to flexibly respond to a change in the actual alignment accuracy.

(Second modification)
The correspondence table stored in advance in the storage circuit 12 is not limited to the correspondence table shown in FIG. For example, in the correspondence table, the imaging conditions of the image types may include secondary types in addition to T1, T2, and DWI. For example, imaging conditions include cDWI (Computed DWI) and the like. The image generated by cDWI is called a computational diffusion-weighted image, and is estimated as a higher b-value image by analyzing two images with two different b-values.

FIG. 12 is a diagram showing a second modification of the correspondence table shown in FIG. 4 in the medical image processing apparatus 1.

As shown in FIG. 12, the alignment accuracy "95" is associated with the combination of the image type "CT / contrast" and the image type "MR / cDWI (b = 500)". The alignment accuracy may be associated with each of the plurality of b values of cDWI. Further, depending on the medical image processing device 1, it may not be possible to generate a cDWI image. In that case, the selection function 11B may select a combination of image types that does not include the imaging condition "cDWI".

According to the second modification of the medical image processing device 1, in addition to the effect of the medical image processing device 1 described above, the accuracy of selecting the combination is improved by subdividing the imaging conditions in the correspondence table.

(Third variant)
The correspondence table stored in advance in the storage circuit 12 is not limited to the correspondence table shown in FIG. For example, a plurality of correspondence tables according to the patient's attributes such as the patient's gender and age, which are parameters that can classify medical images based on DICOM information, may be used.

FIG. 13 is a diagram showing a third modification of the correspondence table shown in FIG. 4 in the medical image processing apparatus 1.

FIG. 13 shows four correspondence tables for each gender and age range. The two left and right correspondence tables in the upper row are for male patients. The two left and right correspondence tables at the bottom are for female patients. The two upper and lower correspondence tables on the left side are for patients aged 21 to 30 years. The two upper and lower correspondence tables on the right side are for patients aged 31 to 60 years.

Then, the acquisition function 11A selects a correspondence table according to the attribute of a predetermined patient from the four correspondence tables. The acquisition function 11A acquires n alignment accuracy corresponding to each of n combinations for m image types from the selected correspondence table.

According to the third modification of the medical image processing device 1, in addition to the effect of the medical image processing device 1 described above, the accuracy of selection of the combination is improved by using the correspondence table according to the attributes of the patient.

(Fourth modification)
The correspondence table stored in advance in the storage circuit 12 is not limited to the correspondence table shown in FIG. For example, in the correspondence table, the imaging conditions include X-ray conditions such as dose (tube current) in CT, which is a parameter that can classify medical images based on DICOM information, in addition to imaging methods such as “contrast” and “T1”. May include. The imaging method is also called an imaging protocol.

FIG. 14 is a diagram showing a fourth modification of the correspondence table shown in FIG. 4 in the medical image processing apparatus 1.

As shown in FIG. 14, for the modality type "CT" and the imaging method "contrast", the three tube currents "200 [mA]", "100 [mA]", and "50 [mA]" as X-ray conditions. "Is set. In general, the higher the dose, the higher the alignment accuracy with other medical images.

Then, the acquisition function 11A acquires n positioning accuracys corresponding to n combinations of m image types from the correspondence table. For example, the acquisition function 11A acquires the alignment accuracy and the like corresponding to the combination of the image type "CT / contrast / 200 mA" and the image type "MR / T1" from the correspondence table.

According to the fourth modification of the medical image processing device 1, in addition to the effect of the medical image processing device 1 described above, the accuracy of selection of the combination can be improved by subdividing the imaging conditions in the correspondence table into the imaging method and the X-ray conditions. improves.

According to the medical image processing apparatus, the medical image processing method, and the medical image processing program of at least one embodiment described above, any combination can be efficiently selected from a plurality of combinations of image types.

Although some embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

1 ... Medical image processing device 11 ... Processing circuit 12 ... Storage circuit 13 ... Input circuit 14 ... Display 11A ... Acquisition function 11B ... Selection function 11C ... Alignment function

Claims (12)

An acquisition means for acquiring a plurality of medical images belonging to a plurality of image types and a plurality of alignment accuracy corresponding to a plurality of combinations of different image types from a storage unit.
A selection means for selecting a predetermined combination corresponding to a predetermined alignment accuracy among the plurality of alignment accuracy from the plurality of combinations.
From the acquired plurality of medical images, a plurality of medical images belonging to the image type corresponding to the predetermined combination are extracted, the extracted plurality of medical images are aligned, and each medical image after the alignment is performed. And an alignment means for aligning each medical image with another medical image belonging to the same image type.
Medical image processing device having. The alignment means extracts a plurality of medical images belonging to different modality species as a plurality of medical images belonging to the image types corresponding to the predetermined combination .
The medical image processing apparatus according to claim 1. The selection means displays the plurality of alignment accuracy on the display unit, and selects the predetermined combination in response to an instruction from the input unit.
The medical image processing apparatus according to claim 1 or 2. The selection means selects the maximum of the plurality of alignment accuracy as the predetermined combination.
The medical image processing apparatus according to any one of claims 1 to 3. The image species include at least modality species.
The medical image processing apparatus according to any one of claims 1 to 4. The image type includes the modality type and imaging conditions, and the acquired plurality of medical images include a plurality of medical images belonging to different modality species and a plurality of medical images belonging to the same modality species and different imaging conditions. Including,
The medical image processing apparatus according to claim 5. The imaging condition includes the modality type, an imaging protocol as the imaging condition, and an X-ray condition, and the plurality of medical images acquired belong to the same modality type and different X-ray conditions with the same imaging protocol. Includes multiple medical images,
The medical image processing apparatus according to claim 6. The storage unit stores in advance a correspondence table in which the combination of the image types and the alignment accuracy are associated with each other.
The medical image processing apparatus according to any one of claims 1 to 7. The acquisition means updates the alignment accuracy of the correspondence table stored in the storage unit.
The medical image processing apparatus according to claim 8. The storage unit stores in advance a plurality of correspondence tables according to the attributes of the patient as the correspondence table.
The medical image processing apparatus according to claim 8 or 9. A medical image processing method using a device equipped with a control unit and a storage unit.
The control unit
From the storage unit, it acquires a plurality of medical images belonging to a plurality of image type, and a plurality of positioning accuracy corresponding to the combination of plural kinds of different image types,
The combination of the plurality of ways, selects a predetermined combination corresponding to a predetermined positioning accuracy of the plurality of alignment accuracy,
From the plurality of acquired medical images, a plurality of medical images belonging to the image type corresponding to the predetermined combination are extracted.
Aligning the plurality of extracted medical images,
Align each medical image after the alignment with another medical image belonging to the same image type as each medical image.
Medical image processing method. On the computer
A function to acquire a plurality of medical images belonging to a plurality of image types and a plurality of alignment accuracy corresponding to a plurality of combinations of different image types from a storage unit.
A function of selecting a predetermined combination corresponding to a predetermined alignment accuracy from the plurality of alignment accuracy from the plurality of combinations, and
A function of extracting a plurality of medical images belonging to an image type corresponding to the predetermined combination from the acquired plurality of medical images, and
The function of aligning a plurality of extracted medical images and
A function for aligning each medical image after the alignment with another medical image belonging to the same image type as each medical image, and
A medical image processing program that realizes.

Images