JP6645810B2 - Medical image processing apparatus, medical image processing method, medical image processing system, and medical image processing program - Google Patents

Description

  Embodiments of the present invention generally relate to the field of medical image processing, and more specifically, to a medical image processing apparatus, a medical image processing method, a medical image processing system, and a medical image processing program.

  In the identification diagnosis based on the medical image, the diagnosis accuracy for the current medical image is improved by referring to the past image (reference image) in which the diagnosis result is specified. Usually, a conventional medical image to be referred to is searched from a reference image database based on the label of the reference image or by comparing the image characteristics of the current medical image and the image characteristics of the reference image as a whole.

JP 2007-209583 A JP 2011-067253 A

  An object of the present invention is to provide a medical image processing apparatus, a medical image processing method, a medical image processing system, and a medical image processing program that can specify a reference image useful for diagnosis.

  The medical image processing device according to the embodiment includes a positioning unit, a deformation unit, a first setting unit, a second setting unit, and a search unit. The positioning unit positions the medical image and each of the plurality of reference images. The deforming unit deforms the medical image based on a positioning result by the positioning unit. The first setting unit sets a first region of interest in the deformed medical image. The second setting unit sets a second region of interest corresponding to the first region of interest to at least two of the plurality of reference images. The search unit searches for a reference image similar to the image in the first region of interest from the reference image in which the second region of interest is set.

FIG. 1 is a block diagram illustrating an example of the arrangement of an image processing apparatus according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating an arrangement example of an image processing apparatus according to another embodiment. FIG. 3A is a diagram illustrating an example of a predetermined template for setting a region of interest. FIG. 3B is a diagram illustrating an example of a predetermined template for setting a region of interest. FIG. 4 is a block diagram illustrating an arrangement example of an image processing apparatus according to another embodiment. FIG. 5 is a block diagram illustrating an arrangement example of an image processing apparatus according to another embodiment. FIG. 6 is a block diagram illustrating an arrangement example of an image processing apparatus according to another embodiment. FIG. 7 is a block diagram illustrating an arrangement example of an image processing apparatus according to another embodiment. FIG. 8 is a block diagram illustrating an arrangement example of an image processing apparatus according to another embodiment. FIG. 9 is a flowchart illustrating an example of a process of an image processing method according to an embodiment of the present invention. FIG. 10 is a block diagram illustrating an arrangement example of the medical imaging system according to the embodiment of the present invention. FIG. 11 is a block diagram showing a configuration example of a computer for realizing the method and apparatus of the present invention.

  In the following, an overview of some embodiments of the present invention will be introduced for a basic understanding of the present invention. This summary does not define key or important areas of the invention and does not limit the scope of the invention. Its purpose is merely to provide a simplified description and for a more detailed description to be given later.

  According to one embodiment of the present invention, a medical image processing apparatus is provided. The medical image processing device includes a matching unit and a specifying unit. The matching unit specifies a matching result between the target image, which is a medical image to be processed, and a reference image in the reference image set. However, the matching result is specified by matching the region of interest of the target image with the corresponding sub-region of the reference image. The specifying unit specifies one or more reference images having a high degree of similarity with the target image based on the matching result.

  According to another embodiment of the present invention, there is provided a medical image processing method. The method includes identifying a matching result between the target image and a reference image in the reference image set. However, the matching result is specified by matching the region of interest of the target image with the corresponding sub-region of the reference image. The method also includes the step of identifying one or more reference images having a high degree of similarity to the target image based on the matching result.

  According to another embodiment of the present invention, there is provided a medical imaging system including the medical image processing device.

  According to another embodiment of the present invention, there is provided a program product of a computer-readable instruction code, and when reading and executing the instruction code by a computer, the computer-aided medical image processing method according to the embodiment of the present invention. Can be realized.

  According to another embodiment of the present invention, there is provided a storage medium for loading a program product storing a computer-readable instruction code.

  According to the embodiment of the present invention, specifying a reference image for a specific region of interest can specify (search) a reference image for identification diagnosis more accurately and effectively.

  Hereinafter, by describing the present embodiment with reference to the drawings, the objects, features, and merits of the present embodiment can be further easily understood. The configuration in the drawings is for illustrating the principle of the present embodiment. In the drawings, the same or similar technical features or configurations will be represented using the same or similar drawing notations.

  Hereinafter, the present embodiment will be described with reference to the drawings. Note that in the following description, structures and features described in one drawing or one embodiment can be combined with structures or features described in one or more other drawings or embodiments. Further, for the sake of clarity, in the drawings and description, descriptions and descriptions of contents unrelated to the present embodiment, and configurations and processes well known to those skilled in the art are omitted.

  As shown in FIG. 1, the medical image processing apparatus 100 according to one embodiment of the present invention includes a matching unit 110 and a specifying unit 120.

  The matching unit 110 specifies a matching result between the target image and the reference image in the reference image set. The matching unit 110 specifies the matching result by matching the region of interest of the target image with the corresponding sub-region of the reference image.

  The region of interest may include one or more predetermined sub-regions of the image, and the sub-regions may have a predetermined shape. As will be described later, for example, the region of interest may be defined by the user, or the region of interest may be specified based on a predetermined position template.

  The specifying unit 120 specifies one or more reference images having a high degree of similarity with the target image based on the matching result of the matching unit 110. For example, a predetermined number of reference images having the highest similarity may be provided, or a reference image having a similarity higher than a predetermined threshold may be provided.

  The reference image may be a conventional medical image in which a type, for example, a disease type is marked, and the reference image specified by the specifying unit 120 is provided to a user (operator), for example, a doctor to perform identification diagnosis. be able to. Therefore, the user, for example, a doctor does not need to browse a large number of conventional images, and makes a determination by referring to only the specified reference image, so that the operation efficiency can be improved. For example, the reference image is an atlas image.

  Certain diseases have a typical distribution that is within a particular anatomical region. For example, about 75% of cerebellopontine angle tumors are acoustic neuromas. Also, for example, two common sites for chordomas are the skull clivus and the sacrum at the base of the spine. Compared with the existing method of identifying a reference image similar to the target image by matching the entirety of the target image and the reference image, the embodiment of the present invention performs image matching based on a predetermined region of interest. , A similar reference image can be specified, and a reference image having a high possibility of providing valid information can be specified more accurately and effectively.

  Here, the accuracy is not the accuracy of the identification diagnosis. The final diagnosis is performed by a user of the medical image processing apparatus, for example, a doctor, and is not performed by the medical image processing apparatus. The accuracy here is the accuracy of specifying a corresponding reference image based on the target image. More specifically, when the accuracy is high, the specified reference image and the target image have higher similarity ( (Including embodiments of location distribution), thereby providing a user, eg, a physician, with reference information for identification and diagnosis.

  Next, a configuration example of the medical image processing apparatus 200 according to the embodiment will be described with reference to FIG. The medical image processing device 200 includes a matching unit 210, a specifying unit 220, and a setting unit 230. The matching unit 210 and the specifying unit 220 are the same as the matching unit 110 and the specifying unit 120, respectively. The setting unit 230 sets at least one region of interest in the target image.

  The setting unit 230 can set a region of interest based on a user's instruction. For example, the user can manually select one or more regions (including, for example, a region of a particular feature and its symmetric region) as a region of interest based on image features included in the target image. . The setting unit 230 may provide information on the set region of interest to the matching unit 210 to perform matching.

  Alternatively, the setting unit 230 can set a region of interest based on a predetermined position template. The position template can be stored in advance. For example, the position template used before is stored in the storage unit of the template and is selected by the user. Further, according to an embodiment, the image processing apparatus 200 may include a creating unit 240, and the creating unit 240 creates a new position template based on a user input. That is, the setting unit 230 sets at least one of the plurality of regions of interest based on the position template in which each of the plurality of regions of interest is arranged in a predetermined positional relationship.

  The schematic diagrams of FIGS. 3A and 3B are two examples of a position template for a cross-sectional image of the brain.

  In the template illustrated in FIG. 3A, regions 312A-312H show six regions of interest at the periphery of the brain, and regions 314A-314F show six regions of interest in a more intermediate region of the brain.

  In the template shown in FIG. 3B, regions 322A to 322H indicate six regions of interest at the periphery of the brain, and region 324 indicates a region of interest in the middle region of the brain.

  For a particular disease, one or more of the above templates can be selected as a region of interest. For example, it is distinguished that multiple white matter damage is caused by multiple sclerosis or vascular disease, and the positions where multiple sclerosis and vascular disease occur in the brain have certain characteristics. For example, multiple sclerosis usually occurs at periventricular, infratentorial, and spinal cord locations, whereas vascular disease does not usually occur at these locations. In another embodiment, the vascular disease usually occurs at the location of the basal nuclei, but multiple sclerosis does not usually occur at the location of the basal nucleus.

  For an example in which identification diagnosis is performed for white matter damage, the medical image processing apparatus according to the embodiment of the present invention specifies a region of interest based on the position of occurrence of white matter damage in the target image, and specifies the region of interest from a reference image database. A reference image similar to the target image can be specified.

  For example, if there is a lesion in the region corresponding to the region 314D shown in FIG. 3A in the target image, the region 314D can be selected as the region of interest, and the region 314C at a position symmetrical to the region 314D is also selected as the region of interest. can do. The specifying unit can specify the reference image to be provided to the user as the reference image based on matching between the regions of interest 314C and 314D and the corresponding sub-region of the reference image in the reference image database.

  In another application, the identification diagnosis identifies whether the skull base tumor is a chordoma or a chondrosarcoma. Chordoma lesions are usually located in the central region, while chondrosarcoma is usually off the central region. The application example can adopt the example of the position template shown in FIG. 3B. More specifically, a similar reference image can be specified, for example, using the region 324 shown in FIG. 3B as the region of interest based on the distribution situation of the lesion portion in the target image.

  In the existing form of identifying a reference image by global matching of images, for example, multiple white matter damage in a target image is caused by multiple hardening, but a similar reference image obtained by global matching of images is a medical image corresponding to a vascular disease. It may be. In this case, the accuracy of the user's identification diagnosis may be affected, or the user is required to have more reference images, which causes an increase in processing load.

  By performing matching with the reference image for a specific region of interest, a reference image closer to the lesion occurrence position of the target image can be provided to the user, for example, a physician. It can be specified (searched) accurately and effectively.

  As described above, the embodiment in which the similar reference image is specified based on the position template has been described by the specific application example, but the embodiment is not limited to the above specific example. For a particular application, the user selects, for example, an appropriate location template from a database of templates, which includes, for example, regions of interest set for multiple locations of a particular disease. Alternatively, as described above with reference to FIG. 2, the user can define the position template by the creation unit 240.

  Also, for matching between the region of interest of the target image and the corresponding sub-region of the reference image, various image matching methods known in the art can be adopted. According to one embodiment, image features of a sub-region of a reference image are stored in advance, and matching between a region of interest of a target image and a corresponding sub-region of a reference image can be performed based on the stored image features.

  As shown in FIG. 4, the medical image processing device 400 according to one embodiment includes a matching unit 410, a specifying unit 420, an extracting unit 430, and a storage unit 440. The specifying unit 420 is similar to the specifying unit described above.

  The extracting unit 430 extracts the image feature of the region of interest of the target image. That is, the extraction unit 430 extracts a first image feature that is a feature of the image included in the first region of interest set in the medical image.

  The storage unit 440 stores the image characteristics of the sub-region corresponding to the region of interest in the target image of the reference image in the reference image set. That is, the storage unit 440 stores the second image feature that is the feature of the image included in the second region of interest set in the reference image.

  The matching unit 410 compares the target image and the reference image based on the similarity between the image feature of the region of interest to be processed extracted by the extraction unit 430 and the image feature of the corresponding sub-region of the reference image stored in the storage unit 440. Is performed.

  Specifically, the region of interest of the target image may be specified based on a predetermined position template. For example, the storage unit 440 can store image features extracted from corresponding sub-regions of the reference image based on a plurality of predetermined templates.

  For example, an image feature can be indicated by a vector based on a Hu invariant moment, an outline rectangular view, or the like. Accordingly, the storage unit 440 can store the image feature vector of each area of each reference image. The extracting unit 430 can extract, for example, an image feature of the region of interest in the target image indicated by a vector based on the position template. The matching unit 410 can perform matching by specifying a distance between the image feature vector of the region of interest of the target image and the image feature vector of the corresponding sub-region of the reference image. For example, when the distance is equal to or less than the predetermined threshold, it can be specified that there is a reference image sub-region that matches the region of interest.

  In addition, since the imaging target, the discrimination of the imaging parameters and the like embodiments, there is a possibility that there is a misalignment between the target image and the reference image, in other words, a coordinate system that does not match the target image and the reference image May have. As shown in FIG. 5, a medical image processing apparatus 500 according to an embodiment includes a matching unit 510, a specifying unit 520, a positioning unit 530, and a deforming unit 540, as illustrated in FIG. . The specifying unit 520 is similar to the specifying unit described above.

  The positioning unit 530 positions the target image and the reference image. As described above, the reference image in the reference image set may be an image set having the same coordinate system by alignment and deformation. The positioning unit 530 is configured to perform one or more reference images of the target image and the reference image set (for example, a representative reference image set in advance, or a reference image for positioning selected based on the similarity with the target image). ) And position. Specifically, an image alignment method known in the art, for example, a method based on mutual information can be employed to align the target image with the reference image. The positioning unit 530 provides the alignment result, for example, a transfer function to the deformation unit 540. That is, the positioning unit 530 positions the medical image and each of the plurality of reference images.

  The deformation unit 540 performs a deformation process on the target image based on the alignment result of the positioning unit 530. For example, the deforming unit 540 resamples the target image based on the transfer function specified by the positioning unit 530, and obtains an image having the same coordinate system as the reference image. That is, the deforming unit 540 deforms the medical image based on the positioning result by the positioning unit 530.

  The matching unit 510 performs matching between the region of interest of the target image and the corresponding sub-region of the reference image based on the target image deformed by the deforming unit 540, for example, based on a predetermined position template, and specifies a matching result. A reference image similar to the target image provided to 520 is identified.

  As shown in FIG. 6, the medical image processing device 600 according to one embodiment includes a matching unit 610, a specifying unit 620, and a selecting unit 630. The specifying unit 620 is the same as the specifying unit described above.

  The selection unit 630 selects at least one of the regions of interest based on a user instruction or a predetermined mode. The matching unit 610 performs matching between the target image and the reference image for the selected region of interest.

  For example, in an application example of performing multiple diagnosis of multiple sclerosis and vascular disease for multiple white matter injuries, the selection unit 630 can select, for example, the regions 314C and 314D illustrated in FIG. 3A as regions of interest based on a user instruction. . Further, for example, in the above-described application example of the identification diagnosis of chordoma and chondrosarcoma, the selection unit 630 can select the region 324 illustrated in FIG. 3B as a region of interest based on, for example, a user's instruction.

  In a predetermined mode, for example, in a mode in which a reference image is automatically searched for a specific disease type based on a target image, the selection unit 630 selects a corresponding region of interest from a position template based on a preset scheme. be able to.

  In the above embodiment, the specifying unit specifies one or more reference images having a high degree of similarity to the target image from the reference image set based on the matching result of the matching unit. The reference image specified by the specifying unit is presented to a user, for example, a doctor. Therefore, the medical image processing apparatus 700 according to an embodiment may include the display unit 730 as well as the matching unit 710 and the specifying unit 720. The display unit 730 displays the reference image specified by the specifying unit 720.

  In another embodiment, for example, the image processing apparatus provides the reference image specified by the output unit to the external display, and presents the specified reference image to the user.

  The user can specify the type of the target image based on the specified reference image. For example, a doctor performs identification diagnosis on a target image based on a reference image, and specifies, for example, a disease type or the like reflected in the target image.

  As shown in FIG. 8, the medical image processing apparatus 800 according to one embodiment includes a receiving unit 830 in addition to the matching unit 810 and the specifying unit 820. The receiving unit 830 specifies the type of the target image based on the user's input. The target image for which the type is specified can be stored in a corresponding database.

  According to one embodiment, the medical image processing apparatus 800 further includes an updating unit 840, and adds a target image whose type is specified as a reference image to a reference image set. Therefore, the target image can be a reference image of a subsequent target image.

  In the above embodiment, the brain medical image is an example of the target image and the reference image, but is not limited thereto. For example, embodiments of the present invention can be applied to medical images including sites such as the chest and abdominal cavity.

  Further, in the above embodiment, the case where the sub-region of the reference image is set in advance has been described, but the embodiment is not limited to this. For example, in the embodiment, each time the matching is performed, a sub-region may be set in the reference image, and the set sub-region may be matched with the region of interest of the target image. Hereinafter, the medical image processing apparatus in this case will be described.

  For example, the medical image processing apparatus includes a positioning unit, a transformation unit, a first setting unit, a second setting unit, and a search unit. The positioning part and the deformation part are the same as the positioning part 530 and the deformation part 540, respectively.

  The first setting unit sets a first region of interest in the medical image deformed by the deforming unit. For example, the first setting unit sets at least one region of interest on the deformed target image based on a predetermined position template. This processing is the same as the processing of the setting unit 230 described above.

  The second setting unit sets a second region of interest corresponding to the first region of interest to at least two of the plurality of reference images. For example, the second setting unit sets a sub-region corresponding to the region of interest to at least one of the plurality of reference images. Further, for example, the second setting unit sets a sub-region corresponding to the region of interest included in the position template to at least one of the plurality of reference images. Specifically, the target image has already been transformed into an image having the same coordinate system as the reference image by the transformation performed by the transformation unit. Therefore, for example, the second setting unit refers to the coordinates of the region of interest set in the target image, and sets the sub-region at the same coordinates in the reference image.

  The search unit searches for a reference image similar to the image in the first region of interest from the plurality of reference images in which the second region of interest is set. For example, the search unit searches for a reference image most similar to the image in the first region of interest. Further, for example, the search unit performs the search based on the similarity between the image feature of the first region of interest and the image feature of the second region of interest (sub-region).

  As described above, the medical image processing apparatus can set the sub-region in the reference image and match the set sub-region with the region of interest of the target image.

  In the above example, the case where the deforming unit deforms the medical image is described, but the embodiment is not limited to this. For example, the deformation unit may deform the reference image. In this case, in the medical image processing apparatus, the positioning unit positions the medical image and each of the plurality of reference images. The deformation unit deforms at least one of the plurality of reference images based on a positioning result by the positioning unit. The first setting unit sets a first region of interest in a medical image. The second setting unit sets the second region of interest corresponding to the first region of interest to a plurality of deformed reference images. The search unit searches for a reference image similar to the image in the first region of interest from the plurality of reference images in which the second region of interest is set.

  Further, the embodiments of the present invention can be applied to various types of medical images. Includes magnetic resonance imaging images, computed tomography imaging images, ultrasound imaging images, X-ray imaging images, positron emission tomography images, and the like.

  In the above, some processes or methods have been described in the description of the medical image processing apparatus according to the embodiment. Hereinafter, in the case where there is no overlap with the above embodiment, those methods will be described in detail. Note that the method described in the description process of the medical image processing apparatus does not necessarily need to employ the above-described processing unit, or may not be executed by the above-described processing unit. For example, embodiments of the medical image processing apparatus may be implemented using hardware and / or firmware as a part or completely, and the medical image processing method described below is also completely computer-executable. It may be realized by a simple program, or may be a mode that employs hardware and / or firmware of a medical image processing apparatus.

  Next, an example of a process of the medical image processing method according to the embodiment of the present invention will be described with reference to FIG.

  As shown in FIG. 9, the medical image processing method according to the present embodiment includes step S910 of specifying a matching result between a target image and a reference image in a reference image set. However, the matching result is specified by matching the region of interest of the target image with the corresponding sub-region of the reference image.

  In step S920, one or more reference images having a high degree of similarity to the target image are specified based on the matching result in S910.

  Although not shown, the medical image processing method according to an embodiment may further include setting at least one region of interest in the target image.

  However, the region of interest can be set based on a predetermined position template. In addition, the medical image processing method according to an embodiment further includes creating a position template based on a user input.

  Further, the medical image processing method according to one embodiment includes a step of extracting an image feature of a region of interest of the target image and a step of storing an image feature of a corresponding sub-region of the reference image in the reference image set. Accordingly, matching between the target image and the reference image can be performed based on the similarity of the image features.

  Further, the medical image processing method according to one embodiment includes a step of aligning the target image with the reference image and a step of performing a deformation process on the target image based on the alignment result.

  In addition, the medical image processing method according to an embodiment may further include selecting at least one of the regions of interest based on a user instruction or a predetermined mode. Then, matching between the target image and the reference image can be performed for the selected region of interest.

  In addition, the medical image processing method according to an embodiment may further include displaying the specified reference image.

  In addition, the medical image processing method according to an embodiment may include a step of specifying a type of the target image based on a user input. Further, the method can include a step of adding the target image whose type is specified to the reference image set as a reference image.

  FIG. 10 is a block diagram illustrating an arrangement example of a medical imaging system according to another embodiment of the present invention.

  The medical imaging system 1000 according to one embodiment of the present invention includes a medical image processing device 1010. The medical image processing device 1010 can include the arrangement of the medical image processing device described in the above embodiment. For example, the medical imaging system 1000 includes a positioning unit, a deforming unit, a first setting unit, a second setting unit, and a search unit. The positioning unit positions the medical image and each of the plurality of reference images. The deforming unit deforms the medical image based on the positioning result by the positioning unit. The first setting unit sets a first region of interest in the transformed medical image. The second setting unit sets a second region of interest corresponding to the first region of interest to at least one of the plurality of reference images. The search unit searches for a reference image similar to the image in the first region of interest from the reference image in which the second region of interest is set. In the medical imaging system 1000, all of the positioning unit, the deforming unit, the first setting unit, the second setting unit, and the search unit may be installed in a single device, or each may be distributed to a plurality of devices. It may be installed. Note that the medical imaging system 1000 is an example of a medical image processing system.

  As an example, each step of the medical image processing method described above and each configuration and / or part of the medical image processing apparatus described above may be implemented as software, firmware, hardware, or a combination thereof. When realized via software or firmware, a computer having a dedicated hardware structure (for example, FIG. 11) from a memory medium or via a network to execute a software program (medical image processing program) of the above-described method. To a general-purpose computer 1100), and various functions can be performed in a state where various programs are downloaded to the computer.

  In FIG. 11, an arithmetic processing unit (that is, CPU) 1101 executes a program stored in a read-only memory (ROM) 1102 or a program written from a memory unit 1108 to a read / write memory (RAM) 1103. Various processes are performed based on the above. The RAM 1103 also stores data necessary for the CPU 1101 to perform various processes, if necessary. The CPU 1101, the ROM 1102, and the RAM 1103 are connected via an integrated line 1104, respectively. An input / output interface 1105 is also connected to the integrated line 1104.

  The following units are connected to an input / output interface 1105: an input unit 1106 (including a keyboard, a mouse, and the like), an output unit 1107 (a monitor, for example, a cathode ray tube (CRT), a liquid crystal monitor (LCD), a speaker, and the like). Etc.), a memory unit 1108 (including a hard disk), a communication unit 1109 (a network interface card, for example, a LAN card, a modem, etc.). The communication unit 1109 performs communication processing via a network (for example, the Internet). If necessary, a driver 1110 can also be connected to the input / output interface 1105. The removable medium 1111 is, for example, a magnetic disk, an optical disk, an MO, a semiconductor memory, or the like. The removable medium 1111 is mounted on the driver 1110 as needed, reads out a computer program as needed, and is downloaded to the memory unit 1108. .

  When performing the above-described system processing via software, a program constituting software may be downloaded from a network (for example, the Internet) or a storage medium (for example, a removable medium 1111).

  For those skilled in the art, such a storage medium storing a program as shown in FIG. 11 is not limited to a removable medium 1111 which provides a user with a program from a place away from the apparatus. Examples of the removable medium 1111 include a magnetic disk (floppy (registered trademark) disk, an optical disk (including CD-ROM and DVD), a magnetic optical disk (including MiniDisc (MD, registered trademark)), and a semiconductor storage device. Further, the storage medium may be the ROM 1102, or a form in which the program is stored in a hard disk or the like included in the memory unit 1108, and the program is sent from a device including the program to the user.

  According to the present invention, a program product storing a device-readable command code as a memory can be applied. When the command code is read via a device, the method according to the embodiment of the present invention is performed.

  A storage medium for receiving a program product storing the device-readable command code is also applicable to the present invention. The storage medium is not limited to a hard disk, an optical disk, a magnetic optical disk, a memory card, and a memory stick.

  In the specific embodiments described above, features similar to those of one embodiment may be applied in one or more other implementations, combined with other implementations, or implemented in other implementations. It is also possible to substitute features in the method.

  Further, the use of the term "include / include" indicates the presence of a feature, configuration, step or structure. However, this does not mean that other features, configurations, steps, or structures are present or excluded.

  In the above embodiment, each step or configuration is described using a figure symbol of a numeric configuration. However, those skilled in the art should understand that these figure symbols are merely for the sake of explanation and illustration, and do not represent the order or any other limitation.

  In addition, the method of the present embodiment is not limited to being performed in the time sequence described in the detailed description section, and may be performed simultaneously or independently in other time sequences. good. Therefore, the order of performing the methods described in the detailed description of the present application does not limit the configuration of the embodiment in the technical scope.

  In the above, the present embodiment has already been described with the description of the specific embodiment of the present embodiment. However, all the above-described embodiments are merely examples and do not limit the present invention. Those skilled in the art can make various modifications and improvements of the present embodiment or design equivalents within the spirit and scope of the claims. These modifications, improvements or equivalents are included in the protection scope of the present embodiment.

Reference Signs List 100 medical image processing device 110 matching unit 120 specifying unit

Claims (16)

A medical image, a positioning unit that positions each of the plurality of reference images,
Based on a positioning result by the positioning unit, a deforming unit that deforms the medical image,
A first setting unit that sets a first region of interest in the deformed medical image;
A second setting unit that sets a second region of interest corresponding to the first region of interest to at least two of the plurality of reference images;
A search unit that searches a reference image in which the second region of interest is set, for a reference image similar to an image in the first region of interest;
A medical image processing apparatus comprising: A medical image, a positioning unit that positions each of the plurality of reference images,
A deforming unit that deforms at least one of the plurality of reference images based on a positioning result by the positioning unit;
A first setting unit that sets a first region of interest in the medical image;
A second setting unit that sets a second region of interest corresponding to the first region of interest to a deformed reference image;
A search unit that searches a reference image in which the second region of interest is set, for a reference image similar to an image in the first region of interest;
A medical image processing apparatus comprising: The search unit searches for a reference image most similar to an image in the first region of interest,
The medical image processing device according to claim 1. The first setting unit sets a plurality of the first regions of interest,
The second setting unit sets a plurality of second regions of interest corresponding to each of the plurality of first regions of interest set by the first setting unit.
The medical image processing device according to claim 1. A selecting unit that selects at least one of the plurality of first regions of interest;
The search unit searches for a reference image most similar to each of the images in the first region of interest selected by the selection unit.
The medical image processing device according to claim 4. The medical image, further comprising a display control unit that simultaneously displays the reference image searched by the search unit on a display unit,
The medical image processing apparatus according to claim 1. The reference image is an atlas image,
The medical image processing apparatus according to claim 1. The first setting unit sets at least one of the plurality of first regions of interest based on a position template in which each of the plurality of first regions of interest is arranged in a predetermined positional relationship.
The medical image processing apparatus according to claim 1. The apparatus further includes a creating unit that creates the position template based on an input of an operator,
The medical image processing apparatus according to claim 8. An extraction unit configured to extract a first image feature that is a feature of an image included in a first region of interest set in the medical image;
A storage unit that stores a second image feature that is a feature of the image included in the second region of interest set in the reference image,
The search unit searches based on a similarity between the first image feature and the second image feature.
The medical image processing apparatus according to claim 1. A receiving unit that receives designation of a type of the medical image based on an input of an operator,
An update unit that adds the medical image whose type is specified as the reference image,
The medical image processing apparatus according to claim 1. The medical image and the plurality of reference images include an image of a brain,
A medical image processing apparatus according to claim 1. The medical image and the plurality of reference images include a magnetic resonance imaging image, a computed tomography imaging image, an ultrasound imaging image, or an X-ray imaging image,
The medical image processing apparatus according to claim 1. Positioning the medical image and each of the plurality of reference images,
Based on the positioning result, deform the medical image,
Acceptance based setting of the first region of interest definitive to modified the medical image to an input of the operator,
Setting a second region of interest corresponding to the first region of interest to at least two of the plurality of reference images;
A medical image processing method, comprising: searching a reference image in which the second region of interest is set, for a reference image similar to an image in the first region of interest. A medical image, a positioning unit that positions each of the plurality of reference images,
Based on a positioning result by the positioning unit, a deforming unit that deforms the medical image,
A first setting unit that sets a first region of interest in the deformed medical image;
A second setting unit that sets a second region of interest corresponding to the first region of interest to at least two of the plurality of reference images;
A search unit that searches a reference image in which the second region of interest is set, for a reference image similar to an image in the first region of interest;
A medical image processing system comprising: Positioning the medical image and each of the plurality of reference images,
Based on the positioning result, deform the medical image,
Setting a first region of interest in the transformed medical image,
Setting a second region of interest corresponding to the first region of interest to at least two of the plurality of reference images;
A medical image processing program that causes a computer to execute each process of searching for a reference image similar to an image in the first region of interest from a reference image in which the second region of interest is set.

Images