Medical image processing devices, storage media, medical devices, and treatment systems

Abstract

The medical image processing apparatus of this embodiment includes a comparison unit and a positioning region determination unit. The comparison unit compares a first image obtained by photographing a patient with a comparison image, which is an image used in past radiotherapy and is designated with an effective area for alignment during radiotherapy. The positioning region determination unit determines a positioning region similar to the effective area contained in the first image based on the comparison result of the comparison unit.

Description

Technical Field

[0001] Embodiments of the present invention relate to medical image processing apparatus, storage medium, medical device, and treatment system. Background Technology

[0002] Radiation therapy is a treatment method that uses radiation to destroy lesions located within a patient's body. Radiation can affect normal tissue when it strikes it, therefore, radiation must be precisely directed to the lesion. Thus, in the treatment planning phase, for example, a computed tomography (CT) scan is performed beforehand to determine the three-dimensional location of the lesion within the patient's body. Based on this location, the direction and intensity of the radiation are planned. Then, during treatment, the patient's position is aligned with the planned position, and radiation is delivered to the lesion according to the planned direction and intensity.

[0003] Previously disclosed technologies related to radiotherapy systems employ methods to improve positioning accuracy by utilizing an effective region of interest when locating the patient in a consistent position during radiotherapy (see, for example, Patent Document 1). In these prior art techniques, patient positioning is achieved by integrating the results of positioning within the overall image with the results of positioning based on feature quantities related to the region of interest input in the treatment plan.

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent Document 1: Japanese Patent No. 6095112 Summary of the Invention

[0007] The problem that the invention aims to solve

[0008] However, in previous techniques, even areas that were effective for localization could not be used as localization areas if they were not entered into the treatment plan.

[0009] The present invention was completed based on the above-mentioned understanding of the problem, and its purpose is to provide a medical image processing device, storage medium, medical device and treatment system capable of high-precision patient positioning.

[0010] Methods for solving problems

[0011] One embodiment of the medical image processing apparatus includes a comparison unit and a positioning region determination unit. The comparison unit compares a first image obtained by capturing a patient with a comparison image, which is an image used in past radiotherapy and has been designated with an effective region for alignment in the radiotherapy. The positioning region determination unit determines a positioning region similar to the effective region contained in the first image based on the comparison result of the comparison unit.

[0012] Invention Effects

[0013] Based on the above method, it is possible to provide a medical image processing device, storage medium, medical device, and treatment system capable of high-precision patient positioning. Attached Figure Description

[0014] Figure 1 This is a block diagram showing the general structure of a treatment system, which includes a medical device comprising the medical image processing apparatus of the first embodiment.

[0015] Figure 2 This is a block diagram showing the schematic structure of the medical device and medical image processing device according to the first embodiment.

[0016] Figure 3 This is a diagram showing an example of a comparative image referenced by the medical image processing apparatus of the first embodiment.

[0017] Figure 4 This is a diagram showing another example of a comparative image referenced by the medical image processing apparatus of the first embodiment.

[0018] Figure 5 This is a flowchart illustrating the operation of the treatment system according to the first embodiment.

[0019] Figure 6A This diagram schematically illustrates an example of the operation of the comparison unit and the positioning area determination unit included in the medical image processing apparatus of the first embodiment.

[0020] Figure 6B This diagram schematically illustrates an example of the operation of the comparison unit and the positioning area determination unit included in the medical image processing apparatus of the first embodiment.

[0021] Figure 6C This diagram schematically illustrates an example of the operation of the comparison unit and the positioning area determination unit included in the medical image processing apparatus of the first embodiment.

[0022] Figure 6D This diagram schematically illustrates an example of the operation of the comparison unit and the positioning area determination unit included in the medical image processing apparatus of the first embodiment.

[0023] Figure 7 This is a block diagram illustrating the general structure of the medical device and the medical image processing device according to the second embodiment.

[0024] Figure 8A This diagram illustrates the concept of the patient orientation correction unit in the medical image processing apparatus of the second embodiment correcting the orientation of an image.

[0025] Figure 8B This diagram illustrates the concept of correcting the orientation of the patient orientation correction unit image in the medical image processing apparatus of the second embodiment.

[0026] Figure 9A This diagram schematically illustrates an example of the orientation correction processing of an image by the patient orientation correction unit of the medical image processing apparatus of the second embodiment.

[0027] Figure 9B This diagram schematically illustrates an example of the orientation correction processing of an image by the patient orientation correction unit of the medical image processing apparatus of the second embodiment.

[0028] Figure 9C This diagram schematically illustrates an example of the orientation correction processing of an image by the patient orientation correction unit of the medical image processing apparatus of the second embodiment.

[0029] Figure 9D This diagram schematically illustrates an example of the orientation correction processing of an image by the patient orientation correction unit of the medical image processing apparatus of the second embodiment.

[0030] Figure 10 This is a flowchart illustrating the operation of the treatment system according to the second embodiment.

[0031] Figure 11 This is a block diagram illustrating the general structure of the medical device and the medical image processing device according to the third embodiment.

[0032] Figure 12 This diagram shows an example of a confirmation image generated by the confirmation image generation unit of the medical image processing apparatus according to the third embodiment.

[0033] Figure 13 This diagram shows another example of a confirmation image generated by the confirmation image generation unit of the medical image processing apparatus according to the third embodiment.

[0034] Figure 14 This is a flowchart illustrating the operation of the treatment system according to the third embodiment. Detailed Implementation

[0035] Hereinafter, the medical image processing apparatus, medical image processing program, medical device, and treatment system according to the embodiments will be described with reference to the accompanying drawings.

[0036] (First Implementation)

[0037] Figure 1 This is a block diagram showing the general structure of a treatment system that includes a medical device comprising the medical image processing apparatus of the first embodiment. The treatment system 1 includes, for example, a treatment table 10, an examination bed control unit 11, two radiation sources 20 (radiation source 20-1 and radiation source 20-2), two radiation detectors 30 (radiation detector 30-1 and radiation detector 30-2), a treatment beam irradiation gate 40, a first image acquisition unit 50, a second image acquisition unit 60, a positioning unit 70, a display control unit 80, a display device 81, a medical image processing apparatus 100, and a comparison image database (DB) 110.

[0038] In addition, Figure 1 The hyphen "-" and the following numbers after the various reference numerals in the accompanying drawings are used to identify correspondences. For example, in the correspondence between radiation source 20 and radiation detector 30, radiation source 20-1 and radiation detector 30-1 correspond to form one group, and radiation source 20-2 and radiation detector 30-2 correspond to form another group. Furthermore, when the following description does not distinguish between multiple identical constituent elements, the hyphen "-" and the following numbers are not shown.

[0039] The treatment table 10 is an examination bed that fixes the subject (patient) P who is to receive radiation therapy. The examination table control unit 11 controls the parallel mechanism and the rotation mechanism provided on the treatment table 10 to change the direction of the treatment beam irradiated to the patient P who is fixed on the treatment table 10. For example, the examination table control unit 11 controls the parallel mechanism and the rotation mechanism of the treatment table 10 along three axes, i.e., six axes.

[0040] Radiation source 20-1 irradiates the body of patient P from a predetermined angle with radiation r-1. Radiation source 20-2 irradiates the body of patient P from a different predetermined angle with radiation r-2. Radiation r-1 and radiation r-2 are, for example, X-rays. Figure 1 The image shows X-ray imaging of a patient P fixed to treatment table 10 from two directions. Additionally, in... Figure 1 The diagram of the control unit that controls the irradiation of radiation r by radiation source 20 is omitted.

[0041] Radiation detector 30-1 detects radiation r-1 that irradiates from radiation source 20-1 and passes through the patient P's body, generating an X-ray fluoroscopic image PI of the patient P's body corresponding to the energy of the detected radiation r-1. Radiation detector 30-2 detects radiation r-2 that irradiates from radiation source 20-2 and passes through the patient P's body, generating an X-ray fluoroscopic image PI of the patient P's body corresponding to the energy of the detected radiation r-2. In the radiation detector 30, the X-ray detectors are arranged in a two-dimensional array, generating digital images representing the energy of the radiation r reaching each X-ray detector, as X-ray fluoroscopic images PI. The radiation detector 30 is, for example, a flat panel detector (FPD), an image intensifier, or a color image intensifier. In the following description, it is assumed that each radiation detector 30 is an FPD. The radiation detector 30 (FPD) outputs the generated X-ray fluoroscopic images PI to the medical image processing apparatus 100. Furthermore, in Figure 1 The diagram of the control unit that controls the generation of the X-ray fluoroscopic image PI by the 30X radiation detector is omitted.

[0042] In the treatment system 1, the combination of radiation source 20 and radiation detector 30 is an example of the "imaging apparatus" as described in the claims. Figure 1 The image shows an imaging device for taking X-ray fluoroscopic images of patient P from two different directions. Additionally, in... Figure 1 The treatment system 1 shown depicts two sets of radiation sources 20 and radiation detectors 30, i.e., a structure with two imaging devices. However, the number of imaging devices in the treatment system 1 is not limited to two. For example, the treatment system 1 may also have three or more imaging devices (three or more sets of radiation sources 20 and radiation detectors 30). Alternatively, the treatment system 1 may also have only one imaging device (one set of radiation sources 20 and radiation detectors 30).

[0043] The treatment beam irradiation gate 40 irradiates radiation intended to destroy the lesion or other part of the patient P's body, as a treatment beam B. The treatment beam B can be, for example, X-rays, gamma rays, electron beams, positron beams, neutron beams, heavy particle beams, etc. The treatment beam B is irradiated linearly from the treatment beam irradiation gate 40 to the patient P (more specifically, the lesion within the patient P's body). The irradiation of the treatment beam B in the treatment beam irradiation gate 40 is controlled, for example, by a treatment beam irradiation control unit (not shown). In the treatment system 1, the treatment beam irradiation gate 40 is an example of the "irradiation unit" as described in the claims.

[0044] In addition, Figure 1The treatment system 1 shown includes a structure with a fixed treatment beam irradiation gate 40, but it is not limited to this; the treatment system 1 may also have multiple treatment beam irradiation gates. For example, the treatment system 1 may also include a treatment beam irradiation gate that irradiates a treatment beam towards the patient P from a horizontal direction. Alternatively, the treatment system 1 may have a structure where a treatment beam irradiation gate rotates around the patient P, thereby irradiating a treatment beam towards the patient P from various directions. For example, Figure 1 The treatment beam irradiation gate 40 shown can also be relative to... Figure 1 The structure shown is capable of rotating 360 degrees along its horizontal Y-axis. This type of treatment system 1 is called a rotating gate type treatment system. Furthermore, in the rotating gate type treatment system, the radiation source 20 and the radiation detector 30 also rotate 360 ​​degrees simultaneously relative to the same axis as the rotation axis of the treatment beam irradiation gate 40.

[0045] In the treatment system 1, the combination of the first image acquisition unit 50, the second image acquisition unit 60, the positioning unit 70, the display control unit 80, and the medical image processing device 100 constitutes an example of the "medical device" as claimed in the claims. Furthermore, the medical device may include some or all of the functions of its constituent elements, for example, a hardware processor such as a CPU (Central Processing Unit) and a storage device for storing programs (software) (a storage device with a non-volatile storage medium), whereby the processor executes the program to realize the functions of each constituent element. Additionally, some or all of the functions of the constituent elements of the medical device can be implemented using hardware (circuit unit, including circuitry) such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or GPU (Graphics Processing Unit), or the functions of each constituent element can be realized through the cooperation of software and hardware. Furthermore, some or all of the functions of the components of the medical device can be implemented using a dedicated LSI. Here, the program (software) can be pre-stored in a storage device (non-volatile storage medium) such as ROM (Read Only Memory), RAM (Random Access Memory), HDD (Hard Disk Drive), or flash memory, or it can be stored in a removable storage medium (non-volatile storage medium) such as a DVD or CD-ROM. This storage medium is installed on the drive unit of the treatment system 1, thereby being installed in the storage device of the treatment system 1. Alternatively, the program (software) can be pre-downloaded from other computer devices via a network and installed in the storage device of the treatment system 1.

[0046] The first image acquisition unit 50 acquires a three-dimensional image of the patient P inside the body, which is capable of being visualized through the X-ray fluoroscopic image. The three-dimensional image is, for example, a three-dimensional image of the patient P acquired by an imaging device such as a CT scanner, cone-beam CT scanner, magnetic resonance imaging (MRI) device, or ultrasound diagnostic device. The three-dimensional image is used, for example, as a CT image of the patient P acquired during the planning stage before radiotherapy, such as the treatment planning stage in radiotherapy, to predetermine the location of the treatment site, the orientation (irradiation direction) of the treatment beam B irradiating the treatment site, and the intensity (irradiation intensity) of the irradiated treatment beam B. The three-dimensional image can also be a digitally reconstructed radiograph (DRR) image obtained by virtually reconstructing the X-ray fluoroscopic image PI from the CT image. In the following description, it is assumed that the first image acquisition unit 50 acquires a CT image. The first image acquisition unit 50 outputs the acquired CT image to the image positioning unit 70 and the medical image processing device 100. Furthermore, the CT image may also include the region of interest (ROI) during radiotherapy. The three-dimensional image (e.g., a CT image) or DRR image acquired by the first image acquisition unit 50 is an example of the "first image" in the claims.

[0047] The medical image processing apparatus 100 refers to comparison images collected in the comparison image database 110 and determines a positioning region for alignment of patient P based on the CT image output by the first image acquisition unit 50. Alternatively, the medical image processing apparatus 100 may acquire comparison images collected in the comparison image database 110 via, for example, a LAN (Local Area Network) or WAN (Wide Area Network), and determine the positioning region based on the acquired comparison images for the CT image. The medical image processing apparatus 100 outputs information about the determined positioning region to the positioning unit 70. Furthermore, the medical image processing apparatus 100 outputs the CT image output by the first image acquisition unit 50 and the determined positioning region information to the display control unit 80. Details regarding the structure and processing of the medical image processing apparatus 100 will be described later.

[0048] The comparative image database 110 collects comparative images generated from three-dimensional stereoscopic images (e.g., CT images) used for patient alignment during past radiotherapy. In the comparative image database 110, multiple comparative images are collected for each treatment site treated in past radiotherapy. In other words, the comparative image database 110 contains image sets of comparative images for each treatment site. The comparative images collected in the comparative image database 110 can be either three-dimensional or two-dimensional. Details related to the structure of the comparative images collected in the comparative image database 110 will be described later.

[0049] The second image acquisition unit 60 acquires an X-ray fluoroscopic image PI of the patient P currently fixed to the treatment table 10 in the treatment room where the treatment system 1 is installed. The second image acquisition unit 60 acquires the X-ray fluoroscopic image PI of the patient P currently fixed to the treatment table 10 via each radiation detector 30. That is, the second image acquisition unit 60 acquires an X-ray fluoroscopic image PI of the patient P taken at a different time than the CT image acquired by the first image acquisition unit 50. Furthermore, the second image acquisition unit 60 and the radiation detectors 30 may be connected separately via LAN or WAN. The second image acquisition unit 60 outputs the acquired X-ray fluoroscopic image PI to the positioning unit 70. The X-ray fluoroscopic image PI is an example of the "second image" in the claims.

[0050] The positioning unit 70 compares the CT image output by the first image acquisition unit 50 with the X-ray fluoroscopic image PI output by the second image acquisition unit 60, and determines the preferred position of the patient P for radiotherapy by comparing the positioning area information output by the medical image processing device 100. Furthermore, the positioning unit 70 calculates the amount of movement of the treatment table 10 required to move the current position of the patient P, which is fixed to the treatment table 10, to the preferred position for radiotherapy. In other words, for the current position of the patient P, the positioning unit 70 calculates the amount of movement of the treatment table 10 required to irradiate the treatment beam B towards the treatment site from the irradiation direction predetermined in the planning stage based on the CT image. The positioning unit 70 outputs the calculated movement information to the examination table control unit 11, and moves the position of the patient P by means of a parallel mechanism and a rotation mechanism provided on the treatment table 10.

[0051] The display control unit 80 displays an image on the display device 81, overlaying the positioning area determined by the medical image processing device 100 onto the CT image output by the medical image processing device 100. Thus, the range of the positioning area within the CT image is displayed on the display device 81, such as a liquid crystal display (LCD), allowing the practitioner (doctor, etc.) performing radiotherapy using the treatment system 1 to visually confirm the determined positioning area. Furthermore, the treatment system 1 may also be structured to include a user interface such as an operation unit (not shown) operated by the practitioner (doctor, etc.) to manually adjust the positioning area determined by the medical image processing device 100. Additionally, in the treatment system 1, the "medical device" may also be structured to include, in addition to the first image acquisition unit 50, the second image acquisition unit 60, the positioning unit 70, the display control unit 80, and the medical image processing device 100, a user interface such as an operation unit (not shown). Furthermore, in the treatment system 1, the "medical device" may be an integrated structure with the display device 81.

[0052] Next, the structure of the medical device including the medical image processing apparatus 100 constituting the first embodiment of the treatment system 1 will be described. Figure 2 This is a block diagram showing the schematic structure of the medical device and the medical image processing device 100 according to the first embodiment. Figure 2 The diagram shows the connection relationships between the first image acquisition unit 50, the second image acquisition unit 60, the positioning unit 70, and the medical image processing device 100 constituting the medical device. Additionally, in... Figure 2 The connection between the comparison image database 110 and the examination bed control unit 11, which are related to the medical device including the medical image processing device 100, is also shown. Furthermore, in Figure 2 In this context, the connection relationship between the display control unit 80 constituting the medical device and other components (more specifically, the medical image processing device 100) is determined according to... Figure 1 It's easy to understand, so it's omitted.

[0053] Regarding the comparison images collected in the comparison image database 110, the segmented images and the effective region images are grouped together. Figure 2 The image shows a state where multiple comparison images Ci, from comparison image Ci-1 to comparison image Ci-n, are collected in the comparison image database 110. Additionally, in... Figure 2In the diagram, comparison image Ci-1 is composed of the segmented image Di-1 and the effective region image Ei-1; comparison image Ci-2 is composed of the segmented image Di-2 and the effective region image Ei-2; and comparison image Ci-n is composed of the segmented image Di-n and the effective region image Ei-n. Furthermore, the "-" and the following numbers assigned after the reference numerals of the comparison images Ci are used to identify the correspondence. Additionally, when not distinguishing between individual images in the following description, the "-" and the following numbers are not shown.

[0054] A segmented image is a patch image obtained by cutting out a defined area and segmenting a three-dimensional image (e.g., a CT image) used for patient alignment in past radiotherapy. The CT image, etc., used for patient alignment in past radiotherapy, includes the region of interest that was considered when aligning the patient's position (so that the patient faces the treatment site and the direction of the treatment beam B) during that radiotherapy. This region of interest refers to the area that was utilized during patient alignment in past radiotherapy. A segmented image is an image obtained by cutting out a defined area containing the characteristic shape of this region of interest. Here, the region of interest, for example, refers to the area designated by the radiotherapy practitioner (doctor, etc.) during past radiotherapy as the region of interest for patient alignment, such as an area containing images of bones within the patient's body. Furthermore, the region of interest contained in the segmented image is not limited to the area designated for the current patient P. For example, the region of interest contained in the segmented image refers to the area designated by the radiotherapy practitioner (doctor, etc.) in the past for patient alignment during radiotherapy. In other words, the region of interest contained in a segmented image refers to the region that is specified for radiotherapy of the same treatment site, but is specified for multiple unspecified patients.

[0055] An effective region image refers to an image in which the region of interest contained in the corresponding segmented image is shown as the effective region, that can be effectively used for patient alignment during subsequent radiotherapy. Therefore, an effective region image may also be, for example, a portion of the region of interest designated by the radiotherapy practitioner (physician, etc.) in past radiotherapy sessions, which is shown as the effective region.

[0056] Here, an example of a comparison image Ci collected in the comparison image database 110 is illustrated. Figure 3 This is a diagram illustrating an example of a comparison image Ci referenced by the medical image processing apparatus 100 of the first embodiment. Figure 3An example of a comparative image Ci is shown, depicting a treatment site within the facial region of patient P where a therapeutic beam B is irradiated. Additionally, Figure 3 The CT image shown is a conceptual diagram of the bones (skull) of the patient's head.

[0057] exist Figure 3 In one example of the comparison image Ci shown, five segmented images (segmentation images Di-11 to Di-15) corresponding to the bones of the patient's head (skull bone (conceptual diagram)) and five effective region images (effective region images Ei-11 to Ei-15) are grouped together. Furthermore, the comparison images Ci collected in the comparison image database 110 can be either three-dimensional or two-dimensional images, as described above. Figure 3 For ease of explanation, an example of a two-dimensional comparison image Ci is shown.

[0058] As described above, each segmented image Di is obtained by cutting out a region of interest containing a characteristic shape from a three-dimensional stereoscopic image (e.g., a CT image CTI) used in past radiotherapy for patient alignment, within a defined range. Figure 3 The example shown is a segmented image Di containing the curved portion of the outer periphery of the skull and portions of the eyes and nose as characteristic shapes. Furthermore, as described above, for each effective region image Ei, the characteristic shapes contained in the corresponding segmented image Di are shown as effective regions that can be effectively utilized for patient alignment during radiotherapy. Figure 3 The image shows an example of an effective region image Ei that uses a portion of the skull bones as the effective region Ea. Furthermore, the effective region Ea in the effective region image Ei can not only include... Figure 3 The bone portion shown can also be shaped, for example, the boundary between the bone-bearing portion and the boneless portion (in...). Figure 3 In this context, the effective region is defined as the shape of the skull bones, the curves of the periphery, and the boundaries of the eyes and nose. Thus, the comparison image Ci collected in the medical image processing device 100 refers to a group of images where the segmented image Di and the effective region image Ei are paired. Therefore, the segmented image Di and the effective region image Ei can also be assigned the same information (e.g., the same identification information (ID)) to indicate that they are a group.

[0059] Furthermore, as mentioned above, the effective region Ea shown in the effective region image Ei can also be only a portion of the region of interest contained in the segmented image Di. Figure 3In one example shown, effective region images Ei-13 and Ei-14 are examples of effective region images Ei in which only a portion of the region of interest contained in segmentation image Di is shown as effective region Ea. In effective region images Ei-13 and Ei-14, the bones of the jaw are removed from effective region Ea. This is because the patient's jaw contains joints whose shape varies depending on how the mouth is open at the time of imaging, and these are not necessarily considered to be effective for alignment with the patient. Furthermore, in cases such as those involving diseases where the treatment site moves along with the bone during radiation therapy, where the bones of the joints are also considered effective regions, the bones of the joints can also be shown as effective regions in effective region image Ei. Therefore, the structure and number of segmentation images Di and effective region images Ei collected according to the treatment site are different, as described above. Additionally, there are cases where fixation clamps used to immobilize the patient are captured in segmentation image Di. In this case, the fixation clamps are removed from the effective region in effective region image Ei, regardless of the treatment site. This is because fixation clamps are clamps that fix the current posture of the patient, and it is more reasonable to assume that they should not be fixed in the same posture as during past radiotherapy.

[0060] Thus, in the image database 110 for comparison, a group of images of segmented image Di and the effective region image Ei corresponding to segmented image Di are collected together according to the treatment site. The segmented image Di is obtained by cutting out the region of interest containing a characteristic shape within a specified range from a three-dimensional stereoscopic image used for patient alignment in past radiotherapy. Figure 4 This is a diagram illustrating another example of a comparative image referenced by the medical image processing apparatus of the first embodiment. Figure 4 An example of a comparative image Ci is shown, depicting a disease at a treatment site within the patient's waist area where therapeutic beam B is irradiated. Additionally, Figure 4 To make it easier to identify the subject in the CT image shown, CTI set the background color to white.

[0061] exist Figure 4 In one example of the comparison using image Ci, the two segmented images (segmentation image Di-21 and segmentation image Di-22) corresponding to the bones of the patient's pelvis, and the two effective region images (effective region image Ei-21 and effective region image Ei-22) are grouped together. Additionally, in Figure 4 In one example of the comparison using image Ci, the two segmented images (segmentation image Di-23 and segmentation image Di-24) corresponding to the bones of the patient's leg, and the two effective region images (effective region image Ei-23 and effective region image Ei-24) are grouped together. Additionally, in Figure 4 In one example of the comparison using image Ci, a segmented image Di-25 corresponding to the patient's coccyx and an effective region image Ei-25 are grouped together. Additionally, in Figure 4 In this context, as an example of a comparison image Ci used for parts other than the patient's body, a segmented image Di-26 corresponding to the structural portion of the treatment table 10 and an effective region image Ei-26 are grouped together. Additionally, in Figure 4 For ease of explanation, an example of a two-dimensional comparison image Ci is shown.

[0062] exist Figure 4 In one example shown, segmentation image Di-21 and segmentation image Di-23 are the same segmentation image Di. Additionally, in Figure 4 In the example shown, segmentation image Di-22 and segmentation image Di-24 are the same segmentation image Di. However, different effective regions Ea are shown in the corresponding effective region images Ei. This is to select the effective region image Ei based on various conditions such as the treatment site of the radiation therapy and whether it includes joint portions with shape variations as described above. Figure 4 The segmented images Di-21 and Di-23 shown correspond to effective region images Ei-21 and Ei-23, respectively. Depending on whether the effective region Ea is a bone of the pelvis or a bone of the leg, different effective region images Ei are generated. Similarly, with... Figure 4 The effective region images Ei-22 and Ei-24 corresponding to the segmented images Di-22 and Di-24, respectively, are also generated as different effective region images Ei depending on whether the effective region Ea is a bone of the pelvis or a bone of the leg. This is because the position and angle relationship between the bones of the pelvis and the leg may not be the same depending on the patient's posture during treatment and the patient's posture during imaging.

[0063] in addition, Figure 4 The group of segmented images Di-25 corresponding to the patient's coccyx and effective region images Ei-25 shown can be used simultaneously, regardless of whether the effective region Ea is the bone of the pelvis or the bone of the leg.

[0064] In addition, Figure 4As an example of a portion of the patient's body structure removed by the effective region Ea, an example is shown where a part of the treatment table 10 is included in the segmentation image Di-26. As described above, the portion of the patient's body outside the treatment site is removed by the effective region Ea. Therefore, the effective region Ea is not shown in the effective region image Ei-26 corresponding to the segmentation image Di-26. Thus, even if the portion removed by the effective region is captured in the segmentation image Di, by not showing it as the effective region Ea in the effective region image Ei, it is possible to remove areas that are not utilized during patient alignment (in other words, invalid areas).

[0065] Return to Figure 2 The medical image processing device 100 includes a comparison unit 101 and a positioning area determination unit 102.

[0066] The comparison unit 101 compares the three-dimensional image (e.g., a CT image) output by the first image acquisition unit 50 with each comparison image Ci (more specifically, segmented images Di) collected in the comparison image database 110. At this time, the comparison unit 101 selects an image group of comparison images Ci corresponding to the treatment site and compares the segmented images Di contained in the selected image group with the CT image. The information used to select the image group of comparison images Ci for comparison by the comparison unit 101 can be, for example, information about the treatment site input by the radiation therapist (doctor, etc.) through an operation unit (not shown), or information about the treatment site contained in the CT image. The comparison unit 101 calculates, for example, the squared error of the brightness in the pixels of each image constituting the CT image and the comparison image Ci, thereby comparing the CT image with the comparison image Ci. Furthermore, the method for comparing the CT image and the comparison image Ci in the comparison unit 101 is not limited to the method of calculating the squared error. The comparison unit 101 compares the CT image with the comparison image Ci and selects a segmentation image Di that is similar to a certain location in the CT image (e.g., a segmentation image Di with a similarity to the CT image of a predetermined value or higher). The comparison unit 101 outputs information indicating the comparison result to the localization region determination unit 102. The comparison unit 101 outputs information indicating the selected segmentation image Di (e.g., the identification information (ID) assigned to the segmentation image Di) and information about the location in the CT image similar to the segmentation image Di as comparison result information to the localization region determination unit 102. Alternatively, the comparison unit 101 may include information about the similarity between the CT image and the segmentation image Di in the comparison result information and output it to the localization region determination unit 102. In addition, if there are multiple segmentation images Di that are similar to the CT image, the comparison unit 101 outputs the comparison result information corresponding to each segmentation image Di to the localization region determination unit 102.

[0067] The positioning region determination unit 102 determines the range of the effective region contained in the CT image as the positioning region based on the comparison result information output by the comparison unit 101. The positioning region determination unit 102 extracts the effective region Ea shown in the effective region image Ei corresponding to the segmented image Di selected by the comparison unit 101, and allocates the extracted effective region Ea within the CT image, thereby determining the range of the effective region Ea contained in the CT image as the positioning region. Furthermore, if the comparison result information output by the comparison unit 101 shows a situation similar to multiple segmented images Di, the positioning region determination unit 102 combines the ranges of the effective regions Ea shown in the effective region images Ei corresponding to each segmented image Di, and determines the range of the combined effective region Ea as the range of the positioning region in the CT image. At this time, when there are overlapping ranges in the effective regions Ea shown in each effective region image Ei, the positioning region determination unit 102 may also determine the positioning region using only the effective region Ea shown in one effective region image Ei. Alternatively, the positioning region determination unit 102 may also determine the positioning region by averaging the overlapping ranges of each effective region Ea. Furthermore, the positioning region determination unit 102 can also determine the positioning region by averaging the ranges of repeated effective regions Ea based on the similarity information contained in the comparison results output by the comparison unit 101. Alternatively, the positioning region determination unit 102 can use the most frequent value of the ranges of repeated effective regions Ea to determine the positioning region. The positioning region determination unit 102 outputs information indicating the range of the determined positioning region within the CT image to the positioning unit 70. Additionally, the positioning region determination unit 102 outputs the CT image and the determined positioning region within the CT image to the display control unit 80.

[0068] According to this structure, in the medical image processing apparatus 100, the comparison unit 101 compares the CT image with the segmented image Di, and the positioning region determination unit 102 determines the positioning region within the CT image. Therefore, in the medical image processing apparatus 100, for example, when a user interface (not shown) is used by an operator (doctor, etc.) who does not require radiotherapy to specify the area of ​​interest during patient P alignment, the positioning region can be automatically set to be the same as the area of ​​interest used for patient alignment in past radiotherapy treatments of the same treatment site. Thus, in a medical apparatus including the medical image processing apparatus 100, the direction of patient P undergoing radiotherapy can be directed toward the position determined by the positioning unit 70, that is, the direction in which patient P is irradiated by the treatment beam B can be preferred.

[0069] Next, an overview of the actions of treatment system 1 will be provided. Figure 5This is a flowchart illustrating the operation process of the treatment system 1 according to the first embodiment. Furthermore, in the following description, it is assumed that a CT image (three-dimensional stereoscopic image) of the patient P is prepared in advance using a CT scanner. It is also assumed that the treatment system 1 is input with information about the treatment site of the patient P who will subsequently undergo radiotherapy. That is, the medical image processing device 100 (more specifically, the comparison unit 101) has been input with the image group of which comparison image Ci collected in the comparison image database 110 is selected.

[0070] When the treatment system 1 starts operating, the first image acquisition unit 50 acquires a CT image (step S100). Furthermore, the first image acquisition unit 50 outputs the acquired CT image to the positioning unit 70 and the comparison unit 101 provided in the medical image processing device 100.

[0071] Next, the comparison unit 101 compares the CT image output by the first image acquisition unit 50 with each segmented image Di of the treatment site collected in the comparison image database 110 (step S101). Furthermore, the comparison unit 101 outputs the comparison result information to the positioning region determination unit 102.

[0072] Next, the positioning region determination unit 102 determines the positioning region for the CT image based on the comparison result information output by the comparison unit 101 (step S102). Furthermore, the positioning region determination unit 102 outputs information indicating the range of the positioning region determined for the CT image to the positioning unit 70.

[0073] Here, an example of the operation of the comparison unit 101 comparing the CT image with the segmented image Di (step S101) and the localization region determination unit 102 determining the localization region for the CT image (step S102) will be described. Figure 6A , Figure 6B , Figure 6C as well as Figure 6D This diagram schematically illustrates an example of the operation of the comparison unit 101 and the positioning region determination unit 102 included in the medical image processing apparatus 100 of the first embodiment. Figure 6A The image shows the state in which comparison images Ci are collected in the comparison image database 110. Additionally, in... Figure 6B The diagram schematically illustrates an example of the comparison unit 101 comparing the CT image CTI with the segmented image Di. Additionally, in Figure 6C as well as Figure 6D The diagram schematically illustrates an example of the operation of the positioning region determination unit 102 in determining the positioning region (allocation of the effective region for CT image CTI) for a CT image CTI. In the following description, as... Figure 6A As shown, assuming Figure 3Comparative images Ci corresponding to the bones of the patient's head (skull (conceptual diagram)) as shown are collected in the comparative image database 110.

[0074] In step S101, the comparison unit 101 first selects an image group of comparison images Ci collected in the comparison image database 110. Furthermore, within the CT image CTI output by the first image acquisition unit 50, the comparison unit 101 searches for positions similar to each segmented image Di contained in the selected image group. While searching for positions similar to segmented images Di, the comparison unit 101 moves the segmented images Di sequentially within the CT image CTI, calculates the similarity between the segmented images Di and the CT image CTI at each position, and designates positions with a similarity score of a predetermined value or higher as positions within the CT image CTI similar to the segmented images Di. Figure 6B The illustrated action example shows a state in which segmented images Di-15 are sequentially moved within a CT image CTI in a scanning (raster scan) manner. The similarity between segmented images Di-15 and the CT image CTI is calculated at each position, thereby searching for positions within the CT image CTI similar to segmented images Di-15. The comparison unit 101 performs this search for positions similar to segmented images Di within all segmented images Di in the selected image group, establishes a correspondence between information of segmented images Di indicating similar positions within the CT image CTI (positions with similarity values ​​exceeding a specified value) and information of the obtained positions within the CT image CTI, and outputs this comparison result to the positioning region determination unit 102.

[0075] Furthermore, the method by which the comparison unit 101 compares the CT image CTI with the segmented image Di in step S101 is not limited to, for example... Figure 6B The method described above calculates similarity by sequentially moving the selected segmented image Di within the CT image CTI. For example, another method involves sequentially cutting out regions of the same size as segmented image Di from the CT image CTI using a raster scan, and comparing the cut-out regions with each segmented image Di contained in the selected image group. In other words, another method involves searching for locations within the CT image CTI similar to segmented image Di. Figure 6B The action example shown is the opposite, searching for a segmented image Di that is similar to a specified location within the CTI of a CT image.

[0076] Next, in step S102, the positioning region determination unit 102 first selects the effective region image Ei corresponding to the segmented image Di shown in the comparison result information output by the comparison unit 101 from the image group of comparison images Ci collected in the comparison image database 110. Furthermore, the positioning region determination unit 102 extracts the effective regions shown in each of the acquired effective region images Ei and assigns them within the CT image CTI. Figure 6C The illustrated operation example shows a state in which the effective region images Ei-11 to Ei-15 corresponding to the segmented images Di-11 to Di-15, as shown by the comparison result information output by the comparison unit 101, are obtained, and the effective regions Ea shown in each effective region image Ei are allocated within the CT image CTI. The positioning region determination unit 102 determines the range of the effective regions Ea thus allocated within the CT image CTI as the positioning region, and outputs information indicating the range of the determined positioning region to the positioning unit 70.

[0077] In addition, Figure 3 and Figure 6A , Figure 6B , Figure 6C as well as Figure 6D The diagram shows five comparative images Ci corresponding to the bones of a patient's head (skull (conceptual diagram)) collected in the comparative image database 110. However, as described above, the comparative image database 110 also includes comparative images Ci representing effective regions designated by the practitioner (doctor, etc.) during past radiotherapy patient alignment. Therefore, by increasing the number of comparative images Ci collected in the comparative image database 110, for example... Figure 6D As shown, the effective region Ea may also be allocated within the entire skull of patient P captured in the CT image CTI. In this case, the positioning region determination unit 102 determines the entire extent of the skull of patient P captured in the CT image CTI as the positioning region, and outputs information indicating that the entire extent of the skull is the extent of the positioning region to the positioning unit 70.

[0078] Return to Figure 5 Next, the second image acquisition unit 60 acquires the X-ray fluoroscopic image PI of the current patient P output by each radiation detector 30 (step S103). Furthermore, the second image acquisition unit 60 outputs the acquired X-ray fluoroscopic image PI to the positioning unit 70.

[0079] Next, the positioning unit 70 compares the CT image output by the first image acquisition unit 50 and the X-ray fluoroscopic image PI output by the second image acquisition unit 60 with the information indicating the range of the positioning area output by the positioning area determination unit 102 to determine the position of the patient P (step S104). Furthermore, the positioning unit 70 calculates the amount of movement required to move the treatment table 10 to the determined position of the patient P. The positioning unit 70 then outputs the calculated amount of movement of the treatment table 10 to the examination table control unit 11.

[0080] Next, the examination table control unit 11 moves the treatment table 10 according to the movement information output by the positioning unit 70 (step S105). As a result, the current position of the patient P, which is fixed to the treatment table 10, is moved to a preferred position for radiotherapy.

[0081] As described above, in the medical image processing apparatus 100, referring to the comparison image Ci collected in the comparison image database 110, the positioning region used for the alignment of patient P is determined for the CT image output by the first image acquisition unit 50, and information indicating the range of the determined positioning region is output to the positioning unit 70. More specifically, in the medical image processing apparatus 100, the comparison unit 101 compares the CT image output by the first image acquisition unit 50 with the segmented image Di constituting the comparison image Ci collected in the comparison image database 110. Furthermore, in the medical image processing apparatus 100, the positioning region determination unit 102 allocates an effective region Ea, as shown in the effective region image Ei constituting the comparison image Ci, within the CT image based on the comparison result information output by the comparison unit 101, and determines the positioning region used for the alignment of patient P, and outputs information indicating the range of the determined positioning region to the positioning unit 70. Therefore, in the treatment system 1 equipped with a medical device including a medical image processing unit 100, even if the positioning area used for patient P alignment is not determined in the CT images taken during the radiotherapy planning stage, the positioning area can be automatically set during the radiotherapy treatment stage, for example, without the need for the radiotherapy practitioner (doctor, etc.) to specify the positioning area. In other words, in the treatment system 1 equipped with a medical device including a medical image processing unit 100, the positioning area that has been used in past radiotherapy patient alignment can be automatically set.

[0082] Furthermore, in the medical device including the medical image processing device 100, the positioning unit 70 determines the position of the patient P by comparing the CT image output by the first image acquisition unit 50 with the X-ray fluoroscopic image PI output by the second image acquisition unit 60, based on information indicating the range of the positioning area output by the positioning area determination unit 102. Moreover, the positioning unit 70 calculates the amount of movement of the treatment table 10 based on the determined position of the patient P and outputs the calculated amount of movement of the treatment table 10 to the examination table control unit 11. Thus, in the treatment system 1 equipped with the medical device including the medical image processing device 100, the current position of the patient P, fixed to the treatment table 10, can be moved to a preferred position for radiotherapy. Therefore, in the treatment system 1 equipped with the medical device including the medical image processing device 100, the positioning of the patient P during radiotherapy can be performed with high precision.

[0083] Furthermore, in the above description, the case where the comparison image Ci collected in the comparison image database 110 is a patch image was explained. This patch image is obtained by cutting out a range of a predetermined size from a three-dimensional stereoscopic image (e.g., a CT image) used for patient alignment in past radiotherapy and then segmenting it. In other words, the case where the segmented image Di is a three-dimensional patch image was explained. However, the segmented image Di is not limited to a three-dimensional patch image. For example, the segmented image Di may also be a two-dimensional patch image obtained by cutting out a range of a predetermined angle from a three-dimensional stereoscopic image, or a two-dimensional image itself. In this case, the comparison unit 101 similarly selects the two-dimensional segmented image Di with a similarity of a predetermined value or higher to the CT image, and outputs information representing the selected two-dimensional segmented image Di (e.g., the identification information (ID) assigned to the segmented image Di) as the comparison result to the positioning region determination unit 102. Alternatively, the comparison unit 101 may select the two-dimensional segmented image Di with the highest similarity, and output the identification information (ID) assigned to the selected two-dimensional segmented image Di with the highest similarity as the comparison result to the positioning region determination unit 102. In this case, the positioning region determination unit 102 may directly output the range of the effective region Ea shown in the two-dimensional effective region image Ei corresponding to the two-dimensional segmented image Di selected by the comparison unit 101 as information representing the range of the positioning region within the determined CT image to the positioning unit 70.

[0084] Furthermore, in treatment system 1, the positions of the radiation source 20 and the radiation detector 30 are fixed, so the direction (relative to the fixed coordinate system of the treatment room) of the imaging device composed of the radiation source 20 and the radiation detector 30 is fixed. However, in treatment system 1, such as Figure 1As shown, X-ray fluoroscopic images PI of patient P are captured from two different directions. That is, the X-ray fluoroscopic image PI of patient P captured in treatment system 1 is a three-dimensional image. Therefore, the comparison between the CT image and the X-ray fluoroscopic image PI performed by the positioning unit 70 to determine the position of patient P becomes a comparison of three-dimensional images. In this case, the positioning unit 70, for example, moves the CT image with parameters of parallelism and rotation, and determines the position of patient P for which the error between the CT image and the X-ray fluoroscopic image PI is minimized as the preferred position for radiotherapy. At this time, it is also possible that the positioning unit 70 changes the error weighting between the effective area Ea in the CT image and the area outside the effective area Ea based on information representing the range of the positioning area output by the positioning area determination unit 102, and uses the effective area Ea to determine the position of patient P. Alternatively, it is also possible that the positioning unit 70 uses the mutual information of each image of the CT image and the X-ray fluoroscopic image PI to determine the preferred position of patient P for radiotherapy.

[0085] Furthermore, as described above, in treatment system 1, the case where the positioning unit 70 compares the images taken by the comparison when determining the position of patient P is a CT image and an X-ray fluoroscopy image PI, i.e., images taken by different imaging devices (medical imaging equipment), has been explained. However, it is also possible that the positioning unit 70 compares the images taken by the same imaging device (medical imaging equipment) when determining the position of patient P. In this case, the positioning unit 70 may use the sum of squared residuals of the pixels constituting each image, or the sum of the absolute values ​​of the residuals, normalized cross-correlation, etc., to determine the position where the error between the images is minimized as the preferred position for radiotherapy.

[0086] Furthermore, as described above, in treatment system 1, the positioning unit 70 determines the position of patient P by comparing three-dimensional images, such as CT images and X-ray fluoroscopy images PI, with each other. However, it is also possible that the images compared by the positioning unit 70 when determining the position of patient P are images of different dimensions. For example, when the radiation source 20 and the radiation detector 30 are a set in treatment system 1, the X-ray fluoroscopy image PI becomes a two-dimensional image. In this case, the positioning unit 70 may project the CT image into a two-dimensional image according to the geometric information of the X-ray fluoroscopy image PI when calculating the error between the CT image and the X-ray fluoroscopy image PI, thereby comparing the two-dimensional images with each other. In this case, the positioning unit 70 also projects the range of the positioning region (i.e., the range of the effective region Ea) output by the positioning region determination unit 102 into a two-dimensional image according to the geometric information. Thus, the positioning unit 70 can, in the same way as the case described above where three-dimensional images are compared with each other, change the error weighting between the effective region Ea in the CT image and the region outside the effective region Ea, and use the effective region Ea for determining the position of patient P. At this time, the positioning unit 70 can use a similar scale as when comparing a CT image projected as a two-dimensional image with a two-dimensional X-ray fluoroscopy image PI, similar to the scale used when comparing three-dimensional images as described above. "Geometric information" refers to information that, when three-dimensional coordinates are defined within the three-dimensional space where the treatment system 1 is installed, can represent the positions of the radiation source 20 and the radiation detector 30 using coordinate values ​​on three axes. Using this geometric information, the position of the patient P, located at any position within the specified three-dimensional coordinates, can be determined based on the position of the radiation r irradiated by the radiation source 20 as it passes through the patient P's body and reaches the radiation detector 30. Furthermore, the geometric information can be obtained from the installation positions of the radiation source 20 and the radiation detector 30 designed when the treatment system 1 is installed. Additionally, the geometric information can also be obtained from the installation positions of the radiation source 20 and the radiation detector 30 measured by a three-dimensional measuring instrument or the like.

[0087] Furthermore, the positioning unit 70 moves the CT image to align its position with the position of the X-ray fluoroscopy image PI, thereby determining the preferred position of the patient P for radiotherapy. However, in actual radiotherapy, a treatment beam B is irradiated onto the treatment site of the patient P from an irradiation direction predetermined during the radiotherapy planning phase based on the CT image. Therefore, the amount of movement of the treatment table 10 determined by the positioning unit 70 is calculated by reversing the direction and amount of movement of the CT image to align its position with the position of the X-ray fluoroscopy image PI. In other words, the amount of movement of the treatment table 10 determined by the positioning unit 70 is the amount of movement required to move the patient P, who is fixed to the treatment table 10, in a manner that allows each radiation detector 30 to capture an X-ray fluoroscopy image PI identical to the CT image captured during the planning phase.

[0088] As described above, the medical image processing apparatus 100 includes: a comparison unit 101 that compares a first image (a three-dimensional stereoscopic image (e.g., a CT image)) obtained by photographing a patient P with a comparison image Ci, wherein the comparison image Ci is an image (a three-dimensional stereoscopic image (e.g., a CT image)) used in past radiotherapy and is designated with an effective region Ea used for alignment in radiotherapy; and a positioning region determination unit 102 that determines a positioning region similar to the effective region Ea contained in the first image based on the comparison result of the comparison unit 101.

[0089] Alternatively, as explained above, in the medical image processing apparatus 100, the comparison image Ci may contain multiple such images that were collected during past radiotherapy, and a portion of a segmented image Di obtained by dividing a fluoroscopic image PI (a three-dimensional image (e.g., a CT image) used in past radiotherapy into a specified size is designated as the effective region Ea. The positioning region determination unit 102 extracts regions similar to the effective region Ea from the multiple comparison images Ci, and combines the regions extracted from the multiple comparison images Ci to determine the positioning region.

[0090] Alternatively, as explained above, the medical image processing apparatus 100 may prepare multiple comparison images Ci, each comparison image Ci being merged into multiple image groups according to the treatment site treated in past radiotherapy, and the comparison unit 101 selecting the image group of comparison images Ci to be compared with the first image according to the treatment site of the patient P.

[0091] Alternatively, as explained above, in the medical image processing apparatus 100, the first image may be a DRR image.

[0092] Alternatively, as described above, the medical device may include: a first image acquisition unit 50 that acquires a first image (a three-dimensional image, such as a CT image) obtained by photographing a patient P; a second image acquisition unit 60 that acquires a second image (an X-ray fluoroscopic image PI) corresponding to the radiation r irradiated on the patient P at a time different from when the first image was acquired, obtained from an imaging device that detects and images the irradiated radiation r by a radiation detector 30; a medical image processing device 100; and a positioning unit 70 that uses the first image and the X-ray fluoroscopic image PI to determine the position of the patient P during radiotherapy based on a positioning area.

[0093] Alternatively, as described above, the medical device may also include a display control unit 80, which displays an image on the display device 81 that overlays the positioning area onto the first image.

[0094] Alternatively, as described above, the treatment system 1 may include: a medical device; a treatment beam irradiation gate 40 for irradiating the treatment beam B onto the treatment area of ​​the patient P; and an examination table control unit 11 for controlling the amount of movement of the treatment table 10 fixed to the patient P in a manner that aligns with the position determined by the positioning unit 70.

[0095] Alternatively, the medical image processing device 100 may be implemented using processors such as CPUs and GPUs, or hardware such as LSIs, ASICs, and FPGAs, or dedicated LSIs, and may include storage devices such as ROMs or RAMs, HDDs, and flash memory. As a medical image processing device 100 having a comparison unit 101 and a positioning region determination unit 102, the medical image processing program for enabling the processor to function is stored in the storage device. The comparison unit 101 compares a first image (a three-dimensional stereoscopic image (e.g., a CT image)) obtained by capturing a patient P with a comparison image Ci. The comparison image Ci is an image (a three-dimensional stereoscopic image (e.g., a CT image)) used in past radiotherapy and is designated with an effective region Ea used for alignment in radiotherapy. The positioning region determination unit 102 determines a positioning region similar to the effective region Ea contained in the first image based on the comparison result of the comparison unit 101.

[0096] (Second Implementation)

[0097] The second embodiment will be described below. Furthermore, the structure of the treatment system comprising the medical image processing apparatus of the second embodiment is as follows: Figure 1In the structure of the treatment system 1 shown, which includes the medical image processing device 100 of the first embodiment, the medical image processing device 100 is replaced by the medical image processing device of the second embodiment (hereinafter referred to as "medical image processing device 200"). In the following description, the treatment system including the medical device 200 is referred to as "treatment system 2".

[0098] Furthermore, in the following description, for the components of the treatment system 2 having a medical device including a medical image processing apparatus 200, the same reference numerals are used for the components of the treatment system 1 having a medical device including a medical image processing apparatus 100 of the first embodiment, and detailed descriptions related to each component are omitted. Moreover, in the following description, only the structure, operation, and processing of the medical image processing apparatus 200, which are different from those of the medical image processing apparatus 100 of the first embodiment, will be described.

[0099] In the treatment system 2, the combination of the first image acquisition unit 50, the second image acquisition unit 60, the positioning unit 70, the display control unit 80, and the medical image processing device 200 constitutes an example of the "medical device" as described in the claims. Alternatively, the medical device may utilize some or all of the functions of its constituent elements, such as a hardware processor like a CPU and a storage device storing a program (software), where the processor executes the program to implement the functions of each constituent element. Furthermore, some or all of the functions of the constituent elements of the medical device may be implemented using hardware (circuit unit, including circuitry) such as LSI, ASIC, FPGA, or GPU, or through a combination of software and hardware. Alternatively, some or all of the functions of the constituent elements of the medical device may be implemented using a dedicated LSI. Here, the program (software) can be pre-stored in a storage device (a storage device with non-volatile storage media) provided by the treatment system 2, such as ROM, RAM, HDD, or flash memory, or it can be stored in a removable storage medium (a non-volatile storage medium) such as DVD or CD-ROM. The storage medium is installed in the drive device provided by the treatment system 2, thereby being installed in the storage device provided by the treatment system 2. Alternatively, the program (software) can be pre-downloaded from another computer device via a network and installed in the storage device provided by the treatment system 2.

[0100] The medical image processing apparatus 200 is the same as the medical image processing apparatus 100 of the first embodiment. Referring to comparison images collected in the comparison image database 110, it determines the positioning region used for the alignment of patient P based on the CT image output by the first image acquisition unit 50. The medical image processing apparatus 200, like the medical image processing apparatus 100 of the first embodiment, outputs information about the determined positioning region to the positioning unit 70. Furthermore, like the medical image processing apparatus 100 of the first embodiment, the medical image processing apparatus 200 outputs the CT image output by the first image acquisition unit 50 and the information about the determined positioning region to the display control unit 80.

[0101] Figure 7 This is a block diagram illustrating the schematic structure of the medical device and medical image processing device 200 according to the second embodiment. Figure 7 In, with Figure 2 The medical device of the first embodiment and the medical image processing device 100 shown have the same general structure. The connection relationships of the first image acquisition unit 50, the second image acquisition unit 60, the positioning unit 70, and the medical image processing device 200 constituting the medical device are shown. Furthermore, in Figure 7 In, with Figure 2 The schematic structure of the medical device of the first embodiment and the medical image processing device 100 shown is the same, and the connection relationship between the comparison image database 110 and the examination bed control unit 11 associated with the medical device including the medical image processing device 200 is also shown. Furthermore, in Figure 7 In, with Figure 2 The medical device and the medical image processing device 100 shown in the first embodiment have the same general structure, but the connection relationship between the display control unit 80 constituting the medical device and other components (more specifically, the medical image processing device 200) is omitted.

[0102] The medical image processing apparatus 200 includes a comparison unit 101, a positioning area determination unit 102, and a patient orientation correction unit 203. The medical image processing apparatus 200 is a structure of the medical image processing apparatus 100 of the first embodiment with the addition of the patient orientation correction unit 203.

[0103] The comparison unit 101 replaces the three-dimensional stereoscopic image (e.g., a CT image) output by the first image acquisition unit 50, and compares the three-dimensional stereoscopic image (e.g., a CT image) output by the patient orientation correction unit 203 with each comparison image Ci (more specifically, segmented image Di) collected in the comparison image database 110. The operation and processing of the comparison unit 101 are the same as those of the comparison unit 101 provided in the medical image processing apparatus 100 of the first embodiment, except that the CT image compared with the segmented image Di is different. Furthermore, the positioning region determination unit 102 is the same as that provided in the medical image processing apparatus 100 of the first embodiment. Therefore, detailed descriptions related to the operation and processing of the comparison unit 101 and the positioning region determination unit 102 are omitted.

[0104] The patient orientation correction unit 203 corrects the orientation of the three-dimensional stereoscopic image (e.g., a CT image) output by the first image acquisition unit 50. The patient orientation correction unit 203 corrects the orientation of the CT image output by the first image acquisition unit 50 in such a way that the orientation of the image of patient P captured in the CT image matches the orientation of the image of patient P shown in the comparison image Ci collected in the comparison image database 110. The patient orientation correction unit 203 corrects the orientation of the CT image, for example, by performing image symmetry evaluation and pattern matching of the subject image captured in the CT image. Furthermore, the method by which the patient orientation correction unit 203 corrects the orientation of the CT image is not limited to image symmetry evaluation and pattern matching of the subject image. The patient orientation correction unit 203 outputs the orientation-corrected CT image to the comparison unit 101.

[0105] (An example of an orientation correction method for CT images based on image symmetry evaluation)

[0106] Here, an example of a method for correcting the orientation of a CT image based on the evaluation of image symmetry by the patient orientation correction unit 203 will be described. The patient orientation correction unit 203 assumes that the human body is approximately symmetrical in shape to correct the orientation of the CT image. In other words, the patient orientation correction unit 203 considers that the closer the tilt of the patient P along its body axis is to 0 degrees, the more symmetrical the image of patient P captured in the CT image is, and corrects the orientation of the CT image accordingly. Therefore, the patient orientation correction unit 203 evaluates the symmetry of the image of patient P captured in the CT image and corrects the orientation of the CT image based on the evaluation result. This method can be used when comparing the symmetry of the orientation of patient P captured in image Ci.

[0107] Figure 8A as well as Figure 8BThis diagram illustrates the concept of the patient orientation correction unit 203, included in the medical image processing apparatus 200 of the second embodiment, correcting the orientation of a CT image based on an evaluation of image symmetry. Figure 8A as well as Figure 8B The image shows an example of the orientation of the jawbone (skull) of patient P's head as seen in a CT image CTI, and the degree of symmetry between the left and right sides of the CT image CTI. Additionally, Figure 8A as well as Figure 8B To make it easier to identify the subject in the CT image shown, CTI set the background color to white. Figure 8A The image shows an example of a patient P whose skull bones are not symmetrically oriented. Figure 8B The image shows an example of a patient P whose skull bones are symmetrically oriented. Furthermore, in the following description, it is assumed that the image of patient P was taken from comparative image Ci collected in comparative image database 110, with the upper side of the image representing the front of patient P.

[0108] The degree of left-right symmetry in a CT image CTI can be determined, for example, by evaluating (comparing) the pixel values ​​at locations equidistant from the centerline CL of the patient (P). This is because if the patient's orientation is symmetrical, the pixel values ​​at locations equidistant from the centerline CL are approximately the same. In other words, it can be said that the smaller the difference in pixel values ​​at locations equidistant from the centerline CL, the more symmetrical the image of the patient (P) captured in the CT image CTI. For example, in... Figure 8A In the CT image CTI, the orientation of the skull bones in patient P is not symmetrical, resulting in a significant difference in pixel value between pixel PL1 (located to the left of the center line CL) and pixel PR1 (located to the right of the center line CL). Similarly, in... Figure 8A In the CT image CTI, the pixel value of pixel PL2, located to the left of the center line CL, is significantly different from the pixel value of pixel PR2, located to the right of the center line CL.

[0109] Therefore, the patient orientation correction unit 203 rotates the entire CT image CTI by making the difference in pixel values ​​between pixels located at equal distances to the left and right of the center line CL a smaller value than a predetermined value, thereby correcting the orientation of the CT image CTI. Thus, for example... Figure 8B Like the CTI CT images, the orientation of the bones in patient P's head is symmetrical. Figure 8BIn the CT image CTI, the orientation of the bones in patient P's head is symmetrical, so the pixel value of pixel PL1, located to the left of the center line CL, is smaller than the pixel value of pixel PR1, located to the right of the center line CL. Similarly, in... Figure 8B In the CT image CTI, the pixel value of pixel PL2, located to the left of the center line CL, is also smaller than the pixel value of pixel PR2, located to the right of the center line CL.

[0110] Thus, the patient orientation correction unit 203 corrects the orientation of the CT image CTI by comparing the pixel values ​​of each pixel located at the same distance to the left and right when referenced to the center line CL in the image of the patient P captured by the CT image CTI. An example of the processing by the patient orientation correction unit 203 in this case will be described below.

[0111] Figure 9A , Figure 9B , Figure 9C as well as Figure 9D This diagram schematically illustrates an example of the orientation correction processing of a CT image CTI by the patient orientation correction unit 203 included in the medical image processing apparatus 200 of the second embodiment. Figure 9A , Figure 9B , Figure 9C as well as Figure 9D The flowchart shows the sequence of orientation correction processing of CT image CTI by the patient orientation correction unit 203. Additionally, Figure 9A , Figure 9B , Figure 9C as well as Figure 9D To make it easier to identify the subject, the background color of each image shown is set to white.

[0112] (Sequence P-1): The patient faces the correction unit 203 and acquires the CT image CTI output by the first image acquisition unit 50. Figure 9A In sequence P-1, the state of the patient's head bone (skull) jaw, which is not symmetrical about left and right orientation, is shown in the CT image CTI-B (three-dimensional stereoscopic image) obtained by the correction unit 203 before correction.

[0113] (Sequence P-2): The patient orientation correction unit 203 extracts an image from the acquired CT image CTI-B to evaluate the symmetry (degree of left-right symmetry) of the image of patient P captured in CT image CTI-B. This image for evaluating symmetry can be extracted, for example, by cutting out the center position of CT image CTI-B. Hereinafter, the image extracted by the patient orientation correction unit 203 by cutting out the center position of CT image CTI-B will be referred to as "cutout image CTI-C". Figure 9BIn sequence P-2, an example of a cutout image CTI-C extracted from the patient facing the correction unit 203 is shown.

[0114] (Sequence P-3): While the patient faces the correction unit 203, the cut-out image CTI-C is rotated within a specified angular range, and symmetry evaluation is performed. Figure 9C In sequence P-3, the evaluation process is shown while rotating the cut-out image CTI-C within an angle range of -40 degrees to 40 degrees. The patient orientation correction unit 203 determines the angle considered most symmetrical (highest degree of left-right symmetry) through the evaluation process in sequence P-3. In other words, it determines the angle used to correct the orientation of the CT image CTI-B.

[0115] (Sequence P-4): The patient orientation correction unit 203 rotates the entire CT image CTI-B to the angle determined by the evaluation process in sequence P-3, correcting the orientation of the CT image CTI-B. Figure 9D In sequence P-4, an example is shown in which the entire CT image CTI-B (three-dimensional stereoscopic image) obtained in sequence P-1 is rotated to the corrected CT image CTI-A at the angle determined in sequence P-3.

[0116] In this sequential process, the patient orientation correction unit 203 corrects the orientation of the CT image CTI-B (before correction) output by the first image acquisition unit 50, and outputs the corrected CT image CTI-A (after correction) to the comparison unit 101. Thus, in the medical image processing apparatus 200, the comparison unit 101 compares the CT image CTI-A, whose orientation has been corrected by the patient orientation correction unit 203, with the segmented image Di, and the positioning region determination unit 102 determines the positioning region for the CT image CTI-A, whose orientation has been corrected by the patient orientation correction unit 203.

[0117] In addition, Figure 9A , Figure 9B , Figure 9C as well as Figure 9DIn the flow diagram of the patient orientation correction unit 203's orientation correction processing for CT image CTI, one cutout image CTI-C is shown, and the angle used to correct the orientation of the CT image CTI is determined. However, the number of cutout images CTI-C cut from CT image CTI-B to determine the angle used to correct the orientation of the CT image CTI is not limited to one; multiple cutout images CTI-C can be cut from CT image CTI-B, and the angle used to correct the orientation of the CT image CTI can be determined. In this case, the angle determined through the evaluation processing of each cutout image CTI-C is integrated, thereby enabling higher accuracy correction of the orientation of the CT image CTI.

[0118] Here, for Figure 9C The evaluation process (method for evaluating left-right symmetry) in sequence P-3 is explained below. For example... Figure 8A as well as Figure 8B As shown, when evaluating the left-right symmetry of a CT image CTI by comparing pixel values ​​at positions equidistant from the centerline CL of the image of patient P captured in a CT image CTI, it is necessary to determine the reference centerline CL. However, during the radiotherapy planning phase, patient P may not be captured at the center of the CT image CTI. Therefore, it is necessary to infer the center position of patient P before evaluation, or to determine the center position of patient P using evaluation values ​​with position-invariant properties.

[0119] One method for inferring the center position of patient P is to use a recognizer that pre-machines an image pattern near the center of patient P. In this method, an image pattern cut from the positions of each pixel in the uncorrected CT image is input into the recognizer, and the position where the recognizer's output is the largest can be inferred as the center position of patient P. Therefore, the patient orientation correction unit 203 can compare the pixel values ​​of each pixel with the center line CL determined based on the inferred center position as a reference, and evaluate the symmetry (degree of left-right symmetry) of the image of patient P captured in the CT image.

[0120] As a method for using evaluation values ​​with position-invariant properties, one approach is to perform a Fourier transform on a CT image and utilize the amplitude value in the frequency space. In this method, the amplitude value in the frequency space obtained by the Fourier transform can be used as an evaluation value with position-invariant properties to determine the center position of patient P. For example, if the Fourier transform of image I(x, y) is F(u, v), and image I(x, y) is linearly symmetric at the center of the image, then the Fourier transform F(u, v) is also linearly symmetric at the center. Therefore, the amplitude value is represented by the following equation (1).

[0121] [Formula 1]

[0122]

[0123] Even when the image is moved in parallel, the amplitude value expressed by equation (1) above is only a phase shift in the frequency region, and the amplitude remains unchanged, so it always holds true. Therefore, the patient orientation correction unit 203 can evaluate the symmetry (degree of left-right symmetry) of the image of patient P captured in the CT image by evaluating the symmetry of the amplitude value in the frequency region, regardless of the position of patient P in the CT image.

[0124] (An example of an orientation correction method for CT images based on pattern matching of the photographed subject)

[0125] Next, an example of a method for correcting the orientation of CT images by matching the pattern of the photographed body image will be described regarding the patient orientation correction unit 203. In correcting the orientation of CT images by matching the pattern of the photographed body image, multiple images are prepared in advance to ensure that the patient's orientation is consistent. Here, the prepared images can also be images of multiple unspecified patients. Furthermore, a recognizer is prepared to learn image patterns by using each of the prepared images as training images. The recognizer is trained at two levels: correct image patterns and incorrect image patterns. For example, the training images are randomly moved and rotated to generate arbitrary image patterns. Furthermore, image patterns with smaller offsets relative to the initial values ​​are selected as correct image patterns and learned by the recognizer. On the other hand, image patterns with larger offsets relative to the initial values ​​are selected as incorrect image patterns and learned by the recognizer.

[0126] When inferring the orientation of patient P, the patient orientation correction unit 203 alters the position and orientation of the CT image output from the first image acquisition unit 50, cuts out an image pattern, and inputs it into a recognizer. Based on the recognizer's determination result, it infers the orientation of patient P captured in the CT image. Furthermore, if the recognizer's determination result is a correct image pattern, the patient orientation correction unit 203 corrects the orientation of the CT image to the position and orientation of the image pattern cut out from the CT image.

[0127] Thus, the patient orientation correction unit 203 corrects the orientation of the CT image by using a pattern matcher that has been pre-learned for image patterns.

[0128] Next, an overview of the actions of the treatment system 2 will be provided. Figure 10 This is a flowchart illustrating the operation of the treatment system 2 according to the second embodiment. Figure 10 In the flowchart of the treatment system 2 shown, in Figure 5 In the flowchart of the treatment system 1 of the first embodiment shown, step S200 is inserted between steps S101 and S102. In other words, in the treatment system 2, the processing other than step S200 is the same as that in the treatment system 1 of the first embodiment.

[0129] When the treatment system 2 starts operating, the first image acquisition unit 50 acquires a CT image (step S100). Furthermore, the first image acquisition unit 50 outputs the acquired CT image to the positioning unit 70 and the patient orientation correction unit 203 provided in the medical image processing device 200.

[0130] Next, the patient orientation correction unit 203 corrects the orientation of the CT image output by the first image acquisition unit 50 (step S200). Furthermore, the patient orientation correction unit 203 outputs the corrected CT image to the comparison unit 101.

[0131] Later, with Figure 5 Similar to the flowchart of the treatment system 1 of the first embodiment shown, the comparison unit 101 compares the corrected CT image output by the patient toward the correction unit 203 with the segmented image Di (step S101), and the positioning region determination unit 102 determines the positioning region for the corrected CT image (step S102). Furthermore, with... Figure 5Similar to the flowchart of the treatment system 1 of the first embodiment shown, the second image acquisition unit 60 acquires an X-ray fluoroscopic image PI (step S103), the positioning unit 70 determines the position of the patient P and calculates the amount of movement of the treatment table 10 (step S104), and the examination table control unit 11 moves the treatment table 10 according to the information on the amount of movement output by the positioning unit 70 (step S105). Thus, the current position of the patient P, which is fixed to the treatment table 10, is moved to a preferred position for radiotherapy.

[0132] As described above, in the medical image processing apparatus 200, after the orientation of the CT image is corrected by the patient orientation correction unit 203, the corrected CT image is compared with the segmented image Di by the comparison unit 101, and the positioning region determination unit 102 determines the positioning region within the CT image. Therefore, even in the medical image processing apparatus 200, similar to the medical image processing apparatus 100 of the first embodiment, the user interface (not shown) used by the practitioner (doctor, etc.) who does not require radiotherapy to specify the area of ​​interest when aligning the patient P can automatically set the same positioning region used for aligning patients at the same treatment site treated in past radiotherapy. Furthermore, in the medical image processing apparatus 200, the patient orientation correction unit 203 corrects the orientation of the image of the patient P captured in the three-dimensional stereoscopic image (e.g., CT image) to match the orientation of the image of the patient P shown in the segmented image Di, thus enabling the positioning region to be set with higher precision than in the medical image processing apparatus 100 of the first embodiment. Therefore, in the medical device including the medical image processing device 200, the direction of the patient P undergoing radiotherapy can be directed towards the position determined by the positioning unit 70, that is, the patient P is directed towards the preferred direction of the irradiation treatment beam B. Thus, in the treatment system 2 equipped with the medical device including the medical image processing device 200, the positioning of the patient P during radiotherapy can be performed with high precision.

[0133] Furthermore, the above description explained the case where the patient orientation correction unit 203 rotates the entire CT image to correct its orientation. However, the correction of the CT image by the patient orientation correction unit 203 is not limited to the entire CT image. For example, the patient orientation correction unit 203 may only correct the image of the subject captured in the CT image, that is, only correct the orientation of the patient P.

[0134] As explained above, the medical image processing apparatus 200 may also include a patient orientation correction unit 203 for correcting the orientation of the first image, such that the orientation of the patient P captured in the first image (a three-dimensional image (e.g., a CT image)) is consistent with the orientation of the patient P shown in the comparison image Ci, and the comparison unit 101 compares the first image whose orientation has been corrected by the patient orientation correction unit 203 with the comparison image Ci.

[0135] (Third Implementation)

[0136] The third embodiment will be described below. Furthermore, the structure of a treatment system comprising a medical device including the medical image processing apparatus of the third embodiment is based on having... Figure 1 In the structure of the treatment system 1 of the medical device of the first embodiment of the medical image processing apparatus 100 shown, the medical image processing apparatus 100 is replaced by the medical image processing apparatus of the third embodiment (hereinafter referred to as "medical image processing apparatus 300"). In the following description, the treatment system having the medical device including the medical image processing apparatus 300 is referred to as "treatment system 3".

[0137] Furthermore, in the following description, for the components of the treatment system 3 having a medical device including a medical image processing device 300, the same reference numerals are used for the components of the treatment system 1 having a medical device including a medical image processing device 100 of the first embodiment, and detailed descriptions related to each component are omitted. Moreover, in the following description, only the structure, operation, and processing of the medical image processing device 300, which are different from those of the medical image processing device 100 of the first embodiment, will be described.

[0138] In the treatment system 3, the combination of the first image acquisition unit 50, the second image acquisition unit 60, the positioning unit 70, the display control unit 80, and the medical image processing device 300 constitutes an example of the "medical device" in the claims. Alternatively, the medical device may include a hardware processor such as a CPU and a storage device storing the program (software) (a storage device with a non-volatile storage medium), with the processor executing the program to implement the functions of each component. Furthermore, the functions of the medical device may be implemented either by hardware (circuit unit, including circuitry) such as LSI, ASIC, FPGA, or GPU, or through a combination of software and hardware. Alternatively, the functions of the medical device may be implemented by a dedicated LSI. Here, the program (software) can be pre-stored in a storage device (a storage device with non-volatile storage media) provided by the treatment system 3, such as ROM, RAM, HDD, or flash memory, or it can be stored in a removable storage medium (non-volatile storage medium) such as DVD or CD-ROM. The storage medium is installed in the drive device provided by the treatment system 3, thereby being installed in the storage device provided by the treatment system 3. Alternatively, the program (software) can be pre-downloaded from another computer device via a network and installed in the storage device provided by the treatment system 3.

[0139] Similar to the medical image processing apparatus 100 of the first embodiment, the medical image processing apparatus 300 determines the positioning region used for the alignment of patient P based on the CT image output by the first image acquisition unit 50, referring to comparison images collected in the comparison image database 110. At this time, the medical image processing apparatus 300 considers the range of the treatment beam B irradiated during radiotherapy to determine the positioning region used for the alignment of patient P. Similar to the medical image processing apparatus 100 of the first embodiment, the medical image processing apparatus 300 outputs information about the determined positioning region to the positioning unit 70. Furthermore, the medical image processing apparatus 300 generates an image that prioritizes the confirmation of the region of interest used for the alignment of patient P, taking into account the range of the treatment beam B, and outputs it to the display control unit 80.

[0140] Figure 11 This is a block diagram illustrating the schematic structure of the medical device and medical image processing device 300 according to the third embodiment. Figure 11 The diagram shows the connection relationships between the first image acquisition unit 50, the second image acquisition unit 60, the positioning unit 70, the display control unit 80, and the medical image processing device 300 constituting the medical device. Furthermore, in... Figure 11 In, with Figure 2 The schematic structure of the medical device of the first embodiment and the medical image processing device 100 shown is the same, and the connection relationship between the comparison image database 110 and the examination bed control unit 11 associated with the medical device including the medical image processing device 300 is also shown. Furthermore, in Figure 11 The connection relationships between the second image acquisition unit 60 constituting the medical device and other components (more specifically, the radiation detector 30), as well as the connection relationships between the display control unit 80 constituting the medical device and other components (more specifically, the display device 81), are omitted.

[0141] The medical image processing apparatus 300 includes a comparison unit 101, a positioning region determination unit 302, a range extraction unit 304, and a confirmation image generation unit 305. The medical image processing apparatus 300 is a structure in which the positioning region determination unit 102 of the medical image processing apparatus 100 of the first embodiment is replaced by the positioning region determination unit 302, and the range extraction unit 304 and the confirmation image generation unit 305 are added.

[0142] The range extraction unit 304 obtains range information as the arrival distance of the treatment beam B based on the three-dimensional image (e.g., a CT image) output by the first image acquisition unit 50 and treatment plan information (information predetermined in the treatment planning stage), and extracts a predetermined range that is preferentially used when considering the range in the alignment of the patient P. For example, the range extraction unit 304 obtains the range information of the treatment beam B based on information such as the location of the treatment site, the irradiation direction of the treatment beam B, and the irradiation intensity predetermined based on the CT image. Based on the obtained range information of the treatment beam B, the range extraction unit 304 extracts the range of the treatment beam B within a predetermined distance range centered on the treatment beam B. In the following description, the range of range extracted by the range extraction unit 304 is referred to as the "range range". For example, when the range of the treatment beam B is a path, the range extraction unit 304 extracts the range of a cylinder extending from the treatment beam B as the length of the range. The range extraction unit 304 outputs the extracted range information to the positioning area determination unit 302.

[0143] The positioning region determination unit 302, similar to the positioning region determination unit 102 of the medical image processing apparatus 100 in the first embodiment, determines the range of an effective region contained within the CT image as a positioning region based on the comparison result information output by the comparison unit 101. Furthermore, the positioning region determination unit 302, based on the range information output by the range extraction unit 304, determines the range of an effective region preferentially utilized for the alignment of patient P within the determined positioning region as a priority positioning region. In other words, within the effective region determined based on the comparison result information output by the comparison unit 101, the positioning region determination unit 302 determines the range of an effective region existing along the path of the range to the treatment beam B, effective in the alignment of patient P, as a priority positioning region. At this time, the positioning region determination unit 302 selects an effective region within the range determined based on the comparison result information output by the comparison unit 101, and determines the range of the selected effective region as a priority positioning region. Here, the determined priority positioning region becomes the range of an effective region within the positioning region existing on the side of the treatment beam irradiation gate 40, i.e., the anterior side, relative to the treatment site. In other words, the priority positioning area is located inside the range of the treatment beam B, that is, in a position not reached by the treatment beam B, and therefore becomes the range excluding the effective area that may not need to be aligned in the alignment of patient P.

[0144] Furthermore, the method by which the positioning area determination unit 302 determines the priority positioning area is not limited to the method described above, where, after determining the positioning area, the range of effective areas within the firing range is selected, and the selected effective area is determined as the priority positioning area. For example, the positioning area determination unit 302 may, based on the same concept as when determining the range of effective areas as the positioning area, determine the range of effective areas within the firing range output by the firing range extraction unit 304 as the priority positioning area based on the comparison result information output by the comparison unit 101. Alternatively, the comparison result information in the comparison unit 101 may be calculated within the firing range. This can reduce the calculation time in the comparison unit 101.

[0145] The positioning region determination unit 302 outputs information indicating the extent of the determined positioning region within the CT image and information indicating the extent of the determined priority positioning region to the positioning unit 70.

[0146] Therefore, the positioning unit 70 can determine the preferred position of the patient P for radiotherapy with high precision based on the information indicating the range of the preferred positioning area output by the positioning area determination unit 302. For example, in an X-ray fluoroscopic image PI, both the bone located anterior to the treatment site and the bone located medially are captured. That is, the X-ray fluoroscopic image PI is captured when the position of the bone in the depth direction is not easily discernible. Even in this state of the X-ray fluoroscopic image PI, the positioning unit 70 can determine the position of the patient P by removing the effective area of ​​the bone that is medially to the treatment beam B from the effective area used for the alignment of the patient P, based on the information indicating the range of the preferred positioning area.

[0147] Alternatively, the positioning region determination unit 302 may output only information indicating the extent of the preferred positioning region within the determined CT image to the positioning unit 70. In this case, the positioning unit 70 uses the information indicating the extent of the preferred positioning region output by the positioning region determination unit 302 as the information indicating the extent of the positioning region output by the positioning region determination unit 102 included in the medical image processing apparatus 100 of the first embodiment, thereby determining the preferred location of the patient P to undergo radiotherapy. Moreover, in this case, the positioning region determination unit 302 only needs to determine the preferred positioning region, thus enabling high-speed processing of determining the positioning region and reducing processing load.

[0148] In addition, the positioning area determination unit 302 outputs the determined priority positioning area in the CT image to the confirmation image generation unit 305.

[0149] The confirmation image generation unit 305 generates a confirmation image that overlaps with the three-dimensional stereoscopic image (e.g., a CT image) output by the first image acquisition unit 50, emphasizing the priority positioning area output by the positioning area determination unit 302. The confirmation image generation unit 305 outputs the generated confirmation image to the display control unit 80. As a result, the display control unit 80 causes the confirmation image output by the confirmation image generation unit 305 to be displayed on the display device 81.

[0150] Alternatively, in the medical image processing apparatus 300, the positioning region determination unit 302 may be identical to the positioning region determination unit 102 of the medical image processing apparatus 100 of the first embodiment, outputting the CT image output by the first image acquisition unit 50, information about the positioning region within the determined CT image, and information about the preferred positioning region to the display control unit 80. In this case, the display control unit 80 may also be configured to generate a confirmation image and display it on the display device 81. In this configuration, the medical image processing apparatus 300 may also be configured without a confirmation image generation unit 305.

[0151] (An example of confirming an image)

[0152] Here, an example of a confirmation image generated by the confirmation image generation unit 305 will be described. Figure 12 This diagram illustrates an example of a confirmation image generated by the confirmation image generation unit 305 of the medical image processing apparatus 300 according to the third embodiment. Figure 12 The image shown is an example (confirmation image) representing the extent of the preferred localization area determined by the localization area determination unit 302 within the range of bones (skull) of the patient P's head as captured in a CT image. Additionally, Figure 12 The confirmation image VRI (CT image) shown has a white background to facilitate identification of the subject.

[0153] The confirmation image generation unit 305 generates confirmation images by emphasizing (making prominent) the preferred localization area within the CT image. For example, it generates confirmation images that allow the practitioner of radiotherapy (such as a doctor) to visually confirm the area of ​​interest that is preferentially utilized when considering the range in the alignment of the patient P. For instance, the confirmation image generation unit 305 generates confirmation images that make the preferred localization area prominent by setting the area of ​​the preferred localization area to a different color than other localization areas.

[0154] exist Figure 12 The image shown is an example of such a confirmatory VRI (CT image) in which an effective region Ea is allocated to the entire skull of patient P as captured in the CT image CTI (e.g., refer to...). Figure 6D This emphasizes (makes it prominent) the priority positioning area PEa used for alignment when irradiating (i.e., scanning irradiation) the therapeutic beam B from the front of the patient P's face towards a prescribed area. Figure 12 In one example of the confirmation image VRI (CT image) shown, the priority positioning area PEa on the side (in front of) the treatment site relative to the treatment beam irradiation gate 40 is emphasized (made more prominent) by setting its color to a different color than the effective area Ea on the inside of the treatment site (e.g., the effective area Ea is blue, and the priority positioning area PEa is red). The confirmation image generation unit 305 generates this confirmation image and outputs it to the display control unit 80, which then displays the confirmation image on the display device 81. As a result, practitioners (doctors, etc.) performing radiotherapy can more clearly visually observe the priority positioning area PEa within the confirmed effective area Ea.

[0155] Furthermore, the confirmation image showing the effective region Ea and the preferred localization region PEa in the CT image can be rotated, for example, through a user interface such as an operating unit (not shown) operated by the radiation therapist (doctor, etc.). Thus, for example, the radiation therapist (doctor, etc.) can rotate the confirmation image to confirm the effective region Ea and the preferred localization region PEa from various angles.

[0156] (Another example of confirming an image)

[0157] Figure 13 This diagram illustrates another example of a confirmation image generated by the confirmation image generation unit 305 included in the medical image processing apparatus 300 of the third embodiment. Figure 13 An example of such an image (confirmation image) is shown, indicating the extent of the preferred localization region PEa determined by the localization region determination unit 302 within the range of bones (skull) of the patient P's head captured in various DRR images reconstructed from CT images. Additionally, Figure 13 The confirmation image VRI (DRR image) shown has a white background to make it easier to identify the subject.

[0158] For example, the image confirmed by the radiotherapy practitioner (doctor, etc.) in alignment with the patient P can also be considered as an X-ray fluoroscopic image PI of the patient P currently fixed on the treatment table 10, output by the two radiation detectors 30 respectively. In this case, the confirmation image generation unit 305 generates, for example, each DRR image reconstructed corresponding to the two radiation sources 20, and generates a confirmation image showing the priority localization region PEa on each of the generated DRR images. In this case, the confirmation image generation unit 305 sets the region of the priority localization region PEa in each DRR image to a different color than the effective region Ea, thereby generating a confirmation image that makes the emphasized part in each DRR image stand out.

[0159] exist Figure 13 An example of such a confirmatory image VRI (DRR image) is shown in the individual DRR images reconstructed with an effective area Ea allocated to the entire skull of patient P captured in the CT image. The priority positioning area PEa used for alignment when scanning the treatment beam B from the front of patient P's face toward the prescribed range is highlighted (made prominent). Figure 13 The DRR image on the left is, for example, a confirmation image VRI-L (DRR image) corresponding to an X-ray fluoroscopic image PI taken by an imaging device consisting of a radiation source 20-1 and a radiation detector 30-1 in treatment system 1. Additionally, Figure 13The DRR image on the right is, for example, a confirmation image (VRI-R) corresponding to an X-ray fluoroscopic image PI taken by an imaging device consisting of a radiation source 20-2 and a radiation detector 30-2 in treatment system 1. Figure 13 In one example of the confirmation images VRI (DRR images) shown, the color of the priority positioning area PEa on the side (front side) of the treatment site relative to the treatment beam irradiation gate 40 is set to a different color than the effective area Ea on the inside side relative to the treatment site (e.g., the effective area Ea is blue, and the priority positioning area PEa is red, etc.), thereby emphasizing (highlighting) it. The confirmation image generation unit 305 generates these confirmation images and outputs them to the display control unit 80, which then displays each confirmation image on the display device 81. Thus, for example, a radiotherapy practitioner (doctor, etc.) can compare the X-ray fluoroscopic image PI of the patient P currently fixed on the treatment table 10 with the corresponding confirmation images (DRR images) to more clearly visually observe the priority positioning area PEa within the effective area Ea shown in the confirmation images (DRR images). Alternatively, the confirmation images (DRR images) can also be generated solely based on the priority positioning area PEa in a CT image. This allows for the clear identification of the priority localization area PEa, and enables the comparison of monochrome X-ray fluoroscopic images (PI) and DRR images with each other, just as in conventional radiotherapy.

[0160] Next, an overview of the actions of the treatment system 3 will be provided. Figure 14 This is a flowchart illustrating the operation process of the treatment system in the third embodiment. Figure 14 The flowchart of the treatment system 3 shown includes... Figure 5 The processes shown in the flowchart of the treatment system 1 of the first embodiment are the same. Therefore, in the following description, detailed descriptions of the processes that are the same as those in the treatment system 1 of the first embodiment in the operation of the treatment system 3 will be omitted.

[0161] When the treatment system 3 starts operating, the first image acquisition unit 50 acquires a CT image (step S100). Furthermore, the first image acquisition unit 50 outputs the acquired CT image to the positioning unit 70 and the comparison unit 101, range extraction unit 304, and confirmation image generation unit 305 provided in the medical image processing device 300.

[0162] Next, the range extraction unit 304 obtains information about the range of the treatment beam B from the CT image output by the first image acquisition unit 50, and extracts the range (step S300). Furthermore, the range extraction unit 304 outputs the extracted range information to the positioning area determination unit 302.

[0163] Next, the comparison unit 101 compares the CT image output by the first image acquisition unit 50 with each segmented image Di of the treatment site collected in the comparison image database 110 (step S101). Furthermore, the comparison unit 101 outputs the comparison result information to the localization region determination unit 102. Additionally, the processing of step S101 in the comparison unit 101 can be performed simultaneously (in parallel) with the processing of step S300 in the range extraction unit 304. Alternatively, the processing of step S101 in the comparison unit 101 and the processing of step S300 in the range extraction unit 304 can be performed in reverse order.

[0164] Next, the positioning region determination unit 302 determines the positioning region for the CT image based on the comparison result information output by the comparison unit 101. Furthermore, the positioning region determination unit 302 determines the preferred positioning region within the range based on the range range information output by the range range extraction unit 304 (step S302). The positioning region determination unit 302 then outputs information indicating the range of the positioning region determined for the CT image and information indicating the range of the preferred positioning region to the positioning unit 70.

[0165] Next, the second image acquisition unit 60 acquires the X-ray fluoroscopic image PI of the current patient P output by each radiation detector 30 (step S103). Furthermore, the second image acquisition unit 60 outputs the acquired X-ray fluoroscopic image PI to the positioning unit 70.

[0166] Next, the confirmation image generation unit 305 generates a confirmation image that overlaps with the priority positioning region output by the positioning region determination unit 302 in the CT image output by the first image acquisition unit 50 (step S303). Furthermore, the confirmation image generation unit 305 outputs the generated confirmation image to the display control unit 80. As a result, the display control unit 80 causes the confirmation image output by the confirmation image generation unit 305 to be displayed on the display device 81.

[0167] Next, the positioning unit 70 compares the CT image output by the first image acquisition unit 50 with the X-ray fluoroscopic image PI output by the second image acquisition unit 60 based on the information indicating the range of the priority positioning area output by the positioning area determination unit 302, and determines the position of the patient P (step S304). Furthermore, the positioning unit 70 calculates the amount of movement required to move the treatment table 10 to the determined position of the patient P. The positioning unit 70 then outputs the calculated amount of movement of the treatment table 10 to the examination table control unit 11. Additionally, the processing in step S304 of the positioning unit 70 can be performed simultaneously (in parallel) with the processing in step S303 of the confirmation image generation unit 305.

[0168] Next, the examination table control unit 11 moves the treatment table 10 according to the movement information output by the positioning unit 70 (step S105). As a result, the current position of the patient P, which is fixed to the treatment table 10, is moved to a preferred position for radiation therapy determined according to the priority positioning area.

[0169] As described above, even the medical image processing device 300, like the medical image processing device 100 of the first embodiment, refers to the comparison image Ci collected in the comparison image database 110 and determines the positioning area used for the alignment of patient P based on the CT image output by the first image acquisition unit 50. Furthermore, in the medical image processing device 300, information on the range of the treatment beam B is obtained from the CT image, and the range is extracted to determine the preferred positioning area within the determined positioning area. Moreover, in the medical image processing device 300, information indicating the range of the determined positioning area and information indicating the range of the preferred positioning area are output to the positioning unit 70. Thus, even the medical image processing device 300, like the medical image processing device 100 of the first embodiment, can automatically set the same positioning area used for the alignment of patients with the same treatment site treated in past radiotherapy by specifying the area of ​​interest when aligning patient P through a user interface such as an operation unit (not shown) operated by the practitioner (doctor, etc.) who does not require radiotherapy. Furthermore, in the medical image processing apparatus 300, the range extraction unit 304 extracts the range from the CT image, and the positioning region determination unit 302 determines a priority positioning region that prioritizes the range to be used in the alignment of the patient P. Therefore, a more effective positioning region (a priority positioning region that requires focused alignment in radiotherapy) can be set than that of the medical image processing apparatus 100 in the first embodiment. As a result, in a medical device including the medical image processing apparatus 300, the direction of the patient P undergoing radiotherapy can be directed toward the position determined by the positioning unit 70, that is, the patient P can be directed toward a more preferred direction for irradiating the treatment beam B. Thus, in the treatment system 3 equipped with a medical device including the medical image processing apparatus 300, the positioning of the patient P during radiotherapy can be performed with higher precision.

[0170] Furthermore, in the medical image processing apparatus 300, the confirmation image generation unit 305 generates confirmation images that overlap to emphasize the priority localization area in the CT image. As a result, in medical devices including the medical image processing apparatus 300, for example, practitioners (doctors, etc.) performing radiotherapy can more clearly visually confirm the priority area of ​​interest when the range is taken into account in the alignment of the patient P.

[0171] Furthermore, in the above description, the structure in which the medical image processing apparatus 100 of the first embodiment is replaced by the medical image processing apparatus 300 has been described. In other words, the structure in which the medical image processing apparatus 300 is applied to a treatment system 1 having a medical apparatus including the medical image processing apparatus 100 of the first embodiment has been described. However, the medical image processing apparatus 300 is not limited to the structure that replaces the medical image processing apparatus 100 of the first embodiment described above. For example, the medical image processing apparatus 300 may also be a structure that replaces the medical image processing apparatus 200 of the second embodiment. In this case, the range extraction unit 304 of the medical image processing apparatus 300 obtains information about the range of the treatment beam B from the CT image whose orientation has been corrected by the patient orientation correction unit 203, extracts the range range, and the confirmation image generation unit 305 generates a confirmation image showing the priority positioning area output by the range extraction unit 304 within the CT image whose orientation has been corrected by the patient orientation correction unit 203.

[0172] As explained above, the medical image processing device 300 may also include a range extraction unit 304 that obtains information about the range of radiation r irradiated during radiotherapy from a first image (a three-dimensional image (e.g., a CT image)) and extracts a predetermined range within the first image that includes the obtained range. The positioning region determination unit 302 determines a second positioning region (preferred positioning region) similar to the effective region Ea contained in the first image within the predetermined range that includes the range.

[0173] Alternatively, as described above, the medical image processing apparatus 300 may also include a confirmation image generation unit 305 that generates a confirmation image that overlaps with the range of the priority positioning area in the first image.

[0174] As explained above, in the medical image processing apparatus of each embodiment, by means of the structure of the comparison unit and the positioning region determination unit, and by referring to comparison images collected in a comparison image database, the positioning region used for patient alignment is determined for the three-dimensional stereoscopic image. Therefore, in a medical apparatus including the medical image processing apparatus of each embodiment, by comparing the three-dimensional stereoscopic image with the X-ray fluoroscopic image (PI) based on the positioning region output by the medical image processing apparatus, the amount of movement required to move the treatment table to the preferred position for radiotherapy can be determined. Furthermore, in a treatment system equipped with a medical apparatus including the medical image processing apparatus of each embodiment, patient positioning can be performed with high precision during radiotherapy.

[0175] Furthermore, in the various embodiments described above, the case where the comparison images (segmented images and effective region images) collected in the comparison image database are three-dimensional images has been explained. In this case, the effective region shown in the effective region image is, as described above, for example, the region of interest designated by the radiotherapy practitioner (doctor, etc.) for three-dimensional stereoscopic images in past radiotherapy treatments. However, the treatment system may also have a structure in which the radiotherapy practitioner (doctor, etc.) designates the region of interest for DRR images. In this case, the comparison image becomes a two-dimensional image. Moreover, the effective region shown in the effective region image also becomes a two-dimensional region. However, even when the designated region of interest is a two-dimensional region, if the imaging conditions of the image that forms the basis of the DRR image are known, such as the imaging direction when the imaging device captures the image, a three-dimensional effective region can be constructed based on the two-dimensional region of interest and shown in the effective region image. Thus, the medical image processing apparatus of the various embodiments described above can determine the positioning region in the same way as the various embodiments described above, and determine the amount of movement required to move the treatment table to the preferred position for performing radiotherapy. Furthermore, by increasing the viewpoint of the DRR image—in other words, by increasing the shooting direction of the image used to capture the basis of the DRR image—and by increasing the number of DRR images, the accuracy is improved when constructing a three-dimensional effective region based on the two-dimensional region of interest. Therefore, it is possible to group multiple effective region images showing a two-dimensional effective region for a three-dimensional segmented image to form comparison images and collect them in a comparison image database. In other words, the comparison image database can collect not only segmented images grouped with three-dimensional segmented images and three-dimensional effective region images as described in the various embodiments above, but also segmented images grouped with three-dimensional segmented images and two-dimensional effective region images.

[0176] The medical image processing program used in the medical image processing apparatus described in the above embodiments is a medical image processing program that enables a computer to function as a medical image processing apparatus. The medical image processing apparatus includes: a comparison unit that compares a first image obtained by photographing a patient with a comparison image, the comparison image being an image used in past radiotherapy and designated with an effective area for alignment in radiotherapy; and a positioning area determination unit that determines a positioning area similar to the effective area contained in the first image based on the comparison result of the comparison unit.

[0177] According to at least one embodiment described above, by having a comparison unit (101) and a positioning area determination unit (102), the positioning of the patient (P) can be performed with high precision. The comparison unit (101) compares a three-dimensional stereoscopic image (CT image) obtained by taking a picture of the patient (P) with a comparison image (Ci). The comparison image (Ci) is a three-dimensional stereoscopic image (CT image) used in past radiotherapy, which is designated with an effective area (Ea) used for alignment in radiotherapy. The positioning area determination unit (102) determines a positioning area similar to the effective area (Ea) contained in the three-dimensional stereoscopic image (CT image) based on the comparison result of the comparison unit (101).

[0178] Several embodiments of the present invention have been described, but these embodiments are merely illustrative and not intended to limit the scope of the invention. These embodiments can be implemented in a wide variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope or spirit of the invention, as well as in the scope of the invention as described in the claims and its equivalents.

Claims

1. A medical image processing device, comprising: The comparison unit compares a first image obtained from photographing the patient with a comparison image, which is an image used in past radiotherapy and is designated with the effective area utilized for alignment in the radiotherapy; and The positioning region determination unit determines a positioning region similar to the effective region contained in the first image based on the comparison result of the comparison unit. The comparison images comprise a plurality of images collected during the previous radiotherapy, and specify a portion of a segmented image obtained by dividing a fluoroscopic image used in the previous radiotherapy into a predetermined size as the effective region. The positioning region determination unit extracts regions in the first image that are similar to the effective region from the multiple comparison images, and combines the regions extracted from the multiple comparison images to determine the positioning region.

2. The medical image processing device according to claim 1, The medical image processing device further includes a patient orientation correction unit, which corrects the orientation of the first image in such a way that the orientation of the patient captured in the first image matches the orientation of the patient shown in the comparison image. The comparison unit compares the first image, whose orientation has been corrected by the patient orientation correction unit, with the comparison image.

3. The medical image processing device according to claim 1, Multiple comparative images were prepared, and each comparative image was integrated into multiple image groups according to each treatment site treated in the previous radiation therapy. The comparison unit selects a group of comparison images to be compared with the first image based on the patient's treatment site.

4. The medical image processing device according to claim 1, The medical image processing device further includes a range extraction unit, which obtains information about the range of the radiation irradiated during the radiotherapy based on the first image, and extracts a predetermined range within the first image that includes the obtained range. The positioning area determination unit determines a second positioning area similar to the effective area contained in the first image within a specified range including the range.

5. The medical image processing device according to claim 4, The medical image processing device further includes a confirmation image generation unit that generates a confirmation image of the range in the first image that emphasizes and overlaps the second positioning region.

6. The medical image processing device according to claim 1, The first image is a digitally reconstructed radiographic image, i.e., a DRR image.

7. A storage medium storing a medical image processing program for enabling a computer to function as a medical image processing device, the medical image processing device comprising: The comparison unit compares a first image obtained from photographing the patient with a comparison image, which is an image used in past radiotherapy and is designated with the effective area utilized for alignment in the radiotherapy; and The positioning region determination unit determines a positioning region similar to the effective region contained in the first image based on the comparison result of the comparison unit. The comparison images comprise a plurality of images collected during the previous radiotherapy, and specify a portion of a segmented image obtained by dividing a fluoroscopic image used in the previous radiotherapy into a predetermined size as the effective region. The positioning region determination unit extracts regions in the first image that are similar to the effective region from the multiple comparison images, and combines the regions extracted from the multiple comparison images to determine the positioning region.

8. A medical device comprising: The medical image processing apparatus according to any one of claims 1 to 6; The first image acquisition unit acquires the first image; The second image acquisition unit acquires a second image corresponding to the radiation that irradiated the patient at a time different from the time at which the first image was captured, from an imaging device that detects the irradiated radiation by a detector and images it. The positioning unit uses the first image and the second image to determine the patient's position during radiotherapy based on the positioning area.

9. The medical device according to claim 8, The medical device further includes a display control unit that enables the display device to display an image superimposed on the first image, showing the positioning area.

10. A treatment system comprising: The medical device as described in claim 8 or 9; The irradiation unit irradiates a therapeutic beam onto the treatment area of ​​the patient. The examination table control unit controls the amount of movement of the treatment table, on which the patient is fixed, in a manner that aligns with the position determined by the positioning unit.

Images