Medical image management system, medical image alignment method, and medical image alignment program

Abstract

The challenge is to reduce the adverse effects of the head restraint when aligning medical images that include the head restraint. [Solution] When aligning image A, which is a FLAIR image, with image B, which is a CT image showing a head restraint, first, the head restraint shown in image B is removed. Then, by performing 3D registration analysis on image B' and image A after this removal process, the same area as a certain part in image A' is displayed in image B''. For example, the positions of the cross-shaped cursors in image A' and image B'' indicate the same area.

Description

Technical Field

[0001] The present invention relates to a medical image management system, a medical image alignment method, and a medical image alignment program that can reduce the adverse effects of a head fixation table when aligning the position of a medical image in which the head fixation table is reflected.

Background Art

[0002] In recent years, medical digital image generation technologies using modalities such as MRI devices (Magnetic Resonance Imaging) and CT devices (Computed Tomography) have become widespread. Medical digital images (hereinafter referred to as "medical images") generated by these medical digital image generation technologies are used, for example, for reading by a doctor in charge of reading films (hereinafter referred to as a "radiologist") or for diagnosis by a doctor in charge of diagnosing a patient (hereinafter referred to as an "attending doctor").

[0003] Here, "reading" is image diagnosis based on a medical image. In order to perform this image diagnosis, it is necessary to align the position of the patient's body reflected in the medical images taken by each modality. The reason is that identifying the same part of the patient's body in different medical images is a prerequisite for performing image diagnosis.

[0004] For this reason, for example, in Patent Document 1, in order to perform alignment, the medical images are superimposed, and in addition to candidate points suitable for the superimposition, regions inappropriate for the superimposition are registered in a database in advance, and feature points within the region inappropriate for the superimposition mapped onto the images to be superimposed are excluded, and accurate superimposition is performed by associating candidate points suitable for the superimposition with the feature points.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

[0006] However, medical images come in various types depending on the modality and imaging method. Specifically, MRI machines produce types such as T1 (T1-weighted images), T2 (T2-weighted images), FLAIR (Fluid Attenuated Inversion Recovery), DWI (Diffusion-weighted imaging), and MRA (vascular images). There are also CT images produced by CT machines. Therefore, when performing medical image alignment using the above conventional techniques, it becomes necessary for the radiologist to make the judgment to align these multiple different types of medical images, which is inefficient.

[0007] Furthermore, while 3D registration analysis can be used to align different types of medical images, CT images of the head taken with a CT scanner may include the head restraint table. When aligning multiple medical images, including CT images that show this head restraint table, there is a problem in that the accuracy of the alignment decreases.

[0008] The present invention has been made to solve the problems (issues) of the above-mentioned prior art, and aims to provide a medical image management system, a medical image alignment method, and a medical image alignment program that can reduce the adverse effects of a head restraint when performing alignment of medical images that show the head restraint. [Means for solving the problem]

[0009] To solve the above problems, the present invention provides a medical image management system comprising: a medical image captured by a medical image acquisition device; a server device for storing the medical image; an image interpretation device for displaying the medical image; and an image processing unit for performing three-dimensional alignment between a plurality of the medical images, wherein the image processing unit comprises: an acquisition means for acquiring the medical image; a removal processing means for removing a head restraint visible in the medical image; and an analysis means for performing three-dimensional alignment on the medical image after removal processing by the removal processing means when a predetermined analysis instruction is received, and the removal processing means is Multiple images that make up a 3D image The area of ​​the same object included in a medical image In each of the aforementioned medical images Each is calculated, and the calculated area By integrating the aforementioned multiple medical images The process of calculating the volume of the aforementioned object The medical images shown above Perform this for each object. calculated The object with the largest volume Subject to inspection It was determined to be the head, Objects other than those identified as the head are removed from each of the multiple medical images. The method is characterized by removing the head restraint.

[0010] Furthermore, the present invention is characterized in that, in the above invention, the removal processing means is performed on CT images captured by a computed tomography scanner.

[0011] Furthermore, the present invention is characterized in that, in the above invention, the removal processing means is a UTE-MRI image captured by a nuclear magnetic resonance imaging apparatus.

[0013] Furthermore, the present invention is characterized in that, in the above invention, the image processing unit is installed in the image interpretation device or the server device, and the results of the 3D alignment analysis performed by the image processing unit are displayed on the image interpretation device.

[0014] Furthermore, the present invention relates to a medical image alignment method in a medical image management system having a medical image captured by a medical image acquisition device, a server device for storing the medical image, a reading device for displaying the medical image, and an image processing unit for performing three-dimensional alignment between a plurality of the medical images, the method comprising: an acquisition step for acquiring the medical image; a removal step for removing a head restraint visible in the medical image; and an analysis step, when a predetermined analysis instruction is received, for performing the three-dimensional alignment on the medical image after the removal step, wherein the removal step is Multiple images that make up a 3D image The area of ​​the same object included in a medical image In each of the aforementioned medical images Each is calculated, and the calculated area By integrating the aforementioned multiple medical images The process of calculating the volume of the aforementioned object The medical images shown above Perform this for each object. calculated The object with the largest volume Subject to inspection It was determined to be the head, Objects other than those identified as the head are removed from each of the multiple medical images. The method is characterized by removing the head restraint.

[0015] Furthermore, the present invention relates to a medical image alignment program executed by an image processing unit that performs three-dimensional alignment between a plurality of medical images, comprising: an acquisition procedure for acquiring the medical images; a removal procedure for removing a head restraint visible in the medical images; and an analysis procedure, when a predetermined analysis instruction is received, for performing three-dimensional alignment on the medical images after the removal procedure, wherein the removal procedure is: Multiple images that make up a 3D image The area of ​​the same object included in a medical image In each of the aforementioned medical images Each is calculated, and the calculated area By integrating the aforementioned multiple medical images The process of calculating the volume of the aforementioned object The medical images shown above Perform this for each object. calculated The object with the largest volume Subject to inspection It was determined to be the head, Objects other than those identified as the head are removed from each of the multiple medical images. The method is characterized by having a computer perform a process to remove the head restraint. [Effects of the Invention]

[0016] According to the present invention, when aligning a medical image in which a head fixing table is reflected, it is possible to reduce the adverse influence caused by the head fixing table.

Brief Description of the Drawings

[0017] [Figure 1] FIG. 1 is an explanatory diagram of the outline of a medical image management system. [Figure 2] FIG. 2 is a diagram showing the system configuration of a medical image management system. [Figure 3] FIG. 3 is a functional block diagram showing the configuration of the management server shown in FIG. 2. [Figure 4] FIG. 4 is a diagram showing an example of medical image data shown in FIG. 3. [Figure 5] FIG. 5 is a functional block diagram showing the configuration of the reading center server shown in FIG. 2. [Figure 6] FIG. 6 is a diagram showing an example of the original image data, the removed image data, and the aligned image data shown in FIG. 5. [Figure 7] FIG. 7 is a diagram showing an example of a medical image related to the removal of a head fixing table. [Figure 8] FIG. 8 is a flowchart showing a processing procedure related to the alignment of medical images. [Figure 9] FIG. 9 is a diagram showing an example of the hardware configuration related to the reading center server. [Figure 10] FIG. 10 is a diagram showing an example of a UTE-MRI image in which a head fixing table appears.

Embodiments for Carrying Out the Invention

[0018] Hereinafter, embodiments of a medical image management system, a medical image alignment method, and a medical image alignment program according to the present embodiment will be described in detail based on the drawings.

[0019] <Outline of Medical Image Management System> First, let's explain the overview of the medical image management system. Figure 1 is an explanatory diagram of the overview of the medical image management system. In the medical image management system, medical images acquired by a certain modality are used to align multiple medical images with each other.

[0020] As shown in Figure 1, when aligning Image A, which is a FLAIR image, with Image B, which is a CT image showing a head restraint, the head restraint shown in Image B is first removed. Then, 3D registration analysis is performed on Image B' and Image A, after this removal process.

[0021] As a result, the same area in image A' is displayed in image B''. For example, the cross-shaped cursors in image A' and image B'' point to the same area.

[0022] Thus, in the medical image management system according to this embodiment, when performing 3D registration analysis using a CT image that shows a head restraint, the system is configured to remove the head restraint from the CT image before performing the 3D registration analysis. This reduces the adverse effects of the head restraint when aligning CT images that show the head restraint.

[0023] <System Configuration of Medical Image Management System> Next, we will describe the system configuration of the medical image management system. Figure 2 shows the system configuration of the medical image management system.

[0024] As shown in Figure 2, multiple modalities 20 are installed in medical facility G, and each modality 20 is connected to the management server 10 for communication. A reading center server 30 and a reading device 40 are installed in the reading center, and they are connected to each other for communication. A medical terminal 50 is installed in medical facility H where the attending physician works.

[0025] The image interpretation center server 30, the management server 10, and the medical treatment terminal 50 are each connected to the Internet, and via this Internet, the image interpretation center server 30 is able to communicate with the management server 10 and the medical treatment terminal 50.

[0026] Modality 20 is an MRI or CT scanner installed within medical facility G. Once Modality 20 has acquired images of a patient, it adds a DICOM (Digital Imaging and Communications in Medicine) tag to the image, including the examination ID, examination date, examination time, patient ID, modality name, and imaging method, and transmits it to the management server 10 as medical image data.

[0027] The management server 10 is a device that manages medical images captured by the modality 20. When the management server 10 receives medical image data from the modality 20, it stores the received data and transmits it to the image interpretation center server 30.

[0028] The image interpretation center server 30 is installed in the image interpretation center and is a device that processes images for interpretation. When the image interpretation center server 30 receives medical image data from the management server 10, it stores the received data in the original image data.

[0029] Furthermore, if the image interpretation center server 30 receives a removal instruction from the image interpretation device 40, it extracts data corresponding to the examination ID and image UID included in this removal instruction from the original image data. Then, it performs a head restraint removal process on the extracted image data, associates the DICOM tag of the original data with the processed image, stores it in the removed image data, and transmits it to the image interpretation device 40.

[0030] Furthermore, when the image interpretation center server 30 receives an analysis instruction from the image interpretation device 40, it extracts data corresponding to the examination ID and patient ID included in the analysis instruction from the original image data and the removed image data, and uses this as the data to be analyzed. Then, it performs 3D registration analysis on the images corresponding to the image UIDs included in the data to be analyzed, stores the results in the alignment image data, and transmits them to the image interpretation device 40.

[0031] Furthermore, if the image interpretation center server 30 receives a notification instruction from the medical terminal 50, it extracts data corresponding to the examination ID and patient ID included in the notification instruction from the alignment image data and sends it to the medical terminal 50.

[0032] The image interpretation device 40 is installed in the image interpretation center and is a terminal operated by the radiologist. When the image interpretation device 40 receives the examination ID and image UID, it notifies the image interpretation center server 30 of a removal instruction including this examination ID and image UID. When the image interpretation device 40 receives the removed image data from the image interpretation center server 30, it displays the received data.

[0033] Furthermore, if the image interpretation device 40 receives the examination ID and patient ID, it notifies the image interpretation center server 30 of the analysis instructions including the examination ID and patient ID. If the image interpretation device 40 receives alignment image data from the image interpretation center server 30, it displays the received data.

[0034] The medical terminal 50 is installed in medical facility H and is operated by the attending physician. When the medical terminal 50 receives the examination ID and patient ID, it notifies the image interpretation center server 30 of a notification instruction including the examination ID and patient ID. When the medical terminal 50 receives alignment image data from the image interpretation center server 30, it displays the received data.

[0035] <Configuration of Management Server 10> Next, the configuration of the management server 10 shown in Figure 2 will be described. Figure 3 is a functional block diagram showing the configuration of the management server 10 shown in Figure 2. As shown in Figure 3, the management server 10 is connected to an input unit 11 and a display unit 12, and has an external communication unit 13, a communication unit 14, a storage unit 15, and a control unit 16.

[0036] The input unit 11 is an input device such as a keyboard or mouse. The display unit 12 is a display device such as an LCD panel or display device. The external communication unit 13 is an interface unit for data communication with the image interpretation center server 30 via the internet. The communication unit 14 is an interface unit for data communication with the modality 20.

[0037] The storage unit 15 is a storage device such as a hard disk drive or non-volatile memory, and stores medical image data 15a. The medical image data 15a is data indicating a medical image received from modality 20, and includes DICOM tags such as examination ID, examination date, examination time, patient ID, modality name, and imaging method.

[0038] The control unit 16 is a control unit that performs overall control of the management server 10 and includes an image acquisition unit 16a and a notification unit 16b. In practice, these programs are loaded into the CPU (Central Processing Unit) and executed, causing the image acquisition unit 16a and the notification unit 16b to execute the processes corresponding to them.

[0039] The image acquisition unit 16a is a processing unit that acquires medical image data from the modality 20. When the image acquisition unit 16a receives medical image data from the modality 20, it stores the received data in the medical image data 15a.

[0040] The notification unit 16b is a processing unit that transmits medical image data to the image interpretation center server 30. If the medical image data 15a is updated by the image acquisition unit 16a, the notification unit 16b transmits this medical image data 15a to the image interpretation center server 30.

[0041] Next, an example of data stored in the storage unit 15 of the management server 10 shown in Figure 3 will be described. Figure 4 shows an example of medical image data 15a shown in Figure 3.

[0042] The medical image data 15a shown in Figure 4 corresponds to the following conditions: examination ID "KS1234", examination date "2025 / 4 / 1", examination time "10:10", patient ID "KJ5678", modality name "MR", imaging method "FLAIR", and image UID "0123···4567".

[0043] Furthermore, medical image data 15a is associated with the following conditions: examination ID is "KS1234", examination date is "2025 / 4 / 1", examination time is "10:15", patient ID is "KJ5678", modality name is "MR", imaging method is "DWI", and image UID is "0123···4568".

[0044] Furthermore, medical image data 15a is associated with the following conditions: examination ID is "CT4321", examination date is "2025 / 4 / 1", examination time is "10:30", patient ID is "KJ5678", modality name is "CT", imaging method is "-", and image UID is "0123···4569".

[0045] <Configuration of Image Interpretation Center Server 30> Next, the configuration of the image interpretation center server 30 shown in Figure 2 will be explained. Figure 5 is a functional block diagram showing the configuration of the image interpretation center server 30 shown in Figure 2. As shown in Figure 5, the image interpretation center server 30 is connected to an input unit 31 and a display unit 32, and includes an external communication unit 33, a communication unit 34, a storage unit 35, and a control unit 36.

[0046] The input unit 31 is an input device such as a keyboard or mouse. The display unit 32 is a display device such as an LCD panel or display device. The external communication unit 33 is an interface unit for data communication between the management server 10 and the medical treatment terminal 50 via the internet. The communication unit 34 is an interface unit for data communication with the image interpretation device 40.

[0047] The storage unit 35 is a storage device such as a hard disk drive or non-volatile memory, and stores the original image data 35a, the removed image data 35b, and the alignment image data 35c. The original image data 35a is data showing a medical image received from the management server 10. The removed image data 35b is data showing a medical image in which the head restraint has been removed from the medical image in which the head restraint was visible.

[0048] The alignment image data 35c is data indicating a medical image that has undergone alignment processing. The original image data 35a, the removed image data 35b, and the alignment image data 35c all include DICOM tags such as examination ID, examination date, examination time, patient ID, modality name, and imaging method.

[0049] The control unit 36 ​​is a control unit that performs overall control of the image interpretation center server 30, and has an image processing unit 36a and a notification unit 36e. The image processing unit 36a includes an image acquisition unit 36b, an image removal unit 36c, and an analysis unit 36d. In practice, by loading these programs into the CPU and executing them, the image processing unit 36a, which includes the image acquisition unit 36b, the image removal unit 36c, and the analysis unit 36d, and the notification unit 36e will execute processes corresponding to them, respectively.

[0050] The image processing unit 36a is a processing unit that performs image processing on medical images. The image processing unit 36a acquires medical images from the management server 10, performs head rest removal processing on the acquired medical images, and performs 3D registration analysis processing. This image processing unit 36a corresponds to the "image processing unit" described in the claims.

[0051] The image acquisition unit 36b is a processing unit that acquires medical image data from the management server 10. When the image acquisition unit 36b receives medical image data from the management server 10, it stores the received data in the original image data 35a.

[0052] The removal unit 36c is a processing unit that performs the removal of a head restraint from a medical image in which a head restraint is visible. When the removal unit 36c receives a removal instruction from the image interpretation device 40, it extracts data corresponding to the examination ID and image UID included in this removal instruction from the original image data 35a. Then, it performs the head restraint removal process on the extracted image data and stores the processed image associated with the DICOM tag of the original data in the removed image data 35b. The head restraint removal process is performed according to the following procedure.

[0053] Since the images to be removed are a set of multiple images that make up a 3D image, the area of ​​objects that can be identified as the same object (for example, a head) is calculated in each image, and the volume of the object is calculated by summing the areas of the multiple images. This process is performed for each object that appears in the image. The object with the largest calculated volume is identified as the head to be inspected, and the other objects are removed from each image.

[0054] The analysis unit 36d is a processing unit that performs 3D registration analysis. When the analysis unit 36d receives an analysis instruction from the image interpretation device 40, it extracts data corresponding to the examination ID and patient ID included in the analysis instruction from the original image data 35a and the removed image data 35b, and uses this as the data to be analyzed. In this case, if there are data with the same examination time in the extracted data, the data extracted from the original image data 35a is excluded from the data to be analyzed. Then, 3D registration analysis is performed on the image corresponding to the image UID included in the data to be analyzed, and the results are stored in the alignment image data 35c.

[0055] The notification unit 36e is a processing unit that performs the transmission processing of the removed image data 35b and the alignment image data 35c. If the removed image data 35b is updated by the removal unit 36c, the notification unit 36e transmits this removed image data 35b to the image interpretation device 40.

[0056] Furthermore, if the alignment image data 35c is updated by the analysis unit 36d, the notification unit 36e transmits this alignment image data 35c to the image interpretation device 40.

[0057] Furthermore, if the notification unit 36e receives a notification instruction from the medical treatment terminal 50, it extracts data corresponding to the examination ID and patient ID included in the notification instruction from the alignment image data 35c and transmits it to the medical treatment terminal 50.

[0058] Next, an example of data stored in the memory unit 35 of the image interpretation center server 30 shown in Figure 5 will be described. Figure 6 shows an example of the original image data 35a, the removed image data 35b, and the alignment image data 35c shown in Figure 5.

[0059] The original image data 35a shown in Figure 6(a) corresponds to the following conditions: examination ID is "KS1234", examination date is "2025 / 4 / 1", examination time is "10:10", patient ID is "KJ5678", modality name is "MR", imaging method is "FLAIR", and image UID is "0123···4567".

[0060] Furthermore, the original image data 35a is associated with the following conditions: examination ID "KS1234", examination date "2025 / 4 / 1", examination time "10:15", patient ID "KJ5678", modality name "MR", imaging method "DWI", and image UID "0123···4568".

[0061] Furthermore, the original image data 35a is associated with the following conditions: examination ID is "CT4321", examination date is "2025 / 4 / 1", examination time is "10:30", patient ID is "KJ5678", modality name is "CT", imaging method is "-", and image UID is "0123···4569".

[0062] The removed image data 35b shown in Figure 6(b) corresponds to the following conditions: examination ID is "CT4321", examination date is "2025 / 4 / 1", examination time is "10:30", patient ID is "KJ5678", modality name is "CT", imaging method is "-", and image UID is "0123···6543".

[0063] The alignment image data 35c shown in Figure 6(c) corresponds to the following conditions: examination ID is "KS1234", examination date is "2025 / 4 / 1", examination time is "10:15", patient ID is "KJ5678", modality name is "MR", imaging method is "DWI", and image UID is "0123···9876".

[0064] Furthermore, the alignment image data 35c is associated with the following conditions: examination ID is "CT4321", examination date is "2025 / 4 / 1", examination time is "10:30", patient ID is "KJ5678", modality name is "CT", imaging method is "-", and image UID is "0123···9877".

[0065] <An example of a medical image related to the removal of a head restraint> Next, an example of a medical image related to the removal of a head restraint will be described. Figure 7 shows an example of a medical image related to the removal of a head restraint.

[0066] If a head restraint is visible in the medical image, this head restraint is removed from the medical image. Since the images to be removed are a set of multiple images that make up a 3D image, the area of ​​objects that can be identified as the same object (e.g., a head) is calculated in each image, and the volume of the object is calculated by summing the areas of the multiple images. This process is performed for each object that appears in the image. The object with the largest calculated volume is identified as the head being examined, and all other objects are removed from each image.

[0067] For example, the medical image shown in Figure 7(a) includes a head and a head restraint, so it will be removed. Specifically, because the area of ​​the head near the center (the volume of multiple images combined) is large, the U-shaped head restraint visible elsewhere in the image will be removed from the medical image.

[0068] The removal method involves setting the pixel value of the head rest to be equivalent to that of the surrounding pixels. As a result of this removal process, the medical image will show only the head, as shown in Figure 7(b).

[0069] <Processing procedure for medical image alignment> Next, we will explain the processing procedure for medical image alignment. Figure 8 is a flowchart showing the processing procedure for medical image alignment.

[0070] As shown in Figure 8, if the image interpretation center server 30 receives medical image data from the management server 10 (step S101; Yes), it stores the received data in the original image data 35a.

[0071] If a removal instruction is received from the image interpretation device 40 (step S102; Yes), the data corresponding to the examination ID and image UID included in this removal instruction is extracted from the original image data 35a, the head restraint is removed (step S103), and stored in the removed image data 35b.

[0072] If an analysis instruction is received from the image interpretation device 40 (step S104; Yes), data corresponding to the examination ID and patient ID included in this analysis instruction is extracted from the original image data 35a and the removed image data 35b, duplicate data is deleted, and then 3D registration analysis is performed (step S105).

[0073] The results of the 3D registration analysis are notified to the image interpretation device 40 (step S106), and the process is terminated.

[0074] <An example of hardware configuration for the image interpretation center server 30> Next, we will explain the correspondence between the image interpretation center server 30 and the main hardware configuration of the computer. Figure 12 is a diagram showing an example of the hardware configuration related to the image interpretation center server 30.

[0075] Generally, a computer consists of components such as a CPU 81, ROM 82, RAM 83, and non-volatile memory 84, connected by a bus 85. A hard disk drive may be used instead of the non-volatile memory 84. For the sake of clarity, only the basic hardware configuration is shown.

[0076] Here, the ROM 82 or non-volatile memory 84 stores programs necessary for starting the operating system (hereinafter simply referred to as "OS"), and the CPU 81 reads and executes the OS program from the ROM 82 or non-volatile memory 84 when the power is turned on.

[0077] On the other hand, various application programs executed on the OS are stored in non-volatile memory 84, and the CPU 81 executes the application programs using RAM 83 as main memory, thereby executing the processes corresponding to the applications.

[0078] Furthermore, the alignment program for the image interpretation center server 30 according to this embodiment is stored in non-volatile memory 84 or the like, just like other application programs, and the CPU 81 loads and executes this program. In the case of the image interpretation center server 30 according to this embodiment, the alignment program, which includes routines corresponding to the image processing unit 36a, which includes the image acquisition unit 36b, the removal unit 36c, and the analysis unit 36d shown in Figure 5, and the notification unit 36e, is stored in non-volatile memory 84 or the like. When the CPU 81 loads and executes the alignment program, an alignment process corresponding to the image processing unit 36a, which includes the image acquisition unit 36b, the removal unit 36c, and the analysis unit 36d, and the notification unit 36e is generated.

[0079] As described above, in the medical image management system according to this embodiment, when performing 3D registration analysis using a CT image that shows a head restraint, the system is configured to remove the head restraint shown in the CT image before performing the 3D registration analysis. This reduces the adverse effects of the head restraint when aligning CT images that show the head restraint.

[0080] In the above embodiment, the case of aligning image A, which is a FLAIR image, with image B, which is a CT image showing a head restraint, was described. However, the present invention is not limited to this, and can also be applied to aligning CT images that show head restraints. In registration analysis between images that show head restraints, the head restraints become corresponding parts, and the analysis is performed to align these positions, which may have an effect. This is because the position of the head restraint differs from examination to examination, so when the head restraint is shown, it is easy for registration misalignment to occur.

[0081] Furthermore, although the above embodiment uses the term "head restraint stand," the term "head restraint stand" is a general term for a jig that restrains the head, and may be a U-shaped object made of a rigid material, or it may be something like a pillow, cushion, or blanket.

[0082] Furthermore, while the above embodiment gives an example of a head restraint visible in a CT image, a head restraint may also be visible in "UTE (ultrashort echo time)-MRI images" acquired with a very short echo time. Therefore, the presence of a head restraint in the MRI image can cause registration misalignment. As shown in Figure 10, when performing registration analysis with a head restraint visible in the UTE-MRI image, it becomes difficult to determine where the head ends and other parts of the image begin, making misalignment more likely.

[0083] Furthermore, although the above embodiment describes a case in which the image processing unit 36a, including the image acquisition unit 36b, the removal unit 36c, and the analysis unit 36d, is provided in the image interpretation center server 30, the present invention is not limited thereto. Such an image processing unit 36a can be provided in the image interpretation device 40, or it can be provided in the management server 10.

[0084] Furthermore, the configurations illustrated in the above embodiments are functionally schematic and do not necessarily have to be physically represented as shown. In other words, the form of distribution and integration of each device is not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions. [Industrial applicability]

[0085] The medical image management system, medical image alignment method, and medical image alignment program according to the present invention are suitable for reducing the adverse effects of a head restraint when performing alignment of medical images that include a head restraint. [Explanation of symbols]

[0086] 10 Management Server 11 Input section 12 Display section 13 External Communications Department 14 Communications Department 15 Storage section 15a Medical image data 16 Control Unit 16a Image acquisition unit 16b Notification section 20 Modalities 30 Image Interpretation Center Server 31 Input section 32 Display section 33 External Communications Department 34 Communications Department 35 Storage section 35a Original image data 35b Removed image data 35c Alignment Image Data 36 Control Unit 36a Image Processing Unit 36b Image acquisition unit 36c removal part 36d analysis department 36e Notification section 40 Image interpretation device 50 medical terminals 81 CPU 82 ROM 83 RAM 84 Non-volatile memory 85 Bus

Claims

1. A medical image management system comprising: medical images captured by a medical image acquisition device; a server device for storing the medical images; an image interpretation device for displaying the medical images; and an image processing unit for performing three-dimensional alignment between a plurality of the medical images, The aforementioned image processing unit, The acquisition means for acquiring the aforementioned medical image, A removal processing means for removing the head restraint visible in the aforementioned medical image, When a predetermined analysis instruction is received, the analysis means performs the three-dimensional alignment on the medical image after the removal process by the removal processing means. Equipped with, The aforementioned removal processing means is The process involves calculating the area of ​​the same object in each of the multiple medical images that form a 3D image, summing the calculated areas across the multiple medical images to calculate the volume of the object, determining that the object with the largest calculated volume is the head of the subject being examined, and removing all objects other than the head from each of the multiple medical images to remove the head support. A medical image management system characterized by the following:

2. The aforementioned removal processing means is The medical image management system according to claim 1, characterized in that it is performed on CT images acquired by a computed tomography scanner.

3. The aforementioned removal processing means is The medical image management system according to claim 1, characterized in that the images are UTE-MRI images acquired by a nuclear magnetic resonance imaging apparatus.

4. The image processing unit is installed in the image interpretation device or the server device. A medical image management system according to any one of claims 1 to 3, characterized in that the results of the three-dimensional alignment analysis performed by the image processing unit are displayed on the image interpretation device.

5. A medical image alignment method in a medical image management system comprising a medical image captured by a medical image acquisition device, a server device for storing the medical images, a reading device for displaying the medical images, and an image processing unit for performing three-dimensional alignment between a plurality of the medical images, wherein The acquisition process for acquiring the aforementioned medical image, A removal process for removing the head restraint visible in the medical image, When a predetermined analysis instruction is received, an analysis step is performed to perform the three-dimensional alignment on the medical image after the removal process by the removal process. Includes, The aforementioned removal process is: The process involves calculating the area of ​​the same object in each of the multiple medical images that form a 3D image, summing the calculated areas across the multiple medical images to calculate the volume of the object, determining that the object with the largest calculated volume is the head of the subject being examined, and removing all objects other than the head from each of the multiple medical images to remove the head support. A medical image alignment method characterized by the following:

6. A medical image alignment program is executed by an image processing unit that performs three-dimensional alignment between a plurality of medical images, comprising: a medical image captured by a medical image acquisition device; a server device that stores the medical image; an image interpretation device that displays the medical image; and a medical image alignment program that performs three-dimensional alignment between a plurality of the medical images. The acquisition procedure for obtaining the aforementioned medical image, A removal procedure for removing the head restraint visible in the aforementioned medical image, When a predetermined analysis instruction is received, an analysis procedure is performed to perform the three-dimensional alignment on the medical image after the removal process by the removal process procedure. Includes, The aforementioned removal procedure is: The process involves calculating the area of ​​the same object in each of the multiple medical images that form a 3D image, summing the calculated areas across the multiple medical images to calculate the volume of the object, determining that the object with the largest calculated volume is the head of the subject being examined, and removing all objects other than the head from each of the multiple medical images to remove the head support. A medical image alignment program characterized by having a computer perform the processing.

Images