Medical image output device, program, medical image output method and medical image output system
Patent Information
- Application Number
- JP2023074433
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-04-28
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2043-04-28
AI Technical Summary
【0039】 本発明によれば、自動的に画像の調整を行うことで撮影者の業務負荷を低減させることができる。
Smart Images

Figure 2024158858000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a medical image output device, a program, a medical image output method, and a medical image output system. [Background technology]
[0002] When taking X-rays, radiologists adjust the images (rotate, crop, center) to make them easier for doctors to interpret. This adjustment operation requires that the image be aligned according to the hospital's agreement or the direction specified by each doctor, but since adjustments must be made for each image, the burden on radiologists is extremely high. In addition, it is necessary to pay attention to the patient's pain and waiting time during imaging, and there are limitations to simply adjusting the position of the radiation field and panel.
[0003] In Patent Document 1, the image cut-out position can be selected from a fixed pattern. However, Patent Document 1 is based on the premise that each subject is photographed in a similar position, and is not necessarily suitable for various conditions such as subject position or inclination that change with each photograph.
[0004] Patent Document 2 also makes it possible to align the cut-out position with that of previous shots, but it also does not deal with subject position or inclination, etc., which change with each shot.
[0005] On the other hand, it was found that there is a need to fine-tune the position and angle of the subject in the image according to the rules of each facility.Currently, radiologists recognize and position the object in the image, and then adjust the image (rotate, crop, center). [Prior art documents] [Patent documents]
[0006] [Patent Document 1] JP 2012-55491 A [Patent Document 2] JP 2015-150072 A Summary of the Invention [Problem to be solved by the invention]
[0007] However, the techniques described in Patent Documents 1 and 2 trim an image without recognizing the object depicted in the image, and are unable to accommodate appropriate cropping positions and rotation angles, etc., that differ for each shot. In addition, the most appropriate standards must be met depending on the facility (reader), but unless the object shown in the image is recognized, no action can be taken, and so the only way to respond is by a human.
[0008] It is possible to automatically rotate or crop an image, but conventionally, humans have had to recognize and position the object in the image before deciding how to rotate or crop it. To rotate an image automatically, it is necessary to identify the part, position, and shape, such as which part is the elbow and what its shape is. In other words, even if you try to rotate or crop an image automatically, it is not possible to know how to rotate or crop it.
[0009] SUMMARY OF THE PRESENT EMBODIMENT An object of the present invention is to reduce the workload of a photographer by automatically adjusting an image. [Means for solving the problem]
[0010] Incidentally, in recent years, image recognition technology has been developing, and it is now possible to automatically recognize objects in an image and automatically identify target regions, for example. The inventors of the present invention realized that if the object is automatically recognized, the image can be automatically adjusted, and thus arrived at the present invention.
[0011] The invention described in claim 1 is a medical image output device having a recognition unit that automatically recognizes structures of a subject in a medical image, an adjustment unit that automatically adjusts the medical image based on the recognized structures, and an output unit that outputs the adjusted medical image.
[0012] The invention described in claim 2 is a medical image output device described in claim 1, wherein the automatic adjustment of the medical image includes at least one of adjustment of the rotation angle of the medical image, adjustment of the position of the rotation center of the medical image, adjustment of the cropping of the medical image, and adjustment of the position of the center of the cropping of the medical image.
[0013] According to a third aspect of the present invention, in the medical image output device according to the first aspect, the automatic adjustment of the medical image is adjustment of a rotation angle of the medical image or adjustment of a position of a rotation center of the medical image.
[0014] The invention described in claim 4 is a medical image output device described in any one of claims 1 to 3, wherein the adjustment unit determines an automatic adjustment standard, which is a standard for automatically adjusting the medical image, based on the recognized structure or shooting order information related to the medical image.
[0015] The invention described in claim 5 is a medical image output device described in claim 4, wherein the automatic adjustment criteria for the medical image include at least one of a criterion for adjusting the rotation angle of the medical image, a criterion for adjusting the position of the rotation center of the medical image, a criterion for adjusting the cropping of the medical image, and a criterion for adjusting the position of the center of cropping of the medical image.
[0016] The invention described in claim 6 is a medical image output device described in claim 4, wherein the automatic adjustment standard for the medical image is a standard for adjusting the rotation angle of the medical image, or a standard for adjusting the position of the rotation center of the medical image.
[0017] According to a seventh aspect of the present invention, in the medical image output device according to the fourth aspect, the automatic adjustment reference is information indicating a shape of a region to be photographed of an imaging subject or an anatomical region of the region to be photographed.
[0018] The invention described in claim 8 is a medical image output device described in any one of claims 1 to 3, further comprising a storage unit that stores, for each shooting part of a subject, a correspondence between the shooting part of the subject and whether or not to automatically adjust the medical image, and the adjustment unit determines whether or not to perform the automatic adjustment based on the shooting part of the subject, which is the recognized structure, or shooting order information related to the medical image.
[0019] The invention described in claim 9 is a medical image output device described in any one of claims 1 to 3, wherein the automatic adjustment has a plurality of items, and a memory unit is provided which stores, for each shooting part of the subject, a correspondence between the shooting part of the subject and whether or not to perform automatic adjustment of each of the plurality of items, and the adjustment unit determines whether or not to perform automatic adjustment of each of the items based on the shooting part of the subject, which is the recognized structure, or shooting order information related to the medical image.
[0020] The invention described in claim 10 is a medical image output device described in any one of claims 1 to 3, further comprising a memory unit that stores, for each shooting part of a subject, an automatic adjustment standard, which is a standard for automatically adjusting the medical image, in association with the shooting part of the subject, and the adjustment unit determines the automatic adjustment standard based on the shooting part of the subject, which is the recognized structure, or shooting order information related to the medical image.
[0021] The invention described in claim 11 relates to a medical image output device described in any one of claims 1 to 3, wherein the automatic adjustment criteria, which are criteria for automatically adjusting the medical image, have a plurality of items, and the device is provided with a memory unit that stores, for each shooting part of the subject, the shooting part of the subject in correspondence with the automatic adjustment criteria for each of the plurality of items, and the adjustment unit determines the automatic adjustment criteria for each of the items based on the shooting part of the subject, which is the recognized structure, or shooting order information related to the medical image.
[0022] The invention described in claim 12 is the medical image output device described in any one of claims 1 to 3, wherein the medical image is a radiation image.
[0023] The invention described in claim 13 is the medical image output device described in any one of claims 1 to 3, wherein the recognition unit is a trained model obtained by machine learning.
[0024] The invention described in claim 14 is a program for causing a computer to function as a recognition unit that automatically recognizes structures of a subject in a medical image, an adjustment unit that automatically adjusts the medical image based on the recognized structures, and an output unit that outputs the adjusted medical image.
[0025] The invention described in claim 15 is the program described in claim 14, wherein the automatic adjustment of the medical image includes at least one of adjustment of the rotation angle of the medical image, adjustment of the position of the rotation center of the medical image, adjustment of the cropping of the medical image, and adjustment of the position of the center of the cropping of the medical image.
[0026] In accordance with a sixteenth aspect of the present invention, in the program according to the fourteenth aspect, the automatic adjustment of the medical image is adjustment of a rotation angle of the medical image or adjustment of a position of a rotation center of the medical image.
[0027] The invention described in claim 17 is a program described in any one of claims 14 to 16, wherein the adjustment unit determines an automatic adjustment standard, which is a standard for automatically adjusting the medical image, based on the recognized structure or shooting order information related to the medical image.
[0028] The invention described in claim 18 is the program described in claim 17, wherein the automatic adjustment criteria for the medical image include at least one of a criterion for adjusting the rotation angle of the medical image, a criterion for adjusting the position of the rotation center of the medical image, a criterion for adjusting the cropping of the medical image, and a criterion for adjusting the position of the center of cropping of the medical image.
[0029] The invention described in claim 19 is the program described in claim 17, wherein the automatic adjustment criterion for the medical image is a criterion for adjusting the rotation angle of the medical image, or a criterion for adjusting the position of the rotation center of the medical image.
[0030] In accordance with a twentieth aspect of the present invention, in the program according to the seventeenth aspect, the automatic adjustment reference is information indicating a shape of a region to be photographed of an imaging subject or an anatomical region of the region to be photographed.
[0031] The invention described in claim 21 is the program described in any one of claims 14 to 16, which causes the computer to function as a memory unit that stores, for each imaging part of the subject, a correspondence between the imaging part of the subject and whether or not to automatically adjust the medical image, and the adjustment unit determines whether or not to perform the automatic adjustment based on the imaging part of the subject, which is the recognized structure, or imaging order information related to the medical image.
[0032] The invention described in claim 22 is the program described in any one of claims 14 to 16, wherein the automatic adjustment has a plurality of items, and the computer is caused to function as a storage unit that stores, for each part of a part of a subject, a correspondence between the part of the subject and whether or not to perform automatic adjustment of each of the plurality of items, and the adjustment unit determines whether or not to perform automatic adjustment of each of the items based on the part of the subject that is the recognized structure, or imaging order information related to the medical image.
[0033] The invention described in claim 23 is the program described in any one of claims 14 to 16, which causes the computer to function as a storage unit that stores, for each shooting part of a subject, an automatic adjustment standard, which is a standard for automatically adjusting the medical image, in association with the shooting part of the subject, and the adjustment unit determines the automatic adjustment standard based on the shooting part of the subject, which is the recognized structure, or imaging order information related to the medical image.
[0034] The invention described in claim 24 provides the program described in any one of claims 14 to 16, wherein the automatic adjustment criteria, which are criteria for automatically adjusting the medical image, have a plurality of items, and the computer is caused to function as a memory unit that stores, for each shooting part of the subject, the shooting part of the subject in association with the automatic adjustment criteria for each of the plurality of items, and the adjustment unit determines the automatic adjustment criteria for each of the items based on the shooting part of the subject, which is the recognized structure, or shooting order information related to the medical image.
[0035] The invention described in claim 25 is the program described in any one of claims 14 to 16, wherein the medical image is a radiation image.
[0036] The invention described in claim 26 is the program described in any one of claims 14 to 16, wherein the recognition unit is a trained model obtained by machine learning.
[0037] The invention described in claim 27 is a medical image output method including a recognition step of automatically recognizing a structure of a subject in a medical image, an adjustment step of automatically adjusting the medical image based on the recognized structure, and an output step of outputting the adjusted medical image.
[0038] The invention described in claim 28 is a medical image output system having a recognition unit that automatically recognizes structures of a subject in a medical image, an adjustment unit that automatically adjusts the medical image based on the recognized structures, and an output unit that outputs the adjusted medical image. Effect of the Invention
[0039] According to the present invention, the workload of the photographer can be reduced by automatically adjusting the image. [Brief description of the drawings]
[0040] [Figure 1] 1 is a system configuration diagram of a radiation imaging system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a block diagram showing a functional configuration of a console. [Diagram 3] FIG. 11 is a diagram illustrating an example of a data configuration of a setting table. [Figure 4] FIG. 13 is a diagram for explaining a method of describing an angle on an image. [Diagram 5] (a) is an example of a side image of an elbow joint, (b) is a diagram showing an automatic rotation reference (pattern A1), and (c) is a diagram showing an automatic rotation reference (pattern A2). [Figure 6] (a) is an example of a frontal chest image, (b) is a diagram showing an automatic trimming reference (pattern B1), and (c) is a diagram showing an automatic trimming reference (pattern B2). [Figure 7] (a) is an example of a lateral image of a knee joint, (b) is a diagram showing an automatic rotation reference (pattern C1), and (c) is a diagram showing an automatic rotation reference (pattern C2). [Figure 8] FIG. 11 is a diagram for explaining automatic adjustment of an output size. [Figure 9] 5 is a flowchart showing a shooting control process executed in the console. [Figure 10] 13 is an example of an examination screen. [Figure 11] 13 is a flowchart showing an automatic adjustment process. [Figure 12] 1 is an example of a lateral image of an elbow joint. [Figure 13] 13 is an example of an image after automatic rotation of a lateral image of an elbow joint. [Figure 14] 13 is an example of an image after a trimming frame is moved relative to a rotated image. [Figure 15] 13 is an example of a preview display screen including an automatically adjusted lateral image of an elbow joint. [Figure 16] 13 is an example of a preview display screen including an automatically adjusted frontal chest image. [Figure 17] 13 is an example of an examination screen including a lateral image of an elbow joint that has been automatically adjusted based on pattern A1. [Figure 18]13 is an example of an examination screen including a lateral image of an elbow joint automatically adjusted based on pattern A2. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0041] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. However, the technical scope of the present invention is not limited to the following embodiment and illustrated examples.
[0042] <Radiation imaging system configuration> First, a schematic configuration of a radiation imaging system (hereinafter, referred to as a system 100) as a medical image output system according to this embodiment will be described. FIG. 1 is a system configuration diagram of a system 100. 1, the system 100 includes a radiographic image capturing device (hereinafter, referred to as the capturing device 1), a console 2, a radiation generating device (hereinafter, referred to as the generating device 3), and an image management device 4. The devices 1 to 4 are capable of communicating with each other via a communication network N such as a LAN (Local Area Network), a WAN (Wide Area Network), or the Internet.
[0043] The system 100 may be installed in an imaging room, or may be configured to be movable (for example, a mobile cart). Furthermore, the system 100 may be capable of communicating with a hospital information system (HIS), a radiology information system (RIS), and the like, which are not shown.
[0044] The generating device 3 includes a generator 31 , an irradiation instruction switch 32 , and a radiation source 33 . Based on the operation of an irradiation instruction switch 32, a generator 31 applies a voltage according to preset imaging conditions to a radiation source 33 (a tube). When a voltage is applied from the generator 31, the radiation source 33 generates radiation R (for example, X-rays) with a dose corresponding to the applied voltage.
[0045] The generating device 3 generates radiation R in a manner that corresponds to the form of a radiation image to be generated. The form of a radiation image includes a still image, a dynamic image having a plurality of frames, and the like. In the case of a still image, radiation R is irradiated only once each time the irradiation instruction switch 32 is pressed. In the case of dynamic images, each time the irradiation instruction switch 32 is pressed, the irradiation of pulsed radiation R is repeated multiple times per predetermined time (for example, 15 times per second), or the irradiation of radiation R is continued for a predetermined time.
[0046] The imaging device 1 generates digital data of a radiation image showing an imaging region of a subject. The imaging device 1 is a portable FPD (Flat Panel Detector). Specifically, the imaging device 1 includes a sensor board, a scanning unit, a readout unit, a control unit, a communication unit, and the like, which are not shown in the figure. The sensor board has imaging elements that generate charges according to the dose of radiation R when exposed to the radiation R, and switch elements that store and release the charges, which are arranged two-dimensionally (in a matrix). The scanning unit switches each switch element ON / OFF. The readout unit reads out the amount of charge released from each pixel as a signal value. The control unit controls each unit, and generates a radiation image from the multiple signal values read out by the readout unit. The communication unit transmits radiation image data and various signals to other devices (the console 2, the generator 3, the image management device 4, etc.) and receives various information and various signals from other devices.
[0047] The imaging device 1 accumulates and releases electric charges and reads out signal values in synchronization with the timing of irradiation of radiation R from the generating device 3. In this way, the imaging device 1 generates image data of a still image (hereinafter, still image data) or image data of a dynamic image (hereinafter, dynamic image data). When still image data is to be generated, a radiation image is generated only once for each depression of the irradiation instruction switch 32. When dynamic image data is generated, the generation of frames constituting a dynamic image is repeated multiple times per predetermined time (for example, 15 times per second) for each depression of the irradiation instruction switch 32.
[0048] The image capturing device 1 may be integrated with the generating device 3 .
[0049] The console 2 sets various imaging conditions for at least one of the imaging device 1 and the generating device 3. The console 2 is composed of a PC, a dedicated device, and the like. The photographing conditions include, for example, conditions related to the subject S, conditions related to the irradiation of radiation R, and conditions related to image reading by the photographing device 1. The conditions related to the subject S include the photographed part, the photographing direction, the physique, etc. The conditions related to the irradiation of radiation R include the tube voltage, the tube current, the irradiation time, the current-time product (mAs value), etc. The conditions related to image reading by the photographing device 1 include the frame rate, the frame interval, the pixel size, the image size (matrix size), etc.
[0050] The console 2 may automatically set the imaging conditions based on imaging order information acquired from another system (HIS, RIS, etc.) The console 2 may also manually set the imaging conditions based on an operation performed by a user (e.g., an operator such as a radiologist) on the operation unit 25 (see FIG. 2).
[0051] The image manager 4 manages the image data generated by the photographing device 1 . The image management device 4 is a Picture Archiving and Communication System (PACS), an image diagnosis workstation (IWS), or the like.
[0052] <Console detailed configuration> Next, the configuration of the console 2 will be described in detail. In this embodiment, the functions of the medical image output device according to the present invention are installed in the console 2. The medical image output device includes a radiation image display device, an MRI image display device, and an ultrasound image display device. The radiation image display device includes a radiation image capturing device, a console of the radiation image capturing device, and a radiation image management device (PACS).
[0053] FIG. 2 is a block diagram showing the functional configuration of the console 2. 2, the console 2 includes a control unit 21, a storage unit 22, a communication unit 23, a display unit 24, and an operation unit 25. The units 21 to 25 are electrically connected to each other via a bus or the like.
[0054] The control unit 21 is composed of a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like. The ROM stores various programs executed by the CPU as well as parameters necessary for executing the programs. The CPU reads out various programs stored in the ROM, loads them into the RAM, executes various processes according to the loaded programs, and centrally controls the operation of each part of the console 2.
[0055] The storage unit 22 is composed of a non-volatile memory, a hard disk, or the like. The storage unit 22 also stores image data of radiation images acquired from other devices (the imaging device 1, the image management device 4, etc.).
[0056] The memory unit 22 also stores a trained model M. The trained model M is a machine learning (e.g., deep learning) process for automatically recognizing structures of a subject in a medical image. The trained model M is generated by machine learning using image data of a radiological image and structures of the subject in the radiological image (correct answer label). When image data of a radiological image is input, the trained model M performs inference and outputs information about the structure as output data.
[0057] Moreover, the storage unit 22 stores the imaging order information transmitted from the RIS or the like.
[0058] The communication unit 23 is composed of a communication module and the like. The communication unit 23 transmits and receives various signals and various data to and from other devices (the photographing device 1, the generating device 3, the image management device 4, etc.) connected via the communication network N in a wired or wireless manner.
[0059] The display unit 24 is configured with, for example, an LCD (Liquid Crystal Display), an organic EL display, etc. The display unit 24 displays a radiation image, etc., in accordance with an image signal received from the control unit 21.
[0060] The operation unit 25 includes a keyboard, a pointing device, a touch panel laminated on the surface of the display unit 24, etc. The keyboard includes cursor keys, numeric input keys, various function keys, etc. The pointing device is, for example, a mouse, etc. The operation unit 25 outputs a control signal to the control unit 21 according to an operation performed by the user.
[0061] The console 2 may not include the display unit 24 and the operation unit 25, and may receive a control signal from an input device provided separately from the console 2, for example, via the communication unit 23. The console 2 may also output an image signal to a display device (monitor) provided separately from the console 2. Furthermore, when the other device (such as the image management device 4) has a display unit and an operation unit, the display unit and the operation unit may be shared with the console 2. In other words, the console 2 may receive a control signal from the operation unit of the other device and output an image signal to the display unit of the other device.
[0062] The control unit 21 automatically recognizes the structure of the subject in the medical image. That is, the control unit 21 functions as a recognition unit. Specifically, for example, the control unit 21 analyzes the medical image to recognize objects in the image. The control unit 21 (recognition unit) may automatically recognize the structure of the subject in the medical image by image processing such as edge extraction and histogram analysis.
[0063] The medical images include radiological images, MRI images, and ultrasonic images. In this embodiment, a case where the medical image is a radiological image will be described. The subject's structure may include the target part or imaging part of the subject, and may also include a jig or marker for positioning. The subject's structure is preferably the target part or imaging part of the subject.
[0064] The control unit 21 may automatically recognize structures of subjects in medical images by using a trained model M obtained by machine learning. The trained model M includes, for example, an algorithm (program) and trained parameters. According to the trained model M, it is easy to automatically recognize the structure of the subject in the medical image, even if the joint is an artificial joint or the bone is missing due to a fracture, etc. Since the recognition accuracy is improved, the accuracy of correct output of the adjusted medical image is also improved.
[0065] The control unit 21 automatically adjusts the medical image based on the recognized structure, that is, functions as an adjustment unit. The automatic adjustment of the medical image includes rotation of the medical image and adjustment of the display range. Adjustment of the display range includes cropping.
[0066] The automatic adjustment of the medical image includes at least one of adjustment of a rotation angle of the medical image, adjustment of a position of a rotation center of the medical image, adjustment of a cropping of the medical image, and adjustment of a position of a cropping center of the medical image. The trimming adjustment includes adjusting the trimming size and adjusting the trimming position. Adjusting the position of the cropping center refers to adjusting the position of the center in the X-axis direction (e.g., left-right direction, horizontal direction) when cropping a medical image, or adjusting the position of the center in the Y-axis direction (e.g., up-down direction, vertical direction). Adjusting the rotation angle of a medical image includes correcting the tilt of the medical image.
[0067] The control unit 21 (adjustment unit) determines an automatic adjustment standard, which is a standard for automatically adjusting a medical image, based on the recognized structure or imaging order information related to the medical image.
[0068] The automatic adjustment criteria for the medical image include at least one of a criterion for adjusting the rotation angle of the medical image, a criterion for adjusting the position of the rotation center of the medical image, a criterion for adjusting the trimming of the medical image, and a criterion for adjusting the position of the center of trimming of the medical image. The criteria for adjusting the rotation angle include, for example, the display mode and shape of the imaging part of the imaging subject when the medical image is rotated, and the criteria for adjusting the rotation angle also include the display mode and shape that serve as a sample for adjusting the rotation angle.
[0069] The automatic adjustment criterion is information indicating the shape of the imaging region of the imaging subject or the anatomical region of the imaging region. The automatic adjustment criterion may also include information indicating the final display mode that serves as a criterion when rotating or cropping the medical image. For example, when a predetermined rotation angle pattern (patterns A1, A2, etc., described later) is selected in the item of the rotation standard of the medical image, the medical image is rotated so as to be displayed in the state of the rotation angle pattern, and the display image is determined. Also, for example, when the vertebral body center is selected in the item of the trimming standard (X-axis direction) of the medical image, the medical image is trimmed so that the vertebral body is located at the center, and the display image is determined.
[0070] The storage unit 22 stores, for each imaging part of the imaging subject, whether to automatically adjust the medical image in association with the imaging part of the imaging subject. That is, in the storage unit 22, whether to automatically adjust the medical image is set in association with the imaging part of the medical image. For example, in the case of setting to automatically adjust, it is possible to further set whether to adjust the rotation or whether to adjust the trimming. In some cases, whether to automatically adjust is stored for each imaging part in association with the imaging part, and in other cases, whether to automatically adjust is stored for each imaging part and imaging direction information in association with the imaging part.
[0071] The automatic adjustment of the medical image may have multiple items. In that case, the storage unit 22 stores, for each imaging part of the imaging subject, the imaging part of the imaging subject and whether or not to automatically adjust each of the multiple items in association with each other.
[0072] The control unit 21 (adjustment unit) refers to the correspondence relationship (photographing area-whether to perform automatic adjustment) stored in the memory unit 22, and determines whether to perform automatic adjustment based on the photographing area of the photographing subject, which is a recognized structure, or the photographing order information related to the medical image.
[0073] When the automatic adjustment of a medical image has multiple items, the control unit 21 (adjustment unit) refers to the correspondence stored in the memory unit 22 and determines whether or not to automatically adjust each item based on the imaging part of the imaging subject, which is the recognized structure, or the imaging order information related to the medical image.
[0074] The storage unit 22 stores the photographing part of the subject in association with an automatic adjustment standard, which is a standard for automatically adjusting a medical image, for each photographing part of the subject. In other words, the storage unit 22 stores the automatic adjustment standard for the medical image in association with the photographing part of the medical image.
[0075] The automatic adjustment standard may have a plurality of items. In this case, the storage unit 22 stores the imaging part of the imaging subject and the automatic adjustment standard for each of the plurality of items in association with each imaging part of the imaging subject.
[0076] The control unit 21 (adjustment unit) refers to the correspondence relationship (photographing area-automatic adjustment standard) stored in the memory unit 22, and determines the automatic adjustment standard based on the photographing area of the photographing target, which is the recognized structure, or the photographing order information related to the medical image.
[0077] When the automatic adjustment criteria have multiple items, the control unit 21 (adjustment unit) refers to the correspondence stored in the memory unit 22 and determines the automatic adjustment criteria for each item based on the imaging part of the imaging subject, which is the recognized structure, or the imaging order information related to the medical image.
[0078] In one embodiment, the medical image output device includes a display unit that displays the automatically adjusted medical image. The display unit 24 of the console 2 is one embodiment of an output unit that outputs the adjusted medical image. In another embodiment, the medical image output device may include a storage unit for storing the automatically adjusted medical image and a display unit for displaying the stored medical image. In this embodiment, the adjusted image is stored first, and then the adjusted image is displayed. In another embodiment, the medical image output device may include a storage unit that stores information on the angle and position of the automatic adjustment, and a display unit that displays a display image based on the information on the angle and position of the automatic adjustment. This embodiment is a pattern in which the information on the adjustment angle and position is saved and adjusted at the timing of display. In another embodiment, the medical image output device may be provided with an output section that outputs at least one of the automatically adjusted medical image, the automatically adjusted and stored medical image, and the automatically adjusted angle and position information to another device.
[0079] The storage unit 22 stores a setting table 221. In the setting table 221, whether or not to automatically adjust a medical image and the automatic adjustment standard for the medical image are set for each imaging part. The setting table 221 can be set, for example, for each medical facility that uses the system 100. In addition, the setting table 221 may be set for each user (medical worker such as a doctor) or for each group to which a user belongs.
[0080] FIG. 3 shows an example of the data configuration of the setting table 221. As shown in FIG. 3, the ON / OFF of the automatic trimming function, the automatic trimming standard, the ON / OFF of the automatic rotation function, and the automatic rotation standard are associated with each imaging region. Here, the imaging region also includes the imaging direction.
[0081] The ON / OFF of the automatic trimming function is information indicating whether or not automatic adjustment is performed regarding the trimming of the medical image. "ON" is set when automatic adjustment regarding the trimming is performed, and "OFF" is set when automatic adjustment regarding the trimming is not performed. Note that the trimming adjustment is not limited to removing the part outside the specified range of the medical image, but also includes adjustment of the display range and display position of the medical image.
[0082] The automatic trimming criterion is an automatic adjustment criterion for trimming a medical image. The automatic trimming criterion includes, for example, the center position of trimming (X-axis direction, Y-axis direction). Only one of the two directions (X-axis direction, Y-axis direction) may be specified as the center position of trimming. In addition, the automatic trimming criterion may specify a positional relationship such that a predetermined structure is included in the medical image. For example, for the imaging site "front of the abdomen," a positional relationship such as "OK if the diaphragm is included at the top" may be specified as the automatic trimming criterion in the Y-axis direction.
[0083] The ON / OFF of the automatic rotation function is information indicating whether or not to perform automatic adjustment regarding the rotation of medical images. "ON" is set when automatic adjustment regarding rotation is performed, and "OFF" is set when automatic adjustment regarding rotation is not performed.
[0084] The automatic rotation reference is an automatic adjustment reference for the rotation of a medical image. The automatic rotation reference includes, for example, a rotation center position (X-axis direction, Y-axis direction) and a rotation angle pattern. The rotation center position is the position of the rotation axis when rotating a medical image. The rotation angle pattern is, for example, information indicating in what positional relationship the image is desired to be displayed (target rotation state).
[0085] For example, in the setting table 221 shown in FIG. 3, for the imaging area "front chest," the trimming center in the X-axis direction (left-right direction) is set to "center of the vertebral body (spine)," and the center in the Y-axis direction (up-down direction) is set to "between the 6th and 7th thoracic vertebrae." However, there is also a policy of not adjusting the position in the Y-axis direction so that the entire subject can be confirmed. Therefore, it may be possible to separately set ON / OFF for cropping (centering) in the Y-axis direction. Furthermore, for the imaging region "front of the chest," the rotation function is generally not used because it would make it difficult to determine the degree of curvature of the spine.
[0086] Regarding the automatic adjustment standard, when there are generally multiple patterns (standards) for the same imaging region, a selection of patterns (candidates) is presented to the user when setting the standard, allowing the user to select from the selection.
[0087] <Example of automatic adjustment> As an example of automatic adjustment, automatic rotation and automatic trimming for an "elbow joint lateral image" will be described. In the following explanation of angles on an image, as shown in FIG. 4, the positive direction of the X-axis is set to 0 degrees with the origin of the XY plane as the center, and angles are taken counterclockwise.
[0088] FIG. 5(a) shows an example of a side image 50 of an elbow joint. The elbow joint side image 50 shows the humerus 51, forearm bones 52 (ulna and radius), and the joint movable part on the humerus side (humeral trochlea 53). The elbow joint side image 50 is adjusted so that the humerus 51 and forearm bones 52 are at a predetermined angle around the humeral trochlea 53. There are at least two patterns for the rotation angle. In the case of the right arm, as shown in Fig. 5(b), the rotation angle in which the humerus direction D1 is oriented in the 45 degree direction and the forearm direction D2 is oriented in the 315 degree direction with the elbow joint bent at approximately 90 degrees is defined as "Pattern A1". In the case of the left arm, "Pattern A1" is a state in which the humerus direction D1 is oriented in the 135 degree direction and the forearm direction D2 is oriented in the 225 degree direction. 5(c), the rotation angle of the right arm is set to 90 degrees with the humerus direction D1 facing 90 degrees and the forearm direction D2 facing 0 degrees with the elbow joint bent at approximately 90 degrees, as shown in FIG. 5(c). For the left arm, "Pattern A2" is set to a state in which the humerus direction D1 faces 90 degrees and the forearm direction D2 faces 180 degrees. The basis for rotation can be changed in advance by changing the settings. Also, the image position is adjusted so that the trochlea of the humerus 53 is at the center of the image.
[0089] An automatic adjustment method for the "side image of the elbow joint" will be described. (1) In the lateral image 50 of the elbow joint, the position of the center of the recognized trochlea 53 of the humerus (center of rotation of the image) is calculated. (2) The angular directions of the humerus 51 and forearm 52 with this center of rotation as the origin are calculated. (3) Determine the bisector L1 of the angle between the humerus bone direction D1 and the forearm bone direction D2 (see Figures 5(b) and 5(c)). (4) When "Pattern A1" is set as the automatic rotation reference, the image is rotated so that the bisector L1 faces in the 0 degree direction with respect to the "side image of the elbow joint" of the right arm, as shown in Fig. 5(b). When "Pattern A2" is set as the automatic rotation reference, the image is rotated so that the bisector L1 faces in the 45 degree direction with respect to the "side image of the elbow joint" of the right arm, as shown in Fig. 5(c). In the "side image of elbow joint," if the angle at which the elbow joint is bent is not approximately 90 degrees, the image is rotated so that only the humerus direction D1 is oriented at 90 degrees.
[0090] Next, automatic trimming for a "front chest image" will be described. FIG. 6(a) shows an example of a frontal chest image 60. The front chest image 60 includes lung fields, vertebral bodies, etc. The position of the front chest image 60 is adjusted so that the left-right center of the lung fields (vertebral bodies) becomes the left-right center of the image (X-axis direction). The up-down direction (Y-axis direction) of the front chest image 60 may not be adjusted, the position of the apex of the lung (the upper end of the lung field) may be adjusted, or the position of a specified structure may be set as the center of the image. As shown in FIG. 6(b), the state in which the image is trimmed so that the center L2 of the lung field in the left-right direction is the center of the image in the left-right direction is designated as "Pattern B1". As shown in Figure 6(c), the state in which the image is trimmed so that the left-right center L2 of the lung field is at the left-right center of the image and the apex of the lung is a predetermined value L3 (e.g., how many centimeters) from the top of the image area is called "Pattern B2". Although not shown in the drawings, the position of the predetermined structure may be adjusted so that, for example, the space between the sixth and seventh thoracic vertebrae becomes the center of the image in the vertical direction. The position of the image is adjusted in the left-right and up-down directions based on the set criteria.
[0091] An automatic adjustment method for a "frontal chest image" will be described. (1) As shown in FIG. 6(a), in a frontal chest image 60, a rectangular region 61 surrounding the recognized lung field is detected as a region of interest (ROI). (2) The position of the image is adjusted so that the center L2 in the horizontal direction of the rectangular area 61 becomes the center in the horizontal direction of the image (see FIGS. 6(b) and 6(c)). (3) When the position of the apex of the lung is specified in the up-down direction, the upper end of the rectangular area 61 is adjusted to be a predetermined value L3 from the upper end of the image area, as shown in FIG. 6(c).
[0092] In this case, it is assumed that the center L2 of the lung field in the left-right direction (the center of the rectangular region 61) coincides with the center of the vertebral body. The center position of the vertebral body may be obtained by automatically recognizing the vertebral body from the frontal chest image 60.
[0093] Next, automatic rotation and automatic trimming for the "side image of the knee joint" will be described. FIG. 7(a) shows an example of a side image 70 of a knee joint. The knee joint lateral image 70 shows a femur 71, a tibia 72 (tibia and fibula), and a femoral condyle. The knee joint lateral image 70 is adjusted so that the femur 71 and the tibia 72 are at a predetermined angle with the femoral condyle center 73 as the center. Here, the femoral condyle center 73 is used as the "center of the knee joint" which is the center of rotation. There are at least two patterns for the rotation angle. As shown in FIG. 7(b), a rotation angle in which the lower leg bone direction D4 is turned in a 270 degree direction (downward) is defined as "Pattern C1." 7(c), the rotation angle of the right knee is defined as "Pattern C2" when the bisector L4 of the angle between the thigh bone direction D3 and the tibia direction D4 is oriented in the 0 degree direction. For the left knee, "Pattern C2" is when the bisector L4 of the angle between the thigh bone direction D3 and the tibia direction D4 is oriented in the 180 degree direction. The basis for rotation can be changed in advance by changing the settings. Also, the image position is adjusted so that the femoral condyle center 73 is at the center of the image.
[0094] An automatic adjustment method for the "side image of the knee joint" will be described. (1) In a lateral knee joint image 70, the position of the recognized femoral condyle center 73 (center of rotation of the image) is calculated. (2) The angular directions of the femur 71 and the lower leg bone 72 with this center of rotation as the origin are calculated. (3) When "Pattern C2" is set as the automatic rotation reference, a bisector L4 of the angle between the thigh bone direction D3 and the lower leg bone direction D4 is obtained. (4) When "Pattern C1" is set as the automatic rotation reference, the image is rotated so that the lower leg bone direction D4 faces 270 degrees with respect to the "side image of the knee joint," as shown in FIG. 7(b). When "Pattern C2" is set as the automatic rotation reference, the image is rotated so that the bisector L4 faces 0 degrees with respect to the "side image of the knee joint" of the right knee, as shown in FIG. 7(c). When "Pattern C2" is set as the automatic rotation reference, the image is rotated so that the bisector L4 faces 180 degrees with respect to the "side image of the knee joint" of the left knee.
[0095] Furthermore, in the automatic trimming adjustment, if the ROI recognized from the medical image is larger than the output size of the image, the output size may be automatically changed. For example, assume that an ROI 81 is recognized from an entire medical image 80 as shown in Fig. 8(a). The output size 82 is large (14 x 14 inches), while the height of the ROI 81 is 15 inches. In this case, as shown in Fig. 8(b), the height of the output size 82 is automatically changed to 15 inches or more.
[0096] <Console operation> Next, the operation of the console 2 will be described. 9 is a flowchart showing the shooting control process executed in the console 2. The shooting control process is executed by the CPU of the control unit 21 in cooperation with a program stored in the ROM.
[0097] First, the control unit 21 accepts the selection of radiography order information for radiography to be performed (region to be radiographed, direction to be radiographed) through an operation on the operation unit 25 (step S1).
[0098] 10 shows an example of an examination screen 241 displayed on the display unit 24. The examination screen 241 is provided with an imaging selection area 241A, a setting area 241B, an image display area 241C, an output button 241D, and the like. The radiography selection area 241A displays the contents of each radiography (region to be radiographed, radiography direction, etc.) corresponding to each piece of radiography order information. The setting area 241B is an area for setting image reading conditions and image processing conditions for photography. The captured radiographic image is displayed in the image display region 241C. Note that, at the stage of step S1, the radiographic image is not yet displayed in the image display region 241C. The output button 241D is a button for instructing output of a radiation image.
[0099] A user (an image-taker such as a radiologist) operates the operation unit 25 to select any one of the pieces of image capture order information in the image capture selection area 241A of the examination screen 241.
[0100] Next, the control unit 21 sets the photographing conditions in the photographing device 1 and the generating device 3 (step S2). For example, the control unit 21 automatically sets the imaging conditions in the imaging device 1 and the generating device 3 based on the selected imaging order information. Alternatively, the control unit 21 may set the imaging conditions for the imaging to be performed in the imaging device 1 and the generating device 3 in response to an operation of the operation unit 25 by the user on the examination screen 241 .
[0101] Next, the user places the subject S between the radiation source 33 of the generating device 3 and the imaging device 1, and performs positioning. When the user operates the irradiation instruction switch 32, the radiation generator 3 irradiates the region of the subject S to be imaged with the radiation R. The imaging device 1 generates a radiation image (still image, dynamic image) showing the imaging region at the timing when it receives radiation R from the generation device 3. The imaging device 1 transmits image data of the radiation image (still image data, dynamic image data) to the console 2.
[0102] The control unit 21 of the console 2 acquires image data of the radiation image generated by imaging via the communication unit 23 (step S3).
[0103] Next, the control unit 21 analyzes the image data of the radiographic image and automatically recognizes the structure of the subject in the radiographic image (step S4). For example, the control unit 21 reads out the trained model M and automatically recognizes the structure in the radiographic image. The control unit 21 inputs the image data of the received radiographic image into the trained model M and causes it to perform inference, thereby outputting the recognition result of the structure. The trained model M outputs, as structure recognition results, for example, the imaging part, imaging direction, names and positions of bones, names and positions of organs, etc.
[0104] Next, the control unit 21 performs an automatic adjustment process on the radiation image based on the recognized structure (step S5). Now, the automatic adjustment process will be described with reference to FIG.
[0105] The control unit 21 refers to the setting table 221 stored in the storage unit 22 and determines whether or not the automatic rotation function corresponding to the imaging region of the radiographic image is ON (step S11). The imaging region of the radiation image may be information automatically recognized from the radiation image in step S4, or may be information included in the imaging order information selected in step S1.
[0106] When the automatic rotation function corresponding to the imaging region of the radiographic image is ON (step S11; YES), the control unit 21 acquires an automatic rotation reference corresponding to the imaging region of the radiographic image from the setting table 221 (step S12). The automatic rotation reference includes the rotation center and the rotation angle pattern of the image.
[0107] Next, the control unit 21 calculates a position in the radiographic image around which the image will be rotated (rotation center position) based on the rotation center included in the automatic rotation reference and a structure recognized in the radiographic image (step S13).
[0108] Next, the control unit 21 calculates the amount of rotation of the image so that the radiographic image conforms to the automatic rotation standard (step S14). For example, the control unit 21 calculates the amount of rotation for arranging the radiographic image in accordance with the rotation angle pattern based on the rotation angle pattern included in the automatic rotation standard and the structure recognized from within the radiographic image.
[0109] Next, the control unit 21 rotates the radiographic image by the calculated rotation amount around the rotation center position (step S15).
[0110] After step S15, or in step S11, if the automatic rotation function corresponding to the imaging region of the radiation image is not ON (step S11; NO), the process proceeds to step S16.
[0111] In step S16, the control unit 21 determines whether or not an automatic trimming function corresponding to the imaging region of the radiation image is ON.
[0112] When the automatic trimming function corresponding to the imaging region of the radiographic image is ON (step S16; YES), the control unit 21 acquires the automatic trimming standard corresponding to the imaging region of the radiographic image from the setting table 221 (step S17).
[0113] Next, the control unit 21 calculates which position in the radiographic image should be the center for trimming (trimming center position) based on the trimming center included in the automatic trimming criteria and the structure recognized in the radiographic image (step S18).
[0114] Next, the control unit 21 calculates the shift amount and the trimming size of the image so that the radiographic image conforms to the automatic trimming standard (step S19). For example, the control unit 21 calculates the shift amount and the trimming size for arranging the radiographic image according to the automatic trimming standard, based on the automatic trimming standard and the structure recognized from within the radiographic image.
[0115] Next, the control unit 21 adjusts the trimming position of the radiographic image (step S20). The control unit 21 adjusts the trimming position in accordance with the trimming center position, the shift amount, and the trimming size.
[0116] After step S20, or in step S16, if the automatic trimming function corresponding to the imaging region of the radiation image is not ON (step S16; NO), the automatic adjustment process ends.
[0117] Here, a specific example of automatic recognition and automatic adjustment of a structure will be described with reference to FIGS. 12 is the processing target, the control unit 21 recognizes the humerus 51, forearm bones 52, trochlea 53, etc. from the elbow joint lateral image 50 in step S4. Furthermore, based on the humerus 51, forearm bones 52, trochlea 53, etc. recognized within the image, the control unit 21 recognizes that the photographed site of the elbow joint lateral image 50 is the "lateral side of the elbow joint" of the "right arm".
[0118] Here, in the setting table 221, for the imaging area "lateral side of elbow joint", the automatic rotation function is set to "ON", the rotation center in the X-axis and Y-axis directions is set to "center of the trochlea of the humerus", and the rotation angle pattern is set to "Pattern A1 (see FIG. 5(b))". Also, in the setting table 221, the automatic trimming function is set to "ON" for the imaging region "lateral surface of elbow joint", and the trimming center in the X-axis direction and Y-axis direction is set to "center of the trochlea of the humerus".
[0119] In step S15, the control unit 21 rotates the elbow joint lateral image 50 around the humerus trochlea 53 so that the bisector L1 of the angle between the humerus direction and the forearm bone direction faces in the 0 degree direction, as shown in Figure 13, to generate a rotated image 50A. In step S20, the control unit 21 moves the trimming frame 50B in the rotated image 50A so that the center of the trimming frame 50B coincides with the trochlea of the humerus 53, as shown in FIG.
[0120] After the automatic adjustment process, returning to FIG. 9, the control unit 21 displays a preview of the automatically adjusted radiation image on the display unit 24 (step S6).
[0121] 15 shows an example of a preview display screen 242 displayed on the display unit 24. The preview display screen 242 is displayed superimposed on the examination screen 241. An automatically adjusted lateral image of an elbow joint is displayed on the preview display screen 242. Specifically, the preview display screen 242 displays an elbow joint lateral image that has been automatically rotated to match the pattern A1 (see FIG. 5(b)) and automatically cropped so that the center of the trochlea of the humerus is the center of the image.
[0122] 16 shows an example of another preview display screen 243 displayed on the display unit 24. The preview display screen 243 is displayed superimposed on the examination screen 241. An automatically adjusted frontal chest image (chest in upright position) is displayed on the preview display screen 243. In addition, in the setting table 221, for the imaging area "front chest", the automatic cropping function is set to "ON", the cropping center in the X-axis direction is set to "center of vertebral body", and the cropping center in the Y-axis direction is set to "none". Also, in the setting table 221, the automatic rotation function is set to "OFF" for the imaging region "front chest". On the preview display screen 243, a frontal chest image that has been automatically cropped so that the center of the vertebral body (the center L2 of the lung field in the left-right direction) is at the center of the image in the X-axis direction is displayed.
[0123] Here, when a radiation image is captured in the console 2, the automatically adjusted image is displayed (initial display), but the control unit 21 may perform automatic rotation adjustment and automatic trimming adjustment of the image at any timing. For example, when a radiation image before adjustment is displayed, the automatically adjusted image may be displayed in response to a predetermined operation by the user (such as pressing an automatic adjustment button). Furthermore, the timing for displaying the automatically adjusted image may be set in advance from "initial display," "when a button is pressed," etc. This setting may also be changed for each facility and each user.
[0124] The user checks the previewed radiographic image after the automatic adjustment. For example, the user presses the close buttons 242A, 243A (see Figs. 15 and 16) on the preview display screens 242, 243 by operating the operation unit 25. The control unit 21 then displays the previewed radiographic image after the automatic adjustment in the image display area 241C (see Fig. 10) of the examination screen 241.
[0125] 17 and 18 show display examples in which a radiation image after automatic adjustment is displayed in the image display area 241C of the examination screen 241. The screen configuration of the examination screen 241 shown in FIGS. 17 and 18 is the same as that in FIG. The image display area 241C shown in Figure 17 displays a lateral image of an elbow joint that has been automatically rotated to match pattern A1 (see Figure 5(b)) and automatically cropped so that the center of the trochlea of the humerus is the center of the image.
[0126] In FIG. 18, in the setting table 221, for the imaging area "lateral side of elbow joint", the automatic rotation function is set to "ON", the rotation center in the X-axis and Y-axis directions is set to "center of the trochlea of the humerus", and the rotation angle pattern is set to "Pattern A2 (see FIG. 5(c))". Also, in the setting table 221, the automatic trimming function is set to "ON" for the imaging region "lateral surface of elbow joint", and the trimming center in the X-axis direction and Y-axis direction is set to "center of the trochlea of the humerus". The image display area 241C shown in Figure 18 displays a lateral image of the elbow joint that has been automatically rotated to match pattern A2 (see Figure 5(c)) and automatically cropped so that the center of the trochlea of the humerus is the center of the image.
[0127] The user may further manually adjust the automatically adjusted radiation image by operating the operation unit 25.
[0128] When the user presses the output button 241D (see Figs. 17 and 18) on the examination screen 241 by operating the operation unit 25, the control unit 21 outputs the radiographic image displayed in the image display area 241C (step S7). For example, the control unit 21 stores the automatically adjusted radiographic image in the storage unit 22. The control unit 21 also transmits the automatically adjusted radiographic image to the image management device 4 via the communication unit 23. This completes the shooting control process.
[0129] As described above, the control unit 21 of the console 2 automatically recognizes structures of the subject in a medical image, and automatically adjusts the medical image based on the recognized structures. This eliminates the need for the user to manually adjust the medical image. The control unit 21 can always output images that have been adjusted to a stable level, regardless of the skill of the user (the photographer, such as a radiologist). The control unit 21 can reduce the workload of the photographer by automatically adjusting the image. Since images with a uniform positioning of the subject can be obtained in medical facilities, etc., subsequent interpretation of the images becomes easier.
[0130] For example, the control unit 21 can adjust the rotation angle of a medical image, adjust the position of the rotation center of a medical image, adjust the trimming of a medical image, and adjust the position of the center of trimming of a medical image.
[0131] Furthermore, the control unit 21 can determine an automatic adjustment standard based on the recognized structure or imaging order information related to the medical image. Specifically, the control unit 21 can determine a criterion for adjusting the rotation angle of a medical image, a criterion for adjusting the position of the rotation center of a medical image, a criterion for adjusting the trimming of a medical image, a criterion for adjusting the position of the center of trimming of a medical image, etc.
[0132] For example, by using information indicating the shape of the imaging region of the imaging subject or the anatomical region of the imaging region as the automatic adjustment standard, a display mode serving as a model for adjustment or a target arrangement state of medical images can be set.
[0133] Furthermore, since the imaging region of the imaging subject is associated with whether or not to automatically adjust the medical image in the storage unit 22, the control unit 21 can determine whether or not to automatically adjust the medical image based on the imaging region. Here, when a structure recognized in a medical image is used as the imaging area to be used when determining whether to perform automatic adjustment, the control unit 21 can determine whether to perform automatic adjustment based on information obtained from the medical image. When the control unit 21 uses information included in the shooting order information as the shooting area to be used when determining whether to perform automatic adjustment, the control unit 21 can determine whether to perform automatic adjustment based on the information set at the time of shooting.
[0134] Furthermore, the control unit 21 can determine whether or not to automatically adjust each of the functions such as the automatic rotation function and the automatic trimming function based on the imaging region.
[0135] Furthermore, since the imaging region of the imaging subject is associated with the automatic adjustment reference in the storage unit 22, the control unit 21 can determine the automatic adjustment reference based on the imaging region. Here, when a structure recognized in a medical image is used as the imaging part to be used when determining the automatic adjustment standard, the control unit 21 can determine the automatic adjustment standard based on information obtained from the medical image. When using information included in the radiography order information as the radiographing region used when determining the automatic adjustment standard, the control unit 21 can determine the automatic adjustment standard based on information set at the time of radiography.
[0136] Furthermore, the control unit 21 can determine an automatic adjustment standard for each item such as an automatic rotation standard, an automatic trimming standard, etc., based on the imaging region.
[0137] Specifically, whether or not to perform automatic adjustment and the automatic adjustment standard can be set in advance in the setting table 221 for each imaging region in accordance with the agreement within the medical facility and each doctor.
[0138] Furthermore, the control unit 21 calculates the amount of adjustment (amount of rotation, amount of shift, etc.) according to the automatic adjustment standard based on the structure recognized from the medical image, so that adjustment suited to the actual state of the image can be performed.
[0139] In addition, by using a trained model M obtained by machine learning as a recognition unit that automatically recognizes structures of subjects in medical images, structures can be automatically recognized with high accuracy.
[0140] It goes without saying that the present invention is not limited to the above-described embodiment, and can be modified as appropriate without departing from the spirit of the present invention.
[0141] In the above embodiment, the case where the functions of the medical image output device according to the present invention are installed in the console 2 has been described, but the functions of the medical image output device may be installed in a device other than the console 2. Also, a dedicated device having the functions of the medical image output device may be installed.
[0142] In the above embodiment, the control unit 21 of the console 2 has been described as causing the automatically adjusted image to be displayed on the display unit 24, but the automatically adjusted image may be displayed on a display device separate from the console 2. Also, the recognition unit, adjustment unit, and output unit of the present invention may be mounted on different devices to configure a medical image output system.
[0143] Furthermore, a plurality of types of automatic adjustment standards for the same imaging region may be prepared in the setting table 221, and the automatic adjustment standard to be adopted may be switched according to the operation of the medical facility.
[0144] Furthermore, the adjustment unit of the present invention may be a trained model obtained by machine learning.
[0145] Furthermore, in the above embodiment, rotation and trimming have been described as adjustments of medical images, but the control unit 21 may automatically adjust the gradation, contrast, etc. of the medical image.
[0146] The computer-readable medium for storing the program for executing each process is not limited to the above examples, and a portable recording medium such as a CD-ROM may also be used. A carrier wave may also be used as a medium for providing program data via a communication line. [Explanation of symbols]
[0147] 1. Radiation imaging device (imaging device) 2 Console 3 Radiation Generator (Generator) 4. Image management device 21 Control section 22 Memory section 23 Communications Department 24 Display section 25 Control section 31 Generator 32 Irradiation switch 33 Radiation source 100 Radiography system (system) 221 Setting Table M trained models N Communication Network
Claims
1. A recognition unit that automatically recognizes a structure of a subject in a medical image; an adjustment unit that automatically adjusts the medical image based on the recognized structure; an output unit that outputs the adjusted medical image; A medical image output device having the above configuration.
2. The medical image output device according to claim 1 , wherein the automatic adjustment of the medical image includes at least one of adjustment of a rotation angle of the medical image, adjustment of a position of a rotation center of the medical image, adjustment of a cropping of the medical image, and adjustment of a position of a center of cropping of the medical image.
3. The medical image output device according to claim 1 , wherein the automatic adjustment of the medical image is adjustment of a rotation angle of the medical image or adjustment of a position of a rotation center of the medical image.
4. The medical image output device according to claim 1 , wherein the adjustment unit determines an automatic adjustment standard, which is a standard for automatically adjusting the medical image, based on the recognized structure or imaging order information related to the medical image.
5. The medical image output device of claim 4, wherein the automatic adjustment criteria for the medical image include at least one of a criterion for adjusting the rotation angle of the medical image, a criterion for adjusting the position of the rotation center of the medical image, a criterion for adjusting the trimming of the medical image, and a criterion for adjusting the position of the center of the trimming of the medical image.
6. 5. The medical image output device according to claim 4, wherein the automatic adjustment reference for the medical image is a reference for adjustment of a rotation angle of the medical image or a reference for adjustment of a position of a rotation center of the medical image.
7. 5. The medical image output device according to claim 4, wherein the automatic adjustment reference is information indicating a shape of a region to be photographed of an imaging subject or an anatomical region of the region to be photographed.
8. a storage unit that stores, for each imaging region of an imaging subject, information on whether or not to automatically adjust the medical image in association with the imaging region of the imaging subject; The medical image output device according to claim 1 , wherein the adjustment unit determines whether or not to perform the automatic adjustment based on the imaging part of the imaging subject, which is the recognized structure, or imaging order information related to the medical image.
9. The automatic adjustment has a plurality of items, a storage unit that stores, for each imaging region of a subject, information on whether or not to automatically adjust each of the plurality of items in association with the imaging region of the subject; 4. The medical image output device according to claim 1, wherein the adjustment unit determines whether or not to automatically adjust each of the items based on the recognized structure, that is, the imaging part of the imaging subject, or imaging order information related to the medical image.
10. a storage unit that stores, for each imaging region of an imaging target, an automatic adjustment standard that is a standard for automatically adjusting the medical image in association with the imaging region of the imaging target; The medical image output device according to claim 1 , wherein the adjustment unit determines the automatic adjustment standard based on an imaging part of a subject that is the recognized structure or imaging order information related to the medical image.
11. The automatic adjustment criteria, which are criteria for automatically adjusting the medical image, have a plurality of items, a storage unit that stores, for each imaging region of an imaging subject, an imaging region of the imaging subject and an automatic adjustment standard for each of the plurality of items in association with each other; The medical image output device according to claim 1 , wherein the adjustment unit determines an automatic adjustment standard for each of the items based on an imaging part of a subject, which is the recognized structure, or imaging order information related to the medical image.
12. The medical image output device according to claim 1 , wherein the medical image is a radiological image.
13. The medical image output device according to claim 1 , wherein the recognition unit is a trained model obtained by machine learning.
14. Computer, a recognition unit that automatically recognizes structures of objects in medical images; an adjustment unit that automatically adjusts the medical image based on the recognized structure; an output unit that outputs the adjusted medical image; A program to function as a
15. The program according to claim 14 , wherein the automatic adjustment of the medical image includes at least one of adjustment of a rotation angle of the medical image, adjustment of a position of a rotation center of the medical image, adjustment of a cropping of the medical image, and adjustment of a position of a center of cropping of the medical image.
16. The program according to claim 14 , wherein the automatic adjustment of the medical image is adjustment of a rotation angle of the medical image or adjustment of a position of a rotation center of the medical image.
17. The program according to claim 14 , wherein the adjustment unit determines an automatic adjustment standard that is a standard for automatically adjusting the medical image, based on the recognized structure or imaging order information related to the medical image.
18. The program of claim 17, wherein the automatic adjustment criteria for the medical image include at least one of a criterion for adjusting the rotation angle of the medical image, a criterion for adjusting the position of the rotation center of the medical image, a criterion for adjusting the cropping of the medical image, and a criterion for adjusting the position of the center of the cropping of the medical image.
19. The program according to claim 17 , wherein the automatic adjustment criterion for the medical image is a criterion for adjusting a rotation angle of the medical image or a criterion for adjusting a position of a rotation center of the medical image.
20. The program according to claim 17 , wherein the automatic adjustment reference is information indicating a shape of a region to be imaged of an imaging subject or an anatomical region of the region to be imaged.
21. The computer is caused to function as a storage unit that stores, for each imaging part of an imaging subject, information as to whether or not to automatically adjust the medical image in association with the imaging part of the imaging subject; The program according to claim 14 , wherein the adjustment unit determines whether or not to perform the automatic adjustment based on an imaging part of a subject that is the recognized structure or imaging order information related to the medical image.
22. The automatic adjustment has a plurality of items, The computer is caused to function as a storage unit that stores, for each imaging region of an imaging subject, information on whether or not to automatically adjust each of the plurality of items in association with the imaging region of the imaging subject; The program according to claim 14 , wherein the adjustment unit determines whether or not to automatically adjust each of the items based on an imaging part of a subject, which is the recognized structure, or imaging order information related to the medical image.
23. The computer is caused to function as a storage unit that stores, for each imaging part of an imaging object, an automatic adjustment standard that is a standard for automatically adjusting the medical image in association with the imaging part of the imaging object; The program according to claim 14 , wherein the adjustment unit determines the automatic adjustment standard based on an imaging site of a subject, which is the recognized structure, or imaging order information related to the medical image.
24. The automatic adjustment criteria, which are criteria for automatically adjusting the medical image, have a plurality of items, causing the computer to function as a storage unit that stores, for each imaging region of an imaging subject, an imaging region of the imaging subject and an automatic adjustment standard for each of the plurality of items in association with each other; The program according to claim 14 , wherein the adjustment unit determines an automatic adjustment standard for each of the items based on an imaging part of a subject, which is the recognized structure, or imaging order information related to the medical image.
25. The program according to claim 14 , wherein the medical image is a radiological image.
26. The program according to claim 14 , wherein the recognition unit is a trained model obtained by machine learning.
27. A recognition step of automatically recognizing a structure of a subject in a medical image; an adjustment step of automatically adjusting the medical image based on the recognized structure; an output step of outputting the adjusted medical image; A medical image output method comprising the steps of:
28. A recognition unit that automatically recognizes a structure of a subject in a medical image; an adjustment unit that automatically adjusts the medical image based on the recognized structure; an output unit that outputs the adjusted medical image; A medical image output system having the above configuration.
Citation Information
Patent Citations
Method and system for automatically extracting magnetic resonance image corpus callosum
CN104083170A
Image processing selecting method, image selecting method, and image processor
JP2001351092A
Image processing apparatus, image processing method, and recording medium which stores program according to which computer perform pertinent image processing
JP2004174217A
Magnetic resonance imaging apparatus
JP2012110688A
X-ray imaging apparatus and image processing apparatus for medical use
JP2013135832A
