Medical information processing device, x-ray diagnostic device, method for processing medical information, and medical information processing program

Abstract

To support use of a breast configuration.SOLUTION: A medical information processing device includes: a first acquisition part for acquiring a first breast configuration from a mammographic image in accordance with a predetermined standard; a second acquisition part for acquiring a second breast configuration different from the first breast configuration from the mammographic image; and a display control unit for displaying the first breast configuration and the second breast configuration on a display part.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The embodiments disclosed in this specification and the drawings relate to a medical information processing apparatus, an X-ray diagnostic apparatus, a medical information processing method, and a medical information processing program. [Background technology]

[0002] An index called breast configuration is known. Breast configuration is an index that indicates the amount of mammary gland tissue, and can be obtained from mammography images obtained by X-raying the subject's breasts. For example, breast configuration can be judged visually by a person reading the mammography image, or automatically by image processing. However, breast configuration can change depending on the judgment method, and it can be difficult to judge how reliable the presented breast configuration can be. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-170881 A [Patent Document 2] JP 2022-105079 A [Patent Document 3] JP 2022-162969 A [Non-patent literature]

[0004] [Non-Patent Document 1] Hirotake Minami, Introduction to Breast Configuration Analysis Software (Bda) Using Digital Mammography Images, KONICA MINOLTA TECHNOLOGY REPORT VOL.19, 2022, pp. 78-82 [Non-Patent Document 2] Toshihiro Kai, Characteristics of breast mass software and an attempt to correct measurement values ​​in the "apparent high density" and "relatively low density" groups, Journal of the Japanese Society of Breast Cancer Screening, March 30, 2021, pp. 87-95 Summary of the Invention [Problem to be solved by the invention]

[0005] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to support the use of breast configurations. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described below can also be positioned as other problems. [Means for solving the problem]

[0006] A medical information processing device according to an embodiment includes a first acquisition unit that acquires a first breast configuration from a mammography image in accordance with a predetermined criterion, a second acquisition unit that acquires a second breast configuration different from the first breast configuration from the mammography image, and a display control unit that displays the first breast configuration and the second breast configuration on a display unit. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of a medical information processing system according to the first embodiment. [Diagram 2] FIG. 2 is a block diagram showing an example of the configuration of the X-ray diagnostic apparatus according to the first embodiment. [Diagram 3] FIG. 3 is a diagram for explaining an outline of a breast configuration according to the first embodiment. [Figure 4] FIG. 4 is a diagram for explaining an overview of processing by the medical image processing apparatus according to the first embodiment. [Diagram 5] FIG. 5 is a flowchart showing a series of processes performed by the medical image processing apparatus according to the first embodiment. [Figure 6A] FIG. 6A is a display example according to the first embodiment. [Figure 6B] FIG. 6B is a display example according to the first embodiment. [Figure 6C] FIG. 6C is a display example according to the first embodiment. [Figure 7A] FIG. 7A is a display example according to the second embodiment. [Figure 7B] FIG. 7B is a display example according to the second embodiment. [Figure 7C] FIG. 7C is a display example according to the third embodiment. [Figure 7D] FIG. 7D is a display example according to the third embodiment. [Figure 8] FIG. 8 is a diagram for explaining an overview of processing by the medical image processing apparatus according to the fourth embodiment. [Figure 9] FIG. 9 is a flowchart showing a series of processes performed by the medical image processing apparatus according to the fourth embodiment. [Figure 10A] FIG. 10A is a display example according to the fourth embodiment. [Figure 10B] FIG. 10B is a display example according to the fourth embodiment. [Figure 11] FIG. 11 is a flowchart showing a series of processes performed by the medical image processing apparatus according to the fifth embodiment. [Figure 12A] FIG. 12A is a conceptual diagram showing division into image groups according to the fifth embodiment. [Figure 12B] FIG. 12B is a conceptual diagram showing division into image groups according to the fifth embodiment. [Figure 13] FIG. 13 shows a display example according to the sixth embodiment. [Figure 14] FIG. 14 is a block diagram showing an example of the configuration of an X-ray diagnostic apparatus according to the sixth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, with reference to the attached drawings, the embodiments of the medical information processing device, the X-ray diagnostic device, the medical information processing method, and the medical information processing program will be described in detail. Note that the embodiments are not limited to the following description, and can be appropriately modified without departing from the spirit of the invention. In addition, in the drawings described below, the same reference numerals are used to designate parts having the same functions, and their description may be omitted.

[0009] (First embodiment) In the first embodiment, a medical information processing system 1 including a medical information processing device 30 will be described as an example. For example, as shown in Fig. 1, the medical information processing system 1 includes an X-ray diagnostic apparatus 10, a database 20, and the medical information processing device 30. Fig. 1 is a block diagram showing an example of the configuration of the medical information processing system 1 according to the first embodiment.

[0010] 1, an X-ray diagnostic apparatus 10, a database 20, and a medical information processing apparatus 30 are connected via a network 40. Here, the network 40 may be configured as a local network closed within a hospital, or may be a network via the Internet. For example, the network 40 includes a LAN (Local Area Network) and a WAN (Wide Area Network).

[0011] The X-ray diagnostic apparatus 10 is an apparatus for acquiring mammography images from a subject. A specific configuration example of the X-ray diagnostic apparatus 10 will be described later.

[0012] The database 20 is a storage device that stores various data, and is realized by computer equipment such as a server or a workstation. The database 20 may be a server of an information management system such as a Radiology Information System (RIS), a Hospital Information System (HIS), or a Picture Archiving and Communication System (PACS). For example, the database 20 includes an image storage device that stores mammography images collected by the X-ray diagnostic apparatus 10. Although a single database 20 is shown in FIG. 1, the database 20 may be realized by a combination of multiple storage devices.

[0013] The medical information processing device 30 supports the use of breast configurations obtained from mammography images through processing by the processing circuitry 35. For example, as shown in FIG. 1, the medical information processing device 30 has a communication interface 31, an input interface 32, a display 33, a memory 34, and a processing circuitry 35.

[0014] The communication interface 31 is composed of, for example, a network card such as a LAN card, a network adapter, etc. The communication interface 31 transmits and receives various information to and from devices connected via a network 40 under the control of a processing circuit 35.

[0015] The input interface 32 receives various input operations from the user, converts the received input operations into electrical signals, and outputs the electrical signals to the processing circuit 35. For example, the input interface 32 is realized by a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touchpad that performs input operations by touching the operation surface, a touch screen in which a display screen and a touchpad are integrated, a non-contact input circuit using an optical sensor, a voice input circuit, and the like. The input interface 32 may be configured as a tablet terminal or the like capable of wireless communication with the main body of the medical information processing device 30. The input interface 32 may also be a circuit that receives input operations from the user by motion capture. For example, the input interface 32 can receive the user's body movement, line of sight, and the like as input operations by processing signals acquired via a tracker and images collected about the user. The input interface 32 is not limited to only those that include physical operation parts such as a mouse and a keyboard. For example, an example of the input interface 32 also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the medical information processing device 30 and outputs this electrical signal to the processing circuit 35.

[0016] The display 33 displays various information. For example, under the control of the processing circuit 35, the display 33 displays mammography images captured by the X-ray diagnostic apparatus 10 and breast configurations obtained from the mammography images. For example, the display 33 displays a GUI (Graphical User Interface) for receiving various instructions and settings from a user via the input interface 32. For example, the display 33 is a liquid crystal display or a CRT (Cathode Ray Tube) display. The display 33 may be a desktop type, or may be configured as a tablet terminal or the like capable of wireless communication with the main body of the medical information processing apparatus 30. The display 33 is an example of a display unit.

[0017] 1, the medical information processing device 30 is described as having a display 33, but the medical information processing device 30 may have a projector instead of or in addition to the display 33. The projector can project onto a screen, wall, floor, etc. under the control of the processing circuit 35. As an example, the projector can also project onto any plane, object, space, etc. by projection mapping. Such a projector is an example of a display unit.

[0018] The memory 34 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, a hard disk, an optical disk, etc. For example, the memory 34 stores various data such as mammography images and breast configurations acquired from mammography images. The memory 34 also stores programs for enabling circuits included in the medical information processing device 30 to realize their functions. The memory 34 may be realized by a group of servers (cloud) connected to the medical information processing device 30 via a network 40.

[0019] The processing circuitry 35 controls the operation of the entire medical information processing device 30 by executing a receiving function 351, a first acquisition function 352, a second acquisition function 353, and a display control function 354. The first acquisition function 352 is an example of a first acquisition unit. The second acquisition function 353 is an example of a second acquisition unit. The display control function 354 is an example of a display control unit.

[0020] For example, the processing circuitry 35 reads out from the memory 34 and executes a program corresponding to the receiving function 351 to receive a mammography image captured by the X-ray diagnostic apparatus 10 and store it in the memory 34. For example, the receiving function 351 controls the operation of the communication interface 31 to receive a mammography image stored in the database 20 via the network 40. Alternatively, the receiving function 351 may receive the mammography image directly from the X-ray diagnostic apparatus 10 without going through the database 20.

[0021] Processing circuitry 35 also reads out from memory 34 a program corresponding to first acquisition function 352 and executes it to acquire a first breast configuration from a mammography image according to a predetermined standard. Processing circuitry 35 also reads out from memory 34 a program corresponding to second acquisition function 353 and executes it to acquire a second breast configuration different from the first breast configuration from a mammography image. Processing circuitry 35 also reads out from memory 34 a program corresponding to display control function 354 and executes it to display the first breast configuration and the second breast configuration on the display unit. Details of the processing by first acquisition function 352, second acquisition function 353, and display control function 354 will be described later.

[0022] 1, each processing function is stored in the form of a program executable by a computer in a memory 34. The processing circuitry 35 is a processor that realizes a function corresponding to each program by reading and executing the program from the memory 34. In other words, the processing circuitry 35 in a state in which a program has been read has a function corresponding to the read program.

[0023] 1, the receiving function 351, the first acquiring function 352, the second acquiring function 353, and the display control function 354 are realized by a single processing circuit 35. However, the processing circuit 35 may be configured by combining a plurality of independent processors, and each processor may execute a program to realize the functions. Furthermore, each processing function of the processing circuit 35 may be realized by being appropriately distributed or integrated in a single or a plurality of processing circuits.

[0024] The processing circuitry 35 may also realize functions by using a processor of an external device connected via a network 40. For example, the processing circuitry 35 reads out and executes a program corresponding to each function from the memory 34, and realizes each function shown in FIG. 1 by using a server group (cloud) connected to the medical information processing device 30 via the network 40 as a computational resource.

[0025] Next, an example of the configuration of the X-ray diagnostic apparatus 10 will be described with reference to Fig. 2. The X-ray diagnostic apparatus 10 shown in Fig. 2 is a mammography apparatus that photographs the breasts of a subject P.

[0026] The X-ray diagnostic apparatus 10 shown in Fig. 2 has a base 101 and a stand 102. The stand 102 is erected on the base 101 and supports an imaging table 103, a compression plate 104, an X-ray tube 105, an X-ray aperture 106, an X-ray detector 107, and a signal processing circuit 108. Here, the stand 102 supports the imaging table 103, the compression plate 104, the X-ray detector 107, and the signal processing circuit 108 so as to be movable in the vertical direction.

[0027] The imaging table 103 is a table that supports the breast of the subject P, and has a support surface on which the breast is placed. The compression plate 104 is disposed above the imaging table 103, and is provided so as to face the imaging table 103 in parallel. Here, the compression plate 104 is provided so as to be movable in a direction toward and away from the imaging table 103. For example, the compression plate 104 compresses the breast supported on the imaging table 103 by moving in a direction approaching the imaging table 103. The breast compressed by the compression plate 104 is spread thinly, and the overlap of the mammary glands within the breast is reduced.

[0028] The X-ray tube 105 is a vacuum tube having a cathode (filament) that generates thermoelectrons and an anode (target) that generates X-rays upon impact of the thermoelectrons. The X-ray tube 105 generates X-rays by irradiating thermoelectrons from the cathode to the anode using a high voltage supplied from the X-ray high voltage device 110.

[0029] The X-ray aperture 106 is disposed between the X-ray tube 105 and the compression plate 104, and controls the X-rays generated by the X-ray tube 105. For example, the X-ray aperture 106 has a collimator that narrows the irradiation range of the X-rays, and a filter that adjusts the X-rays.

[0030] The collimator in the X-ray aperture 106 has, for example, four slidable aperture blades, and by sliding these aperture blades, the X-rays generated by the X-ray tube 105 are narrowed down and irradiated onto the breast. Here, the aperture blades are plate-shaped members made of lead or the like, and are provided near the X-ray irradiation port of the X-ray tube 105 in order to adjust the irradiation range of the X-rays.

[0031] The filter in the X-ray aperture 106 changes the radiation quality of the transmitted X-rays depending on its material and thickness, in order to reduce the radiation dose to the subject and improve image quality, thereby reducing soft ray components that are easily absorbed by the subject and reducing high energy components that cause a decrease in image contrast. In addition, the filter changes the dose and irradiation range of the X-rays depending on its material, thickness, position, etc., and attenuates the X-rays so that the X-rays irradiated to the subject P have a predetermined distribution.

[0032] For example, the X-ray aperture 106 has a driving mechanism such as a motor and an actuator, and controls the irradiation of X-rays by operating the driving mechanism under the control of the processing circuitry 115 described later. For example, the X-ray aperture 106 applies a driving voltage to the driving mechanism in response to a control signal received from the processing circuitry 115, thereby adjusting the opening of the aperture blades of the collimator, and controls the irradiation range of the X-rays irradiated to the subject P. Also, for example, the X-ray aperture 106 applies a driving voltage to the driving mechanism in response to a control signal received from the processing circuitry 115, thereby adjusting the position of the filter, and thereby controlling the distribution of the dose of the X-rays irradiated to the subject P.

[0033] The X-ray detector 107 is, for example, an X-ray flat panel detector (FPD) having detection elements arranged in a matrix. The X-ray detector 107 detects X-rays irradiated from the X-ray tube 105 and transmitted through the breast of the subject P, and outputs a detection signal corresponding to the detected X-ray amount to a signal processing circuit 108. The X-ray detector 107 may be an indirect conversion type detector having a grid, a scintillator array, and a photosensor array, or may be a direct conversion type detector having a semiconductor element that converts incident X-rays into an electric signal.

[0034] For example, the X-ray detector 107 detects an X-ray pulse irradiated from the X-ray tube 105, and generates a detection signal corresponding to the detected X-ray amount. Here, the X-ray detector 107 holds the generated detection signal. After irradiating the X-ray pulse, the X-ray detector 107 outputs the detection signal to the signal processing circuit 108. Then, the signal processing circuit 108 generates projection data based on the detection signal output from the X-ray detector 107, and stores the projection data in the memory 114.

[0035] As shown in FIG. 2, the X-ray diagnostic apparatus 10 further includes an elevator drive device 109, an X-ray high voltage device 110, a communication interface 111, an input interface 112, a display 113, a memory 114, and a processing circuit 115.

[0036] The lifting drive device 109 is connected to the imaging table 103 and the compression plate 104. For example, the lifting drive device 109 lifts and lowers the imaging table 103 in the up-down direction. Also, for example, the lifting drive device 109 lifts and lowers the compression plate 104 in the up-down direction (the direction toward and away from the imaging table 103). For example, the lifting drive device 109 has a drive mechanism such as a motor and an actuator, and controls the lifting and lowering of the imaging table 103 and the compression plate 104 by operating the drive mechanism under the control of the processing circuit 115.

[0037] The X-ray high voltage device 110 supplies a high voltage to the X-ray tube 105 under the control of the processing circuit 115. For example, the X-ray high voltage device 110 has electric circuits such as a transformer and a rectifier, and includes a high voltage generating device that generates a high voltage to be applied to the X-ray tube 105, and an X-ray control device that controls the output voltage according to the X-rays irradiated by the X-ray tube 105. The high voltage generating device may be of a transformer type or an inverter type.

[0038] Detailed description will be omitted for the communication interface 111, the input interface 112, the display 113, and the memory 114. For example, the communication interface 111, the input interface 112, the display 113, and the memory 114 can be configured in the same manner as the communication interface 31, the input interface 32, the display 33, and the memory 34 shown in FIG.

[0039] The processing circuitry 115 controls the overall operation of the X-ray diagnostic apparatus 10 by executing an acquisition function 1151 and an output function 1152. The acquisition function 1151 is an example of an acquisition unit. The output function 1152 is an example of a display control unit.

[0040] For example, the processing circuitry 115 reads out from the memory 114 a program corresponding to the acquisition function 1151 and executes it to capture an image of the subject P to acquire a mammography image. For example, the acquisition function 1151 acquires a plurality of projection data obtained by changing the X-ray irradiation angle with respect to the breast of the subject P, and reconstructs a plurality of mammography images (slices) from the plurality of projection data. Note that the mammography image of the embodiment is an image of the subject P captured for the purpose of medical diagnosis, examination, research, and the like. The mammography image of the embodiment is, for example, an image in the craniocaudal (CC) direction or the mediolateral oblique (MLO) direction. Note that the device configuration of FIG. 2 is merely an example, and any X-ray mammography device or tomosynthesis device capable of acquiring a mammography image can be adopted as the X-ray diagnostic device 10.

[0041] Furthermore, the processing circuitry 115 reads out from the memory 114 a program corresponding to the output function 1152 and executes it to output the mammography image collected by the collection function 1151. For example, the output function 1152 causes the display 113 to display the mammography image. Also, for example, the output function 1152 transmits the mammography image to the database 20 via the network 40 for storage. Alternatively, the output function 1152 may transmit the mammography image to the medical information processing device 30.

[0042] In the X-ray diagnostic apparatus 10 shown in Fig. 2, each processing function is stored in the form of a program executable by a computer in the memory 114. The various circuits shown in Fig. 2 are processors that realize the function corresponding to each program by reading and executing the program from the memory 114. In other words, the circuit in the state where a program has been read has the function corresponding to the read program.

[0043] 2, the collection function 1151 and the output function 1152 are realized by a single processing circuit 115. However, the processing circuit 115 may be configured by combining a plurality of independent processors, and each processor may execute a program to realize the function. Furthermore, each processing function of the processing circuit 115 may be realized by being appropriately distributed or integrated into a single or a plurality of processing circuits.

[0044] The processing circuitry 115 may also realize functions by using a processor of an external device connected via the network 40. For example, the processing circuitry 115 reads out and executes a program corresponding to each function from the memory 114, and realizes each function shown in FIG. 2 by using a server group (cloud) connected to the X-ray diagnostic apparatus 10 via the network 40 as a computational resource.

[0045] The above describes the medical information processing system 1 including the X-ray diagnostic apparatus 10, the database 20, and the medical information processing apparatus 30. With this configuration, the medical information processing apparatus 30 supports the use of breast reconstruction.

[0046] First, an overview of the breast configuration will be described with reference to Fig. 3. In the following, as an example, a mammography image in the mediolateral oblique direction (MLO) will be illustrated.

[0047] As shown in mammography image I11 in Fig. 3, various tissues appear in a mammography image of the breast of subject P. Note that in Fig. 3, various tissues are defined and explained in accordance with the guidelines of the Japan Breast Cancer Screening Quality Control Center, a non-profit organization, but the definitions of tissues can be changed as appropriate.

[0048] For example, a mammography image I11 includes a breast A11 and a pectoralis major muscle A14. The breast A11 includes an area A12 where mammary gland tissue originally existed, and an area A13 where mammary glands currently exist. Area A13 is the sum of areas with density equal to or greater than that of the pectoralis major muscle. In the above guidelines, the ratio of area A13 to area A12 is defined as the mammary gland density.

[0049] Breast configuration is, for example, a category for classifying the amount of breast density. For example, the above guidelines define four classifications of breast configuration: "fatty," "scattered breast," "heterogeneous dense," and "extremely dense." More specifically, the above guidelines stipulate the following criteria for determining (classifying) breast configuration from breast density: breast density of less than 10% is "fatty," 10% to less than 50% is "scattered breast," 50% to less than 80% is "heterogeneous dense," and 80% or more is "extremely dense." The numerical values ​​that serve as criteria for determining breast configuration, such as "10%, "50%," and "80%," are also referred to as cutoff values.

[0050] In the following description, the "area where mammary gland tissue originally existed" such as area A12 in Fig. 3 will also be referred to as the mammary gland tissue area. Also, the "sum of areas with a density equal to or greater than that of the pectoral muscle" such as area A13 will also be referred to as the mammary gland area.

[0051] Conventionally, breast configuration has been judged by visual inspection by a radiologist. In addition, various methods for automatically judging breast configuration have been studied. For example, Non-Patent Document 1 proposes an automatic method for judging breast configuration based on mammary gland density. In addition, Non-Patent Document 2 sets a unique cutoff value for an individual or facility performing radiology reading, rather than a predefined cutoff value, as a cutoff value used when calculating breast configuration from the mammary gland mass ratio, so that the breast configuration automatically judged by software approaches the breast configuration judged visually by the individual or facility performing radiology reading.

[0052] By performing an automatic determination so as to approximate the breast configuration determined by visual inspection, the breast configuration can be made into information that is easy for users such as doctors to use. In other words, since the final diagnosis is made by the user, it is meaningful to determine the breast configuration so as to provide information that is close to the user's physical sensation. However, when performing such an automatic determination, there may be variation in the results of the breast configuration determination depending on the individual or facility performing the image interpretation, and it may be difficult to determine how reliable the presented breast configuration can be.

[0053] Therefore, the medical information processing device 30 according to the first embodiment supports the use of breast configurations through processing by the processing circuitry 35, which will be described in detail below. Specifically, the medical information processing device 30 supports the use of breast configurations by acquiring a first breast configuration from a mammography image according to a predetermined standard, acquiring a second breast configuration different from the first breast configuration from the mammography image, and displaying the first breast configuration and the second breast configuration on a display unit.

[0054] First, an overview of the processing of the medical information processing device 30 will be described with reference to Fig. 4. In Fig. 4, ROM 34a, RAM 34b, and storage unit 34c are shown as examples of memory 34. ROM 232 is composed of non-volatile memory and stores various programs, data, etc. RAM 233 is composed of volatile memory and temporarily stores programs and data currently being executed. Storage unit 34c is composed of, for example, a HDD (Hard Disk Drive) and stores various programs and data.

[0055] The medical information processing apparatus 30 according to the first embodiment includes, as its functional configuration, a first mammary gland density acquisition unit 352a, a first breast configuration acquisition unit 352b, a correction information acquisition unit 353a, a second breast configuration acquisition unit 353b, and a display control unit 354a, as shown in FIG. 4. For example, the first mammary gland density acquisition unit 352a and the first breast configuration acquisition unit 352b are realized by the processing circuitry 35 reading a program corresponding to the first acquisition function 352 from the memory 34 and executing it. Similarly, the correction information acquisition unit 353a and the second breast configuration acquisition unit 353b are realized by the processing circuitry 35 reading a program corresponding to the second acquisition function 353 from the memory 34 and executing it. Similarly, the display control unit 354a is realized by the processing circuitry 35 reading a program corresponding to the display control function 354 from the memory 34 and executing it.

[0056] The first mammary gland density acquisition unit 352a acquires the mammary gland density from the mammography image. The mammary gland density acquired by the first mammary gland density acquisition unit 352a from the mammography image is also referred to as the first mammary gland density.

[0057] In the following description, values ​​obtained from mammography images and used to obtain breast configuration are referred to as calculated values. The term calculated value does not limit the method of acquisition, and may be the result of measuring a mammography image, the result of calculation processing based on a mammography image or measurement results, or a value obtained by other methods. The first breast density is an example of a calculated value obtained from a mammography image.

[0058] The first breast configuration acquisition unit 352b acquires a breast configuration based on the first mammary gland density according to a predetermined standard. For example, the first breast configuration acquisition unit 352b acquires a breast configuration according to the above-mentioned guidelines. The breast configuration acquired by the first breast configuration acquisition unit 352b according to the predetermined standard is also referred to as the first breast configuration.

[0059] The correction information acquisition unit 353a acquires correction information used to correct the first mammary gland density. The second breast configuration acquisition unit 353b acquires a second mammary gland density by applying the correction information to the first mammary gland density, and acquires a breast configuration based on the second mammary gland density. The second mammary gland density is an example of a corrected calculated value.

[0060] Here, applying the correction information to the first breast density to obtain the second breast density is a step not included in the above-mentioned guideline. That is, the breast configuration obtained by the second breast configuration obtaining unit 353b based on the second breast density is not in accordance with a predetermined standard, and is a breast configuration different from the above-mentioned first breast configuration. The breast configuration obtained by the second breast configuration obtaining unit 353b and different from the first breast configuration is also described as the second breast configuration. The display control unit 354a controls the display of the obtained first breast configuration and second breast configuration on the display 33.

[0061] Next, a more detailed specific example of the processing of the medical image processing device 30 will be described with reference to the flowchart shown in FIG.

[0062] First, prior to the processing of step S101, a mammography image is acquired. As described above, processing circuitry 35 can receive a mammography image via network 40 and store it in memory 34 by reading and executing a program corresponding to receiving function 351 from memory 34. For example, based on an instruction to acquire an image from a user via input interface 32, processing circuitry 35 acquires a mammography image to be interpreted by searching for images stored in database 20 using an identifier (also called an "ID") that can uniquely identify the image.

[0063] In step S101, the first mammary gland density acquisition unit 352a acquires a first mammary gland density. For example, the first mammary gland density acquisition unit 352a estimates a mammary gland tissue region and a mammary gland region in the acquired mammography image by a machine learning model (not shown). Then, the first mammary gland density is acquired by dividing the area of ​​the mammary gland region by the area of ​​the mammary gland tissue region.

[0064] The machine learning model used here is stored in, for example, the database 20. In this case, the first mammary gland density acquisition unit 352a can appropriately read and use the machine learning model via the network 40. The machine learning model is constructed by machine learning a convolutional neural network (CNN) so that, for example, a plurality of data pairs of an image, a mammary gland tissue region, and a mammary gland region are used as teacher data, an image is input, and a mammary gland tissue region and a mammary gland region are output. Here, the machine learning model may be constructed using a method other than CNN, such as a deep neural network (DNN), a support vector machine (SVM), or a vision transformer (ViT). The machine learning model may also be a combination of a machine learning model that estimates a mammary gland tissue region and a machine learning model that estimates a mammary gland region. The machine learning model that estimates a mammary gland region may estimate a threshold value of a luminance value for determining a mammary gland region, and may acquire a region equal to or greater than the estimated threshold value as a mammary gland region. The machine learning model may also be estimated using an image analysis method such as a discriminant analysis method. Furthermore, instead of estimating the mammary gland region and mammary gland tissue region using a machine learning model, information previously assigned to the image to be acquired may be stored in the database 20 and the mammary gland region and mammary gland tissue region may be acquired from the database 20.

[0065] In step S102, the first breast configuration acquisition unit 352b acquires the first breast configuration according to a predetermined standard. For example, the first breast configuration acquisition unit 352b acquires the first breast configuration by applying a cutoff value to the first breast density according to the above-mentioned guidelines. That is, the first breast configuration acquisition unit 352b compares the first breast density with the cutoff value, and determines that the first breast density is "fatty" if it is less than 10%, "scattered breast" if it is 10% or more and less than 50%, "heterogeneous high density" if it is 50% or more and less than 80%, and "extremely high density" if it is 80% or more.

[0066] In step S103, the correction information acquisition unit 353a acquires the correction information. In step S104, the second breast configuration acquisition unit 353b acquires the second breast density by correcting the first breast density based on the correction information, and acquires the second breast configuration by applying the same cutoff value as in step S102 to the second breast density.

[0067] For example, the second breast configuration acquisition unit 353b acquires the second mammary gland density by adding a correction value, which is a constant, to the first mammary gland density. In this case, the correction information acquisition unit 353a can acquire the correction value as correction information, for example, from the database 20. Note that the correction information may include text information explaining the content of the correction (for example, "add a correction value to mammary gland density") as information related to the correction other than the correction value. Note that the correction method is not limited to adding a correction value, and may be, for example, subtraction, multiplication, division, or a combination of these.

[0068] Also, as information on correction other than the correction value, information on the application method of the correction value may be acquired, and the first breast density may be corrected by the acquired application method. Here, the information on the application method of the correction value is, for example, information such as "addition", "multiplication", "subtraction" or "division". Alternatively, as information on the application method of the correction value, a linear or nonlinear correction formula for calculating the corrected breast density from the pre-correction breast density may be stored, acquired and applied. Also, the correction information may be in any form as long as it is information that allows the corrected breast density to be calculated from the pre-correction breast density. For example, the correction information may be a look-up table that allows the corrected breast density to be looked up from the pre-correction breast density.

[0069] In step S105, the display control unit 354a causes the display unit to display the first breast configuration and the second breast configuration. For example, the display control unit 354a causes the display 33 to display the first breast configuration and the second breast configuration together.

[0070] A display example of the first and second breast configurations by the display control unit 354a will be described with reference to Fig. 6A. Fig. 6A is a display example when the first and second breast configurations are displayed together. For example, the display control unit 354a displays a mammography image I12 to be interpreted and a presentation area R11 of the breast configuration on the display screen D.

[0071] Then, the display control unit 354a displays the first breast configuration and the second breast configuration in text format in the presentation region R11. In the display example of Fig. 6A, "Before correction: fatty" is displayed as the first breast configuration, and "After correction: scattered breast" is displayed as the second breast configuration. That is, the display example of Fig. 6A indicates that the first breast configuration acquired according to a predetermined standard without performing correction using correction information is "fatty", and the second breast configuration acquired based on the second breast density obtained by correcting the first breast density is "scattered breast".

[0072] The display control unit 354a may switch between the first and second breast configurations and display them in the presentation area R11 of the breast configuration. FIG. 6B and FIG. 6C are display examples when the first and second breast configurations are switched. In the display examples of FIG. 6B and FIG. 6C, whether to display the first breast configuration (breast configuration before correction) or the second breast configuration (breast configuration after correction) can be switched by a user's instruction to the check box R12. In FIG. 6B, the check box R12 is not checked to instruct correction, so the display control unit 354a displays the first breast configuration in the presentation area R11 of the breast configuration. On the other hand, in FIG. 6C, the check box R12 is checked to instruct correction, so the display control unit 354a displays the second breast configuration in the presentation area R11 of the breast configuration.

[0073] For example, the display control unit 354a acquires an instruction to switch the screen via a check box for screen switching based on a mouse operation by the user, and switches the display of the presentation area R11 of the breast configuration. Note that the screen may be switched by a radio button, a pull-down menu, a switching button, or the like, other than the check box. Also, an instruction to switch the screen may be acquired by any user interface, such as a keyboard, a touch panel, a non-contact sensor, or voice recognition, other than the mouse operation. Also, other than based on a user instruction, the screen may be automatically switched according to a predetermined setting, such as switching at regular intervals, for example.

[0074] The display screen D in Figures 6A to 6C is merely an example, and various modifications are possible. For example, the display control unit 354a may present the breast configurations by displaying them as icons, abbreviations, numbers, or by arranging arrows on an axis showing the four classifications of breast configurations, in addition to displaying them as text as shown in Figures 6A to 6C. In addition, the display manner of the first breast configuration and the second breast configuration may be different.

[0075] The display control unit 354a may further display information regarding the difference between the first breast configuration and the second breast configuration. The information regarding the difference is, for example, information indicating the difference, and may include basic information before the difference is acquired. For example, the display control unit 354a may change the display mode of the information related to the breast configuration based on the state of the difference between the first breast configuration and the second breast configuration. For example, when the difference between the two breast configurations satisfies a predetermined condition, the display control unit 354a may display information notifying the user of that fact. For example, when the two breast configurations are different, the display control unit 354a may notify the user by displaying an alert or highlighting the first breast configuration. Note that the predetermined condition is not limited to the case where the two breast configurations are different, and may be the case where the two breast configurations differ by two or more stages.

[0076] Although an example in which the first breast configuration and the second breast configuration are displayed unconditionally has been described, the display control unit 354a may display the two breast configurations only when the two breast configurations do not match. That is, the display control unit 354a may display only the second breast configuration (or only the first breast configuration) when the two breast configurations match. Furthermore, when the two breast configurations match, the display control unit 354a may display information indicating that the breast configurations before and after correction match together with the second breast configuration (or the first breast configuration) as information regarding the difference between the first breast configuration and the second breast configuration.

[0077] As described above, the first acquisition function 352 according to the first embodiment acquires a first breast configuration from a mammography image according to a predetermined criterion. The second acquisition function 353 acquires a second breast configuration different from the first breast configuration from the mammography image. The display control function 354 causes the display unit to display the first breast configuration and the second breast configuration. This allows the medical information processing device 30 according to the first embodiment to support the use of the breast configuration.

[0078] For example, the second breast configuration is acquired based on the second breast density obtained by correcting the first breast density. In this case, the second breast configuration can be useful information close to the user's bodily sensation, but may vary depending on the content of the correction. Here, the user can judge how reliable the second breast density is by referring to the first breast configuration acquired according to a predetermined standard. For example, if there is no difference between the first breast configuration and the second breast configuration, it can be determined that the reliability of the breast configuration is high. On the other hand, if there is a difference between the first breast configuration and the second breast configuration, appropriate measures can be taken, such as instructing to reacquire the breast configuration or referring to other types of medical data, so as not to rely too much on the breast configuration in making a diagnosis.

[0079] (Modification of the first embodiment) Next, a modified example of the first embodiment will be described. In the first embodiment, an example has been described in which a second mammary gland density is obtained by correcting a first mammary gland density, and a second breast configuration is obtained from the second mammary gland density. That is, in the first embodiment, an example has been described in which the mammary gland density is the correction target among the calculated values ​​used to obtain the breast configuration. However, the calculated value to be corrected is not limited to this. That is, the second breast configuration acquisition unit 353b may correct a calculated value other than the mammary gland density calculated in the process of obtaining the breast configuration from a mammography image, and may acquire the second breast configuration by correcting the calculated value.

[0080] As an example, the area of ​​the mammary gland region will be described as the calculated value to be corrected. Below, the differences in processing from the first embodiment when the area of ​​the mammary gland region is the correction target will be described.

[0081] In step S101, the first mammary gland density acquisition unit 352a of this modification acquires the area of ​​the mammary gland region as a predetermined intermediate value to be corrected in addition to the first mammary gland density. In step S103, the correction information acquisition unit 353a acquires correction information for correcting the area of ​​the mammary gland region from the database 20. Thereafter, in step S104, the second breast configuration acquisition unit 353b performs correction by adding the correction value acquired by the correction information acquisition unit 353a to the area of ​​the mammary gland region. Then, the second breast configuration acquisition unit 353b acquires the second breast configuration by dividing the corrected mammary gland region by the mammary gland tissue region. Note that the correction target in this modification is not limited to the area of ​​the mammary gland region, and may be, for example, the area of ​​the mammary gland tissue region.

[0082] As in the first embodiment, in this modification, in addition to the breast configuration (second breast configuration) corrected to be closer to the visual judgment, the breast configuration (first breast configuration) judged according to a predetermined standard is further displayed. This has the effect of making it easier to judge how much the breast configuration (second breast configuration) that has been brought closer to the visual judgment can be trusted.

[0083] Second embodiment Next, a second embodiment will be described. In the second embodiment, an example in which correction information is displayed in addition to the first and second breast configurations will be described. In the following description, the same configurations and processes as those in the first embodiment are given the same reference numerals, and the description will be omitted.

[0084] In step S105 of the flowchart shown in Fig. 5, the display control unit 354a according to the second embodiment displays the correction information on the display screen in addition to the first and second breast configurations. For example, the display control unit 354a displays a correction value as the correction information. Hereinafter, a display example according to the second embodiment will be described with reference to Figs. 7A to 7B.

[0085] For example, as shown in Fig. 7A, the display control unit 354a displays a mammography image I12 to be interpreted, a presentation area R11 for breast configuration, and a presentation area R13 for correction information on the display screen D. In the example of Fig. 7A, the display control unit 354a displays, in the presentation area R13 for correction information, a correction value of "correction value X:5", a correction formula of "corrected breast density = breast density + X", and text information explaining the content of the correction of "add correction value to breast density". Note that the correction formula and the text information explaining the content of the correction are examples of information relating to the method of applying the correction value.

[0086] The display control unit 354a may display all or a part of various correction information such as correction values, correction formulas, text information explaining the correction contents, etc. The display control unit 354a may also switch between the first and second breast configurations described in Fig. 6B to Fig. 6C and display the correction information.

[0087] FIG. 7B is another display example according to the second embodiment. FIG. 7B shows an example in which an area enlargement process of a mammary gland region is performed as a correction process for acquiring a second breast configuration. For example, the correction information acquisition unit 353a acquires a predetermined correction value, and the second breast configuration acquisition unit 353b adds or multiplies the correction value to the area of ​​the mammary gland region acquired from the mammography image I12 to be interpreted. Note that such an area enlargement process may be performed multiple times in response to a request from a user, for example. Furthermore, the second breast configuration acquisition unit 353b acquires a mammary gland density by dividing the area of ​​the mammary gland region after the area enlargement process by the area of ​​the mammary gland tissue region, and acquires the second breast configuration by comparing the acquired mammary gland density with a cutoff value.

[0088] Here, in Fig. 7B, the correction information displayed is that the area enlargement process has been performed "n1 times", that the calculation formula for the mammary gland density before the correction was "x1 pixel / y1 pixel", and that the calculation formula for the mammary gland density after the correction was "x2 pixel / y1 pixel", etc. In other words, Fig. 7B shows that the mammary gland region has been enlarged from "x1 pixel" to "x2 pixels" by the area enlargement process.

[0089] The display control unit 354a may display the mammary gland region before and after the correction on the mammography image I12 to be interpreted. For example, when the area of ​​the mammary gland region is corrected as described above, the display control unit 354a displays the mammography image I12 on the display 33, and superimposes the mammary gland region whose area has not been corrected and the mammary gland region whose area has been corrected on the mammography image I12 so that they can be distinguished. For example, the display control unit 354a displays the mammary gland region before the correction as shown by the solid line on the mammography image I12 in FIG. 7B, and displays the mammary gland region after the area enlargement process as shown by the dashed line.

[0090] Although the area enlargement process has been described as an example of the process for the area of ​​the mammary gland region, the embodiment is not limited thereto. For example, the present invention can be similarly applied to a process for reducing the area of ​​the mammary gland region acquired from the mammography image I12 to be interpreted.

[0091] According to this embodiment, in addition to the effects of the first embodiment, it is possible to understand what corrections were applied when approaching a visual judgment, and it is easier to determine how reliable the breast configuration (second breast configuration) that has been brought closer to a visual judgment can be.

[0092] (Third embodiment) Next, a third embodiment will be described. In the third embodiment, an example in which mammary gland density is displayed in addition to the first breast configuration, the second breast configuration, and the correction information will be described. In the following description, the same configurations and processes as those in the first and second embodiments are given the same reference numerals, and the description will be omitted.

[0093] In step S105 of the flow chart shown in FIG. 5, the display control unit 354a according to the third embodiment displays the mammary gland density on the display screen in addition to the first breast configuration, the second breast configuration, and the correction information acquired in step S105. For example, in step S105, the display control unit 354a displays the first breast configuration acquired in step S102, the second breast configuration acquired in step S104, and the correction information acquired in step S103 together on the display 33. Furthermore, in step S105, the display control unit 354a displays the first mammary gland density acquired in step S101 and the second mammary gland density acquired in step S104 in a comparative manner. For example, the display control unit 354a displays the first mammary gland density and the second mammary gland density together, or switches between them. Hereinafter, a display example according to the third embodiment will be described with reference to FIGS. 7C to 7D.

[0094] For example, the display control unit 354a displays the values ​​of the first and second mammary gland densities in text form, with identifiers for "before correction" and "after correction." Fig. 7C is an example of a display screen when displaying the first and second mammary gland densities in addition to the first and second breast configurations and correction information.

[0095] For example, as shown in Fig. 7C, the display control unit 354a displays a mammography image I12 to be interpreted, a presentation area R11 for breast configuration, a presentation area R13 for correction information, and a presentation area R14 for mammary gland density on the display screen D. In the example of Fig. 7C, the presentation area R14 for mammary gland density displays "before correction: 8%" as the first mammary gland density and "after correction: 13%" as the second mammary gland density.

[0096] The display screen D shown in Fig. 7C is merely an example, and various modifications are possible. For example, the display of the mammary gland density in the presentation area R14 may be performed by displaying an arrow on an axis indicating the mammary gland density, an icon, a graph, or the like, in addition to displaying it in text. In addition, the display of the mammary gland density may be performed by combining these pieces of information.

[0097] FIG. 7D is an example of a display screen using an axis showing breast density. For example, the display control unit 354a displays an axis showing the breast density value (0 to 100) and arrows pointing to the first breast density and the second breast density in a state where they can be compared in the presentation region R15. Furthermore, the axis showing breast density is associated with breast configurations (four classifications: "fatty", "scattered breast", "unevenly dense", and "extremely dense"), so that the two arrows point to the first breast configuration and the second breast configuration, respectively. The display control unit 354a may also display a cutoff value on the axis showing breast density. For example, as shown in FIG. 7D, the display control unit 354a displays a scale showing the cutoff value on the axis showing breast density. The display shown in FIG. 7D makes it possible to simultaneously grasp the increase or decrease in the value before and after correction and the change in breast density, and to grasp how close the breast density after correction is to the boundary of the breast configuration.

[0098] In the example of Fig. 7D, since the mammary gland density and the breast configuration are displayed in the display area R15, the display area R11 of the breast configuration is not displayed, but the display area R11 of the breast configuration may be displayed separately. Also, the display of the correction information is not essential, and the display of the display area R13 of the correction information may be omitted as appropriate.

[0099] As described above, in this embodiment, in addition to the effects of the first embodiment, a mammary gland density (first mammary gland density) quantitatively determined according to a predetermined standard and a mammary gland density (second mammary gland density) corrected so that the breast configuration approaches the visual determination are displayed together. This has the effect of making it possible to grasp how close the corrected mammary gland density is to the boundary of the breast configuration, and making it easier to determine how reliable the breast configuration (second breast configuration) that has been brought closer to the visual determination can be.

[0100] (Fourth embodiment) Next, a fourth embodiment will be described. In the first embodiment, an example in which correction information is acquired from the database 20 is described, whereas in this embodiment, an example in which a third breast configuration is acquired and correction information is acquired using the acquired breast configuration is described. In the following description, the same reference numerals are used for configurations and processes similar to those in the first to third embodiments, and description thereof will be omitted.

[0101] First, an overview of the processing of the medical information processing device 30 according to the fourth embodiment will be described with reference to Fig. 8. Compared with the medical information processing device 30 according to the first embodiment shown in Fig. 4, the medical information processing device 30 according to the fourth embodiment is different in that it includes a third mammary gland density acquisition unit 353c and a correction information acquisition unit 353d instead of the correction information acquisition unit 353a. The third mammary gland density acquisition unit 353c and the correction information acquisition unit 353d are realized by the processing circuitry 35 reading out a program corresponding to the second acquisition function 353 from the memory 34 and executing it.

[0102] The third breast density acquisition unit 353c acquires multiple mammography images other than the mammography image to be interpreted from the database 20, and acquires the breast density of each mammography image (hereinafter, the third breast density). The correction information acquisition unit 353d acquires from the user breast configuration findings for the multiple mammography images acquired by the third breast density acquisition unit 353c, and acquires correction information based on the degree of agreement with the third breast configuration.

[0103] Next, the processing of the medical image processing device 30 according to the fourth embodiment will be described in more detail with reference to the flowchart shown in Fig. 9. The processing of steps S101, S102, S104, and S105 shown in Fig. 9 is similar to the processing of steps S101, S102, S104, and S105 shown in Fig. 5, and therefore the description thereof will be omitted.

[0104] In step S201, the third mammary gland density acquisition unit 353c acquires a plurality of mammography images and a third mammary gland density corresponding to each image from the database 20. Note that the third mammary gland density can be acquired, for example, in the same manner as the first mammary gland density, by estimating a mammary gland tissue region and a mammary gland region using a machine learning model (not shown) and dividing the area of ​​the mammary gland region by the area of ​​the mammary gland tissue region.

[0105] In step S202, the correction information acquisition unit 353d calculates correction information that maximizes the degree of agreement between the third breast configuration and the breast configurations separately assigned to the multiple mammography images, and acquires this as the correction information to be used in the process of step S104. Here, the third breast configuration is acquired by correcting the third breast density acquired in step S201 based on the correction information candidate, and the breast configurations separately assigned to the multiple mammography images are acquired in step S201. For example, when the correction method is addition, the third breast density is updated by adding a correction value candidate as a correction information candidate to the third breast density of each of the multiple mammography images. Then, the degree of agreement between the third breast configuration corresponding to the updated third breast density and the separately assigned breast configuration is calculated. This process is repeated, and the candidate value that maximizes the degree of agreement is acquired as the correction value. That is, the correction information acquisition unit 353d acquires multiple third breast configurations by applying correction information candidates to multiple third breast densities, and acquires the correction information candidate that maximizes the degree of match between the multiple third breast configurations and the separately assigned breast configuration as the correction information shown in step S202.

[0106] The correction information and the correction method here are the same as the correction information and the correction method described in the first embodiment. The method of acquiring the third breast configuration is the same as the method of acquiring the second breast configuration described in the first embodiment. The separately assigned breast configuration is, for example, a breast configuration determined by visual inspection at the user's facility. The separately assigned breast configuration is not limited to the user's facility, and may be a breast configuration determined at another facility or multiple facilities.

[0107] The degree of match may be, for example, the number or percentage of images with matching breast configurations. In addition, the degree of match may be greater than or equal to a predetermined value, within a predetermined range, or the like, other than the maximum degree of match.

[0108] The processes of steps S201 and S202 do not need to be performed every time a mammography image to be interpreted is obtained. Therefore, for example, the correction information calculated when the process is performed for the first time may be stored in the storage unit 34c, and the correction information may be read from the storage unit 34c and used from the second time onward. Also, for example, the processes of steps S201 and S202 may be performed and the correction information updated when a change is made to a group of mammography images to which a breast configuration is separately assigned and a predetermined condition is satisfied. In addition, the correction information may be updated when a mammography image to which a breast configuration is assigned is newly added, when the assigned information is changed, or when the number or ratio of additions or changes exceeds a certain amount. Also, the processes of steps S201 and S202 may be performed periodically to periodically update the correction information. The processes of steps S201 and S202 may be performed independently of the processes of steps S101, S102, S104, and S105. Furthermore, the processes in steps S201 and S202 may be performed by an external information processing device, and the medical information processing device 30 may acquire the results (corrected information).

[0109] (Modification of the fourth embodiment) Next, a modified example of the fourth embodiment will be described. In the fourth embodiment, an example is described in which one correction information is acquired that maximizes the degree of agreement between the third breast configuration acquired by correcting the third breast density and the breast configurations separately assigned to multiple mammography images. In contrast, in this modified example, an example is described in which multiple correction information is acquired and a second breast configuration corresponding to the multiple correction information is presented.

[0110] For example, when there are multiple correction values ​​that maximize the degree of agreement between the third breast configuration and the breast configurations separately assigned to multiple mammography images, the correction information acquisition unit 353d acquires these multiple correction values. Also, for example, the correction information acquisition unit 353d acquires multiple correction values ​​when the degree of agreement is within a predetermined range. For example, the correction information acquisition unit 353d can acquire two correction values ​​at the upper and lower ends of the predetermined range, acquire multiple correction values ​​at any interval, or acquire multiple correction values ​​randomly.

[0111] When the correction information acquisition unit 353d acquires a plurality of pieces of correction information, the second breast configuration acquisition unit 353b acquires a second breast configuration for each of the acquired correction information in the process of step S104. In this case, the display control unit 354a can display the plurality of pieces of correction information and the plurality of second breast configurations acquired by the second breast configuration acquisition unit 353b in the process of step S105. By presenting the plurality of second breast configurations corresponding to the plurality of pieces of correction information, the user can recognize that there is ambiguity in the correction value, and it becomes possible to select a more appropriate breast configuration.

[0112] A display example according to a modified example of the fourth embodiment will be described below with reference to Figures 10A to 10B. Figures 10A to 10B show an example of a display screen when a plurality of pieces of correction information, a plurality of second mammary gland densities, and a plurality of second breast configurations are displayed.

[0113] For example, as shown in FIG. 10A, the display control unit 354a displays a mammography image I21 to be interpreted, a presentation area R21 for correction information, a presentation area R22 for breast density, and a presentation area R23 for breast configuration in the display screen D. In the display example of FIG. 10A, the presentation area R21 for correction information displays the first correction information and the second correction information. Specifically, in the display example of FIG. 10A, "correction value x: 5" is displayed as the first correction information, and "correction value x: 10" is displayed as the second correction information. In addition, in the display example of FIG. 10A, the presentation area R22 for breast density displays "corrected 1: 9%" as the first second breast density, and "corrected 2: 14%" as the second second breast density. In addition, in the display example of Figure 10A, in the breast configuration presentation area R23, "Corrected 1: Scattered mammary glands" is displayed as the first second breast configuration, and "Corrected 2: Non-uniform high density" is displayed as the second second breast configuration.

[0114] 10A is merely an example, and various modifications are possible. For example, the two breast densities may be displayed as arrows or icons on an axis showing the numerical values ​​of the breast densities, as in the second embodiment.

[0115] FIG. 10B is an example of a display screen using axes showing values ​​of breast density and breast configuration. For example, as shown in FIG. 10B, the display control unit 354a displays a mammography image I21 to be interpreted, a presentation area R21 for correction information, and a presentation area R24 in the display screen D. In the presentation area R24, an axis showing breast density and arrows pointing to the first breast density, the first second breast density, and the second second breast density are displayed. Furthermore, by associating breast configuration with the axis showing breast density, the three arrows respectively point to the first breast configuration, the first second breast configuration, and the second second breast configuration. Furthermore, a rectangular object is placed between the first arrow showing the first breast density and the second arrow showing the second breast density, and the area between the two arrows is the possible range of the second breast density.

[0116] As described above, in this embodiment, in addition to the breast configuration (second breast configuration) corrected to be closer to the visual judgment, a breast configuration (first breast configuration) quantitatively judged according to a predetermined standard is further displayed. This has the effect of making it easier to judge how reliable the breast configuration (second breast configuration) that has been brought closer to the visual judgment can be. Furthermore, according to this embodiment, the breast configuration (second breast configuration) that has been judged to be closer to the visual judgment can be displayed.

[0117] Furthermore, in a modified example of this embodiment, a breast configuration (second breast configuration) determined to be closer to the visual determination and a mammary gland density (second mammary gland density) corrected to be closer to the visual determination are displayed in multiple ways. This has the effect of making it easier to determine how much the breast configuration (second breast configuration) that has been adjusted to be closer to the visual determination can be trusted.

[0118] Fifth embodiment Next, a fifth embodiment will be described. In this embodiment, an example will be described in which correction information corresponding to a mammography image to be interpreted is selected from among a plurality of correction information and applied. In the following description, the same configurations and processes as those in the first to fourth embodiments are given the same reference numerals, and description thereof will be omitted.

[0119] The correction information acquisition unit 353d according to this embodiment acquires from the user breast configuration findings for the multiple mammography images acquired by the third breast density acquisition unit 353c, and acquires multiple pieces of correction information based on the degree of agreement with the third breast configuration. The second breast configuration acquisition unit 353b according to this embodiment selects one piece of correction information from the multiple pieces of correction information acquired by the correction information acquisition unit 353d according to the mammography image to be interpreted. Then, the second breast configuration acquisition unit 353b uses the selected correction information to perform the same process as in step S104 described above to acquire the second breast configuration.

[0120] Hereinafter, the details of the processing performed by the medical image processing device 30 according to this embodiment will be described with reference to the flowchart shown in Fig. 11. The processing of steps S101, S102, S201, S104, and S105 in Fig. 11 is similar to the processing of steps S101, S102, S201, S104, and S105 shown in Fig. 5 or Fig. 9, and therefore the description thereof will be omitted.

[0121] In step S301, the correction information acquisition unit 353d divides the multiple mammography images acquired in step S201 into multiple image groups based on a predetermined condition. Here, the predetermined condition is, for example, the magnitude of mammary gland density. For example, the correction information acquisition unit 353d estimates areas related to mammary glands on the multiple mammography images and acquires mammary gland density based on the areas related to mammary glands. Examples of areas related to mammary glands include mammary gland areas and mammary gland tissue areas. For example, as shown in a conceptual diagram in FIG. 12A, images I3111, I3112, and I3113 having mammary gland density of 60% or more and 100% or less are divided into an image group I311. Similarly, images I3121, I3122, and I3123 having mammary gland density of 30% or more and less than 60% are divided into an image group I312. Similarly, images I3131, I3132, and I3133, which have mammary gland densities of 0% or more and less than 30%, are divided into an image group I313. Note that the magnitude of mammary gland density used for division is not limited to this.

[0122] 12B, instead of the mammary gland density, the area of ​​the mammary gland tissue region may be used for division. In addition, division may be based on the area of ​​the mammary gland region, the area of ​​the breast region, the area of ​​the pectoral muscle region, the imaging position (e.g., CC or MLO), the model number of the device, the age of the subject P, etc. Division may also be performed based on a combination of multiple conditions.

[0123] Next, in step S302, the correction information acquisition unit 353d acquires correction information for each image group divided in step S301. Here, the method of acquiring each piece of correction information is the same as the method used in step S202 described above, for example.

[0124] Next, in step S303, the second breast configuration acquisition unit 353b selects correction information to be applied to the mammography image to be interpreted from among the multiple pieces of correction information acquired for each image group in step S302. To achieve this, in this step, first, the image group to which the image belongs is determined. This determination is made by determining which image group the image belongs to based on the predetermined conditions used to divide the image groups in step S301. For example, if the image groups are divided by the magnitude of mammary gland density, the determination is made based on the first mammary gland density of the image acquired in step S101. Then, from the multiple pieces of correction information acquired in step S302, correction information corresponding to the image group to which the image belongs is selected.

[0125] As described above, in this embodiment, in addition to the breast configuration (second breast configuration) corrected to be closer to the visual judgment, the breast configuration (first breast configuration) quantitatively judged according to a predetermined standard is further displayed. This has the effect of facilitating a judgment as to how much the breast configuration (second breast configuration) that has been judged to be closer to the visual judgment can be trusted. Furthermore, according to this embodiment, it is possible to grasp what kind of visual judgment the breast configuration (second breast configuration) judged to be closer to the visual judgment has been brought closer to, and it is effective in facilitating a judgment as to how much the breast configuration (second breast configuration) that has been brought closer to the visual judgment can be trusted. Furthermore, according to this embodiment, by selecting correction information according to the mammography image to be interpreted, a correction value suitable for the characteristics of the image is applied, so that appropriate correction can be performed. Furthermore, even in such a case, the selected correction information is displayed, so that it is possible to grasp what kind of correction has been made, and it is effective in facilitating a judgment as to how much the breast configuration (second breast configuration) that has been brought closer to the visual judgment can be trusted.

[0126] Sixth embodiment In addition to the above-described embodiment, various modifications may be made.

[0127] For example, in the above-described embodiment, the calculation values ​​such as the mammary gland density and the mammary gland area are corrected, and the second breast configuration is obtained based on the corrected calculation values. However, the correction is not limited to the calculation values.

[0128] For example, the second acquisition function 353 may perform correction on the threshold value used for extracting the mammary gland region. For example, the first acquisition function 352 extracts the mammary gland region from the mammography image using a predetermined brightness value as a threshold value, divides the area of ​​the mammary gland region by the area of ​​the mammary gland tissue region to obtain a first mammary gland density, and compares the first mammary gland density with a cutoff value to obtain a first breast configuration. The second acquisition function 353 also corrects the threshold value used for acquiring the first breast configuration, extracts the mammary gland region from the mammography image based on the corrected threshold value, divides the area of ​​the mammary gland region by the area of ​​the mammary gland tissue region to obtain a second mammary gland density, and compares the second mammary gland density with the cutoff value to obtain a second breast configuration. The correction of the threshold value may be performed based on predetermined correction information stored in the database 20, for example, or may be performed in response to a user's operation. In this case, the display control function 354 may display the threshold value used to obtain the first breast configuration "before correction: brightness value z1" and the threshold value used to obtain the second breast configuration "before correction: brightness value z2" in the correction information presentation area R13, as shown in, for example, FIG. 13.

[0129] Also, for example, the second acquisition function 353 may perform correction on the cutoff value. For example, the first acquisition function 352 acquires a first breast density from a mammography image, and acquires a first breast configuration by comparing the first breast density with a predetermined cutoff value. Also, the second acquisition function 353 corrects the cutoff value, and acquires a second breast configuration by comparing the first breast density with the corrected cutoff value. The correction of the cutoff value may be performed based on, for example, predetermined correction information stored in the database 20, or may be performed in response to a user's operation. In this case, the display control function 354 may display each cutoff value before and after correction in the presentation area of ​​the correction information.

[0130] In addition, the object of the correction process performed when acquiring the second breast configuration can be modified in various ways. For example, the second acquisition function 353 may correct a mammography image, and acquire a breast configuration acquired based on the corrected mammography image as the second breast configuration. Alternatively, the second acquisition function 353 may correct a first breast configuration, and acquire a breast configuration after correction as the second breast configuration.

[0131] Also, although an example of acquiring the second breast configuration by performing any of the above-mentioned correction processes has been described, it is possible to omit the correction process. For example, the second breast configuration may be acquired by visually determining the breast configuration by the user. Also, for example, the second breast configuration may be acquired by inputting a mammography image to be interpreted into a trained model that is functionalized to receive an input of a mammography image and determine the breast configuration, and acquiring the breast configuration output from the trained model as the second breast configuration. That is, examples of the second breast configuration acquired by the second acquisition function 353 include various breast configurations excluding the first breast configuration acquired according to a predetermined standard.

[0132] Also, so far, the first acquisition function 352 has been described as acquiring a first breast density from a mammography image to be interpreted, and acquiring a first breast configuration based on the first breast density. That is, an example has been described in which the first breast configuration is acquired using the guidelines of the Japan Breast Cancer Screening Quality Management Center, a non-profit organization, as a predetermined standard. However, the embodiment is not limited to this, and the first acquisition function 352 may acquire the first breast configuration using other guidelines as a predetermined standard. For example, depending on the guidelines, the result of visual judgment by a specific user may be regarded as the breast configuration. In this case, the first acquisition function 352 may acquire the breast configuration visually judged by the user as the first breast configuration.

[0133] For example, in the above-described embodiment, an example has been described in which the processing of the first acquisition function 352 and the second acquisition function 353 is executed in the medical information processing device 30. However, the embodiment is not limited to this, and for example, in an X-ray diagnostic apparatus 10 that collects mammography images from a subject P, processing similar to the processing by the first acquisition function 352 and the second acquisition function 353 may be performed.

[0134] Fig. 14 is a block diagram showing an example of the configuration of an X-ray diagnostic apparatus 10 according to the sixth embodiment. The X-ray diagnostic apparatus 10 shown in Fig. 14 differs from the X-ray diagnostic apparatus 10 shown in Fig. 2 in that the processing circuitry 115 further includes a first acquisition function 1153 and a second acquisition function 1154.

[0135] The first acquisition function 1153 is a function similar to the above-mentioned first acquisition function 352, and acquires a first breast configuration from a mammography image according to a predetermined criterion. The second acquisition function 1154 is a function similar to the above-mentioned second acquisition function 353, and acquires a second breast configuration different from the first breast configuration from a mammography image. In this case, the output function 1152, like the above-mentioned display control function 354, can display the first breast configuration and the second breast configuration on the display unit.

[0136] The term "processor" used in the above description means a circuit such as a CPU, a GPU (Graphics Processing Unit), an ASIC, a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)). When the processor is, for example, a CPU, the processor realizes a function by reading and executing a program stored in a memory circuit. On the other hand, when the processor is, for example, an ASIC, instead of storing a program in a memory circuit, the function is directly incorporated as a logic circuit in the circuit of the processor. Note that each processor in the embodiment is not limited to being configured as a single circuit for each processor, but may be configured as one processor by combining multiple independent circuits to realize the function. Furthermore, multiple components in each figure may be integrated into one processor to realize the function.

[0137] Each component of each device according to the above-mentioned embodiment is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or a part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc. Furthermore, each processing function performed by each device can be realized in whole or in any part by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

[0138] The medical information processing method described in the above embodiment can be realized by executing a prepared medical information processing program on a computer such as a personal computer or a workstation. This medical information processing program can be distributed via a network such as the Internet. This medical information processing program can also be recorded on a non-transitory recording medium readable by a computer such as a hard disk, a flexible disk (FD), a CD-ROM, an MO, or a DVD, and executed by being read from the recording medium by a computer.

[0139] At least one of the embodiments described above can assist in utilizing breast configurations.

[0140] Although some embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents as described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0141] 1: Medical information processing system 10: X-ray diagnostic equipment 101: Foundation 102: Stand 103: Photo stand 104: Compression plate 105:X-ray tube 106: X-ray squeezer 107: X-ray detector 108: Signal processing circuit 109: Lifting drive device 110: X-ray high voltage device 111: Communication interface 112: Input interface 113: Display 114: Memory 115: Processing circuit 1151: Collection function 1152: Output function 1153: First acquisition function 1154: Second acquisition function 20: Database 30: Medical information processing device 31: Communication interface 32: Input interface 33: Display 34: Memory 35: Processing circuit 351: Receiving function 352: First acquisition function 353: Second acquisition function 354: Display control function 352a: First breast density acquisition unit 352b: First breast configuration acquisition unit 353a: Correction information acquisition unit 353b: Second breast configuration acquisition unit 353c: 3rd breast density acquisition section 353d: Correction information acquisition unit 354a: Display control unit 40: Network

Claims

1. a first acquisition unit that acquires a first breast configuration from a mammography image according to a predetermined criterion; a second acquisition unit that acquires a second breast configuration different from the first breast configuration from the mammography image; a display control unit that causes a display unit to display the first breast configuration and the second breast configuration; A medical information processing device comprising:

2. the first acquisition unit acquires the first breast configuration based on a calculated value acquired from the mammography image; The medical image processing apparatus according to claim 1 , wherein the second acquisition unit acquires the second breast configuration based on a corrected calculated value obtained by correcting the calculated value.

3. The medical information processing device according to claim 2 , wherein the calculated value is a breast density.

4. The medical information processing apparatus according to claim 2 , wherein the display control unit further causes the display unit to display at least a part of correction information used when correcting the calculated value to obtain the corrected calculated value.

5. the correction information includes at least a correction value used when correcting the calculated value to obtain the corrected calculated value, The medical information processing apparatus according to claim 4 , wherein the display control unit causes the display unit to display the correction value as the correction information.

6. The correction information includes at least information regarding a method of applying the correction value when correcting the calculated value, The medical information processing apparatus according to claim 5 , wherein the display control unit causes the display unit to display information about the application method as the correction information.

7. The medical information processing device according to claim 6 , wherein the information regarding the application method is at least one of a method of linearly calculating the correction value for the calculated value, a method of non-linearly calculating the correction value, and a method of combining these methods, and information based on these methods.

8. The medical information processing device according to claim 1 , wherein the display control unit further causes the display unit to display information relating to a difference between the first breast configuration and the second breast configuration.

9. the first acquisition unit acquires a first mammary gland density from the mammography image as the calculated value, or acquires a first mammary gland density based on the calculated value, and acquires the first breast configuration based on the first mammary gland density; The medical information processing device of claim 3 , wherein the second acquisition unit acquires a second mammary gland density as the corrected calculated value, or acquires a second mammary gland density based on the corrected calculated value, and acquires a second breast configuration based on the second mammary gland density.

10. The medical information processing apparatus according to claim 9 , wherein the display control unit further causes the display unit to display the first mammary gland density and the second mammary gland density in a comparative manner.

11. The medical information processing device of claim 10, wherein the display control unit displays an axis indicating mammary gland density and arrows indicating the first mammary gland density and the second mammary gland density in a contrastable state, and further displays breast configuration in correspondence with the axis.

12. The medical image processing device according to claim 11 , wherein the display control unit further causes a cutoff value serving as a reference for determining a breast configuration to be displayed on the axis.

13. the first acquisition unit acquires an area of ​​a mammary gland region and an area of ​​a mammary gland tissue region from the mammography image as the calculated value, and acquires the first mammary gland density from the area of ​​the mammary gland region and the area of ​​the mammary gland tissue region; 10. The medical information processing device of claim 9, wherein the second acquisition unit corrects at least one of the area of ​​the mammary gland region and the area of ​​the mammary gland tissue region to acquire the corrected calculated value, and acquires the second mammary gland density based on the area of ​​the mammary gland region and the area of ​​the mammary gland tissue region, at least one of which has been corrected.

14. the first acquisition unit acquires at least an area of ​​a mammary gland region from the mammography image as the calculated value, and acquires the first mammary gland density based on the area of ​​the mammary gland region; The second acquisition unit corrects an area of ​​the mammary gland region and acquires the second mammary gland density based on the corrected area; The medical information processing device of claim 9, wherein the display control unit causes the mammography image to be displayed on the display unit, and causes the mammography image to be superimposed on the mammography image so that the mammary gland area whose area has not been corrected to obtain the second mammary gland density and the mammary gland area whose area has been corrected can be distinguished from each other.

15. 15. The medical information processing device according to claim 14, wherein the display control unit displays the mammary gland region whose area has not been corrected to obtain the second mammary gland density in a solid line, and displays the mammary gland region whose area has been corrected in a dashed line.

16. The medical information processing device of claim 4, wherein the second acquisition unit acquires a plurality of third breast densities from a plurality of mammography images other than the mammography image to be interpreted, acquires a plurality of third breast configurations by applying correction information candidates to the plurality of third breast densities, and acquires the correction information candidates as the correction information when a degree of agreement between the plurality of third breast configurations and breast configurations separately assigned to the plurality of mammography images satisfies a predetermined condition.

17. The medical image processing apparatus according to claim 16 , wherein the predetermined condition is any one of a case where the degree of match is equal to or greater than a predetermined value, a case where the degree of match is within a predetermined range, and a case where the degree of match is maximized.

18. The second acquisition unit acquires a plurality of pieces of correction information, and acquires the second breast configuration for each of the acquired correction information, The medical information processing apparatus according to claim 16 , wherein the display control unit causes a plurality of pieces of the correction information and a plurality of the second breast configurations corresponding to the plurality of pieces of the correction information to be displayed.

19. The medical image processing apparatus according to claim 16 , wherein the second acquisition unit divides the plurality of mammography images into a plurality of image groups under a predetermined condition, and acquires the correction information for each image group.

20. The medical image processing device according to claim 19 , wherein the predetermined condition is a magnitude of mammary gland density in the plurality of mammography images.

21. The medical image processing device according to claim 16 , wherein the second acquisition unit estimates areas relating to mammary glands on the plurality of mammography images, and acquires mammary gland density based on the areas relating to the mammary glands.

22. The medical image processing device according to claim 19 , wherein the predetermined condition is a size of an area relating to mammary glands on the plurality of mammography images.

23. the second acquisition unit acquires a plurality of second breast densities based on a first breast density acquired from the mammography image and the correction information; The medical information processing apparatus according to claim 4 , wherein the display control unit causes the first mammary gland density and the plurality of second mammary gland densities to be displayed together.

24. The second acquisition unit acquires a plurality of second breast configurations based on the plurality of second mammary gland densities, The medical information processing apparatus according to claim 23 , wherein the display control unit causes the plurality of second breast configurations to be displayed.

25. the first acquisition unit extracts a first mammary gland region from the mammography image using a predetermined brightness value as a threshold value, and acquires the first breast configuration based on an area of ​​the first mammary gland region; 2 . The medical information processing device according to claim 1 , wherein the second acquisition unit corrects the threshold, extracts a second mammary gland region from the mammography image based on the corrected threshold, and acquires the second breast configuration based on an area of ​​the second mammary gland region.

26. the first acquisition unit acquires a first breast density from the mammography image and acquires the first breast configuration by comparing the first breast density with a predetermined cutoff value; The medical information processing device according to claim 1 , wherein the second acquisition unit acquires the second breast configuration by correcting the predetermined cutoff value and comparing the first mammary gland density with the corrected cutoff value.

27. an acquisition unit that acquires mammography images by photographing a subject; a first acquisition unit that acquires a first breast configuration from the mammography image according to a predetermined criterion; a second acquisition unit that acquires a second breast configuration different from the first breast configuration from the mammography image; a display control unit that causes a display unit to display the first breast configuration and the second breast configuration; An X-ray diagnostic apparatus comprising:

28. Obtaining a first breast configuration from the mammography image according to a predetermined criterion; obtaining a second breast configuration from the mammography image, the second breast configuration being different from the first breast configuration; Displaying the first breast configuration and the second breast configuration on a display unit A medical information processing method comprising:

29. Obtaining a first breast configuration from the mammography image according to a predetermined criterion; obtaining a second breast configuration from the mammography image, the second breast configuration being different from the first breast configuration; Displaying the first breast configuration and the second breast configuration on a display unit A medical information processing program that causes a computer to execute each process.

Images