Information processing system, control method for information processing system, control program, and recording medium

Abstract

The present invention assists planning of surgical treatment suitable for the affected bone of a subject. The information processing system is provided with an identification unit and an output unit. The identification unit has a trained first learning model. The output unit outputs at least one of instrument information, prediction information, parameter information, and implant information identified by the identification unit.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing system that supports the formulation of a surgical treatment plan suitable for an affected bone of a subject, and a control method thereof. [Background technology]

[0002] Patent Document 1 discloses a technique for proposing a surgical procedure to a doctor who is about to perform surgery on a patient's joint with higher accuracy than before. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2021-115188 Summary of the Invention

[0004] In order to solve the above problem, an information processing system according to one embodiment of the present disclosure includes an acquisition unit that acquires input information including medical images of the affected bone of a subject; an identification unit that has a first learning model trained using first training data including bone information regarding at least one of bone density and bone quality of the bone of each of a plurality of learning subjects before a surgical treatment including an implant placement procedure is applied, shape characteristics, and treatment information regarding the surgical treatment applied to the bone; and an output unit that outputs at least one of instrument information indicating surgical instruments to be used in a surgical treatment suitable for the affected bone of the subject, identified by the identification unit based on the input information; prediction information predicting the condition of the affected bone of the subject after the surgical treatment is applied; parameter information indicating parameters that may be selected when applying a surgical treatment to the affected bone of the subject; and implant information regarding implants that may be implanted in the affected bone of the subject.

[0005] Furthermore, a control method of an information processing system according to one aspect of the present disclosure includes an acquisition step of acquiring input information including medical images of the affected bone of a subject; and an output step of outputting, using a first learning model trained using first training data including bone information regarding at least one of bone density and bone quality of the bone of each of a plurality of learning subjects before a surgical treatment including an implant placement procedure is applied, shape characteristics, and treatment information regarding the surgical treatment applied to the bone, at least one of instrument information indicating surgical instruments to be used in a surgical treatment suitable for the affected bone of the subject, identified based on the input information; prediction information predicting the condition of the affected bone of the subject after the surgical treatment procedure is applied; parameter information indicating parameters that may be selected when a surgical treatment procedure is applied to the affected bone of the subject; and implant information regarding an implant that may be implanted in the affected bone of the subject.

[0006] In addition, the information processing system according to each aspect of the present disclosure may be realized by a computer. In this case, the control program of the information processing system that realizes the information processing system on a computer by causing the computer to operate as each part (software element) of the information processing system, and the computer-readable recording medium on which it is recorded, also fall within the scope of the present disclosure. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram illustrating a configuration example of an information processing system according to an aspect of the present disclosure. [Figure 2] FIG. 10 is a diagram illustrating a configuration example of an information processing system according to another aspect of the present disclosure. [Figure 3] 1 is a block diagram illustrating an example of a configuration of an information processing device according to an aspect of the present disclosure. [Figure 4] FIG. 10 is a diagram illustrating an example of the configuration of a first learning model executed by an identification unit. [Figure 5] 10 is a flowchart showing an example of the flow of a learning process by a learning unit. [Figure 6]10 is a flowchart illustrating an example of a flow of processing performed by an information processing device. [Figure 7] 1 is a block diagram illustrating an example of a configuration of an information processing device according to an aspect of the present disclosure. [Figure 8] FIG. 1 is a diagram illustrating a configuration example of an information processing system according to an aspect of the present disclosure. [Figure 9] 1 is a block diagram illustrating an example of a configuration of an information processing device according to an aspect of the present disclosure. [Figure 10] FIG. 2 is a diagram illustrating an example of the configuration of a learning model executed by an estimation unit. [Figure 11] 10 is a flowchart showing an example of the flow of a learning process by a learning unit. [Figure 12] 10 is a flowchart illustrating an example of a flow of processing performed by an information processing device. [Figure 13] FIG. 1 is a diagram illustrating a configuration example of an information processing system according to an aspect of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0008] As technology to assist in the planning of surgical treatment is in its infancy, one of the challenges is providing support information that is more appropriate for each patient.

[0009] One aspect of the present disclosure can assist in planning appropriate surgical treatment for the affected bone of a subject.

[0010] Each embodiment of the present disclosure will be described below. In the following description, the case where the subject to which the application of a surgical treatment is considered is a human (i.e., a "subject") will be described as an example, but the subject is not limited to humans. That is, the "subject" according to the present disclosure may also be a mammal other than a human, such as an equine, feline, canine, bovine, or porcine. The present disclosure also includes, among the following embodiments, embodiments in which "subject" is replaced with "animal" if the embodiment is applicable to these animals.

[0011] [Embodiment 1] Hereinafter, an information processing device 1 according to an embodiment of the present disclosure will be described in detail as an example.

[0012] The information processing device 1 outputs at least one of instrument information, prediction information, parameter information, and implant information identified using a trained first learning model 34 based on input information including medical images of the affected bone of the subject. Here, the instrument information is information indicating surgical instruments to be used in a surgical treatment method suitable for the affected bone of the subject. The prediction information is information predicting the state of the affected bone of the subject after the surgical treatment method suitable for the affected bone of the subject has been applied. The parameter information is information indicating parameters that may be selected when applying a surgical treatment method to the affected bone of the subject. The implant information is information regarding implants that may be implanted in the affected bone of the subject. The implant information may include inventory information of implants that may be implanted in the affected bone of the subject.

[0013] The trained first learning model 34 is trained using first training data including bone information on at least one of bone density and bone quality of the bone of each of a plurality of training subjects before the application of a surgical treatment including implant placement, shape characteristics, and treatment information on the surgical treatment applied to the bone. Here, the training subjects include, for example, patients with a specific disease, but may also include subjects unrelated to the disease, and will be simply referred to as "patients" in the following description.

[0014] The medical image may be, for example, at least one of an X-ray image, a CT (Computed Tomography) image, a magnetic resonance imaging (MRI) image, and an ultrasound image, but is not limited to these. The medical image may be, for example, an inspection device image acquired from an inspection device (e.g., an X-ray inspection device), or an inspection device image with noise reduction. The body part shown in the medical image may be any of the head, neck, chest, lower back, hip joint, knee joint, ankle joint, foot, toe, shoulder joint, elbow joint, wrist joint, hand, and fingers. The medical image may also be, for example, a dental image.

[0015] The bone density of the bone can be measured by actually measuring bone density from at least one of the hand, lumbar vertebrae, proximal femur, tibia, heel, and arm (e.g., radius, etc.). Bone density can be measured by, for example, single-energy X-ray absorptiometry, dual-energy X-ray absorptiometry (DXA), ultrasound, or quantitative computed tomography (CT).

[0016] The bone density of the bone may be, for example, a patient's bone density estimated by inputting an X-ray image of the patient's bone into a trained estimation model that has been machine-learned using training data including X-ray images of the bone and actual bone density of the bone. Alternatively, the bone density of the bone may be, for example, a patient's future bone density predicted by inputting an X-ray image of the patient's bone into a trained prediction model that has been machine-learned using training data including X-ray images of the patient's bone and actual bone density measured a predetermined period of time (e.g., one year, three years, etc.) after the X-ray images were taken. The bone density of the bone may be any information related to bone density. The bone density of the bone may be, for example, information in accordance with the definition in the osteoporosis guidelines or may be an original index. Information related to the training data is used for the bone density. For example, bone mineral density per unit area (g / cm) may be used as the bone density of the bone. 2 ), bone mineral density per unit volume (g / cm 3 ), YAM, T-score, and / or Z-score. YAM is an abbreviation for "Young Adult Mean" and may be referred to as the percent young adult mean. For example, the output layer 230 may provide bone mineral density per unit area (g / cm 2 Alternatively, bone density expressed by YAM, bone density expressed by T-score, and bone density expressed by Z-score may be used. Furthermore, bone density may be classified (e.g., SD -1.0 or more, less than -1.0, less than -2.5, YAM 80% or more, less than 80%, etc.).

[0017] Bone quality can be determined based on at least one of bone statistical properties, bone geometric properties, bone mechanical properties, and bone chemical properties. Bone quality can be determined based on at least one of bone metabolic markers, sex, race, menopausal status, age, cortical bone condition, cancellous bone condition, cancellous trabecular bone condition, disease information, bone evaluation information, medication information, and the presence or absence of fractures. More specifically, bone quality can be determined based on at least one of bone formation markers, bone resorption markers, bone quality markers (e.g., vitamin K level), cortical bone thickness, trabecular density, trabecular orientation, and cancellous bone structure index (trabecular bone score), but is not limited to these. Disease information can include at least one of osteoporosis, rheumatoid arthritis, osteonecrosis (e.g., femoral head necrosis), systemic sclerosis, kidney disease, osteopetrosis, etc. The bone evaluation information may include information evaluated by a Fracture Risk Assessment Tool (FRAX (registered trademark)). The drug information may include at least one of the trade name, generic name, dosage, administration period, and administration method (e.g., oral, intravenous injection, intramuscular injection, subcutaneous injection, etc.) for drugs including at least one of drugs that suppress bone resorption, drugs that promote bone formation, and other drugs (e.g., calcium preparations, vitamin preparations, female hormone preparations, etc.).

[0018] The bone quality may also include, for example, the type of medullary cavity shape. For example, the Dorr classification can be used for the medullary cavity shape. The medullary cavity shape can be classified as follows, using at least one of the thickness of the cortical bone and the shape of the medullary cavity, for example: Type A: The cortical bone is thick and the medullary cavity is narrow. Type B: Between Type A and Type C, the medullary cavity is neither narrow nor wide. Type C: The cortical bone is thin and the medullary cavity is wide.

[0019] The geometric characteristics include, for example, at least the relative positional relationship, size, shape, and general form of bones. In the case of an artificial hip joint, the geometric characteristics may include, for example, the shape of the pelvis, the size of the pelvis, the shape of the acetabulum of the pelvis, the size of the acetabulum of the pelvis, the position of the femoral head, the size of the femoral head, and the positional relationship between the femur and the pelvis (such as the femoral head and the acetabulum of the pelvis). In the case of an artificial knee joint, the geometric characteristics may include, for example, the position of the femoral head, the curvature angle of the femur, the size of the distal part of the femur, the shape of the femur, the angle of the femoral articular surface, the amount of posterior offset of the femur, the size of the tibia (e.g., the proximal part that contacts the tibia), the shape of the tibia (e.g., the proximal part that contacts the tibia), the size of the patella, the shape of the patella, and the positional relationship between the femur and the tibia (such as the angle between the femur and the tibia). In the case of a dental implant, the relative positional relationship of bones among the shape characteristics may be, for example, at least two distances between the alveolar bone crest, the floor of the maxillary sinus, the floor of the nasal cavity, the upper edge of the mandibular canal, and the mental foramen.

[0020] In the present disclosure, the surgical treatment may be at least one of artificial joint replacement surgery and dental implant surgery, and may be performed by a surgical robot. In this case, the information processing device 1 and a surgical robot control device may be communicably connected, and various information output from the information processing device 1 may be transmitted to the surgical robot control device. In this case, the surgical robot can be appropriately configured by referring to the instrument information, prediction information, parameter information, and implant information output from the information processing device 1.

[0021] More specifically, the settings of the surgical robot can include setting at least one of the type and size of the instruments used by the surgical robot. Also, various parameters of the instruments used by the surgical robot during surgery can be set. Examples of the various parameters include the angle at which the bone (e.g., the femoral neck in the case of total hip replacement surgery, and the femoral condyle, distal femur, or proximal tibia in the case of total knee replacement surgery) is resected, the resection amount, the insertion angle of the instrument into the human body (including the medullary cavity, for example), the insertion depth, the number of rotations of the instrument (including torque), the removal angle of the instrument, and the bone cutting time. These various parameters may be set in combination, or multiple parameters may be set.

[0022] (Configuration of information processing system 100a) First, the configuration of an information processing system 100a according to one embodiment of the present disclosure will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the configuration of the information processing system 100a in a medical facility 8 in which an information processing device 1 has been introduced.

[0023] The information processing system 100a includes an information processing device 1 and one or more terminal devices 7 communicatively connected to the information processing device 1. The information processing device 1 identifies a surgical treatment method suitable for the affected bone of a subject and an implant that can be used in the surgical treatment method from a medical image showing the subject's bone. The information processing system 100a is a computer that transmits at least one of instrument information, prediction information, parameter information, and implant information to the terminal device 7. The information processing device 1 according to an embodiment of the present disclosure is a device that outputs various information that is useful when a doctor or the like considers and formulates a surgical treatment method suitable for the affected bone of a subject.

[0024] The terminal device 7 functions as an output unit in the information processing system 100a and presents information received from the information processing device 1. The terminal device 7 is a computer used by medical personnel such as doctors or nurses (medical personnel) belonging to the medical facility 8. The terminal device 7 is, for example, a personal computer, a tablet terminal, a smartphone, etc. The terminal device 7 has a communication unit for transmitting and receiving data to and from other devices, an input unit such as a keyboard and a microphone, a display unit capable of displaying information transmitted from the information processing device 1, an output unit such as a speaker, etc.

[0025] 1 shows an example in which a local area network (LAN) is installed within the medical facility 8, and the information processing device 1 and the terminal device 7 are connected to the LAN, but this is not limiting. For example, the network within the medical facility 8 may be the Internet, a telephone communication line network, an optical fiber communication network, a cable communication network, a satellite communication network, or the like. The information processing system 100a is compatible with a hospital information system (HIS), a radiology information system (RIS), a picture archiving and communication system (PACS), or the like within the medical institution 8. Furthermore, communication in the information processing system 100a complies with international standards such as DICOM (Digital Imaging and Communications in Medicine).

[0026] In addition to the information processing device 1 and the terminal device 7, a medical image management device 5 and an inventory management device 6 may be communicatively connected to the LAN within the medical facility 8. The medical image management device 5 is a computer that functions as a server for managing medical images taken at the medical facility 8. In this case, the information processing device 1 may acquire medical images showing the affected bone of the subject from the medical image management device 5. The inventory management device 6 is a computer that functions as a server for managing the inventory status of implants, surgical instruments, etc. used in various treatments performed at the medical facility 8.

[0027] In the information processing system 100a, a server device (not shown) communicably connected to the terminal device 7, the medical image management device 5, the inventory management device 6, etc. may be configured to have various functions of the information processing device 1. In this case, the server device functions as the information processing device 1 in the information processing system 100a.

[0028] The LAN within the medical facility 8 may be communicably connected to an external communication network. In the medical facility 8, the information processing device 1 and the terminal device 7 may be directly connected without going through a LAN.

[0029] (Configuration of information processing device 1) Next, the configuration of the information processing device 1 applied to the information processing system 100a shown in Fig. 1 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing an example of the configuration of the information processing device 1.

[0030] The information processing device 1 includes a control unit 2 that comprehensively controls each unit of the information processing device 1, and a storage unit 3 that stores various data used by the control unit 2. The control unit 2 includes an acquisition unit 21, an identification unit 23, an output unit 24, and a learning unit 25. The storage unit 3 stores a control program 31, which is a program for performing various controls on the information processing device 1, as well as first teacher data 32, an implant / surgical instrument information database 33, and a trained first learning model 34.

[0031] <Acquisition part 21> The acquisition unit 21 acquires input information including medical images showing the affected bone of the subject. For example, the acquisition unit 21 shown in FIG. 3 may be capable of acquiring medical images showing the affected bone of the subject from a medical image management device 5. The input information is input data input to the identification unit 23. When the surgical treatment method suitable for the affected bone of the subject includes implant placement, the acquisition unit 21 may acquire the availability status of each implant and surgical instrument used in the implant placement from an inventory management device 6 in the medical facility 8. The availability status is not limited to the availability status at the medical facility 8, but may also be, for example, the availability status at a facility including at least one of a manufacturer, a wholesaler, and a distributor. Furthermore, the availability status may include, for example, delivery date information received by the medical facility 8 from a facility including at least one of a manufacturer, a wholesaler, and a distributor.

[0032] <Specific part 23> The identification unit 23 identifies at least one of the above-mentioned instrument information, prediction information, parameter information, and implant information by inputting input information into the trained first learning model 34. Here, the trained first learning model 34 has been previously trained (also referred to as training) using first teacher data 32. The first teacher data 32 is data including bone information relating to at least one of the bone density and bone quality of the bone of each of a plurality of patients before a surgical treatment including implant placement is applied, shape characteristics, and treatment information relating to the surgical treatment applied to the bone.

[0033] The treatment information regarding the surgical treatment method as the first training data 32 is, for example, information that combines at least one of instrument information, prediction information, parameter information, implant information when the surgical treatment method is applied to the patient, and treatment progress information after the surgical treatment is applied. The treatment progress information includes progress information of the patient after the surgical treatment is applied. Specifically, the treatment progress information includes, for example, at least one of the following: whether or not the implant has loosened, whether or not there has been postoperative infection in the affected area or the whole body, the intensity, duration, and change in range of motion of pain, and whether or not there has been implant replacement, but is not limited to these.

[0034] The identification unit 23 may, for example, input input information into the trained first learning model 34 to identify a surgical treatment method suitable for the affected bone of the subject and an implant that can be implanted in the affected bone of the subject during the surgical treatment. In this case, the first training data 32 used to train the trained first learning model 34 may be data including, as treatment information, the content and results of a surgical treatment method applied to the affected bone of each of multiple patients. Alternatively, the first training data 32 used to train the trained first learning model 34 may be data including information indicating the surgical treatment method applied to the affected bone of each of multiple patients, medical images of the affected bone of each of the multiple patients before the surgical treatment method was applied, and information regarding the implant implanted in the affected bone of each of the multiple patients.

[0035] Here, the information about implants may be information about artificial joints, information about spinal implants, and information about various parameters of artificial prostheses or dental implants determined during implantation surgery. Here, the artificial joints may include artificial hip joints, artificial knee joints, artificial shoulder joints, artificial elbow joints, artificial ankle joints, etc. The spinal implants may include at least one implant applied to the cervical vertebrae, thoracic vertebrae, lumbar vertebrae, sacrum, and coccyx. The artificial prostheses may include at least one of artificial bones (e.g., block or granular), artificial talus, artificial skull, intramedullary nail, and bone fixation plate. The information about implants may be, for example, at least one of the implant's product name, model number, manufacturer, distributor, surface treatment, and whether the implant is antibacterial treated. The information about implants may include information about various parameters including at least one of the implant's size, dimensions, angle, and material.

[0036] In the case of an artificial hip joint, the information about the implant may include, for example, at least one of the following information: The information about the implant may be the following information itself, or may be at least one of the product name, model number, manufacturer, and distributor of the implant that matches the following information, but is not limited to these. Information about the outer diameter of the cup. Information about the cup's fixing screws. ·Information about the femoral head diameter. -Information about stem neck length. Information about the offset from the center of rotation of the stem portion inserted into the medullary canal to the center of rotation of the neck. ·Information about surface treatment. Information about the method of fixation to bone or tissue. Here, the information regarding the fixing screws of the cup may be the number of fixing screws, the position of the fixing screws, the length of the fixing screws, the surface treatment of the fixing screws, the pitch of the fixing screws (e.g., the pitch between the threads), the diameter of the fixing screws (the diameter of the threaded portion), etc.

[0037] In the case of an artificial knee joint, the information about the implant may include, for example, at least one of the following information: The information about the implant may be the following information itself, or may be at least one of the product name, model number, manufacturer, and distributor of the implant that matches the following information, but is not limited to these. Femoral component size information · Information about the size of the tibial component. · Information about the tibial insert (e.g., the thickness of the tibial insert). · Information about the length of the tibial stem. · Information about patellar component size. Information about the type of component by cruciate ligament treatment (e.g., at least one of a posterior cruciate ligament-preserving component, a posterior cruciate ligament-releasing component, a posterior cruciate ligament-compensating component, and a bicruciate ligament-preserving component). Implant type information (e.g., at least one of hinged, unilateral, mobile insert, patellofemoral, cemented, uncemented, and hybrid). Information about the method of fixation to bone or tissue.

[0038] In the case of a spinal implant, the information about the implant may include, for example, at least one of the following information: The information about the implant may be the following information itself, or may be at least one of the product name, model number, manufacturer, and distributor of the implant that matches the following information, but is not limited to these. -Information about the procedure. ·Information about spinal cages. ·Information about spinal fixation plates. Information about the fixing screws. Information about the rod that connects the fixing screws. ·Information about surface treatment. Information about the method of fixation to bone or tissue. The information on the surgical procedure includes, for example, information on at least one of an anterior approach where an incision is made on the front of the patient's body, a lateral approach where an incision is made on the side, and a posterior approach where an incision is made on the back. More specifically, the information on the surgical procedure includes, for example, information on an anterior lumbar interbody fusion (ALIF), a posterior lumbar interbody fusion (PL ... This information includes lumbar interbody fusion (LLIF; Lateral Lumbar Interbody Fusion), lumbar extralateral interbody fusion (XLIF; eXtreme Lumbar Interbody Fusion), lumbar anterolateral interbody fusion (OLIF; Oblique Lumbar Interbody Fusion), and lumbar transformational interbody fusion (TLIF; Lateral Lumbar Interbody Fusion).

[0039] In the case of a dental implant, the information about the implant may include, for example, at least one of the following information: The information about the implant may be the following information itself, or may be at least one of the product name, model number, manufacturer, and distributor of the implant that matches the following information, but is not limited to these. -Information about the tip shape that will be embedded in the bone. ·Information about surface treatment. ·Information about intraosseous length. -Information about diameter. Information about the method of fixation to bone or tissue.

[0040] Examples of information on surface treatment include information on surface treatment for growing bone on the surface (On-Growth), or information on surface treatment for growing bone in porous material (In-Growth), etc. Here, examples of surface treatment include at least one of hydroxyapatite, which is mainly composed of calcium hydroxide phosphate, surface roughening treatment, Ti spraying, functional porous layer by 3D printing, alkali heat treatment, anodizing treatment, and acid treatment, but are not limited to these.

[0041] The information regarding the fixation method to bone or biological tissue may be, for example, information regarding a cement-retained type, a non-cement-retained type, a hybrid fixation method of cement-retained and non-cement-retained types, a screw-retained type, or an overdenture type. The information regarding the fixation method to bone or biological tissue may include, for example, information regarding the cement placement area in the cement-retained type or hybrid fixation type (e.g., including at least one of the placement location, placement range, and placement amount). Furthermore, the information regarding the fixation method to bone or biological tissue may include information regarding the cement placement area in the case of reinforcement with cement in the non-cement-retained type.

[0042] The information regarding the fixation method to bone or biological tissue may be, for example, at least one of information regarding autologous bone grafting and information regarding artificial bone grafting. The information regarding autologous bone grafting includes, for example, at least one of the following: whether or not autologous bone grafting is performed, the site where the autologous bone was obtained, the amount of autologous bone obtained, the amount of autologous bone grafted, the form of the autologous bone (e.g., at least one of crushed bone and block bone), and the content of the autologous bone (e.g., cancellous bone, etc.). The information regarding artificial bone grafting includes, for example, at least one of the manufacturer, material, and amount of the artificial bone to be grafted. For example, in the case of an artificial hip joint, there may be a lack of bone covering the acetabulum during cup installation. In such cases, the information regarding the fixation method to bone or biological tissue may be useful information regarding the fixation method to bone or biological tissue, including at least one of the necessity, amount, location, and area of ​​cancellous bone or block bone grafting.

[0043] The information regarding whether or not the implant has been antibacterial treated includes, for example, information indicating the suitability of the antibacterial implant for the patient, information indicating the probability of infection occurring at the affected area, information indicating the probability of infection reduction at the affected area, a prediction of the degree of inflammation at the affected area, or information indicating the probability of side effects occurring when the antibacterial treated implant is applied.Instead of the information regarding whether or not the implant has been antibacterial treated, the first training data 32 may include information indicating the concentration of blood markers related to the patient's resistance to bacterial infection and the results of a culture test in which a specific bacterium is cultured using the patient's blood.

[0044] The identifying unit 23 may identify inventory information of implants that can be implanted in the affected bone of the subject by referring to the possession status of the implants, which the acquiring unit 21 has acquired from the inventory management device 6. Alternatively, the identifying unit 23 may identify inventory information of surgical instruments used in a surgical treatment method suitable for the affected bone of the subject by referring to the possession status of the surgical instruments, which the acquiring unit 21 has acquired from the inventory management device 6.

[0045] The identification unit 23 may further identify instrument information indicating surgical instruments that can be used in a surgical treatment method suitable for the affected bone of the subject, for example, by inputting input information into the trained first learning model 34. In this case, the first training data 32 used to train the trained first learning model 34 may be data that includes information about surgical instruments used in a surgical treatment method applied to each of the affected bones of multiple patients.

[0046] The information about surgical instruments may be information about surgical instruments for bone processing before implanting an implant. For example, if the affected part of the subject is the hip joint and the surgical treatment appropriate for the affected bone of the subject includes implanting an artificial hip joint, a reamer or rasp, which is one of the instruments for cutting the affected bone, may be used as a preparatory step for inserting a stem into the affected bone. A reamer or rasp is an instrument for cutting the inner wall of the medullary cavity of the femur into which the stem of the artificial hip joint is inserted. A plurality of reamers or rasps are prepared in different sizes corresponding to, for example, the size or type of stem. In other words, information about the size (i.e., the number) of the stem or rasp may be information about the surgical instrument. The information about the surgical instrument may include a reamer or rasp size that does not correspond to the size or type of stem. More specifically, the information about the surgical instrument may include a reamer or rasp size that is optimal for the patient, which differs from the size or type of stem.

[0047] The information about the surgical instrument may also be, for example, a trial instrument to be used during surgery. The trial instrument may be, for example, an instrument for confirming the size of an implant or a surgical instrument, or an instrument for confirming the movement of an implant. In this case, the information about the surgical instrument may be, for example, the trial instrument required for the surgery, the size or shape of a trial instrument that may be compatible with the patient, etc. In a total hip replacement surgery, the trial instrument may include, for example, a neck trial, a ball trial, a broach trial, a stem trial, a plug trial, or a cup trial. In a total knee replacement surgery, the trial instrument may include, for example, a femoral trial, a plate trial, a tibial tray trial, a tibial stem trial, etc.

[0048] The information about the surgical instrument may, for example, indicate that a surgical instrument suitable for the patient of the input information is not available from the same manufacturer as the implant manufacturer. The information about the surgical instrument may, for example, suggest the use of a custom-made surgical instrument if a surgical instrument suitable for the patient of the input information is not available from a general surgical instrument manufacturer.

[0049] In response to input information being input to the input layer 231 (see FIG. 4), the identification unit 23 performs calculations based on the trained first learning model 34 and outputs a surgical treatment method suitable for the affected bone of the subject and an implant that can be used in the surgical treatment method from the output layer 232 (see FIG. 4). As an example, the identification unit 23 may be configured to extract features from the input information and use them as input data. Publicly known algorithms such as those listed below may be applied to extract the features. Convolutional neural network (CNN). Autoencoder. Recurrent neural network (RNN). ·LSTM (Long Short-Term Memory). ·ConvLSTM (Convolutional Long Short-Term Memory).

[0050] The trained first learning model 34 is a computational model used by the identification unit 23 when performing computations based on input data. The trained first learning model 34 is generated by the learning unit 25 performing machine learning on an untrained neural network using first teacher data 32, which will be described later. Here, the trained first learning model 34 can also be applied to non-human animals. In this case, the "patient" in the first teacher data 32 may be of the same biological species as the "subject." In other words, the information processing device 1 according to the present disclosure can also identify a surgical treatment method suitable for the affected bone of a non-human animal. Specific examples of the first teacher data 32, the configuration of the neural network, and the learning process will be described later.

[0051] <Output section 24> The output unit 24 transmits each piece of information identified by the identification unit 23 to the terminal device 7. The output unit 24 may extract information about the implant identified by the identification unit 23 from the implant / surgical instrument information database 33. The information processing device 1 may be configured to include a display unit (not shown). In that case, the output unit 24 causes the display unit to display each piece of information.

[0052] <Study Section 25> The learning unit 25 controls the learning process for an untrained neural network. The learning unit 25 executes the learning process for the untrained neural network to create a trained neural network that functions as the identification unit 23. For this learning, first teacher data 32 (described later) is used. Specific examples of the learning performed by the learning unit 25 will be described later.

[0053] (Configuration of the identification unit 23) The configuration of the identification unit 23 will be described below with reference to Fig. 4. The configuration shown in Fig. 4 is an example, and the configuration of the identification unit 23 is not limited to this.

[0054] 4, the identification unit 23 performs calculations based on the trained first learning model 34 on input data input to the input layer 231, and outputs output data from the output layer 232. The output data is at least one of instrument information, prediction information, parameter information, and implant information.

[0055] The identification unit 23 in FIG. 4 includes a neural network having an input layer 231 and an output layer 232. While FIG. 4 illustrates a case where the neural network is an LSTM, this is not limiting. For example, the neural network may be a ConvLSTM network that combines a CNN and an LSTM. The input layer 231 can extract features related to changes in input data. The output layer 232 can calculate new features based on the features extracted by the input layer 231, the changes over time in the input data, and initial values. The input layer 231 and the output layer 232 each include multiple LSTM layers. Each of the input layer 231 and the output layer 232 may include three or more LSTM layers.

[0056] (Learning process by learning unit 25) The learning process for generating the trained first learning model 34 will be described below with reference to Fig. 5. Fig. 5 is a flowchart showing an example of the flow of the learning process by the learning unit 25.

[0057] The learning unit 25 acquires first training data 32 from the storage unit 3 (step S1). The first training data 32 includes explanatory variables and objective variables to be input to the input layer 231. Here, the explanatory variables are bone information and shape characteristics related to at least one of bone density and bone quality of the bone of each of multiple patients before a surgical treatment including implant placement is performed, and the objective variable is treatment information related to the surgical treatment performed on the bone. The bone information related to at least one of bone density and bone quality of the bone before a surgical treatment including implant placement is performed may be information indicating the measurement results of a bone metabolic marker or information indicating bone density estimated based on an X-ray image. The bone information may include, for example, at least one of bone mass, bone density, trabecular number, trabecular spacing, trabecular connectivity density, cancellous bone structure index, and measurement results of a bone metabolic marker.

[0058] Next, the learning unit 25 inputs bone information of a patient (referred to as patient A) to whom a surgical treatment was applied to the input layer 231 (step S2).

[0059] Next, the learning unit 25 obtains output data related to the surgical treatment applied to the bones of patient A from the output layer 232 (step S3). This output data contains the same content as the objective variables of the first training data 32. In FIG. 5, the order of steps S2 and S3 may be reversed. Alternatively, in FIG. 5, steps S2 and S3 may be configured to be executed simultaneously.

[0060] Next, the learning unit 25 acquires the objective variables for patient A included in the first teacher data 32. Then, the learning unit 25 compares the output data acquired in step S3 with the objective variables for patient A to calculate an error (step S4), and adjusts the first learning model being learned so as to reduce the error (step S5).

[0061] Any known method can be applied to adjust the first learning model during learning. For example, the backpropagation method may be adopted as a method for adjusting the first learning model. The adjusted first learning model becomes a new first learning model, and the identification unit 23 uses the new first learning model in subsequent calculations. During the adjustment stage of the first learning model, parameters used by the identification unit 23 (e.g., filter coefficients, weighting coefficients, etc.) may be adjusted.

[0062] If the error is not within a predetermined range and explanatory variables for all patients included in the first teacher data 32 have not been input (NO in step S6), the learning unit 25 returns to step S2 and repeats the learning process. If the error is within a predetermined range and explanatory variables for all patients included in the first teacher data 32 have been input (YES in step S6), the learning unit 25 ends the learning process.

[0063] When the above-described learning process is adopted, the identification unit 23 can identify at least one of instrument information, prediction information, parameter information, and implant information, which is information regarding a surgical treatment method suitable for the affected bone of the subject, from input information including a medical image showing the affected bone of the subject.

[0064] (Variation 1) The first training data 32 may further include at least one of event information related to events that occurred during implant placement surgery in each of the bones of multiple patients and information on procedures performed during the implant placement surgery. By using such first training data 32, the trained first learning model 34 can output, from medical images showing the bones of a subject, events that may occur when performing implant placement surgery on the subject, procedures to be performed, etc.

[0065] Here, the event information may be information regarding one or more of fracture, loosening, implant fracture, range of motion, and infection during implant placement. The information regarding fracture may be, for example, information regarding whether or not a fracture occurred in the affected bone when a stem was inserted into the medullary canal of a bone that had been cut with a reamer or rasp. Alternatively, the information regarding fracture may be, for example, information regarding whether or not a bone fracture occurred when a rasp of a certain size was inserted into the medullary canal of the subject's bone. The event information may also include information regarding the size of the reamer or rasp used in the cutting process when the bone fracture occurred.

[0066] The surgical procedure information may be information regarding the impact when embedding the implant, the time required for the surgery, the amount of bleeding, the amount of blood transfusion, the use of bone cement, the type of bone cement, the position where the bone cement was applied, the use of antibiotics, and treatments such as infection control and hemostasis. The information regarding the impact may include, for example, the number of impacts, the maximum instantaneous load, the impact sound, the type of impactor, the type of hammer, etc. For a ceramic component, it may be output that a resin hammer should be used.

[0067] According to this configuration, the information processing device 1 can provide a doctor or the like with information to be noted in advance when formulating a surgical treatment method to be applied to the subject. This allows the information processing device 1 of the subject to more highly support the formulation of a surgical treatment plan suitable for the affected bone of the subject.

[0068] (Variation 2) The adjustment of the trained first learning model 34 may be performed on a computer different from the information processing device 1. In this case, the information processing device 1 may install and use the trained first learning model 34. In other words, the learning unit 25 is not an essential component of the information processing device 1.

[0069] (Processing performed by information processing device 1) The flow of processing performed by the information processing device 1 will be described below with reference to Fig. 6. Fig. 6 is a flowchart showing an example of the flow of processing performed by the information processing device 1. Fig. 6 shows an example of processing performed when the information processing device 1 outputs the following pieces of information from input information, but the information processing device 1 may be configured to output at least one of these pieces of information: Instrument information indicating surgical instruments to be used in a surgical treatment method suitable for the affected bone of the subject. Prediction information predicting the state of the affected bone of the subject after the surgical treatment method has been applied. Parameter information indicating parameters that may be selected when applying a surgical treatment to the affected bone of the subject. Implant information regarding implants that may be placed in the subject's affected bone.

[0070] First, the acquisition unit 21 acquires input information including a medical image showing the affected bone of the subject (step S11: acquisition step).

[0071] Next, the identification unit 23 inputs the input information into the trained first learning model 34 to identify instrument information, prediction information, parameter information, and implant information related to a surgical treatment method suitable for the affected bone of the subject (step S12: identification step).

[0072] The output unit 24 outputs each piece of information identified in step S12 (step S13: output step).

[0073] According to this configuration, the information processing device 1 and the information processing system 100a can output useful information for considering and deciding on a surgical treatment method suitable for the affected bone of the subject. The instrument information, prediction information, parameter information, and implant information output from the information processing device 1 are all important information for doctors and other professionals to consider a surgical treatment method suitable for the affected bone of the subject. For example, depending on the availability of surgical instruments and implants, the timing of applying a surgical treatment to the subject may have to wait until the implant to be used is delivered, or the schedule for applying a surgical treatment to a person other than the subject may have to be adjusted. By outputting the above information, the information processing device 1 and the information processing system 100a support the formulation of a surgical treatment plan suitable for the affected bone of the subject. Since osteotomy may be difficult depending on the bone quality (e.g., osteopetrosis), for example, an estimated osteotomy time may also be output.

[0074] [Embodiment 2] Other embodiments of the present disclosure will be described below. For convenience of explanation, the same reference numerals will be used to designate components having the same functions as those described in the above embodiment, and the description thereof will not be repeated.

[0075] The information processing system 100a may be configured to generate, from the medical image included in the input information, a first predicted image that is generated from the medical image included in the input information and that anticipates the state of the affected bone of the subject after a surgical treatment has been applied to the affected bone of the subject. The information processing system 100a may also be configured to output parameter information that includes surgical parameters estimated from the results of image analysis of the first predicted image and that can be selected by a medical professional who applies a surgical treatment suitable for the affected bone of the subject.

[0076] Examples of parameter information include the angle at which the bone (for example, the femoral neck in the case of total hip replacement surgery, and the femoral condyle, distal femur, or proximal tibia in the case of total knee replacement surgery) is resected, the resection amount, the insertion angle of the instrument into the human body (including, for example, the medullary cavity), the insertion depth, the number of rotations of the instrument (including torque), the angle at which the instrument is removed, suggestions for osteophyte removal, removal methods for osteophyte removal (for example, the resection amount, resection range, etc.), and the bone cutting time. These parameter information may be set in combination, or a single parameter may be set multiple times.

[0077] (Configuration of information processing device 1a) The configuration of the information processing device 1a having such a configuration will be described with reference to Fig. 7. Fig. 7 is a block diagram showing an example of the configuration of the information processing device 1a. The information processing device 1a can be applied to information processing systems 100a, 100b, 100c, and 100d.

[0078] The information processing device 1a includes a control unit 2a that controls each unit of the information processing device 1a in an integrated manner, and a storage unit 3a that stores various data used by the control unit 2a. The control unit 2a includes an acquisition unit 21, an identification unit 23, an output unit 24, and a learning unit 25, as well as a generation unit 26 and an estimation unit 27. The storage unit 3a stores a control program 31, which is a program for performing various controls of the information processing device 1a, first teacher data 32, an implant / surgical instrument information database 33, a trained first learning model 34, and a trained second learning model 35.

[0079] The generation unit 26 generates a first predicted image from the medical image included in the input information using a second learning model 35 trained using the second training data. Here, the second training data is data including medical images of the affected bone of a patient to which a surgical treatment suitable for the affected bone of the subject has been applied, captured before and after the application of the surgical treatment. The output unit 24 transmits the generated first predicted image to the terminal device 7. Here, the first predicted image may be an image converted from the medical image (two-dimensional image) included in the input information into a three-dimensional image using a known image conversion method.

[0080] By checking the first predicted image before actually applying a surgical treatment to the subject, a doctor or the like can determine whether the surgical treatment suitable for the affected bone of the subject is really appropriate for the subject. This allows the information processing device 1a to support the application of a surgical treatment more suitable for the affected bone of the subject.

[0081] The estimation unit 27 may estimate surgical parameters that can be selected by a physician or the like who will apply a surgical treatment to a subject, based on the results of image analysis of the first predicted image. Here, the surgical parameters may include any operation parameters related to the surgical procedure and surgical instruments. The surgical parameters may be, for example, the amount of bone resection. The surgical parameters may be parameters that are monitored or changed by a physician or the like during surgery, or may be parameters that are selected before surgery.

[0082] Furthermore, when an operation to change the surgical parameters estimated by the estimation unit 27 is received, the generation unit 26 may generate a second predicted image by processing the first predicted image in accordance with the change. This allows the information processing device 1a to facilitate trial and error by a doctor or the like to consider a surgical treatment method more appropriate for the bones of the subject, and to support the application of a surgical treatment method more appropriate for the bones of the subject.

[0083] Alternatively, the estimation unit 27 may output an estimation result regarding the bone strength of the affected bone of the subject from the first predicted image. The bone strength of the affected bone of the subject is important information for formulating an appropriate surgical treatment method. The estimation result regarding the bone strength may be, for example, an estimated value of bone density. By checking such an estimation result, a doctor or the like can correctly determine whether or not a surgical treatment method suitable for the affected bone of the subject can actually be applied. This allows the information processing device 1a to support the application of a surgical treatment method more suitable for the affected bone of the subject.

[0084] [Embodiment 3] (Configuration of information processing system 100b) The information processing device 1 may not be a computer installed in a predetermined medical facility 8, but may be communicably connected to a LAN installed in each of a plurality of medical facilities 8 via a communication network 9. Fig. 2 is a diagram showing an example configuration of an information processing system 100b according to another embodiment of the present disclosure.

[0085] In addition to one or more terminal devices 7a, a medical image management device 5a and an inventory management device 6a may be communicably connected to the LAN within medical facility 8a. Furthermore, in addition to terminal device 7b, a medical image management device 5b and an inventory management device 6b may be communicably connected to the LAN within medical facility 8b. In this disclosure, when there is no particular distinction between medical facilities 8a and 8b, they will be referred to as the "medical facility 8." Furthermore, when there is no particular distinction between terminal devices 7a and 7b, and medical image management devices 5a and 5b, they will be referred to as the "terminal device 7," the "medical image management device 5," and the "inventory management device 6," respectively.

[0086] 2 shows an example in which LANs of medical facilities 8a and 8b are connected to a communication network 9. The information processing device 1 is only required to be communicably connected to the medical image management device 5 and the inventory management device 6 in each medical facility via the communication network 9, and is not limited to the configuration shown in Fig. 2. For example, the information processing device 1 may be installed in the medical facility 8a or the medical facility 8b.

[0087] In the information processing system 100b having such a configuration, the information processing device 1 can acquire medical images of a subject Pa who has been examined at a medical facility 8a from a medical image management device 5a at the medical facility 8a. The information processing device 1 can also acquire the inventory status of implants, surgical instruments, and the like used in various treatments from an inventory management device 6a at the medical facility 8a. The information processing device 1 then transmits at least one of instrument information, prediction information, parameter information, and implant information related to a surgical treatment method suitable for the affected bone of the subject Pa to a terminal device 7a installed at the medical facility 8a. The information processing device 1 transmits instrument information, prediction information, parameter information, and implant information related to a surgical treatment method suitable for the affected bone of the subject Pb to a terminal device 7b.

[0088] If the medical facility 8a does not have (or lacks) implants that can be used in surgical treatment suitable for the affected bone of the subject Pa, the information processing device 1 may send at least one of the following information to the terminal device 7a: · Information about the implant ordering process. · Information about the expected delivery time if you order an implant. The timing of applying a surgical treatment to the subject Pa may be affected by the availability of implants at the medical facility 8a. If the medical facility 8a does not have the implant in stock, the implant must be ordered and the subject must wait until the implant is delivered. By outputting the above information, the information processing device 1 supports the formulation of a surgical treatment plan appropriate for the affected bone of the subject.

[0089] [Embodiment 4] An information processing device 1c according to a fourth embodiment and an information processing system 100c including the information processing device 1c will be described below. In this embodiment, the information processing device 1c outputs estimated bone condition information relating to the future or past bone condition of a subject, estimated using a learning model based on input information including medical information of the subject. The medical information of the subject includes first medical information having medical images depicting the subject's bones and second medical information having feature information of the subject at a time different from the time the medical images were captured. The learning model is trained using training data including a plurality of medical images depicting the bones of a specific person and information having feature information of the specific person at a time different from the time the medical images were captured.

[0090] (Configuration of information processing system 100c) First, the configuration of an information processing system 100c according to this embodiment will be described with reference to Fig. 8. Fig. 8 is a diagram showing an example of the configuration of an information processing system 100c in a medical facility 8 in which an information processing device 1c has been introduced.

[0091] The information processing system 100c includes an information processing device 1c and one or more terminal devices 7 communicably connected to the information processing device 1c. The information processing device 1c estimates bone condition information regarding the future or past bone condition of a subject from medical information including first medical information having a medical image of the subject's bones and second medical information having characteristic information of the subject at a time different from the time the medical image was captured. In the following description, an example of estimating (predicting) bone condition information regarding the subject's future bone condition will be described, and the "bone condition information regarding the future bone condition" will also be simply referred to as "future bone condition information." The information processing device 1c is a computer that transmits estimated information regarding the subject's future bone condition information to the terminal device 7. The information processing device 1c may be installed on a cloud. In this case, the terminal device 7 transmits the first medical information to the information processing device 1c on the cloud via a communication network and receives the estimated information estimated by the information processing device 1c via the communication network.

[0092] In addition to the information processing device 1c and the terminal device 7, a medical image management device 5, an attribute information management device 4, an inventory management device 6, a test value management device 10, a diagnosis result management device 11, and a bone information management device 12 may be communicatively connected to the LAN within the medical facility 8.

[0093] The medical image management device 5 is a computer that functions as a server for managing medical images taken at the medical facility 8. The medical image management device 5 may be installed, for example, within the medical facility 8, or may be a cloud. When the medical image management device 5 is a cloud, the medical images can be acquired via a communication network. The medical images may be images similar to the medical images used in the first to third embodiments. Furthermore, the medical images in this embodiment may be any of X-ray images, CT images, MRI images, ultrasound images taken by an ultrasound diagnostic device, PET images, and DXA images. The information processing device 1c may acquire medical images showing the bones of the subject from the medical image management device 5.

[0094] The attribute information management device 4 is a computer that functions as a server for managing the subject's attribute information. The attribute information includes at least one of age, sex, height, weight, race, lifestyle information, medication information, occupational information, blood test information, urine test information, saliva test information, medical history, the subject's family medical history, genetic information, menopausal information, FRAX items, and menopause estimation based on hormone information. The lifestyle information may be, for example, sleep time, wake-up time, sleep duration, daily exercise amount, dietary content, meal times, meal duration, and blood glucose level. The dietary content may include, for example, at least one of the name of the dish, ingested ingredients, and intake amount. The dietary content may be, for example, an estimated intake of at least one of calcium, vitamin B, vitamin D, and vitamin K. The blood glucose level may be, for example, a designated value estimated from parameters acquired by a wearable device.

[0095] The medication information may include, for example, information such as the name of the medication, the amount taken, and the duration of medication. The information about medications taken may include information about steroid drugs being used. The blood test information may be, for example, information about the results of at least one of a biochemistry test, a glucose metabolism test, and an endocrine system test.

[0096] The test value management device 10 is a computer that functions as a server for managing test values ​​obtained from tests performed at the medical facility 8. The test values ​​include at least one of bone density, KL (Kellgren-Lawrence) classification, bone morphology angle, muscle mass, MMSE (Mini Mental State Examination), blood test values, liver function markers, uric acid levels, and malignant tumor markers. The information processing device 1c may obtain the test values ​​of the subject from the test value management device 10.

[0097] The diagnostic results management device 11 is a computer that functions as a server for managing diagnostic results obtained by diagnoses performed in the medical facility 8. The information processing device 1c may obtain the diagnostic results of the subject from the diagnostic results management device 11.

[0098] The bone information management device 12 is a computer that functions as a server for managing bone information acquired at the medical facility 8. The information processing device 1c may acquire past bone information of the subject from the bone information management device 12.

[0099] (Configuration of information processing device 1c) Next, the configuration of an information processing device 1c applied to the information processing system 100c shown in Fig. 8 will be described with reference to Fig. 9. Fig. 9 is a block diagram showing an example of the configuration of the information processing device 1c.

[0100] The information processing device 1c includes a control unit 2c that performs overall control of the various units of the information processing device 1c, and a storage unit 3c that stores various data used by the control unit 2c. The control unit 2c includes an acquisition unit 21, an estimation unit 27c, an output unit 24, and a learning unit 25c. The estimation unit 27 described in the second embodiment may be 27c described in this embodiment. The storage unit 3c stores a control program 31, which is a program for performing various controls of the information processing device 1c, as well as third teacher data 36 and a trained third learning model 37.

[0101] <Acquisition part 21> In this embodiment, the acquisition unit 21 acquires input information including medical information of the subject. The input information is data input to the estimation unit 27c. In this embodiment, the input information includes first medical information having a medical image showing the subject's bones and second medical information having feature information of the subject at a time different from the time the medical image was captured. In the following description, the medical image showing the subject's bones included in the first medical information may be referred to as the first medical image. The second medical information may be information captured, for example, 15 days, 1 month, 3 months, 6 months, 1 year, 3 years, or 5 years after the medical image of the first medical information was captured. The second medical information may be past information prior to the time the medical image included in the first medical information was captured, or future information after the time.

[0102] The characteristic information included in the second medical information includes at least one of the subject's medical images, past bone information, attribute information, test values, and diagnosis results. In the following description, a medical image of the subject's bones included in the second medical information may be referred to as the second medical image. The second medical information may be information from multiple points in time, or may be information from a single point in time.

[0103] The acquisition unit 21 may, for example, acquire a first medical image and / or a second medical image from the medical image management device 5, acquire attribute information of the subject from the attribute information management device 4, acquire test values ​​of the subject from the test value management device 10, acquire diagnostic results of the subject from the diagnostic result management device 11, or acquire past bone information of the subject from the bone information management device 12. For example, the acquisition unit 21 acquires, as input information, an X-ray image taken at a first time point as the first medical information and an X-ray image taken at a time point different from the first time point, for example, a second time point earlier than the first time point, as the second medical information. The acquisition unit 21 may further acquire, as input information, an X-ray image taken at a third time point earlier than the second time point as the second medical information.

[0104] The first medical information may include the same information elements as the feature information contained in the second medical information. In other words, the first medical information may include, in addition to the first medical image, the same information as the feature information contained in the second medical information. For example, if the second medical information includes height information of the subject as feature information, the first medical information may include, in addition to the first medical image, the height information of the subject at the time the first medical image was captured.

[0105] <Estimation part 27c> The estimation unit 27c estimates the subject's future bone condition information by inputting the input information acquired by the acquisition unit 21 into the third learning model 37. Here, the third learning model 37 has been trained in advance using third training data 36. The third training data 36 is data including medical information of a specific person. The specific person may be a patient suffering from a bone-related disease or a person without a disease. The medical information included in the third training data 36 may include a plurality of pieces of information including medical images showing the bones of the specific person and characteristic information of the specific person at a time point different from the time point at which the medical images were captured.

[0106] The estimation unit 27c may estimate future or past bone condition information of the subject by inputting, as the input information, input information to the third learning model 37, including first medical information having medical images of the subject's bones and second medical information having characteristic information of the subject at a time different from the time the medical images were captured. By inputting the input information to the third learning model 37, the estimation unit 27c may estimate, as the bone condition information, at least one of the following: the probability of the subject's future or past fracture; the time at which the subject's future or past fracture will occur or has occurred (e.g., 4 to 5 years later); the subject's future or past bone density; and the subject's future or past bone quality. More specifically, when the bone condition information is bone density, the estimation unit 27c can estimate, for example, what the bone density was when the first medical information was acquired in the past, even if bone density has not been measured in the past. The estimation unit 27c may also estimate the subject's bone density at multiple future and past time points from the first medical information. The estimation unit 27c may estimate a transition of the bone mineral density of the subject from a certain point in the past to a certain point in the future. The information processing device 1c may graph the estimated transition and display it on the display unit.

[0107] The estimation unit 27c may estimate, as the bone condition information, what kind of bone condition information will be obtained or how the bone condition information will change if the subject undergoes treatment. More specifically, when the bone condition information is the subject's future bone density, the estimation unit 27c may estimate, as the bone condition information, the bone density or change in bone density when the subject undergoes treatment. Alternatively, the estimation unit 27c may estimate the details of the treatment in addition to the bone condition information. The information processing device 1c may then display the estimated details of the treatment on the display unit. The treatment may include, for example, taking medication, taking nutritional supplements, or improving lifestyle habits for a predetermined period of time. The medication may include information about a medication that has at least one of an effect on bone formation and an effect on bone resorption. Medication that has an effect on bone formation includes, but is not limited to, active vitamin D3 preparations (e.g., calcitriol, eldecalcitol, or alfacalcidol), teriparatide acetate, and teriparatide (genetically recombinant). Furthermore, examples of drugs that have an effect on bone resorption include, but are not limited to, calcitonin preparations, bisphosphonate preparations, and anti-RANKL monoclonal antibodies.

[0108] The third learning model 37 is a computational model used by the estimation unit 27c when performing computations based on input data. The third learning model 37 is generated by the learning unit 25c performing machine learning on an untrained neural network using third teacher data 36, ​​which will be described later. Here, the third learning model 37 can also be applied to non-human animals. In this case, the "predetermined person" in the third teacher data 36 may be the same biological species as the "subject." In other words, the information processing device 1c according to the present disclosure can also estimate the onset and / or progression of diseases in non-human animals. Specific examples of the third teacher data 36, ​​the configuration of the neural network, and the learning process will be described later.

[0109] <Output section 24> The output unit 24 transmits the information estimated by the estimation unit 27c to the terminal device 7. The information processing device 1c may be configured to include a display unit (not shown). In this case, the output unit 24 causes the display unit to display the information estimated by the estimation unit 27c.

[0110] <Study Section 25c> The learning unit 25c controls the learning process for the untrained neural network. The learning unit 25c executes the learning process for the untrained neural network to create a trained neural network that functions as the estimation unit 27c. Third teacher data 36 (described later) is used for this learning. Specific examples of the learning performed by the learning unit 25c will be described later.

[0111] (Configuration of the estimation unit 27c) The configuration of the estimation unit 27c will be described below with reference to Fig. 10. The configuration shown in Fig. 10 is an example, and the configuration of the estimation unit 27c is not limited to this.

[0112] 10, the estimation unit 27c performs calculations based on the third learning model 37 on input data input to the input layer 271, and outputs output data from the output layer 272. In this embodiment, the output data is future bone condition information of the subject. The future bone condition information may be, for example, the probability of fracture in the subject's future, the subject's bone mineral density in the subject's future, or the subject's bone quality in the subject's future.

[0113] The estimation unit 27c in FIG. 10 includes a neural network having an input layer 271 and an output layer 272. While FIG. 10 illustrates a case where the neural network is an LSTM, this is not limiting. For example, the neural network may be a ConvLSTM network that combines a CNN and an LSTM. The input layer 271 can extract features related to changes in input data. The output layer 272 can calculate new features based on the features extracted by the input layer 271, changes over time in the input data, and initial values. The input layer 271 and the output layer 272 each include multiple LSTM layers. Each of the input layer 271 and the output layer 272 may include three or more LSTM layers.

[0114] (Learning process by learning unit 25c) The learning process for generating the third learning model 37 will be described below with reference to Fig. 11. Fig. 11 is a flowchart showing an example of the flow of the learning process by the learning unit 25c.

[0115] The learning unit 25c acquires third training data 36 from the memory unit 3c (step S21). The third training data 36 includes a plurality of pieces of information, including bone condition information regarding the future bone condition of a specific person, and includes explanatory variables and objective variables to be input to the input layer 271. In this embodiment, the explanatory variables are medical images showing the bones of the specific person and characteristic information of the specific person at a time different from the time when the medical images were captured, and the objective variables are bone condition information for each person. The third training data 36 may also include details of treatment for the specific person. The treatment may include, for example, taking medicine, taking nutritional supplements, or improving lifestyle habits over a specific period of time. The medicine may include information about a medicine that has at least one of an effect on bone formation and an effect on bone resorption. Examples of drugs that affect bone formation include, but are not limited to, activated vitamin D3 preparations (e.g., calcitriol, eldecalcitol, or alfacalcidol), teriparatide acetate, and teriparatide (recombinant). Examples of drugs that affect bone resorption include, but are not limited to, calcitonin preparations, bisphosphonate preparations, and anti-RANKL monoclonal antibodies.

[0116] Next, the learning unit 25c inputs into the input layer 271 a medical image showing the bones of a person (referred to as person A) and characteristic information of person A at a time different from the time the medical image was taken, as information including future bone condition information (step S22).

[0117] Next, the learning unit 25c acquires output data related to the bone condition information of person A from the output layer 272 (step S23). This output data contains the same content as the objective variable of the third teacher data 36. In FIG. 11, the order of steps S22 and S23 may be reversed. Alternatively, in FIG. 11, steps S22 and S23 may be configured to be executed simultaneously.

[0118] Next, the learning unit 25c acquires the objective variable for person A included in the third teacher data 36. Then, the learning unit 25c compares the output data acquired in step S23 with the objective variable for person A to calculate an error (step S24), and adjusts the learning model being learned so as to reduce the error (step S25).

[0119] Any known method can be applied to adjust the learning model during learning. For example, the backpropagation method may be adopted as a method for adjusting the learning model. The adjusted learning model becomes a new learning model, and the estimation unit 27c uses the new learning model in subsequent calculations. During the learning model adjustment stage, parameters used by the estimation unit 27c (e.g., filter coefficients, weighting coefficients, etc.) can be adjusted.

[0120] If the error is not within a predetermined range and explanatory variables for all people included in the third teacher data 36 have not been input (NO in step S26), the learning unit 25c returns to step S22 and repeats the learning process. If the error is within a predetermined range and explanatory variables for all people included in the third teacher data 36 have been input (YES in step S26), the learning unit 25c ends the learning process.

[0121] When the above-described learning process is adopted, the estimation unit 27c can estimate the future bone condition information of the subject from medical information including first medical information having a medical image showing the subject's bones, and second medical information having characteristic information of the subject at a time different from the time when the medical image was taken.

[0122] In one embodiment of the present disclosure, the third learning model 37 may be a learning model trained using training data including medical information of a specific person acquired at multiple different time points. For example, the third learning model 37 may be a learning model trained using training data including medical images of the specific person acquired at multiple different time points as explanatory variables and bone density of the specific person acquired at the multiple different time points as a target variable. In this way, by inputting medical information of the subject acquired at at least two different time points into the third learning model 37, estimation accuracy can be improved.

[0123] (Processing performed by information processing device 1c) The flow of processing performed by the information processing device 1c will be described below with reference to Fig. 12. Fig. 12 is a flowchart showing an example of the flow of processing performed by the information processing device 1c.

[0124] First, the acquisition unit 21 acquires medical information including first medical information having a medical image showing the subject's bones and second medical information having characteristic information of the subject at a time different from the time the medical image was taken (step S31: acquisition step).

[0125] Next, the estimation unit 27c inputs the acquired medical information into the third learning model 37 to estimate future bone condition information of the subject (step S32: estimation step).

[0126] The output unit 24 outputs each piece of information including the bone condition information estimated in step S32 (step S33: output step).

[0127] According to this configuration, the information processing device 1c and the information processing system 100c estimate future bone condition information of a subject from medical information including first medical information having a medical image showing the subject's bones and second medical information having characteristic information of the subject at a time point different from the time point at which the medical image was captured. This improves the estimation accuracy compared to when bone condition information is estimated using input information including medical information acquired at a single time point.

[0128] The estimation unit 27c may estimate the bone condition information of the subject after a time shorter than the time interval between any two of the time point when the first medical information was acquired and at least one time point when the second medical information was acquired, thereby enabling more accurate estimation of the bone condition information based on information about changes in the condition of the subject over a time interval longer than the time interval from the current time point to the estimation time point.

[0129] The estimation unit 27c may estimate the future bone condition information of the subject by inputting input information including medical information at three or more points in time, i.e., first medical information having medical images showing the bones of the subject, and second medical information having feature information of the subject at two or more points in time different from the points in time at which the medical images were captured, into the third learning model 37. This allows the degree of acceleration of the time change in the bone condition up to the present time to be known, and enables more accurate estimation of the bone condition information at the estimation time.

[0130] The estimation unit 27c may estimate whether the subject has undergone menopause based on the subject's attribute information and the degree of acceleration of time-dependent changes in bone condition at three or more points in time. In this case, the estimation unit 27c may use the estimated menopause information as the menopause information of the subject's attribute information.

[0131] When the second medical information is a medical image, the area depicted in the medical image of the second medical information may be different from the area depicted in the medical image of the first medical information. For example, the area depicted in the image of the first medical information may be the chest, and the medical image of the second medical information may be a dental medical image. This allows for flexible use of images taken during health checkups or dental treatment, improving versatility.

[0132] The estimation unit 27c may estimate the subject's bone condition information at a time (hereinafter referred to as the estimation time) that is longer than the time interval (hereinafter referred to as the first time interval) between the earliest and latest of at least one time points at which the first medical information was acquired and the second medical information was acquired. As described above, the information processing system 100c of the present disclosure estimates the subject's future bone condition information using the first medical information and the second medical information acquired at different time points, and therefore can estimate the subject's future bone condition information within the first time interval from the current time point with high accuracy. Therefore, when estimating the subject's bone condition information after the first time interval from the current time point, the estimation can be performed using the subject's bone condition information estimated with high accuracy for the first time interval from the current time point. As a result, the subject's bone condition information can be estimated more accurately than when estimating the bone condition information using medical information from a single time point.

[0133] When the second medical information acquired by the acquisition unit 21 includes medical information at two or more time points, and any of the data in the second medical information and the first medical information at the two or more time points is anomalous data, the estimation unit 27c may input data excluding the anomalous data into the third learning model 37. The anomalous data may be, for example, a medically impossible test value resulting from a test error or the like. This configuration reduces the possibility of inputting incorrect information into the third learning model 37, thereby improving estimation accuracy. In this case, the estimation unit 27c may, for example, specify the lower and upper limits of medically possible values ​​for the test value as thresholds, and input data excluding data outside the range of the thresholds into the third learning model 37.

[0134] When the second medical information acquired by the acquisition unit 21 includes medical information at two or more points in time, and any data of the second medical information at the two or more points in time and the first medical information is idiosyncratic data, the estimation unit 27c may replace the idiosyncratic data with data that approximates the other data and input the data to the third learning model 37. This configuration can reduce the possibility of inputting erroneous information to the third learning model 37, thereby improving estimation accuracy.

[0135] Here, it has been known that bone mineral density significantly decreases upon menopause. Therefore, if the subject is a woman who has not yet undergone menopause, the estimation unit 27c may output at least one of a first estimation result assuming that the subject has undergone menopause and a second estimation result assuming that the subject has not undergone menopause. This allows for the output of more accurate estimation results that take into account the presence or absence of menopause. If the subject is a woman who has not yet undergone menopause, the estimation unit 27c may simultaneously output the first estimation result assuming that the subject has undergone menopause and the second estimation result assuming that the subject has not undergone menopause.

[0136] [Embodiment 5] (Configuration of information processing system 100d) The information processing device 1c may not be a computer installed in a predetermined medical facility 8, but may be communicably connected to a LAN installed in each of the multiple medical facilities 8 via a communication network 9. Fig. 13 is a diagram showing an example of the configuration of an information processing system 100d according to yet another aspect of the fourth embodiment.

[0137] In addition to one or more terminal devices 7a, a medical image management device 5a, an inventory management device 6a, an attribute information management device 4a, a test value management device 10a, a diagnostic result management device 11a, and a bone information management device 12a may be communicably connected to a LAN in a medical facility 8c. In addition to terminal device 7b, a medical image management device 5b, an inventory management device 6b, an attribute information management device 4b, a test value management device 10b, a diagnostic result management device 11b, and a bone information management device 12b may be communicably connected to a LAN in a medical facility 8d. In this disclosure, when there is no particular distinction between medical facilities 8c and 8d, they will be referred to as "medical facility 8." Furthermore, when no particular distinction is made between the terminal devices 7a and 7b, the medical image management devices 5a and 5b, the attribute information management devices 4a and 4b, the test value management devices 10a and 10b, the diagnostic result management devices 11a and 11b, and the bone information management devices 12a and 12b, they will be referred to as the "terminal device 7," the "medical image management device 5," the "attribute information management device 4," the "test value management device 10," the "diagnostic result management device 11," and the "bone information management device 12," respectively.

[0138] 13 shows an example in which LANs of medical facilities 8c and 8d are connected to a communication network 9. The information processing device 1c is only required to be communicably connected to the medical image management device 5, inventory management device 6, attribute information management device 4, test value management device 10, diagnosis result management device 11, and bone information management device 12 in each medical facility via the communication network 9, and is not limited to the configuration shown in FIG. 13. For example, the information processing device 1c may be installed in the medical facility 8c or the medical facility 8d.

[0139] In the information processing system 100d having such a configuration, the information processing device 1c can acquire medical images, attribute information, test values, and diagnosis results of the subject Pa who has been examined at the medical facility 8c from the medical image management device 5a, attribute information management device 4a, test value management device 10a, and diagnosis result management device 11a of the medical facility 8c. The information processing device 1c then transmits the estimated future bone condition information of the subject Pa to a terminal device 7a installed at the medical facility 8c. Similarly, the information processing device 1c transmits the future bone condition information of the subject Pb to a terminal device 7b.

[0140] [Special Notes] It is not essential that all of the functional blocks included in the control unit 2 of the information processing device 1 are included in the information processing device 1. For example, in the information processing system 100a, the terminal device 7 may have the function of the acquisition unit 21, and the information processing device 1 may receive input information from the terminal device 7. In the information processing systems 100b, 100c, and 100d, the information processing device 1 may also receive input information from the terminal device 7.

[0141] For example, in the information processing systems 100a, 100b, 100c, and 100d, the functions of the learning unit 25 may be configured to install on the information processing device 1 the trained first learning model 34, second learning model 35, and third learning model 37, which have been trained by a computer other than the information processing device 1.

[0142] For example, in the information processing systems 100a, 100b, 100c, and 100d, the function of the generation unit 26 may be provided by a computer or terminal device 7 other than the information processing device 1. Furthermore, in the information processing systems 100a, 100b, 100c, and 100d, the function of the estimation units 27 and 27c may be provided by a computer or terminal device 7 other than the information processing device 1.

[0143] [Software implementation example] The functions of the information processing devices 1, 1a, 1c (hereinafter referred to as "devices") can be realized by a program that causes a computer to function as the device, and a program that causes a computer to function as each control block of the device (particularly each part included in the control units 2, 2a, 2c).

[0144] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The control device and storage device execute the program, thereby realizing the functions described in each of the above embodiments.

[0145] The program may be non-transitory and may be recorded on one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

[0146] In addition, some or all of the functions of each of the control blocks can be realized by logic circuits. For example, integrated circuits in which logic circuits that function as each of the control blocks are formed are also included in the scope of the present disclosure. In addition, the functions of each of the control blocks can also be realized by, for example, a quantum computer.

[0147] Furthermore, each process described in each of the above embodiments may be executed by AI (Artificial Intelligence). In this case, the AI ​​may run on the control device or on another device (for example, an edge computer or a cloud server).

[0148] The invention according to the present disclosure has been described above based on the drawings and examples. However, the invention according to the present disclosure is not limited to the above-described embodiments. In other words, the invention according to the present disclosure can be modified in various ways within the scope of the present disclosure, and embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the invention according to the present disclosure. In other words, it should be noted that a person skilled in the art can easily make various modifications or corrections based on the present disclosure. It should also be noted that these modifications or corrections are included in the scope of the present disclosure.

[0149] 〔summary〕 An information processing system according to a first aspect of the present disclosure includes an acquisition unit that acquires input information including medical images of the affected bone of a subject; an identification unit having a first learning model trained using first training data including bone information regarding at least one of bone density and bone quality of the bone of each of a plurality of patients before a surgical treatment including an implant placement procedure is applied, shape characteristics, and treatment information regarding the surgical treatment applied to the bone; and an output unit that outputs at least one of instrument information indicating surgical instruments to be used in a surgical treatment suitable for the affected bone of the subject, identified by the identification unit based on the input information; prediction information predicting the condition of the affected bone of the subject after the surgical treatment is applied; parameter information indicating parameters that may be selected when applying a surgical treatment to the affected bone of the subject; and implant information regarding implants that may be implanted in the affected bone of the subject.

[0150] In the information processing system according to the second aspect of the present disclosure, in the first aspect, the implant information may include inventory information of implants that can be implanted in the affected bone of the subject.

[0151] In the information processing system of aspect 3 of the present disclosure, in aspect 1 or 2 above, the first training data may include, as the treatment information, the content and results of a surgical treatment applied to the affected bone of each of the multiple patients.

[0152] In an information processing system according to aspect 4 of the present disclosure, in any of aspects 1 to 3 above, the first training data may include information indicating a surgical treatment applied to the affected bone of each of the multiple patients, medical images of the affected bone of each of the multiple patients before the surgical treatment was applied, and information regarding implants embedded in the affected bone of each of the multiple patients.

[0153] In an information processing system according to aspect 5 of the present disclosure, in any of aspects 1 to 4 above, the first training data may include information regarding surgical instruments used in the surgical treatment applied to the affected bones of each of the multiple patients.

[0154] In the information processing system according to aspect 6 of the present disclosure, in any of aspects 1 to 5 above, the output unit may further output inventory information of surgical instruments used in a surgical treatment method suitable for the affected bone of the subject, identified by the identification unit based on the input information.

[0155] In the information processing system of aspect 7 of the present disclosure, in any of aspects 1 to 6 above, the first teaching data may further include at least one of event information regarding events that occurred during implant placement surgery in each of the bones of the multiple patients, and treatment information performed during the implant placement surgery.

[0156] In an information processing system according to aspect 8 of the present disclosure, in any of aspects 1 to 7 above, the output unit may output the predictive information including a first predicted image generated from the medical image included in the input information, the first predicted image assuming the state of the affected bone of the subject after a surgical treatment is applied to the affected bone.

[0157] In an information processing system according to aspect 9 of the present disclosure, in aspect 8 above, the first predicted image may be an image generated from the medical image included in the input information using a second learning model trained using second training data including medical images of the affected bone of a patient to whom a surgical treatment suitable for the affected bone of the subject has been applied, taken before and after the application of the surgical treatment.

[0158] The information processing system of aspect 10 of the present disclosure may, in aspect 8 or 9 above, output parameter information including surgical parameters estimated from the results of image analysis of the first predicted image, which may be selected by medical personnel to apply a surgical treatment method suitable for the affected bone of the subject to the subject.

[0159] The information processing system of aspect 11 of the present disclosure may further include a generation unit that, when an operation instructing a change to the estimated surgical parameters is received in aspect 10 above, generates a second predicted image by applying processing to the first predicted image corresponding to the change.

[0160] The information processing system of aspect 12 of the present disclosure, in any of aspects 8 to 11 above, may further include an estimation unit that outputs an estimation result regarding the strength of the bone in the affected area of ​​the subject from the first predicted image.

[0161] In the information processing system according to aspect 13 of the present disclosure, in any one of aspects 8 to 12, the first predicted image may be an image converted from a two-dimensional image into a three-dimensional image.

[0162] In the information processing system according to aspect 14 of the present disclosure, in any one of aspects 1 to 13 above, the surgical treatment may be at least one of artificial joint replacement surgery and dental implant surgery.

[0163] In the information processing system according to aspect 15 of the present disclosure, in any one of aspects 1 to 14, the surgical treatment may be performed by a surgical robot.

[0164] A control method of an information processing system according to aspect 16 of the present disclosure includes an acquisition step of acquiring input information including medical images of the affected bone of a subject; and an output step of using a first learning model trained using first training data including bone information regarding at least one of bone density and bone quality of the bone of each of a plurality of patients before a surgical treatment including an implant placement procedure is applied, shape characteristics, and treatment information regarding the surgical treatment applied to the bone, to output at least one of instrument information indicating surgical instruments to be used in a surgical treatment suitable for the affected bone of the subject, identified based on the input information; prediction information predicting the condition of the affected bone of the subject after the surgical treatment is applied; parameter information indicating parameters that may be selected when applying a surgical treatment to the affected bone of the subject; and implant information regarding an implant that may be implanted in the affected bone of the subject.

[0165] The control program of the information processing device according to aspect 17 of the present disclosure is a control program for causing a computer to function as an information processing system described in any one of aspects 1 to 15 above, and is a control program for causing a computer to function as the acquisition unit, the identification unit, and the output unit.

[0166] A recording medium according to an eighteenth aspect of the present disclosure is a computer-readable recording medium on which the control program according to the seventeenth aspect is recorded. [Explanation of symbols]

[0167] 1, 1a Information processing device 21 Acquisition Department 23 Specific section 24 Output section 26 Generation part 27 Estimation part 32 First training data 34 Trained First Learning Model (First Learning Model) 35 Trained Second Learning Model (Second Learning Model) 100a, 100b, 100c, 100d Information Processing Systems S11 Acquisition step S12 Specific step S13 Output Step

Claims

1. an acquisition unit that acquires input information including a medical image showing the affected bone of the subject; an identification unit having a first learning model trained using first training data including bone information relating to at least one of bone density and bone quality of the bone of each of a plurality of subjects before a surgical treatment including an implant placement procedure is applied, shape characteristics, and treatment information relating to the surgical treatment applied to the bone; an output unit that outputs at least one of: instrument information indicating a surgical instrument to be used in a surgical treatment method suitable for the affected bone of the subject, which is identified by the identification unit based on the input information; prediction information that predicts the state of the affected bone of the subject after the surgical treatment method has been applied; parameter information that indicates parameters that may be selected when applying a surgical treatment method to the affected bone of the subject; and implant information regarding an implant that may be embedded in the affected bone of the subject.

2. The information processing system according to claim 1 , wherein the implant information includes inventory information of implants that can be implanted in the affected bone of the subject.

3. The information processing system according to claim 1 or 2, wherein the first training data includes, as the treatment information, the content and results of surgical treatments applied to the affected bones of each of the plurality of subjects.

4. 3. The information processing system of claim 1, wherein the first training data includes information indicating a surgical treatment applied to the affected bone of each of the plurality of study subjects, medical images showing the affected bone of each of the plurality of study subjects before the surgical treatment was applied, and information regarding implants embedded in the affected bone of each of the plurality of study subjects.

5. The information processing system according to claim 1 or 2, wherein the first training data includes information regarding surgical instruments used in surgical treatments applied to the affected bones of each of the plurality of subjects.

6. The information processing system according to claim 1 or 2, wherein the output unit further outputs inventory information of surgical instruments used in a surgical treatment method suitable for the affected bone of the subject, identified by the identification unit based on the input information.

7. The information processing system of claim 1 or 2, wherein the first training data further includes at least one of event information regarding events that occurred during implant placement surgery for each of the multiple learning subjects, and treatment information performed during the implant placement surgery.

8. The output unit 2. The information processing system of claim 1, wherein the predictive information includes a first predicted image generated from the medical image included in the input information, the first predicted image assuming the state of the affected bone of the subject after a surgical treatment is applied to the affected bone.

9. 9. The information processing system of claim 8, wherein the first predicted image is an image generated from the medical images included in the input information using a second learning model trained using second training data including medical images of the affected bone of a training subject to which a surgical treatment appropriate for the affected bone of the subject has been applied, taken before and after the application of the surgical treatment.

10. The output unit 10. The information processing system according to claim 8, wherein the parameter information includes surgical parameters estimated from the results of image analysis of the first predicted image, the surgical parameters being selectable by a medical professional who applies to the subject a surgical treatment method suitable for the affected bone of the subject.

11. 11. The information processing system according to claim 10, further comprising a generation unit that, when an operation instructing a change to the estimated surgical parameters is received, generates a second predicted image by processing the first predicted image in accordance with the change.

12. The information processing system according to claim 8 , further comprising an estimation unit that outputs an estimation result regarding bone strength of the affected part of the subject from the first predicted image.

13. The information processing system according to claim 8 , wherein the first predicted image is an image converted from a two-dimensional image to a three-dimensional image.

14. 3. The information processing system according to claim 1, wherein the surgical treatment is at least one of artificial joint replacement surgery and dental implant surgery.

15. The information processing system according to claim 1 or 2, wherein the surgical treatment can be performed by a surgical robot.

16. an acquisition step of acquiring input information including a medical image showing the affected bone of the subject; A control method for an information processing system, comprising: an output step of outputting, using a first learning model trained using first training data including bone information regarding at least one of bone density and bone quality of the bone of each of a plurality of learning subjects before a surgical treatment including an implant placement procedure is applied, shape characteristics, and treatment information regarding the surgical treatment applied to the bone, at least one of instrument information indicating a surgical instrument to be used in a surgical treatment suitable for the affected bone of the subject, identified based on the input information; prediction information predicting the condition of the affected bone of the subject after the surgical treatment procedure is applied; parameter information indicating parameters that may be selected when applying a surgical treatment procedure to the affected bone of the subject; and implant information regarding an implant that may be implanted in the affected bone of the subject.

17. 3. A control program for causing a computer to function as the information processing system according to claim 1, wherein the control program causes the computer to function as the acquisition unit, the identification unit, and the output unit.

18. A computer-readable recording medium on which the control program according to claim 17 is recorded.

Images