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

Abstract

The present invention assists planning of surgical treatment suitable for a bone of an affected part of a subject person. This information processing system comprises a first inference unit and an output unit. The first inference unit inputs, to a first trained model having been trained, input information including a first image showing an affected part including a subject bone, of a subject person, in which an implant has been embedded, and infers first inference information relating to at least one of the bone density, the bone quantity, and the bone quality of the subject bone. The output unit outputs the first inference information.

Description

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

[0001] The present disclosure relates to an information processing system that estimates the prognosis of a subject who has undergone implant placement surgery, and a control method thereof.

[0002] Patent Document 1 discloses a technique for diagnosing a patient's risk of implant-related revision.

[0003] Japan Special Table 2020-507783 Publication

[0004] An information processing system according to one aspect of the present disclosure includes an acquisition unit that acquires input information including a first image showing at least a portion of a target bone in which a first implant of a subject is embedded, a first estimation unit that inputs the input information into a first learning model trained using first teacher data including a second image showing at least a portion of a bone of an animal including a human, and bone information regarding at least one of the bone density, bone mass, and bone quality of the bone, thereby estimating first estimated information regarding at least one of the bone density, bone mass, and bone quality of the target bone, and an output unit that outputs the first estimated information.

[0005] 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 a first image showing at least a portion of a target bone in which a first implant of a subject is embedded, and an output step of inputting the input information into a learning model trained using first teacher data including a second image showing at least a portion of a bone of an animal including a human, and bone information regarding at least one of the bone density, bone mass, and bone quality of the bone, to estimate first estimated information regarding at least one of the bone density, bone mass, and bone quality of the target bone, and outputting the first estimated information.

[0006] 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.

[0007] 1 is a diagram illustrating an example configuration of an information processing system according to an aspect of the present disclosure. FIG. 2 is a diagram illustrating an example configuration of an information processing system according to another aspect of the present disclosure. FIG. 3 is a block diagram illustrating an example configuration of an information processing device according to an aspect of the present disclosure. FIG. 4 is a diagram illustrating an example of a plurality of parts of a target bone. FIG. 5 is a diagram illustrating an example of a plurality of parts of a target bone. FIG. 6 is a diagram illustrating an example configuration of a first learning model executed by an identification unit. FIG. 7 is a flowchart illustrating an example flow of learning processing by a learning unit. FIG. 8 is a flowchart illustrating an example flow of processing performed by an information processing device. FIG. 9 is a block diagram illustrating an example configuration of an information processing device according to an aspect of the present disclosure. FIG. 10 is a diagram illustrating an example of a plurality of parts of a target bone. FIG. 11 is a diagram illustrating an example of a plurality of parts of a target bone. FIG. 12 is a flowchart illustrating another example flow of learning processing by a learning unit. FIG. 13 is a diagram illustrating an example configuration of an information processing system according to an aspect of the present disclosure. FIG. 14 is a block diagram illustrating an example configuration of an information processing device according to an aspect of the present disclosure. FIG. 15 is a diagram illustrating an example configuration of a learning model executed by an estimation unit according to an aspect of the present disclosure. FIG. 16 is a flowchart illustrating an example flow of learning processing by a learning unit according to an aspect of the present disclosure. FIG. 17 is a flowchart illustrating an example flow of processing performed by an information processing device according to another aspect of the present disclosure.

[0008] 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," "patient," and "person" are replaced with "animal" if the embodiments are applicable to these animals.

[0009] First Embodiment Hereinafter, an information processing device 1 according to an embodiment of the present disclosure will be described in detail as an example.

[0010] The information processing device 1 outputs first estimated information estimated using a first learning model based on input information including a first image depicting an affected area of ​​a subject. In this case, the affected area includes at least a portion of a bone (hereinafter referred to as the "target bone") in which an implant (first implant) is embedded. The first estimated information is information related to the training data of the first learning model, and includes, for example, bone information regarding the subject's bone condition. The bone information may include, for example, at least one of the following: presence or absence of a fracture, possibility of osteoporosis, drug efficacy, incident occurrence, bone density, bone mass, bone quality, trabecular number, trabecular spacing, trabecular width, trabecular orientation, bone connectivity density, and trabecular bone structure index. Alternatively, the bone information may be obtained by analyzing bone strength based on the condition of cortical bone and / or trabecular bone. The first estimated information may include bone information regarding at least one of bone density, bone mass, and bone quality for a portion of the target bone in which an implant is embedded. The affected area may refer to a diseased or injured area. In this context, the affected area includes areas with previous disease or injury.

[0011] The possibility of osteoporosis may include, for example, "no osteoporosis," "suspected osteoporosis," or "yes" based on at least one of the presence or absence of a fracture, the possibility of a fracture, and a change in bone density. More specifically, the possibility of osteoporosis may be indicated as primary osteoporosis if there is no disease that reduces bone mass, no secondary osteoporosis, and the presence or high possibility of a fracture. The drug effect may include, for example, the name of a drug that improves bone condition when taken or / and administered for a certain period of time, or may include bone information including at least one of bone density, bone mass, and trabecular bone condition after a certain period of time. The occurrence of an incident may include, for example, implant loosening, implant loss, or peri-implant infection. Examples of implants include artificial hip joints, artificial knee joints, spinal implants, bolts implanted in bone, and dental implants.

[0012] The first image showing at least a portion of the bone in which the implant is embedded can be, for example, an image showing various implants (described below) and a portion of the surrounding bone. The first image can be, for example, at least one of an X-ray image, a computed tomography (CT) image, a magnetic resonance imaging (MRI) image, a positron emission tomography (PET) image, a dual-energy X-ray absorptiometry (DXA) image, and an ultrasound image, but is not limited to these. The first image can be, for example, an inspection device image acquired from an inspection device (e.g., an X-ray inspection device), or an image obtained by reducing noise from an inspection device image captured by the inspection device. Noise reduction can be achieved using, for example, machine learning. The information processing device 1 can acquire the first image showing the subject's bones from the image management device 5. The X-ray image can include, for example, a panoramic X-ray image used for dental purposes. The panoramic X-ray image can be, for example, an image including multiple teeth (e.g., all teeth). The first image may include, for example, at least one of an inspection device image acquired from an inspection device (e.g., an X-ray inspection device), an image of an inspection device image with noise reduction, and an image of an X-ray film output from the inspection device. The first image may be, for example, an inspection device image stored in an external storage terminal or an image of an inspection device image with noise reduction. The first image showing the implant and bone may be, for example, an inspection device image to which image processing has been applied to improve the image of the bone around the implant. The first image may be, for example, an image taken by irradiating a portion of the skeleton with plain X-rays. The first image may be, for example, an image showing the entire bone, or an image showing at least a portion of the bone. The first image may be an image showing bone trabeculae. The captured region of the first image may include, for example, at least a portion of the head, neck, chest, lower back, hip joint, knee joint, ankle joint, foot, toe, shoulder joint, elbow joint, wrist joint, hand, fingers, and temporomandibular joint. Note that the types of captured regions of the first image are not limited to these.The X-ray image may be a frontal image of the target area irradiated with plain X-rays (e.g., an image obtained by irradiating the target area with X-rays in the front-to-back direction) or a lateral image of the target area (e.g., an image obtained by irradiating the target area with X-rays in the left-to-right direction). The X-ray image may be an image showing at least one of cortical bone and cancellous bone. For example, a frontal chest X-ray image including a person's chest or a frontal lumbar X-ray image including a person's lumbar region may be used as the X-ray image. The chest X-ray image is, for example, an image showing at least one of the ribs, clavicle, and sternum. The lumbar X-ray image is, for example, an image showing at least one of the lumbar vertebrae, pelvis, and femur. The first image is not limited to the lumbar region or chest, and may be, for example, an image showing the teeth, jaw, arm, hand, shoulder joint, knee joint, heel, skull, or foot bone. In addition, when a CT image is used as the first image, information about the bone trabeculae based on a three-dimensionally constructed image may be used, or information about the bone trabeculae based on a two-dimensionally captured image may be used.

[0013] The bone density of the bone used in the first learning model can be, for example, a measurement value obtained 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, for example, by single-energy X-ray absorptiometry, dual-energy X-ray absorptiometry (DXA), ultrasound, or quantitative computed tomography (CT). In a DXA device that measures bone density using the DXA method, when measuring bone density of the lumbar vertebrae, X-rays are irradiated from the front of the lumbar vertebrae of the subject. In addition, when measuring bone density of the proximal femur, X-rays are irradiated from the front of the proximal femur of the subject. Here, "front of the lumbar vertebrae" and "front of the proximal femur" refer to the direction that correctly faces the imaging site, such as the lumbar vertebrae and the proximal femur, and may be the ventral side of the subject's body or the back side of the subject. The proximal femur includes, for example, at least one of the neck, trochanter, shaft, and the entire proximal femur (neck, trochanter, and shaft). In the MD method, X-rays are irradiated onto, for example, the hand.

[0014] The bone density of the bone used in the first learning model may be, for example, a patient's bone density estimated by inputting a second image of the patient's bone into a trained estimation model trained by machine learning using training data including at least one image of the bone, such as an X-ray image, a CT image, an MRI image, or an ultrasound image, and the measured bone density of the bone. The bone density of the bone used in the first learning model may be, for example, a patient's future and / or past bone density predicted by inputting a second image of the patient's bone into a prediction model trained by machine learning using training data including at least one image of the bone, such as an X-ray image, a CT image, an MRI image, or an ultrasound image, and the measured bone density of the bone. The prediction model may be a trained model trained by machine learning using training data including an image of the patient's bone and bone density measured at a time point different from the time the image was taken (e.g., 3 months, 6 months, 1 year, 3 years, 5 years, etc.). The predicted result may be a result after a period shorter than the predetermined period, a result after a period longer than the predetermined period, or a result after a period equal to the predetermined period. The bone mineral density may be estimated for a specific portion of a predetermined region of the bone (e.g., a portion of the vertebral body and a portion of the femur), or may be estimated separately for multiple specific portions.

[0015] The bone may be, for example, a single bone or a skeleton made up of multiple bones.

[0016] The second image may be, for example, at least one of an X-ray image, a CT image, a nuclear magnetic resonance image, a PET image, a DXA image, and an ultrasound image, but is not limited thereto. The second image may be, for example, an inspection image acquired from an inspection device (e.g., an X-ray inspection device), or may be an image in which noise has been reduced from a captured inspection image. Noise reduction may be performed using, for example, machine learning. The X-ray image may include, for example, a panoramic X-ray image used in dentistry. The panoramic X-ray image may be, for example, an image including multiple teeth (e.g., all teeth). The second image may include, for example, at least one of an inspection image acquired from an inspection device (e.g., an X-ray inspection device), an image in which noise has been reduced from an inspection image, and an image in which an X-ray film output from an inspection device has been digitized. The second image may be, for example, an inspection image stored in an external storage terminal or an image in which noise has been reduced from an inspection image. The second image showing the implant (second implant) and bone may be, for example, an inspection image to which image processing has been applied to improve the visibility of the bone around the implant. The second image may be, for example, an image captured by irradiating a portion of the skeleton with plain X-rays. The second image may be, for example, an image capturing the entire bone, or an image capturing at least a portion of the bone. The captured region of the second image may include, for example, at least a portion of the head, neck, chest, lower back, hip joint, knee joint, ankle joint, foot, toe, shoulder joint, elbow joint, wrist joint, hand, fingers, and temporomandibular joint. Note that the type of captured region of the second image is not limited to this. Furthermore, the X-ray image may be a frontal image of the target region irradiated with plain X-rays (e.g., an image obtained by irradiating the target region with X-rays in the front-to-back direction) or a lateral image of the target region (e.g., an image obtained by irradiating the target region with X-rays in the left-to-right direction). The X-ray image may be an image capturing at least one of trabecular bone, cortical bone, and cancellous bone. For example, the X-ray image may be a frontal chest X-ray image including a human chest or a frontal lumbar X-ray image including a human lumbar region. The chest X-ray image is an image showing at least one of the ribs, clavicles, and sternum, for example. The lumbar X-ray image is an image showing at least one of the lumbar vertebrae, pelvis, and femur, for example.The second image is not limited to the lower back or chest, and may be, for example, an image showing the teeth, jaw, arm, hand, shoulder joint, knee joint, heel, skull, or foot bones. When a CT image is used as the second image, information about the trabecular bone based on a three-dimensionally constructed image may be used, or information about the trabecular bone based on a two-dimensionally captured image may be used.

[0017] Bone mass is an index related to bone density and is a concept that includes bone density. Bone mass may be the sum of bone mineral and bone matrix protein. In the present disclosure, bone mass is an index related to bone density, and may be the amount of bone tissue in the skeleton. Bone quality can be based on, for example, at least one of bone statistical properties, bone geometric properties, bone mechanical properties, and bone chemical properties. Bone mass information may be information measured using a bone density measuring device such as DXA, or information obtained by estimating bone density using trained parameters from X-ray images. Bone quality may also include information on the subject's attributes, as described below. Bone quality can be based on, for example, at least one of bone metabolic markers, gender, race, whether or not the subject has undergone menopause, birth information, age, cortical bone condition, cancellous bone condition, cancellous bone trabecular condition, disease information, bone evaluation information, medication information, presence or absence of fractures, number of fractures, location of fractures, and fracture history. More specifically, bone quality may be measured using at least one of bone formation markers, bone resorption markers, bone quality markers (e.g., vitamin K levels), cortical bone thickness, trabecular density, trabecular orientation, and trabecular bone structure index (trabecular bone score), but is not limited to these. Disease information may include at least one of osteoporosis, rheumatoid arthritis, osteonecrosis (e.g., femoral head necrosis), systemic sclerosis, kidney disease, and osteopetrosis. Bone evaluation information may include information evaluated using the Fracture Risk Assessment Tool (FRAX®). Drug information may include at least one of trade name, generic name, dosage, administration period, and administration method (e.g., oral, intravenous, intramuscular, subcutaneous, 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] Furthermore, bone quality may include, for example, the type of medullary cavity shape. For example, the Dorr classification can be used for the medullary cavity shape. For example, 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: Type A: A type in which the cortical bone is thick and the medullary cavity is narrow. Type B: A type between Type A and Type C in which the medullary cavity is neither narrow nor wide. Type C: A type in which the cortical bone is thin and the medullary cavity is wide.

[0019] The first learning model is trained using a second image of a human bone and first training data including bone information related to at least one of the bone density, bone mass, and bone quality of the bone. The second image in the first training data may include an image of at least a portion of a bone in which an implant is embedded. Here, the human bone may be a bone that includes bone from the same location as the target bone, or a bone that does not include bone from the same location as the target bone. Furthermore, the second image may be, for example, an image of an area that includes at least the entire bone in which the implant is embedded. The second image may be, for example, an image of an area that includes at least a portion of the implant and a portion of the bone surrounding the implant.

[0020] In the present disclosure, the term "implant" refers to an artificial object implanted in the human body through a surgical procedure (including dental procedures). The implant may be implanted in a target bone or implanted in each of the bones of multiple patients. The implant may include, for example, at least one of an artificial joint, a spinal implant, a trauma implant, a plastic implant, and a dental implant. The artificial joint may be, for example, at least one of an artificial hip joint, an artificial knee joint, an artificial shoulder joint, an artificial elbow joint, an artificial ankle joint, and an artificial finger joint. The spinal implant may be, for example, at least one of an instrumentation, a cage, an artificial intervertebral disc, and an artificial vertebral body. The trauma implant may be, for example, at least one of a plate, a screw, and a nail. The plastic implant may be, for example, at least one of a skull plate and a nasal bone prosthesis. The implant may also include, for example, bone cement for fixing the implant to the bone. The bone cement may be, for example, a material primarily composed of polymethyl methacrylate.

[0021] (Configuration of Information Processing System 100a) First, the configuration of the information processing system 100a according to one aspect of the present disclosure will be described with reference to Fig. 1. Fig. 1 is a diagram illustrating an example configuration of the information processing system 100a in a medical facility 8 in which an information processing device 1 has been introduced.

[0022] The information processing system 100a includes an information processing device 1 and one or more terminal devices 7 communicably connected to the information processing device 1. The information processing device 1 estimates first estimated information regarding at least any of bone information of a target bone, such as bone density, bone mass, and bone quality, from a first image that captures at least a portion of the target bone. The information processing system 100a is a computer that transmits the first estimated information to the terminal device 7. The first estimated information can be useful information for physicians and others to identify signs of risks that may occur in the target bone and an implant embedded in the target bone. Therefore, the information processing device 1 according to one embodiment of the present disclosure is a device that outputs information that is useful for physicians and others to estimate prognostic risks of a subject who has undergone implant placement surgery.

[0023] The terminal device 7 functions as an output unit in the information processing system 100a and outputs information received from the information processing device 1. The terminal device 7 is, for example, a computer used by medical personnel (medical personnel) such as doctors belonging to the medical facility 8. The terminal device 7 may be installed, for example, within the medical facility 8 or within a company providing analysis services, or may be a cloud. If the image management device 5 is a cloud, the first image and / or the second image can be acquired via a communication network. The terminal device 7 may be, for example, a device with a function to output information received from the information processing device 1 on paper. 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.

[0024] 1 illustrates 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. However, 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 facility 8. Furthermore, communication within the information processing system 100a complies with international standards such as DICOM (Digital Imaging and Communications in Medicine).

[0025] In addition to the information processing device 1 and the terminal device 7, an image management device 5 and an electronic medical record management device 6 may be communicatively connected to the LAN within the medical facility 8. The image management device 5 and the electronic medical record management device 6 may be installed within the medical facility 8 or in a facility outside the medical facility 8. The image management device 5 is a computer that functions as a server for managing images captured at the medical facility 8. In this case, the information processing device 1 may acquire a first image showing at least a portion of the target bone from the image management device 5. The information processing device 1 may also acquire a first image showing at least a portion of the target bone from the image management device 5 and the electronic medical record management device 6 installed in a facility outside the medical facility 8. The electronic medical record management device 6 is a computer that functions as a server for managing electronic medical record information of subjects who have received medical treatment at the medical facility 8. The electronic medical record information may include attribute information of the subject and surgical information including information on the surgical procedure for implant placement applied to the target bone.

[0026] The LAN in 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.

[0027] (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.

[0028] The information processing device 1 includes a control unit 2 that performs overall control of 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, a first estimation unit 23, an output unit 24, and a learning unit 25. The storage unit 3 stores a control program 31 that is a program for performing various controls of the information processing device 1, as well as first teacher data 32 and a trained first learning model 33.

[0029] <Acquisition unit 21> The acquisition unit 21 acquires input information including a first image that captures at least a portion of a target bone. For example, the acquisition unit 21 shown in FIG. 3 may be able to acquire the first image from the image management device 5. The input information is input data input to the first estimation unit 23. The acquisition unit 21 may acquire attribute information and surgery information of the subject from the electronic medical record management device 6 in the medical facility 8.

[0030] <First Estimation Unit 23> The first estimation unit 23 estimates the first estimated information by inputting input information into the trained first learning model 33. Here, the trained first learning model 33 has been trained in advance using first training data 32. The first training data may be data including a second image of a human bone and bone information regarding at least one of the bone density, bone mass, and bone quality of the bone. For example, the first training data may be data including at least a second image of a bone without an implant for each of a plurality of patients and bone information regarding at least one of the bone density, bone mass, and bone quality of the bone. Alternatively, the first training data may be data including a second image of a bone without an implant for each of a plurality of patients and bone information regarding at least one of the bone density, bone mass, and bone quality of the bone in which the implant is implanted.

[0031] The first estimation unit 23 may estimate first estimated information including bone information regarding at least one of bone density, bone mass, and bone quality of each of multiple regions of the target bone, including regions adjacent to the implant.

[0032] The multiple regions can be set to any region adjacent to the implant. The region adjacent to the implant may be a region captured in a single image. For example, the region adjacent to the implant may refer to a region in contact with the implant. The region adjacent to the implant may refer to a region not in contact with the implant. The multiple regions will be described using the stem of a cementless artificial hip joint as an example, but are not limited to this. Each of the multiple regions may be arranged along a first direction L1 from the insertion port (proximal side) into which the implant stem is inserted to the distal end (distal side) of the stem. The multiple regions can be regions classified by the Gruen classification, as shown in FIG. 4 . FIG. 4 is a diagram illustrating an example of multiple regions in a target bone (right femur) B1. FIG. 4 is a diagram illustrating an artificial hip joint (i.e., implant I1) implanted in a right hip joint, viewed from the ventral side (anterior side). That is, in FIG. 4 , the left side is the lateral side (right arm side), and the right side is the medial side (left arm side). Figure 4 shows area 1 (outside) and area 7 (inside) located closest to the insertion opening, area 2 (outside) and area 6 (inside) next closest to the insertion opening, area 3 (outside) and area 5 (inside) next closest to the insertion opening, and area 4 farthest from the insertion opening.

[0033] When the implant embedded in the bone of the subject is an artificial hip implant including a stem, the target bone is the femur in which the stem is embedded. In this case, the first estimation unit 23 may estimate multiple pieces of first estimated information within a region of the femur, which is the target bone, classified according to the Gruen classification. Here, the multiple pieces of first estimated information may include first estimated information within a proximal region of the femur in which the stem is embedded.

[0034] For example, the first estimating unit 23 may estimate bone information related to at least one of bone density, bone mass, and bone quality for each of the plurality of regions thus divided. In this case, the first estimating unit 23 may estimate different items for each of the plurality of regions, or may estimate the same item. For example, the first estimating unit 23 may estimate bone density, bone mass, and bone quality (e.g., cancellous bone structure index) for regions 1, 7, 2, and 6, while estimating only bone density for regions 3, 4, and 5. Alternatively, the first estimating unit 23 may estimate only bone density for all regions 1 to 7. Bone density may be a value related to bone density. Bone density is bone mineral density per unit area (g / cm ２ ), bone mineral density per unit volume (g / cm ３ ), YAM (%), AGE, T-score, and Z-score. YAM (%) is an abbreviation for "Young Adult Mean" and may be referred to as the young adult mean percentage. For example, bone mineral density is expressed as bone mineral density per unit area (g / cm ２ ) and YAM (%). AGE may be a value compared to the average value for the same age or age group. Bone mineral density may be an index determined by guidelines or an original index. For example, values ​​used in osteoporosis guidelines (such as, but not limited to, the 2015 edition of the Prevention and Treatment Guidelines of the Japan Osteoporosis Society) can be used for bone mineral density.

[0035] The first estimation unit 23 may estimate the first estimated information for all of the regions 1 to 7. Alternatively, the first estimation unit 23 may estimate only some of the regions as the first estimated information. More specifically, to estimate the loosening of an implant in a target bone, bone information including at least one of bone density, bone mass, and bone quality of the region of the target bone B1 on the insertion side of the stem of the implant I1 (i.e., regions 1, 2, 6, and 7 in FIG. 4 ) is more important. Therefore, the first estimation unit 23 may estimate, for example, only regions 1 and 7 as the first estimated information. Alternatively, the first estimation unit 23 may estimate the first estimated information with different accuracy for each region based on the importance of the region for the loosening of the implant I1. Estimating with different accuracy for each region includes, for example, changing the number of calculations for each region, changing the learning model for each region, or changing the variables used during calculation for each region. For example, the regions 1 and 7 may be estimated with high accuracy, and the other regions may be estimated with lower accuracy than the regions 1 and 7.

[0036] Alternatively, each of the plurality of sites may be a site along a second direction L2 from the medullary cavity side to the outer shell side of the target bone B1 (i.e., a direction away from the axis of the stem of the implant I1). In order to estimate the loosening of the implant in the target bone B1, bone information including at least one of bone density, bone mass, and bone quality at a site of the target bone B1 near the stem of the implant I1 on the medullary cavity side of the target bone B1 is more important.

[0037] The multiple regions may be set two-dimensionally by dividing the regions in the first direction L1 and the second direction L2. The multiple regions may be set as regions with different areas. Furthermore, the multiple regions may be set as regions with smaller areas of specific portions. The multiple regions may be set arbitrarily, for example, according to the subject's attribute information. For example, if the subject has a history of fractures, the regions may be set as regions with smaller areas of specific portions than for subjects without a history of fractures. More specifically, in the first direction L1, the regions may be set so that the areas of the regions become smaller toward the regions 1 and 7 compared to other regions. In the second direction L2, the regions may be set so that the areas of the regions closer to the implant I1 become smaller compared to regions further from the implant. Furthermore, if cement is used when implanting an artificial hip joint, the multiple regions may be set to avoid the cement portion, for example, by considering the cement as part of the artificial joint.

[0038] (Examples of multiple parts of an implant) The above describes the stem of a cementless artificial hip joint, but as shown in Examples 1 to 3 below, other artificial joints can also be divided into regions and the first estimated information can be estimated for each region.

[0039] Example 1: In the case of a cementless artificial hip joint, the multiple sites can be set at any site adjacent to the cup. The cup is, for example, embedded in the acetabulum of the pelvis. The multiple sites of the acetabulum adjacent to the cup can be, for example, regions I to III of the Chanley classification, as shown in Figure 4.

[0040] When the implant embedded in the bone of the subject is an artificial hip joint implant including a cup, the target bone is the acetabulum in which the cup is embedded. In this case, the first estimation unit 23 may estimate a plurality of pieces of first estimated information within a region of the acetabulum, which is the target bone, classified according to the Charnley classification.

[0041] Example 2: The regions divided by the Gruen classification are not limited to the example shown in FIG. 4 and can also be applied when viewing an artificial hip joint from the side. FIG. 5 is a diagram showing an example of multiple regions in a target bone (left femur) B2. FIG. 5 is a diagram showing an artificial hip joint (i.e., implant I2) implanted in a left hip joint viewed from the left arm side (laterally). That is, in FIG. 5, the left side is the ventral side and the right side is the dorsal side. FIG. 5 shows region 8 (ventral side) and region 14 (dorsal side) located closest to the insertion opening, region 9 (ventral side) and region 13 (dorsal side) next closest to the insertion opening, region 10 (ventral side) and region 12 (dorsal side) next closest to the insertion opening, and region 11 furthest from the insertion opening.

[0042] Example 3: Multiple regions that can be set in the case of an artificial knee joint will be described using FIGS. 10 to 12 . FIG. 10 is a diagram showing examples of multiple regions on a target bone (left femur) B3. FIG. 10 is a diagram showing an artificial knee joint (i.e., implant I3) implanted in the left femur B3 as viewed from the left arm side (lateral side). That is, in FIG. 10, the left side is the ventral side and the right side is the dorsal side. Regions 1 to 7 are shown in FIG. 10 . FIG. 11 is a diagram showing examples of multiple regions on a target bone (left tibia) B4. FIG. 11 is a diagram showing an artificial knee joint (i.e., implant I4) implanted in the left tibia B4 as viewed from the ventral side (anterior side). That is, in FIG. 11, the left side is the medial side (right arm side) and the right side is the lateral side (left arm side). Regions 1 to 7 are shown in FIG. 11 . FIG. 12 is a diagram showing examples of multiple regions on a target bone (left tibia) B5. Figure 12 is a view of the artificial knee joint implanted in the left tibia B5 as seen from the left arm side (anterior). That is, in Figure 12, the left side is the ventral side and the right side is the dorsal side. In Figure 12, parts 1 to 3 are shown.

[0043] In any of Examples 1 to 3, each of the multiple sites may be arranged along a first direction L1 from the insertion port side (proximal side) into which the stem of implant I2 to I5 is inserted to the tip side (distal side) of the stem. Each of the multiple sites may be arranged along a second direction L2 from the medullary cavity side to the outer shell side of the target bone (i.e., the direction away from the axis of the stem of implant I2 to I5 that is embedded).

[0044] In response to input information being input to the input layer 231 (see FIG. 6 ), the first estimation unit 23 performs calculations based on the trained first learning model 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. 6 ). As an example, the first estimation unit 23 may be configured to extract features from the input information and use them as input data. The following well-known algorithms may be applied to extract the features: Convolutional neural network (CNN), autoencoder, recurrent neural network (RNN), long short-term memory (LSTM), and convolutional long short-term memory (ConvLSTM).

[0045] The trained first learning model 33 is a computational model used by the first estimation unit 23 when performing computations based on input data. The trained first learning model 33 is generated by the learning unit 25 performing machine learning on an untrained neural network using first teacher data 32 (described later). Here, the trained first learning model 33 may also be applied to non-human animals. In this case, the "patient" in the first teacher data 32 may be the same biological species as the "subject." In other words, the information processing device 1 according to the present disclosure can also estimate first estimated information regarding at least any of bone information, such as bone density, bone mass, and bone quality, of a bone in which an implant is embedded in 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.

[0046] <Output unit 24> The output unit 24 transmits the first estimated information estimated by the first estimation unit 23 to the terminal device 7. The information processing device 1 may be configured to include a display unit (not shown). In this case, the output unit 24 causes the display unit to display the above information. The display unit may, for example, change the color of each divided area according to the received first estimated information. The display unit may, for example, display the received first estimated information as a heat map.

[0047] <Learning Unit 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 (trained first learning model 33) that functions as the first estimation unit 23. This learning uses first teacher data 32 (described later). Specific examples of the learning performed by the learning unit 25 will be described later.

[0048] (Configuration of First Estimation Unit 23) The configuration of the first estimator 23 will be described below with reference to Fig. 6. The configuration shown in Fig. 6 is an example, and the configuration of the first estimator 23 is not limited to this.

[0049] 6 , the first estimation unit 23 performs calculations based on the trained first learning model 33 on input data input to the input layer 231, and outputs output data from the output layer 232. The output data is bone information related to at least one of the bone density, bone volume, and bone quality of the bone in which the implant is embedded.

[0050] The first estimator 23 in FIG. 6 includes a neural network having an input layer 231 and an output layer 232. While FIG. 6 illustrates a case in which the neural network is an LSTM, this is not limiting. For example, the neural network may be a ConvLSTM network, which 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 time change in the input data, and an initial value. The time change is the difference in time between the time when the input data is acquired and the time to be estimated. The time change may be input by the system user, such as 1 year, 3 years, 5 years, 10 years, 20 years, or 50 years, or may be automatically determined within the system. The initial value may be the value of bone mass or bone quality at the time when the input data is acquired. The initial value may be estimated by the first estimator 23, or a value of bone mass or bone quality measured by a separate device may be used. The input layer 231 and the output layer 232 each have a plurality of LSTM layers. Each of the input layer 231 and the output layer 232 may have three or more LSTM layers.

[0051] (Learning Process by the Learning Unit 25) The learning process for generating the trained first learning model 33 will be described below with reference to Fig. 7. Fig. 7 is a flowchart showing an example of the flow of the learning process by the learning unit 25.

[0052] 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 a second image depicting a human bone, and the objective variable may be bone information related to at least one of bone density, bone mass, and bone quality of the human bone depicted in the second image. In addition to the bone information, the objective variable may include at least one of area and position information of the bone information, or information related to implant loosening. The area or position information of the bone information may be used as the explanatory variable. The position information may be information representing a position on the image, such as XY coordinates on the image. Alternatively, the position information may be information indicating the interface between the bone and the implant, or a position a predetermined distance away from the interface of the implant. Alternatively, the position information may be the name of a specific part of the human body. For example, the position information may be information such as the trochanter for the proximal femur, the posterior condyle for the distal femur, or the medial side for the proximal tibia. The information regarding implant loosening may be at least one of the following: whether or not loosening has occurred, the probability that loosening has occurred, whether or not a bone radiograph is present, the thickness of the bone radiograph, the range of the bone radiograph, changes in the thickness or range of the bone radiograph, sensation or pain felt by the patient, and changes in sensation or pain felt by the patient.

[0053] Next, the learning unit 25 inputs a second image showing a person's bones to the input layer 231 (step S2).

[0054] Next, the learning unit 25 acquires bone information (i.e., output data) relating to at least one of bone density, bone mass, and bone quality of the bones of the person appearing in the second image input in step S2 from the output layer 232 (step S3). This output data contains the same content as the objective variable of the first training data 32. In FIG. 7, the order of steps S2 and S3 may be reversed. Alternatively, in FIG. 7, steps S2 and S3 may be executed simultaneously.

[0055] Next, the learning unit 25 acquires a dependent variable related to the person appearing in the second image input in step S2, which is included in the first teacher data 32. Then, the learning unit 25 compares the output data acquired in step S3 with the dependent variable related to the person, calculates an error (step S4), and adjusts the first learning model 33 being learned so as to reduce the error (step S5).

[0056] Any known method can be applied to adjust the first learning model during learning. For example, backpropagation may be used as a method for adjusting the first learning model. The adjusted first learning model becomes a new first learning model, and the first estimator 23 uses the new first learning model in subsequent calculations. During the adjustment stage of the first learning model, parameters used by the first estimator 23 (e.g., filter coefficients, weighting coefficients, etc.) may be adjusted.

[0057] If the error is not within a predetermined range and explanatory variables for all people 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 people included in the first teacher data 32 have been input (YES in step S6), the learning unit 25 ends the learning process.

[0058] When the above-described learning process is adopted, the first estimation unit 23 can estimate first estimated information regarding at least one of bone information of bone density, bone mass, and bone quality of a portion of the target bone from input information including a first image showing at least a portion of the target bone in which an implant is embedded.

[0059] (Another example of learning process by learning unit 25) Hereinafter, another example of the learning process for generating the trained first learning model 33 will be described with reference to Fig. 13. Fig. 13 is a flowchart showing another example of the flow of the learning process by the learning unit 25.

[0060] The learning unit 25 acquires first training data 32 from the storage unit 3 (step S1a). The first training data 32 includes explanatory variables and objective variables to be input to the input layer 231. Here, the explanatory variables include second images of at least the bones in which the implants are embedded for each of the multiple patients, and the objective variables are bone information related to at least one of the bone density, bone mass, and bone quality of the bones in which the implants are embedded.

[0061] Next, the learning unit 25 inputs a second image showing at least a part of a bone in which an implant of a certain patient (referred to as Patient A) is embedded, to the input layer 231 (step S2a).

[0062] Next, the learning unit 25 obtains output data relating to at least one of bone information, such as bone density, bone mass, and bone quality, of the bone in which the implant of patient A is embedded from the output layer 232 (step S3a). This output data contains the same content as the objective variable of the first teacher data 32. In Fig. 13, the order of steps S2a and S3a may be reversed. Alternatively, in Fig. 13, steps S2a and S3a may be executed simultaneously.

[0063] Next, the learning unit 25 acquires the objective variable for patient A included in the first teacher data 32. Then, the learning unit 25 compares the output data acquired in step S3a with the objective variable for patient A to calculate an error (step S4a), and adjusts the first learning model 33 being learned so as to reduce the error (step S5a).

[0064] Any known method can be applied to adjust the first learning model during learning. For example, backpropagation may be used as a method for adjusting the first learning model. The adjusted first learning model becomes a new first learning model, and the first estimator 23 uses the new first learning model in subsequent calculations. During the adjustment stage of the first learning model, parameters used by the first estimator 23 (e.g., filter coefficients, weighting coefficients, etc.) may be adjusted.

[0065] If the error is not within the predetermined range and the explanatory variables for all patients included in the first teacher data 32 have not been input (NO in step S6a), the learning unit 25 returns to step S2a and repeats the learning process. If the error is within the predetermined range and the explanatory variables for all patients included in the first teacher data 32 have been input (YES in step S6a), the learning unit 25 ends the learning process.

[0066] When the above-described learning process is adopted, the first estimation unit 23 can estimate first estimated information regarding at least one of bone information of bone density, bone mass, and bone quality of a portion of the target bone from input information including a first image showing at least a portion of the target bone in which an implant is embedded.

[0067] (Aspect 1 of Embodiment 1) The first training data 32 may further include at least one of attribute information for each of a plurality of patients and surgical information related to the implantation technique used to implant the implant in each patient's bone. By using such first training data 32, the trained first learning model 33 can more accurately estimate first estimated information related to at least one of bone information, such as bone density, bone mass, and bone quality, of the target bone from the input information. In this case, the input information may include at least a first image of the target bone, attribute information for the subject, and surgical information related to the implantation technique used to implant the implant in the target bone.

[0068] In the first teacher data 32 (and input information), the attribute information may include at least one of the following for each patient (and subject): age, sex, height, weight, race, whether or not the patient has undergone menopause, whether or not the patient has had a fracture, the number of fractures, the location of the fractures, the history of fractures, lifestyle information, information about medications being taken (medication information), information indicating the results of blood tests (blood test information), urine test information, saliva test information, medical history, the medical history of the subject's family, genetic information, birth information, menopausal information, predicted menopausal stage based on hormone information, and birth information. In the first teacher data 32 (and input information), the surgical information may include at least one of the model of implant implanted in each patient's bone (and the subject's bone), the size of the implant, the surgical procedure used, the duration of the implantation procedure, the amount of blood loss during the implantation procedure, information indicating the medical facility that performed the implantation procedure, and information indicating the surgeon who performed the implantation procedure. The lifestyle habits may be, for example, sleep duration, wake-up time, sleep duration, daily exercise amount, dietary content, meal times, meal durations, blood glucose levels, etc. The dietary content may include, for example, at least one of the name of a 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. The information processing device 1 may acquire attribute information of the subject from the attribute information management device 4. If this attribute information is added to the acquired first image and / or second image, the information processing device 1 may extract the attribute information from the first image and / or second image.

[0069] 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.

[0070] When applying implant placement surgery, both the patient's (and subject's) attribute information and surgical information may be information related to or affecting the prognosis of the affected area where the implant placement surgery was applied. With this configuration, the information processing device 1 can provide the first estimated information to a doctor or the like with higher accuracy. This allows the information processing device 1 to assist in estimating the risk of the target bone's prognosis.

[0071] (Aspect 2 of Embodiment 1) The adjustment of the trained first learning model 33 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 33. In other words, the learning unit 25 is not a required component of the information processing device 1.

[0072] (Processing Performed by Information Processing Device 1) Hereinafter, the flow of processing performed by the information processing device 1 will be described with reference to Fig. 8. Fig. 8 is a flowchart showing an example of the flow of processing performed by the information processing device 1. Fig. 8 shows an example of processing performed by the information processing device 1 when outputting first estimated information related to bone information of a target bone from input information.

[0073] First, the acquisition unit 21 acquires input information including a first image in which at least a part of a target bone is captured (step S11: acquisition step).

[0074] Next, the first estimation unit 23 estimates first estimated information regarding at least one of the bone information of the target bone, namely bone density, bone mass, and bone quality, by inputting the input information into the trained first learning model 33 (step S12: estimation step).

[0075] The output unit 24 outputs the first estimated information estimated in step S12 (step S13: output step).

[0076] According to this configuration, the information processing device 1 and the information processing system 100a can output useful information for doctors and others to estimate the risks that may occur in the affected area of ​​a subject who has undergone implant placement surgery.

[0077] [Embodiment 2] Another embodiment 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.

[0078] The information processing system 100a may be configured to output second estimated information about an event that may occur in the subject due to the placement of the implant, which is estimated based on the input information.

[0079] (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. 9. Fig. 9 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 the information processing systems 100a and 100b.

[0080] The information processing device 1a includes a control unit 2a that performs overall control of each unit of the information processing device 1a, and a storage unit 3a that stores various data used by the control unit 2a. The control unit 2a includes an acquisition unit 21, a first estimation unit 23, an output unit 24, and a learning unit 25, as well as a second estimation unit 26. 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, a trained first learning model 33, and a trained second learning model 34.

[0081] The second estimation unit 26 estimates second estimated information from the first image included in the input information using a second learning model 34 trained using second training data. Here, the second training data is data including a third image showing a human bone and history information related to an event that occurred due to the implantation of an implant (third implant) into the bone. The second training data may be, for example, data including a third image showing at least a portion of the bone in which the implant is embedded, for each of a plurality of patients, and history information related to an event that occurred due to the implantation of the implant.

[0082] The output unit 24 transmits the estimated second estimated information to the terminal device 7. The third image included in the second teacher data may be, for example, an image taken within a certain period (e.g., six months) after the acquisition of the progress information after implant placement. The second teacher data may further include a combination of the following information (i) and (ii):

[0083] (i) Information about future bone density obtained from a prediction result about the bone condition when a predetermined period (e.g., 5 years) has passed since the third image taken in the past (e.g., at the time of implant placement). The future bone density may be information about the bone condition or bone density when a predetermined period has passed since the third image taken in the past (e.g., an actual measurement value of bone density measured when a predetermined period has passed since the third image taken in the past).

[0084] (ii) Information about the current bone density (e.g., at the time the third image was captured). The current bone density may be the actual bone density measured when the third image was captured. Alternatively, the current bone density may be the bone density estimated from the analysis results of the bone image captured in the third image.

[0085] Here, events that occur as a result of the implant being placed may include at least one of the following: Loosening of the implant; Fracture of the bone in which the implant is placed; Dislocation of the joint associated with the bone in which the implant is placed; Infection of the affected area including the bone in which the implant is placed; Fracture of the implant.

[0086] Loosening of an implanted implant can be detected, for example, based on at least one of an X-ray image of the implant and the bone interface where the implant is implanted, a bone radiograph, and a medical examination (e.g., interview and / or palpation, etc.) by a physician. Loosening of an implanted implant can be determined, for example, by at least one of the patient's sensation, pain, the gap between the implant and the bone (e.g., the width of the gap), and the positional change of the implant since implantation, and the presence or absence of loosening and the degree of loosening. Fractures of the bone in which the implant is implanted, dislocations of joints related to the bone in which the implant is implanted, infections of the affected area including the bone in which the implant is implanted, and implant fractures can be detected, for example, based on at least one of an X-ray image of the affected area and a medical examination (e.g., interview and / or palpation, etc.). Fractures of the bone in which the implant is implanted include, for example, fractures of bones in the skeleton surrounding the bone in which the implant is implanted.

[0087] The second training data may be, for example, progress information at a single time point, or may include progress information at multiple different time points. When progress information at multiple different time points is stored as the second training data, trends between the multiple different time points can be used as training data. For example, the trained second training model 34 may be a training model trained using second training data including, as explanatory variables, third images of the patient and progress information acquired at multiple different time points, and events resulting from the implantation of the patient's implant observed at the multiple different time points, as objective variables. The progress information may include, for example, information regarding at least one of the position of the bone radiograph, the thickness of the bone radiograph, the range of the bone radiograph, sensations experienced by the patient, pain (e.g., pain intensity, type of pain, duration of pain, etc.), the distance or angle between the implant and the bone, and changes in the position of the implant from the time of implantation to the present time.

[0088] By checking the second estimated information about the affected area in addition to the first estimated information about the affected area, the doctor or other medical professional can accurately determine the risk that may occur in the affected area of ​​the subject. This allows the information processing device 1a to support the doctor or other medical professional in estimating the risk that may occur in the prognosis of the affected area of ​​the subject.

[0089] Furthermore, when implant loosening is predicted in this way, the extent to which it will improve with treatment may also be displayed. It may also be possible to predict how implant loosening will change as a result of treatment being administered to a patient.

[0090] Implant loosening occurs due to a decrease in bone density in the bone surrounding the implant. In other words, improving the bone density of the bone surrounding the implant leads to improved implant loosening. Physicians can refer to the first estimated information and the second estimated information to determine a treatment plan, including prescribing a drug to the subject that is expected to have the effect of suppressing implant loosening and delaying the onset of implant loosening. Drugs considered for prescription to the subject may include, for example, drugs that act on bone formation and drugs that act on bone resorption. Drugs that act on bone formation include, but are not limited to, active vitamin D3 preparations (e.g., calcitriol, eldecalcitol, or alfacalcidol), teriparatide acetate, and teriparatide (recombinant). Drugs that act on bone resorption include, but are not limited to, calcitonin preparations, bisphosphonate preparations, and anti-RANKL monoclonal antibodies.

[0091] [Embodiment 3] (Configuration of information processing system 100b) The information processing device 1 may be communicably connected to a LAN disposed in each of a plurality of medical facilities 8 via a communication network 9, instead of being a computer installed in a predetermined medical facility 8. Figure 2 is a diagram showing an example configuration of an information processing system 100b according to another aspect of the present disclosure.

[0092] In addition to one or more terminal devices 7a, an image management device 5a and an electronic medical record management device 6a may be communicatively connected to the LAN within medical facility 8a. Furthermore, in addition to terminal device 7b, an image management device 5b and an electronic medical record management device 6b may be communicatively 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 "medical facility 8." Furthermore, when there is no particular distinction between terminal devices 7a and 7b, image management devices 5a and 5b, and electronic medical record management devices 6a and 6b, they will be referred to as "terminal device 7," "image management device 5," and "electronic medical record management device 6," respectively.

[0093] 2 shows an example in which the LANs of medical facilities 8a and 8b are connected to a communication network 9. The information processing device 1 is not limited to the configuration shown in Fig. 2 as long as it is communicably connected to the image management device 5 and electronic medical record management device 6 in each medical facility via the communication network 9. For example, the information processing device 1 may be installed in the medical facility 8a or the medical facility 8b.

[0094] In the information processing system 100b having such a configuration, the information processing device 1 can acquire a first image of a subject Pa who has been examined at a medical facility 8a from an image management device 5a at the medical facility 8a. The information processing device 1 can also acquire attribute information and surgery information of the subject Pa from an electronic medical record management device 6a at the medical facility 8a. The information processing device 1 then transmits first estimated information about the subject Pa to a terminal device 7a installed at the medical facility 8a. Similarly, the information processing device 1 can acquire attribute information and surgery information of a subject Pb from an electronic medical record management device 6b at the medical facility 8b. The information processing device 1 then transmits the first estimated information about the subject Pb to a terminal device 7a installed at the medical facility 8b.

[0095] [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 system 100b, the information processing device 1 may also receive input information from the terminal device 7.

[0096] For example, in the information processing systems 100a and 100b, the functions of the learning unit 25 may be configured to install a learned first learning model 33 on the information processing device 1, the learning process of which has been performed by another computer other than the information processing device 1.

[0097] For example, in the information processing systems 100a and 100b, the function of the second estimator 26 may be provided by a computer or a terminal device 7 different from the information processing device 1. Furthermore, in the information processing systems 100a and 100b, the function of the second estimator 26 may be provided by a computer or a terminal device 7 different from the information processing device 1.

[0098] [Embodiment 4] Another embodiment of the present disclosure will be described below. The information processing device 1001 in this embodiment outputs third estimated information of bone information related to the bone condition of a subject, which is estimated using a third learning model 1034 based on input information including at least one of a medical image showing the subject's trabeculae and a first virtual image representing the color shading in the medical image for each predetermined area (pixel), as the first image and / or the second image in embodiment 1. The learning model in this embodiment is trained using training data including at least one of a second medical image showing the trabeculae of a specific person and information including trabecular bone information related to the trabecular bone condition of the specific person, and a second virtual image representing the color shading in the second medical image for each predetermined area.

[0099] FIG. 14 is a diagram illustrating an example configuration of an information processing system 1100a in a medical facility 8 that has introduced an information processing device 1001. As illustrated in FIG. 14 , the information processing system 1100a includes an information processing device 1001 instead of the information processing device 1 in the information processing system 100a of embodiment 1. The information processing device 1001 estimates bone information related to the bone condition of the subject from medical information including at least one of a first image showing the subject's bone trabeculae and a first virtual image that represents the color shading in the first image for each predetermined area. The information processing device 1001 may estimate the subject's future bone information or the subject's current bone information. The information processing device 1001 is a computer that transmits third estimated information of the subject's bone information to the terminal device 7.

[0100] The information processing system 1100a includes an image management device 5A instead of the image management device 5 in embodiment 1. The information processing system 1100a may include a test value management device 1005 and a diagnosis result management device 1006 in addition to the configuration of the information processing system 100a in embodiment 1. The information processing device 1001, the terminal device 7, the image management device 5A, the electronic medical record management device 6, the test value management device 1005, and the diagnosis result management device 1006 may be communicably connected via a LAN within the medical facility 8.

[0101] The image management device 5A generates a virtual image that represents the color shading in the first image for each predetermined area. The virtual image is generated from the shading of the cancellous bone and / or cortical bone portion and the non-bone portion of the bone image information that includes the bone portion in the first image. More specifically, the virtual image can be generated, for example, by converting the bone shading from the bone image information for each predetermined area into a numerical value and representing the numerical value as a color shading.

[0102] The predetermined area may be, for example, one pixel of the image or multiple pixels of the image. The predetermined area may take into account at least one of the following: trabeculae, trabecular number (e.g., the number of trabeculae per unit length), trabecular spacing (e.g., the spatial distance between trabeculae), trabecular width (e.g., the width or thickness of trabeculae), trabecular orientation (e.g., the degree of trabecular alignment within trabeculae), and bone connectivity density (e.g., the number of paths connecting the ends of trabeculae per unit area). The numerical value may be, for example, at least one of bone mass (e.g., a numerical value in grams), bone density, and cancellous bone structure index. The color shading may be, for example, two-tone white and black, grayscale (e.g., two-tone white and black plus 254 shades of gray between white and black), or a heat map using multiple colors. The information processing device 1 may acquire, from the image management device 5A, medical images showing the subject's trabecular bones, and virtual images generated using the medical images.

[0103] The test value management device 1005 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, for example, at least one of the Kellgren-Lawrence (KL) classification, bone morphology angle, muscle mass, MMSE (Mini Mental State Examination), blood test values ​​(for example, at least one of a bone formation marker, a bone resorption marker, and a vitamin K value), a liver function marker, a uric acid level, bone evaluation information, and a malignant tumor marker. The information processing device 1001 may obtain the test values ​​of the subject from the test value management device 1005.

[0104] The diagnostic results management device 1006 is a computer that functions as a server for managing diagnostic results obtained by diagnoses performed at the medical facility 8. The information processing device 1001 may acquire the diagnostic results of the subject from the diagnostic results management device 1006. The diagnostic results may include the presence or absence of a fracture and the progression of osteoporosis. For the fracture, information regarding the cause, such as a fragility fracture, a stress fracture, or a traumatic fracture, may be added.

[0105] 14 shows an example of a configuration including an image management device 5A, an electronic medical record management device 6, a test value management device 1005, and a diagnosis result management device 1006, but is not limited to this. For example, a configuration may be provided that includes a management device that has the functions of any two or more or all of these devices.

[0106] (Configuration of Information Processing Apparatus 1001) Next, the configuration of the information processing apparatus 1001 applied to the information processing system 1100a shown in Fig. 14 will be described with reference to Fig. 15. Fig. 15 is a block diagram showing an example of the configuration of the information processing apparatus 1001.

[0107] The information processing device 1001 includes a control unit 1002 that performs overall control of each unit of the information processing device 1001, and a storage unit 1010 that stores various data used by the control unit 1002. The control unit 1002 includes an acquisition unit 1021, an estimation unit 1023, an output unit 1024, and a learning unit 1025. The storage unit 1010 stores a control program 1031 that is a program for performing various controls of the information processing device 1001, as well as teacher data 1032 and a trained third learning model 1034.

[0108] <Acquisition Unit 1021> The acquisition unit 1021 acquires input information including a first image of the subject. The input information is data input to the estimation unit 1023. The input information includes at least one of a first image showing the subject's trabecular bones and a virtual image representing the color shading in the first image for each specified area. In the following description, the first image showing the subject's trabecular bones may be referred to as the first medical image, and the virtual image representing the color shading in the medical image for each specified area may be referred to as the first virtual image. The acquisition unit 1021 may acquire the first medical image and / or the first virtual image from the image management device 5A. The acquisition unit 1021 may acquire, from the virtual image generation device, a first virtual image generated using the first medical image by a virtual image generation device other than the image management device 5A. In addition to the first medical image and the first virtual image, the acquisition unit 1021 may acquire the subject's attribute information from the electronic medical record management device 6 as input information, may acquire the subject's test values ​​from the test value management device 1005, or may acquire the subject's diagnostic results from the diagnostic result management device 1006.

[0109] <Estimation unit 1023> The estimation unit 1023 estimates third estimated information, which is bone information regarding the bone condition of the subject, by inputting the input information acquired by the acquisition unit 1021 into the third learning model 1034. In this embodiment, an example in which the estimation unit 1023 estimates the subject's future bone information will be described. However, the subject's past bone information may also be estimated. Here, the third learning model 1034 is trained in advance using training data 1032. The training data 1032 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 training data 1032 includes at least one of information including a second medical image showing the specific person's trabecular bones and trabecular bone information regarding the specific person's trabecular bone condition, and a second virtual image representing the color shading in the second medical image for each specific area. In the following explanation, a medical image showing the bone trabeculae of a specified person may be referred to as the second medical image, and a virtual image that represents the color shades in the second medical image for each specified area may be referred to as the second virtual image.

[0110] The estimation unit 1023 may estimate the subject's future bone information by inputting input information including at least one of the first medical image and the first virtual image into the third learning model 1034. The estimation unit 1023 may (1) input the medical information including the first medical image into the third learning model 1034 trained using training data including at least information including a second medical image depicting the trabeculae of a specific person and trabecular bone information related to the state of the trabeculae of the specific person, or (2) input medical information including the first virtual image into the third learning model 1034 trained using training data including at least a second virtual image that represents color shading in the second medical image for each specific area, thereby estimating the subject's future bone information. The estimation unit 1023 may estimate, as the bone information, at least one of the following: a trabecular bone structure index, a fracture occurrence probability, a possibility of osteoporosis, a drug effect, an incident occurrence, a bone mineral density, a trabecular bone number, a trabecular space, and a bone connectivity density, by inputting the input information into the third learning model 1034. Alternatively, the bone information may be obtained by analyzing bone strength from the state of the cortical bone and / or the trabecular bone.

[0111] The third learning model 1034 is a computational model used by the estimation unit 1023 when performing computations based on input data. The learning unit 1025 performs machine learning on an untrained neural network using the training data 1032 described below, thereby generating the third learning model 1034. Here, the third learning model 1034 may also be applied to non-human animals. In this case, the "predetermined person" in the training data 1032 may be of the same biological species as the "subject." In other words, the information processing device 1001 according to the present disclosure can also estimate bone information regarding the bone condition of non-human animals. Specific examples of the training data 1032, the configuration of the neural network, and the learning process will be described later.

[0112] <Output unit 1024> The output unit 1024 transmits the information estimated by the estimation unit 1023 to the terminal device 1030. The information processing device 1001 may be configured to include a display unit (not shown). In that case, the output unit 1024 causes the display unit to display the information estimated by the estimation unit 1023.

[0113] <Learning Unit 1025> The learning unit 1025 controls the learning process for an untrained neural network. The learning unit 1025 executes the learning process for the untrained neural network to create a trained neural network that functions as the estimation unit 1023. Teacher data 1032 (described later) is used for this learning. Specific examples of the learning performed by the learning unit 1025 will be described later.

[0114] (Configuration of Estimation Unit 1023) The configuration of the estimation unit 1023 will be described below with reference to Fig. 16. The configuration shown in Fig. 16 is an example, and the configuration of the estimation unit 1023 is not limited to this.

[0115] 16 , the estimation unit 1023 performs calculations based on the third learning model 1034 on input data input to the input layer 1210, and outputs output data from the output layer 1230. The output data is future bone information of the subject. The future bone information may be, for example, at least one of a cancellous bone structure index, a fracture occurrence probability, a possibility of osteoporosis, a drug effect, an incident occurrence, bone mineral density, trabecular number, trabecular spacing, trabecular width, trabecular orientation, and bone connectivity density.

[0116] The estimation unit 1023 in FIG. 16 includes a neural network 200 having an input layer 1210 and an output layer 1230. FIG. 16 illustrates a case where the neural network 1200 is a CNN. As illustrated in FIG. 16, the neural network 1200 includes, for example, an input layer 1210, a hidden layer 1220, and an output layer 1230. The hidden layer 1220 is also referred to as an intermediate layer. The hidden layer 1220 includes, for example, multiple convolutional layers 1240, multiple pooling layers 1250, and a fully connected layer 1260. In the neural network 1200, the fully connected layer 1260 is located before the output layer 1230. In the neural network 1200, the convolutional layers 1240 and the pooling layers 1250 are alternately arranged between the input layer 1210 and the fully connected layer 1260. Note that the configuration of the neural network 1200 is not limited to the example in Fig. 16. For example, the neural network 1200 may include one convolutional layer 1240 and one pooling layer 1250 between the input layer 1210 and the fully connected layer 1260. Furthermore, the neural network 1200 may be a neural network other than a convolutional neural network.

[0117] The neural network 1200 is not limited to a CNN and may be an LSTM. The neural network 1200 may be, for example, a ConvLSTM network that combines a CNN and an LSTM. In this case, the input layer can extract features related to changes in input data. The output layer can calculate new features based on the features extracted in the input layer, the time changes in the input data, and the initial values. The input layer and the output layer each have multiple LSTM layers. Each of the input layer and the output layer may have three or more LSTM layers.

[0118] (Learning Process by Learning Unit 1025) The learning process for generating the third learning model 1034 will be described below with reference to Fig. 17. Fig. 17 is a flowchart showing an example of the flow of the learning process by the learning unit 1025.

[0119] The learning unit 1025 acquires training data 1032 from the storage unit 1010 (step S101). The training data 1032 includes information including a second medical image showing the trabecular bones of a specific person and trabecular bone information related to the state of the trabecular bones of the specific person, at least one of the second virtual images, and data related to the state of the trabecular bones of the specific person a predetermined time after the second medical image is captured, and includes explanatory variables and objective variables to be input to the input layer 1210. Here, the explanatory variables are the information including the second medical image showing the trabecular bones of the specific person and trabecular bone information related to the state of the trabecular bones of the specific person, and at least one of the second virtual images, and the objective variable is data related to the state of the trabecular bones of the specific person a predetermined time after the second medical image is captured.

[0120] Next, the learning unit 1025 inputs information including a second medical image showing the trabeculae of a certain person (referred to as person A) and trabecular information regarding the state of the trabeculae of the specified person, as well as information including at least one of the second virtual images, into the input layer 210 (step S102).

[0121] Next, the learning unit 1025 acquires output data related to bone information of person A from the output layer 1230 (step S103). This output data contains the same content as the objective variable of the training data 1032. In FIG. 17, the order of steps S102 and S103 may be reversed. Alternatively, in FIG. 17, steps S102 and S103 may be executed simultaneously.

[0122] Next, the learning unit 1025 acquires the objective variable for person A included in the teacher data 1032. Then, the learning unit 1025 compares the output data acquired in step S103 with the objective variable for person A to calculate an error (step S104), and adjusts the third learning model 1034 being learned so as to reduce the error (step S105).

[0123] 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 1023 uses the new learning model in subsequent calculations. During the learning model adjustment stage, parameters used by the estimation unit 1023 (e.g., filter coefficients, weighting coefficients, etc.) may be adjusted.

[0124] If the error is not within a predetermined range and explanatory variables for all people included in the teacher data 1032 have not been input (NO in step S106), the learning unit 1025 returns to step S102 and repeats the learning process. If the error is within a predetermined range and explanatory variables for all people included in the teacher data 1032 have been input (YES in step S106), the learning unit 1025 ends the learning process.

[0125] When the above-described learning process is employed, the estimation unit 1023 can estimate the subject's future bone information from medical information including at least one of a first medical image showing the subject's bone trabeculae and a first virtual image representing the color shading in the first medical image for each predetermined area. When the training data 1032 includes multiple first medical images and / or multiple first virtual images of the same person, the third learning model 1034 may be constructed based on temporal changes in the feature values ​​of characteristic regions. This allows the subject's future bone information to be estimated taking into account changes in the state of the bone trabeculae over time, thereby improving the accuracy of the estimation.

[0126] (Processing Performed by Information Processing Apparatus 1001) The flow of processing performed by the information processing apparatus 1001 will be described below with reference to Fig. 18. Fig. 18 is a flowchart showing an example of the flow of processing performed by the information processing apparatus 1001.

[0127] First, the acquisition unit 1021 acquires medical information including at least one of a first medical image showing the subject's bone trabeculae and a first virtual image that represents the color shading in the first medical image for each specified area (step S1011: acquisition step).

[0128] Next, the estimation unit 1023 estimates the subject's future bone information by inputting the acquired medical information into the third learning model 1034 (step S1012: estimation step).

[0129] The output unit 1024 outputs each piece of information including the bone information estimated in step S1012 (step S1013: output step).

[0130] According to this configuration, the information processing device 1001 and the information processing system 1100a estimate future bone information of a subject from medical information including at least one of a first medical image showing the subject's bone trabeculae and a first virtual image representing the color shading of the first medical image for each predetermined area. Here, the first medical image shows the bone trabeculae, which are the internal structure of the bone. Therefore, the estimation result output from the third learning model 1034 when the estimation unit uses the first medical image or a first virtual image generated using the first medical image as input information reflects the internal structure of the bone, resulting in high estimation accuracy. In other words, the information processing device 1001 and the information processing system 1100a can estimate bone information related to the subject's future bone condition with high accuracy.

[0131] In the above description, the information processing device 1001 estimates bone information related to the subject's future bone condition. However, the information processing device 1001 of this embodiment is not limited to this. The information processing device 1001 may also estimate bone information related to the subject's current bone condition. In this case, the learning unit 1025 generates the third learning model 1034 using data related to the state of the trabecular bone of the specified person at the time the second medical image was captured as the objective variable. As a result, the estimation unit 1023 can estimate bone information related to the subject's current bone condition by inputting medical information including at least one of the first medical image and the first virtual image into the third learning model 1034.

[0132] Here, it is considered that the bone condition changes significantly due to menopause. Therefore, when estimating bone information regarding the future bone condition of a subject, and when the subject is a female who has not yet undergone menopause, the estimation unit 1023 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 will not undergo menopause, if the subject is a female who has not yet undergone menopause. This makes it possible to output a more accurate estimation result that takes into account the presence or absence of menopause. When the subject is a female who has not yet undergone menopause, the estimation unit 1023 may simultaneously output the first estimation result assuming that the subject has undergone menopause and the second estimation result assuming that the subject will not undergo menopause.

[0133] [Embodiment 5] (Configuration of Information Processing System 1100b) The information processing device 1001 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 1009. Fig. 19 is a diagram showing an example configuration of an information processing system 1100b according to another aspect of the present disclosure.

[0134] In addition to one or more terminal devices 7a, an image management device 5Aa, an electronic medical record management device 6a, a test value management device 1005a, and a diagnosis result management device 1006a may be communicably connected to the LAN in medical facility 8a. In addition to terminal device 7b, an image management device 5Ab, an electronic medical record management device 6b, a test value management device 1005b, and a diagnosis result management device 1006b may be communicably connected to the LAN in medical facility 8b. In this disclosure, when there is no particular distinction between medical facilities 8a and 8b, they will be referred to as "medical facility 8." Furthermore, when no particular distinction is made between terminal devices 7a and 7b, image management devices 5Aa and 5Ab, electronic medical record management devices 6a and 6b, test value management devices 1005a and 1005b, and diagnostic result management devices 1006a and 1006b, they will be referred to as "terminal device 7," "image management device 5A," "electronic medical record management device 6," "test value management device 1005," and "diagnostic result management device 1006," respectively.

[0135] 19 shows an example in which the LANs of medical facilities 8a and 8b are connected to a communication network 1009. The information processing device 1001 is only required to be communicably connected to the image management device 5A, electronic medical record management device 6, test value management device 1005, and diagnosis result management device 1006 in each medical facility via the communication network 1009, and is not limited to the configuration shown in FIG. 19. For example, the information processing device 1001 may be installed in the medical facility 8a or the medical facility 8b.

[0136] In the information processing system 1100b having such a configuration, the information processing device 1001 can acquire a first image, attribute information, test values, and diagnosis results of a subject Pa who has been examined at a medical facility 8a from an image management device 5Aa, an electronic medical record management device 6a, a test value management device 1005a, and a diagnosis result management device 1006a of the medical facility 8a. The information processing device 1001 then transmits the estimated future bone information of the subject Pa to a terminal device 7a installed at the medical facility 8a. Similarly, the information processing device 1001 transmits the future bone information of the subject Pb to a terminal device 7b.

[0137] [Special Notes] It is not essential that all of the functional blocks included in the control unit 1002 of the information processing device 1001 are included in the information processing device 1001. For example, in the information processing system 1100a, the terminal device 7 may have the function of the acquisition unit 1021, and the information processing device 1001 may receive input information from the terminal device 7. In the information processing system 1100b, the information processing device 1001 may also receive input information from the terminal device 7.

[0138] For example, in the information processing systems 1100a and 1100b, a third learning model 1034 in which the function of the learning unit 1025 has been learned by a computer other than the information processing device 1001 may be installed in the information processing device 1001. For example, in the information processing systems 1100a and 1100b, the function of the learning unit 1025 may be provided by a computer or terminal device 1030 other than the information processing device 1001. Furthermore, in the information processing systems 1100a and 1100b, the function of the estimation unit 1023 may be provided by a computer or terminal device 1030 other than the information processing device 1001.

[0139] [Example of implementation by software] The functions of the information processing device 1, 1a, 1001 (hereinafter referred to as the "device") 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 unit included in the control unit 2, 2a, 1002).

[0140] 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 functions described in each of the above embodiments are realized by executing the program using the control device and storage device.

[0141] 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.

[0142] Furthermore, some or all of the functions of the control blocks can be realized by logic circuits. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of the control blocks can also be realized by, for example, a quantum computer.

[0143] 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).

[0144] 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.

[0145] [Summary] The information processing system according to aspect 1 of the present disclosure includes an acquisition unit that acquires input information including a first image showing at least a portion of a target bone in which a first implant of a subject is embedded, a first estimation unit that inputs the input information into a first learning model trained using first teacher data including a second image showing at least a portion of a bone of an animal including a human, and bone information related to at least one of bone density, bone mass, and bone quality of the bone, thereby estimating first estimated information related to at least one of bone density, bone mass, and bone quality of the target bone, and an output unit that outputs the first estimated information.

[0146] In the information processing system according to aspect 2 of the present disclosure, in the above aspect 1, the second image may include an image showing at least a portion of the bone in which the second implant is embedded.

[0147] In the information processing system according to aspect 3 of the present disclosure, in the above-mentioned aspect 1 or 2, the first estimated information may include information regarding at least one of bone density, bone mass, and bone quality for a portion of the target bone in which the first implant is embedded.

[0148] In the information processing system according to aspect 4 of the present disclosure, in any one of aspects 1 to 3 above, the first estimated information may include information regarding at least one of bone density, bone mass, and bone quality of multiple areas of the target bone, including areas adjacent to the first implant.

[0149] An information processing system according to aspect 5 of the present disclosure, in any one of aspects 1 to 4 above, may be such that the first implant is an artificial hip joint implant including a stem, the target bone is a femur in which the stem is embedded, and the first estimation unit estimates multiple pieces of the first estimated information within an area of ​​the femur classified by the Gruen classification.

[0150] In an information processing system according to aspect 6 of the present disclosure, in the above-mentioned aspect 5, the first estimated information may include the first estimated information within a proximal region of the femur in which the stem is embedded.

[0151] An information processing system according to aspect 7 of the present disclosure, in any one of aspects 1 to 4 above, may be such that the first implant is an artificial hip implant including a cup, the target bone is an acetabulum in which the cup is embedded, and the first estimation unit estimates a plurality of the first estimated information within an area of ​​the acetabulum classified by the Charnley classification.

[0152] The information processing system according to aspect 8 of the present disclosure, in any of aspects 1 to 7 above, further includes a second estimation unit that inputs the input information into a second learning model trained using second teacher data including a third image showing at least a portion of a bone of an animal, including a human, and progress information regarding an event that occurred due to the implantation of a third implant in the bone, and estimates second estimated information regarding an event that may occur in the subject due to the implantation of the first implant, and the output unit may transmit the second estimated information.

[0153] In the information processing system according to aspect 9 of the present disclosure, in the above aspect 8, the event may include at least one of loosening of the implanted first implant, fracture of the bone in which the first implant is implanted, dislocation of a joint associated with the bone in which the first implant is implanted, infection of an area including the bone in which the first implant is implanted, and fracture of the first implant.

[0154] In the information processing system according to aspect 10 of the present disclosure, in any one of aspects 1 to 9 above, the input information may include at least one of attribute information of the subject and surgical information regarding the implantation procedure used to implant the first implant into the target bone.

[0155] In the information processing system according to aspect 11 of the present disclosure, in the above aspect 10, the attribute information may include at least any of the subject's age, sex, height, weight, race, whether or not they have undergone menopause, whether or not they have had a fracture, the number of fractures, the location of the fractures, their fracture history, information about their lifestyle habits, information about medications they are taking, and information indicating the results of a blood test.

[0156] In the information processing system according to aspect 12 of the present disclosure, in the above-mentioned aspect 10, the surgical information may include at least any of the following: the model of the first implant embedded in the target bone, the size of the first implant, the surgical procedure for the implantation procedure, the surgical time for the implantation procedure, the amount of bleeding during the implantation procedure, information indicating the medical facility that performed the implantation procedure, and information indicating the surgeon who performed the implantation procedure.

[0157] In an information processing system according to aspect 13 of the present disclosure, in any of aspects 1 to 12 above, the first implant may include at least one of an artificial joint, a spinal implant, a trauma implant, a plastic implant, and a dental implant.

[0158] An information processing system according to aspect 14 of the present disclosure is the same as in aspect 13 above, wherein the artificial joint may be at least one of an artificial hip joint, an artificial knee joint, an artificial shoulder joint, an artificial elbow joint, an artificial ankle joint, and an artificial finger joint, the spinal implant may be at least one of an instrumentation, a cage, an artificial intervertebral disc, and an artificial vertebral body, the trauma implant may be at least one of a plate, a screw, and a nail, and the plastic implant may be at least one of a skull plate and a nasal bone prosthesis.

[0159] A control method for an information processing system according to aspect 15 of the present disclosure includes an acquisition step of acquiring input information including a first image showing at least a portion of a target bone in which a first implant of a subject is embedded, and an output step of inputting the input information into a learning model trained using first teacher data including a second image showing at least a portion of a bone of an animal including a human, and bone information regarding at least one of the bone density, bone mass, and bone quality of the bone, to estimate first estimated information regarding at least one of the bone density, bone mass, and bone quality of the target bone, and outputting the first estimated information.

[0160] The control program of the information processing device according to aspect 16 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 14 above, and is a control program for causing a computer to function as the acquisition unit, the first estimation unit, and the output unit.

[0161] A recording medium according to aspect 17 of the present disclosure is a computer-readable recording medium on which the control program according to aspect 16 above is recorded.

[0162] 1, 1a Information processing device 21 Acquisition unit 23 First estimation unit 24 Output unit 26 Second estimation unit 32 First teacher data 33 Trained first learning model 34 Trained second learning model 100a, 100b Information processing system S11 Acquisition step S12 Estimation step S13 Output step

Claims

1. an acquisition unit that acquires input information including a first image showing at least a part of a target bone in which a first implant of a subject is embedded; a first estimation unit that inputs the input information into a first learning model that has been trained using a second image that shows at least a part of a bone of an animal, including a human, and first teacher data that includes bone information about at least one of bone density, bone mass, and bone quality of the bone, and estimates first estimated information about at least one of bone density, bone mass, and bone quality of the target bone; an output unit that outputs the first estimated information.

2. The information processing system according to claim 1 , wherein the second image includes an image showing at least a portion of the bone in which the second implant is embedded.

3. The information processing system according to claim 1 , wherein the first estimated information includes information on at least one of bone density, bone volume, and bone quality of a partial region of the target bone in which the first implant is embedded.

4. The information processing system according to claim 1 , wherein the first estimated information includes information regarding at least one of bone density, bone mass, and bone quality of a plurality of sites in the target bone, including a site adjacent to the first implant.

5. the first implant is a prosthetic hip implant including a stem; the target bone is a femur in which the stem is embedded, The information processing system according to claim 1 , wherein the first estimation unit estimates a plurality of pieces of the first estimated information within a region of the femur classified according to the Gruen classification.

6. The information processing system according to claim 5 , wherein the first estimated information includes the first estimated information within a proximal region of the femur in which the stem is embedded.

7. the first implant is a hip prosthesis implant including a cup; the target bone is the acetabulum in which the cup is embedded; The information processing system according to claim 1 , wherein the first estimation unit estimates a plurality of pieces of the first estimated information within a region of the acetabulum classified according to the Charnley classification.

8. a second estimation unit that inputs the input information into a second learning model that has been trained using second teacher data including a third image showing at least a part of a bone of an animal including a human, and progress information regarding an event that has occurred due to the implantation of a third implant into the bone, and estimates second estimated information regarding an event that may occur in the subject due to the implantation of the first implant; The information processing system according to claim 1 , wherein the output unit transmits the second estimated information.

9. 9. The information processing system of claim 8, wherein the event includes at least one of loosening of the implanted first implant, fracture of the bone in which the first implant is implanted, dislocation of a joint associated with the bone in which the first implant is implanted, infection of an area including the bone in which the first implant is implanted, and fracture of the first implant.

10. The information processing system according to claim 1 , wherein the input information includes at least one of attribute information of the subject and surgical information relating to the surgical procedure by which the first implant was implanted in the subject bone.

11. 11. The information processing system according to claim 10, wherein the attribute information includes at least one of the subject's age, sex, height, weight, race, whether or not the subject has experienced menopause, whether or not the subject has had a fracture, the number of fractures, the location of the fractures, a history of fractures, information about lifestyle habits, information about medications being taken, and information indicating the results of a blood test.

12. 11. The information processing system of claim 10, wherein the surgical information includes at least one of the following: the model of the first implant implanted in the target bone, the size of the first implant, the surgical procedure for the implantation procedure, the surgical time for the implantation procedure, the amount of bleeding during the implantation procedure, information indicating the medical facility that performed the implantation procedure, and information indicating the surgeon who performed the implantation procedure.

13. The information processing system of claim 1 , wherein the first implant comprises at least one of a prosthetic joint, a spinal implant, a trauma implant, a plastic implant, and a dental implant.

14. The artificial joint is at least one of an artificial hip joint, an artificial knee joint, an artificial shoulder joint, an artificial elbow joint, an artificial ankle joint, and an artificial finger joint, the spinal implant is at least one of an instrumentation, a cage, an artificial disc, and an artificial vertebral body; the trauma implant is at least one of a plate, a screw, and a nail; The information processing system of claim 13 , wherein the plastic implant is at least one of a skull plate and a nasal bone prosthesis.

15. acquiring input information including a first image showing at least a portion of a target bone in which a first implant is implanted in the subject; A control method for an information processing system, comprising: an output step of inputting the input information into a learning model trained using a second image showing at least a portion of a bone of an animal, including a human, and first teacher data including bone information regarding at least one of the bone density, bone mass, and bone quality of the bone, to estimate first estimated information regarding at least one of the bone density, bone mass, and bone quality of the target bone, and outputting the first estimated information.

16. A control program for causing a computer to function as the information processing system according to claim 1, the control program causing the computer to function as the acquisition unit, the first estimation unit, and the output unit.

17. A computer-readable recording medium on which the control program according to claim 16 is recorded.