Information processing device and information processing method

Abstract

An information processing device (10) comprises: a model generation unit (11) that generates a model through deep learning based on medical image information obtained by imaging a region of a person's body and background information relating to the person that includes age information at the time of imaging the region; an inference unit (13) that, on the basis of the generated model, a medical image obtained by imaging the aforementioned region on a subject for inference, and background information relating to the subject that includes age information at the time of imaging the region and target age information for inference, infers a medical image of the region for the subject at the target age; and an output unit (14) that outputs the medical image of the region of the subject obtained by means of the inference.

Description

Information processing device and information processing method

[0001] The present disclosure relates to an information processing device and an information processing method for inferring and outputting medical images. Note that the term "medical image" refers to an image obtained by actually capturing an image of an internal part of the human body (e.g., an organ such as the brain, lungs, heart, stomach, intestines, or kidneys) or by inference for the purpose of diagnosing or treating a human disease.

[0002] It is known that human cognitive function is related to the volume of the hippocampus in the brain, and patients with diseases related to cognitive function (such as Alzheimer's disease) are often shown a numerical representation of their hippocampal volume. However, simply showing a numerical value is often difficult for patients to understand, and rarely leads to behavioral changes such as lifestyle improvements. Therefore, it is desirable to visually show patients the state of brain atrophy so that they can recognize their condition. Patent Document 1 listed below proposes a technology for predicting future brain images by performing a specified image processing (erosion processing) on ​​a patient's current brain image.

[0003] Japanese Patent Application Laid-Open No. 2017-023457

[0004] However, current image processing for brain images has limitations in prediction accuracy, so there is a need to apply prediction technology using artificial intelligence (AI prediction), which has become increasingly popular in recent years, to predict brain images with greater accuracy. This situation is not limited to brain image prediction, but also applies to cases such as predicting medical images of diseased areas for cancer patients.

[0005] Therefore, an object of the present disclosure is to accurately predict medical images of human parts.

[0006] The information processing device according to the present disclosure includes a model generation unit that generates a model by deep learning based on medical image information of a part of a person's body and background information about the person including age information at the time the part was imaged; an inference unit that infers a medical image of the part of the subject at a target age based on the model generated by the model generation unit, medical images of the part of the person to be inferred, and background information about the subject including age information at the time the part was imaged and target age information for inference; and an output unit that outputs the medical image of the part of the subject obtained by inference by the inference unit.

[0007] According to the present disclosure, medical images of human parts can be predicted with high accuracy.

[0008] It is a functional block configuration diagram of an information processing device. It is a flow diagram showing processing executed in a learning process. It is a flow diagram showing processing executed in an inference process. It is a diagram for explaining ingenuity in model generation. It is a diagram showing an example of a hardware configuration of an information processing device.

[0009] An embodiment of an information processing device according to the present disclosure will be described below with reference to the drawings. In the following, an embodiment will be described assuming that a medical image to be inferred is a magnetic resonance image (i.e., a magnetic resonance imaging image (hereinafter referred to as an "MRI image")) of a human brain.

[0010] (Configuration of Information Processing Apparatus) As shown in Fig. 1, an information processing apparatus 10 in this embodiment includes, as functional blocks, a model generation unit 11, a trained model storage unit 12, an inference unit 13, and an output unit 14. The functions of each unit will be outlined below. Details of the functions will be described later together with processing explanations following the flow charts in Figs. 2 and 3.

[0011] The model generation unit 11 is a functional unit that acquires information on medical images of various human body parts (here, MRI images of the brain (hereinafter referred to as "brain MRI images")) and background information including age information at the time the MRI images were captured, and generates a model M by deep learning based on the acquired brain MRI image information and background information. Note that the "background information" refers to various information about the person whose brain MRI image was captured, including age information at the time the brain MRI image was captured, and may also include other attribute information about the person (e.g., current age information, gender information, information about physique, information about medical history, information about lifestyle habits, etc.). More specifically, the model generation unit 11 acquires image information of the brain MRI image as training image information and the background information as training background information, and generates (constructs) a model M using the training image information and training background information as inputs in deep learning to internally solve a regression problem of determining the age of the brain image of the inferred image. In this case, the model generating unit 11 of this embodiment has a first feature, which will be described later, of incorporating the regression loss into the overall loss.

[0012] Regarding the acquisition of the above-mentioned learning image information and learning background information, a learning information storage unit in which this information is stored in advance may be provided within the information processing device 10, and the learning image information and learning background information may be acquired from this learning information storage unit, or the above-mentioned learning information storage unit may not be provided, and the information may be acquired from an external server in which the information is stored in advance.

[0013] As an example of the generator in the deep learning described above, a U-Net (officially a "U-type convolutional neural network"), which is commonly known as a type of convolutional neural network, is used. The U-Net is a model consisting of an encoder and a decoder. The U-Net encoder convolves an input image multiple times to extract features of the image, and the U-Net decoder receives the features extracted by the encoder from the encoder and performs a process inverse to normal convolution (deconvolution) to output a probability map of the same size as the input image. The model generation unit 11 of this embodiment has a second feature, described below, in that background information, including age information, is reflected in the generation of a model during the U-Net processing process, after the encoder compresses the training image information and before the decoder starts to restore the training image information (this timing is also known as the bottleneck of the U-Net).

[0014] The generator in deep learning is not limited to the above-mentioned U-Net, and may be, for example, Residual Neural Networks (ResNet).

[0015] The trained model storage unit 12 is a functional unit that stores the model M generated by the model generation unit 11.

[0016] The inference unit 13 is a functional unit that infers a medical image (here, a brain MRI image) of a part of the subject at a target age based on the model M generated by the model generation unit 11, a medical image (here, a brain MRI image) of a part of the subject to be inferred, and background information about the subject including age information at the time the medical image was taken and target age information for inference, and further has the function of generating an image (difference image) showing the difference between the medical image at the target age obtained by inference and the medical image at the age at the time of taking the image (i.e., the medical image used as the basis for inference).

[0017] The output unit 14 is a functional unit that outputs medical images (brain MRI images in this case) and difference images of the subject's body parts obtained by inference and generation by the inference unit 13. Note that "output" can take various forms, such as display output, print output, and data transmission to outside the information processing device 10.

[0018] (Regarding the processing executed in the information processing device) Below, the processing executed in the information processing device 10 of this embodiment will be described in order: (1) processing executed in the learning process that generates a model (Figure 2), and (2) processing executed in the inference process that performs inference using the model (Figure 3).

[0019] 2 shows a processing flow of the processing executed in the learning process. First, the model generation unit 11 acquires brain MRI images of various people as learning image information and background information about the people as learning background information (step S1), and generates a model M by deep learning based on the acquired brain MRI images and background information as follows (step S2).

[0020] In the deep learning of step S2, the model generation unit 11 uses the acquired training image information and training background information as inputs to generate (construct) a model M to internally solve a regression problem that determines the age of the brain image associated with the inferred image. In this process, the model generation unit 11 incorporates the regression loss into the overall loss (first feature). The deep learning algorithm used in this process is CycleGAN (see FIG. 4), a type of GAN (Generative Adversarial Network), a method of unsupervised learning. CycleGAN generates an image and then transforms it back into the original image. Unlike conventional GANs, CycleGAN not only predicts whether the generated image is authentic, but also learns to ensure that the transformed image matches the original input image.

[0021] The first feature, that is, incorporating the regression loss into the overall loss, is shown in the following equation (1), which is also shown at the top of Figure 4: L = L ＧＡＮ +λ ｃｙｃｌｅ L ｃｙｃｌｅ +λ ｉｄｔ Lｉｄｔ +λ ｒｅｇ L ｒｅｇ (1) That is, the total cycle loss L is: Normal GAN ​​loss L ＧＡＮ and the loss L for the retransformed image to match the original input image. ｃｙｃｌｅ and the loss L for returning the identity mapping when the same domain is input. ｉｄｔ In addition to the linear equation, the regression loss L ｒｅｇ The term (λ ｒｅｇ L ｒｅｇ ) is calculated by the above formula (1) incorporating the above.

[0022] The first feature (incorporating regression loss into the overall loss) allows the generated model M to more accurately determine the age of a given brain MRI image as learning progresses. In other words, by incorporating the error (loss) for the problem of estimating age from brain MRI images into the calculation of the overall cycle loss L, the generated model M can acquire knowledge for solving that problem. This improves the accuracy of inferring brain MRI images of any target age. Conversely, if the error (loss) for the problem of estimating age from brain MRI images is not incorporated into the calculation of the overall cycle loss L, model M will not have the opportunity to learn about this specific problem, and as a result, will not be able to acquire the ability to properly estimate age from brain MRI images, which will result in a decrease in the accuracy of inferring brain MRI images of any target age.

[0023] As a second feature, in the deep learning of step S2, the model generation unit 11 reflects background information including age information in the generation of the model after the input learning image information is compressed by the encoder of the U-Net used as a generator and before the decoder of the U-Net starts to restore the learning image information (the timing also called the bottleneck part of the U-Net). AB "," "G BA" corresponds to the U-Net, and in each U-Net, from left to right, the encoder first compresses the training image information, and then the age information is reflected immediately thereafter (as indicated by the upward arrow in Figure 4), after which the decoder begins to restore the training image information. The second feature described above allows the age information to contribute more to the generation of the model than when the general method of reflecting the age information before compression by the encoder is adopted.

[0024] Returning to FIG. 2, the model M generated in step S2 is passed to the trained model storage unit 12 and stored by the trained model storage unit 12 (step S3).

[0025] 3 shows a processing flow of the inference process. First, the inference unit 13 acquires a brain MRI image of the subject as subject image information and background information about the subject (including age information at the time of imaging and target age information for inference) as subject background information (step S11). The acquired subject image information and subject background information are input into a trained model M, and an inference result (image information of the subject's target age) is obtained as an output from the model M (step S12). Furthermore, the inference unit 13 generates an image (difference image) showing the difference between the brain MRI image at the target age obtained by inference and the brain MRI image at the age at imaging (step S13). The generated difference image, the brain MRI image at the target age obtained by inference, and the brain MRI image at the age at imaging used as the basis for inference are passed to the output unit 14.

[0026] Then, the output unit 14 outputs the brain MRI image at the age at the time of imaging (the basis of inference), the brain MRI image at the target age obtained by inference, and a difference image showing the difference between them (step S14).

[0027] According to the embodiment described above, the subject can visually recognize the brain MRI image of the subject at the target age obtained by inference. In addition to the brain MRI image at the target age, the subject can also visually recognize a difference image showing the difference between the brain MRI image at the age at the time of imaging that was the basis for inference and the brain MRI image at the target age. This allows the subject to clearly recognize, for example, the state of brain atrophy, which can be linked to behavioral changes such as lifestyle improvements.

[0028] In the above embodiment, an embodiment has been described in which a human brain MRI image is assumed as the medical image to be inferred. However, the inference target may also be a medical image of an organ or other part of the body other than the human brain, and the inference target is not limited to an MRI image, but may also be a medical image obtained by other imaging means such as X-rays.

[0029] Furthermore, it is not essential to generate a difference image between the brain MRI image at the target age obtained by inference and the brain MRI image at the age at the time of imaging; at the very least, it is sufficient to generate a brain MRI image at the target age. Simply visually recognizing the brain MRI image at the target age allows the subject to clearly recognize the state of brain atrophy, which can lead to behavioral changes such as improving lifestyle habits.

[0030] The gist of the present disclosure lies in the following [1] to [6]. [1] An information processing device comprising: a model generation unit that generates a model by deep learning based on medical image information of a body part of a person and background information about the person including age information at the time of imaging of the body part; an inference unit that infers a medical image of the body part of a subject at a target age based on the model generated by the model generation unit, medical images of the body part of the subject to be inferred, and background information about the subject including age information at the time of imaging of the body part and target age information for inference; and an output unit that outputs the medical image of the body part of the subject obtained by inference by the inference unit. [2] The information processing device described in [1], wherein the inference unit further generates an image showing a difference between the medical image at the target age obtained by inference and the medical image at the age at the time of imaging, and the output unit further outputs the image showing the difference. [3] The information processing device according to any one of [1] to [2], wherein the model generation unit, in the deep learning, reflects the background information in the generation of the model at a timing after the input medical image is compressed and before restoration of the medical image begins. [4] The information processing device according to any one of [1] to [3], wherein the model generation unit, in the deep learning, generates the model to solve a regression problem that solves how old the medical image of the part of a person obtained by inference is when the medical image of the part of the person was obtained, and incorporates the regression loss into an overall loss. [5] The information processing device according to any one of [1] to [4], wherein the medical image is a magnetic resonance image of the brain of the person or the subject.[6] An information processing method comprising: a step in which an information processing device generates a model by deep learning based on medical image information of a part of a person's body and background information about the person, including age information at the time the part was imaged; a step in which the information processing device infers a medical image of the part of the subject at the target age, based on the generated model, medical images of the part of the subject to be inferred, and background information about the subject, including age information at the time the part was imaged and target age information for inference; and a step in which the information processing device outputs the medical image of the part of the subject obtained by inference.

[0031] [Explanation of Terms, Explanation of Hardware Configuration (FIG. 5), etc.] The block diagrams used in the description of the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0032] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0033] For example, an information processing device according to an embodiment of the present disclosure may function as a computer that executes the processes of the present disclosure. Fig. 5 is a diagram illustrating an example of a hardware configuration of an information processing device 10 according to an embodiment of the present disclosure. The information processing device 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0034] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0035] Each function of the information processing device 10 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0036] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc.

[0037] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. While the various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

[0038] The memory 1002 is a computer-readable recording medium and may be configured by, for example, at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to an embodiment of the present disclosure.

[0039] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0040] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD).

[0041] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0042] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0043] The information processing device 10 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0044] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0045] Each aspect / embodiment described in the present disclosure may be implemented using any of the following standards: LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), 6th generation mobile communication system (6G), xth generation mobile communication system (xG) (xG (x is, for example, an integer or a decimal number)), FRA (Future Radio Access), NR (new Radio), New radio access (NX), Future generation radio access (FX), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.17 (WiMAX (registered trademark)), IEEE 802.19 (WiMAX (registered trademark)), IEEE 802.20 (WiMAX (registered trademark)), IEEE 802.21 (Wi-Fi (registered trademark)), IEEE 802.22 (WiMAX (registered trademark)), IEEE 802.23 (WiMAX (registered trademark)), IEEE 802.24 (WiMAX (registered trademark)), IEEE 802.25 (WiMAX (registered trademark)), IEEE 802.26 (WiMAX (registered trademark)), IEEE 802.27 (WiMAX (registered trademark)), IEEE 802.28 (WiMAX (registered trademark)), IEEE 802.29 (WiMAX (registered trademark)), IEEE 802.30 (WiMAX (registered trademark)), IEEE 802.31 (Wi-Fi (registered trademark)), IEEE 802.32 (WiMAX (registered trademark)), IEEE 802.33 (WiMAX (registered trademark)), IEEE 802.34 ( The present invention may be applied to at least one of systems using 802.20, UWB (Ultra-Wide Band), Bluetooth (registered trademark), or other suitable systems, and next-generation systems that are extended, modified, created, or defined based on these systems. The present invention may also be applied to a combination of multiple systems (e.g., a combination of LTE and / or LTE-A with 5G).

[0046] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0047] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0048] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0049] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0050] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0051] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0052] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0053] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0054] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0055] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0056] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or other corresponding information. For example, a radio resource may be indicated by an index.

[0057] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0058] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0059] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0060] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0061] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0062] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0063] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0064] 10...information processing device, 11...model generation unit, 12...trained model storage unit, 13...inference unit, 14...output unit, M...model, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims

1. An information processing apparatus comprising: a model generation unit that generates a model by deep learning based on medical image information obtained by imaging a part of a human body and background information regarding the human including age information at the time of imaging the part; an inference unit that infers a medical image of the part of the subject at the target age based on the model generated by the model generation unit, a medical image obtained by imaging the part of the subject for inference, and background information regarding the subject including age information at the time of imaging the part and target age information for inference; and an output unit that outputs the medical image of the part of the subject obtained by the inference by the inference unit.

2. The information processing apparatus according to claim 1, wherein the inference unit further generates an image showing a difference between the medical image at the target age obtained by inference and the medical image at the age at the time of imaging, and the output unit further outputs the image showing the difference.

3. The information processing apparatus according to claim 1, wherein the model generation unit reflects the background information in the generation of the model at a timing after the input medical image is compressed and before restoration of the medical image is started in the deep learning.

4. The information processing apparatus according to claim 1, wherein the model generation unit generates the model so as to solve a regression problem of solving at what age of the person the medical image of the part of the person obtained by inference is, and incorporates the regression loss into the overall loss in the deep learning.

5. The information processing apparatus according to claim 1, wherein the medical image is a magnetic resonance image obtained by imaging the brain of the human or the subject.

6. A step in which an information processing apparatus generates a model by deep learning based on medical image information obtained by imaging a part of a human body and background information about the human including age information at the time of imaging of the part; A step in which the information processing apparatus infers a medical image of the part of the subject at the target age based on the generated model, a medical image of the part of the subject to be inferred, and background information about the subject including age information at the time of imaging of the part and target age information for inference; A step in which the information processing apparatus outputs the medical image of the part of the subject obtained by inference; An information processing method comprising the above steps.

Images