Information processing device, information processing method, information processing program, and trained model

Abstract

This invention provides an information processing device, an information processing method, an information processing program, and a trained model that can monitor the health status of a subject during imaging for diagnostic purposes. [Solution] The information processing device 10 includes a processor, which acquires color information of at least a portion of the body surface of a subject during imaging for diagnostic imaging, and monitors the subject's health status during imaging using an estimation model for estimating changes in color information when the subject's health status changes.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information processing method, an information processing program, and a learned model.

Background Art

[0002] Conventionally, various techniques for grasping a user's health condition are known.

[0003] For example, Patent Document 1 discloses recognizing a patient's expression based on continuously recorded face information of the patient, generating an index indicating a time-series change in the expression using the face information and the patient's medical data, and displaying the index and the expression together with the time-series change in the medical data. Also, for example, Patent Document 2 discloses recognizing a predetermined user from an analysis target image generated by imaging the front of a mirror and analyzing the physical state based on a determination criterion feature amount of the user and an analysis-time feature amount obtained from the analysis target image.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] In recent years, advances in medical equipment such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging) scanners have led to the use of higher-quality, high-resolution 3D images in diagnostic imaging. While contrast agents may be used in CT and MRI imaging for more detailed diagnoses, these agents can sometimes cause discomfort in patients. Furthermore, even without contrast agents, patients may experience sudden changes in their condition or become unwell due to anxiety. Therefore, there is a need for technologies that can monitor the health status of patients during imaging for diagnostic purposes.

[0006] This disclosure provides an information processing device, an information processing method, an information processing program, and a trained model that can monitor the health status of a subject during imaging for diagnostic purposes. [Means for solving the problem]

[0007] A first aspect of the present disclosure is an information processing device comprising a processor, the processor acquiring color information of at least a portion of the body surface of a subject during imaging for diagnostic imaging, and monitoring the subject's health status during imaging using an estimation model for estimating changes in color information when the subject's health status changes.

[0008] The estimation model may be a pre-trained model that takes reference color information, which is color information that serves as a standard for the subject's health status, as input and outputs abnormal color information, which is color information that indicates an abnormal state of the subject's health. The processor may acquire the color information of the subject's body surface before the start of imaging as reference color information, input the reference color information into the estimation model to generate abnormal color information, and estimate that the subject's health status is abnormal if the comparison result between the color information during imaging and the abnormal color information satisfies predetermined conditions.

[0009] The estimation model may output multiple abnormal color information for each of the different types of abnormal health conditions of the subject. The processor may estimate that the subject's health condition is abnormal if the comparison result between the color information being captured and at least one of the multiple abnormal color information satisfies predetermined conditions.

[0010] The estimation model may be trained using machine learning, with training data consisting of combinations of color information for normal health conditions and color information for abnormal health conditions.

[0011] The processor may issue a warning if it estimates that the subject's health condition is abnormal.

[0012] The processor may extract color information from a visible light image obtained by photographing the subject in visible light.

[0013] The processor may extract color information from a visible light image for a predetermined area of ​​the subject's body surface.

[0014] The color information may be color information from at least one of the subject's skin and mucous membranes.

[0015] The color information may also be color information from the subject's face.

[0016] The imaging may involve the administration of a contrast agent.

[0017] Multiple estimation models may be generated depending on the color information of the subject's normal health condition.

[0018] A second aspect of this disclosure is an information processing method, wherein a computer performs a process to monitor the health status of a subject during imaging by acquiring color information of at least a portion of the body surface of the subject during imaging, and using an estimation model for estimating changes in color information when the health status of the subject changes.

[0019] A third aspect of the present disclosure is an information processing program for causing a computer to execute a process of monitoring the health state of a subject during imaging for image diagnosis, by acquiring color information of at least a part of the body surface of the subject during imaging and using an estimation model for estimating a change in the color information when the health state of the subject changes.

[0020] A fourth aspect of the present disclosure is a learned model for causing a computer to function so as to input color information of at least a part of the body surface of a subject who undergoes imaging for image diagnosis as reference color information serving as a reference for the health state of the subject, and output abnormal color information which is color information when the health state of the subject becomes abnormal. The learned model is a learned model preliminarily learned by machine learning using, as learning data, a combination of color information when the health state is normal and color information when the health state is abnormal.

Advantages of the Invention

[0021] According to the above aspect, the information processing apparatus, information processing method, information processing program, and learned model of the present disclosure can monitor the health state of a subject during imaging for image diagnosis.

Brief Description of the Drawings

[0022] [Figure 1] It is a perspective view showing an overview of a CT apparatus. [Figure 2] It is a block diagram showing an example of the hardware configuration of an information processing apparatus. [Figure 3] It is a block diagram showing an example of the functional configuration of an information processing apparatus. [Figure 4] It is a diagram for explaining the processing of an information processing apparatus. [Figure 5] It is a diagram for explaining the processing of an information processing apparatus. [Figure 6] It is a diagram showing an example of a screen displayed on a display. [Figure 7] It is a flowchart showing an example of information processing.

Modes for Carrying Out the Invention

[0023] The following describes an example of an embodiment of the disclosed technology with reference to the drawings. In each drawing, identical or equivalent components and parts are given the same reference numerals, and redundant descriptions are omitted. Furthermore, the dimensional ratios in the drawings are exaggerated for illustrative purposes and may differ from actual ratios.

[0024] Referring to Figure 1, the configuration of the CT (Computed Tomography) device 1 will be described. As shown in Figure 1, the CT device 1 according to this embodiment comprises a gantry 2, a patient bed 3, and a console 4. The gantry 2, patient bed 3, and console 4 are configured to be connectable via a wired or wireless network (not shown). The console 4 may be located remotely from the gantry 2 and patient bed 3 (for example, in a separate room).

[0025] Gantry 2 has a tunnel-shaped structure with an opening 5 in its center. Inside gantry 2 are a radiation source that emits X-rays and a detection unit that detects X-rays and generates a radiation image (neither of which is shown). The radiation source and the detection unit can rotate along the annular shape of gantry 2 while maintaining a relative position facing each other. Also inside gantry 2 is a control unit that controls the operation of the CT device 1.

[0026] Furthermore, Gantry 2 has a camera 7 for capturing visible light images of the subject H during imaging for diagnostic purposes. Camera 7 is capable of capturing R (red), G (green), and B (blue) color images by detecting the reflected light from the subject H. Camera 7 has a lens and an image sensor such as a CCD (Charge Coupled Device), and acquires a visible light image, which is a moving image, by capturing the subject H on the bed 3 at a predetermined frame rate, and outputs it to the console 4.

[0027] Specifically, camera 7 may be positioned near the radiation source so as to capture the face of subject H as he is being transported into the opening 5 of gantry 2 (see Figure 1). Alternatively, camera 7 may be positioned on the ceiling or wall of the imaging room, or on the housing of gantry 2, so as to capture the face of subject H when his face is exposed through the opening 5. Furthermore, camera 7 may be positioned in multiple locations as described above.

[0028] A patient H is placed on the bed 3. The bed 3 comprises a bed section 3A on which the patient H lies, a base section 3B that supports the bed section 3A, and a drive unit 3C that moves the bed section 3A back and forth in the direction of arrow A. The bed section 3A is slidable relative to the base section 3B in the direction of arrow A by the drive unit 3C. When taking CT images, the bed section 3A slides, and the patient H lying on the bed section 3A is transported into the opening 5 of the gantry 2.

[0029] In the CT scanner 1, CT images are acquired by driving the gantry 2 and the patient table 3 based on input from an operator such as a technician on the console 4. The console 4 contains the information processing device of this disclosure. The information processing device according to this embodiment has a function for monitoring the health status of the subject H during imaging for diagnostic purposes. An example of the configuration of the information processing device 10 according to this embodiment will be described below.

[0030] First, an example of the hardware configuration of the information processing device 10 according to this embodiment will be described with reference to Figure 2. The information processing device 10 includes a CPU (Central Processing Unit) 21, a non-volatile storage unit 22, and a memory 23 as a temporary storage area. The information processing device 10 also includes a display 24, an input unit 25, and a network interface 26. The CPU 21, storage unit 22, memory 23, display 24, input unit 25, and network interface 26 are connected to each other via a bus 28, such as a system bus and a control bus, enabling the exchange of various types of information.

[0031] The storage unit 22 is implemented by a storage medium such as an HDD (Hard Disk Drive), SSD (Solid State Drive), and flash memory. The information processing program 27 of the information processing device 10 is stored in the storage unit 22. The CPU 21 reads the information processing program 27 from the storage unit 22, expands it into memory 23, and executes the expanded information processing program 27. The CPU 21 is an example of the processor of this disclosure.

[0032] The display 24 is, for example, a liquid crystal display and displays various information. The input unit 25 includes a pointing device such as a mouse and a keyboard, and is used to input various information to the device. The display 24 may be configured as a touch panel and used in conjunction with the input unit 25. The display 24 and the input unit 25 are also shown in Figure 1.

[0033] Network I / F26 is an interface for communicating with various devices, including the CT device 1, via the network. For this communication, wired communication standards such as Ethernet® or FDDI (Fiber Distributed Data Interface), or wireless communication standards such as 4G, 5G, or Wi-Fi® can be used. As the information processing device 10, for example, a server computer, personal computer, smartphone, tablet terminal, and wearable terminal can be appropriately applied.

[0034] Next, with reference to Figure 3, an example of the functional configuration of the information processing device 10 according to this embodiment will be described. As shown in Figure 3, the information processing device 10 includes an acquisition unit 30, an estimation unit 32, and a control unit 34. The CPU 21 executes the information processing program 27, thereby enabling the acquisition unit 30, estimation unit 32, and control unit 34 to function.

[0035] The acquisition unit 30 acquires color information of at least a portion of the body surface of the subject H during imaging for diagnostic imaging. Imaging for diagnostic imaging means, for example, CT imaging using the CT device 1, rather than visible light imaging using the camera 7, and will be referred to as "CT imaging" below. Imaging for diagnostic imaging may also involve the administration of a contrast agent. The body surface refers to, for example, the skin of the entire body, including the face, as well as mucous membranes such as the lips and eyes. Nails are also included in the skin. As color information, for example, a combination of R, G, and B components may be applied, or a combination of hue, lightness, and saturation may be applied, or both of these may be applied.

[0036] Specifically, the acquisition unit 30 may extract color information from a visible light image obtained by photographing the subject H with the camera 7 in visible light. Alternatively, the acquisition unit 30 may extract color information from a predetermined area of ​​the subject H's body surface from the visible light image. This is because even if there is a change in health, the color of the body surface does not change uniformly, and often only certain areas change partially or in a patchy manner.

[0037] Of the body surface, it is preferable to select a predetermined area where the color is likely to change according to the health condition of the subject H. For example, an area including the skin of subject H and at least one of the mucous membranes such as the lips and eyes is suitable. That is, the color information is preferably the color information of at least one of the skin and mucous membranes of subject H. Furthermore, within the whole body, the face is particularly suitable. That is, the color information is preferably the color information of the subject's face.

[0038] Furthermore, the acquisition unit 30 repeatedly acquires color information of at least a portion of the body surface of the subject H over time, from before the start of the CT scan to during the CT scan. Here, the color information that serves as a standard for the health status of the subject H is referred to as the reference color information. For example, the acquisition unit 30 may acquire the color information of the body surface of the subject H before the start of the CT scan as the reference color information. Alternatively, for example, the acquisition unit 30 may acquire the color information of the body surface of the subject H that is first acquired after the start of the CT scan (i.e., immediately after the start) as the reference color information.

[0039] The estimation unit 32 monitors the health status of subject H during CT scanning using an estimation model 40 for estimating changes in color information when the health status of subject H changes. Specifically, the estimation unit 32 generates color information (hereinafter referred to as abnormal color information) when the health status of subject H becomes abnormal by inputting reference color information into the estimation model 40.

[0040] Estimation model 40 is a pre-trained model that causes a computer to function by taking reference color information as input and outputting abnormal color information. For example, machine learning models such as convolutional neural networks and recurrent neural networks can be applied to estimation model 40.

[0041] The training data for the estimation model 40 consists of a combination of color information for normal health conditions and color information for abnormal health conditions. Since there are individual differences in body surface color, it is preferable to perform training using combinations of normal and abnormal color information for the body surfaces of various people. Through machine learning using such training data, the estimation model 40 is trained to output abnormal color information appropriate to the input reference color information, regardless of the body surface color of the subject H.

[0042] Furthermore, the estimation model 40 may output multiple abnormal color information for different types of abnormal states in the health condition of subject H. For example, in a CT scan, it is assumed that the subject may become unwell due to the effects of the contrast agent and become cyanotic due to oxygen deprivation. In this case, the estimation model 40 may output abnormal color information for the case where the subject becomes unwell due to the effects of the contrast agent and abnormal color information for the case where the subject becomes cyanotic. In addition, multiple estimation models 40 may be generated for each of these types of abnormal states.

[0043] Next, the estimation unit 32 compares the color information acquired during CT scanning with the abnormal color information each time color information is obtained during CT scanning. If the comparison result satisfies predetermined conditions, it estimates that the health status of subject H is abnormal. The predetermined conditions include, for example, when the difference between the color information acquired during CT scanning and the abnormal color information falls below a predetermined threshold. The difference between the color information can be calculated, for example, using the Euclidean distance.

[0044] Furthermore, if multiple abnormal color information is generated for each type of abnormal state, the estimation unit 32 may estimate that the health condition of subject H is abnormal if the comparison result between the color information during CT imaging and at least one of the multiple abnormal color information satisfies predetermined conditions. For example, if the abnormal color information for when the subject becomes unwell due to the effects of contrast agent and the abnormal color information for when the subject becomes cyanotic, the estimation unit 32 may estimate that the health condition of subject H is abnormal if only one of these satisfies predetermined conditions.

[0045] An example of the processing of the acquisition unit 30 and the estimation unit 32 will be described with reference to Figures 4 and 5. Figure 4 shows a visible light image 50 acquired before the start of CT scanning. Figure 5 shows a visible light image 50C acquired when the patient's health condition becomes abnormal during CT scanning. Here, it is assumed that the CT scan involves the administration of a contrast agent, and that it is possible to estimate whether the patient H is unwell due to the effects of the contrast agent from the degree of redness and paleness of the patient H's cheeks. Furthermore, it is assumed that it is possible to estimate whether the patient H is cyanotic due to oxygen deprivation from the color of the patient H's lips.

[0046] The acquisition unit 30 acquires a visible light image 50, which is acquired before the start of CT scanning as shown in Figure 4. The acquisition unit 30 also detects the facial region 52 from the visible light image 50. Then, the acquisition unit 30 detects the cheek region 54 and the lip region 56 from the facial region 52. Any known image recognition technique can be appropriately applied as a method for detecting each region.

[0047] Next, the acquisition unit 30 extracts color information, such as the R component, G component, and B component, from the detected cheek region 54 and lip region 56, respectively. This color information extracted from the visible light image 50 acquired before the start of CT scanning becomes the reference color information for the cheek region 54 and lip region 56, respectively.

[0048] The estimation unit 32 generates abnormal color information for the cheek region 54 and the lip region 56 by inputting reference color information for each region into the estimation model 40. As an example, Figures 4 and 5 show sample 60A and sample 60B of abnormal color information. Sample 60A shows abnormal color information for the cheek region 54, and an abnormal state is estimated when the color information changes towards flushing or paleness. Sample 60B shows abnormal color information for the lip region 56, and an abnormal state is estimated when the color information changes towards cyanosis.

[0049] When CT scanning begins, the acquisition unit 30 acquires visible light images over time. In addition, the acquisition unit 30 extracts color information for the cheek region 54 and the lip region 56, respectively, in the same way as for the visible light image 50. The acquisition unit 30 may extract color information each time a visible light image is acquired (i.e., in accordance with the frame rate of the camera 7), or it may extract color information at predetermined time intervals, such as every second or every 30 frames.

[0050] The estimation unit 32 compares the color information acquired during CT scanning with the abnormal color information each time color information is acquired during CT scanning to monitor whether the health status of the subject H is abnormal. Suppose that the visible light image 50C and its color information shown in Figure 5 are acquired during CT scanning. In this case, the estimation unit 32 estimates that the cheek region 54 is in an abnormal state because the difference between the current color information and the abnormal color information has fallen below a predetermined threshold.

[0051] Figure 6 shows an example of screen D1 displayed on the display 24 by the control unit 34. As shown in Figure 6, the control unit 34 may be controlled to display the visible light image 50 from which the reference color information has been acquired, and the current visible light image 50C. The control unit 34 may also be controlled to display samples 60A and 60B of abnormal color information for the user to refer to.

[0052] Furthermore, it is preferable for the control unit 34 to issue a warning if it is estimated that the health condition of subject H is abnormal. In the example in Figure 6, a warning message 90 indicating that the health condition of subject H is abnormal is displayed. The warning may be a simple message that only states that there is an abnormal condition, without including the cause or detailed condition, or it may be a specific message such as flushing, pallor, or cyanosis. Also, the method of warning is not limited to text, but may also be the use of sound and light, for example.

[0053] Furthermore, if the reference color information used as input to the estimation model 40 is expected to differ significantly for each subject H, it is preferable to prepare multiple estimation models 40 corresponding to the reference color information. In other words, it is preferable to generate multiple estimation models 40 according to the color information when subject H is in normal health. For example, if training is performed by mixing training data for different races such as Caucasoid, Negroid, and Mongoloid, the variability may be too large, hindering training progress or reducing the accuracy of estimation. In this case, these problems can be avoided by generating estimation models 40 with separate training data for each race.

[0054] Next, the operation of the information processing device 10 will be explained with reference to Figure 7. In the information processing device 10, the CPU 21 executes the information processing program 27, thereby executing the information processing shown in Figure 7. This processing is executed, for example, when the user issues an instruction to start execution.

[0055] In step S10, the acquisition unit 30 acquires a visible light image obtained by taking a visible light image of the subject H with the camera 7 before the start of CT scanning. In step S12, the acquisition unit 30 extracts color information from the visible light image acquired in step S10 and uses it as reference color information. In step S14, the estimation unit 32 inputs the reference color information extracted in step S12 into the estimation model 40 to generate abnormal color information in the event that the health condition of the subject H becomes abnormal.

[0056] In step S16, the user starts the CT scan. If a contrast agent is used, the contrast agent is administered to the subject H. In step S18, the acquisition unit 30 acquires a visible light image obtained by taking a visible light image of the subject H with the camera 7 during the CT scan. In step S20, the acquisition unit 30 extracts color information from the visible light image acquired in step S18.

[0057] In step S22, the estimation unit 32 compares the color information extracted in step S20 during CT scanning with the abnormal color information generated in step S14 and determines whether the comparison result satisfies predetermined conditions. If step S22 is affirmed (i.e., the comparison result satisfies predetermined conditions), it is estimated that the health condition of subject H is abnormal, and the process proceeds to step S24. In step S24, the control unit 34 warns that the health condition of subject H is abnormal and proceeds to step S26.

[0058] On the other hand, if step S22 is denied (i.e., the comparison result does not meet the predetermined conditions), the health status of subject H is presumed to be normal, and the process proceeds to step S26. In step S26, the control unit 34 determines whether or not the CT scan has been completed. If step S26 is denied (i.e., the CT scan has not been completed), steps S18 to S26 are repeated. On the other hand, if step S26 is affirmed (i.e., the CT scan has been completed), this information processing is terminated.

[0059] As described above, the information processing device 10 according to this embodiment includes a processor. The processor acquires color information of at least a portion of the body surface of the subject H during imaging for diagnostic imaging, and monitors the health status of the subject H during imaging using an estimation model 40 for estimating changes in color information when the health status of the subject H changes. Therefore, according to the information processing device 10 according to this embodiment, the health status of the subject H during imaging for diagnostic imaging can be monitored.

[0060] In the above embodiment, a method for extracting color information from a visible light image was described, but the invention is not limited to this. Color information of at least a portion of the body surface of subject H may be measured, for example, by a color sensor using a photoelectric sensor.

[0061] Furthermore, at least one of the functional units of the information processing device 10 in the above embodiment may be provided by other devices such as the control device provided by the gantry 2 and the control device provided by the drive unit 3C.

[0062] Furthermore, although the above embodiment was described using CT scanner 1, the technology of this disclosure can also be applied to various modalities other than CT scanner 1 that perform imaging for diagnostic imaging. Examples of such modalities include plain X-ray scanners, MRI (Magnetic Resonance Imaging) scanners, PET (Positron Emission Tomography) scanners, mammography scanners, ultrasound diagnostic scanners, endoscopes, and fundus cameras.

[0063] Furthermore, in the above embodiment, the hardware structure of the processing unit that performs various processes, such as the acquisition unit 30, the estimation unit 32, and the control unit 34, can be the various processors shown below. As mentioned above, these various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as programmable logic devices (PLDs), such as FPGAs (Field Programmable Gate Arrays), which have circuit configurations that can be changed after manufacturing, and dedicated electrical circuits, such as ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processes.

[0064] A single processing unit may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, multiple processing units may be composed of a single processor.

[0065] Examples of configuring multiple processing units with a single processor include, firstly, a configuration where one or more CPUs and software combine to form a single processor, which then functions as multiple processing units, as exemplified by client and server computers. Secondly, a configuration using a processor that realizes the functions of the entire system, including multiple processing units, on a single IC (Integrated Circuit) chip, as exemplified by System on Chip (SoC). Thus, various processing units are configured, in terms of hardware structure, using one or more of the above-mentioned processors.

[0066] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits, which are combinations of circuit elements such as semiconductor devices.

[0067] Furthermore, although the above embodiment describes an embodiment in which the information processing program 27 is pre-stored (installed) in the storage unit 22, the invention is not limited to this. The information processing program 27 may be provided in the form of a recording medium such as a CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), or USB (Universal Serial Bus) memory. Alternatively, the information processing program 27 may be provided in the form of a download from an external device via a network.

[0068] Furthermore, this disclosure is also applicable to programs and program products. Specifically, the information processing program 27 in the above embodiment may be provided as a program product. A program product includes any form of product for providing a program. For example, a program product includes a program provided via a network such as the Internet, and a computer-readable recording medium for non-temporarily storing a program.

[0069] The technology of this disclosure can also be appropriately combined with the above-described embodiments and modifications. The descriptions and illustrations shown above are detailed explanations of the parts relating to the technology of this disclosure and are merely examples of the technology of this disclosure. For example, the above descriptions of the configuration, function, operation, and effect are examples of the configuration, function, operation, and effect of the parts relating to the technology of this disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements added, or replaced from the descriptions and illustrations shown above, as long as they do not deviate from the spirit of the technology of this disclosure.

[0070] The following additional information is disclosed regarding the above embodiments. [Note 1] The processor comprises, Acquire color information of at least a portion of the body surface of the subject during imaging for diagnostic purposes. The subject's health status during the recording is monitored using an estimation model for estimating changes in color information when the subject's health status changes. Information processing device. [Note 2] The estimation model is a pre-trained model that takes reference color information, which is the color information that serves as the standard for the subject's health status, as input and outputs abnormal color information, which is the color information that occurs when the subject's health status becomes abnormal. The aforementioned processor, The color information of the subject's body surface before the start of the aforementioned imaging is acquired as the reference color information. By inputting the aforementioned reference color information into the estimation model, the aforementioned abnormal color information is generated. If the comparison result between the color information obtained during the aforementioned shooting and the abnormal color information satisfies predetermined conditions, it is presumed that the subject's health condition is abnormal. The information processing device described in Appendix 1. [Note 3] The estimation model outputs multiple abnormal color information for each case where the subject's health condition is of a different type of abnormal state. The aforementioned processor, If the comparison result between the color information obtained during the aforementioned shooting and at least one of the multiple abnormal color information items satisfies predetermined conditions, it is estimated that the subject's health condition is abnormal. The information processing device described in Appendix 2. [Note 4] The estimation model is trained by machine learning using combinations of color information when the health status is normal and color information when the health status is abnormal as training data. The information processing device described in Appendix 2 or Appendix 3. [Note 5] The processor will issue a warning if it estimates that the subject's health condition is abnormal. An information processing device as described in any one of the appendices 1 through 4. [Note 6] The processor extracts the color information from a visible light image obtained by photographing the subject in visible light. An information processing device as described in any one of the appendices 1 through 5. [Note 7] The processor extracts the color information from the visible light image from a predetermined area of ​​the subject's body surface. The information processing device described in Appendix 6. [Note 8] The aforementioned color information is color information from at least one of the subject's skin and mucous membranes. An information processing device as described in any one of the appendices 1 through 7. [Note 9] The aforementioned color information is the color information of the subject's face. An information processing device as described in any one of the appendices 1 through 8. [Note 10] The aforementioned imaging involves the administration of a contrast agent. An information processing device as described in any one of the appendices 1 through 9. [Note 11] The estimation model generates multiple models depending on the color information when the subject's health status is normal. An information processing device as described in any one of the appendices 1 through 10. [Note 12] Acquire color information of at least a portion of the body surface of the subject during imaging for diagnostic purposes. The subject's health status during the recording is monitored using an estimation model for estimating changes in color information when the subject's health status changes. An information processing method in which a computer performs the processing. [Note 13] Acquire color information of at least a portion of the body surface of the subject during imaging for diagnostic purposes. The subject's health status during the recording is monitored using an estimation model for estimating changes in color information when the subject's health status changes. An information processing program that instructs a computer to perform a task. [Note 14] A trained model for causing a computer to function such that it takes reference color information of at least a portion of the body surface of a subject being photographed for diagnostic imaging as input, and outputs abnormal color information which is the color information when the subject's health condition becomes abnormal, The color information for when the health status is normal and the color information for when the health status is abnormal are used as training data and are pre-trained by machine learning. A pre-trained model. [Explanation of Symbols]

[0071] 1 CT device 2 Gantry 3 berths 3A Sleeping compartment 3B base 3C drive unit 4 Console 5 Openings 7 Cameras 10 Information Processing Devices 21 CPU 22 Memory section 23 memory 24 displays 25 Input section 26 Network Interface 27 Information Processing Programs 28 buses 30 Acquisition Department 32 Estimation part 34 Control Unit 40 Estimated Models 50, 50C visible light image 52. Facial Region 54. Cheek area 56. The area of ​​the lips 60A, 60B Samples 90 Warning statement D1 screen H Subject

Claims

1. The processor comprises, Acquire color information of at least a portion of the body surface of the subject during imaging for diagnostic purposes. Using an estimation model for estimating changes in color information when the subject's health condition changes, the subject's health condition is monitored during the recording. Information processing device.

2. The estimation model is a pre-trained model that takes reference color information, which is the color information that serves as the standard for the subject's health status, as input and outputs abnormal color information, which is the color information that occurs when the subject's health status becomes abnormal. The aforementioned processor, The color information of the subject's body surface before the start of the aforementioned imaging is acquired as the reference color information. By inputting the aforementioned reference color information into the estimation model, the aforementioned abnormal color information is generated. If the comparison result between the color information obtained during the aforementioned shooting and the abnormal color information satisfies predetermined conditions, it is presumed that the subject's health condition is abnormal. The information processing apparatus according to claim 1.

3. The estimation model outputs multiple abnormal color information for each case where the subject's health condition is of a different type of abnormal state. The aforementioned processor, If the comparison result between the color information obtained during the aforementioned shooting and at least one of the multiple abnormal color information items satisfies predetermined conditions, it is presumed that the subject's health condition is abnormal. The information processing apparatus according to claim 2.

4. The estimation model is trained by machine learning using combinations of color information when the health status is normal and color information when the health status is abnormal as training data. The information processing apparatus according to claim 2.

5. The processor will issue a warning if it estimates that the subject's health condition is abnormal. The information processing apparatus according to claim 1.

6. The processor extracts the color information from a visible light image obtained by photographing the subject in visible light. The information processing apparatus according to claim 1.

7. The processor extracts the color information from the visible light image from a predetermined area of ​​the subject's body surface. The information processing apparatus according to claim 6.

8. The aforementioned color information is color information from at least one of the subject's skin and mucous membranes. The information processing apparatus according to claim 1.

9. The aforementioned color information is the color information of the subject's face. The information processing apparatus according to claim 1.

10. The aforementioned imaging involves the administration of a contrast agent. The information processing apparatus according to claim 1.

11. The estimation model generates multiple models depending on the color information when the subject's health status is normal. The information processing apparatus according to claim 1.

12. Acquire color information of at least a portion of the body surface of the subject during imaging for diagnostic purposes. Using an estimation model for estimating changes in color information when the subject's health condition changes, the subject's health condition is monitored during the recording. An information processing method in which a computer performs the processing.

13. Acquire color information of at least a portion of the body surface of the subject during imaging for diagnostic purposes. Using an estimation model for estimating changes in color information when the subject's health condition changes, the subject's health condition is monitored during the recording. An information processing program that instructs a computer to perform a task.

14. A trained model for causing a computer to function such that it takes reference color information of at least a portion of the body surface of a subject being photographed for diagnostic imaging as input, and outputs abnormal color information which is the color information when the subject's health condition becomes abnormal, The color information for when the health status is normal and the color information for when the health status is abnormal are used as training data and are pre-trained by machine learning. A pre-trained model.

Images