JP2024052838A - Image analysis device, image analysis method, and image analysis system - Google Patents

Abstract

[Problem] To improve the safety of peritoneal dialysis. [Solution] An in-home device 1 according to one embodiment of the present invention has an image acquisition unit that acquires an image of a patient undergoing peritoneal dialysis using a dialysis machine 2 or an assistant assisting the patient, a posture identification unit that identifies the posture of the patient or assistant based on the captured image, an analysis unit that analyzes the peritoneal dialysis procedure being performed by the patient or assistant based on the posture, and an output unit that outputs the analysis results by the analysis unit. A management server 4 outputs the analysis results output by the in-home device 1 to an information terminal 5. [Selected Figure] Figure 1

Description

The present invention relates to an image analysis device, an image analysis method, and an image analysis system for analyzing images taken of a patient undergoing peritoneal dialysis.

Hemodialysis (HD) and peritoneal dialysis (PD) are traditionally known methods of dialysis treatment. Hemodialysis requires patients to visit a hospital every time, whereas peritoneal dialysis has the advantage that it can be performed at home or at work.

When performing peritoneal dialysis, the patient or an assistant such as the patient's family member must connect the dialysis equipment to a tube implanted in the patient's abdomen and operate the dialysis equipment (e.g., opening and closing a clamp) in a specific procedure. Patent Document 1 discloses a device that outputs the operating procedure for the dialysis equipment by voice and image when the patient is performing peritoneal dialysis.

JP 2012-40445 A

If a patient or assistant performs peritoneal dialysis using an incorrect procedure, the patient may contract an infection. However, even if the device described in Patent Document 1 outputs the correct peritoneal dialysis procedure, the patient or assistant will not necessarily perform peritoneal dialysis according to that procedure. Because peritoneal dialysis is performed at the patient's home or workplace, doctors and nurses cannot confirm the peritoneal dialysis procedure that the patient or assistant is actually performing, or the patient's condition, such as whether they have an infection. Therefore, there is a demand for technology that improves the safety of peritoneal dialysis.

The present invention was made in consideration of these points, and aims to improve the safety of peritoneal dialysis.

The image analysis device of the first aspect of the present invention has an image acquisition unit that acquires an image of a patient undergoing peritoneal dialysis using a dialysis device or an assistant assisting the patient, a posture identification unit that identifies the posture of the patient or the assistant based on the captured image, an analysis unit that analyzes the procedure of the peritoneal dialysis being performed by the patient or the assistant based on the posture, and an output unit that outputs the analysis result by the analysis unit.

The image analysis device may further include a part identification unit that identifies at least one of the position and state of a part of the dialysis equipment based on the captured image, the analysis unit may determine whether the procedure complies with a predetermined standard based on the posture and at least one of the position and state of the part, and the output unit may output information indicating whether the procedure complies with the predetermined standard as the analysis result.

The part identification unit may identify at least one of the position and state of each of the multiple parts of the dialysis equipment, and the analysis unit may identify the order in which the patient or assistant operated the multiple parts based on the posture and at least one of the positions and states of the multiple parts, and may determine whether the procedure complies with the specified criteria by comparing the identified order with a specified standard order.

The analysis unit may calculate an operation time during which the patient or the assistant operates at least one of the multiple parts in the identified sequence, and determine whether the procedure is smooth or not based on the calculated operation time, and the output unit may output information indicating whether the procedure is smooth or not as the analysis result.

If the analysis unit determines that the procedure does not conform to the predetermined criteria, the output unit may transmit the captured image to an external device of the image analysis device.

The analysis unit may calculate the number of times the patient or assistant touches objects other than the dialysis equipment based on the posture, and evaluate the degree of hygiene of the procedure based on the calculated number of times, and the output unit may output information indicating the degree of hygiene as the analysis result.

The image analysis device may further include a mask detection unit that detects a mask worn by the patient or the assistant based on the captured image, and the output unit may output information indicating whether the mask detection unit has detected the mask.

The image acquisition unit may acquire the captured image including an outlet portion to which the dialysis machine is connected in the patient's body, the analysis unit may evaluate the degree of hygiene of the outlet portion based on the captured image, and the output unit may output information indicating the degree of hygiene as the analysis result.

The analysis unit may obtain information indicating the degree of hygiene of the exit area by inputting the captured image into a machine learning model that outputs information indicating the degree of hygiene of the exit area contained in the captured image by inputting the captured image.

When the degree of hygiene of the outlet portion satisfies a predetermined condition, the output unit may at least one of outputting a predetermined notification and outputting information to stop the dialysis machine.

The image analysis method of the second aspect of the present invention includes the steps of: acquiring an image of a patient undergoing peritoneal dialysis using a dialysis device or an assistant assisting the patient, executed by a processor; identifying the posture of the patient or assistant based on the acquired image; analyzing the peritoneal dialysis procedure being performed by the patient or assistant based on the posture; and outputting the analysis results from the analyzing step.

The image analysis system of the third aspect of the present invention includes an image acquisition device and an image analysis device capable of communicating with the image acquisition device. The image acquisition device has an image acquisition unit that acquires an image of a patient undergoing peritoneal dialysis using a dialysis device or an assistant assisting the patient, a posture identification unit that identifies the posture of the patient or the assistant based on the captured image, and a transmission unit that transmits information indicating the posture to the image analysis device. The image analysis device has a reception unit that receives information indicating the posture from the image acquisition device, an analysis unit that analyzes the procedure of the peritoneal dialysis being performed by the patient or the assistant based on the posture, and an output unit that outputs the analysis result by the analysis unit.

The output unit of the image analysis device may transmit a request for the captured image to the image acquisition device when a predetermined input is received from a user or when the analysis result satisfies a predetermined condition, and the transmission unit of the image acquisition device may transmit the captured image to the image analysis device on the condition that the request is received from the image analysis device.

The present invention has the effect of improving the safety of peritoneal dialysis.

1 is a schematic diagram of an image analysis system according to a first embodiment. 1 is a block diagram of an image analysis system according to a first embodiment. FIG. 1 is a schematic diagram of a dialysis device used in peritoneal dialysis. FIG. 4 is a diagram showing a captured image acquired by an image acquisition unit. FIG. 4 is a diagram showing a captured image acquired by an image acquisition unit. FIG. 4 is a diagram showing a captured image acquired by an image acquisition unit. FIG. 2 is a sequence diagram of an image analysis method executed by the image analysis system according to the first embodiment. FIG. 11 is a block diagram of an image analysis system according to a second embodiment. FIG. 11 is a sequence diagram of an image analysis method executed by an image analysis system according to a second embodiment.

First Embodiment
[Overview of Image Analysis System S]
1 is a schematic diagram of an image analysis system S according to the present embodiment. The image analysis system S includes an in-home device 1, a dialysis machine 2, an imaging device 3, a management server 4, and an information terminal 5. The image analysis system S may include other devices such as a server and a terminal.

The home device 1, dialysis equipment 2, and imaging device 3 are installed in a location such as a home or workplace where peritoneal dialysis is performed on a patient. The home device 1 is a computer that acquires images captured by the imaging device 3 from the imaging device 3 and analyzes the captured images. In other words, the home device 1 functions as an image analysis device. The home device 1 is also called an edge device.

The dialysis equipment 2 is an instrument for injecting dialysis fluid into the patient's body and discharging the dialysis fluid from the patient's body in response to operations by the patient or an assistant assisting the patient. The assistant assisting the patient is a person other than the patient (e.g., the patient's family member, a caregiver, etc.) who performs the tasks required to perform peritoneal dialysis. The dialysis equipment 2 may also include a control device that electrically controls the injection of dialysis fluid into the patient's body and the discharge of dialysis fluid from the patient's body.

More specifically, the dialysis equipment 2 may be an equipment that performs CAPD (Continuous Ambulatory Peritoneal Dialysis), in which the dialysis fluid in the patient's body is manually exchanged in response to the operation of the patient or an assistant, or an equipment that performs APD (Automated Peritoneal Dialysis), in which the dialysis fluid in the patient's body is automatically exchanged by an electrical control device. In either case of CAPD or APD, the patient or an assistant must connect the dialysis equipment 2 to a tube implanted in the patient's abdomen and operate the dialysis equipment 2 in a predetermined procedure (e.g., opening and closing a clamp or operating a switch) in order to perform peritoneal dialysis on the patient.

In this embodiment, the patient or assistant performing peritoneal dialysis is a task for performing peritoneal dialysis on the patient, and includes at least one of the following: connecting the dialysis equipment 2 to the tubes implanted in the patient's body, replacing the infusion bag and the drainage bag, operating the dialysis equipment 2 itself, managing the outlet where the tubes are implanted in the patient's body (observing, cleaning, disinfecting, applying chemicals, etc.), and other tasks related to peritoneal dialysis (keeping records, etc.).

The imaging device 3 has at least one imaging section (camera) that captures an image of a patient undergoing peritoneal dialysis using the dialysis equipment 2 or an assistant assisting the patient. The imaging device 3 outputs the captured image of the patient or assistant undergoing peritoneal dialysis to the home device 1. The range captured by the imaging device 3 may be the entire body of the patient or assistant, or may be a part of the body of the patient or assistant. The imaging device 3 may be integrated with the home device 1, and may transmit and receive signals between the imaging device 3 and the home device 1 via a wired or wireless connection.

The management server 4 is a computer that records the information output by the home device 1 and outputs information for the user to the information terminal 5. The user is, for example, a medical professional such as a doctor or a nurse. The management server 4 may be connected to multiple home devices 1 and multiple information terminals 5.

The information terminal 5 is a computer that accepts user operations and displays information output by the management server 4. The information terminal 5 may be integrated with the management server 4, and may transmit and receive signals between the information terminal 5 and the management server 4 via wired or wireless communication. The information terminal 5 has an operation unit such as a keyboard or mouse that can accept operations by the user, and a display unit such as a liquid crystal display that can display information.

An overview of the image analysis process performed by the image analysis system S according to this embodiment is given below. First, the home device 1 uses the imaging device 3 to capture an image of a patient undergoing peritoneal dialysis or an assistant assisting the patient using the dialysis equipment 2, and obtains the captured image.

The home device 1 identifies the posture of the patient or assistant performing peritoneal dialysis based on the acquired captured image. The home device 1 analyzes the peritoneal dialysis procedure being performed by the patient or assistant based on the identified posture. For example, as described below, the home device 1 determines whether the peritoneal dialysis procedure is correct (i.e., whether it conforms to a predetermined standard) by detecting whether an unsanitary act is being performed during peritoneal dialysis based on the posture of the patient or assistant. The home device 1 also identifies the order in which the patient or assistant operated parts such as clamps (fasteners) of the dialysis equipment 2, based on the posture of the patient or assistant, and determines whether the peritoneal dialysis procedure conforms to a predetermined standard based on whether the identified order is in accordance with the predetermined order.

The home device 1 transmits the analysis results using the captured images to the management server 4. Furthermore, if the home device 1 determines that the peritoneal dialysis procedure is incorrect, it transmits the captured images to the management server 4. The management server 4 displays the analysis results and captured images received from the home device 1 on the information terminal 5.

In this way, the image analysis system S according to this embodiment analyzes the peritoneal dialysis procedure actually performed by the patient or assistant based on captured images of the patient undergoing peritoneal dialysis or the assistant assisting the patient, and outputs the analysis results to a user such as a medical professional. As a result, the user such as a medical professional can provide appropriate guidance to the patient or assistant based on the peritoneal dialysis procedure actually performed by the patient or assistant, thereby improving the safety of peritoneal dialysis for the patient.

[Configuration of image analysis system S]
FIG. 2 is a block diagram of an image analysis system S according to this embodiment. In FIG. 2, the arrows indicate the main data flows, and there may be data flows not shown in FIG. 2. In FIG. 2, each block indicates a functional unit configuration, not a hardware (device) unit configuration. Therefore, the blocks shown in FIG. 2 may be implemented in a single device, or may be implemented separately in multiple devices. Data exchange between blocks may be performed via any means, such as a data bus, a network, or a portable storage medium.

The indoor device 1 has a control unit 11 and a memory unit 12. The control unit 11 has an image acquisition unit 111, a posture identification unit 112, a mask detection unit 113, a part identification unit 114, an analysis unit 115, and an output unit 116. The memory unit 12 has an image memory unit 121, an analysis criteria memory unit 122, and an analysis result memory unit 123.

The storage unit 12 is a storage medium including a ROM (Read Only Memory), a RAM (Random Access Memory), a hard disk drive, etc. The storage unit 12 stores in advance a program executed by the control unit 11. The storage unit 12 may be provided outside the home device 1, in which case data may be exchanged between the storage unit 12 and the control unit 11 via a network. The image storage unit 121 stores images captured by the imaging device 3. The analysis criteria storage unit 122 stores information used in analysis, such as reference values for analysis and machine learning models. The analysis result storage unit 123 stores analysis results using the captured images. The image storage unit 121, the analysis criteria storage unit 122, and the analysis result storage unit 123 may each be a storage area on the storage unit 12, or may be a database configured on the storage unit 12.

The control unit 11 is a processor such as a CPU (Central Processing Unit), and functions as an image acquisition unit 111, a posture identification unit 112, a mask detection unit 113, a part identification unit 114, an analysis unit 115, and an output unit 116 by executing a program stored in the memory unit 12. At least some of the functions of the control unit 11 may be performed by an electric circuit. In addition, at least some of the functions of the control unit 11 may be realized by the control unit 11 executing a program executed via a network.

The management server 4 has a control unit 41 and a memory unit 42. The control unit 41 has a receiving unit 411, an analysis unit 412, and an output unit 413. The memory unit 42 has an image memory unit 421, an analysis criteria memory unit 422, and an analysis result memory unit 423.

The storage unit 42 is a storage medium including a ROM, a RAM, a hard disk drive, and the like. The storage unit 42 stores in advance a program to be executed by the control unit 41. The storage unit 42 may be provided outside the management server 4, in which case data may be exchanged between the storage unit 42 and the control unit 41 via a network. The image storage unit 421 stores the captured images captured by the imaging device 3. The analysis criteria storage unit 422 stores information used in the analysis, such as reference values for analysis and machine learning models. The analysis result storage unit 423 stores the analysis results using the captured images. The image storage unit 421, the analysis criteria storage unit 422, and the analysis result storage unit 423 may each be a storage area on the storage unit 42, or may be a database configured on the storage unit 42.

The control unit 41 is a processor such as a CPU, and functions as a receiving unit 411, an analyzing unit 412, and an output unit 413 by executing a program stored in the memory unit 42. At least some of the functions of the control unit 41 may be performed by an electric circuit. In addition, at least some of the functions of the control unit 41 may be performed by a program executed via a network.

The image analysis system S according to this embodiment is not limited to the specific configuration shown in FIG. 2. Each of the in-home device 1 and the management server 4 is not limited to a single device, and may be configured by connecting two or more physically separate devices by wire or wirelessly.

[Configuration of dialysis machine 2]
3 is a schematic diagram of a dialysis device 2 used in peritoneal dialysis. The dialysis device 2 is an instrument that connects a tube implanted in the patient's abdomen, an infusion bag B1 that holds the dialysis fluid before being injected into the patient's body, and a drainage bag B2 that holds the dialysis fluid after being discharged from the patient's body, and controls the transport of the dialysis fluid between them.

The dialysis equipment 2 communicates the tube embedded in the patient's abdomen with the infusion bag B1 and the drainage bag B2 via the tube 21. The tube 21 has a patient side connector 22 for connecting to the tube embedded in the patient's abdomen, an infusion side connector 23 for connecting to the infusion bag B1, and a drainage side connector 24 for connecting to the drainage bag B2. The tube 21 is branched by a branching section 25 into three directions: the tube embedded in the patient's abdomen, the infusion bag B1, and the drainage bag B2.

A number of clamps 26 (fasteners) are provided along the tube 21, which can be switched between an open state and a closed state in response to a user's operation. When the clamps 26 are open, they allow the dialysis fluid to pass through the tube 21. When the clamps 26 are closed, they prevent the dialysis fluid from passing through the tube 21. Because the clamps 26 change shape between the open and closed states, the home device 1 can identify whether the clamps 26 are in the open state or the closed state based on their appearance in the captured image.

In the example of FIG. 3, the multiple clamps 26 include a patient side clamp 26a, a fluid injection side clamp 26b, and a fluid drainage side clamp 26c. The patient side clamp 26a is provided between the patient side connector 22 and the branching portion 25. The fluid injection side clamp 26b is provided between the fluid injection side connector 23 and the branching portion 25. The fluid drainage side clamp 26c is provided between the fluid drainage side connector 24 and the branching portion 25. The multiple clamps 26 are not limited to the example of FIG. 3, and may be any number or provided at any position.

Since the multiple clamps 26 have different colors or patterns, the indoor device 1 can identify each of the multiple clamps 26 based on their appearance in the captured image. In addition, the multiple clamps 26 may be made to have different shapes, allowing the indoor device 1 to identify each of the multiple clamps 26 based on their appearance in the captured image.

The dialysis equipment 2 is not limited to the configuration shown in FIG. 3, and may have other configurations. For example, the dialysis equipment 2 may include a control device that electrically controls the transport of the dialysis fluid. In this case, the control device is connected to a tube implanted in the patient's abdomen via a tube 21, and electrically controls the injection and discharge of the dialysis fluid. A number of clamps 26 are provided midway along the tube 21 that connects the control device to the tube implanted in the patient's abdomen, and the patient or an assistant operates the multiple clamps 26 before and after control by the control device begins.

[Explanation of image analysis method]
The image analysis method executed by the image analysis system S according to the present embodiment will be described in detail below. First, the home device 1 starts capturing images of the patient or assistant by the imaging device 3. At this time, the home device 1 starts capturing images when the patient or assistant performs a predetermined operation (e.g., pressing a start button provided on the home device 1 or the dialysis machine 2). As another method, the home device 1 may automatically start capturing images when a predetermined condition (e.g., the control device included in the dialysis machine 2 is turned on) is satisfied. In addition, the home device 1 ends capturing images when the patient or assistant performs a predetermined operation (e.g., pressing an end button provided on the home device 1 or the dialysis machine 2) or when a predetermined condition (e.g., the control device included in the dialysis machine 2 is turned off) is satisfied. The home device 1 may analyze captured images from the start of capturing images to the end of capturing images collectively, or may analyze captured images at predetermined time intervals from the start of capturing images.

In the home device 1, the image acquisition unit 111 acquires captured images of a patient or assistant undergoing peritoneal dialysis using the dialysis equipment 2 captured by the imaging device 3, and stores the images in the image storage unit 121. The captured images may be moving images or multiple still images captured at a predetermined time interval. The captured images may be one image capturing one imaging range, or a set of multiple images capturing multiple different imaging ranges simultaneously.

Figure 4 is a diagram showing the captured image IM acquired by the image acquisition unit 111. Figure 4 shows an area including the patient in the captured image IM. The posture identification unit 112 identifies the posture P of the patient based on the captured image acquired by the image acquisition unit 111. The posture P identified by the posture identification unit 112 may be the posture of the entire body of the patient, or the position of a specific part of the patient. For example, the posture identification unit 112 uses a posture estimation model to calculate the coordinates of multiple joint points of a human being included in the captured image IM, and identifies the set of coordinates of the calculated multiple joint points as the posture P of the patient. The posture identification unit 112 is not limited to the method shown here, and can use any known posture estimation method capable of estimating the posture P of a human being. The posture identification unit 112 outputs posture information indicating the identified posture P of the patient (for example, the coordinates of multiple joint points of the patient). The posture identification unit 112 may also identify the posture of the assistant based on the captured image using a similar method.

The mask detection unit 113 detects the mask M worn by the patient or assistant based on the captured image acquired by the image acquisition unit 111. For example, the mask detection unit 113 detects the mask M included in the captured image IM using an object recognition model. The mask detection unit 113 is not limited to the method shown here, and any known object detection method capable of detecting the mask M can be used. The mask detection unit 113 outputs mask detection information indicating whether or not the mask M worn by the patient or assistant has been detected (e.g., the coordinates of the mask M). In this way, the mask detection unit 113 can determine whether or not the patient or assistant is performing peritoneal dialysis in a hygienic state by outputting information indicating whether or not the patient or assistant is wearing the mask M.

Figure 5 is a diagram showing the captured image IM acquired by the image acquisition unit 111. Figure 5 shows an area in the captured image IM that includes the multiple clamps 26 (patient side clamp 26a, infusion side clamp 26b, and drainage side clamp 26c) of the dialysis equipment 2. The part identification unit 114 identifies the position and state of each of the multiple clamps 26, which are multiple parts of the dialysis equipment 2, based on the captured image acquired by the image acquisition unit 111. For example, the part identification unit 114 uses an object recognition model to identify the position of each of the multiple clamps 26 included in the captured image IM and to identify whether each of the multiple clamps 26 is in an open state or a closed state. As described above, the position and state of each of the multiple clamps 26 can be identified from the captured image IM based on the color and shape of the multiple clamps 26. The part identification unit 114 is not limited to the method shown here, and can use a known object detection method that can identify the state of the clamp 26. The part identification unit 114 outputs part information indicating the position and state of each of the multiple clamps 26 identified. The part identification unit 114 may output part information indicating the position and status of other parts of the dialysis machine 2, in addition to the clamp 26.

The identification of the orientation P by the orientation identification unit 112, the detection of the mask M by the mask detection unit 113, and the identification of the clamp 26 by the part identification unit 114 may be performed in parallel or in any order.

The analysis unit 115 analyzes the peritoneal dialysis procedure being performed by the patient or assistant based on the patient's posture P or the assistant's posture indicated by the posture information output by the posture identification unit 112. The analysis of the peritoneal dialysis procedure by the analysis unit 115 includes an analysis of whether the patient or assistant is performing unsanitary practices during peritoneal dialysis, and an analysis of whether the patient or assistant is operating the multiple clamps 26 in the correct order. Specifically, the analysis unit 115 first associates the timestamp of the captured image used by the posture identification unit 112 to identify the posture P with the timestamp of the captured image used by the part identification unit 114 to identify the state of the clamps 26, thereby aligning the time between the posture information output by the posture identification unit 112 and the part information output by the part identification unit 114.

Next, when the posture information includes postures P of multiple people, the analysis unit 115 selects one of the postures P as the posture P of the patient. For example, the analysis unit 115 selects the posture P of the patient based on past posture information. In this case, the analysis unit 115 selects, as the posture P of the patient, the posture P that is closest to the posture P of the patient identified at the previous timing in the time series, from among the postures P of multiple people identified at a certain timing. As an alternative method, the analysis unit 115 may select, as the posture P of the patient, the posture P that is closest to the clamp 26, from among the postures P of multiple people identified at a certain timing.

Next, the analysis unit 115 calculates the number of times that the patient or assistant touches objects other than the dialysis machine 2 as an unsanitary act performed by the patient or assistant during peritoneal dialysis, based on the patient's posture P or the assistant's posture indicated by the posture information output by the posture identification unit 112. For example, the analysis unit 115 calculates the number of times that the patient touches his or her own head. The head includes the patient's face and hair. In this case, the analysis unit 115 calculates the distance between the position of the hand and the position of the head in the patient's posture P, and when the distance is equal to or less than a predetermined value, adds 1 to the number of times that the patient touched his or her head, thereby calculating the number of times that the patient touched his or her head. The analysis unit 115 may calculate not only the number of times that the patient's head is touched, but also the number of times that the patient or assistant touches other objects that should not be touched during peritoneal dialysis. The analysis unit 115 then evaluates the degree of hygiene of the peritoneal dialysis procedure based on the calculated number of times.

For example, the analysis unit 115 calculates a lower score indicating the degree of hygiene the greater the calculated number of times, and calculates a higher score indicating the degree of hygiene the smaller the calculated number of times. The analysis unit 115 stores the number of times the patient or assistant touched objects other than the dialysis equipment 2 and information (score) indicating the degree of hygiene evaluated based on the number of times in the analysis result storage unit 123 as the analysis result. In this way, the analysis unit 115 calculates the number of times the patient or assistant touched objects other than the dialysis equipment 2, allowing users such as medical professionals to know that the patient or assistant is engaging in unhygienic behavior during peritoneal dialysis and to provide appropriate guidance.

Next, the analysis unit 115 determines whether the patient or the assistant has operated a part, based on the patient's posture P or the assistant's posture indicated by the posture information output by the posture identification unit 112, and the position and state of each of the multiple parts indicated by the part information output by the part identification unit 114. Below, the processing performed by the analysis unit 115 is described using the clamp 26 as a part of the dialysis machine 2.

The analysis unit 115 determines whether the patient or assistant has operated the clamp 26 based on the patient's posture P or the assistant's posture indicated by the posture information output by the posture identification unit 112 and at least one of the positions and states of each of the multiple clamps 26 indicated by the part information output by the part identification unit 114. At this time, the analysis unit 115 calculates the distance between the hand position in the patient's posture P or the assistant's posture and the position of each of the multiple clamps 26, and determines that the patient or assistant has touched the clamp 26 (i.e., operated the clamp 26) when the distance is equal to or less than a predetermined value.

When the analysis unit 115 determines that the patient or assistant has touched a clamp 26, it associates the identification information of the clamp 26 touched by the patient or assistant (i.e., which of the multiple clamps 26 the patient or assistant touched), the time when the patient or assistant touched the clamp 26, and the state of the clamp 26 at the time when the patient or assistant touched it. The state of the clamp 26 is information indicating, for example, whether the clamp 26 is in an open state or a closed state. The analysis unit 115 identifies the order in which the patient or assistant operated the multiple clamps 26 by repeating the determination of the operation of the clamp 26 by the patient in chronological order for the captured images IM from the start to the end of peritoneal dialysis.

The analysis unit 115 may also determine the order in which the patient or assistant operated the multiple clamps 26 based on the posture of the patient or assistant and the position of the clamps 26, without using the state of the clamps 26. In this case, the analysis unit 115 determines the order in which the patient or assistant operated the multiple clamps 26 by associating the identification information of the clamps 26 touched by the patient or assistant with the time when the patient or assistant touched the clamps 26. With this configuration, even if the analysis unit 115 does not determine a change in the state of the parts of the dialysis equipment 2, it can estimate the operation order of the parts based on the relationship between the posture of the patient or assistant and the position of the parts.

The analysis unit 115 compares the identified sequence with a predetermined reference sequence stored in advance in the analysis criterion storage unit 122. The reference sequence is information indicating in what order and how the multiple clamps 26 included in the dialysis equipment 2 are operated (for example, whether the clamps 26 are switched to an open or closed state, or whether the clamps 26 are touched). If the identified sequence does not match the reference sequence (i.e., if the predetermined criteria are not met), the analysis unit 115 determines that the peritoneal dialysis procedure performed by the patient or assistant is incorrect, and if not, determines that the peritoneal dialysis procedure performed by the patient or assistant is correct. In this way, the analysis unit 115 can accurately determine whether the peritoneal dialysis procedure is correct (i.e., whether it meets the predetermined criteria) by analyzing the peritoneal dialysis procedure based on the operation sequence of the multiple clamps 26.

The analysis unit 115 may identify the order in which the patient or assistant operates other parts of the dialysis equipment 2 (e.g., the infusion bag B1 and the drainage bag B2) in addition to the clamp 26, and may determine whether the peritoneal dialysis procedure complies with a predetermined standard based on the identified order. In this case, the analysis unit 115 identifies the order in which the patient or assistant operates the parts of the dialysis equipment 2 based on the posture of the patient or assistant and at least one of the position and state of the parts of the dialysis equipment 2.

The analysis unit 115 stores in the analysis result storage unit 123 as analysis results the order in which the patient or assistant operated the multiple parts (clamps 26) and a determination of whether the peritoneal dialysis procedure based on that order complies with predetermined standards.

Figures 6(a) and 6(b) are diagrams showing the captured image IM acquired by the image acquisition unit 111. Figures 6(a) and 6(b) show an area of the captured image IM including an outlet part in the patient's body to which the dialysis equipment 2 is connected. The outlet part is a part in the abdominal part of the patient's body in which a tube (catheter) connected to the dialysis equipment 2 is embedded in advance. When the tube of the outlet part is connected to the tube 21 of the dialysis equipment 2, the inside of the patient's body (intraperitoneal cavity) is connected to the tube 21 of the dialysis equipment 2, and the injection and discharge of dialysis fluid becomes possible.

If the area around the exit becomes unsanitary, infection by bacteria, etc. may occur. If peritoneal dialysis is continued with the exit infected, bacteria, etc. may enter the patient's body, causing a more serious infection such as peritonitis. Figure 6(a) shows a state where the exit is not infected, and Figure 6(b) shows a state where the exit is infected. As shown in Figures 6(a) and 6(b), there is a correlation between the appearance of the exit contained in the captured image IM and the degree of hygiene of the exit. Therefore, the analysis unit 115 evaluates the degree of hygiene of the exit based on the captured image IM.

The analysis criteria storage unit 122 prestores information indicating a machine learning model that, when an image is input, outputs information (score) indicating the degree of hygiene of the exit area contained in the image. The machine learning model is generated by learning an image and a score (point number) indicating the degree of hygiene of the exit area contained in the image in advance using a known machine learning method. The score of the degree of hygiene is a value determined according to, for example, the size of swelling, the size of the crust, the size of redness, the intensity of pain, and the type of exudate. In this embodiment, the score is determined so that the higher the score, the worse the hygiene state. The score is not limited to the definition shown here.

The analysis unit 115 obtains a score indicating the degree of hygiene of the exit area by inputting the captured image IM into a machine learning model that is pre-stored in the analysis criteria storage unit 122. The analysis unit 115 stores the obtained score indicating the degree of hygiene of the exit area in the analysis result storage unit 123 as the analysis result. It is very time-consuming for a user such as a medical professional to determine the degree of hygiene of the exit area from the captured image IM every time, but the analysis unit 115 can automatically evaluate the degree of hygiene of the exit area by using the machine learning model.

In this embodiment, the analysis unit 115 uses the captured image IM captured by the imaging device 3 installed in the home, but it may also use a captured image IM captured using an imaging unit of a communication terminal (such as a smartphone) owned by the patient or assistant. In this case, the patient or assistant captures an image of the outlet section using the imaging unit of the communication terminal at the start, middle, or end of peritoneal dialysis. The image acquisition unit 111 of the home device 1 acquires, by communication, the captured image IM including the outlet section captured by the communication terminal. The analysis unit 115 then acquires a score indicating the degree of hygiene of the outlet section using the captured image IM acquired from the communication terminal.

Furthermore, the analysis unit 115 may evaluate the degree of hygiene based on the environment around the patient and dialysis equipment 2 included in the captured image IM. For example, the analysis unit 115 uses a known object detection method to detect specific objects (food or garbage) that are factors that cause unsanitary conditions around the patient and dialysis equipment 2 in the captured image IM. The analysis unit 115 then calculates information (score) indicating the degree of hygiene based on the number and type of detected objects, in addition to the state of the outlet part included in the captured image IM. This allows the analysis unit 115 to evaluate the degree of hygiene taking into account the environment around the patient and dialysis equipment 2.

The analysis unit 115 may further evaluate the degree of hygiene based on at least one of the patient's biometric information, the patient's medication information, and drainage information of the dialysis fluid discharged from the patient's body. In this case, the analysis unit 115 acquires biometric information such as body temperature, blood pressure, and pulse rate from a sensor provided on the patient's body. The analysis unit 115 also acquires the patient's medication information (such as drug name) pre-stored in the memory unit 12. The analysis unit 115 also acquires drainage information such as the color and components of the dialysis fluid after it has been discharged from the patient's body from a sensor provided on the dialysis equipment 2.

The analysis unit 115 then calculates information (score) indicating the degree of hygiene based on the state of the exit port contained in the captured image IM as well as the acquired biometric information, medication information, and drainage information. Specifically, when the biometric information indicates that the patient's condition is different from the normal state (e.g., the patient has a fever), the analysis unit 115 adds a predetermined value to the score. This is because if the patient is not in a normal state, there is a risk that the patient has an infectious disease.

Furthermore, the analysis unit 115 adds a predetermined value to the score when the medication information indicates administration of a predetermined drug (e.g., a prescription drug for diabetes). This is because patients with diabetes, etc. are at high risk of infection. Furthermore, the analysis unit 115 adds a predetermined value to the score when the drainage information indicates that the drainage state is different from the normal state (e.g., the drainage is cloudy). This is because if the drainage state is not normal, there is a risk that the patient has an infection.

In this way, the analysis unit 115 can evaluate the degree of hygiene with higher accuracy by calculating a score indicating the degree of hygiene based on the captured image IM including the exit portion, as well as the biological information, medication information, and drainage information.

The output unit 116 outputs the posture information output by the posture identification unit 112, the mask detection information output by the mask detection unit 113, the part information output by the part identification unit 114, and the analysis result by the analysis unit 115 by transmitting them to the management server 4. The analysis result includes the number of times the patient or assistant touched objects other than the dialysis equipment 2, information indicating the degree of hygiene evaluated based on the number of times, the order in which the patient or assistant operated multiple parts (clamps 26), a determination of whether the peritoneal dialysis procedure based on the order complies with a predetermined standard, and a score indicating the degree of hygiene of the outlet. The analysis result may transmit only a part of this information to the management server 4. The output unit 116 may output the analysis result by other methods such as recording data in a storage device, printing on paper using a printer, outputting sound using a speaker, etc., without being limited to transmission to the management server 4.

Furthermore, the output unit 116 transmits the captured image IM to the management server 4 when a determination of whether or not the peritoneal dialysis procedure based on the order in which the patient or assistant operates multiple parts (clamps 26) meets a predetermined standard satisfies a predetermined condition (e.g., the peritoneal dialysis procedure is incorrect). As a result, the output unit 116 transmits the captured image outside the home device 1 only when it is determined that there is an abnormality in the peritoneal dialysis procedure, for example, and therefore the amount of data communication performed by the home device 1 can be reduced.

Furthermore, the output unit 116 may output a notification to at least one of the patient and the user when the score indicating the degree of hygiene of the outlet meets a predetermined condition stored in advance in the analysis criterion storage unit 122. The condition for outputting the notification is, for example, that the score is equal to or greater than a predetermined value. The notification includes information that the hygiene of the outlet is poor, and is transmitted to a communication terminal (such as a smartphone) held by the patient or assistant, or to an information terminal 5 used by the user, and is output by screen display or voice. In addition, when the score indicating the degree of hygiene of the outlet meets a predetermined condition and the dialysis device 2 includes a control device that electrically controls the transport of the dialysis fluid, the output unit 116 may output information (signal) to stop the dialysis device 2. The condition for stopping the dialysis device 2 is, for example, that the score is equal to or greater than a predetermined value. This allows the output unit 116 to provide feedback to the patient or user based on the score indicating the degree of hygiene of the outlet.

The condition for outputting the notification and the condition for stopping the dialysis equipment 2 may be different from each other. In this way, the output unit 116 can output a notification when the degree of hygiene satisfies, for example, a first condition, and forcibly stop the dialysis equipment 2 when the degree of hygiene satisfies a second condition different from the first condition.

In the management server 4, the receiving unit 411 receives the posture information, mask detection information, part information, and analysis results transmitted by the home device 1, and stores them in the analysis result storage unit 423. The receiving unit 411 also receives the captured image IM transmitted by the home device 1, and stores them in the image storage unit 421.

The analysis unit 412 acquires the posture information, mask detection information, part information, and analysis results transmitted by the home device 1. The analysis unit 412 then performs additional analysis on the acquired posture information, mask detection information, part information, and analysis results. For example, the analysis unit 412 calculates the operation time of each of the multiple steps included in the sequence in which the patient or assistant operated the multiple parts (clamps 26) of the dialysis equipment 2, which is included in the analysis result. Specifically, the analysis unit 412 calculates the operation time of one step as the time from when the patient or assistant starts operating at least one of the multiple clamps 26 (e.g., from when the patient or assistant touches the clamp 26) to when the operation of the clamp 26 is completed (e.g., from when the clamp 26 is released) in the sequence in which the patient or assistant operated the multiple clamps 26. The analysis unit 412 calculates the operation time of each of the multiple steps included in the sequence in which the patient or assistant operated the multiple clamps 26 by repeating the calculation of the operation time for the captured images IM from the start to the end of peritoneal dialysis in chronological order.

The analysis unit 412 determines whether the peritoneal dialysis procedure is smooth or not based on the calculated operation time of each of the multiple steps, and outputs information indicating whether the peritoneal dialysis procedure is smooth or not as an analysis result. For example, the analysis unit 412 determines that the peritoneal dialysis procedure is not smooth if the operation time of at least one of the calculated multiple steps is longer than a predetermined reference time, and determines that the peritoneal dialysis procedure is smooth if this is not the case. In this way, the analysis unit 412 calculates the operation time of each of the multiple steps, allowing a user such as a medical professional to understand which step the patient or assistant is confused about and to provide appropriate guidance. The analysis unit 412 is not limited to the analysis shown here and may perform other analyses.

In the image analysis system S, the home device 1 (edge device) is installed in each home and therefore has low computing power, while the management server 4 is assumed to have higher computing power than the home device 1. In such a configuration, the analysis unit 412 of the management server 4 can reduce the load on the home device 1 by performing additional analysis not performed by the home device 1. On the other hand, the management server 4 may omit the analysis by the analysis unit 412 and use the analysis results sent by the home device 1 as is.

The output unit 413 outputs the analysis results transmitted by the home device 1 and the analysis results output by the analysis unit 412 by transmitting them to the information terminal 5. The information terminal 5 outputs the analysis results transmitted by the management server 4 by screen display or audio. The output unit 413 may also transmit the mask detection information transmitted by the home device 1 to the information terminal 5. The output unit 413 may also transmit the captured image IM transmitted by the home device 1 to the information terminal 5.

[Image analysis method sequence]
7 is a sequence diagram of an image analysis method executed by the image analysis system S according to this embodiment. First, the home device 1 starts capturing an image of a patient or an assistant using the imaging device 3. The image acquisition unit 111 acquires an image captured by the imaging device 3 of a patient undergoing peritoneal dialysis using the dialysis machine 2 or an assistant assisting the patient (S11).

The posture identification unit 112 identifies the posture P of the patient or the posture of the assistant based on the captured image acquired by the image acquisition unit 111 (S12). The mask detection unit 113 detects the mask M worn by the patient or assistant based on the captured image acquired by the image acquisition unit 111 (S13). The part identification unit 114 identifies the position and state of each of the multiple parts (clamps 26) based on the captured image acquired by the image acquisition unit 111 (S14).

The analysis unit 115 calculates the number of times the patient or assistant touches objects other than the dialysis equipment 2 based on the patient's posture P or the assistant's posture indicated by the posture information output by the posture identification unit 112 (S15). The analysis unit 115 determines whether the patient or assistant has operated a part based on the patient's posture P or the assistant's posture indicated by the posture information output by the posture identification unit 112 and at least one of the position and state of each of the multiple parts indicated by the part information output by the part identification unit 114. The analysis unit 115 identifies the order in which the patient or assistant operated the multiple parts by repeating the determination of the operation of the parts by the patient in chronological order (S16).

The analysis unit 115 calculates information (score) indicating the degree of hygiene based on the calculated number of times. Furthermore, if the identified sequence does not match the standard sequence (i.e., does not meet the specified criteria), the analysis unit 115 determines that the peritoneal dialysis procedure performed by the patient or assistant is incorrect, and if not, determines that the peritoneal dialysis procedure performed by the patient or assistant is correct (S17).

The analysis unit 115 evaluates the degree of hygiene of the outlet based on the captured image IM (S18). The output unit 116 outputs the posture information output by the posture identification unit 112, the mask detection information output by the mask detection unit 113, the part information output by the part identification unit 114, and the analysis results by the analysis unit 115 by transmitting them to the management server 4 (S19). At this time, the output unit 116 may transmit the captured image IM to the management server 4 if the determination of whether or not the peritoneal dialysis procedure based on the order in which the patient or assistant operated multiple parts complies with a predetermined standard satisfies a predetermined condition (for example, the peritoneal dialysis procedure is incorrect).

In the management server 4, the receiving unit 411 receives the posture information, mask detection information, part information, and analysis results transmitted by the in-home device 1. The analysis unit 412 calculates the operation time for each of the multiple steps included in the sequence in which the patient or assistant operated the multiple parts included in the analysis result (S20). The analysis unit 412 outputs the calculated operation time for each of the multiple steps as the analysis result.

The output unit 413 outputs the analysis results sent by the in-home device 1 and the analysis results output by the analysis unit 412 by sending them to the information terminal 5 (S21). The information terminal 5 outputs the analysis results sent by the management server 4 by displaying them on a screen or by voice.

[Effects of the embodiment]
The image analysis system S according to the present embodiment identifies the posture of the patient or assistant from an image of the patient undergoing peritoneal dialysis or the assistant assisting the patient, analyzes the procedure of peritoneal dialysis actually performed by the patient or assistant based on the identified posture, and outputs the analysis result to a user such as a medical professional. Therefore, the user such as a medical professional can provide appropriate guidance to the patient based on the procedure of peritoneal dialysis actually performed by the patient or assistant, thereby improving the safety of peritoneal dialysis for the patient.

Second Embodiment
In the first embodiment, the in-home device 1 mainly performs the analysis, whereas in the present embodiment, the management server 4 mainly performs the analysis. The following describes configurations that are different from the first embodiment.

Figure 8 is a block diagram of an image analysis system S according to this embodiment. Unlike the configuration of Figure 2, the in-home device 1 according to this embodiment does not have an analysis unit 115. Instead, the analysis unit 412 of the management server 4 performs the analysis that was performed by the analysis unit 115 in the first embodiment. That is, in this embodiment, the in-home device 1 functions as an image acquisition device, and the management server 4 functions as an image analysis device.

Specifically, in the indoor device 1, the output unit 116 outputs the posture information output by the posture identification unit 112, the mask detection information output by the mask detection unit 113, and the part information output by the part identification unit 114 by transmitting them to the management server 4 as information to be used for analysis. Unlike the first embodiment, the output unit 116 does not transmit the analysis results. The output unit 116 may synchronize the posture information output by the posture identification unit 112 and the part information output by the part identification unit 114 before transmitting them.

In the management server 4, the receiving unit 411 receives the posture information, mask detection information, and part information transmitted by the home device 1 as information to be used for analysis. Similar to the analysis unit 115 in the first embodiment, the analysis unit 412 calculates the number of times the patient or assistant touches objects other than the dialysis equipment 2 based on the posture information transmitted by the home device 1, and evaluates the degree of hygiene of the peritoneal dialysis procedure based on the calculated number of times. The analysis unit 412 stores the number of times the patient or assistant touches objects other than the dialysis equipment 2 and information indicating the degree of hygiene evaluated based on the number of times in the analysis result storage unit 423 as analysis results.

Similarly to the analysis unit 115 of the first embodiment, the analysis unit 412 identifies the order in which the patient or assistant operated multiple parts (clamps 26) based on the posture information and part information transmitted by the in-home device 1, and determines whether the peritoneal dialysis procedure is correct (i.e., whether it complies with a predetermined standard) based on the identified order. The analysis unit 412 stores the order in which the patient or assistant operated multiple parts and the determination of whether the peritoneal dialysis procedure based on the order complies with a predetermined standard in the analysis result storage unit 423 as the analysis result.

Furthermore, as in the first embodiment, the analysis unit 412 calculates the operation time for each of the multiple steps included in the sequence in which the patient or assistant operates the multiple parts. The analysis unit 412 stores the calculated operation time for each of the multiple steps as the analysis result in the analysis result storage unit 423.

The output unit 413 outputs the analysis results by the analysis unit 412 by transmitting them to the information terminal 5. The information terminal 5 outputs the analysis results transmitted by the management server 4 by screen display or audio. The output unit 413 may also transmit the mask detection information transmitted by the home device 1 to the information terminal 5. In this embodiment, since the home device 1 does not perform analysis, the computational power of the home device 1 can be configured to be low, and the cost of introducing the home device 1 into the patient's home can be reduced.

The analysis unit 412 may evaluate the degree of hygiene of the exit area based on the captured image IM. In this case, the output unit 116 of the home device 1 transmits the captured image IM to the management server 4 in addition to the posture information, mask detection information, and part information. In the management server 4, the receiving unit 411 receives the captured image IM transmitted by the home device 1 and stores it in the image storage unit 421. The analysis unit 412 evaluates the degree of hygiene of the exit area based on the captured image IM, similar to the analysis unit 115 of the first embodiment. The analysis unit 412 stores the acquired score indicating the degree of hygiene of the exit area in the analysis result storage unit 423 as the analysis result. This allows the management server 4, rather than the home device 1, to evaluate the degree of hygiene of the exit area.

The information terminal 5 may receive an input for requesting the captured image IM from a user such as a medical professional who has referred to the analysis results. When the information terminal 5 receives an input for requesting the captured image IM from a user, the output unit 413 transmits a request for the captured image IM to the home device 1. In addition, the output unit 413 may automatically transmit a request for the captured image IM to the home device 1 when a determination of whether or not the peritoneal dialysis procedure based on the order in which the patient or assistant operates multiple parts meets a predetermined standard satisfies a predetermined condition (for example, the peritoneal dialysis procedure is incorrect).

In the home device 1, the output unit 116 transmits the captured image IM captured during the next peritoneal dialysis (i.e., the first peritoneal dialysis after the output unit 116 receives the request for the captured image IM) to the management server 4, on condition that the output unit 116 receives a request for the captured image IM from the management server 4. In the management server 4, the receiving unit 411 receives the captured image IM transmitted by the home device 1 and stores it in the image storage unit 421. The output unit 413 transmits the captured image IM transmitted by the home device 1 to the information terminal 5. With this configuration, even if the home device 1 has not recorded the captured image IM, it can transmit the next captured image IM to the management server 4 in response to a user request, allowing the user to check the captured image IM.

[Image analysis method sequence]
Fig. 9 is a sequence diagram of an image analysis method executed by the image analysis system S according to this embodiment. Steps S11 to S14 are the same as those in Fig. 7. The output unit 116 outputs the orientation information output by the orientation identification unit 112, the mask detection information output by the mask detection unit 113, and the part information output by the part identification unit 114 by transmitting them to the management server 4 as information to be used in analysis (S15').

In the management server 4, the receiving unit 411 receives the posture information, mask detection information, and part information transmitted by the home device 1 as information to be used for analysis. The analysis unit 412 calculates the number of times the patient or assistant touches objects other than the dialysis equipment 2 based on the posture information transmitted by the home device 1, and evaluates the degree of hygiene of the peritoneal dialysis procedure based on the calculated number of times (S16'). The analysis unit 412 identifies the order in which the patient or assistant operates multiple parts (clamps 26) of the dialysis equipment 2 based on the posture information and part information transmitted by the home device 1 (S17').

The analysis unit 412 calculates information (score) indicating the degree of hygiene based on the calculated number of times. Furthermore, if the identified sequence does not match the reference sequence, the analysis unit 412 determines that the peritoneal dialysis procedure performed by the patient or assistant is incorrect, and if not, determines that the peritoneal dialysis procedure performed by the patient or assistant is correct (S18').

The analysis unit 412 evaluates the degree of hygiene of the exit section based on the captured image IM sent by the indoor device 1 (S19'). The analysis unit 412 calculates the operation time of each of the multiple steps included in the sequence in which the patient or assistant operated the multiple parts (S20').

The output unit 413 outputs the analysis results by the analysis unit 412 by transmitting them to the information terminal 5 (S21'). The information terminal 5 outputs the analysis results transmitted by the management server 4 by displaying them on a screen or by voice.

[Effects of the embodiment]
According to the image analysis system S of this embodiment, as in the first embodiment, a user such as a medical professional can provide appropriate guidance to a patient based on the procedure of peritoneal dialysis actually performed by the patient or an assistant, thereby improving the safety of peritoneal dialysis for the patient. Furthermore, since the management server 4, not the home device 1, mainly performs the analysis, the cost of introducing the home device 1 can be reduced.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist of the invention. For example, all or part of the device can be configured by distributing or integrating functionally or physically in any unit. In addition, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effect of the new embodiment resulting from the combination also has the effect of the original embodiment.

The processors of the in-home device 1 and the management server 4 are responsible for each step (process) included in the image analysis method shown in Figures 7 and 9. That is, the processors of the in-home device 1 and the management server 4 read a program for executing the image analysis method shown in Figures 7 and 9 from a storage unit, and execute the program to control each unit of the image analysis system S, thereby executing the image analysis method shown in Figures 7 and 9. Some of the steps included in the image analysis method shown in Figures 7 and 9 may be omitted, the order of the steps may be changed, and multiple steps may be performed in parallel.

S Image analysis system 1 In-home device 11 Control unit 111 Image acquisition unit 112 Posture identification unit 113 Mask detection unit 114 Part identification unit 115 Analysis unit 116 Output unit 4 Management server 41 Control unit 411 Reception unit 412 Analysis unit 413 Output unit

Claims (10)

an image acquisition unit that acquires an image of a patient undergoing peritoneal dialysis using a dialysis device or an assistant assisting the patient;
a posture identification unit that identifies a posture of the patient or the assistant based on the captured image;
a part identification unit that identifies at least one of a position and a state of each of a plurality of parts included in the dialysis machine based on the captured image;
an analysis unit that identifies a sequence of a plurality of steps in which the patient or the assistant operates the plurality of parts based on the posture and at least one of the position and state of each of the plurality of parts, calculates an operation time in which the patient or the assistant operates each of the plurality of parts in each of the plurality of steps, and judges whether each of the plurality of steps has been performed smoothly based on the calculated operation time;
an output unit that outputs an analysis result including information indicating whether each of the plurality of steps has been performed smoothly;
An image analysis device comprising: the component identification unit identifies whether each of the plurality of components is in an open state that allows the dialysis fluid to pass or a closed state that does not allow the dialysis fluid to pass based on the captured image;
the analysis unit identifies a sequence of the steps based on the posture and whether each of the plurality of components is in the open state or the closed state.
The image analysis device according to claim 1 . The analysis unit calculates the number of times that the patient or the assistant touches an object other than the dialysis equipment based on the posture, and evaluates a degree of hygiene of the peritoneal dialysis procedure based on the calculated number of times;
The image analyzing device according to claim 1 , wherein the output unit outputs the analysis result including information indicating a degree of hygiene. A mask detection unit detects a mask worn by the patient or the assistant based on the captured image,
The image analyzing device according to claim 1 , wherein the output unit outputs the analysis result including information indicating whether or not the mask detection unit has detected the mask. the image acquisition unit acquires the captured image including an outlet portion of the patient's body to which the dialysis machine is connected;
The analysis unit evaluates a degree of hygiene of the exit portion based on the captured image,
The image analyzing device according to claim 1 , wherein the output unit outputs the analysis result including information indicating a degree of hygiene. The image analysis device according to claim 5, wherein the analysis unit obtains information indicating the degree of hygiene of the exit area by inputting the captured image into a machine learning model that outputs information indicating the degree of hygiene of the exit area contained in the captured image by inputting the captured image. The image analysis device according to claim 5 or 6, wherein the output unit performs at least one of outputting a predetermined notification and outputting information to stop the dialysis machine when the degree of hygiene of the outlet portion satisfies a predetermined condition. The processor executes
A step of identifying a posture of a patient or an assistant assisting the patient based on a captured image, the captured image being an image of the patient or an assistant performing peritoneal dialysis using a dialysis device;
Identifying at least one of a position and a state of each of a plurality of components of the dialysis device based on the captured image;
Identifying an order of a plurality of steps in which the patient or the assistant manipulated the plurality of parts based on the posture and at least one of the position and state of each of the plurality of parts;
calculating an operation time during which the patient or the assistant operates each of the plurality of parts in each of the plurality of steps;
determining whether each of the plurality of steps has been smoothly performed based on the calculated operation time;
outputting an analysis result including information indicating whether each of the plurality of steps was performed smoothly;
The image analysis method comprises: An image acquisition device and an image analysis device capable of communicating with the image acquisition device,
The image acquisition device includes:
an image acquisition unit that acquires an image of a patient undergoing peritoneal dialysis using a dialysis device or an assistant assisting the patient;
a posture identification unit that identifies a posture of the patient or the assistant based on the captured image;
a part identification unit that identifies at least one of a position and a state of each of a plurality of parts included in the dialysis machine based on the captured image;
a transmission unit that transmits information indicating the posture and information indicating at least one of a position and a state of each of the plurality of parts to the image analyzing device;
having
The image analysis device includes:
a receiving unit that receives information indicating the posture and information indicating at least one of a position and a state of each of the plurality of parts from the image acquisition device;
an analysis unit that identifies a sequence of a plurality of steps in which the patient or the assistant operates the plurality of parts based on the posture and at least one of the position and state of each of the plurality of parts, calculates an operation time in which the patient or the assistant operates each of the plurality of parts in each of the plurality of steps, and judges whether each of the plurality of steps has been performed smoothly based on the calculated operation time;
an output unit that outputs an analysis result including information indicating whether each of the plurality of steps has been performed smoothly;
An image analysis system comprising: the output unit of the image analysis device transmits a request for the captured image to the image acquisition device when a predetermined input is received from a user or when the analysis result satisfies a predetermined condition;
The image analysis system according to claim 9 , wherein the transmission unit of the image acquisition device transmits the captured image to the image analysis device on condition that the request is received from the image analysis device.

Images