KR20230112602A - Pressure calculation method and apparatus for ventricular-abdominal shunt based on multiple medical images - Google Patents

Abstract

The present invention relates to a method and apparatus for calculating pressure for ventricular-peritoneal shunting. In the pressure calculation method for ventricular-peritoneal shunting according to an embodiment of the present invention, the step of collecting a plurality of medical image data; generating a dataset by checking pressure values labeled on each of the plurality of collected medical image data; Performing learning on an artificial intelligence model using the generated dataset; and when medical image data is input, calculating a pressure value corresponding to the input medical image data using the learned artificial intelligence model, wherein the pressure value determines the amount of cerebrospinal fluid drained from the first catheter inserted into the ventricle to the second catheter inserted into the abdominal cavity, and can be applied to a pressure regulating valve provided between the first catheter and the second catheter.

Description

Pressure calculation method and apparatus for ventricular-abdominal shunting based on multiple medical images

The present disclosure relates to a method and apparatus for calculating pressure for ventricle-abdominal shunting, and more particularly, to a method and apparatus for calculating pressure for ventricle-abdominal shunting, which can automatically calculate and provide pressure for ventricle-abdominal shunting based on a plurality of medical images.

The amount of cerebrospinal fluid (cerebrospinal fluid) surrounding the brain and spinal cord or in the ventricle is about 140 ml, about 25 ml in the ventricle, and the normal cerebrospinal fluid pressure is less than 150 mmH ₂ O, and 400 to 500 ml per day at 0.35 ml per minute is produced. Absorption of cerebrospinal fluid is achieved by a pressure difference of about 7mmH ₂ O between the subarachnoid pressure and the dural sinus through the arachnoid villi of the dural sinus (dural venous sinus). Hydrocephalus is caused by causes such as excessive production of cerebrospinal fluid, obstruction of cerebrospinal fluid, and impaired venous drainage.

In general, ventriculoperitoneal shunting is an operation performed to treat various causes of hydrocephalus. It is a surgery to insert a catheter of a shunt system into the abdominal cavity using a separate incision in the abdomen by perforating the skull, puncturing the ventricles, and tunneling the subcutaneous tissue therefrom. At this time, in order to control the amount of cerebrospinal fluid drained from the ventricle to the abdominal cavity, a pressure control valve device or a flow control valve device is provided between the ventricle and the abdominal cavity to control the amount of discharged fluid (discharge amount) of the cerebrospinal fluid.

When this cerebrospinal fluid is overdrained, symptoms such as headache, nausea, orthostatic hypotension, and intracranial hemorrhage may be caused, and conversely, when cerebrospinal fluid is underdrained, symptoms such as increased intracranial pressure may be induced.

Therefore, it is necessary to develop a technology for providing and adjusting a pressure value suitable for each patient.

Korean Patent Publication No. 10-2020-0116352 (published on October 12, 2020)

The present invention has been proposed to solve the above problems, and provides a pressure calculation method and apparatus for ventricle-peritoneal shunting, which learns a data set composed of input values corresponding to a plurality of medical images based on an artificial intelligence model, and automatically calculates and provides input values suitable for input medical images using the learning data.

In addition, the present invention provides a pressure calculation method and apparatus for ventricular-peritoneal shunting that minimizes the occurrence of symptoms or complications that may occur due to application of an incorrect pressure value by automatically calculating a highly reliable input value using normal operation data of other patients without the need for a user to visually check a patient's medical image and determine an input value based on experience.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

A pressure calculation method for ventricle-peritoneal shunting according to an embodiment of the present invention for solving the above problems includes collecting a plurality of medical image data; generating a dataset by checking pressure values labeled on each of the plurality of collected medical image data; Performing learning on an artificial intelligence model using the generated dataset; and calculating, when medical image data is input, a pressure value corresponding to the input medical image data using the learned artificial intelligence model, wherein the pressure value determines the amount of cerebrospinal fluid drained from the first catheter inserted into the ventricle to the second catheter inserted into the abdominal cavity, and can be applied to a pressure regulating valve provided between the first catheter and the second catheter.

On the other hand, a pressure calculating device for ventricular-peritoneal shunting according to an embodiment of the present invention includes a communication module for transmitting and receiving at least one piece of information or data; A learning module for learning an artificial intelligence model using a dataset; a storage module for storing various types of information or data and storing at least one process required to calculate a pressure value corresponding to the patient's medical image data; and a control module that performs an operation for calculating a pressure value corresponding to the patient's medical image data based on the at least one process, wherein the control module collects a plurality of medical image data, checks a pressure value labeled on each of the collected medical image data, creates a data set, learns an artificial intelligence model using the generated data set, and calculates a pressure value corresponding to the input medical image data using the learned artificial intelligence model when the medical image data is input, , The pressure value determines the drainage amount of the cerebrospinal fluid drained from the first catheter inserted into the ventricle to the second catheter inserted into the abdominal cavity, and is provided between the first catheter and the second catheter. Can be applied to a pressure control valve.

Other specific details of the invention are included in the detailed description and drawings.

According to the present invention, a dataset composed of input values corresponding to a plurality of medical images is learned based on an artificial intelligence model, and input values suitable for a patient's medical image are automatically calculated and provided using the learning data.

In addition, according to the present invention, the user automatically calculates a highly reliable input value using normal operation data of other patients without the need to visually check the patient's medical image and determine the input value depending on the experience value, thereby minimizing the occurrence of symptoms or complications that may occur due to the application of an incorrect pressure value.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram for a brief description of ventricle-peritoneal shunting.
FIG. 2 is a view for explaining an x-ray image as medical image data of a patient who has undergone ventricular-abdominal cavity shunting and its structure.
3 is a block diagram showing the configuration of a pressure calculation system for ventricular-peritoneal shunting according to an embodiment of the present invention.
4 is a diagram showing an example of a pressure gauge indicator for checking a pressure value in a pressure calculating device according to an embodiment of the present invention.
5 is a flow chart showing a pressure calculation method for ventricle-peritoneal shunting according to an embodiment of the present invention.
6 is a diagram illustrating an example in which notification information transmitted from a pressure calculating device according to an embodiment of the present invention is displayed through a display unit of a manager terminal.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in a variety of different forms, and only these embodiments are provided to complete the disclosure of the present invention and to fully inform those skilled in the art of the scope of the present invention to which the present invention belongs, and the present invention is only defined by the scope of the claims.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements. Like reference numerals throughout the specification refer to like elements, and “and/or” includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various components, these components are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first element mentioned below may also be the second element within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

The spatially relative terms "below", "beneath", "lower", "above", "upper", etc. may be used to easily describe the relationship between one component and other components as shown in the figures. Spatially relative terms should be understood as including different orientations of elements in use or operation in addition to the orientations shown in the drawings. For example, when flipping components shown in the drawings, components described as “below” or “beneath” other components may be placed “above” the other components. Thus, the exemplary term “below” may include directions of both below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

The term "unit" or "module" used in the specification means a hardware component such as software, FPGA or ASIC, and "unit" or "module" performs certain roles. However, "unit" or "module" is not meant to be limited to software or hardware. A "unit" or "module" may be configured to reside in an addressable storage medium and may be configured to reproduce one or more processors. Thus, as an example, “unit” or “module” includes components such as software components, object-oriented software components, class components and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. Functionality provided within components and “units” or “modules” may be combined into fewer components and “units” or “modules” or further separated into additional components and “units” or “modules”.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

In this specification, "medical image data" is a medical image captured by a medical imaging equipment, and includes all medical images that can be implemented as a 2D model or a 3D model of a subject's body. "Medical image data" may include X-ray, computed tomography (CT) images, magnetic resonance imaging (MRI), and positron emission tomography (PET) images.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1 is a diagram for a brief description of ventricular-peritoneal shunting, and FIG. 2 is a diagram for explaining an x-ray image as medical image data of a patient who has undergone ventricular-peritoneal shunting and its structure.

The human brain is a soft structure like the head, and the skull surrounding it is composed of hard bones. To protect the brain, a fluid called cerebrospinal fluid surrounds the brain and acts as a buffer against direct shock from the skull. Without the cushioning material surrounding the brain, our brain would hit the skull every time the body was shaken and would not survive. About 150cc to 200cc of cerebrospinal fluid is contained around our brain, and about 500ml of cerebrospinal fluid is produced, absorbed, and circulated per day. In normal conditions, the production and absorption of cerebrospinal fluid is balanced, but when hydrocephalus occurs, this balance is broken, and the unabsorbed cerebrospinal fluid increases intracranial pressure, resulting in various symptoms. The most effective surgical treatment for treating hydrocephalus is to insert a flexible tube called a shunt into the patient's cerebrospinal fluid passage to allow the cerebrospinal fluid to be absorbed from other parts of the body (mainly the abdominal cavity, thoracic cavity, or atrium).

Among them, in the ventricle-abdominal cavity shunting, a first catheter 10 is inserted into the patient's ventricle and a second catheter 20 is inserted into the patient's abdominal cavity so that cerebrospinal fluid is drained into the patient's abdominal cavity. At this time, a pressure control valve 30 is provided between the first catheter 10 and the second catheter 20 to adjust the amount of drainage of the cerebrospinal fluid.

3 is a block diagram showing the configuration of a pressure calculation system for ventricular-peritoneal shunting according to an embodiment of the present invention.

Referring to FIG. 3 , a pressure calculating system according to an embodiment of the present invention may include a pressure calculating device 100 and at least one manager terminal 200 .

Specifically, the pressure calculating device 100 may include a communication module 110, a learning module 130, a storage module 150, and a control module 170.

The communication module 110 transmits and receives at least one piece of information or data with at least one manager terminal 200 . In addition, the communication module 110 may perform communication with other servers or devices, and transmit and receive wireless signals in a communication network according to wireless Internet technologies.

Wireless Internet technologies include, for example, WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Wi-Fi (Wireless Fidelity) Direct, DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband), WiMAX (World Interoperability for Microwave Access), HSDPA (High Speed Downlink Packet Access), HSUPA (High Speed Uplink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution) -Advanced) and the like, and the pressure calculating device 100 transmits and receives data according to at least one wireless Internet technology within a range including Internet technologies not listed above.

As for short range communication, at least one of Bluetooth™, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, Near Field Communication (NFC), Wireless-Fidelity (Wi-Fi), Wi-Fi Direct, and Wireless Universal Serial Bus (USB) technologies may be used to support short-range communication. Wireless communication between the pressure calculating device 100 and at least one manager terminal 200 may be supported through such wireless area networks. At this time, the local area wireless communication network may be a local area wireless personal area network (Wireless Personal Area Networks).

The learning module 130 learns an artificial intelligence model using an input data set. At this time, the artificial intelligence model may be at least one, but is not limited thereto.

The storage module 150 stores various data (information), artificial intelligence models, etc. received by the pressure calculator 100 or generated or acquired (measured) by the pressure calculator 100, and stores at least one process required to calculate a pressure value corresponding to the patient's medical image data. Here, at least one artificial intelligence model may be stored.

The control module 170 controls all components to perform an operation for calculating a pressure value corresponding to the patient's medical image data based on at least one process stored in the storage module 150.

Specifically, the control module 170 collects a plurality of medical image data, checks the pressure value labeled on each of the collected plurality of medical image data, generates a data set, and then uses the generated data set to perform training on an artificial intelligence model.

Meanwhile, the plurality of medical image data is an X-ray image of a patient who has undergone ventricular-abdominal shunting and discharges cerebrospinal fluid, and may include medical image data determined to be in normal operation according to preset standards.

In addition, each of the plurality of medical image data may further label or include body shape information of the patient in addition to the pressure value. In this case, the control module 170 may further consider the body shape information when generating the data set. In this case, the body shape information may include information on at least one of age, height, and weight that affect the amount of cerebrospinal fluid drainage. In this way, when using a data set in which body shape information that affects the displacement of cerebrospinal fluid is further considered, a pressure value more suitable for the patient can be calculated.

Then, when the medical image data of a specific patient is input, the control module 170 calculates and provides a pressure value corresponding to the input medical image data using the pre-learned artificial intelligence model.

At this time, the control module 170 may manually receive the pressure value of the pressure regulating valve for each of the plurality of medical image data when generating the data set, but may also detect the pressure regulating valve for each of the plurality of collected medical image data, check the detected pressure values of the pressure regulating valve, and automatically label the checked pressure value in the corresponding medical image data.

On the other hand, after the calculated pressure value is applied, the pressure calculating device 100 determines whether there is an abnormality in the actual drainage amount based on a preset threshold range at each preset cycle when data on the actual drainage volume is received from a sensor attached to the pressure control valve 20 provided between the first catheter inserted into the patient's ventricle and the second catheter inserted into the patient's abdominal cavity. As a result of the determination, if it is determined that there is an abnormality, notification information is generated and transmitted to at least one manager terminal 200 registered in advance.

Meanwhile, at least one manager terminal 200 may be a terminal used by a manager, and displays notification information received from the pressure calculating device 100 on a display unit so that the manager checks the patient's condition. Here, the manager may be a medical staff, a caregiver, a guardian, and the like, but is not limited thereto.

On the other hand, the notification information may include at least one of patient information, message information informing of an abnormality, measurement value information for measuring an actual culture medium (a measurement value determined to have an abnormality), and an adjustment value to be adjusted to lower or increase the pressure. In addition, the notification information may further include measurement value information measured prior to the point in time at which the abnormality is detected so as to check the occurrence trend of the abnormality. In this case, the measurement value measured before that time may be all data or data within a preset range, and may be, for example, a measurement value measured right before the measurement value determined to be abnormal.

In addition, at least one administrator terminal 200 is a mobile terminal, mobile phone, smart phone, laptop computer, desktop computer, digital broadcast terminal, PDA (personal digital assistants), PMP (portable multimedia player), navigation, slate PC, tablet PC, ultrabook, wearable device (e.g., watch type terminal (smartwatch), glass type terminal) It may be a computer device or an electric communication device such as (smart glass), head mounted display (HMD), etc., but is not limited thereto.

4 is a diagram showing an example of a pressure gauge indicator for checking a pressure value in a pressure calculating device according to an embodiment of the present invention.

Referring to FIG. 4, as described above, a pressure control valve 30 is provided between the first catheter 10 inserted into the ventricle and the second catheter 20 inserted into the abdominal cavity of the patient. The pressure control valve 30 is provided with a pressure gauge indicator 31 for displaying a pressure value.

Meanwhile, although not shown in FIG. 4 , a sensor capable of measuring (collecting) the drainage amount of the cerebrospinal fluid drained based on the pressure value may be further provided. At this time, the sensor transmits the measured data, that is, data on the actual displacement amount, to the pressure calculating device 10 based on the Internet of Things (IoT).

5 is a flow chart showing a pressure calculation method for ventricle-peritoneal shunting according to an embodiment of the present invention.

Referring to FIG. 5 , when a plurality of medical image data is collected or input (S301), a pressure value labeled on each of the collected plurality of medical image data is checked to create a data set (S303).

Here, each of the plurality of collected medical image data may be further labeled or include information on the body shape of the patient in addition to the pressure value, and the body shape information may be further considered when generating a dataset in step S303. In this case, the body shape information may include information on at least one of age, height, and weight that affect the amount of cerebrospinal fluid drainage.

Meanwhile, although the pressure value for each of the plurality of medical image data may be previously labeled in step S303, the corresponding medical image data may be labeled by detecting the pressure control valve 30 in each of the plurality of medical image data and checking the pressure value based on the pressure gauge indicator 31 of the detected pressure control valve 30. At this time, labeling can also be done automatically through a pre-learned artificial intelligence model.

Next, the artificial intelligence model is learned using the generated dataset (S305), and then, medical image data of a specific patient is input to the learned artificial intelligence model (S307).

As a result, a pressure value corresponding to the input medical image data is calculated (S309).

6 is a diagram illustrating an example in which notification information transmitted from a pressure calculating device according to an embodiment of the present invention is displayed through a display unit of a manager terminal. However, for convenience of description, the description will be limited to the first manager terminal 210 .

Referring to FIG. 6 , when notification information is received from the pressure calculating device 100 , the first manager terminal 210 displays it through the display unit 211 .

At this time, the notification information may include basic information (name, gender, age, etc.), surgery date, etc. of the patient, as well as message information informing of an abnormality, measurement value information obtained by measuring the actual culture medium, and pressure. It may further include at least one of adjustment values to be adjusted to lower or increase.

Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination thereof. A software module may reside in random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable recording medium well known in the art.

In the above, the embodiments of the present invention have been described with reference to the accompanying drawings, but those skilled in the art to which the present invention pertains may be embodied in other specific forms without changing the technical spirit or essential features of the present invention. It will be appreciated. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

10: first catheter 20: second catheter
30: pressure control valve 31: pressure gauge indicator
100: pressure calculating device 110: communication module
130: learning module 150: storage module
170: control module 200: manager terminal
210: first manager terminal 220: nth manager terminal
211: display unit

Claims (15)

In the pressure calculation method for ventricular-peritoneal shunting performed by a computing device,
Collecting a plurality of medical image data;
generating a dataset by checking pressure values labeled on each of the plurality of collected medical image data; and
Including the step of performing learning on the artificial intelligence model using the generated dataset,
The step of creating the dataset is,
detecting a pressure control valve for each of the plurality of collected medical image data;
checking the pressure values of the detected pressure control valve; and
Labeling the confirmed pressure value to the corresponding medical image data,
The detected pressure value of the pressure control valve is
Confirmed based on the pressure gauge indicator of the detected pressure control valve,
Pressure calculation method for ventricular-abdominal shunting. According to claim 1,
The plurality of medical image data,
It is an X-ray image of a patient who has undergone ventricular-abdominal shunting and discharged cerebrospinal fluid,
Characterized in that it includes medical image data determined to be normal operation according to preset criteria,
Pressure calculation method for ventricular-abdominal shunting. According to claim 1,
Each of the collected plurality of medical image data includes body shape information about the patient,
Characterized in that the body shape information is further considered when generating the dataset,
Pressure calculation method for ventricular-abdominal shunting. According to claim 3,
The body shape information,
Characterized in that it includes information on at least one of age, height and weight that affects the drainage amount,
Pressure calculation method for ventricular-abdominal shunting. In the pressure calculation method for ventricular-peritoneal shunting performed by a computing device,
Collecting a plurality of medical image data;
generating a dataset by checking pressure values labeled on each of the plurality of collected medical image data; and
Including the step of performing learning on the artificial intelligence model using the generated dataset,
receiving data on an actual displacement amount from a sensor attached to the pressure control valve after the calculated pressure value is applied to the pressure control valve;
Determining whether or not the actual drainage amount is abnormal based on a preset threshold range at each preset period; and
Characterized in that, as a result of the determination, if it is determined that there is an abnormality, generating notification information and transmitting it to at least one manager terminal registered in advance.
Pressure calculation method for ventricular-abdominal shunting. According to claim 5,
The notification information is
Characterized in that it includes at least one of message information indicating an abnormality, measurement value information obtained by measuring an actual culture medium, and an adjustment value to be adjusted to lower or increase the pressure.
Pressure calculation method for ventricular-abdominal shunting. According to claim 6,
The data on the actual drainage amount,
Characterized in that it is received based on the Internet of Things (IoT),
Pressure calculation method for ventricular-abdominal shunting. In the pressure calculating device for ventricular-peritoneal shunting,
A communication module for transmitting and receiving at least one piece of information or data;
A learning module for learning an artificial intelligence model using a dataset;
a storage module for storing various types of information or data and storing at least one process required to calculate a pressure value corresponding to the patient's medical image data; and
A control module performing an operation for calculating a pressure value corresponding to the medical image data of the patient based on the at least one process,
The control module,
Collecting a plurality of medical image data, checking the pressure value labeled on each of the plurality of collected medical image data to create a dataset, and learning about an artificial intelligence model using the generated dataset,
The control module,
When generating the dataset, a pressure control valve is detected for each of the plurality of collected medical image data, and after checking the pressure values of the detected pressure control valve, the checked pressure value is labeled in the corresponding medical image data,
The detected pressure value of the pressure control valve is
Confirmed based on the pressure gauge indicator of the detected pressure control valve,
Pressure Calculation Device for Ventricular-Abdominoplasty. According to claim 8,
The plurality of medical image data,
It is an X-ray image of a patient who has undergone ventricular-abdominal shunting and discharged cerebrospinal fluid,
Characterized in that it includes medical image data determined to be normal operation according to preset criteria,
Pressure Calculation Device for Ventricular-Abdominoplasty. According to claim 8,
Each of the collected plurality of medical image data includes body shape information about the patient,
Characterized in that the control module further considers the body shape information when generating the dataset.
Pressure Calculation Device for Ventricular-Abdominoplasty. According to claim 10,
The body shape information,
Characterized in that it includes information on at least one of age, height and weight that affects the drainage amount,
Pressure Calculation Device for Ventricular-Abdominoplasty. In the pressure calculating device for ventricular-peritoneal shunting,
A communication module for transmitting and receiving at least one piece of information or data;
A learning module for learning an artificial intelligence model using a dataset;
a storage module for storing various types of information or data and storing at least one process required to calculate a pressure value corresponding to the patient's medical image data; and
A control module performing an operation for calculating a pressure value corresponding to the medical image data of the patient based on the at least one process,
The control module,
A plurality of medical image data is collected, a pressure value labeled on each of the plurality of collected medical image data is checked to create a dataset, and an artificial intelligence model is learned using the created dataset,
The control module,
After the calculated pressure value is applied to the pressure control valve, when data on the actual displacement amount is received from a sensor attached to the pressure control valve, whether or not the actual displacement amount is abnormal based on a preset threshold range for each preset period. As a result of the determination, if it is determined that there is an abnormality, notification information is generated and transmitted to at least one manager terminal registered in advance.
Pressure Calculation Device for Ventricular-Abdominoplasty. According to claim 12,
The notification information is
Characterized in that it includes at least one of message information indicating an abnormality, measurement value information obtained by measuring an actual culture medium, and an adjustment value to be adjusted to lower or increase the pressure.
Pressure Calculation Device for Ventricular-Abdominoplasty. According to claim 13,
The data on the actual drainage amount,
Characterized in that it is received based on the Internet of Things (IoT),
Pressure Calculation Device for Ventricular-Abdominoplasty. A computer program stored in a computer readable recording medium to be combined with a computer and execute the pressure calculation method for ventricular-peritoneal shunting according to any one of claims 1 to 7.