Injection system for regulating injecting of material into lung sample on basis of artificial intelligence, and method using same

An AI-controlled injection system addresses the challenge of varying lung anatomy by using a camera, server, and pressure regulator to ensure precise and consistent formalin or OCT compound injection into lung specimens, preventing damage and facilitating accurate diagnosis.

WO2024237464A1PCT designated stage expired Publication Date: 2024-11-21THE CATHOLIC UNIV OF KOREA IND ACADEMIC COOP FOUND
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2024/003950
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-18
Filing Date
2024-03-28
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

The challenge in accurately injecting formalin or OCT compounds into lung specimens is due to the varying anatomical structure of lungs, leading to irregular pressure changes that can cause substance leakage or tissue damage, making precise diagnosis difficult.

Method used

An artificial intelligence-controlled injection system that includes a camera for imaging, a server for analyzing injection states, a pressure regulator, and a processor to adjust injection pressure based on learned models, ensuring consistent and appropriate material injection.

Benefits of technology

The system enables precise control of substance injection, preventing tissue damage and ensuring accurate diagnosis by maintaining optimal pressure and volume changes, even in varying lung anatomies.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2024003950_21112024_PF_FP_ABST
    Figure KR2024003950_21112024_PF_FP_ABST
Patent Text Reader

Abstract

The present disclosure relates to an injection system for regulating the injecting of a material into a lung sample on the basis of artificial intelligence, and a method using same, the present injection system comprising: an injection device for injecting a material into a first sample which is a lung sample corresponding to a specific patient; a camera for photographing material injection states of second samples which are a plurality of lung samples corresponding to various patients; and a server configured to, on the basis of artificial intelligence, analyze and model images of the material injection states of the second samples acquired through the camera. The injection device comprises: a filler tank containing the material which is injected into the first sample; a pressure gauge for measuring the pressure at which the material is injected into the first sample; a pressure regulator for regulating the pressure at which the material is injected into the first sample; and a processor. The processor may be configured to check the pressure measured through the pressure gauge and regulate the checked pressure through the pressure regulator on the basis of an adequate material injection state acquired from the server.
Need to check novelty before this filing date? Find Prior Art

Description

An injection system for controlling the injection of a substance into a lung specimen based on artificial intelligence and a method using the same

[0001] The present disclosure relates to an injection system and method utilizing the same for controlling the injection of substances into a lung specimen based on artificial intelligence. More specifically, the present disclosure relates to a process for automatically controlling the injection of substances for a patient's lung examination based on data learned through artificial intelligence.

[0002] The lungs are an organ of the human body. After resection for lung cancer or other therapeutic or diagnostic purposes, formalin is injected into the lungs with a syringe to fix them in the pathology department. OCT compound is also injected for frozen section examination. The reason for injecting these substances is that the lungs are originally filled with air, but all air must be removed during the surgery. Furthermore, maintaining the lungs' original shape is essential for an accurate clinical diagnosis. If the substances are not injected into the lungs, internal fixation will be delayed, leading to necrosis and making an accurate diagnosis difficult.

[0003] Advances in artificial intelligence technology are enabling the system to learn optimal conditions and automatically perform control operations to maintain a state that meets the desired outcome. Leveraging this technology in lung diagnosis will facilitate easier results.

[0004] Formalin or OCT compound, substances injected into the lungs, are difficult to inject at a consistent rate. Furthermore, lung anatomy varies significantly from patient to patient, frequently leading to sudden pressure increases during injection, resulting in leakage or reflux. If pressure increases, irregular expansion within the lungs can damage lung tissue, making accurate diagnosis difficult.

[0005] The problems to be solved by the present disclosure 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.

[0006] An injection system for controlling injection of a substance into a lung specimen based on artificial intelligence according to various embodiments of the present disclosure includes an injection device for injecting a substance into a first specimen, which is a lung specimen corresponding to a specific patient, a camera for photographing a state of injection of a substance into a second specimen, which is a plurality of lung specimens corresponding to various patients, and a server configured to analyze and model an image of the state of injection of a substance into the second specimen obtained through the camera based on artificial intelligence, wherein the injection device may include a filler tank containing a substance to be injected into the first specimen, a pressure measuring device for measuring a pressure at which a substance is injected into the first specimen, a pressure regulator for controlling a pressure at which a substance is injected into the first specimen, and a processor configured to check the pressure measured through the pressure measuring device and control the checked pressure through the pressure regulator based on an appropriate state of injection of a substance obtained from the server.

[0007] The injection device of the injection system for controlling injection of a substance into a lung specimen based on artificial intelligence according to various embodiments of the present disclosure includes a pump connected to the filler tank for injecting a substance into the first specimen and an expansion detector for detecting whether the first specimen is irregularly expanded, and the server learns by labeling an image of a state of injection of a substance into a normal injection state, and generates a model capable of determining an appropriate state of injection of a substance into the second specimen through the learning, and the processor can be set to confirm an appropriate state of injection of a substance into the first specimen based on the generated model.

[0008] The processor of the injection system for controlling injection of a substance into a lung specimen based on artificial intelligence according to various embodiments of the present disclosure may be configured to check the weight of the substance to be injected into the first specimen, check the tension of the first specimen, and control the pressure through the pressure regulator based on at least one of the weight and tension.

[0009] The processor of the injection system for controlling the injection of a substance into a lung specimen based on artificial intelligence according to various embodiments of the present disclosure may be configured to obtain an image of an appropriate volume change amount for each region of the second specimen from the server, and to detect the pressure, weight, tension, and irregular expansion based on the image through the expansion detector.

[0010] The processor of the injection system for controlling injection of a substance into a lung specimen based on artificial intelligence according to various embodiments of the present disclosure may be configured to determine whether the pressure exceeds a preset pressure, determine whether the weight of the injected substance relative to the weight of the first specimen exceeds a preset ratio, determine whether the tension of the first specimen exceeds a preset tension, and determine whether a difference between the volume change amount by region for the second specimen acquired based on an image of the appropriate volume change amount by region for the second specimen and the volume change amount by region for the first specimen exceeds a preset difference value.

[0011] An injection system for controlling injection of a substance into a lung specimen based on artificial intelligence according to various embodiments of the present disclosure may be characterized in that, when a bronchus exists in the first specimen, the injection substance is formalin and the formalin is injected into the first specimen through a needle-type injection or the bronchus, and when a bronchus does not exist in the first specimen, the injection substance is OCT compound and the OCT compound is injected into the first specimen through a needle-type injection.

[0012] The processor of the injection system for controlling injection of a substance into a lung specimen based on artificial intelligence according to various embodiments of the present disclosure may be configured to check clinical finding data for the second specimen stored in the server, check clinical data for the first specimen after completion of injection of the substance into the first specimen, and analyze clinical data for the first specimen based on clinical finding data for the second specimen to provide clinical finding data for the first specimen.

[0013] A method for controlling injection of a substance into a lung specimen based on artificial intelligence according to various embodiments of the present disclosure may include: a step of confirming a pressure measured by a pressure measuring device for measuring a pressure at which a substance is injected into a first lung specimen corresponding to a specific patient; a step of obtaining information on an appropriate state of the substance injection from a server set to model an image of a state of the substance injection into a second specimen, which is a plurality of lung specimens corresponding to various patients, obtained by a camera for photographing the state of the substance injection into the second specimen, based on artificial intelligence; and a step of controlling the confirmed pressure based on the information on the appropriate state of the substance injection, through a pressure regulator for controlling the pressure at which the substance is injected into the first specimen.

[0014] According to the aforementioned problem-solving method of the present disclosure, the pressure of injecting a substance into a lung specimen can be automatically detected and controlled. The AI-based injection system of the present disclosure can accurately secure the specimen on a slippery surface and check the tension to inject the substance to an appropriate weight. Furthermore, it can detect irregular expansion through an image of the lung specimen surface, enabling comprehensive control of the substance injection.

[0015] The injection system of the present disclosure can prevent damage to lung specimens by enabling multiple injections, such as injection at the lung surface, injection at the lung resection margin, and injection through the bronchus, due to the characteristics of lung resection specimens.

[0016] The effects of the present disclosure 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.

[0017] FIG. 1 is a schematic block diagram of an injection system for controlling material injection including an injection device according to various embodiments of the present disclosure.

[0018] FIG. 2 is a schematic block diagram of internal components of an injection device according to various embodiments of the present disclosure.

[0019] FIG. 3 is a general flow diagram of an injection system according to various embodiments of the present disclosure.

[0020] FIGS. 4 and 5 are exemplary diagrams of injection devices according to various embodiments of the present disclosure.

[0021] FIG. 6 is a schematic flowchart of an artificial intelligence-based material injection process according to various embodiments of the present disclosure.

[0022] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components.

[0023] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.

[0024] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0025] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0026] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0027] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0028] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0029] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0030] As used herein, the term "device according to the present disclosure" encompasses a variety of devices capable of performing computational processing and providing results to a user. For example, the device according to the present disclosure may include a computer, a server device, and a portable terminal, or may be any one of them.

[0031] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0032] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0033] The above portable terminal may include, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as a PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, a smart phone, and a wearable device such as a watch, a ring, a bracelet, an anklet, a necklace, glasses, contact lenses, or a head-mounted device (HMD).

[0034] FIG. 1 is a schematic block diagram of an injection system for controlling material injection including an injection device according to various embodiments of the present disclosure.

[0035] Referring to FIG. 1, the injection system (10) includes an injection device (100), a camera (200), and a server (300). Each node can exchange data with other nodes. Each node can be connected via a network. In the present disclosure, the substance injected into various patients and / or lung specimens of a specific patient may be formalin or an OCT compound.

[0036] An injection device (100) according to various embodiments of the present disclosure is a device capable of injecting a substance to determine the condition of a lung or lung sample of a patient (e.g., a human). The injection device (100) can transmit or receive clinical findings data, clinical data, etc. regarding the condition of a lung sample of a patient to or from another device connected via a wired and / or wireless connection. In addition, the injection device (100) can receive learned data that serves as a basis for determining clinical findings data, clinical data, etc. from another device. The injection device (100) can receive various data within the injection system (10) and provide the data via an application or web service.

[0037] A camera (200) according to various embodiments of the present disclosure captures the state of a substance injection into multiple lung specimens of various patients. The various patients may be patients awaiting lung surgery or suffering from lung-related diseases. The camera (200) can capture images of the entire lung or lung specimens in real time by injecting a specific substance into the entire lung or lung specimens for lung examination of various patients. The images may include videos. The camera (200) can capture images of the state of a substance injection into the entire lung and / or images of the state of a substance injection into a portion of the lung. The multiple lung specimens corresponding to various patients may be second specimens and may be utilized as basic data or learned data for observation of a specific patient for whom an actual examination is to be performed by the injection system (10) of the present disclosure.

[0038] According to various embodiments of the present disclosure, the server (300) may analyze, based on artificial intelligence, images of the substance injection status for second samples corresponding to various patients, acquired through the camera (200), in order to accurately determine the status of the first sample, which is a lung sample of a specific patient to be confirmed through the injection system (10). The server (300) may learn by labeling the images of the substance injection status for the second sample as a normal injection status. The server (300) may create a model capable of determining the appropriate substance injection status for the second sample through learning. That is, the server (300) may create a model for determining the appropriate substance injection status for lung samples of patients, and may repeatedly learn based on the images of the substance injection status for lung samples of patients, so as to determine whether the substance injected into the lung sample through the injection device (100) is appropriate.

[0039] FIG. 2 is a schematic block diagram of internal components of an injection device according to various embodiments of the present disclosure.

[0040] Referring to FIG. 2, the injection device (100) may include, but is not limited to, internal components such as a processor (110), a filler tank (120), a pressure gauge (130), a pressure regulator (140), a pump (150), and an expansion sensor (160).

[0041] The injection device (100) according to various embodiments of the present disclosure is a device that injects a substance into the lungs to determine the lung condition of a specific patient and provides observation results. The injection device (100) can analyze the data as numerical values ​​by parameterizing various indicators that can clinically determine the lung condition of a specific patient through images, tension, weight, pressure, etc. after the substance injection.

[0042] The processor (110) according to an embodiment of the present disclosure may be configured to perform the aforementioned operations using a memory storing data for an algorithm for controlling the operation of components within the injection device (100) or a program reproducing the algorithm, and data stored in the memory. In this case, the processor (110) and the memory may be implemented as separate chips. Alternatively, the processor (110) and the memory may be implemented as a single chip.

[0043] The processor (110) can control any one or a combination of the components discussed above to implement various embodiments according to the present disclosure described in FIGS. 3 and 6 below in the injection device (100).

[0044] According to an embodiment, the filler tank (120) can contain a substance to be injected into lung specimens of various patients or a specific patient. That is, the filler tank (120) corresponds to a tank that contains a substance to be injected into a first specimen or a second specimen. The pressure gauge (130) can measure the pressure at which the substance is injected into lung specimens of various patients or a specific patient. The pressure regulator (140) can control the pressure at which the substance is injected into lung specimens of various patients or a specific patient. The pressure regulator (140) can control the pressure for the first specimen based on data learned through artificial intelligence for the second specimen, and the factors by which the pressure regulator (140) controls the pressure can be an image, tension, weight, pressure, etc. The pump (150) can be connected to the filler tank (120) and configured to inject a substance into the first specimen or the second specimen. The expansion detector (160) can detect whether the first specimen or the second specimen is expanded irregularly.

[0045] A communication unit (not shown) according to an embodiment may include one or more components that enable communication with a server (e.g., server (300) of FIG. 1), and may include, for example, at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0046] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a Digital Visual Interface (DVI), RS-232 (recommended standard 232), power line communication, or plain old telephone service (POTS).

[0047] The wireless communication module may include a wireless communication module that supports various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a WiFi module and a Wireless Broadband module.

[0048] The short-range communication module is for short-range communication, and can support short-range communication using at least one of Bluetooth™, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0049] A memory (not shown) according to an embodiment can store data supporting various functions of the injection device (100), a program for the operation of the processor (110), can store input / output data (e.g., images, videos, etc.), and can store a plurality of application programs (or applications) run on the injection device (100), data for the operation of the injection device (100), and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

[0050] Such memory (not shown) may include at least one type of storage medium among flash memory type, hard disk type, SSD (Solid State Disk type), SDD (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk. In addition, the memory is separate from the injection device (100), but may be a database connected by wire or wirelessly.

[0051] An output unit (not shown) according to an embodiment is intended to generate output related to visual, auditory, or tactile sensations, and may include a display unit. The display unit may be formed as a touch screen by forming a mutual layer structure with a touch sensor or by forming an integral structure. Such a touch screen may function as a user input unit that provides an input interface between the mental health injection device (100) and the user, and at the same time, may provide an output interface between the injection device (100) and the user.

[0052] The display unit displays (outputs) information processed in the injection device (100). For example, the display unit may display execution screen information of an application program (e.g., an application) driven by the injection device (100), or UI (User Interface) or GUI (Graphical User Interface) information according to such execution screen information.

[0053] At least one component may be added or deleted to correspond to the performance of the components illustrated in FIG. 2. Furthermore, it will be readily apparent to those skilled in the art that the relative positions of the components may be altered to correspond to the performance or structure of the device.

[0054] Meanwhile, each component illustrated in FIG. 2 refers to software and / or hardware components such as a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).

[0055] FIG. 3 is a general flow diagram of an injection system according to various embodiments of the present disclosure.

[0056] Referring to FIG. 3, the injection device (e.g., the injection device (100) of FIG. 1) can check the pressure injected into the lung sample in step S310. At this time, the injection device checks the pressure injected into the lung sample through a pressure measuring device (e.g., the pressure measuring device (130) of FIG. 2).

[0057] In step S320, the injection device can determine whether the state of the substance injected into the lung specimen is appropriate based on data acquired based on the learning model. At this time, the injection device can control the pressure confirmed based on the appropriate state of the substance injection acquired from a server (e.g., server (300) of FIG. 1) through a pressure regulator (e.g., pressure regulator (140) of FIG. 2).

[0058] An injection device according to an embodiment can check the weight of a substance injected into a lung specimen (e.g., a first specimen). In addition, the injection device can check the tension of the first specimen. Accordingly, the injection device can be set to adjust the pressure through a pressure regulator based on at least one of the weight and the tension. The injection device can be set to obtain an image of an appropriate volume change amount for each region for a second specimen from a server, and to detect irregular expansion of the first specimen based on the pressure, weight, tension, and the image through an expansion detector (e.g., the expansion detector (160) of FIG. 2). That is, the injection device can determine in real time whether the substance injected into the first specimen is properly injected.

[0059] In step S330, the injection device can detect irregular expansion. The injection device can utilize at least one of pressure, weight, tension, and image as a factor (e.g., parameter) for detecting irregular expansion.

[0060] In step S340, the injection device may provide clinical findings data for the lung specimen. In an embodiment, the injection device may check clinical findings data for the second specimen stored on the server. The injection device may check the clinical data for the first specimen after the completion of the material injection for the first specimen, and analyze the clinical data for the first specimen based on the clinical findings data for the second specimen. Accordingly, the injection device may provide clinical findings data for the first specimen.

[0061] According to an embodiment, the injection device can confirm various clinical finding data that can clinically determine the condition of a lung specimen in a state where a substance has been injected. Accordingly, the injection device can provide clinical finding data for a first specimen that has actually been injected and observed based on various clinical finding data. In addition, the injection device can cumulatively store the clinical finding data provided for the first specimen and update the existing various clinical finding data. In this way, the updating of clinical finding data by the injection device can be done through the results after the injection of the substance for the first specimen corresponding to an actual lung specimen, but is not limited thereto. In addition, the injection device can directly receive clinical finding data from a doctor.

[0062] FIGS. 4 and 5 are exemplary diagrams of injection devices according to various embodiments of the present disclosure.

[0063] Figures 4 and 5 are exemplary diagrams of injecting a substance into a lung specimen (190) (e.g., first specimen) using the injection device (100) of Figure 1 and controlling the pressure at which the substance is injected. A difference between Figures 4 and 5 may be the presence or absence of a bronchial tube in the lung specimen (190).

[0064] Referring to FIG. 4, the lung specimen (190) may not have bronchi. In this case, the injection device (100) may inject a substance into the lung specimen (190) via a needle-shaped nozzle (410) connected to a syringe (180). If the lung specimen (190) does not have bronchi, the injected substance may be an OCT compound.

[0065] Referring to FIG. 5, the lung specimen (190) may have a bronchial tube. In this case, the injection device (100) may inject a substance into the bronchial tube of the lung specimen (190) through a bronchial clamping clip (411) connected to the first syringe (181). In addition, the injection device (100) may inject a substance into the lung specimen (190) through a needle-shaped nozzle (412) connected to the second syringe (182). If the lung specimen (190) has a bronchial tube, the injection substance may be formalin. In this case, the formalin may be injected through the needle-shaped nozzle or the bronchial tube. As another example, if the lung specimen (190) has a bronchial tube, the injection substance may be both formalin and OCT compound. In this case, the formalin may be injected through the bronchial tube, and the OCT compound may be injected through the needle-shaped nozzle.

[0066] The injection device (100) according to the embodiment can check whether the weight of the injected substance relative to the weight of the lung specimen (190) exceeds a preset ratio through the weight change measuring device (170). That is, the weight change measuring device (170) may measure the weight of the injected substance while the weight of the lung specimen (190) is actually input. At this time, the injection device (100) can compare the weight of the injected substance relative to the weight of the lung specimen (190) with a preset ratio.

[0067] FIG. 6 is a schematic flowchart of an artificial intelligence-based material injection process according to various embodiments of the present disclosure.

[0068] In step 610, the injection device (e.g., the injection device (100) of FIG. 1) can check the pressure at which the substance is injected into the first sample in real time using a pressure measuring device (e.g., the pressure measuring device (130) of FIG. 2). Accordingly, the injection device can check the pressure of the first sample (e.g., P lung ) is a preset pressure (e.g. P ref) can be checked to see if it exceeds the preset pressure. The preset pressure may be, for example, a pressure at which a substance is injected into the first sample and confirmed to be in an appropriate state. The preset pressure may be obtained and set through experimental result data or clinical result data.

[0069] In step 620, the injection device can check the weight of the substance injected into the lung sample in real time. Accordingly, the injection device can check the weight of the first sample (e.g., M) that is known in advance. ref ) can check the ratio of the weight of the injected substance (e.g., m1). The injection device can check whether the ratio exceeds a preset ratio (e.g., k). The preset ratio may be a ratio at which the substance is injected into the first sample and confirmed to be in an appropriate state, and may be obtained and set through an experiment.

[0070] At step 630, the injection device measures the tension of the first sample in real time (e.g., T lung ) can be confirmed. Accordingly, the injection device is configured to have a tension of the first sample set to a preset tension (e.g., T ref ) can be checked. Here, the preset tension may be a tension at which the first sample can be confirmed to be in an appropriate state, and may be obtained and set through the experiment.

[0071] In step 640, the injection device can check the volume change by region for the first sample in real time. Accordingly, the injection device can check whether the difference between the volume change by region for the second sample, which is acquired based on the volume change by region image for the second sample that is already known, and the volume change by region for the first sample exceeds a preset difference value. Here, the volume change by region image may refer to the same region of the first sample and the first sample. The region may correspond to a region that medically refers to by dividing the lung sample. The acquisition of the change by the injection device based on the volume change by region image of the lung sample may be through iterative learning. That is, the injection system (e.g., the injection system (10) of FIG. 1) can iteratively model and learn various data to determine the condition of the lung sample, and process the data acquired thereby to use it to diagnose the condition of the lung sample of the target patient through the injection device.

[0072] In step 650, the injection device can adjust the pressure for injecting the substance into the first sample based on the judgment in steps 610 to 640. That is, the injection device can automatically adjust the substance injection pressure when the standard values ​​(e.g., pressure, weight ratio, tension, image-based change difference, etc.) that serve as reference values ​​for determining whether the substance is being injected into the first sample in an appropriate state are exceeded. This is because the standard values ​​can be readjusted through the substance injection pressure, and corresponds to controlling the injection device so as to maintain an optimal substance injection state, i.e., an appropriate state, by applying results learned in advance through artificial intelligence.

[0073] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0074] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical data storage devices.

[0075] The disclosed embodiments have been described with reference to the attached drawings as described above. Those skilled in the art will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

Claims

1. In an injection system that controls the injection of a substance into a lung specimen based on artificial intelligence, An injection device for injecting a substance into a first sample, which is a lung sample corresponding to a specific patient; A camera that photographs the state of material injection into a second sample, which is a plurality of lung samples corresponding to various patients; and Including a server set to model and analyze an image of a material injection state of the second sample acquired through the camera based on artificial intelligence; The above injection device, A filler tank containing a substance to be injected for the first sample; A pressure measuring device for measuring the pressure at which a substance is injected into the first sample; A pressure regulator for controlling the pressure at which a substance is injected into the first sample; and An injection system comprising a processor configured to check the pressure measured through the pressure measuring device and to control the checked pressure through the pressure regulator based on the material injection appropriateness status obtained from the server.

2. In paragraph 1, The above injection device, A pump connected to the above filler tank for injecting a substance into the first sample; and Including an expansion detector that detects whether the first sample is irregularly expanded, The above server, Learning by labeling the image of the material injection state for the second sample as the normal injection state, Through the above learning, a model capable of determining the appropriate state of material injection for the second sample is created, The above processor, An injection system set to check the proper state of material injection for the first sample based on the above-mentioned generated model.

3. In paragraph 2, The above processor, Check the weight of the substance injected into the first sample above, Check the tension of the first sample above, An injection system configured to regulate pressure through said pressure regulator based on at least one of said weight and tension.

4. In paragraph 3, The above processor, Obtain an image of the appropriate volume change amount for each region for the second sample from the server, An injection system configured to detect irregular expansion based on the pressure, weight, tension, and image through the expansion sensor.

5. In paragraph 4, The above processor, Check if the above pressure exceeds the preset pressure, Check whether the weight of the injection material compared to the weight of the first sample exceeds the preset ratio, Check whether the tension of the first sample above exceeds the preset tension, An injection system configured to check whether the difference between the volume change amount by region for the second sample and the volume change amount by region for the first sample, obtained based on the image of the appropriate volume change amount by region for the second sample, exceeds a preset difference value.

6. In paragraph 5, In the case where a bronchus exists in the first sample, the injection material is formalin, and the formalin is characterized in that it is injected into the first sample through a needle injection or the bronchus. An injection system, characterized in that when a bronchus does not exist in the first sample, the injection material is an OCT compound and the OCT compound is injected into the first sample through a needle-type injection.

7. In paragraph 6, The above processor, Check the clinical findings data for the second sample stored in the above server, Confirm the clinical data for the first sample after the completion of the material injection for the first sample. An injection system configured to analyze clinical data for the first sample based on clinical finding data for the second sample and provide clinical finding data for the first sample.

8. A method for controlling the injection of a substance into a lung specimen based on artificial intelligence, A step of checking the pressure measured by a pressure measuring device that measures the pressure at which a substance is injected into a first sample, which is a lung sample corresponding to a specific patient; A step of obtaining information on the proper state of material injection from a server set to model and analyze images of the state of material injection for the second sample, which are multiple lung samples corresponding to various patients, obtained through a camera that photographs the state of material injection for the second sample, based on artificial intelligence; and A method for controlling material injection, comprising a step of controlling the pressure confirmed based on the material injection appropriateness status information through a pressure regulator that controls the pressure at which the material is injected into the first sample.

9. In paragraph 8, The step of obtaining information on the appropriate state of the above material injection is: A step of learning by labeling the image of the material injection state for the second sample as a normal injection state; and A step of generating a model capable of determining the appropriate state of material injection for the second sample through the above learning is included, The above material injection control method is, A method for controlling material injection, further comprising a step of confirming the proper state of material injection for the first sample based on the generated model.

10. In paragraph 9, The above adjusting steps are: A step of checking the weight of the substance injected into the first sample; A step of checking the tension of the first sample; and A method for controlling material injection, comprising the step of controlling pressure through the pressure regulator based on at least one of the weight and tension.

11. In paragraph 10, A step of obtaining an image of the appropriate volume change amount for each region for the second sample from the server; and A method for controlling material injection, comprising the step of detecting irregular expansion based on the pressure, weight, tension, and image through an expansion sensor.

12. In paragraph 11, The above adjusting steps are: A step of checking whether the above pressure exceeds the preset pressure; A step of checking whether the weight of the injection material compared to the weight of the first sample exceeds a preset ratio; A step of checking whether the tension of the first sample exceeds a preset tension; and A method for controlling material injection, comprising a step of checking whether the difference between the volume change amount by region for the second sample and the volume change amount by region for the first sample, obtained based on the image of the appropriate volume change amount by region for the second sample, exceeds a preset difference value.

13. In paragraph 12, In the case where a bronchus exists in the first sample, the injection material is formalin, and the formalin is characterized in that it is injected into the first sample through a needle injection or the bronchus. A method for controlling material injection, characterized in that when a bronchus does not exist in the first sample, the injection material is an OCT compound and the OCT compound is injected into the first sample through a needle-type injection.

14. In paragraph 13, A step of confirming clinical findings data for the second specimen stored in the server; A step of confirming clinical data for the first sample after completion of material injection for the first sample; and A method for controlling material injection, further comprising a step of analyzing clinical data for the first sample based on clinical finding data for the second sample to provide clinical finding data for the first sample.

15. A computer-readable storage medium having recorded thereon a computer program for performing the method of Article 8.

Citation Information

Patent Citations

  • Tissue engineering of lung

    KR101822662B1

  • Method and apparatus for monitoring patient

    KR1020180099434A

  • Submersible pump

    KR102448922B1

  • Screw type continuous low-temperature pyrolysis apparatus

    KR102677246B1

  • Apparatuses and methods for pulmonary drug delivery

    US20090139520A1