System and method for indicating gastroscopic examination site

Abstract

The method for indicating a gastroscopic examination site according to the present invention comprises: a step in which a model loading / condition setting unit loads a gastroscopic image analysis model and sets analysis conditions of the gastroscopic image analysis model; a step in which a control unit initializes an analysis screen and displays an image of a normal stomach; a step in which an image preprocessing unit preprocesses a gastroscopic image received through an image receiving unit to facilitate subsequent image analysis; a step in which an image analysis unit analyzes the preprocessed gastroscopic image using an AI-based image analysis model; a step in which the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site from the gastroscopic image on the basis of the analyzed result; and a step in which the control unit provides an analysis result analyzed by the image analysis unit.

Description

Gastroscopy Examination Site Indication System and Method

[0001] The present invention relates to a system and method for indicating the gastroscopy examination site, and more specifically, to a system and method for indicating the gastroscopy examination site that displays a situation such as a hernia in which a portion of the upper stomach enters the thoracic cavity during a gastroscopy examination by changing the stomach image to show a hernia that differs from a normal stomach on the examination screen.

[0002] The national research and development projects that supported this invention are as follows.

[0003] Project unique number not assigned

[0004] Assignment Number P0026379

[0005] Ministry of Trade, Industry and Energy

[0006] Project Management Agency Name: Korea Institute for Industrial Technology Promotion

[0007] Research Project Name (24-25) Scale-up Technology Commercialization Program R&D Support (Phase 2)

[0008] Research Project Title: Development of Advanced Gastrointestinal Endoscopy Image Analysis System and Diagnosis Reporting AI System

[0009] Project Executing Organization Name: Waysen (Lead) / Junseong Patent (Joint)

[0010] Research Period: 2024.01.01 ~ 2025.12.31

[0011] In modern medical examinations, the diagnosis of gastric neoplasms is typically made primarily by a physician using a gastroscopy. The physician then makes an initial determination regarding whether the condition is gastric cancer by considering the shape and size of the internal stomach within the endoscopic images. Among these cases, tissue samples are often collected via gastroscopy for lesions suspected of being cancerous, and a definitive diagnosis is made through a pathological biopsy. However, gastroscopy requires the patient to swallow the endoscope, causing significant discomfort as it travels through the esophagus to the stomach. Furthermore, there is a risk of complications such as esophageal or gastric perforation; therefore, it is necessary for the patient's benefit to diagnose gastric neoplasms while reducing the frequency of these procedures.

[0012] Therefore, rather than doctors performing a gastroscopy to detect gastric neoplasms, analyzing the results, and then conducting another gastroscopy for a biopsy, it is essential to detect gastric neoplasm lesions in the images during a single examination, assess their risk in real-time, immediately determine whether a biopsy is necessary for any lesions at risk of cancer, and perform a biopsy on the spot. Gradually reducing the number of gastroscopy procedures in this manner is the current trend. When assessing the risk of gastric neoplasm lesions in real-time, underestimating the risk leads to missing cancerous lesions and the serious consequence of failing to provide cancer treatment; conversely, overestimating the risk results in unnecessary biopsies, causing damage to the patient's tissues.

[0013] However, there is no established standard method for evaluating the risk of gastric lesions by viewing gastroscopic images in real time. Currently, such risk assessment relies almost entirely on the subjective judgment of the physician performing the gastroscopy. However, this method presents a problem in that diagnoses can vary depending on the physician's experience, and accurate diagnosis cannot be achieved in areas lacking sufficiently experienced doctors.

[0014] The present invention was created by comprehensively considering the above-mentioned matters, and aims to provide a gastroscopy examination site indication system and method that enables detailed indication of the gastric examination site by distinguishing between a normal stomach and a herniated stomach and indicating them on the screen, and allows for a more thorough gastroscopy examination by notifying the examiner of the herniation.

[0015] In addition, another objective of the present invention is to provide a gastroscopy examination site indication system and method that, by indicating major gastric examination sites, allows verification of areas examined to date, verification of locations missed after the examination is completed, and information regarding the presence of a hernia.

[0016] To achieve the above objective, a gastroscopy examination site indication system according to one embodiment of the present invention is,

[0017] A model loading / condition setting unit that loads a gastroscopy image analysis model and sets the analysis conditions of the analysis model;

[0018] An image receiver that receives gastroscopy image frames;

[0019] An image preprocessing unit that preprocesses a gastroscopy image received through the image receiving unit to facilitate subsequent image analysis;

[0020] An image analysis unit that analyzes a gastroscopic image preprocessed by the image preprocessing unit using an AI (artificial intelligence)-based image analysis model, and detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopic image based on the analyzed result; and

[0021] The invention is characterized by including a control unit that controls the status check and operation of the above-mentioned model loading / condition setting unit, image receiving unit, image preprocessing unit, and image analysis unit, and when the loading of the gastroscopy image analysis model and the setting of analysis conditions of the analysis model are completed by the above-mentioned model loading / condition setting unit, initializes the analysis screen and displays an image of a normal stomach, and provides the analysis results analyzed by the above-mentioned image analysis unit.

[0022] Here, the preprocessing of the gastroscopy image by the image preprocessing unit may include cropping the analysis area and adjusting the input size.

[0023] In addition, the image analysis model of the image analysis unit may be composed of a single image analysis model that detects the inspection site and the hernia site.

[0024] In addition, the image analysis model of the image analysis unit may be composed of an inspection area detection model that detects the inspection area and a hernia detection model that detects the hernia area.

[0025] In addition, the image analysis model of the image analysis unit may be composed of an inspection area detection model that detects the inspection area, a hernia detection model that detects the hernia area, and a lesion detection model that detects the lesion area.

[0026] At this time, the above lesion detection model may be equipped with a lesion attribute classification function that distinguishes whether the lesion is benign or malignant.

[0027] In addition, when the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopic image, the examination site includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenal bulb, and the hernia site may include a superior gastric hernia and a perisophageal hernia.

[0028] In addition, the control unit may transmit a command to change the instruction condition to the image analysis unit such that, when the image analysis unit detects and indicates at least one of the examination site, hernia site, and lesion site in the gastroscopic image, the gastroesophageal junction is indicated if it is a superior gastric hernia, and the gastric cardia and fundus are indicated if it is a peresophageal hernia.

[0029] In addition, the control unit may transmit a command to the image analysis unit to change the instruction condition, such that when the image analysis unit detects and indicates at least one of the examination area, hernia area, and lesion area in the gastroscopic image, the hernia is indicated differently in the normal stomach image, the hernia is not indicated in the normal stomach image, or the gastric hernia is indicated.

[0030] In addition, to achieve the above objective, a method for indicating the gastroscopy examination site according to one embodiment of the present invention is,

[0031] a) A step in which the model loading / condition setting unit loads the gastroscopy image analysis model and sets the analysis conditions of the analysis model;

[0032] b) A step in which the control unit initializes the analysis screen and displays the image above the normal;

[0033] c) A step in which the image preprocessing unit preprocesses the gastroscopy image received through the image receiving unit so that subsequent image analysis can be performed smoothly;

[0034] d) A step in which an image analysis unit analyzes the preprocessed gastroscopy image using an AI-based image analysis model;

[0035] e) a step in which an image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopy image based on the analyzed result; and

[0036] f) The control unit is characterized by including a step of providing an analysis result analyzed by the image analysis unit.

[0037] Here, the preprocessing of the gastroscopy image by the image preprocessing unit in step c) above may include cropping the analysis area and adjusting the input size.

[0038] In addition, in step d) above, the image analysis model may be composed of a single image analysis model that detects the inspection site and the hernia site.

[0039] In addition, in step d) above, the image analysis model may be composed of an inspection area detection model that detects an inspection area and a hernia detection model that detects a hernia area.

[0040] In addition, in step d) above, the image analysis model may be composed of an inspection area detection model that detects an inspection area, a hernia detection model that detects a hernia area, and a lesion detection model that detects a lesion area.

[0041] At this time, the above lesion detection model may be equipped with a lesion attribute classification function that distinguishes whether the lesion is benign or malignant.

[0042] In addition, in step e) above, when the image analysis unit detects and indicates at least one of the examination site, the hernia site, and the lesion site in the gastroscopic image, the examination site includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenal bulb, and the hernia site may include a superior gastric hernia and a perisophageal hernia.

[0043] In addition, in step e) above, when the image analysis unit detects and indicates at least one of the examination site, the hernia site, and the lesion site in the gastroscopic image, the control unit may transmit a command to change the indication condition to the image analysis unit such that if it is a superior gastric hernia, the gastroesophageal junction is indicated, and if it is a peresophageal hernia, the gastric cardia and the fundus are indicated.

[0044] In addition, in step e) above, when the image analysis unit detects and indicates at least one of the examination area, the hernia area, and the lesion area in the gastroscopy image, the control unit may transmit a command to change the indication condition to indicate the hernia differently in the normal stomach image, not indicate the hernia in the normal stomach image, or indicate the gastric hernia.

[0045] In addition, to achieve the above objective, a gastroscopy examination site indication system according to another embodiment of the present invention is,

[0046] A model loading / condition setting unit that loads a gastroscopy analysis model and a voice keyword recognition model, and sets the analysis conditions of the analysis model;

[0047] An image receiver that receives gastroscopy image frames;

[0048] An image preprocessing unit that preprocesses a gastroscopy image received through the image receiving unit to facilitate subsequent image analysis;

[0049] An image analysis unit that analyzes a gastroscopic image preprocessed by the image preprocessing unit using an AI (artificial intelligence)-based image analysis model, and detects and indicates at least one of an examination site, a hernia site, or a lesion site in the gastroscopic image based on the analyzed result;

[0050] A voice recognition unit that reads audio from a buffer storing audio while video analysis is being performed by the video analysis unit, analyzes it using an AI-based voice keyword recognition model, recognizes voice keywords based on the analyzed results, and transmits them to the video analysis unit; and

[0051] The invention is characterized by including a control unit that controls the status check and operation of the above-mentioned model loading / condition setting unit, image receiving unit, image preprocessing unit, image analysis unit, and voice recognition unit, and when the loading of the gastroscopy image analysis model and the setting of the analysis conditions of the analysis model are completed by the above-mentioned model loading / condition setting unit, initializes the analysis screen and displays an image of a normal stomach, and provides the analysis results analyzed by the above-mentioned image analysis unit, and provides the analysis results by connecting the analysis target detected by the above-mentioned image analysis model with a voice command (keyword) related to the analysis target uttered by the examiner.

[0052] Here, the preprocessing of the gastroscopy image by the image preprocessing unit may include cropping the analysis area and adjusting the input size.

[0053] In addition, the image analysis model of the image analysis unit may be composed of a single image analysis model that detects the inspection site and the hernia site.

[0054] In addition, the image analysis model of the image analysis unit may be composed of an inspection area detection model that detects the inspection area and a hernia detection model that detects the hernia area.

[0055] In addition, the image analysis model of the image analysis unit may be composed of an inspection area detection model that detects the inspection area, a hernia detection model that detects the hernia area, and a lesion detection model that detects the lesion area.

[0056] At this time, the above lesion detection model may be equipped with a lesion attribute classification function that distinguishes whether the lesion is benign or malignant.

[0057] In addition, when the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopic image, the examination site includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenal bulb, and the hernia site may include a superior gastric hernia and a perisophageal hernia.

[0058] In addition, the control unit may transmit a command to change the instruction condition to the image analysis unit such that, when the image analysis unit detects and indicates at least one of the examination site, hernia site, and lesion site in the gastroscopic image, the gastroesophageal junction is indicated if it is a superior gastric hernia, and the gastric cardia and fundus are indicated if it is a peresophageal hernia.

[0059] In addition, the control unit may transmit a command to the image analysis unit to change the instruction condition, such that when the image analysis unit detects and indicates at least one of the examination area, hernia area, and lesion area in the gastroscopic image, the hernia is indicated differently in the normal stomach image, the hernia is not indicated in the normal stomach image, or the gastric hernia is indicated.

[0060] In addition, to achieve the above objective, a method for indicating the gastroscopy examination site according to another embodiment of the present invention is,

[0061] p) A step in which the model loading / condition setting unit loads the gastroscopy analysis model and the voice keyword recognition model, and sets the analysis conditions of the analysis model;

[0062] q) A step in which the control unit initializes the analysis screen and displays an image of a normal stomach;

[0063] r) A step in which the image preprocessing unit preprocesses the gastroscopy image received through the image receiving unit so that subsequent image analysis can be performed smoothly;

[0064] s) A step in which an image analysis unit analyzes a gastroscopy image preprocessed by the image preprocessing unit using an AI-based image analysis model;

[0065] t) A step in which an image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopy image based on the analyzed result;

[0066] u) a step in which a voice recognition unit reads audio from a buffer storing audio while video analysis is being performed by the video analysis unit, analyzes it using an AI-based voice keyword recognition model, recognizes voice keywords based on the analyzed results, and transmits them to the video analysis unit; and

[0067] v) The control unit is characterized by including a step of providing an analysis result by connecting an analysis target detected by the image analysis model of the image analysis unit with a voice command (keyword) related to an analysis target spoken by the examiner.

[0068] Here, in step r), the preprocessing of the gastroscopic image by the image preprocessing unit may include cropping the analysis area and adjusting the input size.

[0069] In addition, in step s) above, the image analysis model may be composed of a single image analysis model that detects the inspection site and the hernia site.

[0070] In addition, in step s) above, the image analysis model may be composed of an inspection area detection model that detects the inspection area and a hernia detection model that detects the hernia area.

[0071] In addition, in step s) above, the image analysis model may be composed of an inspection area detection model that detects the inspection area, a hernia detection model that detects the hernia area, and a lesion detection model that detects the lesion area.

[0072] At this time, the above lesion detection model may be equipped with a lesion attribute classification function that distinguishes whether the lesion is benign or malignant.

[0073] In addition, in step t), when the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopic image, the examination site includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenal bulb, and the hernia site may include a superior gastric hernia and a perisophageal hernia.

[0074] In addition, in step t), when the image analysis unit detects and indicates at least one of the examination area, the hernia area, and the lesion area in the gastroscopic image, the control unit may transmit a command to change the indication condition to the image analysis unit such that if it is a superior gastric hernia, the gastroesophageal junction is indicated, and if it is a peresophageal hernia, the gastric cardia and the fundus are indicated.

[0075] In addition, in step t), when the image analysis unit detects and indicates at least one of the examination area, the hernia area, and the lesion area in the gastroscopic image, the control unit may transmit a command to change the indication condition to indicate the hernia differently in the normal stomach image, not indicate the hernia in the normal stomach image, or indicate the gastric hernia.

[0076] According to the present invention, by distinguishing between a normal stomach and a herniated stomach and displaying them on the screen, it is possible to indicate the detailed examination area of ​​the stomach and, by notifying the examiner of the herniation, it has the advantage of enabling a more thorough gastroscopic examination.

[0077] In addition, by indicating the major gastric examination sites, it has the advantage of allowing verification of areas examined so far, identification of missed locations after the examination is completed, and information regarding the presence of a hernia.

[0078] FIG. 1 is a schematic diagram showing the configuration of a gastroscopy examination site indication system according to one embodiment of the present invention.

[0079] FIGS. 2a to 2c are drawings showing examples of configurations of image analysis models.

[0080] FIG. 3 is a flowchart illustrating the execution process of a method for indicating a gastroscopy examination site according to one embodiment of the present invention.

[0081] Figure 4 is a flowchart showing the execution process of a first modified example of the method for indicating the gastroscopy examination site of Figure 3.

[0082] Figure 5 is a flowchart showing the execution process of a second modified example of the method for indicating the gastroscopy examination site of Figure 3.

[0083] Figure 6 is a flowchart showing the execution process of a third modified example of the method for indicating the gastroscopy examination site of Figure 3.

[0084] FIG. 7 is a schematic diagram showing the configuration of a gastroscopy examination site indication system according to another embodiment of the present invention.

[0085] FIG. 8 is a flowchart illustrating the execution process of a method for indicating a gastroscopy examination site according to another embodiment of the present invention.

[0086] FIG. 9 is a flowchart showing the execution process of a modified example of a method for indicating a gastroscopy examination site according to another embodiment of the present invention.

[0087] Figure 10 is a diagram showing the main parts of the above.

[0088] Figure 11 is a drawing showing the upper side.

[0089] Figure 12 is a drawing showing the inspection area of ​​the stomach (in the case of a normal stomach).

[0090] Figure 13 is a drawing showing the inspection site of the stomach (in the case of upper gastric hernia).

[0091] Figure 14 is a diagram showing the inspection site markings above (in the case of a peresophageal hernia).

[0092] Figure 15 is a drawing showing another example of the inspection site marking above (in the case of upper gastric hernia).

[0093] Figure 16 is a diagram showing another example of the above inspection site marking (in the case of perisophageal hernia).

[0094] Figure 17 is a diagram showing an example of providing analysis results (an example of a normal stomach examination).

[0095] Figure 18 is a diagram showing an example of providing analysis results (example of upper gastric hernia, lesion detection).

[0096] Figure 19 is a diagram showing an example of providing analysis results (an example of a peresophageal hernia examination).

[0097] Figure 20 is a diagram showing an example of providing analysis results (example of a result report).

[0098] Embodiments of the present invention will be described in detail below with reference to the attached drawings.

[0099] FIG. 1 is a schematic diagram showing the configuration of a gastroscopy examination site indication system according to one embodiment of the present invention.

[0100] Referring to FIG. 1, a gastroscopy examination site indication system (100) according to one embodiment of the present invention may be configured to include a model loading / condition setting unit (110), an image receiving unit (120), an image preprocessing unit (130), an image analysis unit (140), and a control unit (150).

[0101] The model loading / condition setting unit (110) loads the gastroscopy image analysis model and sets the analysis conditions of the analysis model. Here, the analysis conditions of the analysis model can be set, for example, to a predicted probability value of 0.85 or higher.

[0102] The image receiving unit (120) receives the gastroscopy image frame.

[0103] The image preprocessing unit (130) preprocesses the gastroscopic image received through the image receiving unit (120) so that subsequent image analysis can be performed smoothly. Here, the preprocessing of the gastroscopic image by the image preprocessing unit (130) as described above may include cutting the analysis area and adjusting the input size.

[0104] The image analysis unit (140) analyzes the gastroscopic image preprocessed by the image preprocessing unit (130) using an AI (artificial intelligence)-based image analysis model, and based on the analyzed results, detects and indicates at least one of the examination area, hernia area, and lesion area in the gastroscopic image. Here, the image analysis model of the image analysis unit (140) may be composed of a single image analysis model that detects the examination area and the hernia area, as shown in FIG. 2a. In FIG. 2a, (a) shows an example of an internal indication from the entry into the stomach, and (b) shows an example of an internal center indication of the stomach.

[0105] In addition, the image analysis model of the image analysis unit (140) may be composed of an inspection area detection model (Model A) that detects the inspection area and a hernia detection model (Model B) that detects the hernia area, as shown in FIG. 2b. In FIG. 2b, (a) shows an example of internal indication from the upper entry, and (b) shows an example of internal center indication of the upper.

[0106] In addition, the image analysis model of the image analysis unit (140) may be composed of an inspection area detection model (Model A) that detects the inspection area, a hernia detection model (Model B) that detects the hernia area, and a lesion detection model (Model C) that detects the lesion area, as illustrated in FIG. 2C. At this time, the lesion detection model (Model C) may be equipped with a lesion attribute classification function that distinguishes whether the lesion is benign or malignant.

[0107] In addition, when the image analysis unit (140) detects and indicates at least one of an examination area, a hernia area, and a lesion area in the gastroscopic image, the examination area includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenum, and the hernia area may include a gastric hernia and a periaesophageal hernia.

[0108] The control unit (150) controls the status check and operation of the model loading / condition setting unit (110), image receiving unit (120), image preprocessing unit (130), and image analysis unit (140). When the loading of the gastroscopy image analysis model and the setting of analysis conditions for the analysis model are completed by the model loading / condition setting unit (110), the control unit (150) initializes the analysis screen, displays an image of a normal stomach, and provides the analysis results analyzed by the image analysis unit (140). Here, the control unit (150) can transmit a command to change the instruction conditions to the image analysis unit (140) such that when the image analysis unit (140) detects and indicates at least one of the examination area, hernia area, and lesion area in the gastroscopy image, if it is a superior gastric hernia, it indicates the gastroesophageal junction, and if it is a peresophageal hernia, it indicates the gastric cardia and fundus. Additionally, the control unit (150) can transmit a command to the image analysis unit (140) to change the instruction condition, such as indicating a hernia differently in a normal stomach image, not indicating a hernia in a normal stomach image, or indicating a gastric hernia (e.g., an alarm or area indication), when the image analysis unit (140) detects and indicates at least one of an examination area, a hernia area, and a lesion area in the gastroscopic image.

[0109] In FIG. 1, reference number 160 represents a database (DB), and such a database (DB) (160) stores and manages various software programs for system operation, data or information required when the model loading / condition setting unit (110), image receiving unit (120), image preprocessing unit (130), and image analysis unit (140) perform functions related to model loading and condition setting, image preprocessing, and image analysis, or process tasks, as well as gastroscopy image analysis result data based on an image analysis model.

[0110] Here, the model loading / condition setting unit (110), image receiving unit (120), image preprocessing unit (130), image analysis unit (140), control unit (150), and database (DB) (160) as described above may also be integrated as a whole to form a single computer system.

[0111] Then, below, we will describe a method for indicating a gastroscopy examination site based on a gastroscopy examination site indicating system according to an embodiment of the present invention having the configuration as described above.

[0112] FIG. 3 is a flowchart illustrating the execution process of a method for indicating a gastroscopy examination site according to one embodiment of the present invention.

[0113] Referring to FIG. 3, a method for indicating a gastroscopic examination site according to one embodiment of the present invention first loads a gastroscopic image analysis model by a model loading / condition setting unit (110) and sets an analysis condition of the analysis model (e.g., a predicted probability value of 0.85 or higher) (step S301).

[0114] Then, the control unit (150) initializes the analysis screen and displays a picture of a normal stomach (step S302).

[0115] As described above, after the model loading and analysis condition settings are completed, the analysis screen is initialized and a normal stomach image is displayed, the control unit (150) determines whether to perform gastroscopic image analysis (step S303). If gastroscopic image analysis is required during this determination, the image preprocessing unit (130) reads the gastroscopic image (image frame) received through the image receiving unit (120) and preprocesses it so that subsequent image analysis can be performed smoothly (step S304). Here, the preprocessing of the gastroscopic image by the image preprocessing unit (130) may include cutting the analysis area and adjusting the input size.

[0116] When the preprocessing of the gastroscopic image is completed in this way, the image analysis unit (140) analyzes the preprocessed gastroscopic image using an AI-based image analysis model (step S305). Here, the image analysis model may be composed of a single image analysis model that detects the examination area and the hernia area as shown in FIG. 2a, as described above. Additionally, the image analysis model may be composed of an examination area detection model (Model A) that detects the examination area and a hernia detection model (Model B) that detects the hernia area, as shown in FIG. 2b. Additionally, the image analysis model may be composed of an examination area detection model (Model A) that detects the examination area, a hernia detection model (Model B) that detects the hernia area, and a lesion detection model (Model C) that detects the lesion area, as shown in FIG. 2c. At this time, the lesion detection model (Model C) may be equipped with a lesion attribute classification function that distinguishes whether the lesion is benign or malignant.

[0117] Additionally, the image analysis unit (140) detects and indicates at least one of the examination area, hernia area, and lesion area in the gastroscopic image based on the analyzed result (steps S306 to S308). Here, when the image analysis unit (140) detects and indicates at least one of the examination area, hernia area, and lesion area in the gastroscopic image, the examination area includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenal bulb, and the hernia area may include a gastric hernia and a periaesophageal hernia.

[0118] Here, we will explain the steps S306 to S308 above in a little more detail.

[0119] When the gastroscopic image analysis is completed by the image analysis unit (140) in step S305, the control unit (150) determines whether a hernia is detected (step S306), and if a hernia is detected, changes the normal stomach image to a hernia stomach image and displays it (see FIGS. 13–16) (step S307), and indicates the inspection area on the stomach image (step S308).

[0120] Afterward, if there is no further request for gastroscopy image analysis in the determination of step S303, the control unit (150) provides the analysis result analyzed immediately prior to by the image analysis unit (140) (step S309).

[0121] Meanwhile, Fig. 4 is a flowchart showing the execution process of a first modified example of the gastroscopy examination site indication method of Fig. 3.

[0122] Referring to FIG. 4, the process described above in FIG. 3 differs from FIG. 3 only in that the processes of storing the inspection start time (step S404), storing the duodenal bulb indication start time (step S410), displaying the inspection time and retrieval time (step S411), determining the change in indication conditions (step S412), changing the indication conditions (step S413), and storing the inspection end time (step S414) are added. The rest of the process is identical to FIG. 3. Therefore, the description of the parts identical to FIG. 3 will be replaced by the description in FIG. 3, and only the parts different from FIG. 3 will be described.

[0123] If gastroscopy image analysis is required in the determination of step S403 of Fig. 4, the control unit (150) stores the examination start time in the database (160) (step S404).

[0124] Afterwards, as described in FIG. 3, the image preprocessing unit (130) reads the gastroscopy image (image frame) received through the image receiving unit (120) and preprocesses it so that subsequent image analysis can be performed smoothly (step S405).

[0125] Additionally, the control unit (150) indicates the inspection area on the stomach diagram (step S409) and stores the start time of the duodenal bulb indication (step S410). Then, the control unit (150) displays the inspection time and the retrieval time (step S411). Here, the inspection time refers to the time from the start time of the inspection to the current time (end of inspection), and the retrieval time refers to the time from the start time of the duodenal bulb indication to the current time (end of inspection).

[0126] Additionally, the control unit (150) determines whether to change the instruction condition (step S412), and if a change in the instruction condition is required, changes the instruction condition (step S413). Here, the control unit (150) can transmit an instruction condition change command to the image analysis unit (140) to indicate the gastroesophageal junction if there is a superior gastric hernia, and to indicate the gastric cardia and fundus if there is a peresophageal hernia.

[0127] Additionally, the control unit (150) can transmit a command to change the instruction condition to the image analysis unit (140) to indicate a hernia differently in the normal stomach image, not indicate a hernia in the normal stomach image, or indicate a stomach hernia (e.g., alarm or area indication).

[0128] Meanwhile, if there is no further request for gastroscopy image analysis in the determination of step S403, the control unit (150) stores the time of end of the examination (step S414) and provides the analysis results up to the present (end of examination) (step S415).

[0129] Figure 5 is a flowchart showing the execution process of a second modified example of the method for indicating the gastroscopy examination site of Figure 3.

[0130] Referring to FIG. 5, the process described above in FIG. 3 differs from FIG. 3 only in that a step (S509) for determining whether a lesion is detected and a step (S510) for indicating lesion information in the stomach figure are added, while the rest of the process is identical to FIG. 3. Therefore, the description of the parts identical to FIG. 3 will be replaced by the description in FIG. 3, and only the parts different from FIG. 3 will be described.

[0131] In FIG. 5, the control unit (150) indicates the inspection area on the stomach figure (step S508), determines whether a lesion is detected (step S509), and if a lesion is detected, indicates lesion information (see FIG. 18) on the stomach figure (step S510).

[0132] Figure 6 is a flowchart showing the execution process of a third modified example of the method for indicating the gastroscopy examination site of Figure 3.

[0133] Referring to FIG. 6, the process described above in FIG. 4 is different only in that a step (S611) for determining whether a lesion is detected and a step (S612) for indicating lesion information in the stomach figure are added, while the rest of the process is the same as FIG. 4.

[0134] That is, if gastroscopy image analysis is required in the determination of step S603 of FIG. 6, the control unit (150) stores the start time of the examination in the database (160) (step S604).

[0135] Afterwards, as described in FIG. 3, the image preprocessing unit (130) reads the gastroscopy image (image frame) received through the image receiving unit (120) and preprocesses it so that subsequent image analysis can be performed smoothly (step S605).

[0136] Additionally, the control unit (150) indicates the inspection area on the stomach drawing (step S609) and stores the start time of the duodenal bulb indication (step S610). Then, the control unit (150) determines whether a lesion is detected (step S611), and if a lesion is detected, indicates lesion information (see FIG. 18) on the stomach drawing (step S612).

[0137] Then, the control unit (150) displays the inspection time and the retrieval time (step S613). Here, the inspection time refers to the time from the start time of the inspection to the current time (end of inspection), and the retrieval time refers to the time from the start time of the duodenal bulb indication to the current time (end of inspection).

[0138] Additionally, the control unit (150) determines whether to change the instruction condition (step S614), and if a change in the instruction condition is required, changes the instruction condition (step S615). Here, the control unit (150) can transmit an instruction condition change command to the image analysis unit (140) to indicate the gastroesophageal junction if there is a superior gastric hernia, and to indicate the gastric cardia and fundus if there is a peresophageal hernia.

[0139] Additionally, the control unit (150) can transmit a command to change the instruction condition to the image analysis unit (140) to indicate a hernia differently in the normal stomach image, not indicate a hernia in the normal stomach image, or indicate a stomach hernia (e.g., alarm or area indication).

[0140] Meanwhile, if there is no further request for gastroscopy image analysis in the determination of step S603, the control unit (150) stores the time of end of the examination (step S616) and provides the analysis results up to the present (end of examination) (step S617).

[0141] FIG. 7 is a schematic diagram showing the configuration of a gastroscopy examination site indication system according to another embodiment of the present invention.

[0142] Referring to FIG. 7, a gastroscopy examination site indication system (700) according to another embodiment of the present invention basically has the same components as the gastroscopy examination site indication system (100) according to one embodiment described above with reference to FIG. 1. However, the gastroscopy examination site indication system (700) according to this other embodiment differs in that it further includes a voice recognition unit (750).

[0143] As illustrated in FIG. 7, a gastroscopy examination site indication system (700) according to another embodiment of the present invention may be configured to include a model loading / condition setting unit (710), an image receiving unit (720), an image preprocessing unit (730), an image analysis unit (740), a voice recognition unit (750), and a control unit (760).

[0144] The model loading / condition setting unit (710) loads the gastroscopy image analysis model and sets the analysis conditions of the analysis model. Here, the analysis conditions of the analysis model can be set, for example, to a predicted probability value of 0.85 or higher.

[0145] The image receiving unit (720) receives the gastroscopy image frame.

[0146] The image preprocessing unit (730) preprocesses the gastroscopic image received through the image receiving unit (720) so that subsequent image analysis can be performed smoothly. Here, the preprocessing of the gastroscopic image by the image preprocessing unit (730) as described above may include cutting the analysis area and adjusting the input size.

[0147] The image analysis unit (740) analyzes the gastroscopic image preprocessed by the image preprocessing unit (730) using an AI (artificial intelligence)-based image analysis model, and based on the analyzed results, detects and indicates at least one of the examination area, hernia area, and lesion area in the gastroscopic image. Here, the image analysis model of the image analysis unit (740) may be composed of a single image analysis model that detects the examination area and the hernia area, as shown in FIG. 2a. In FIG. 2a, (a) shows an example of an internal indication from the entry into the stomach, and (b) shows an example of an internal center indication of the stomach.

[0148] In addition, the image analysis model of the image analysis unit (740) may be composed of an inspection area detection model (Model A) that detects the inspection area and a hernia detection model (Model B) that detects the hernia area, as shown in FIG. 2b. In FIG. 2b, (a) shows an example of internal indication from the upper entry, and (b) shows an example of internal center indication of the upper.

[0149] In addition, the image analysis model of the image analysis unit (740) may be composed of an inspection area detection model (Model A) that detects the inspection area, a hernia detection model (Model B) that detects the hernia area, and a lesion detection model (Model C) that detects the lesion area, as illustrated in FIG. 2C. At this time, the lesion detection model (Model C) may be equipped with a lesion attribute classification function that distinguishes whether the lesion is benign or malignant.

[0150] In addition, when the image analysis unit (740) detects and indicates at least one of an examination area, a hernia area, and a lesion area in the gastroscopic image, the examination area includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenum, and the hernia area may include a gastric hernia and a periaesophageal hernia.

[0151] The voice recognition unit (750) reads audio from a buffer (located in the internal memory of the voice recognition unit (750)) that stores audio while video analysis is being performed by the video analysis unit (740), analyzes it using an AI-based voice keyword recognition model, recognizes voice keywords based on the analyzed results, and transmits them to the video analysis unit (740).

[0152] The control unit (760) controls the status check and operation of the model loading / condition setting unit (710), image receiving unit (720), image preprocessing unit (730), image analysis unit (740), and voice recognition unit (750). When the loading of the gastroscopy image analysis model and the setting of the analysis conditions of the analysis model are completed by the model loading / condition setting unit (710), the analysis screen is initialized and an image of a normal stomach is displayed. The analysis results analyzed by the image analysis unit (740) are provided by connecting the analysis target detected by the image analysis model with a voice command (keyword) related to the analysis target spoken by the examiner.

[0153] Here, the control unit (760) described above can transmit a command to change the instruction condition to the image analysis unit (740) such that when the image analysis unit (740) detects and indicates at least one of the examination area, hernia area, and lesion area in the gastroscopic image, if it is a superior gastric hernia, the gastroesophageal junction is indicated, and if it is a peresophageal hernia, the gastric cardia and fundus are indicated. Additionally, when the image analysis unit (740) detects and indicates at least one of the examination area, hernia area, and lesion area in the gastroscopic image, the control unit (760) can transmit a command to change the instruction condition to indicate the hernia differently in a normal stomach image, not indicate the hernia in a normal stomach image, or indicate the gastric hernia (e.g., alarm or area indication).

[0154] In FIG. 7, reference number 770 represents a database (DB), and such a database (DB) (770) stores and manages data or information required when the model loading / condition setting unit (710), image receiving unit (720), image preprocessing unit (730), image analysis unit (740), and voice recognition unit (750) perform functions related to model loading and condition setting, image preprocessing, image analysis, and voice recognition, or process tasks, as well as gastroscopy image analysis result data based on an image analysis model.

[0155] Here, the model loading / condition setting unit (710), image receiving unit (720), image preprocessing unit (730), image analysis unit (740), voice recognition unit (750), control unit (760), and database (DB) (770) as described above may also be integrated as a whole to form a single computer system.

[0156] Then, below, we will describe a method for indicating a gastroscopy examination site based on a gastroscopy examination site indicating system according to another embodiment of the present invention having the configuration as described above.

[0157] FIG. 8 is a flowchart illustrating the execution process of a method for indicating a gastroscopy examination site according to another embodiment of the present invention.

[0158] Referring to FIG. 8, a method for indicating a gastroscopy examination site according to another embodiment of the present invention first loads a gastroscopy image analysis model and a voice recognition model through a model loading / condition setting unit (710), and sets an analysis condition of the analysis model (e.g., a predicted probability value of 0.85 or higher) (step S801).

[0159] Then, the control unit (760) initializes the analysis screen and displays a picture of a normal stomach (step S802).

[0160] As described above, after the loading of the gastroscopy image analysis model, the loading of the voice recognition model, and the setting of the analysis conditions of the models are completed, and after the analysis screen is initialized and a normal stomach image is displayed, the control unit (760) determines whether to perform gastroscopy image analysis (step S803). If gastroscopy image analysis is required in this determination, the image preprocessing unit (730) reads the gastroscopy image (image frame) received through the image receiving unit (720) and preprocesses it so that subsequent image analysis can be performed smoothly (step S804). Here, the preprocessing of the gastroscopy image by the image preprocessing unit (730) may include cutting the analysis area and adjusting the input size.

[0161] When the preprocessing of the gastroscopic image is completed in this way, the image analysis unit (740) analyzes the preprocessed gastroscopic image using an AI-based image analysis model (step S805). Here, the image analysis model may be composed of a single image analysis model that detects the examination area and the hernia area as shown in FIG. 2a, as described above. Additionally, the image analysis model may be composed of an examination area detection model (Model A) that detects the examination area and a hernia detection model (Model B) that detects the hernia area, as shown in FIG. 2b. Additionally, the image analysis model may be composed of an examination area detection model (Model A) that detects the examination area, a hernia detection model (Model B) that detects the hernia area, and a lesion detection model (Model C) that detects the lesion area, as shown in FIG. 2c. At this time, the lesion detection model (Model C) may be equipped with a lesion attribute classification function that distinguishes whether the lesion is benign or malignant.

[0162] Additionally, the image analysis unit (740) detects and indicates at least one of the examination area, hernia area, and lesion area in the gastroscopic image based on the analyzed result (steps S806 to S808). Here, when the image analysis unit (740) detects and indicates at least one of the examination area, hernia area, and lesion area in the gastroscopic image, the examination area includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenal bulb, and the hernia area may include a gastric hernia and a periaesophageal hernia.

[0163] Here, we will explain the above steps S806 to S808 in a little more detail.

[0164] When the gastroscopic image analysis is completed by the image analysis unit (740) in step S805, the control unit (760) determines whether a hernia is detected (step S806), and if a hernia is detected, changes the normal stomach image to a hernia stomach image and displays it (see FIGS. 13–16) (step S807), and indicates the inspection area on the stomach image (step S808).

[0165] Meanwhile, if gastroscopy image analysis is required during the determination of step S803, the voice recognition unit (750) reads audio from a buffer storing audio while the image analysis is being performed by the image analysis unit (740), analyzes it using an AI-based voice keyword recognition model (step S809), recognizes voice keywords based on the analyzed results (step S810), and transmits them to the image analysis unit (740).

[0166] That is, the voice recognition unit (750) recognizes a voice keyword and determines whether the voice keyword is a hernia keyword (step S811), and if it is a hernia keyword, transmits it to step S807 so that it is reflected in changing the hernia image.

[0167] And, if the above determination is not a hernia keyword, the voice recognition unit (750) determines whether it is an examination area keyword (step S812), and if it is an examination area keyword, transmits it to step S808 so that it is reflected in indicating the examination area in the stomach drawing.

[0168] Subsequently, if there is no further request for gastroscopy image analysis in the determination of step S803, the control unit (760) connects the analysis target detected by the image analysis model of the image analysis unit with the voice command (keyword) related to the analysis target uttered by the examiner, and provides the analysis results up to the present (examination end) by the image analysis unit (740) (step S813).

[0169] FIG. 9 is a flowchart showing the execution process of a modified example of a method for indicating a gastroscopy examination site according to another embodiment of the present invention.

[0170] Referring to FIG. 9, the process described above in FIG. 8 is different from FIG. 8 only in that the following processes are added: storing the start time of the inspection (step S904), storing the start time of the duodenal bulb indication (step S910), determining whether a lesion is detected (step S911), indicating lesion information in the figure above (step S912), displaying the inspection time and retrieval time (step S913), determining whether the indication condition is changed (step S914), changing the indication condition (step S915), and storing the end time of the inspection (step S920). The rest of the process is identical to FIG. 8. Therefore, the description of the parts identical to FIG. 8 will be replaced by the description in FIG. 8, and only the parts different from FIG. 8 will be described.

[0171] If gastroscopy image analysis is required in the determination of step S903 of Fig. 9, the control unit (760) stores the examination start time in the database (770) (step S904).

[0172] Afterwards, as described in FIG. 8, the image preprocessing unit (730) reads the gastroscopy image (image frame) received through the image receiving unit (720) and preprocesses it so that subsequent image analysis can be performed smoothly (step S905).

[0173] Additionally, the control unit (760) indicates the inspection area on the stomach drawing (step S909) and stores the start time of the duodenal bulb indication (step S910). Then, the control unit (760) determines whether a lesion is detected (step S911), and if a lesion is detected, indicates lesion information (see FIG. 18) on the stomach drawing (step S912).

[0174] Then, the control unit (760) displays the inspection time and the retrieval time (step S913). Here, the inspection time refers to the time from the start time of the inspection to the current time (end of inspection), and the retrieval time refers to the time from the start time of the duodenal bulb indication to the current time (end of inspection).

[0175] Additionally, the control unit (760) determines whether to change the instruction condition (step S914), and if a change in the instruction condition is required, changes the instruction condition (step S915). Here, the control unit (760) can transmit an instruction condition change command to the image analysis unit (740) to indicate the gastroesophageal junction if there is a superior gastric hernia, and to indicate the gastric cardia and fundus if there is a peresophageal hernia.

[0176] Additionally, the control unit (760) can transmit a command to change the instruction condition to the image analysis unit (740) to indicate a hernia differently in the normal stomach image, not indicate a hernia in the normal stomach image, or indicate a stomach hernia (e.g., alarm or area indication).

[0177] Meanwhile, if there is no further request for gastroscopy image analysis in the determination of step S903, the control unit (760) stores the time of end of the examination (step S920) and provides the analysis results up to the present (end of examination) (step S921).

[0178] Below, we will provide further explanation regarding the gastroscopy examination site indication system and method according to the present invention as described above.

[0179] Figure 10 is a diagram showing the main parts of the above.

[0180] Referring to Fig. 10, (a) shows the major parts of the stomach, and (b) shows the general examination sequence (direction of gastroscopic photography). The gastroscope is inserted through the esophagus and passes through the gastroesophageal junction and the gastric cardia, which are the parts where the esophagus and stomach meet, to enter the stomach. Once inside the stomach, the gastroscope photographs the inside of the stomach in the order of the body → gastric antrum → duodenal bulb → gastric angle → body → fundus → gastric cardia. At this time, it is recommended to photograph at least the gastroesophageal junction, gastric antrum, duodenal bulb, and gastric angle and to save the captured images.

[0181] Figure 11 is a drawing showing the upper side.

[0182] Referring to Fig. 11, (a) shows a normal stomach, (b) shows a superior gastric hernia, and (c) shows a peresophageal hernia. The superior gastric hernia in (b) is observed while moving from the esophagus to the stomach, and depending on the degree of hernia, it is also observed when the probe makes a U-turn to examine the gastric cardia. The peresophageal hernia in (c) is observed when the gastroscopic probe makes a U-turn to examine the gastric cardia and fundus.

[0183] Figure 12 is a drawing showing the inspection area of ​​the stomach (in the case of a normal stomach).

[0184] Referring to Fig. 12, this shows the process of inserting the gastroscopy probe and indicating the examination area. Generally, the inside of the stomach is observed in the order of examination start → observation of the gastroesophageal junction → observation of the body of the stomach → observation of the antrum → observation of the duodenal bulb → observation of the angle of the stomach → observation of the cardia and fundus of the stomach.

[0185] Figure 13 is a drawing showing the inspection site of the stomach (in the case of upper gastric hernia).

[0186] Referring to Fig. 13, this shows the case where the examination area is indicated starting from the process of inserting the gastroscopy probe. Similar to the case of a normal stomach in Fig. 12, the inside of the stomach is observed in the order of examination start → observation of the gastroesophageal junction → observation of the body of the stomach → observation of the antrum → observation of the duodenal bulb → observation of the angle of the stomach → observation of the cardia and fundus of the stomach.

[0187] Figure 14 is a diagram showing the inspection site markings above (in the case of a peresophageal hernia).

[0188] Referring to Fig. 14, this shows the case where the examination area is indicated starting from the process of inserting the gastroscopy probe. Likewise, the inside of the stomach is observed in the order of examination start → observation of the gastroesophageal junction → observation of the body of the stomach → observation of the antrum → observation of the duodenal bulb → observation of the angle of the stomach → observation of the cardia and fundus of the stomach.

[0189] Figure 15 is a drawing showing another example of the inspection site marking above (in the case of upper gastric hernia).

[0190] Referring to Fig. 15, this shows a case where the examination area is indicated starting from the process of retrieving the gastroscopy probe. The inside of the stomach is observed in the order of examination start → observation of the duodenal bulb → observation of the gastric antrum → observation of the gastric body → observation of the gastric angle → observation of the gastric cardia and fundus → observation of the gastroesophageal junction (i.e., while retrieving the probe in reverse).

[0191] Figure 16 is a diagram showing another example of the above inspection site marking (in the case of perisophageal hernia).

[0192] Referring to Fig. 16, this shows a case where the examination area is indicated starting from the process of retrieving the gastroscopy probe. Similar to the case in Fig. 15 above, the inside of the stomach is observed in the order of examination start → observation of the duodenal bulb → observation of the gastric antrum → observation of the gastric body → observation of the gastric angle → observation of the gastric cardia and fundus → observation of the gastroesophageal junction (i.e., while retrieving the probe in reverse).

[0193] Figure 17 is a diagram showing an example of providing analysis results (an example of a normal stomach examination).

[0194] Referring to FIG. 17, this illustrates the provision of analysis results for a normal gastric examination during the gastroscopic probe insertion process. (a) shows the gastroscopic examination start screen, and (b) and (c) show examples of gastric antrum examination. In particular, (c) shows a state indicating the examination area by a model configuration without the gastric angle. In FIG. 17, reference number 810 represents the gastroscopic image analysis software screen, 820 represents the gastroscopic image analysis area, 830 represents the pylorus, and 840 represents the gastric antrum. Additionally, T represents the examination time and W represents the retrieval time.

[0195] Figure 18 is a diagram showing an example of providing analysis results (example of upper gastric hernia, lesion detection).

[0196] Referring to FIG. 18, this illustrates the analysis results of upper gastric hernia and lesion detection during the gastroscopic probe insertion process. Similarly, (a) shows the gastroscopic examination start screen, and (b) and (c) show examples of gastric antrum examination; in particular, (c) shows a screen indicating the examination site by a model configuration without a gastric angle. In FIG. 18, reference number 810 represents the gastroscopic image analysis software screen, 820 represents the gastroscopic image analysis area, 830 represents the pylorus, 840 represents the gastric antrum, 850 represents the upper gastric hernia, and 860 represents the lesion. Additionally, T represents the examination time and W represents the retrieval time.

[0197] Figure 19 is a diagram showing an example of providing analysis results (an example of a peresophageal hernia examination).

[0198] Referring to FIG. 19, this illustrates the analysis results of a peresophageal hernia examination during the process of retrieving the gastroscopic probe. Similarly, (a) shows the gastroscopic examination start screen, and (b) and (c) show the detection of a hernia when the probe U-turns to examine the gastric cardia and fundus. (b) shows the state in which the peresophageal hernia diagram has been changed, and (c) shows the peresophageal hernia indication state on the normal stomach diagram. In FIG. 19, reference number 810 represents the gastroscopic image analysis software screen, 820 represents the gastroscopic image analysis area, 870 represents the probe, 880 represents the gastric cardia, and 890 represents the peresophageal hernia. Additionally, T represents the examination time and W represents the retrieval time.

[0199] Figure 20 is a diagram showing an example of providing analysis results (example of a result report).

[0200] Referring to FIG. 20, the results of the gastroscopy examination are as follows: (a) shows a case where there are no missed examination sites and no hernia; (b) shows a case where there are missed examination sites including the gastric angle and gastric fundus and no hernia; (c) shows a case where there are no missed examination sites and there is a hernia in the gastric region; and (d) shows a case where there is missed examination site including the gastric angle and a hernia perisophageal hernia.

[0201] As described above, the gastroscopic examination site indication system and method according to the present invention distinguishes between a normal stomach and a herniated stomach and indicates them on the screen, thereby enabling detailed indication of the stomach examination site and allowing for a more thorough gastroscopic examination by notifying the examiner of the herniation.

[0202] In addition, by indicating the major gastric examination sites, it has the advantage of allowing verification of areas examined so far, identification of missed locations after the examination is completed, and information regarding the presence of a hernia.

[0203] Although the present invention has been described in detail through preferred embodiments, the invention is not limited thereto, and it is obvious to those skilled in the art that various modifications and applications can be made within the scope of the technical concept of the invention. Accordingly, the true scope of protection of the present invention should be interpreted by the following claims, and all technical concepts within an equivalent scope should be interpreted as being included within the scope of rights of the present invention.

Claims

1. Model loading / condition setting unit for loading a gastroscopy image analysis model and setting analysis conditions for the analysis model; An image receiver that receives gastroscopy image frames; An image preprocessing unit that preprocesses a gastroscopy image received through the image receiving unit to facilitate subsequent image analysis; An image analysis unit that analyzes a gastroscopic image preprocessed by the image preprocessing unit using an AI (artificial intelligence)-based image analysis model, and detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopic image based on the analyzed result; and A gastroscopy examination site indication system comprising a control unit that controls the status check and operation of the above-mentioned model loading / condition setting unit, image receiving unit, image preprocessing unit, and image analysis unit, and when the loading of the gastroscopy image analysis model and the setting of analysis conditions of the analysis model are completed by the above-mentioned model loading / condition setting unit, initializes the analysis screen and displays an image of a normal stomach, and provides the analysis result analyzed by the above-mentioned image analysis unit.

2. In Paragraph 1, The preprocessing of the gastroscopic image by the above-mentioned image preprocessing unit is a gastroscopic examination site indication system that includes analysis area cutting and input size adjustment.

3. In Paragraph 1, A gastroscopy examination site indication system characterized in that the image analysis model of the above-mentioned image analysis unit is composed of a single image analysis model that detects the examination site and the hernia site.

4. In Paragraph 1, A gastroscopy examination site indication system characterized in that the image analysis model of the above-mentioned image analysis unit is composed of an examination site detection model that detects the examination site and a hernia detection model that detects the hernia site.

5. In Paragraph 1, A gastroscopy examination site indication system characterized in that the image analysis model of the above-mentioned image analysis unit is composed of an examination site detection model that detects the examination site, a hernia detection model that detects a hernia site, and a lesion detection model that detects a lesion site.

6. In Paragraph 5, A gastroscopy examination site indication system characterized by the above-mentioned lesion detection model having a lesion attribute classification function that distinguishes whether a lesion is benign or malignant.

7. In Paragraph 1, A gastroscopic examination site indication system in which the above-described image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the above-described gastroscopic image, wherein the examination site includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenal bulb, and the hernia site includes a superior gastric hernia and a perisophageal hernia.

8. In Paragraph 1, A gastroscopic examination site indication system characterized by the above-described control unit transmitting an instruction condition change command to the above-described image analysis unit, wherein the above-described image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the above-described gastroscopic image, such that if it is a superior gastric hernia, the gastroesophageal junction is indicated, and if it is a peresophageal hernia, the gastric cardia and fundus are indicated.

9. In Paragraph 1, A gastroscopic examination site indication system characterized by the above-described control unit transmitting a command to the image analysis unit to change indication conditions, such as indicating a hernia differently in a normal stomach image, not indicating a hernia in a normal stomach image, or indicating a gastric hernia, when the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopic image. 10.a) A step in which the model loading / condition setting unit loads a gastroscopy image analysis model and sets the analysis conditions of the analysis model; b) A step in which the control unit initializes the analysis screen and displays the image above the normal; c) A step in which the image preprocessing unit preprocesses the gastroscopy image received through the image receiving unit so that subsequent image analysis can be performed smoothly; d) A step in which an image analysis unit analyzes the preprocessed gastroscopy image using an AI-based image analysis model; e) a step in which an image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopy image based on the analyzed result; and f) A method for indicating a gastroscopic examination site comprising the step of a control unit providing an analysis result analyzed by the image analysis unit.

11. In Paragraph 10, The preprocessing of the gastroscopic image by the image preprocessing unit in step c) above is a method for indicating the gastroscopic examination area, including cutting the analysis area and adjusting the input size.

12. In Paragraph 10, A method for indicating a gastroscopy examination site, characterized in that, in step d) above, the image analysis model is composed of a single image analysis model that detects the examination site and the hernia site.

13. In Paragraph 10, A method for indicating an endoscopy examination site, characterized in that, in step d) above, the image analysis model is composed of an examination site detection model that detects an examination site and a hernia detection model that detects a hernia site.

14. In Paragraph 10, A method for indicating an endoscopy examination site, characterized in that, in step d) above, the image analysis model is composed of an examination site detection model that detects an examination site, a hernia detection model that detects a hernia site, and a lesion detection model that detects a lesion site.

15. In Paragraph 14, A method for indicating a gastroscopy examination site, characterized in that the above-mentioned lesion detection model is equipped with a lesion attribute classification function that distinguishes whether a lesion is benign or malignant.

16. In Paragraph 10, A method for indicating an endoscopic examination site in which, in step e) above, the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopic image, wherein the examination site includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenal bulb, and the hernia site includes a superior gastric hernia and a perisophageal hernia.

17. In Paragraph 10, A method for indicating an endoscopy examination site, characterized in that, in step e) above, the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the endoscopy image, and the control unit transmits a command to change the indication condition to the image analysis unit, such that if it is a superior gastric hernia, the gastroesophageal junction is indicated, and if it is a peresophageal hernia, the gastric cardia and fundus are indicated.

18. In Paragraph 10, A method for indicating an endoscopy examination site, characterized in that, in step e) above, the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the endoscopy image, and the control unit transmits a command to change the indication condition to indicate a hernia differently in a normal stomach image, not indicate a hernia in a normal stomach image, or indicate a gastric hernia.

19. Model loading / condition setting unit that loads a gastroscopy analysis model and a voice keyword recognition model, and sets the analysis conditions of the analysis model; An image receiver that receives gastroscopy image frames; An image preprocessing unit that preprocesses a gastroscopy image received through the image receiving unit to facilitate subsequent image analysis; An image analysis unit that analyzes a gastroscopic image preprocessed by the image preprocessing unit using an AI (artificial intelligence)-based image analysis model, and detects and indicates at least one of an examination site, a hernia site, or a lesion site in the gastroscopic image based on the analyzed result; A voice recognition unit that reads audio from a buffer storing audio while video analysis is being performed by the video analysis unit, analyzes it using an AI-based voice keyword recognition model, recognizes voice keywords based on the analyzed results, and transmits them to the video analysis unit; and A gastroscopy examination site indication system comprising a control unit that controls the status check and operation of the above-mentioned model loading / condition setting unit, image receiving unit, image preprocessing unit, image analysis unit, and voice recognition unit, and when the loading of the gastroscopy image analysis model and the setting of analysis conditions of the analysis model are completed by the above-mentioned model loading / condition setting unit, initializes the analysis screen and displays an image of a normal stomach, and provides an analysis result analyzed by the above-mentioned image analysis unit, wherein the analysis result is provided by connecting the analysis target detected by the above-mentioned image analysis model with a voice command (keyword) related to the analysis target uttered by the examiner.

20. In Paragraph 19, The preprocessing of the gastroscopic image by the above-mentioned image preprocessing unit is a gastroscopic examination site indication system that includes analysis area cutting and input size adjustment.

21. In Paragraph 19, A gastroscopy examination site indication system characterized in that the image analysis model of the above-mentioned image analysis unit is composed of a single image analysis model that detects the examination site and the hernia site.

22. In Paragraph 19, A gastroscopy examination site indication system characterized in that the image analysis model of the above-mentioned image analysis unit is composed of an examination site detection model that detects the examination site and a hernia detection model that detects the hernia site.

23. In Paragraph 19, A gastroscopy examination site indication system characterized in that the image analysis model of the above-mentioned image analysis unit is composed of an examination site detection model that detects the examination site, a hernia detection model that detects a hernia site, and a lesion detection model that detects a lesion site.

24. In Paragraph 23, A gastroscopy examination site indication system characterized by the above-mentioned lesion detection model having a lesion attribute classification function that distinguishes whether a lesion is benign or malignant.

25. In Paragraph 19, A gastroscopic examination site indication system in which the above-described image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the above-described gastroscopic image, wherein the examination site includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenal bulb, and the hernia site includes a superior gastric hernia and a perisophageal hernia.

26. In Paragraph 19, A gastroscopic examination site indication system characterized by the above-described control unit transmitting an instruction condition change command to the above-described image analysis unit, wherein the above-described image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the above-described gastroscopic image, such that if it is a superior gastric hernia, the gastroesophageal junction is indicated, and if it is a peresophageal hernia, the gastric cardia and fundus are indicated.

27. In Paragraph 19, A gastroscopic examination site indication system characterized by the above-described control unit transmitting a command to the image analysis unit to change indication conditions, such as indicating a hernia differently in a normal stomach image, not indicating a hernia in a normal stomach image, or indicating a gastric hernia, when the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopic image. 28.p) A step in which the model loading / condition setting unit loads the gastroscopy analysis model and the voice keyword recognition model, and sets the analysis conditions of the analysis model; q) A step in which the control unit initializes the analysis screen and displays an image of a normal stomach; r) A step in which the image preprocessing unit preprocesses the gastroscopy image received through the image receiving unit so that subsequent image analysis can be performed smoothly; s) A step in which an image analysis unit analyzes a gastroscopy image preprocessed by the image preprocessing unit using an AI-based image analysis model; t) A step in which an image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopy image based on the analyzed result; u) a step in which a voice recognition unit reads audio from a buffer storing audio while video analysis is being performed by the video analysis unit, analyzes it using an AI-based voice keyword recognition model, recognizes voice keywords based on the analyzed results, and transmits them to the video analysis unit; and v) A method for indicating a gastroscopic examination site comprising the step of a control unit connecting an analysis target detected by an image analysis model of the image analysis unit with a voice command (keyword) related to an analysis target uttered by an examiner to provide an analysis result.

29. In Paragraph 28, The preprocessing of the gastroscopic image by the image preprocessing unit in step r) above is a method for indicating the gastroscopic examination area, which includes cutting the analysis area and adjusting the input size.

30. In Paragraph 28, A method for indicating a gastroscopy examination site, characterized in that, in step s) above, the image analysis model is composed of a single image analysis model that detects the examination site and the hernia site.

31. In Paragraph 28, A method for indicating an endoscopy examination site, characterized in that, in step s) above, the image analysis model is composed of an examination site detection model that detects the examination site and a hernia detection model that detects the hernia site.

32. In Paragraph 28, A method for indicating an endoscopy examination site, characterized in that, in step s) above, the image analysis model comprises an examination site detection model that detects the examination site, a hernia detection model that detects a hernia site, and a lesion detection model that detects a lesion site.

33. In Paragraph 32, A method for indicating a gastroscopy examination site, characterized in that the above-mentioned lesion detection model is equipped with a lesion attribute classification function that distinguishes whether a lesion is benign or malignant.

34. In Paragraph 28, A method for indicating an endoscopic examination site, wherein in step t) above, the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the gastroscopic image, wherein the examination site includes the gastroesophageal junction, the body of the stomach, the antrum, the cardia, the angle of the stomach, the fundus, and the duodenal bulb, and the hernia site includes a superior gastric hernia and a perisophageal hernia.

35. In Paragraph 28, A method for indicating an endoscopy examination site, characterized in that, in step t) above, the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the endoscopy image, and the control unit transmits a command to change the indication condition to the image analysis unit, such that if it is a superior gastric hernia, the gastroesophageal junction is indicated, and if it is a peresophageal hernia, the gastric cardia and fundus are indicated.

36. In Paragraph 28, A method for indicating an endoscopy examination site, characterized in that, in step t) above, the image analysis unit detects and indicates at least one of an examination site, a hernia site, and a lesion site in the endoscopy image, and the control unit transmits a command to change the indication condition to indicate a hernia differently in a normal stomach image, not indicate a hernia in a normal stomach image, or indicate a gastric hernia.

Images