Hysteroscopy device and method based on artificial intelligence

Abstract

The invention provides a hysteroscopy device and method based on artificial intelligence, and relates to the field of examination devices. According to the hysteroscopy device based on artificial intelligence, a hysteroscope body comprises a hysteroscope body, a light source and a camera system, the hysteroscope body is used for entering a uterine cavity, the light source provides illumination, the camera system captures images, an operating handle is used for controlling the direction and depth of the hysteroscope, and a biopsy channel is used for inserting biopsy forceps, a cell scraper and other tools. The uterine distension liquid container is used for storing uterine distension liquid, the uterine distension pump is used for controlling the injection speed and pressure of the uterine distension liquid, and the pressure sensor is used for monitoring the pressure in a uterine cavity to prevent excessive distension. By arranging the intelligent image diagnosis system, the accuracy and reliability of diagnosis are improved, by arranging the uterus expansion system, a good visual field is provided for the hysteroscope, and by arranging the hysteroscope system, visual vision is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of inspection devices, and in particular to a hysteroscopic inspection device and method based on artificial intelligence. Background Art

[0002] With the rapid development of medical technology, hysteroscopy, as an important means of diagnosing gynecological diseases, is also constantly innovating and improving. Artificial intelligence technology is increasingly used in the medical field, and its powerful data processing and learning capabilities provide strong support for the intelligentization of medical equipment. Especially in hysteroscopy, the introduction of artificial intelligence technology makes the inspection process more accurate and efficient. Through deep learning algorithms, artificial intelligence systems can automatically identify and analyze hysteroscopic images, assist doctors in diagnosis, and thus improve the accuracy and efficiency of diagnosis.

[0003] Although the existing technology uses hysteroscopy to examine gynecological diseases, simple manual diagnosis is prone to misjudgment, resulting in misdiagnosis and increasing the psychological pressure of patients. Therefore, technical personnel in this field provide a hysteroscopy device and method based on artificial intelligence to solve the problems raised in the above background technology. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a hysteroscopy device and method based on artificial intelligence, which solves the problem of improving accuracy in diagnosis and ensuring the safety of patients during examination.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: an artificial intelligence-based hysteroscopy device, comprising: a hysteroscopy system, including a hysteroscope body, an operating handle and a biopsy channel, the hysteroscope body including a scope, a light source and a camera system, wherein the scope is used to enter the uterine cavity, the light source provides lighting, the camera system captures images, the operating handle is used to control the direction and depth of the hysteroscope, and the biopsy channel is used to insert tools such as biopsy forceps and cell scrapers to collect samples;

[0008] An intelligent image diagnosis system, comprising an image acquisition module, an image processing module, an AI analysis module and a diagnosis suggestion module, wherein the image acquisition module is used to acquire real-time image data from a hysteroscopic camera system, the image processing module is used to pre-process the image, such as denoising, contrast enhancement, etc., the AI ​​analysis module uses a deep learning algorithm (such as a convolutional neural network) to analyze the image and identify the location and type of the lesion, and the diagnosis suggestion module provides diagnosis suggestions and possible treatment plans based on the AI ​​analysis results;

[0009] The uterine distension system includes a uterine distension fluid container, a uterine distension pump, and a pressure sensor. The uterine distension fluid container is used to store the uterine distension fluid, the uterine distension pump is used to control the injection speed and pressure of the uterine distension fluid, and the pressure sensor is used to monitor the pressure in the uterine cavity to prevent excessive expansion.

[0010] Monitoring and recording systems, including monitors, recording devices and databases;

[0011] The anesthesia and vital signs monitoring system includes an anesthesia device and a vital signs monitor. The anesthesia device is used to provide anesthesia support to ensure that the patient is painless during the operation, and the vital signs monitor is used to monitor the patient's vital signs during the operation.

[0012] Preferably, the scope allows the doctor to directly observe the conditions in the uterus, identify the site of the lesion, and perform operations such as biopsy and treatment. The light source and camera system transmit the image to the monitor and AI system for analysis.

[0013] Preferably, the AI ​​analysis module can analyze hysteroscopic images in real time, automatically identify common intrauterine lesions, such as endometrial polyps, uterine fibroids, endometrial hyperplasia, etc., and provide diagnostic suggestions through the diagnostic suggestion module to help doctors make more accurate judgments.

[0014] Preferably, the uterine distension system expands the uterine cavity by injecting uterine distension fluid into the uterine cavity, and adjusts the uterine distension pressure and flow rate through a uterine distension pump to maintain them within a safe range.

[0015] Preferably, the uterine distension system uses the following formula during the process of injecting uterine distension fluid:

[0016] Calculation of dosage of uterine distention fluid:

[0017] Where V is the volume of the required distending fluid, P is the expansion ratio of the uterine cavity, and r is the average radius of the uterine cavity;

[0018] Uterine distension pressure monitoring:

[0019] Where P is the distension pressure, F is the distension force, and A is the cross-sectional area of ​​the uterine cavity.

[0020] Preferably, the intelligent image diagnosis system uses the following formula during image processing:

[0021] Denoising formula: I denoised =IN

[0022] Among them, I denoised is the denoised image, I is the original image, and N is the image noise;

[0023] Lesion identification: Probability = Softmax(W·X+b)

[0024] Among them, Probability is the probability distribution of the lesion type, W is the weight matrix, X is the input image feature vector, and b is the bias vector.

[0025] Preferably, the anesthesia and vital signs monitoring system uses the following formula during operation:

[0026] Anesthetic drug dosage calculation:

[0027] Where D is the drug dose, W is the patient's weight, C is the standard drug concentration, and S is the drug sensitivity coefficient;

[0028] Vital Signs Monitoring Formulas;

[0029] Where BP is blood pressure, CO is cardiac output, SVR is systemic vascular resistance, and SV is stroke volume.

[0030] Preferably, a method of a hysteroscopy device based on artificial intelligence comprises the following steps;

[0031] S1. The patient takes the lithotomy position, with both legs placed on the leg rest, buttocks slightly beyond the edge of the operating table, and a sterile towel is placed under the patient's thighs and buttocks. Check whether the anesthesia equipment and vital signs monitor are working properly, connect the patient to the vital signs monitor, monitor heart rate, blood pressure, blood oxygen saturation, etc., select the appropriate anesthesia method according to the patient's condition and the complexity of the operation, implement anesthesia, monitor the patient's vital signs, and ensure anesthesia safety;

[0032] S2. Apply sterile lubricant to the hysteroscope body and cervical os to reduce friction and discomfort. Slowly rotate the hysteroscope and insert it into the cervical os and into the uterine cavity. During the insertion process, pay attention to the monitor screen to ensure that the path of the hysteroscope is correct to avoid damaging the endometrium and myometrium.

[0033] S3. Start the uterine distension device and inject uterine distension fluid (such as saline or glucose solution) into the uterine cavity to expand the uterine cavity for easy observation. Adjust the uterine distension pressure and flow rate to keep them within a safe range to avoid excessive expansion leading to uterine perforation.

[0034] S4. Observe the images in the uterine cavity through the monitor, and use the AI ​​system for real-time image recognition and analysis. The AI ​​system can automatically identify common intrauterine lesions, such as endometrial polyps, uterine fibroids, endometrial hyperplasia, etc. The AI ​​system will provide real-time diagnostic suggestions to help doctors make more accurate judgments. Doctors can make comprehensive diagnoses based on the prompts of the AI ​​system and their own clinical experience;

[0035] S5. Use the AI ​​system to record key images and video clips and save them in the database for subsequent analysis and review. Continuously monitor the patient's vital signs through the monitor to detect and deal with possible complications in a timely manner.

[0036] Working principle: The patient takes the lithotomy position with both legs placed on the leg rests, with the buttocks slightly beyond the edge of the operating table, and a sterile towel is placed under the patient's thighs and buttocks. Check whether the anesthesia equipment and vital signs monitor are working properly. Connect the patient to the vital signs monitor to monitor heart rate, blood pressure, blood oxygen saturation, etc. Select the appropriate anesthesia method according to the patient's condition and the complexity of the operation, implement anesthesia, monitor the patient's vital signs, ensure the safety of anesthesia, apply sterile lubricant to the hysteroscope body and cervical opening to reduce friction and discomfort, slowly rotate the hysteroscope, insert it into the cervical opening and into the uterine cavity. During the insertion process, pay attention to the monitor screen to ensure that the path of the hysteroscope is correct to avoid damaging the endometrium and myometrium, start the uterine distension device, and inject uterine distension fluid (such as Physiological saline or glucose solution) is used to expand the uterine cavity for easy observation. The uterine distension pressure and flow are adjusted to keep them within a safe range to avoid uterine perforation caused by excessive expansion. The images in the uterine cavity are observed through a monitor. The AI ​​system is used for real-time image recognition and analysis. The AI ​​system can automatically identify common intrauterine lesions, such as endometrial polyps, uterine fibroids, endometrial hyperplasia, etc. The AI ​​system will provide real-time diagnostic suggestions to help doctors make more accurate judgments. Doctors can make a comprehensive diagnosis based on the prompts of the AI ​​system and their own clinical experience. The AI ​​system is used to record key images and video clips and save them in a database for subsequent analysis and review. The patient's vital signs are continuously monitored through a monitor to promptly detect and deal with possible complications.

[0037] (III) Beneficial effects

[0038] The present invention provides a hysteroscopy device and method based on artificial intelligence, which has the following beneficial effects:

[0039] 1. By setting up an intelligent image diagnosis system, the system can automatically identify the location and type of lesions in hysteroscopic images, such as endometrial polyps, uterine fibroids, endometrial hyperplasia, etc., reducing the misjudgment rate of manual diagnosis. At the same time, the AI ​​system can accumulate a large amount of case data, and continuously optimize the diagnosis model through deep learning algorithms to improve the accuracy and reliability of diagnosis.

[0040] 2. By setting up a uterine distension system and injecting uterine distension fluid into the uterine cavity, the uterine cavity is expanded, providing a good field of view for the hysteroscope, facilitating observation and operation. At the same time, the uterine distension system can adjust the uterine distension pressure and flow rate to keep them within a safe range to avoid excessive expansion leading to uterine perforation or water intoxication.

[0041] 3. By setting up a hysteroscope system, the hysteroscope system can directly enter the uterine cavity, observe the endometrium, intrauterine lesions, etc. in real time, provide intuitive visual information, and help doctors quickly locate lesions. Doctors can perform biopsy, polypectomy and other operations through hysteroscopy, reducing the trauma and recovery time caused by traditional open surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the structure of the present invention;

[0043] Figure 2 It is a structural schematic diagram of the hysteroscope system of the present invention;

[0044] Figure 3 It is a structural schematic diagram of the intelligent image diagnosis system of the present invention;

[0045] Figure 4 It is a structural schematic diagram of the uterine expansion system of the present invention;

[0046] Figure 5 It is a structural schematic diagram of the anesthesia and vital signs monitoring system of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Embodiment 1:

[0049] like Figure 1-5As shown, an embodiment of the present invention provides an artificial intelligence-based hysteroscopic examination device, including: a hysteroscopic system, including a hysteroscope body, an operating handle and a biopsy channel, the hysteroscope body including a scope, a light source and a camera system, wherein the scope is used to enter the uterine cavity, the light source provides lighting, the camera system captures images, the operating handle is used to control the direction and depth of the hysteroscope, and the biopsy channel is used to insert biopsy forceps, cell scrapers and other tools for sample collection. By setting up the hysteroscopic system, the hysteroscopic system can directly enter the uterine cavity, observe the endometrium, intrauterine lesions, etc. in real time, provide intuitive visual information, and help doctors quickly locate lesions. Doctors can perform biopsy, polypectomy and other operations through hysteroscopy, reducing the trauma and recovery time caused by traditional open surgery.

[0050] The intelligent image diagnosis system includes an image acquisition module, an image processing module, an AI analysis module and a diagnosis suggestion module. The image acquisition module is used to obtain real-time image data from the hysteroscopic camera system. The image processing module is used to pre-process the image, such as denoising, contrast enhancement, etc. The AI ​​analysis module uses a deep learning algorithm (such as a convolutional neural network) to analyze the image and identify the location and type of the lesion. The diagnosis suggestion module provides diagnostic suggestions and possible treatment plans based on the AI ​​analysis results. By setting up an artificial intelligence image diagnosis system, the system can automatically identify the location and type of lesions in hysteroscopic images, such as endometrial polyps, uterine fibroids, endometrial hyperplasia, etc., reducing the misjudgment rate of manual diagnosis. At the same time, the AI ​​system can accumulate a large amount of case data, continuously optimize the diagnosis model through a deep learning algorithm, and improve the accuracy and reliability of the diagnosis.

[0051] The uterine distension system includes a uterine distension fluid container, a uterine distension pump and a pressure sensor. The uterine distension fluid container is used to store the uterine distension fluid, the uterine distension pump is used to control the injection speed and pressure of the uterine distension fluid, and the pressure sensor is used to monitor the pressure in the uterine cavity to prevent excessive expansion. By setting up the uterine distension system, the uterine cavity is expanded by injecting uterine distension fluid into the uterine cavity, providing a good field of view for the hysteroscope, facilitating observation and operation. At the same time, the uterine distension system can adjust the uterine distension pressure and flow to keep it within a safe range to avoid uterine perforation or water poisoning caused by excessive expansion.

[0052] Monitoring and recording systems, including monitors, recording equipment and databases.

[0053] Anesthesia and vital signs monitoring system, including anesthesia equipment and vital signs monitor. Anesthesia equipment is used to provide anesthesia support to ensure that patients are painless during surgery, and vital signs monitor is used to monitor patients' vital signs during surgery.

[0054] The scope allows the doctor to directly observe the conditions inside the uterus, identify the site of the lesion, and perform operations such as biopsy and treatment. The light source and camera system transmit the image to the monitor and AI system for analysis. The AI ​​analysis module can analyze the hysteroscopic images in real time, automatically identify common intrauterine lesions such as endometrial polyps, uterine fibroids, endometrial hyperplasia, etc., and provide diagnostic suggestions through the diagnostic suggestion module to help doctors make more accurate judgments. The uterine distension system expands the uterine cavity by injecting uterine distension fluid into the uterine cavity, and adjusts the uterine distension pressure and flow through the uterine distension pump to keep it within a safe range.

[0055] The following formula is used by the uterine distension system during the injection of uterine distension fluid:

[0056] Calculation of dosage of uterine distention fluid:

[0057] Where V is the volume of the required distending fluid, P is the expansion ratio of the uterine cavity, and r is the average radius of the uterine cavity;

[0058] Uterine distension pressure monitoring:

[0059] Where P is the distension pressure, F is the distension force, and A is the cross-sectional area of ​​the uterine cavity.

[0060] The intelligent image diagnosis system uses the following formula during image processing:

[0061] Denoising formula: I denoised =IN

[0062] Among them, I denoised is the denoised image, I is the original image, and N is the image noise;

[0063] Lesion identification: Probability = Softmax(W·X+b)

[0064] Among them, Probability is the probability distribution of the lesion type, W is the weight matrix, X is the input image feature vector, and b is the bias vector.

[0065] The anesthesia and vital signs monitoring system uses the following formula during operation:

[0066] Anesthetic drug dosage calculation:

[0067] Where D is the drug dose, W is the patient's weight, C is the standard drug concentration, and S is the drug sensitivity coefficient;

[0068] Vital Signs Monitoring Formulas;

[0069] Where BP is blood pressure, CO is cardiac output, SVR is systemic vascular resistance, and SV is stroke volume.

[0070] A method of a hysteroscopy device based on artificial intelligence, comprising the following steps;

[0071] S1. The patient takes the lithotomy position, with both legs placed on the leg rest, buttocks slightly beyond the edge of the operating table, and a sterile towel is placed under the patient's thighs and buttocks. Check whether the anesthesia equipment and vital signs monitor are working properly, connect the patient to the vital signs monitor, monitor heart rate, blood pressure, blood oxygen saturation, etc., select the appropriate anesthesia method according to the patient's condition and the complexity of the operation, implement anesthesia, monitor the patient's vital signs, and ensure anesthesia safety;

[0072] S2. Apply sterile lubricant to the hysteroscope body and cervical os to reduce friction and discomfort. Slowly rotate the hysteroscope and insert it into the cervical os and into the uterine cavity. During the insertion process, pay attention to the monitor screen to ensure that the path of the hysteroscope is correct to avoid damaging the endometrium and myometrium.

[0073] S3. Start the uterine distension device and inject uterine distension fluid (such as saline or glucose solution) into the uterine cavity to expand the uterine cavity for easy observation. Adjust the uterine distension pressure and flow rate to keep them within a safe range to avoid excessive expansion leading to uterine perforation.

[0074] S4. Observe the images in the uterine cavity through the monitor, and use the AI ​​system for real-time image recognition and analysis. The AI ​​system can automatically identify common intrauterine lesions, such as endometrial polyps, uterine fibroids, endometrial hyperplasia, etc. The AI ​​system will provide real-time diagnostic suggestions to help doctors make more accurate judgments. Doctors can make comprehensive diagnoses based on the prompts of the AI ​​system and their own clinical experience;

[0075] S5. Use the AI ​​system to record key images and video clips and save them in the database for subsequent analysis and review. Continuously monitor the patient's vital signs through the monitor to detect and deal with possible complications in a timely manner.

[0076] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A hysteroscopy device based on artificial intelligence, characterized in that: include: A hysteroscope system, comprising a hysteroscope body, an operating handle and a biopsy channel, wherein the hysteroscope body comprises a scope, a light source and a camera system, wherein the scope is used to enter the uterine cavity, the light source provides lighting, the camera system captures images, the operating handle is used to control the direction and depth of the hysteroscope, and the biopsy channel is used to insert tools such as biopsy forceps and cell scrapers for sample collection; An intelligent image diagnosis system, comprising an image acquisition module, an image processing module, an AI analysis module and a diagnosis suggestion module, wherein the image acquisition module is used to acquire real-time image data from a hysteroscopic camera system, the image processing module is used to pre-process the image, such as denoising, contrast enhancement, etc., the AI ​​analysis module uses a deep learning algorithm (such as a convolutional neural network) to analyze the image and identify the location and type of the lesion, and the diagnosis suggestion module provides diagnosis suggestions and possible treatment plans based on the AI ​​analysis results; The uterine distension system includes a uterine distension fluid container, a uterine distension pump, and a pressure sensor. The uterine distension fluid container is used to store the uterine distension fluid, the uterine distension pump is used to control the injection speed and pressure of the uterine distension fluid, and the pressure sensor is used to monitor the pressure in the uterine cavity to prevent excessive expansion. Monitoring and recording systems, including monitors, recording devices and databases; The anesthesia and vital signs monitoring system includes an anesthesia device and a vital signs monitor. The anesthesia device is used to provide anesthesia support to ensure that the patient is painless during the operation, and the vital signs monitor is used to monitor the patient's vital signs during the operation.

2. The artificial intelligence-based hysteroscopy device according to claim 1, characterized in that: The scope allows the doctor to directly observe the conditions inside the uterus, identify the site of the lesion, and perform operations such as biopsy and treatment. The light source and camera system transmit the image to the monitor and AI system for analysis.

3. The artificial intelligence-based hysteroscopy device according to claim 1, characterized in that: The AI ​​analysis module can analyze hysteroscopic images in real time, automatically identify common intrauterine lesions, such as endometrial polyps, uterine fibroids, endometrial hyperplasia, etc., and provide diagnostic suggestions through the diagnostic suggestion module to help doctors make more accurate judgments.

4. The artificial intelligence-based hysteroscopy device according to claim 1, characterized in that: The uterine distension system expands the uterine cavity by injecting uterine distension fluid into the uterine cavity, and adjusts the uterine distension pressure and flow rate through a uterine distension pump to keep them within a safe range.

5. The artificial intelligence-based hysteroscopy device according to claim 1, characterized in that: The uterine distension system uses the following formula during the injection of uterine distension fluid: Calculation of dosage of uterine distention fluid: Where V is the volume of the required distending fluid, P is the expansion ratio of the uterine cavity, and r is the average radius of the uterine cavity; Uterine distension pressure monitoring: Where P is the distension pressure, F is the distension force, and A is the cross-sectional area of ​​the uterine cavity.

6. The artificial intelligence-based hysteroscopy device according to claim 1, characterized in that: The intelligent image diagnosis system uses the following formula during image processing: Denoising formula: I denoised =IN Among them, I denoised is the denoised image, I is the original image, and N is the image noise; Lesion identification: Probability = Softmax(W·X+b) Among them, Probability is the probability distribution of the lesion type, W is the weight matrix, X is the input image feature vector, and b is the bias vector.

7. The artificial intelligence-based hysteroscopy device according to claim 1, characterized in that: The anesthesia and vital signs monitoring system uses the following formula during operation: Anesthetic drug dosage calculation: Where D is the drug dose, W is the patient's weight, C is the standard drug concentration, and S is the drug sensitivity coefficient; Vital Signs Monitoring Formulas; Where BP is blood pressure, CO is cardiac output, SVR is systemic vascular resistance, and SV is stroke volume.

8. The method of the artificial intelligence-based hysteroscopy device according to claim 1, characterized in that: The steps include: S1. The patient takes the lithotomy position, with both legs placed on the leg rest, buttocks slightly beyond the edge of the operating table, and a sterile towel is placed under the patient's thighs and buttocks. Check whether the anesthesia equipment and vital signs monitor are working properly, connect the patient to the vital signs monitor, monitor heart rate, blood pressure, blood oxygen saturation, etc., select the appropriate anesthesia method according to the patient's condition and the complexity of the operation, implement anesthesia, monitor the patient's vital signs, and ensure anesthesia safety; S2. Apply sterile lubricant to the hysteroscope body and cervical os to reduce friction and discomfort. Slowly rotate the hysteroscope and insert it into the cervical os and into the uterine cavity. During the insertion process, pay attention to the monitor screen to ensure that the path of the hysteroscope is correct to avoid damaging the endometrium and myometrium. S3. Start the uterine distension device and inject uterine distension fluid (such as saline or glucose solution) into the uterine cavity to expand the uterine cavity for easy observation. Adjust the uterine distension pressure and flow rate to keep them within a safe range to avoid excessive expansion leading to uterine perforation. S4. Observe the images in the uterine cavity through the monitor, and use the AI ​​system for real-time image recognition and analysis. The AI ​​system can automatically identify common intrauterine lesions, such as endometrial polyps, uterine fibroids, endometrial hyperplasia, etc. The AI ​​system will provide real-time diagnostic suggestions to help doctors make more accurate judgments. Doctors can make comprehensive diagnoses based on the prompts of the AI ​​system and their own clinical experience; S5. Use the AI ​​system to record key images and video clips and save them in the database for subsequent analysis and review. Continuously monitor the patient's vital signs through the monitor to detect and deal with possible complications in a timely manner.

Images