Voice signal and laryngoscope image diagnosis device based on AI

Abstract

The invention provides an AI-based voice signal and laryngoscope image diagnosis device, and relates to the technical field of medical instruments, the AI-based voice signal and laryngoscope image diagnosis device comprises a placement table, a case is arranged below the placement table, a host is arranged in the case, the host is connected with a laryngoscope, the placement table is rotatably connected with a rotary table, and the rotary table is connected with a camera. A directional pickup and a display screen are arranged on the rotary table, and the host is connected with a vibration sensor and a sound sensor; the bottom of the vibration sensor is provided with a buckle cover, and the detection part of the vibration sensor is fixedly provided with a guide sheet. According to the vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord vocal cord

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of medical devices, in particular to an AI-based voice signal and laryngoscope image diagnosis device. BACKGROUND

[0002] Laryngoscopy methods include indirect laryngoscopy and direct laryngoscopy. Indirect laryngoscopy observes the laryngeal structure through a mirror, and direct laryngoscopy needs to be inserted into the nasal cavity to the larynx to observe the mucosa, tongue root, epiglottis, vocal cords and the like. Other laryngoscopy methods also include electronic laryngoscopy and fiber laryngoscopy, which can clearly display the laryngeal condition. Through the search of the published patent, the specific application number is CN202211318641.2, a laryngoscope camera device with a stroboscopic light source function, comprising: an optical endoscope device, a stroboscopic light source, a sound pickup, a controller and a display, wherein the controller is connected with the display, the sound pickup, the stroboscopic light source and the optical endoscope device, the stroboscopic light source is connected with the optical endoscope device, which obtains the sound information of the vocal cords, but obviously mixes the interference sound generated by the external sound transmission to the vocal cords and the patient's own vocal cord surrounding, thus affecting the reliability of the sound change. SUMMARY

[0003] To achieve the above purpose, the application is implemented through the following technical scheme: an AI-based voice signal and laryngoscope image diagnosis device, comprising a placement table, a machine box is arranged below the placement table, a host is arranged in the machine box, a laryngoscope is connected with the host, a rotary table is rotatably connected on the placement table, a directional sound pickup and a display screen are arranged on the rotary table, a vibration sensor and a sound sensor are connected with the host; A buckle cover is mounted at the bottom of the vibration sensor, a guide sheet is fixedly mounted on the detection part of the vibration sensor, the sound sensor is fixedly mounted on the buckle cover, a sponge cover is sleeved outside the sound sensor, a through hole is arranged in the middle of the guide sheet, and the sponge cover passes through the through hole to be attached to the larynx of the patient.

[0004] Preferably, an installation groove is arranged on the rotary table, a first connecting rod is rotatably connected in the installation groove through a damping shaft, the other end of the first connecting rod is rotatably connected with a second connecting rod through a damping shaft, and the other end of the second connecting rod is rotatably connected with the display screen through a damping shaft.

[0005] Preferably, a motor is inlaidly mounted on the upper side of the placement table, the output end of the motor is fixedly connected to the middle position of the bottom of the rotary table, the directional sound pickup is located on the front side of the installation groove, a miniature camera is mounted on the directional sound pickup, and the miniature camera and the motor are electrically connected with the host. The position information of the patient is collected through the miniature camera, then the host controls the motor to rotate the rotary table, so that the directional sound pickup faces the patient to obtain the sound information of the patient in the direction.

[0006] Preferably, the cover comprises two flexible side standing parts made of medical rubber, and an elastic band is arranged between the end parts, and the cover is buckled on the neck corresponding to one side of the thyroid cartilage by crossing the elastic band over the neck.

[0007] Preferably, the case comprises multiple layers of partitions, and the main machine is arranged on one of the partitions, and the case is provided with a wire passing hole at the corresponding position of the side wall.

[0008] Preferably, the flexible side standing part of the cover is provided with a fitting opening fitting the mandible and an arc opening fitting the thyroid of the neck on one side.

[0009] Preferably, the number of vibration sensors and the number of guide sheets are both two and are distributed side by side, the vibration sensors are located on both sides of the sound sensor, and the side close to the two guide sheets is provided with a silica gel film away from the vibration sensor, and the thickness of the silica gel film is 0.1-0.5mm.

[0010] Preferably, the laryngoscope is integrated with an optical endoscope, a stroboscopic light source and a sound pickup.

[0011] The application provides an AI-based voice signal and laryngoscope image diagnosis device. In the application, the voice produced by the muscle and bone vibration around the vocal cord of the patient during speaking and the external sound transmitted to the vocal cord are removed, other interference except the voice produced by the vocal cord during speaking is reduced, and thus the actual voice change of the vocal cord during speaking of the patient can be clearly obtained, and the accuracy is greatly improved. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 It is a structural schematic view of the application; Figure 2 It is a top view of the application; Figure 3 It is a structural schematic view of the application after opening the box door; Figure 4 It is a structural schematic view of the application in Figure 1 It is a structural schematic view of the other side; Figure 5 It is a sectional view of the cover in the application.

[0013] Among them, 1, placing table; 2, directional sound pickup; 3, display screen; 4, turntable; 6, case; 7, guide sheet; 8, cover; 9, elastic band; 10, laryngoscope; 11, first connecting rod; 12, second connecting rod; 13, sponge cover; 14, main machine; 15, vibration sensor; 16, sound sensor. DETAILED DESCRIPTION

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] Example 1: like Figures 1-5 As shown, this embodiment of the invention provides an AI-based voice signal and laryngoscope image diagnostic device, including a placement platform 1, a housing 6 below the placement platform 1, a main unit 14 inside the housing 6, and multiple partitions inside the housing 6, with the main unit 14 located on one of the partitions. The housing 6 has a wiring port on the side wall at the corresponding position, and a door is rotatably provided on the front side of the housing 6. After opening the door, different medical instruments used in laryngoscope examinations can be placed on the partitions. An ultraviolet germicidal lamp can be configured as needed so that the ultraviolet germicidal lamp can irradiate the space accordingly. The main unit 14 is connected to a laryngoscope 10, which integrates an optical endoscope, a stroboscopic light source, and a microphone. The optical endoscope and stroboscopic light source work together to acquire images of the vocal cords of the larynx, and the microphone acquires sound information from inside the larynx. The image and sound information acquired by the laryngoscope 10 are transmitted to the main unit 14. After the intelligent system is installed on the main unit 14, the intelligent system pre-analyzes the image and sound information acquired by the laryngoscope 10, establishes feature recognition labels, and stores them. A turntable 4 is rotatably connected to the placement platform 1. A directional microphone 2 and a display screen 3 are installed on the turntable 4. A vibration sensor 15 and a sound sensor 16 are connected to the main unit 14. A motor is embedded in the upper side of the placement platform 1. The output end of the motor is fixedly connected to the middle position of the bottom of the turntable 4. The directional microphone 2 is located on the front side of the mounting slot. A miniature camera is installed on the directional microphone 2. The miniature camera and the motor are electrically connected to the main unit 14. The position information of the patient is collected by the miniature camera. Then, the main unit 14 controls the motor to rotate the turntable 4 so that the directional microphone 2 faces the patient to obtain sound information from the direction of the patient. Initially, the main unit 14 controls the motor to drive the turntable 4 to rotate so that the miniature camera can obtain the direction of the patient. After the intelligent system of the main unit 14 determines that the direction is towards the patient through the information of the miniature camera, it controls the motor to stop working. In this way, the directional microphone 2 can obtain the sound signal from the direction of the patient. The sound signal obtained by the directional microphone 2 is transmitted to the main unit 14. The bottom of the vibration sensor 15 is provided with a buckle cover 8, the detection part of the vibration sensor 15 is fixedly provided with a guide sheet 7, the sound sensor 16 is fixedly provided on the buckle cover 8, the outside of the sound sensor 16 is sleeved with a sponge cover 13, the guide sheet 7 is provided with a through hole in the middle, the sponge cover 13 passes through the through hole for being close to the throat of the patient, the guide sheet 7 is a copper sheet with a thickness of 0.2 mm, the buckle cover 8 includes two flexible side standing parts made of medical rubber, and an elastic band 9 is arranged between the end parts, the buckle cover 8 is buckled on one side of the neck corresponding to the thyroid cartilage through the elastic band 9 across the neck, the flexible side standing parts of the buckle cover 8 are provided with a close-up mouth close to the mandible and an arc mouth close to the thyroid gland on one side, that is, the sound sensor 16 can obtain the sound when the patient speaks from the outside of the neck, the guide sheet 7 contacts the throat, and then the vibration information of the throat when the patient speaks can be obtained through the vibration sensor 15, and the sound sensor 16 also obtains the sound generated by the vibration of the guide sheet 7, the vibration information of the vibration sensor 15 and the sound information of the sound sensor 16 are transmitted to the host 14, and the buckle cover 8 is wrapped with sound insulation cotton, so that the interference of the doctor and the patient in conversation on the sound sensor 16 can be greatly reduced.

[0016] The rotating table 4 is provided with a mounting groove, the inner side of the mounting groove is rotatably connected with the first connecting rod 11 through a damping shaft, the other end of the first connecting rod 11 is rotatably connected with the second connecting rod 12 through a damping shaft, and the other end of the second connecting rod 12 is rotatably connected with the display screen 3 through a damping shaft, and the angle of the first connecting rod 11, the second connecting rod 12 and the display screen 3 after rotation is maintained through the damping shaft, which is convenient for the doctor to watch the display screen 3, the display screen 3 is used for displaying the image information of the optical endoscope and displaying the sound display image processed by the intelligent system.

[0017] Working principle: first, the buckle cover 8 is covered on the throat of the patient, and the close-up mouth of the flexible side standing part of the buckle cover 8 is close to the mandible, the arc mouth is close to the thyroid gland of the neck, and the sponge cover 13 is aligned with the position of the laryngeal prominence and the thyroid cartilage, then the doctor performs laryngoscopy, in the process, the intelligent system arranged in the host 14 takes the sound signal of the laryngoscope 10 as the reference, compares the sound information of the directional microphone 2 and the sound sensor 16, and then eliminates the sound existing around the doctor and the patient, then matches the vibration signal of the vibration sensor 15 with the sound information of the microphone, and then obtains the vibration condition of the outside of the vocal cords when the patient speaks, then obtains the sound signal difference of the outside vibration through the comparison of the sound sensor 16 and the microphone, finally analyzes the corresponding relationship between the vibration condition of the outside of the vocal cords and the sound signal difference, eliminates the sound deviation generated by the vibration of the guide sheet 7, and then eliminates the remaining sound signal difference from the microphone, which can eliminate the sound signal generated by the external interference and muscle vibration when people speak, and improve the sound accuracy of the microphone of the laryngoscope 10.

[0018] Example two: The number of vibration sensors 15 and the number of guide vanes 7 are both two and are distributed side by side, the vibration sensors 15 are located on both sides of the sound sensor 16, and the side close to the two guide vanes 7 is provided with a silica gel film away from the vibration sensor 15, the thickness of the silica gel film is 0.1-0.5mm, the above-mentioned silica gel film can reduce the interference of the vibration collision of the side close to the two guide vanes 7 on the sound sensor 16, and can also reduce the noise generated by the vibration of the two guide vanes 7 out of step.

[0019] Although embodiments of the present application have been shown and described, it is to be understood that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An AI-based diagnostic device for voice signals and laryngoscopy images, comprising a placement stage (1), wherein a housing (6) is disposed below the placement stage (1), characterized in that: The chassis (6) is equipped with a host (14), the host (14) is connected to a laryngoscope (10), the placement platform (1) is rotatably connected to a turntable (4), the turntable (4) is equipped with a directional pickup (2) and a display screen (3), and the host (14) is connected to a vibration sensor (15) and a sound sensor (16). The vibration sensor (15) is fitted with a cover (8) at its bottom. The detection part of the vibration sensor (15) is fixedly fitted with a guide plate (7). The sound sensor (16) is fixedly fitted on the cover (8). The sound sensor (16) is fitted with a sponge cover (13) on its outer side. The guide plate (7) has a through hole in the middle. The sponge cover (13) passes through the through hole and is used to be attached to the patient's throat.

2. The AI-based voice signal and laryngoscopy image diagnostic device according to claim 1, characterized in that: The turntable (4) is provided with an installation groove. A first connecting rod (11) is rotatably connected to the inside of the installation groove via a damping shaft. The other end of the first connecting rod (11) is rotatably connected to a second connecting rod (12) via a damping shaft. The other end of the second connecting rod (12) is rotatably connected to the display screen (3) via a damping shaft.

3. The AI-based voice signal and laryngoscopy image diagnostic device according to claim 2, characterized in that: A motor is embedded in the upper side of the placement platform (1). The output end of the motor is fixedly connected to the middle position of the bottom of the turntable (4). The directional microphone (2) is located on the front side of the mounting slot. A miniature camera is installed on the directional microphone (2). The miniature camera and the motor are electrically connected to the host (14). The position information of the patient is collected by the miniature camera. Then, the host (14) controls the motor to rotate the turntable (4) so ​​that the directional microphone (2) faces the patient to obtain the sound information of the patient's direction.

4. The AI-based voice signal and laryngoscopy image diagnostic device according to claim 3, characterized in that: The buckle (8) includes two flexible side sections made of medical rubber, and an elastic band (9) is provided between the ends. The buckle (8) is fastened to the side of the neck corresponding to the thyroid cartilage by crossing the elastic band (9) across the neck.

5. The AI-based voice signal and laryngoscopy image diagnostic device according to claim 4, characterized in that: The chassis (6) includes multiple partitions, the host (14) is located on one of the partitions, and the chassis (6) has a cable pass-through port on the side wall at the corresponding position.

6. The AI-based voice signal and laryngoscopy image diagnostic device according to claim 4, characterized in that: The flexible side part of the buckle (8) has a fitting opening for fitting the mandible and an arc opening for fitting the thyroid gland in the neck on one side.

7. The AI-based voice signal and laryngoscopy image diagnostic device according to claim 1, characterized in that: The vibration sensor (15) and the guide plate (7) are both two in number and are arranged side by side. The vibration sensor (15) is located on both sides of the sound sensor (16). A silicone film is provided on the side of the two guide plates (7) that are close to each other and on the side away from the vibration sensor (15). The thickness of the silicone film is 0.1-0.5mm.

8. The AI-based voice signal and laryngoscopy image diagnostic device according to claim 1, characterized in that: The laryngoscope (10) integrates an optical endoscope, a strobe light source, and a microphone.

Images