498 results about "Laryngoscopes" patented technology

The invention discloses a laryngoscope imaging analysis method and system based on deep learning. The method comprises the steps of data acquisition, data preprocessing, lesion static detection, vocal cord dynamic analysis and laryngoscope imaging analysis. The invention relates to the technical field of laryngoscope analysis, in particular to a laryngoscope imaging analysis method and system based on deep learning, according to the scheme, two mutually supporting functional designs of lesion static detection and vocal cord dynamic analysis are adopted, detection of an intuitive lesion area is carried out through a static image, and assistance and support are carried out through vocal cord dynamic analysis; detecting by adopting an improved convolutional neural network method combined with feature optimization; the vocal cord dynamic analysis is carried out by adopting a residual error improved bidirectional long-short-term memory neural network method combined with bidirectional improved time sequence convolution, a powerful auxiliary reference is provided for static image lesion detection, meanwhile, the method can also be used as an independent detection function, and the overall connectivity and reusability of the method are improved.

The invention discloses an image segmentation method and system, and relates to the technical field of image segmentation. According to the image segmentation method, to-be-segmented laryngoscope medical image data is obtained and input into a pre-trained image segmentation model for preliminary segmentation processing, and a laryngoscope structure segmentation image is generated and comprises a plurality of laryngoscope segmentation areas and corresponding segmentation data sets; performing comprehensive analysis to obtain a structure segmentation perception index of each throat segmentation region, performing analysis to obtain a plurality of low-confidence throat regions, and inputting the low-confidence throat regions into an image restoration model in combination with a segmentation data set of a set annular adjacent throat segmentation region for analysis to obtain an enhanced segmentation data set of each enhanced throat region; according to the method, the laryngoscope structure segmentation image is updated through the enhanced segmentation data set of each enhanced laryngoscope region to obtain the structured laryngoscope tissue segmentation image, so that the enhanced regions have the consistency of pixel levels, and the segmentation precision and clinical availability are effectively guaranteed.

A video laryngoscope navigation system is provided that identifies an anatomical feature in an image signal from a camera of a video laryngoscope. Based on the identified anatomical feature, a steering indicator is overlaid on a displayed image of the image signal. In an embodiment, the steering indicator is representative of a steering direction for the camera to orient the camera towards the identified anatomical feature.

The invention relates to the field of children voice data processing, in particular to a multi-modal children voice data processing method based on deep learning and federal learning. According to the scheme, the method comprises the steps that a laryngoscope image and sounding audio data of a child are collected, after preprocessing, local features in the laryngoscope image are extracted through a DLE module, global features in the laryngoscope image are extracted through a GSA module, fusion of the local features and the global features of the laryngoscope image is carried out through an MSFE module, and final fusion features of the laryngoscope image are obtained; local features and global features of the audio data are extracted from the preprocessed Mel spectrogram through an AMFN module, and fusion of the local features and the global features is carried out; and then, a Vision Transform classifier model is trained, and in the training process, the privacy protection and distributed modeling capability of the multi-center medical data are ensured in combination with a federal learning framework. The method is suitable for children voice data classification.

The invention belongs to the technical field of medical treatment, and discloses a laryngeal membrane implantation system combined with a central vein puncture device, which comprises a self-retaining laryngoscope, a hollow puncture needle, a catheter sleeved on the puncture needle, a skin expander, a metal guide wire, a central vein catheter, a non-absorbable suture and a laryngeal membrane. The puncture needle penetrates into the laryngeal cavity, and the catheter is retained. And guiding by using a metal guide wire, expanding the skin by using a skin expander, and smoothly placing into the central venous catheter. The central venous catheter is pulled out of the self-retaining laryngoscope, and the non-absorbable suture is reversely arranged along the tip of the catheter, so that the suture smoothly penetrates out of the larynx from the inside of the larynx to the outside of the larynx, the laryngeal membrane is firmly fixed on the larynx, and further adhesion of vocal cords is avoided. Components required by the invention are simple and easy to obtain. Compared with a traditional method, the method is simple and easy to operate, saves operation time and is easy to popularize nationwide.

The invention relates to a throat reflux disease detection method and system based on a laryngoscope image and an RFS-Net algorithm, and the method comprises the steps: collecting the laryngoscope image, screening a disease type by a professional worker according to the laryngoscope image, and carrying out the RFS evaluation of the collected laryngoscope image, and obtaining a first image; the first image is sent to an FCN-ResNet network for pixel-level region prediction, and a second image is obtained; continuously sending the second image into a DSE-ResNet network for feature quantization to obtain a quantization score of the first image; sending the obtained quantized score of the first image into an RFS-Net model, and performing LPR prediction to output a score; and the throat reflux disease is evaluated according to the score, so that the accuracy of diagnosing the throat reflux disease by machine recognition is improved, and automatic evaluation is realized.

A system and method for a laryngoscopic device which incorporates the electronic and imaging elements within the device with advanced functional iterations that incorporate mathematical pattern recognition / predictive modeling as well as parallel computing and supercomputing for data analysis as well as and integrating it with the patient's record and compiling images from multiple scopes in a cloud-based system for an AI platform to use in diagnosis and disease monitoring.

Disclosed is a video laryngoscope that automatically adjusts display of a portion of an acquired image. The video laryngoscope may detect patient anatomy and / or a tool present in an image captured by a camera of the video laryngoscope. Detection of patient anatomy and / or a tool may be performed via image recognition rules and / or machine learning (ML) models. Based at least on the detected tool(s), a portion of the acquired image may be selected for display. For example, a display region of an acquired image may be selected to include both detected patient anatomy and a portion of a detected tool. Display of the acquired images may be progressively adjusted as a detected tool moves toward or away from the patient anatomy, until a maximum or minimum display region is reached.

Apparatus and methods for placement of an endotracheal tube in an airway of a patient, where the apparatus includes a laryngoscope member with a camera and a suction aperture for clearing unwanted material from the camera, where the laryngoscope member includes a lumen for passage of a tracheoscope member that also has a camera and a suction aperture for clearing unwanted material from the camera, where an endotracheal tube can be advanced over the tracheoscope member and positioned as desired in the airway of the patient, where the cameras facilitate positioning of the laryngoscope member, tracheoscope member, and endotracheal tube, and the suction apertures facilitate clearing unwanted material that could otherwise obscure imaging by the cameras.

The invention discloses a laryngocarcinoma primary screening and lesion area positioning method and device fusing an attention mechanism. The method comprises the following steps: (1) carrying out standardization and non-uniformity correction preprocessing on a laryngoscope image; (2) constructing a parallel deep learning model; (3) designing an adaptive dynamic feature fusion (AFF) module; (4) designing a multi-objective optimization loss function suitable for a laryngeal cancer preliminary screening task; (5) constructing a dual interpretability verification system of the Grad-CAM and the SHAP; and (6) generation and visual presentation of a diagnosis result. According to the method, an Inception-v4 and ViT parallel architecture is adopted, and a hybrid dynamic attention (HDA) mechanism is introduced into an Inception-v4 branch, so that the local feature extraction capability is effectively improved. By designing an adaptive dynamic fusion (AFF) module and combining a cross-modal attention (CMAF) mechanism, efficient interaction of local and global features is realized. Particularly, a multi-objective loss function is designed aiming at the requirement of early screening of laryngeal cancer. At the output end of the model, Grad-CAM thermodynamic diagram positioning and SHAP credibility evaluation are integrated at the same time, and a complete interpretability diagnosis system is constructed.

A multifunctional visualization instrument is provided that, in certain embodiments, includes a body having a proximal end and a distal end. The multifunctional visualization instrument includes a display screen on the body and a camera stick at the distal end of the body and comprising an arm and a camera. The arm of the camera stick is sized to fit within a channel of a removable laryngoscope blade. The multifunctional visualization instrument includes a port on a surface of the laryngoscope, configured to mate with an introducer and a steering input for steering the introducer, displayed on the display screen simultaneously with an image of the patient captured by the camera.

The invention relates to the field of anesthesia, in particular to an anesthesia device used based on a laryngoscope, which comprises a display screen, a handle assembly is arranged on the display screen, a supporting assembly is used for opening an oral cavity, a limiting assembly is arranged on the supporting assembly, a peeping assembly is mounted on the supporting assembly, and the limiting assembly is used for limiting the peeping assembly. The limiting assembly is used for limiting the peeping assembly; a conveying assembly is arranged on the supporting assembly. The supporting assembly can be detached from the handle assembly, the conveying assembly is arranged on the supporting assembly, the sputum can be sucked out from the inside of the throat of a patient conveniently through the conveying assembly, anesthetic can be conveyed to the inside of the throat conveniently through the conveying assembly, and the anesthetic can be accurately sprayed to the wall of the throat where the sputum is discharged; the situation in the throat can be observed through the arranged peeping assembly, and the conveying assembly can be conveyed to the throat wall where anesthetic needs to be sprayed; and accurate positioning can be conveniently achieved when a doctor sprays anesthetic.

The invention provides a throat reflux disease detection method and system based on a laryngoscope image and an RFS-Net algorithm, and relates to the technical field of medical image intelligent detection.The method comprises the following steps that a laryngoscope image sample is obtained and preprocessed, and a standard image is obtained; inputting the standard image into the RFS-Net model, and extracting spatial features and spectrum features; carrying out model training based on an improved Focal Loss function in combination with the extracted spatial features and spectrum features, and balancing sample distribution; fusing the shallow texture features and the deep semantic features of the image samples through a residual attention mechanism RAM; performing lesion analysis on the patient data in combination with clinical indexes and fusion features, and outputting a detection result; according to the method, multi-dimensional feature extraction and fusion are performed on the laryngoscope image through the RFS-Net model, spatial features and frequency spectrum features are covered, the features of the throat reflux disease can be identified more accurately in combination with the improved Focal Loss function optimization model training, and misdiagnosis and missed diagnosis conditions are reduced.

The invention relates to the technical field of laryngoscopes, discloses a drug delivery device for the throat of the pediatric department, and solves the problems that observation dead angles exist and the drug spraying coverage area is too large when a conventional visual laryngoscope end drug delivery structure is used for drug spraying treatment. The medicine spraying falling point enters the shooting range of the shooting module, the medicine spraying range is narrowed in the mode, the opened transparent plate can block the outer side of the medicine spraying range, medicine sputtering is avoided, the medicine spraying assembly is arranged to be adjustable, multiple spraying heads are arranged, and adaptive selection can be made according to the focus area; the lower side of the mounting seat B is also provided with a sputum removal assembly for removing sputum in a medicine spraying area of the medicine spraying assembly, so that medicine can be sprayed after the sputum is removed, and the treatment effect is improved.

The invention relates to the technical field of medical artificial intelligence, in particular to a difficult airway glottis feature intelligent identification method and system.The method comprises the steps that a breathing sound signal of a patient is collected through a miniature microphone embedded in a laryngeal mask, and a time-frequency graph is obtained through preprocessing; time-frequency domain feature self-adaptive extraction is carried out by adopting a three-channel parallel architecture, and a ring-shaped cartilage compression sound and a secretion interference sound are separated through a double-path noise feature learning network; capturing glottis features of different time scales from microcosmic to macroscopic by using a multi-scale glottis feature pyramid fusion technology; time sequence modeling is carried out through a BiGRU network and a time attention mechanism, and a glottis state sequence is identified; according to the method, a Cormack-Lehane grading result is determined based on a double-branch decision network and Bayesian decision reasoning, laryngoscope model recommendation is given, the difficult airway prediction accuracy rate is improved to 91.7% and is improved by 25%-30% compared with a traditional method, anesthesia related complications can be effectively reduced, and the success rate of first intubation is improved.

The multifunctional laryngoscope lens comprises a laryngoscope lens body and a pipeline channel arranged in the laryngoscope lens body, and the pipeline channel extends along the appearance of the laryngoscope lens body; the pipeline channel comprises a water supply pipeline, a soft lens pipeline and a suction pipeline which are sequentially arranged at intervals, and an endoscopic soft lens is inserted into the soft lens pipeline in a penetrating mode. A flow guide channel and a negative pressure channel are formed in the tail end of the pipeline channel, and the position of a lens of the soft endoscope does not exceed the opening position of the flow guide channel and the opening position of the negative pressure channel. By means of the design that the shape follow-up pipeline is embedded in the laryngoscope blade, the radial size of the multifunctional laryngoscope blade is reduced, foreign matter discomfort of a patient in laryngoscope operation is relieved, and the multifunctional laryngoscope blade is suitable for laryngoscope first-aid operation of a special patient in a limited oral cavity space. By additionally arranging the flow guide channel and the negative pressure channel, the laryngoscope lens can be effectively cleaned, and the function of controlling the flushing force of the lens is achieved through the flow speed monitoring unit and the calculation and visualization unit.

The invention discloses an anesthesia intubation auxiliary device, and belongs to the technical field of anesthesia instruments, the anesthesia intubation auxiliary device comprises a clamping mechanism and an adjustable fixing support arranged above the clamping mechanism, the end part of the adjustable fixing support is provided with a mounting support, and the side wall of the mounting support is sequentially provided with an opening mechanism and a U-shaped fitting plate from top to bottom; the opening mechanism downwards penetrates through the U-shaped attaching plate, an intubation positioning mechanism is arranged in the U-shaped attaching plate in a sliding mode, a follow-up centering assembly is arranged between the intubation positioning mechanism and the opening mechanism, the intubation positioning mechanism is arranged at the end, away from the adjustable fixing support, of the U-shaped attaching plate, and a laryngoscope fixing mechanism is arranged on one side of the mounting support. According to the anesthesia intubation auxiliary device, the laryngoscope fixing mechanism is arranged, the laryngoscope can be automatically fixed after the glottis is completely exposed, and therefore the hands of medical workers are liberated in the trachea intubation process, and intubation is convenient.

The invention provides a laryngoscope image super-resolution improving method, system and device based on deep learning. The system comprises an image preprocessing module, a shallow feature extraction module, a deep feature extraction module and an image reconstruction module. The image preprocessing module realizes blurred image enhancement based on wavelet transform; the superficial layer feature extraction module is used for extracting superficial layer features from the low-resolution laryngoscope image; the deep feature extraction module is used for capturing deep features from the shallow features, and performing feature fusion on the shallow features and the captured deep features to generate final features; and the image reconstruction module is used for reconstructing a high-resolution laryngoscope image from the learned final features. According to the scheme, the image resolution and image details can be remarkably improved, artifacts and noise interference are effectively reduced, the visual quality of the image is improved, and the image processing efficiency and stability are improved.

An assisted supporting structure for tracheal intubation, relating to the technical field of intubation, and solving the problems that an operation can only be completed by means of cooperation of two persons during intubation, and the intubation personnel need to have good proficiency, and can operate a laryngoscopic lens and perform tracheal intubation at the same time. An assisted supporting structure for tracheal intubation, comprising a supporting structure sliding rail A(1); a supporting structure sliding rail B(11) is provided on one side of the supporting structure sliding rail A(1); a movable plate (6) is provided between the supporting structure sliding rail A(1) and the supporting structure sliding rail B(11); an arc-shaped plate (13) is provided in front of the movable plate (6); a rotating shaft connecting rod (12) is provided between the arc-shaped plate (13) and the movable plate (6); and the rotating shaft connecting rod (12) is connected to the movable plate (6) by means of a rotating shaft. In this way, the angle of the head of a patient can be automatically adjusted and the mouth of the patient can be pulled open, thus the patient does not need to be assisted by a person aside in the intubation process, and a laryngoscope pressing down on the tongue and the tongue root can be automatically fixed, thereby reducing the requirement for the proficiency of operators.

In one embodiment, a laryngoscopy apparatus includes a handle configured for gripping by an operator, a blade extending from the handle configured for insertion into the trachea of a patient, a clear viewing window provided on the blade that enables a patient's airway to be viewed, and means for clearing material from the viewing window that could obscure the view of the airway.

The invention relates to a laryngoscope image classification method based on multi-scale cross-axis attention collaborative optimization, and the method comprises the steps: carrying out the preprocessing of a to-be-classified laryngoscope image, inputting the to-be-classified laryngoscope image after the preprocessing into a trained classification model based on multi-scale cross-axis attention collaborative optimization, and obtaining a classification result. The classification model sequentially comprises a feature extraction module, a feature coupling module, an average pooling module and a probability conversion module which are serially arranged from input to output. The feature extraction module comprises a first feature extraction unit and a second feature extraction unit which are parallel, the first feature extraction unit comprises an encoder and a decoder which are serial, and the second feature extraction unit is of an OfficientNet-B0 network structure. The encoder is of a ResNet50 network structure, and the decoder is of a multi-scale cross-axis attention network structure. According to the method, the parallel multi-model network is adopted for laryngoscope image feature extraction, the feature representation capability is high, and the problems of over-fitting and weak generalization capability cannot be caused.

The invention discloses a multi-modal-based vocal cord cancerous lesion feature extraction method and analysis system. The method comprises the following steps: step 1, acquiring biochemical indexes, audio and laryngoscope pictures of patients with polyps, precancerous lesions and cancerous lesions in otolaryngological departments of cooperative hospitals in several years as multi-modal data; 2, image processing; 3, constructing a network model based on a deep learning architecture; and 4, performing model preheating by adopting a cross entropy loss function and a self-adaptive optimizer. The lesion feature extraction and analysis system comprises a data acquisition and processing module, a model training and evaluation module and a classification result output module; wherein the data acquisition and processing module executes the steps of data acquisition and data processing, the model training and evaluation module constructs a model based on a deep learning architecture, and the method has the beneficial effects that the omission and error rate of feature extraction is effectively reduced, the success rate of early feature discovery is improved, and the stability and reliability of a feature extraction result are improved.

The invention belongs to the technical field of medical instruments, and particularly relates to a composite material for an anaesthetic laryngoscope and a preparation method thereof. The composite material for the anaesthetic laryngoscope comprises the following raw materials in parts by weight: 50-80 parts of polyvinyl chloride, 45-65 parts of a plasticizer, 0.5-1 part of a lubricant, 0.5-1 part of a stabilizer, 0.5-1 part of a chitosan derivative and 3-8 parts of modified hydroxyapatite. The chitosan derivative, the modified hydroxyapatite and other components are added into the polyvinyl chloride (PVC), so that the composite material is endowed with stable lubricity and antibacterial property, and meanwhile, the mechanical property of the composite material is also improved.

The technology relates to incorporating video laryngoscope data into the electronic medical record (EMR) of a patient. An example intubation system includes a patient terminal, a wireless hub, and a video laryngoscope. In an example method, the patient terminal accesses the electronic medical record of the patient; and receives, from the wireless hub wirelessly coupled to a video laryngoscope, intubation data generated by the video laryngoscope during an intubation procedure of a patient. The intubation data includes video data captured by the video laryngoscope and metadata for the video data generated by the video laryngoscope. The patient terminal then concurrently displays at least a portion of the intubation data with fillable fields of the electronic medical record; receives at least one interaction with the electronic medical record during the concurrent display; and stores the electronic medical record based on the at least one interaction.

The utility model discloses an I-shaped hypopharyngeal retaining laryngoscope. The laryngoscope comprises a handle part, a main body part, an endoscope tube and a suction tube, the main body part comprises an upper plate body, a lower plate body and a connecting plate, the upper plate body and the lower plate body are oppositely arranged up and down, the connecting plate is vertically connected between the upper plate body and the lower plate body to form the I-shaped main body part, and the rear end of the upper plate body extends backwards to exceed the lower plate body and bends and tilts upwards; a handle part is fixedly arranged on the upper side of the upper plate body, an endoscope tube and a suction tube are fixedly arranged on the lower side of the upper plate body, and the endoscope tube and the suction tube both extend along the upper plate body and bend and tilt upwards as well. According to the scheme, the I-shaped hypopharynx supporting laryngoscope can easily expose the hypopharynx, the tongue root, the epiglottis and other parts, the special endoscope channel can release the operation space on the two sides of the I shape to the maximum extent, and therefore two mechanical arms of a surgical robot can stretch into a surgical cavity at the same time to conduct operation.

The invention relates to a rigid, curved laryngoscope. The laryngoscope is characterised in that it has a rigid, curved body, a light source and image-capturing unit integrated in the body and two channels, each suitable for accommodating a flexible surgical instrument, which is suited for a mechanical intervention at the operation site. The laryngoscope according to the invention can be simply and economically produced and is suited for repeated use. It is also mechanically stable and can be handled quickly and easily.

A laryngoscope enhancement system (LES) and an intubation system including an LES are provided. The LES includes a holder and a video stylet. The holder includes an adjustable mount to releasably secure an electronic device with a display, and an end cap configured to removably attach the holder to an upper end of a laryngoscope handle. The video stylet includes a connector removably attachable to the electronic device, a flexible segment, a malleable segment and a video camera. The LES may include wireless communication capabilities.

The invention discloses a tracheal intubation path feature extraction method and device based on AI analysis, and relates to the technical field of intelligent medical robotics.The method comprises the steps that an optical flow method is used for preprocessing an input matrix, an epiglottis deformation displacement field is calculated, the epiglottis deformation displacement field is imported into ANSYSMechical for finite element analysis, and a three-dimensional tracheal path topological graph is obtained; carrying out fluid-solid mechanical joint simulation on the three-dimensional air pipe path topological graph by adopting a COMSOLMultiphysics multi-physics coupling solver, so as to obtain a lifting parameter; an impedance control instruction is generated according to the lifting parameters, and the cooperative mechanical arm is driven to execute the impedance control instruction; and on the basis of the multi-modal data of the laryngoscope after the impedance control instruction is executed, updating the material parameters of ANSYSMechical through a strategy gradient algorithm. According to the method, the problem that optimization of closed-loop feedback driving parameters is missing is solved through a target function gradient direction and step size zooming mechanism.

A laryngoscope and a method of using the laryngoscope in intubating mammals are described. The laryngoscope comprises a pen light grip for holding the laryngoscope like a pen, and an elongate probe attached coaxially via probe grip, wherein the elongate probe (14) is elongate and tapered such that the distal tip of the probe has the smallest cross section profile as compared to any cross section of the probe taken between the tip of the probe and the portion of the probe proximate the probe grip, and where the probe is curved and deflects away from the axis of probe and pen light grip and is substantially made from a material that transmits and or scatters light. The tip angle of deflection is 50 degrees and the deflection measured in mm is 50 mm. The tip 22 is twice as high as it is wide and, at the near tip point, the cross sectional profile is narrower than it is tall.

The utility model discloses a video laryngoscope which comprises a handle, an extending mechanism and a shooting mechanism, and a display mechanism is arranged at one end of the handle. The stretching-in mechanism is arranged at the other end of the handle and comprises an angle adjusting assembly and a telescopic assembly, the angle adjusting assembly is used for adjusting the angle of the stretching-in mechanism based on the handle, and the telescopic assembly is used for adjusting the length of the stretching-in mechanism; the shooting mechanism is installed at the end, away from the handle, of the stretching-in mechanism. By means of the mode, the angle and the length of a video laryngoscope examination part are adjusted, so that the device can cope with examinations of different throat depths and different positions of a patient, and the situation that the device is inserted into the throat of the patient at a single length and a fixed angle to injure the patient is avoided.