40results about How to "Objective diagnosis" patented technology

The invention discloses a depression evaluating system and method based on a heart rate variability analytical method, particularly a depression evaluating system and method in a perinatal period. The depression evaluating system comprises a data storage module used for storing electrocardio and pulse wave signals, a peak detecting module used for acquiring a peak point sequence of recording data, a data correcting module used for acquiring sinus beat NN interval sequence, a heart rate variability curve acquiring module used for acquiring a heart rate variability curve, an HRV analyzing module conducting time domain analysis, frequency domain analysis and nonlinear analysis, a feature parameter selecting module used for selecting a feature parameter from HRV parameters, a modeling module used for obtaining a perinatal period depression classification model, and a model applying module used for inputting the data of a testee into the classification module to obtain a depression degree. By means of the depression evaluating system and method based on the heart rate variability analytical method, degree quantitative evaluation of perinatal period depression is achieved, a scientific research method of the depression based on the technical field of physiological information examination is enriched, a test is simple and practicable, medical resources can be effectively saved, and good clinical practicality is achieved.

Systems and methods for improving quality assurance in pathology using automated quality assessment and digital image enhancements on digital slides prior to analysis by the pathologist are provided. A digital pathology system (slide scanning instrument and software) creates, assesses and improves the quality of a digital slide. The improved digital slide image has a higher image quality that results in increased efficiency and accuracy in the analysis and diagnosis of such digital slides when they are reviewed on a monitor by a pathologist. These improved digital slides yield a more objective diagnosis than reading the corresponding glass slide under a microscope.

The invention relates to pulse signal processing for pulse diagnosis in traditional Chinese medicine (TCM). A TCM pulse diagnosis device according to the invention comprises an input unit, a processing unit and a display terminal, wherein the input unit is used for receiving user input; the processing unit is used for determining the state of pulse condition elements according to characteristic parameters of a pulse waveform of an examined object; and a display screen of the display terminal consists of a first region for displaying the pulse waveform of the examined object, and a second region for displaying the state of the group of pulse condition elements of the examined object. By means of displaying the waveform of pulse signals and the state of the pulse condition elements on the display screen at the same time, a professional can acquire firsthand information of the pulse signals simply and clearly. In addition, the provided season and time when the pulse signals are acquired ensure that the professional can make a more complete diagnosis result. Furthermore, by means of mapping the characteristic parameters of the pulse signals, of which the values are obtained continuously, into the discrete state of the pulse condition elements, a transformed signal processing result is in better conformity with the thinking mode of the TCM diagnosis, so that the usage of the professional is facilitated.

The invention belongs to disease detection kit, and concretely relates to a kit for auxiliary diagnosis of Kawasaki disease by using miRNA as a biological label. The nucleic acid label is hsa-miR-223-3p, and the kit includes a primer subjected to a real-time quantitative polymerase chain reaction (RT-qPCR) for hsa-miR-223-3p. The kit can combine blood routine examination, high-sensitivity C reactive protein, erythrocyte sedimentation rate and cardiac ultrasonography, and is conducive to auxiliary diagnosis of Kawasaki disease and prediction damage of coronary artery.

An application of three-dimensional photoacoustic imaging in a breast tumor scoring system includes the following steps: (1) image information of breast tumor is collected by photoacoustic / ultrasonicdual-mode imaging in vitro; (2) the collected image information is analyzed and morphological scoring and functional scoring are performed respectively; and (3) by combining the results of morphological scoring and functional scoring, a comprehensive score is obtained and whether the breast tumor has a malignant tendency result or not is judged; and if one or all of the morphological scoring or functional scoring are judged as malignant tendency, the tumor is considered as malignant tendency. More stable quantitative results can be provided through three-dimensional tumor imaging. In addition,compared with single breast three-dimensional photoacoustic imaging, a tumor area is depicted by ultrasound imaging, the external and internal characteristics of the tumor can be analyzed respectively, and the diagnostic sensitivity and specificity are improved. In addition, malignant and benign tumors are distinguished based on the critical value of oxygen saturation (SO2), and the method is more convenient, highly repeatable and objective in diagnosis.

The invention discloses a Ki67 cell nucleus counting method and system based on pathological immunohistochemistry, and the method comprises the steps: placing a pathological section after Ki67 staining under an optical microscope, and collecting an image of the pathological section after Ki67 staining through visual detection equipment CCD; obtaining a Ki67 negative cell RGB image and a Ki67 positive cell RGB image; carrying out intercellular substance interference filtering on the RGB image to generate a binary image of Ki67 negative cells and a binary image of Ki67 positive cell RGB; carrying out element marking on the binary image, and calculating the number and indexes of connected regions of the binary image; calculating the area of each connected region, taking a standard cell connected region as a reference form, and filtering the connected region with the area smaller than the reference form; segmenting the adherent cells according to the standard that the area of the connectedregion is equal to twice of the reference form; marking Ki67 positive cells and Ki67 negative cells according to the index of the final connected region, and performing counting.

Method and laser processing device to process tissue. In a general aspect, the method to process tissue may include applying a photosensitizer into an area surrounding a region of the tissue to be processed, and irradiating the region of the tissue to be processed with the pulsed processing laser beam, the laser beam emitting laser pulses with a temporal full width at half maximum in a range between about 100 femtosecond and about 1 nanosecond. In another general aspect, the laser processing device to process tissue may include a laser radiation source to provide a pulsed processing laser beam providing emitting laser pulses, a laser beam decoupling unit to decouple the laser beam towards a region of the tissue to be processed, and an output device to output a photosensitizer in a direction of an area surrounding the region of the tissue to be processed, the output device being connected to the decoupling unit.

The invention discloses a transformer fault diagnosis method based on deep learning, and belongs to the field of transformer fault diagnosis. The method comprises the following steps: firstly, carrying out duplicate removal and abnormal value processing on concentration data of fault characteristic gases H2, CH4, C2H2, C2H4 and C2H6 collected by an analysis method of dissolved gas in oil, fillingmissing values by using a random forest method, and then carrying out normalization processing on the data to form a training set sample and a test set sample; establishing a three-layer stack type sparse noise reduction auto-encoder model, and rewriting a cross entropy loss function in a traditional classification model into a Focal loss function; according to the method, hyper-parameters are determined through class sample weights, white Gaussian noise is added into input, an auto-encoder is made to fully extract effective features, and therefore an effective feature extraction model is obtained, and a Softmax classifier is used for outputting a diagnosis result of the model. Compared with the existing methods such as a three-ratio method, an SVM and a BP neural network, the transformerfault diagnosis method provided by the invention has good diagnosis performance, and the accuracy of transformer fault diagnosis is effectively improved.

The invention discloses a diagnosis assessment system for post-traumatic stress disorder. The system comprises a functional imaging module used for obtaining resting-state functional imaging data from the brain of a detected individual, an attribute extraction module used for extracting resting-state functional image attribute data from the resting-state functional imaging data obtained by the functional imaging module, a post-traumatic stress disorder characteristic sample library module used for storing historical resting-state functional image attribute data of different post-traumatic stress disorder levels, and a post-traumatic stress disorder assessment module used for comparing the resting-state functional image attribute data with the historical resting-state functional image attribute data to obtain a post-traumatic stress disorder level that the resting-state functional image attribute data belongs to. A quantitative index can be obtained for objectively and accurately assessing the post-traumatic stress disorder level of the detected individual, thereby guiding medical personnel to perform diagnosis, management and treatment on patients.

The invention relates to a graded diagnosis method for an insulating state of power transformer oiled paper. The method comprises the following steps of S1, establishing a recovery voltage database ofthe transformer; S2, according to the recovery voltage database, performing insulating grade dividing by means of fuzzy C mean value clustering; S3, according to the recovery voltage database, calculating the weight of an evaluation index based on a scale expansion method; and S4, according to the insulating grade dividing obtained in the S2 and the weight of the evaluation index obtained in theS3, diagnosing the insulating grade of the to-be-evaluated transformer based on an improved ideal diagnosis method. The graded diagnosis method can realize graded diagnosis to the insulating state ofthe power transformer oiled paper, and the diagnosis result accords with the actual condition of the transformer. The graded diagnosis method has high accuracy, high reliability and high engineering application prospect.

The invention relates to a cerebrovascular quantitative analysis method based on a skeleton line. By use of the quantitative analysis method based on cerebrovascular DICOM data, blood vessels of a brain are segmented in original data, a Wills ring portion is identified, and a Wills ring skeleton line and a sampling point radius geometric model are obtained by performing Wills ring skeleton ring extraction by use of a skeleton line extraction algorithm. Semantic identification and rule sampling are performed on each segment of the blood vessels on a skeleton, and feature quantity information at sampling points are calculated and stored in a database. Compared to conventional two-dimensional projection image quantitative analysis and blood vessel three-dimensional volume quantitative analysis, the method provided by the invention can obtain a more accurate result. An original discrete skeleton is fitted by use of a B spline curve method, the blood vessel skeleton form is enabled to be continuous, the feature quantity of any point on the blood vessels can be obtained, and a more accurate feature quantity calculation result can be obtained.

The invention relates to a method for evaluating the oil paper insulation micro-water content by utilizing backward elimination multiple regression analysis. The method comprises the following steps:firstly, preparing five groups of oiled paper insulation samples with different micro-water contents, and extracting nine frequency domain characteristic parameters capable of representing the micro-water contents of oiled paper insulation; then establishing a test model of the oil paper insulation micro-water content and multivariate characteristic parameters at different characteristic frequencies by utilizing a backward elimination multivariate parameter regression manner; and finally, verifying the accuracy and credibility of the test model through an example. According to the method, theminimum characteristic parameters are used for evaluating the oil-paper insulation micro-water content to the maximum extent, and therefore, the method for evaluating the oil paper insulation micro-water content by utilizing backward elimination multiple regression analysis is provided.

The invention discloses a full-automatic blood smear morphological analysis system based on machine vision and relates to the technical field of medical instruments. The system comprises an optical system unit, an upper computer software processing unit and a lower computer hardware unit; the optical system unit comprises a biological microscopic imaging system and a CCD biological camera; the upper computer software processing unit comprises a user control interface module, a blood smear image processing module and an upper and lower computer communication module; the lower computer hardwareunit comprises a focusing motion module and an image acquisition motion module; automatic focusing is performed through the optical system unit; a blood smear digital image is collected; blood smear image features are recognized and processed through a machine learning algorithm of the upper computer software processing unit; different types of leukocytes are classified and counted; and a processing result is displayed the a graphical user interface; a monocular microscope is matched with a reflective light source, so that an optical structure is greatly simplified, and rapid imaging is realized. The full-automatic blood smear morphological analysis system is high in working efficiency, high in accuracy and high in automation level.

The invention discloses a deep convolutional neural network-based lung cancer preventing self-service health cloud service system. The system comprises a convolutional neural network used for deep learning and training identification, a segmentation module which segments out a lung region from a CT image based on a full convolutional neural network, a deep convolutional neural network used for lung cancer diagnosis classification, and a self-service health cloud service platform used for performing early prevention and treatment according to an identified suspected lung cancer type. According to the system, the automation and intelligentization level of mobile internet-based lung cancer screening can be effectively improved, more citizens can know and participate in self-service health detection, assessment and guidance, the sensitivity, specificity and accuracy of early lung cancer screening and clinical diagnosis are improved, the lung cancer can be early discovered, early diagnosed and early treated, and the self-health management capability is enhanced.

The invention provides a body fluid detection method and system based on SERS, the detection method comprises a laser correction large light spot integral measurement mode and a rapid spot scanning measurement mode, and the laser correction large light spot integral measurement mode can rapidly obtain stable and repeatable Raman spectrum results; and a fast spot scan pattern can capture low concentrations of disease-related markers in body fluids. Based on the above two measurement modes, the method can realize accurate detection of overall components and differential components of the body fluid. The system provided by the invention comprises a baseline processing method, a spectrum standardization method, an automatic peak searching method and an imaging method, and realizes rapid, objective and large-batch processing of spectrum data and automatic acquisition of difference characteristic peaks. Rapid, stable, high-throughput and low-cost surface enhanced Raman body fluid detection is effectively realized, rapid disease pre-diagnosis can be carried out to replace a traditional body fluid detection method by detecting and analyzing Raman spectrum characteristic information of human body fluid, and high-frequency general survey of large-area crowds is realized.

The invention provides a chronic obstructive pulmonary disease (COPD) diagnostic kit, and belongs to the field of pulmonary disease detection. The invention provides an application of a reagent for detecting the content of GlcAbeta-Cer (d18: 1 / 18: 0) in serum in preparation of a kit for detecting COPD. The invention also provides a corresponding COPD detection kit. According to the invention, rapid auxiliary diagnosis of COPD can be realized by detecting the content of GlcAbeta-Cer (d18: 1 / 18: 0) in serum.

The invention provides a short-wave infrared otoscope device, which comprises an illumination system, a speculum, a lens barrel and a short-wave infrared detector. The lens barrel comprises a lens barrel body and a speculum adapter, wherein the speculum is connected with one end of the lens barrel body through the speculum adapter, and the other end of the lens barrel body is connected with a short-wave infrared detector; the illumination system comprises a light source and an optical fiber, wherein the light source is configured to emit short-wave infrared light, one end of the optical fiberis coupled with the light source, and the other end of the optical fiber is coupled with the speculum adapter; in operation, the light source emits short-wave infrared light, the optical fiber guidesthe short-wave infrared light into the speculum and enters the ear of the object to be detected from a speculum hole, the short-wave infrared light enters the speculum through the diffuse reflection light formed by the ear of the object to be detected from the speculum hole, and finally reaches the short-wave infrared detector to be imaged through the optical system in the lens barrel. Correspondingly, the invention also provides a short-wave infrared otoscope system and a detection method of ear fluid. In that embodiment of the invention, the inside of the ear of the object to be detected canbe better imaged.

The invention provides an application of a Ulexin C detection reagent in preparation of a COPD diagnostic kit, and belongs to the field of lung disease detection. According to the invention, rapid auxiliary diagnosis of COPD can be realized by detecting the content of Ulexin C in serum.

A medical service system comprises: a user client which is used for a user to operate and input identity information and body health related information, and can be set to whether to synchronize all or part of the information to a service cloud for storage or not; and a doctor client, wherein after the user client is synchronized to the service cloud for storage, the doctor client can select an authorization item on the user client to share corresponding information from the service cloud to be matched and displayed by the doctor client, the corresponding information provides reference for thedoctor, and is combined with the current user condition to obtain a diagnosis result through comprehensive diagnosis, and the result is input into the doctor client and is synchronized to the user client through the service cloud. According to the invention, all information of the user can be recorded through the user client, especially, a patient can control disclosure of disease privacy by himself / herself after medical records are electronized, and in addition, records of the same department can be checked in multiple hospitals, so that doctors in the same department of different hospitalscan fully know diseases of the user, diagnosis is more objective, the medical history of the patient is understood more systematically, and clinical disease diagnosis and treatment are facilitated. Through internal classification of the system, the medical history of the patient is clearer, clearer, simpler and more convenient.

The invention discloses a nuclear cataract recognition method and device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: extracting region features of a crystalline lens nuclear region in a sample eye image, extracting shape features of the crystalline lens nuclear region in the sample eye image, and determining target features of the sample eye image according to the region features and the shape features; and based on the target features of the sample eye image, constructing a nuclear cataract recognition model for determining the nuclear cataract level of the to-be-recognized eye image. According to the technical scheme, the lesion features of the crystalline lens nuclear region in the fundus image can be accurately obtained, so that the judgment of the nuclear cataract level is more accurate, a new thought is provided for automatic diagnosis of the nuclear cataract, and an ophthalmologist can be assisted to efficiently, objectively and accurately diagnose the nuclear cataract.

The invention discloses a depression evaluating system and method based on a heart rate variability analytical method, particularly a depression evaluating system and method in a perinatal period. The depression evaluating system comprises a data storage module used for storing electrocardio and pulse wave signals, a peak detecting module used for acquiring a peak point sequence of recording data, a data correcting module used for acquiring sinus beat NN interval sequence, a heart rate variability curve acquiring module used for acquiring a heart rate variability curve, an HRV analyzing module conducting time domain analysis, frequency domain analysis and nonlinear analysis, a feature parameter selecting module used for selecting a feature parameter from HRV parameters, a modeling module used for obtaining a perinatal period depression classification model, and a model applying module used for inputting the data of a testee into the classification module to obtain a depression degree. By means of the depression evaluating system and method based on the heart rate variability analytical method, degree quantitative evaluation of perinatal period depression is achieved, a scientific research method of the depression based on the technical field of physiological information examination is enriched, a test is simple and practicable, medical resources can be effectively saved, and good clinical practicality is achieved.

A gingivitis diagnosis assistance device (20A) is provided with a cross-section data extraction unit (21) for extracting cross-section data in a depth direction of a gingivitis peripheral part from three-dimensional point group data of a mouth front, and a gingivitis diagnosis data generating unit (25) for processing the cross-section data into a format suitable for gingivitis diagnosis and generating gingivitis diagnosis data, the gingivitis diagnosis data generating unit (25) generating, as the gingivitis diagnosis data, a two-dimensional graph in which the left-right direction or the up-down direction of the mouth front is the first axis and the depth direction is the second axis, for example.

The invention discloses a wheat critical nitrogen concentration dilution curve model. The formula is Nc = 5.25 DW<-0. 472> or Nc = 5.309 DW<-0. 47>, wherein Nc is the critical nitrogen concentration value of the dry matter mass of the overground part of the wheat, and DW is the maximum value of the accumulation amount of the dry matter mass of the overground part of the wheat. Nitrogen level tests of multiple varieties are set in different years to find out a theoretical basis for objectively and quantitatively judging the nitrogen nutrition status of wheat plants, the winter wheat critical nitrogen concentration dilution curve model is established, nitrogen fertilizer operation and quantitative regulation in the region are guided according to the model, and a basis is provided for precise fertilization in wheat production.

The invention discloses application of TPI1 protein as a biomarker for detecting respiratory syncytial virus infection in a sample. The invention further provides a kit for diagnosing respiratory syncytial virus infection. The respiratory syncytial virus infection condition in a sample can be rapidly, simply and specifically detected, and the kit has important clinical diagnosis value and clinical significance for early and rapid diagnosis of respiratory syncytial virus infection.

The embodiment of the invention discloses an electronic stethoscope and belongs to the technical field of medical equipment. The problems that a traditional stethoscope has limitation in use and cannot meet the demands of consumers for self-prevention and self-diagnosis are solved. According to the embodiment, the stethoscope comprises an auscultation head, a pickup sensor and an audio plug, wherein the auscultation head makes contact with the body surface to obtain an auscultation sound; the pickup sensor is connected with the auscultation head and used for filtering the auscultation sound and converting the auscultation sound into an electric signal; the audio plug is connected with the pickup sensor through an audio data line and transmits the electric signal to peripheral equipment through connection with the peripheral equipment. The electronic stethoscope can be used without professional medical staff, the consumers can perform auscultation by themselves, and storage is achieved after recording through the peripheral equipment (such as a mobile phone). The consumers track the health states by comparing multiple auscultation sound signals, and therefore the purpose of self-prevention or self-diagnosis is achieved.