401results about How to "Avoid misdiagnosis" patented technology

In a disease case DB, disease case images are classified by disorder and registered. In a feature quantity DB, a feature quantity (second feature quantity) of each disease case image classified by disorder is registered. A server compares a feature quantity (first feature quantity) of a lesion site included in a diagnosis target image, with the second feature quantity on a disorder-by-disorder basis, retrieves representative disease case images based on a comparison result from the disease case DB on a disorder-by-disorder basis, and provides a user with retrieved representative disease case images. Therefore, the user can obtain disease case images useful for determining a disorder or statistical information and the like regarding the disorder during image diagnosis based on the diagnosis target image.

The invention discloses an online cognitive assessment system and an assessment method, and belongs to the field of assessment systems. The online cognitive assessment system comprises a terminal platform, wherein the terminal platform comprises a processor module, a power supply module, a man-machine interaction module, a communication module, a recording module, an assessment module, a storage module, a calculation module and an output module; the power supply module, the man-machine interaction module, the communication module, the recording module, the assessment module, the storage module, the calculation module and the output module are connected with the processor module respectively. Online cognitive diagnosis is carried out through reading and processing information of each module. By adopting the online cognitive assessment system and the assessment method, rapid and accurate assessment and good accuracy can be realized, and information is updated in real time.

An IGBT (insulated-gate bipolar transistor) stuck-open fault diagnosis method for a three-phase inverter bridge of a frequency converter belongs to the technical field of IGBT fault diagnosis of three-phase inverter bridges and solves problem that misdiagnosis is caused in instant load or instant unload when stuck-open fault of IGBTs of an inverter bridge is determined through the Park vector method. The method comprises the following steps: firstly, three phase currents ia, ib and ic of a motor stator used for speed regulation and controlled by the frequency converter are collected; secondly, the three phase currents ia, ib and ic are transformed through discrete Fourier transform to obtain cosine component aj, k and sine component bj, k of direct current component amplitude and fundamental component amplitude of the three phase currents ia, ib and ic; thirdly, the direct current component amplitude is normalized through the fundamental component amplitude to obtain a direct current component normalization value hj; fourthly, a fault phrase of the three-phase inverter bridge is determined according to the direct current component normalization value hj; and then whether the faultphrase is in an upper transistor or a lower transistor is determined. The invention is suitable for fault diagnosis of three-phase inverter bridges.

A diagnostic apparatus is combined with a high-pressure fuel supply system including a high-pressure fuel pump, a fuel rail, injectors, and a fuel pressure measuring unit for measuring fuel pressure in the fuel rail. The diagnostic apparatus is capable of detecting troubles in the high-pressure fuel pump and injectors and of discriminating between a trouble in the high-pressure fuel pump and a trouble in the injectors includes. The diagnostic apparatus includes: a pump discharge component calculating unit 111 for determining fuel pressure variation synchronous with the operation of the high-pressure fuel pump from the fuel pressure, an injection component calculating unit 112 for determining fuel pressure variation synchronous with the operation of the injectors, a rotating speed component calculating unit 113 for determining fuel pressure variation synchronous with the rotation of a drive shaft for driving the high-pressure fuel pump, a control component calculating unit 114 for determining fuel variation during a control operation for adjusting the fuel pressure to a predetermined desired fuel pressure, and a direct current component calculating unit 115 for calculating a direct current component of fuel pressure variation. The diagnostic apparatus decides whether or not the high-pressure fuel system is malfunctioning on the basis of results of calculation made by those calculating units.

A plug of a power cord of a block heater which is mounted to a cylinder block of an engine, is connected to a household power receptacle to energize the block heater during an engine stoppage in cold climate. Thus, an engine coolant is kept warm to prevent freeze. Existence/nonexistence of the energization to the block heater during the engine stoppage is determined based on a behavior of coolant temperature or a behavior of engine rotation speed immediately after an engine start. If it is determined that the energization to the block heater exists, abnormality diagnosis of a cooling system is prohibited or a condition for the abnormality diagnosis is corrected and estimation coolant temperature is corrected.

The invention discloses an endoscopic image lesion detection method based on based on fusion of global and local features. According to the method, supervised learning and multi-instance learning are combined, two levels of lesion detection mechanisms are established, the rate of missing detection is farthest reduced under the condition that the lesion detection accuracy and reducing labor intensity of doctors are ensured at the same time, and missed diagnosis or error diagnosis due to that a lesion image is mistakenly identified to a non-lesion image is avoided. According to the endoscopic image lesion detection method based on based on fusion of global and local features, only whether a trained image has lesion or not needs to be labeled and a specific lesion region does not need to be labeled when local features are extracted for training a classifier due to introduction of the multi-instance learning, thus the method is more convenient and easy in practical application than conventional method.

The invention provides a method for locating and identifying a lesion of a medical image, a device, an equipment and a storage medium. The method comprises the following steps of obtaining a target image, wherein the target image is a medical image to be localized and identified; preprocessing the target image to obtain a preprocessed image; inputting the pre-processed images into the pre-established lesion location recognition model, and obtaining the corresponding lesion location indication map of the target image and the lesion classification in the target image; obtaining the lesion location recognition model by training medical images with the lesion classification labeled; The lesion location recognition model based on that present application can automatically detect a lesion from amedical image, the location of the lesion is given, which not only saves manpower and reduces the time consumed in identifying and locating the lesion, but also avoids the misdiagnosis, missed diagnosis, locating and identifying lesion caused by manual locating and locating the lesion, which can also assist doctors to carry out rapid and accurate analysis, and improves the diagnosis efficiency and accuracy of doctors.

The invention discloses an open-circuit fault diagnosis method for the drive system of a double-winding fault-tolerant permanent-magnet motor. According to the method, the collected phase current of a motor is respectively subjected to the converting and processing process by a low-pass filter, a Clarke convertor, a Park vector processor, a normalization processor, an average value calculator, an absolute value calculator and an absolute value averaging processor, so as to obtain the average value of the normalized phase current of the motor and the average value of the absolute value of the normalized phase current of the motor. With the average value of the normalized phase current of the motor and the average value of the absolute value of the normalized phase current of the motor as a basis, fault diagnostic variables for the system are constructed, so that the open-circuit fault of the drive system of the double-winding fault-tolerant permanent-magnet motor can be detected and positioned in real time. Based on the above method, no extra current sensor is required, so that the method is simple, feasible and high in reliability. Based on the combined utilization of the average value of the normalized current and the average value of the absolute value of the normalized current, the incorrect diagnosis caused by load sudden change and other reasons during the conventional diagnosis process can be avoided. Meanwhile, the diagnosis time is greatly reduced. Therefore, the open-circuit fault of the drive system can be effectively detected and positioned in real time.

The invention discloses an auxiliary diagnosis method based on depth learning. The method comprises steps that S1, segmentation for raw corpus data is carried out to establish a word embedding query table; S2, a training set is generated based on key characteristic fields of electronic case data, the word embedding query table is utilized for digitalization, the convolutional neural network is utilized to generate an auxiliary diagnosis model; and S3, key characteristic fields of a newly-inputted electronic case are extracted, digital conversion is carried out through the word embedding querytable, the auxiliary diagnosis model is utilized for matching, and the matched diagnosis result is outputted. The invention further provides an auxiliary diagnosis system based on depth learning. Thesystem comprises a corpus data extraction module, a word embedding query table construction module, a historical electronic case data extraction module, a new electronic case data extraction module, asegmentation module, an electronic case digital module and an auxiliary diagnosis module. The method is advantaged in that the diagnosis result is timely and accurate, and doctors are effectively facilitated to carry out rapid condition diagnosis.

Distance information between an observation-target and each pixel of an imaging device is obtained in an endoscope apparatus. The endoscope apparatus includes a scope unit having an illumination-light illuminating unit and an imaging device, and a spectral image processing unit that generates a spectral estimation image signal of a predetermined wavelength by performing spectral image processing on an image signal output from the imaging device. The illumination-light illuminating unit illuminates the observation-target with illumination-light, and the imaging device images the observation-target by receiving light reflected from the observation-target illuminated with the illumination-light. The spectral image processing unit generates the spectral estimation image signal of the predetermined wavelength greater than or equal to 650 nm, as a spectral estimation image signal for obtaining distance information. Distance information representing a distance between the observation-target and each of the pixels is obtained based on the spectral estimation image signal for obtaining distance information.

The invention relates to a fault diagnose method for variable load machine. The fault of the variable load machine is not easy to diagnose automatically, because the vibration value is compared with the alarm threshold set in advance in the traditional diagnose method, but the load is positively correlated to the vibration value; as a result, misinformation and missing report occurs if the traditional method is applied to the variable load machine. The method of the fault diagnose method is that the vibration signal of important parts of the machine and the power signal of the machine are collected simultaneously; then the vibration signal and the power signal are disposed with statistical regression analysis in order to elicit regression equation; the alarm threshold corresponding to the instant power of the machine is worked out according to the equation and the instant power of the machine; then the vibration and the alarm threshold are compared; alarm is given if the vibration surpasses the threshold; the alarm threshold varies with the power the machine. The fault diagnose method for variable load machine is mainly applied to the development and design of the diagnosis system of variable machines (such as the variable flow rate pump used in industry, variable power motor, and wind power generator).

The invention relates to an integrated driving service system, which comprises a mobile phone APP, an intelligent driving diagnosis module, an intelligent driving service platform and an intelligent driving service center, wherein the mobile phone APP is loaded on a mobile phone of a vehicle owner; the intelligent driving diagnosis module is integrated on an intelligent driving diagnostic instrument, the intelligent driving service platform is stored with client serial numbers and intelligent driving diagnostic instrument serial numbers which are sequentially arranged according to the time; and the intelligent driving service platform comprises a diagnostic control, a processing server, a storage server and a communication module. The integrated intelligent driving service system takes an intelligent driving vehicle networking national operation service network as a support, provides functions of one-key navigation, remote diagnosis, security setting, emergency rescue, vehicle removing message passing and maintenance.

The invention provides an intelligent endoscope image analysis method and system. The method comprises steps as follows: acquiring an image and auxiliary information associated with the image; analyzing the image and performing classified marking on the image with a focus zone; extracting the focus zone of the image, comparing the focus zone with a focus feature database corresponding to classified marking of the image, and outputting focus feature information of the focus zone; receiving and displaying focus feature information of the focus zone. Disease feature information contained in the image can be judged by acquiring the image and processing the focus zone of the image and a focus zone selected in an interaction mode, auxiliary diagnosis information is provided for medical diagnosis, and missing diagnosis and misdiagnosis caused by insufficient professional experience of grass-roots doctors can be avoided.

The invention discloses a psychiatric disease auxiliary diagnosis system based on virtual reality technology and physiological parameter detection. The system comprises a patient terminal device and adoctor terminal device; the patient terminal device comprises a physiological parameter monitoring module, a VR/AR interaction module and a data acquisition and processing module; the VR/AR interaction module induces a user to generate special behaviors and mood fluctuations by displaying specific scenes to the user; the physiological parameter monitoring module is used for acquiring various physiological parameter data of the user in real time; acquired data are transmitted to the doctor terminal device through the Internet; the doctor terminal device includes a real scene acquisition module, a communication and control module, a tracking module and a display module, wherein the display module displays various indicators and behavior interaction modes of the user; and therefore, auxiliary diagnosis can be completed. According to the system, the VR/AR technology and physiological parameter monitoring are combined, and therefore, diagnostic accuracy can be improved, and the preventionand early treatment of psychiatric diseases can be benefitted.

The invention relates to the technical field of medical systems, in particular to an intelligent analysis system of medical big data and an application method. The intelligent analysis system comprises an integrated data providing module, a data analysis and processing module, a patient information platform, a hospital diagnosis platform and a database server, wherein the integrated data providingmodule is used for being connected with the internet to obtain drugs, food and disease-related information; the data analysis and processing module is used for analyzing and extracting effective dataof the integrated data providing module with the neural network algorithm, and acts on the patient information platform and the hospital diagnosis platform; the patient information platform is used for providing medical services for patients according to the information of the integrated data providing module; the hospital diagnosis platform is used for providing auxiliary information for diagnosis of doctors according to the integrated data providing module; the database server is used for data accessing. The invention also discloses the application method with the intelligent analysis system. The intelligent analysis system of medical big data and the application method can effectively assist in treatment of the patients and diagnosis of the doctors.

The invention discloses a network construction method and system for thyroid tumor cytology smear image classification. According to the system, an intensive learning method is used to find an existing convolutional neural network which is most suitable for thyroid tumor cytology smear image classification. The specific process of the intensive learning method comprises a step of generating a convolutional neural network by using a circulating neural network, a step of training the convolutional neural network by using a thyroid tumor cytology smear image training set, a step of verifying theaccuracy of the trained convolutional neural network by using a thyroid tumor cytology smear image verification set, setting an accuracy threshold, and determining whether the accuracy is higher thanthe threshold, and a step of taking a convolutional neural network with highest accuracy as a preliminary convolutional neural network and training the network again. The purposes of constructing theconvolutional neural network with high accuracy to assist a doctor in the diagnosis of thyroid tumors and improving the accuracy of diagnosis are achieved.

The invention provides a fast multiplex PCR identification diagnosis detection method of invasive fungus infection based on cfDNA (cell free DNA). The method can be used for identifying the invasive infection caused by clinic common and high-incidence Candida albicans, Candida tropicalis, Candida parapsilosis, Candida krusei, Candida glabrata and Aspergillus fumigtus. An amplification primer is designed according to characteristic genome segments of each fungus category and species; a detection fluorescence probe of a strain can be distinguished according to the amplification segment design; the real time PCR can be performed on a sample to be tested; high sensitivity of nested PCR and high specificity and multi-target performance advantages of multiple fluorescent hybrid probe PCR are integrated for identifying the fungus strain. The invention also provides a PCR diagnosis kit for the invasive fungus infection and application thereof.

The invention relates to a fault diagnosis method of a lithium ion battery sensor of an electric vehicle based on an observer, and belongs to the technical field of battery management. The method comprises the following steps: determining parameters of a lithium ion battery, and establishing an electrothermal coupling dynamic model of the lithium ion battery of the electric vehicle; performing anopen circuit voltage test and an HPPC experiment on the measured battery to obtain characteristic parameters of the battery under different ambient temperatures; establishing a relationship between battery OCV and SoC, and identifying the parameters in the electrothermal coupling dynamic model by using a recursive least square method with a forgetting factor to obtain a quantitative relationship among the battery parameters, the ambient temperatures and the battery SoC; and importing current, a voltage and a temperature sensor measured value into a fault diagnosis and separation algorithm of the lithium ion battery based on the observer, estimating a quantity of state through an extended Kalman filter algorithm to generate a residual, and performing residual evaluation by using a CUSUM test method, and finally achieving fault diagnosis and separation of the lithium ion battery sensor according to combined response conditions of different residuals.

The invention relates to a method for diagnosing a differential pressure sensor which determines a differential pressure across a arranged in an exhaust section exhaust gas treatment unit of an exhaust gas purification system of an internal combustion engine and which is connected to a front connection to the exhaust line prior to the exhaust gas after treatment unit and a rear connection to the exhaust line downstream of the exhaust gas after treatment unit wherein the diagnosis is made based on a comparison of a measured temporal differential pressure gradient the measured differential pressure due to a change in exhaust pressure before the exhaust gas after treatment unit with an expected temporal differential pressure gradient an expected differential pressure . It is envisaged that a correlation between a profile of the measured differential pressure gradient with a gradient of the expected differential pressure gradient is determined and that, for a high correlation to an intact differential pressure sensor with intact terminals and at a low correlation to a faulty differential pressure sensor or to one or two defective terminals of the differential pressure sensor is closed. The invention further relates to a diagnostic unit for carrying out the inventive method. The method and diagnostic unit enables the reliable detection of various errors of a differential pressure sensor.

A failure diagnosis apparatus comprises a controller that is configured to execute a failure diagnosis process of the internal combustion engine based on a predetermined diagnosis requirement. The diagnosis requirement in a case where engine-operation-electric-power supply is executed is made different from the diagnosis requirement in a case where engine-normal-operation is executed such that a failure of the internal combustion engine in the case where the engine-operation-electric-power supply is executed is less likely to be detected or the failure of the internal combustion engine is less likely to be recognized by a driver than in the case where the engine-normal operation is executed.

The invention provides a fault detection method, a computer readable storage medium, an indoor unit, and an air conditioner. The fault detection method is used for the indoor unit having at least onetemperature sensor and comprises the following steps of: acquiring at least one temperature value determined by the temperature sensor; determining the characteristic quantity corresponding to the heat exchange effect of a heat exchanger in the indoor unit according to the at least one temperature value and the air volume of the indoor unit; and determining the fault state of the indoor unit according to the relationship between the characteristic quantity and the characteristic range. According to the technical solution, the characteristic quantity corresponding to the real-time heat exchangeeffect of the heat exchanger of the indoor unit can be determined through the internal temperature value of the indoor unit obtained by the temperature sensor and the corresponding air volume; the fault state can be quickly and accurately judged; and the detection accuracy is improved.