1592results about How to "Improve diagnostic accuracy" patented technology

An image of an electro-anatomical map of a body structure having cyclical motion is overlaid on a 3D ultrasonic image of the structure. The electro-anatomical data and anatomic image data are synchronized by gating both electro-anatomical data acquisition and an anatomic image at a specific point in the motion cycle. Transfer of image data includes identification of a point in the motion cycle at which the 3-dimensional image was captured or is to be displayed.

The invention relates to an extraction method for early failure sensitive characteristics based on ensemble empirical mode decomposition (EEMD) and wavelet packet transform. The extraction method for the early failure sensitive characteristics based on the EEMD and the wavelet packet transform includes the following steps: (1), collected original vibration signals of mechanical and electrical equipment are decomposed according to the EEMD, white noise is added, and intrinsic mode function (IMF) components are obtained through decomposition; (2), the sensitive IMF components closely related to failure are chosen, and other irrelative IMF components are ignored; (3), the sensitive IMF components chosen through step (2) are decomposed in an orthogonal wavelet packet mode, and a wavelet coefficient of each node is obtained; and (4), envelopes are extracted from the obtained wavelet packet coefficients by adoption of the Hilbert transform and the Fourier transform, power spectrums are calculated, the power spectrum corresponding to each wavelet packet coefficient is obtained and serves as the early failure sensitive characteristic , and the sensitive characteristics are automatically obtained. Self-adapting signals can be decomposed, the sensitive characteristics can be convenient to obtain automatically, diagnosis precision and speed are improved, and a mechanical and electrical system can be diagnosed quickly, accurately and stably. The extraction method for the early failure sensitive characteristics based on the EEMD and the wavelet packet transform can be applied to the field of mechanical and electrical equipment failure diagnosis.

The invention relates to a fault diagnosis device and method of a fuel cell system. The fault diagnosis device comprises a communication unit, a diagnosis core unit and a man-machine interaction unit and is characterized in that the communication unit is used for receiving the procedure parameters and working condition information of a main controller as well as the single cell voltage information of a monitor unit and sending diagnosis results and various parameters and data to a field remote control monitoring center and an upper computer; the diagnosis core unit is used for detecting and positioning the faults of the sensor, actuator, controller, monitor unit and galvanic pile of the fuel cell system through the formulated diagnosis strategy; and the main-machine interaction unit is used for displaying, setting, clearing and modifying the diagnosis results and providing maintenance suggestions and measures. By considering the electrochemical reaction mechanism of fuel cells, combining the knowledge and experience of experts and adopting a multisensor information fusion method, the device can be effectively applied to the long-range, short-range, off-line and online fault diagnosis of the fuel cell system, thus the fault diagnosis accuracy and maintainability are improved.

The invention discloses a computerized auxiliary diagnosing method for malignant tumor in early stage based on deep learning algorithm. According to the invention, a deep convolution neural network is used to extract the high-level characteristics of an image layer by layer so that the obtained characteristic dimensions become smaller and smaller. To realize the dimension matching between an outputted probability predicting image and a pre-segmented image, the method uses the reverse convolution network to expand the dimensions of the characteristic image so as to obtain a dimension-consistent probability predicting image. The network generated probability predicting image extracts the binarization of the predicting image through the training of a softmax classifier to finally obtain the segmentation result of the prostate tissue. To some extent, the method effectively increases the accuracy and efficiency for doctors to diagnose prostate diseases.

An abnormality diagnosis device used for a machine apparatus having a part rotating and sliding relative to a stationary member is provided with a detection section (31) and a signal processing section (81). The detection section (31) is fixed to the part rotating or sliding or to the stationary member and has a vibration sensor (32) and a temperature sensor (33). The signal processing section (81) determines the condition of the part based on a signal detected and outputted by the detection section (31). The signal processing section (81) determines whether there is an abnormality in the part, or whether there is an abnormality in the part and the degree of damage of the part.

A Deep Belief Network (DBN) feature extraction-based analogue circuit fault diagnosis method comprises the following steps: a time-domain response signal of a tested analogue circuit is acquired, where the acquired time-domain response signal is an output voltage signal of the tested analogue circuit; DBN-based feature extraction is performed on the acquired voltage signal, wherein learning rates of restricted Boltzmann machines in a DBN are optimized and acquired by virtue of a quantum-behaved particle swarm optimization (QPSO); a support vector machine (SVM)-based fault diagnosis model is constructed, wherein a penalty factor and a width factor of an SVM are optimized and acquired by virtue of the QPSO; and feature data of test data are input into the SVM-based fault diagnosis model, and a fault diagnosis result is output, where the feature data of the test data is generated by performing the DBN-based feature extraction on the test data.

The present invention relates to multimodal spectroscopy (MMS) as a clinical tool for the in vivo diagnosis of disease in humans. The MMS technology combines Raman and fluorescence spectroscopy. A preferred embodiment involves diagnosis cancer of the breast and of vulnerable atherosclerotic plaque, esophageal, colon, cervical and bladder cancer. MMS is used to provide a more comprehensive picture of the metabolic, biochemical and morphological state of a tissue than afforded by either Raman or fluorescence and reflectance spectroscopies alone.

A plurality of electrodes for measuring electrocardiogarphic waveforms are attached on body surface positions that constitute a subset of the standard 12-lead system. The measured electrocardiogarphic waveforms of said subset of said standard 12-lead system are used to calculate the electrocardiogarphic waveforms of remaining leads in the said standard 12-lead system. The measured and calculated electrocardiographic waveforms are synthesized to form a standard 12-lead electrocardiogram. The invention is capable of monitoring the 12-lead electrocardiogram with reduced number of electrodes, wherein a portion of waveforms are directly measured and used as primary information for diagnosing heart disease, and the other portion of waveforms are derived from the measured leads and are used as a secondary information for improving the accuracy of diagnosis. The invention is especially useful in monitoring ischemic heart disease and acute myocardial infarction in cases where mounting and maintaining ten electrodes to obtain 12-lead electrocardiogram is difficult, such as in ambulatory monitoring, long-term monitoring and home monitoring.

The invention provides methods of enhancing tissue sample images by filtering luminance values from an input image and transforming the filtered values to produce an enhanced image for use in diagnostic applications. Preferred methods of the invention provide image enhancement by filtering luminance values of an image that correspond to sample regions that are obstructed or are otherwise not of diagnostic interest, and applying a mathematical transformation based on luminance values from regions that are not filtered out. In this way, image correction is substantially based on portions of the image that are of diagnostic relevance.

The invention discloses a thyroid tumor pathological tissue section image classification method and a thyroid tumor pathological tissue section image classification device. The method comprises the steps of acquiring an original image set of classified thyroid tumor pathological tissue sections; automatically intercepting multiple area images including cells from each original image to serve as asub-image set; using the total or partial sub-image set as a training set; building a preliminary convolutional neural network model; training the preliminary convolutional neural network model by using the training set to acquire a mature convolutional neural network model; and classifying the classified thyroid tumor pathological tissue section images by using the mature convolutional neural network model. Cell nucleuses in the thyroid tumor pathological tissue sections are matched by using Gaussian laplace operator characteristics to find positions of cells, automatic image interception isimplemented in the area with many cells, so that the full-automatic cell image classification and cancer diagnosis are achieved, the workload of a doctor when in checking of the tissue section image can be greatly reduced, and the diagnosis accuracy is improved.

The invention provides an intelligent fault diagnosis method of a numerical control machine tool. The intelligent fault diagnosis method uses fault tree diagnosis as a base, faults are diagnosed by combining a Bayes probability and rule reasoning method, fault cause is found, and maintenance advices are proposed. The intelligent fault diagnosis method includes: firstly extracting fault information from historical maintenance records and machine tool operation instructions, and establishing a numerical control machine tool fault information knowledge base; searching fault trees belonging to a fault position in the fault information knowledge base according to fault characteristic information, calculating probability of occurrence of each fault tree under the current condition if a plurality of fault trees fit conditions, and determining sequence for diagnosing the fault trees according to size of the probability; and finally judging whether all sub-events of top events of the fault trees occur, returning to a fault treatment method corresponding to the events and serving as a solution if the sub-evens are bottom events of the fault trees, otherwise searching sub-events of the events continuously until finding all bottom events fit the fault characteristic information. The intelligent fault diagnosis method of the numerical control machine tool is rapid in diagnosis speed and accurate and reasonable in diagnosis result.

The invention relates to an interactive film interpretation method of a mammary gland CR image. At present, an artificial film interpretation method has low efficiency and accuracy. The method comprises: firstly, reading a mammary gland CR image to be processed; secondly, selecting a region of suspected lesion and computing a scanning line cross section histogram, a distance between two points, a gray scale histogram, a grey scale standard deviation, an area, a circumference, a compactness, an aspect ratio, a distance from edge to center and a fractal dimension; thirdly, performing visual enhancement processing of the region of the suspected lesion by using an image enhancement technique; and finally, searching a lesion having a similar appearance in a lesion database to provide a reference for tumor diagnosis. The method of the invention can conveniently and quickly perform local observation, detailed enhancement and parameter measurement of the mammary gland CR image, improve film interpretation efficiency, reduce working load and improve precision.

The invention discloses a gastrointestinal tumor microscopic hyper-spectral image processing method based on a convolutional neural network, comprising the following steps: reducing and de-noising the spectral dimension of an acquired gastrointestinal tissue hyper-spectral training image; constructing a convolutional neural network structure; and inputting obtained hyper-spectral data principal components (namely, a plurality of 2D gray images, which are equivalent to a plurality of feature maps of an input layer) as input images into the constructed convolutional neural network structure using a batch processing method, and by taking a cross entropy function as a loss function and using an error back propagation algorithm, training the parameters in the convolutional neural network and the parameters of a logistic regression layer according to the average loss function in a training batch until the network converges. According to the invention, the dimension of a hyper-spectral image is reduced using a principal component analysis method, enough spectral information and spatial texture information are retained, the complexity of the algorithm is reduced greatly, and the efficiency of the algorithm is improved.

The invention discloses a composite fault diagnosis method for a diesel engine and a diagnosis system. The fault of a fuel supply system of the diesel engine can be diagnosed based on comprehensive analysis of fuel flow monitoring, exhaust emissions, temperature detection and the like in the state parameter measuring method. In vibration analysis, vibrating signals are measured by a vibration acceleration sensor, noise is removed via empirical mode decomposition (EMD), and then characteristic parameters of the vibration signal acceleration are extracted in a manifold learning method. For failure of a piston cylinder, vibration analysis and fuel analysis are combined, and the degrees of friction and wear are judged according to the vibration amplitude and the content of Fe. The composite fault diagnosis of the diesel engine can be realized based on integration of the fault characteristic information and comparison with typical failure characteristics. The diesel engine fault diagnosis system is developed on the basis of integration of information of multiple characteristics, all characteristic information is fully utilized, the speed and accuracy of diagnosis can be improved, the advantages can be complemented, and the level of diesel engine fault diagnosis can be improved.

The invention discloses an image-based early diagnosis system for senile dementia. The early diagnosis system comprises a brain image collector (1) and a memorizer (2) and is characterized by comprising image preprocessing equipment (3), an image asymmetry characteristic extraction device (4), a consolidator (5), a characteristic vector selector (6), an optimization classifier (7) and an output device. The early diagnosis system has the remarkable effect of being capable of obviously improving the accuracy of early diagnosis of the senile dementia when being applied to the early diagnosis of the senile dementia. The early diagnosis system not only can be used for realizing the clinical application of sequential asymmetry characteristics of anatomical structures in the brain MR (Magnetic Resonance) images in the early diagnosis of the senile dementia, but also is high in diagnosis accuracy and real-time performance.

The invention discloses an ultrasound bone density measuring and analyzing system. The system comprises an ultrasound parameter measuring apparatus, a communication interface and a human machine interaction device, wherein the ultrasound parameter measuring apparatus comprises transmitting unit consisting of a pulse generator, a high-voltage pulse excitation module and a transmitting probe, an ultrasound receiving unit consisting of a receiving probe, a simulation pretreatment module, a gain adjustable amplifier, a phrase comparator, a high-speed ADC and an asynchronous FIFO, and a central processor, a power supply control module and a structural body. the human machine interaction device controls the ultrasound parameter measuring apparatus through the communication interface to measure the width of a calcaneus of a detected person, the transmission speed of an ultrasound wave in the calcaneus, broadband ultrasonic attenuation to calculate the bone intensity indexes and the bone density, so a medical report can be made according to diagnostic standards of osteoporosis and a special data base can be built for long term use. The system adopts wet or dry coupling and other technologies to improve the precision and accuracy of measure and has the advantages of easy carrying, low cost, no damage caused by radiation and can be use in long term monitoring of bone condition of the detected person.

The invention discloses a feature extraction method for a switch action current curve. The method comprises the following steps: obtaining current data of a switch action to generate the switch action current curve; converting the switch action current curve into a projection coordinate system; determining subsections of various switch action sections in the projection coordinate system; and outputting starting points and end points of current value ranges. The method is simple and efficient; the extracted features can provide bases for feature extraction of a diagnosis model; and the selected features can be taken as input parameters of the model. According to a switch fault diagnosis method employing the feature extraction method disclosed by the invention, maintenance information can be timely and accurately provided when a switch is broken down; and on-site maintenance personnel are guided to carry out a maintenance on the faulty switch in a targeted manner, so that the maintenance cost is reduced; the service efficiency of the switch is improved; various adverse effects caused by faults can be reduced; a fault time delay is compressed; a transport delay is further reduced; and the feature extraction method and the switch fault diagnosis method are of important and practical significance in improvement of the safety and the efficiency of a transportation system.

The invention discloses a bearing fault diagnosis method based on transfer learning. The method comprises the steps of selection rules of a training data set and a test data set; auxiliary data normalization transferable degree quantification and a threshold selection method; and the algorithm flow of a TrAdaboost algorithm based on weight adjustment used for bearing fault classification. A thinking strategy that auxiliary data in transfer learning assist target data learning is introduced by aiming at problems of lacking of diagnosis generality caused by the conditions of variable working conditions, unavailable direct measurement and new fault types. According to the method, diagnosis precision of conventional machine learning in a small amount of target data can be enhanced, environmental adaptability of bearing fault diagnosis is enhanced, and the method has potential economic value in the field of bearing fault application under variable working condition loads, new faults and indirect measurement.