34results about How to "Improve the efficiency of clinical diagnosis" patented technology

The invention discloses a method for rapidly selecting and displaying an interested blood vessel in a magnetic resonance blood vessel image. The method comprises the following steps that data are read and displayed, and data of an original image are loaded and the original image is displayed on a terminal; users interact with each other, a starting point is selected in interested areas of the blood vessel selected from the original image, and the growth direction of the blood vessel is determined; the blood vessel is tracked, orientation area growth is carried out from the starting point in the growth direction of the blood vessel to obtain part of the intersected blood vessel areas until all the intersected blood vessel areas are obtained; the selection result is displayed, all the areas of the interested blood vessel are displayed in a three-dimensional rebuilding process. Through the method for rapidly selecting and displaying the interested blood vessel in the magnetic resonance blood vessel image, the interested blood vessel in the magnetic resonance blood vessel image can be rapidly, stably and practically selected.

The invention discloses a test strip for fluorescence immunochromatography of myeloperoxidase. The test strip comprises a base plate, a sample pad, a binding pad, a nitrocellulose membrane and an absorbent pad, and the sample pad, the binding pad, the nitrocellulose membrane and the absorbent pad are assembled on the base plate in a sequential overlapping manner, wherein the absorbent pad and thebinding pad are respectively pressed on two ends of the nitrocellulose membrane in an overlapping manner, and a detection area is formed on the surface of the nitrocellulose membrane; the sample pad is pressed on the binding pad in an overlapping manner, and a myeloperoxidase antibody-fluorescent microsphere compound is immobilized on the binding pad; and the nitrocellulose membrane in the detection area is coated with a detection line formed by a monoclonal antibody for recognizing another epitope of myeloperoxidase and a control line formed by a goat anti-mouse IgG polyclonal antibody. The test strip has the advantages of high sensitivity, high stability, realization of the detection linearity being 3.125-600 ng / ml, no non-specificity, short detection time of 5 min, realization of bedside quick test, and great improvement of the clinical diagnosis efficiency.

The invention discloses an incomplete projection CT image reconstruction method based on VAEGAN. The method comprises the following steps: firstly, a sinusoidal image of complete projection data is used for training a VAEGAN model to obtain a VAEGAN model capable of generating a high-quality sinusoidal image; secondly, using the trained model to predict the missing part of sinusoidal graph of incomplete projection data, the completed projection data can be obtained. Finally, the CT image is reconstructed from the completed projection data using the convolution filtered back projection (FBP) method. The invention can predict the missing projection data and further reconstruct the CT image with high quality in accordance with clinical diagnosis.

The invention discloses a low-dose CBCT image reconstruction method based on a three-dimensional adversarial generation network, and belongs to the technical field of medical image processing. The method comprises the following steps: constructing a three-dimensional adversarial resistance generation network model; training a three-dimensional adversarial resistance generation network model through the sine image and the corresponding projection data; inputting the test image into the trained adversarial resistance generation network model, and predicting the missing part of the sine image of the incomplete projection data to obtain a sine image of complete projection; and reconstructing a CT image according to the sine image of the complete projection data. The method effectively shortens the acquisition time of the cone beam projection data, and improves the clinical diagnosis efficiency.

The present invention discloses a combined detection method of electroencephalogram epilepsy sharp and spike wave discharge based on long short term memory network (LSTM) multi-channels. The combineddetection method comprises the following steps: step 1, filtering input original multi-lead electroencephalogram and eliminating artifacts caused by physiological activities of electrocatdiogram, chewing and swallowing; segmenting processed signals in time domain firstly according to characteristics of target waveform duration characteristics and transforming the signals into a recognition form ofthe subsequent steps; step 2, conducting feature extraction of data of each channel in the segmented signals through the long short term memory network and conducting feature fusion through an adaptive weighted fusion algorithm; and step 3, using results obtained by the feature fusion to classify multi-channel signal fragments through fully connected neural network and finally obtaining classification results of the entire signal at different periods, so as to achieve a purpose of sharp and spike wave discharge detection. The combined detection method can realize a sharp and spike detection effect with higher precision and stronger anti-interference ability under multi-channel signal input.

The invention relates to a method for diagnosing keratoconus cases based on machine learning. According to the method, a support vector machines-recursive feature elimination (SVM-RFE) algorithm and agradient boosting regression tree (ABDT) algorithm are applied to accurate diagnosis of the keratoconus cases. Furthermore for aiming at specific application cases, effective overall plan designing,process designing and algorithm parameter setting are performed. Through test of a large number of clinic instances, the diagnosis accuracy of the method is effectively improved and basically satisfies the requirement for clinic applications.

The invention discloses an abnormal brain connection prediction system, method and device and a readable storage medium, and the method comprises the steps: automatically extracting high-order correlation features in different modes and high-order complementary features between different modes through a deep learning method; and realizing the analysis of abnormal connection of the multi-modal brain network and prediction of different cognitive diseases through an adversarial training method. The method solves the problem that an existing method cannot accurately evaluate the change rule of brain structural morphology and functional connection. According to the method, a prior knowledge guide model is used for learning interpretable characterization, the consistency of different modal characterization distribution is restrained through a paired collaborative discriminator, and then brain graph data is reconstructed for feature codes through a reverse generator and a decoder; and finally, inter-modal and intra-modal high-order correlation features are extracted through a hypergraph perception fusion module, and an adversarial loss function, a reconstruction loss function and a classification loss function are set to guide model learning so as to achieve the purpose of mining the abnormal brain connectivity of the Alzheimer's disease.

The invention provides polypeptide capable of being specifically bound with tuberculosis-positive serum. The polypeptide is one or a combination of A and B, wherein the amino acid sequence of the A is shown as SEQ ID NO: 1; the amino acid sequence of the B is shown as SEQ ID NO: 2. The invention further provides a serological tuberculosis diagnosing kit. The kit contains the polypeptide specifically bound with the tuberculosis-positive serum. The invention further provides a tuberculosis diagnosing kit based on phage display polypeptide. The kit contains a core phage P1 and a core phage P4, wherein the core phage P1 is phage of display polypeptide A; the core phage P4 is phage of display polypeptide B. The polypeptide and the corresponding core phages provided by the invention are high in sensitivity and specificity, and have a good clinical diagnostic value.

The invention discloses a novel coronavirus nucleic acid PCR-colloidal gold immunochromatography detection kit. The kit comprises an amplification reaction solution, a CoV detection solution, a positive reference substance and a negative reference substance, and the CoV detection liquid comprises a specific marker primer aiming at a new coronavirus open reading frame 1ab and a coding nucleocapsid protein N gene, a specific marker primer of a reference gene RNase P and RNase Free ddH2O. According to the kit, after nucleic acid is extracted from a collected cell sample, a specific fragment is amplified under the action of reverse transcriptase and Taq DNA polymerase, then the nucleic acid detection of the new coronavirus is realized by utilizing colloidal gold immunochromatography, in addition, the kit adopts a reference gene RNase P to carry out tracking quality control on sample collection, nucleic acid extraction and PCR amplification processes, and the whole experiment process is ensured to be within a controllable range.

The invention provides a systemic lupus erythematosus (SLE) autoantibody detector which comprises chips and a kit, wherein a porous plate is arranged in the kit; the chips are positioned in the plate holes of the porous plate; reference substances and antigen protein are fixed on the chips according to a dot-matrix array. The detector provided by the invention can shorten the SLE detection time, reduce the detection cost, reduce the serum use for a patient, and improve the clinical diagnosis efficiency of the SLE.

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 present invention provides a Mycoplasma pneumoniae and Chlamydia pneumoniae combined detection reagent card, and a Mycoplasma pneumoniae and Chlamydia pneumoniae combined detection kit and a detection method thereof. The Mycoplasma pneumoniae and Chlamydia pneumoniae combined detection reagent card comprises a shell and a test paper strip, wherein the shell is sequentially provided with a dilution liquid adding hole, a sampling adding hole and a result observation window, the test paper strip comprises a bottom plate, a sample pad, a bonding pad, a nitrocellulose film and a water absorption paper, the sample pad, the bonding pad, the nitrocellulose film and the water absorption paper are sequentially overlapped on the bottom plate, the dilution liquid adding hole and the sample adding hole are corresponding to the sample pad of the test paper strip, the result observation window is corresponding to the nitrocellulose film, and at least a detection line and a quality control line are coated on the nitrocellulose film. According to the present invention, with the reagent card, the kit and the detection method, the one-time combined detection on Mycoplasma pneumoniae and Chlamydia pneumoniae can be achieved, the complete detection is easily achieved, the miss of the detection can be avoided, the detection result can well guide the clinical diagnosis and the correct medication, and the clinical diagnosis efficiency can be improved; and with the combined detection, the sample can be easily saved, and the invasive pain of the detection on the patient can be reduced.

The invention discloses a C-reactive protein and serum amyloid protein A combined detection test strip, a kit and a preparation method of the test strip. The C-reactive protein and serum amyloid protein A combined detection test strip comprises a bottom plate, a sample pad, a combination pad, a reaction pad and a water absorption pad, wherein the combination pad is coated with fluorescent microspheres jointly marked by a CRP antibody and a CRP broadened rabbit anti-antibody, and fluorescent microspheres jointly marked by an SAA antibody and an SAA broadened chicken anti-antibody; and a CRP detection line, an SAA detection line, a CRP widening line and an SAA widening line are formed on the reaction pad. The C-reactive protein and serum amyloid protein A combined detection test strip and the C-reactive protein and serum amyloid protein A combined detection kit containing the test strip can quantitatively detect the content of CRP and SAA in a sample at the same time, are high in sensitivity, good in specificity and high in detection speed, and further have a very wide linear range; and the linear range of CRP is 0.5-600 mg / L, the linear range of SAA is 3-800 mg / L, the operation of repeatedly diluting the sample clinically is reduced, and the clinical diagnosis efficiency is improved.

The invention discloses a mycoplasma genitalium nucleic acid real-time fluorescence PCR detection primer, a probe and a kit. The kit comprises an amplification reaction solution, a mycoplasma genitalium nucleic acid detection solution, a positive reference substance and a negative reference substance, wherein the mycoplasma genitalium nucleic acid detection liquid comprises specific primers and probes aiming at mycoplasma genitalium and a human RNase P gene, the sequences of the primers aiming at the mycoplasma genitalium are as shown in SEQ ID NO.1 and SEQ ID NO.2, and the sequence of the probe aiming at the mycoplasma genitalium is as shown in SEQ ID NO.3. According to the primer, the probe and the kit for real-time fluorescence PCR detection of the mycoplasma genitalium, provided by the invention, the mycoplasma genitalium can be rapidly, accurately and sensitively detected, the repeatability of an experimental result is good, the precision is high, the detection time period is short, and the detection can be completed within 70 minutes as short as possible. Therefore, the detection time is greatly saved, and the clinical diagnosis efficiency can be accelerated.

The present invention provides a polypeptide that can specifically bind to Mycoplasma pneumoniae positive serum, and the amino acid sequence of the polypeptide is shown in SEQ ID NO: 1: T-V-N-F-K-L-Y. The present invention also provides a serological diagnostic kit for Mycoplasma pneumoniae infection, which contains the above-mentioned polypeptide specifically binding to Mycoplasma pneumoniae positive serum. In addition, the present invention also provides a phage-displayed polypeptide-based diagnostic kit for Mycoplasma pneumoniae, the kit includes a core phage, wherein the core phage is a phage displaying the above-mentioned polypeptide. The polypeptide and its corresponding core phage provided by the present invention have high sensitivity and specificity, and have good clinical diagnostic value.

The invention belongs to the technical field of biological detection, and discloses a POCT (Point of Care Testing) detection method for the content of hypoxanthine in urine and application. The method effectively meets the requirement for clinical detection of the content of the hypoxanthine in the urine, and the content of the hypoxanthine in the urine can be rapidly, accurately and sensitively detected. The experiment result is good in repeatability and high in precision. The detection time period is short, the detection can be completed within 20min at the soonest, the detection time is saved, the efficiency is improved, and the method is an efficient auxiliary detection means. The method can be used for clinical and even household fast detection through POCT, and effectively makes up for the defects of clinical auxiliary epilepsy detection at present. An operator only needs to drop the collected urine into a reaction cup for mixed reaction, a reaction product is transferred to a detection card for on-machine detection, a detection instrument only depends on a common handheld spectrophotometer, a result can be automatically interpreted, the requirement for the operator is extremely simple, and clinical and household generalizability is high.

The present invention relates to an auxiliary analysis method, device, system and storage medium for brain injury conditions. The auxiliary analysis method is used for auxiliary analysis of the neonatal brain injury status, including acquiring near-infrared data of the target area of ​​the brain of the neonatal subject in the resting state; based on the acquired near-infrared data, on the display interface The map of the central nodes in tiled mode is displayed in the first area of Each pivot node on the image is not occluded. The present invention displays the central nodes, regional connections, functional connections, and characteristic indicators associated with brain injury conditions on the interface in the form of a combination of pictures and texts, so that doctors can check from multiple angles, compare atlases, and interpret multiple indicators to improve the quality of life. Accuracy, reliability, and clinical diagnostic efficiency of neonatal brain injury status analysis.

The invention discloses a prescribing aided method and device for medicinal materials, a storage medium and a terminal. The method comprises the steps: receiving symptom description text information input by a user; inputting the symptom description text information into a pre-trained prescribing aided model to generate a medicinal material set; generating a recommended medicinal material set based on the medicinal material set, wherein the number of traditional Chinese medicinal materials in the medicinal material set is greater than or equal to that of traditional Chinese medicinal materialsin the recommended medicinal material set; and displaying the recommended medicinal material set on a display interface. Therefore, by adopting the embodiment of the invention, a clinician can be assisted to prescribing medicines according to symptoms of a patient, and the clinical diagnosis efficiency is improved.

The present application discloses a test strip for joint detection of C-reactive protein and serum amyloid A, a kit and a preparation method for the test strip. The test strip comprises a bottom plate, a sample pad, a binding pad, a reaction pad and a water-absorbing pad; the binding pad is coated with fluorescent microspheres jointly labeled with CRP antibody and CRP broadened rabbit anti-antibody, SAA antibody and SAA broadened chicken anti-antibody joint label Fluorescent microspheres; CRP detection line, SAA detection line, CRP widening line and SAA widening line are formed on the reaction pad. The test strip and the test kit containing the test strip of this application can simultaneously quantitatively detect the content of CRP and SAA in the sample, with high sensitivity, good specificity, fast detection speed, and a very wide linear range. The linear range of CRP is 0.5-600mg / L, the linear range of SAA is 3-800mg / L, which reduces the repeated dilution of samples in clinical practice and improves the efficiency of clinical diagnosis.

The invention discloses a method for fully automatic segmentation of coronary calcification lesions based on plain CT of the chest, comprising the following steps: performing preprocessing on the original plain CT image of the chest to obtain preprocessed data; In this method, the heart region in the original chest plain scan CT image is segmented to obtain a heart segmentation image corresponding to the original chest plain scan CT image containing the heart region; the suspected coronary artery calcification is screened in the heart region; Extract multiple candidate sample blocks from arterial calcifications; and based on the multiple candidate sample blocks and their corresponding coordinates in the coordinate system corresponding to the original chest CT image, use the calcification focus segmentation model to obtain the coronary artery calcifications of the candidate sample blocks Split results. The method of the present invention adopts a coarse-to-fine strategy, and uses a two-stage deep neural network to realize the automatic segmentation of coronary artery calcification based on chest plain scan CT, and can also obtain good segmentation results for data with relatively high noise.

The invention relates to the technical field of medical imaging, and discloses an image processing method and system for assisting pneumonia diagnosis. The method includes the steps of: obtaining a thin-layer chest CT initial image; performing segmentation processing on the initial image, and extracting an image of a lung region ; Process the image of the lung area to obtain an image without pulmonary blood vessels; use a neural network to detect the image without pulmonary blood vessels, and output an image with inflammatory markers. The training of the neural network includes using different training data sets and Pre-training and precise training of training objects; segment the lesion area in the image with inflammatory markers, and visualize the image of the lesion area to obtain the final image for doctors to review. Based on various image processing methods and neural network detection technology, the present invention can solve the neural network training problem of limited clinical pneumonia data, obtain stable diagnostic accuracy, and improve clinical diagnosis efficiency.

The invention belongs to the technical field of biological detection, and discloses a combined methylmalonic acidemia gene mutation detection kit. The kit is used for rapidly, accurately and sensitively detecting MMACHC gene mutation by designing three groups of primer pairs and a reaction hole aiming at MMACHC gene hotspot mutation regions. The application of the kit fills the blank of clinical MMACHC gene mutation detection, and experimental results are good in repeatability and high in precision. According to the invention, multiple mutation sites (including new mutation / non-found mutation) can be simultaneously detected at one time, the detection period is short, the detection can be completed within 8 hours at the soonest, the detection time is greatly saved, and the clinical efficiency is improved. Detection is completed through a multiple PCR and sanger sequencing technology, the requirement for operators is simple, the reagent cost is low, and clinical popularization is facilitated.

The invention discloses a novel group B streptococcus nucleic acid PCR-colloidal gold immunochromatography detection kit. The kit comprises an amplification reaction MIX, a GBS detection liquid, a positive reference substance, a negative reference substance and a sample releasing agent; the GBS detection liquid comprises a specific marker primer aiming at a group B streptococcus CAMP gene, a specific marker primer of a reference gene RNAse P and RNase Free ddH2O. According to the novel group B streptococcus nucleic acid PCR-colloidal gold immunochromatography detection kit, after nucleic acid is extracted from collected cell samples, specific fragments are amplified under the action of Taq DNA polymerase, then group B streptococcus nucleic acid detection is achieved through colloidal gold immunochromatography, in the processes of sample collection, nucleic acid extraction and PCR amplification, a reference gene RNAse P is used for quality control tracking, and it is guaranteed that the whole experiment process is within a controllable range.

The invention belongs to the technical field of medical image intelligent processing, and particularly relates to a multi-mode cooperation esophageal cancer lesion image segmentation system based on self-sampling similarity. For early esophageal cancer diagnosis, firstly, a white light image and an NBI data set which are paired are constructed; the segmentation system comprises a feature extraction encoder, a self-sampling similar feature separation module and a feature fusion decoder. the white light image and the NBI are taken as multi-modal input, and features of two modals are extracted respectively by two encoders; for each mode, the self-sampling similar feature separation module effectively distinguishes lesion region features from normal regions; and the decoder completes multi-modal feature fusion in a feature domain, and finally outputs lesion segmentation results of two modal images. Experimental results show that the features of different modes can be reasonably fused, the lesion area and the normal area are remarkably distinguished, accurate segmentation of the lesion area is achieved, and the efficiency of clinical diagnosis is improved.

The invention provides a polypeptide realizing specific combination with mycoplasma pneumoniae positive serum. The amino acid sequence of the polypeptide is shown as SEQ ID NO: 1: L-P-Q-R-L-R-T. The invention also provides a mycoplasma pneumoniae infected serology diagnostic kit. The kit contains polypeptide realizing specific combination with mycoplasma pneumoniae positive serum. In addition, theinvention also provides a mycoplasma pneumoniae diagnostic kit for showing the polypeptide on the basis of polypeptide. The kit contains a core phage, wherein the core phage is a phage showing the polypeptide. The polypeptide and the corresponding core phage provided by the invention have the advantages that the sensitivity and the specificity degree are very high; good clinic diagnosis values are realized.

The invention belongs to the technical field of biological detection, and discloses a combined methylmalonic acidemia gene mutation detection kit. The kit is designed to quickly, quickly, Accurate and sensitive detection of MMAHC gene mutations. The application of the kit fills the blank of clinical MMACHC gene mutation detection, and the experimental results have good repeatability and high precision. The invention can simultaneously detect multiple mutation sites (including new mutations / undiscovered mutations) at one time, and the detection cycle is short, and the detection can be completed within 8 hours at the fastest, which greatly saves detection time and improves clinical efficiency. The invention completes detection through multiple PCR plus sanger sequencing technology, has simple requirements for operators, low reagent cost, and is convenient for clinical promotion.

The invention provides an automatic classification method for a standard section of a fetal face in the field of ultrasonic image classification, and the method comprises the following steps: S10, obtaining a plurality of ultrasonic images of the fetal face, carrying out the preprocessing of each ultrasonic image, and respectively generating standard sections; S20, extracting textural features, including a local binary pattern and a direction gradient histogram, in the standard tangent plane; S30, performing Euclidean distance normalization on the texture features to obtain feature vectors; and S40, based on the feature vectors, learning and classifying the standard tangent planes by utilizing a support vector machine. The method has the advantages that the precision and efficiency of fetal face standard section classification are greatly improved, the clinical diagnosis efficiency is greatly improved, and the clinical diagnosis cost is reduced.

The present application provides an image processing method and apparatus, a computer-readable storage medium and an electronic device, and relates to the technical field of medical image processing. The image processing method includes: determining a candidate calcification region corresponding to the plain-scan CT image sequence based on a sequence of unenhanced CT images corresponding to a target coronary artery; The corresponding first coronary artery calcification data is beneficial to the purpose of automatically segmenting the coronary artery calcification area from the plain CT image. The efficiency of diagnosis provides an important risk assessment basis for predicting the development of coronary heart disease. At the same time, it avoids the radiation of coronary CTA examination to patients, and reduces the cost of medical treatment for patients.