52 results about "Typing methods" patented technology

The invention belongs to the technical field of medical image processing, and particularly relates to an automatic positioning and typing method for cervical posterior longitudinal ligament ossification, which is characterized in that ossification focus spatial distribution characteristics of CT images and spinal cord morphological parameters of MRI images are synchronously analyzed based on CT and MRI images, a vertebral body-ossification-spinal cord spatial relationship is explicitly modeled through anatomical structure topological constraint, and a cervical vertebra-ossification-spinal cord spatial relationship is obtained. Diffuse calcification artifacts, heterogeneity signal interference and multi-modal data registration deviation are overcome, accurate positioning and typing diagnosis of the ossification are achieved, multi-dimensional feature fusion analysis is achieved, the limitation of traditional single iconography index diagnosis is broken through, space continuity and clinical parameters are integrated through a hybrid classifier, and the accuracy of diagnosis is improved. The accuracy and robustness of typing judgment are improved, a structured diagnosis report is automatically generated in the whole process, and the clinical decision-making efficiency and the standardization level are remarkably improved; the principle is scientific and reliable, and the ossification continuity index, the spinal canal invasion rate and the spinal cord compression grading parameters are automatically calculated according to the typing standard.

The invention relates to the technical field of geological data acquisition, and particularly discloses a lossless field real-time acquisition method and system for field data of land quality, and the method comprises the steps: receiving control information inputted by a manager, and creating a dynamic form; determining a sampling point position based on the pattern spot pattern, and synchronously determining an electronic fence of the sampling point position; and sending the sampling point position to the handheld end, obtaining the position of the handheld end in real time, sending the dynamic form to the handheld end when the position is included in the electronic fence, and obtaining land sampling data containing the height based on the dynamic form. According to the method, a management personnel-oriented platform is established, a dynamic form establishment environment is provided, and the form established by the management personnel is received, so that front-line sampling personnel can carry out data filling according to the form and convert an original handwriting mode into a selection mode or a typing mode, and the interaction efficiency is greatly improved.

The invention discloses an intelligent typing method and system for M protein in an immunofixation electrophoresis image, and belongs to the technical field of immunofixation electrophoresis image analysis. According to the intelligent typing method and system for M protein in the immunofixation electrophoresis image, an expert knowledge-driven labeling specification of a double-blind labeling process and a labeling verification algorithm embedded into electrophoresis mobility physical constraint is established; according to the method, the image is subjected to standardization processing through the Vahadane dyeing normalization and strip ROI dynamic extraction technology, intelligent noise suppression processing is carried out on image data, the data quality is improved, standardized interpretation can be carried out on the electrophoresis image through a hybrid neural network deep learning algorithm and an AI model, the influence of human factors is reduced, and the method is suitable for being applied to the field of electrophoresis. And the model can reproduce the specificity and accuracy of the expert level. The problems that traditional naked eye interpretation is high in subjectivity, low in accuracy rate, low in efficiency of searching for expert consultation for complex and difficult cases and the like are solved.

The invention relates to an insomnia diagnosis and typing method based on multi-modal signal fusion, which comprises the following steps of: acquiring multi-source physiological signals of a testee during a rest period at night to construct a multi-modal information source during a sleep period; performing rhythm recognition and consistency judgment on the collected signals, calculating the rhythm change trend of each modal signal in a preset time window, and determining whether a signal fragment with physiological rhythm synchronization imbalance exists or not according to the rhythm collaboration among modals; performing inter-modal logic consistency analysis on the rhythm anomaly signal segments, identifying contradictory states of different modals in the same time window, and marking the contradictory states as modal conflict nodes; extracting an activation sequence of each modal signal according to a sequential relationship of the conflict nodes so as to determine a dominant modal of the insomnia behavior; analyzing a state transition behavior of the multi-mode signal through a sliding time window, identifying a nonlinear fracture section of a sleep state, and determining an insomnia occurrence time section and jump characteristics in combination with a mode activation sequence so as to realize insomnia diagnosis and typing judgment.

A single nucleotide polymorphism typing method based on a CRISPR / Cas12a logic gate realizes typing output of single nucleotide polymorphism through logic gate input of fluorescence signals of a CRISPR / Cas12a reaction system, namely ''existence'' and ''no'', ''strong'' and ''weak'', and is characterized in that the novel single nucleotide polymorphism typing method comprises two steps of target fragment amplification and CRISPR / Cas12a detection; wherein the target fragment amplification is characterized in that a PAM recognition sequence TTTN of CRISPR / Cas12a is introduced to a-15 site to a-11 site of a target site through the design of an amplification primer, and an amplification product can be detected by the CRISPR / Cas12a; according to the CRISPR / Cas12a detection, two crRNA1 and crRNA2 which can distinguish wild type and mutant type amplification products are used as guide chains of a CRISPR / Cas12a reaction system, a novel functionalized single-stranded DNA report probe is designed, and single nucleotide polymorphism typing is achieved through logic gates of'existence 'and'absence' and'strong 'and'weak' of fluorescence signals. The method solves the problem that a traditional CRISPR / Cas12a reaction system cannot realize single nucleotide polymorphism typing, can be used for scientific research analysis and clinical detection, and has a wide market prospect.

The invention relates to the technical field of bioinformatics, and discloses a three-generation full-length transcript sequencing data-based HLA (human leukocyte antigen) typing method, system, equipment and medium, by utilizing the technical advantage of long read length of a three-generation sequencing single molecule, a complete transcript sequence of an HLA gene is directly obtained, full-length HLA typing without PCR (polymerase chain reaction) amplification and short read length splicing is realized, and the method, the system and the equipment are simple and convenient to operate. The blank of the three-generation full-field transcript in the aspect of detecting the HLA typing is filled. The method effectively solves the problem that the cost, the efficiency and the accuracy are difficult to consider in the traditional HLA typing technology, not only avoids PCR amplification preference and short read length assembly errors and remarkably improves the typing accuracy, but also reduces the analysis complexity through an optimized bioinformatics process. According to the method, an efficient solution with economical efficiency and reliability can be provided for application scenes such as clinical transplantation matching and disease association research, and the method has important clinical application value and wide market prospects.

The invention relates to the technical field of classification, in particular to a traditional Chinese medicine syndrome typing method and system. Clinical information of a patient is input into an auto-encoding language model and an auto-regression language model respectively, each model predicts the probability that the disease of the patient belongs to an actual symptom type and the probability that the disease of the patient belongs to a deficiency symptom type, and an auto-encoding prediction result and an auto-regression prediction result are obtained; obtaining an actual symptom keyword set and a deficiency symptom keyword set, counting the number of actual symptom keywords and the number of deficiency symptom keywords in the clinical information of the patient, and combining the two statistical results to obtain a keyword number feature vector; splicing the self-encoding prediction result, the self-regression prediction result and the keyword quantity feature vector to obtain a comprehensive feature vector; and enabling the comprehensive feature vector to sequentially pass through an LSTM layer and a full connection layer to obtain a syndrome typing result of the patient. The accuracy and reliability of traditional Chinese medicine syndrome classification are effectively improved.

The invention discloses an HLA (human leukocyte antigen) gene amplification primer based on a nanopore sequencing platform and a typing method, and relates to the technical field of gene engineering, the amplification primer comprises an HLA-A gene amplification primer pair: a forward primer HLA-A-F5; a reverse primer HLA-A-R5; an HLA-B gene amplification primer pair: a forward primer HLA-B-F3; a reverse primer HLA-B-R3; the HLA-DQB1 gene amplification primer pair comprises a forward primer HLA-DQB1-F7, a reverse primer HLA-DQB1-F7 and a reverse primer HLA-DQB1-F7; a reverse primer of HLA-DQB1-R7; the HLA-DRB1 gene amplification primer pair comprises a forward primer HLA-DRB1-F1, a reverse primer HLA-DRB1-F2, a reverse primer HLA-DRB1 A reverse primer (HLA-DRB1-R1); the HLA-DRB3 gene amplification primer pair comprises a forward primer HLA-DRB3-F6, a reverse primer HLA-DRB3-F6, a reverse primer A reverse primer (HLA-DRB3-R8); by designing the specific amplification primer group and combining with the nanopore sequencing length reading technology, the problems of insufficient resolution and the like of the existing typing technology are solved, the typing accuracy and resolution are improved, and the performance is superior to that of the traditional technology; meanwhile, the process is optimized, the limitation of long detection period and the like is broken through, the whole process is rapidly completed, the technical threshold and detection expenditure are reduced, high efficiency, convenience and economy are considered, and support is provided for clinical popularization and scientific research application.

The application discloses a target typing method, device, equipment and storage medium. The target typing method comprises the following steps: performing feature extraction on a plurality of initial images containing a target to be typed, respectively, to obtain initial features of the target in each initial image; fusing the initial features based on a preset correlation relationship between the initial images to obtain target features; and obtaining a typing result of the target by using the target features. The above scheme can improve the accuracy of the typing result.

The invention belongs to the technical field of biological information processing, and provides a cancer typing method and system based on cross-modal attention and variational representation learning, and the method comprises the steps: obtaining the multi-modal medical data of a patient, coding the multi-modal medical data, mapping the multi-modal medical data to a modal specific representation space of a unified dimension, and obtaining the feature representation of a corresponding modal; a multi-head attention mechanism is introduced, for each attention head in the multi-head attention mechanism, an independent mapping space is constructed for each mode, output of the multiple attention heads is spliced on the feature dimension, and through linear transformation, multi-mode fusion representation aggregating cross-mode complementary information is obtained; deducing statistical parameters of potential posteriori distribution represented by multi-modal fusion, and sampling to obtain potential variables; based on the potential variables and the classifier, obtaining a cancer typing result through Softmax; and end-to-end accurate classification is realized.

The invention discloses a primer group for MLVA typing of bordetella pertussis and application of the primer group. The primer group for MLVA typing of bordetella pertussis comprises primer sequences of VNTR 1-6, a primer sequence of VNTR 2-6, a primer sequence of VNTR 3-6, a primer sequence of VNTR 4-6 and a primer sequence of VNTR 5-6, through selection of the primer group for pertussis bordetella MLVA typing, the primer group can be directly applied to clinical detection of pertussis positive samples, the sample types can be sputum, throat swab, alveolar lavage fluid and other clinical common sample types, and isolated culture is not needed; besides, the Bordetella pertussis MLVA typing method is short in experimental period, a large amount of sequencing sequence data can be obtained at a time, six groups of primers designed in the invention can be carried out in the same reaction tube, one experiment takes about 24 hours, sequencing results of a plurality of samples can be obtained in combination with an NGS sequencing technology, and the detection efficiency is high.

The application discloses a skin type prediction method for small sample data autonomous learning, and relates to the technical fields of deep learning and medical beauty skin type. The initial model is obtained by a convolutional neural network through a small number of labeled samples, and the subsequent new samples are accepted through the initial model, and whether the new samples have labeling value is judged according to the prediction result of the model, so that only the samples determined to be inaccurate by the model are selected for labeling and retraining. Compared with the existing skin type method, a single model can be used to obtain a more perfect result, the model is continuously iteratively optimized by using the enhanced unit in the actual use process, and the idea of active learning is used to select the samples with greater uncertainty for labeling, so that the number of samples needing expert labeling can be greatly reduced, and the labor cost is reduced. According to the reliability module, when the samples are expanded, the skin type with insufficient reliability is preferred, so that the final typing effect is improved.

The application discloses a diploid typing method based on Hi-C data, comprising obtaining an existing typing assembly result; mapping the assembly result and obtaining a pure region and a hybrid region of a diploid genome; filtering a comparison result of the Hi-C reading and reserving a Hi-C comparison result containing a hybrid variation site; identifying a large section switching existing in the assembly result; and counting the number of Hi-C connections between the sections after cutting, thereby completing the typing of the diploid. The application further discloses a system for implementing the diploid typing method based on the Hi-C data, and an assembly method comprising the diploid typing method based on the Hi-C data. The application filters the Hi-C comparison result through the hybrid variation in the diploid genome, detects whether a large parent switching exists by using the filtered Hi-C comparison result, thereby realizing the final diploid typing method and assembly, and therefore the application has higher reliability and better accuracy.

The application discloses a rehabilitation action recognition and classification method, system, device and storage medium, the method comprising: collecting a three-dimensional coordinate sequence of a human skeleton point corresponding to a target rehabilitation action performed by a user; performing normalization and time alignment processing on the three-dimensional coordinate sequence to generate a standardized posture matrix; extracting principal component features for representing action patterns from the standardized posture matrix; performing unsupervised clustering analysis on the principal component features, and dividing a plurality of action pattern categories according to a clustering analysis result; performing similarity matching on the principal component features and features corresponding to the plurality of different action pattern categories in a typical action pattern database; and determining a specific action pattern category to which the target rehabilitation action belongs according to a similarity matching result. The application improves the objectivity, repeatability and clinical interpretability of rehabilitation action recognition and classification, and expands the applicable scenarios.

The invention discloses an HLA-DRB1 gene high-resolution typing method based on group specific primers, and belongs to the technical field of gene detection. The group of specific primers are respectively designed according to exons 1-4 of the HLA-DRB1 gene, sequences of the specific primers are shown as SEQ ID NO.1-SEQ ID NO.20, the specific primers have good conservative property on allele sequences of the HLA-DRB1 gene, compared with gene sequences of HLA-DRB3, HLA-DRB4 and HLA-DRB5, the specific primers have good specificity, 1, 2, 3 and 4 exons of the HLA-DRB1 site can be effectively amplified, the corresponding exons are sequenced, and the specific primers can be used for detecting the HLA-DRB1 gene. The polymorphic site of the HLA-DRB1 gene is fully covered. Therefore, when further typing is carried out, the resolution and accuracy of HLA-DRB1 genetic typing are effectively improved, and the ambiguous condition of HLA-DRB1 genetic typing is improved.

The invention provides an intelligent montella fracture typing method and device based on image-text multi-modal fusion, and relates to the technical field of medical image typing. The method comprises the following steps: extracting an original high-dimensional feature vector of an image by using a ViT pre-training model, and extracting an original high-dimensional feature vector of a text by using a BERT pre-training model; respectively projecting the original high-dimensional feature vectors to a low-dimensional embedding space to obtain projected image and text features; then the image is input to a feature interaction fusion module, the module learns a shared interaction representation through nonlinear transformation, generates two independent attention weights based on the representation, respectively applies the two independent attention weights to projected image and text features, and finally generates a fusion feature vector; according to the method, the accuracy and comprehensiveness of disease prediction and diagnosis are improved through deep interactive fusion, hierarchical information aggregation and a cost-sensitive learning strategy.

The present application belongs to the technical field of cosmetic safety evaluation, and discloses a human patch test result typing method for cosmetics suitable for sensitive skin, which comprises the following steps: collecting comment data and performing deduplication and noise reduction processing, analyzing the comment data set using a trained RoBERTa-large language model, identifying adverse reaction comments, and calculating adverse reaction scores and adverse reaction rates; performing a patch test and setting a typing line according to the patch test results; extracting product characteristics of the cosmetics; establishing a generalized linear model; testing the likelihood ratio chi-square and significance of each generalized linear model, and screening the best typing of the cosmetics corresponding to the patch test. The method of the present application can effectively evaluate the safety risk of cosmetics for target users.

The invention provides an SLE-PAH typing method based on transcriptomics, and the method comprises the following steps: S1, collecting research samples, including an SLE patient and an SLE-PAH patient; s2, collecting and processing data to obtain transcriptome samples of an SLE patient and an SLE-PAH patient; s3, analysis based on a transcriptome sample; the SLE-PAH is divided into three subtypes with different PAH degrees, namely a high inflammation subtype, a moderate inflammation subtype and a low inflammation subtype. The technical problems that in the prior art, the pathogenesis of SLE-PAH is not completely clear, and it is difficult to formulate targeted effective treatment schemes for different degrees of diseases are solved.

The invention discloses a chronic nasosinusitis auxiliary typing method based on radiomics data and related equipment. The method comprises the following steps: acquiring paranasal sinus radiomics data, clinical feature data and biological sample analysis result data of a chronic sinusitis patient; dividing the paranasal sinus radiomics data into a plurality of image clustering categories by adopting an unsupervised clustering algorithm, and associating clinical feature data and biological sample analysis result data corresponding to different image clustering categories respectively; and analyzing clinical feature data differences and biological sample analysis result data differences among different image clustering categories, and constructing a systematic mapping relationship between the image clustering categories and clinical pathological typing so as to carry out chronic sinusitis auxiliary typing. The problems that in typing research of chronic nasosinusitis, traditional intrinsic typing needs to depend on complex and expensive biological sample examination, generalizability is not high, and sampling cannot completely reflect individual heterogeneity of patients and is invasive can be solved.

We will develop a probe set that can process multiple samples simultaneously using sequence capture methods and comprehensively capture genes in the KIR region. [Solution] A probe set for KIR gene typing is provided, each consisting of oligonucleotides having a specific base sequence. Furthermore, a method for KIR gene typing using the probe set is provided.

The invention discloses a gastroesophageal reflux AI auxiliary typing method based on esophageal function and morphological characteristics, and belongs to the technical field of gastroesophageal reflux, a first index parameter is acquired, esophageal functional characteristics are evaluated by using a pre-training model according to the first index parameter, and a functional score is calculated; wherein the first index parameter comprises a high-resolution esophageal power index parameter and an esophageal pH-impedance combined index parameter; obtaining esophageal endoscopic image index parameters, and according to the esophageal endoscopic image index parameters, evaluating the severity of the foraminal hernia defect and cardia relaxation by using the deep learning convolutional neural network prediction model, and calculating a morphological score; comprehensively evaluating the severity of the gastroesophageal reflux according to the functional score and the morphological score, and completing the precise typing of the gastroesophageal reflux. The severity of esophageal dysfunction and morphological defect is effectively evaluated based on a comprehensive index evaluation system, and precise typing of gastroesophageal reflux disease is completed.

This invention provides a highly practical probe set and a method for typing HLA genes using it, which enable efficient and highly accurate simultaneous typing of a large number of samples using the sequence capture method. [Solution] A probe set for HLA gene typing is provided, each consisting of oligonucleotides having a specific base sequence. Furthermore, an HLA gene typing method using the sequence capture method with the probe set is provided.

This invention discloses a arranging mechanism, including an operating table, a placement rack, a conveying component, a feeding component, and an arranging component. A frame is mounted on the operating table; the placement rack is mounted on the frame and used to place several strips; the conveying component includes a conveying element and a pushing element, the pushing element being used to push the bottom strip of the placement rack to the conveying element, and the conveying element is rotatably mounted on the frame; the feeding component is mounted on one side of the frame; the conveying component is used to convey the strips pushed by the pushing element one by one to the arranging component at preset time intervals; the feeding component is used to convey several cores to the arranging component; the arranging component is rotatably mounted on the frame and used to arrange the several cores sequentially on the strips to form a core board. This arranging mechanism can quickly arrange cores onto strips, achieving rapid assembly and high efficiency. In addition, this invention also provides a hot-press arranging machine and arranging method, which is used to press the cores firmly to achieve capacity fixation.

The invention discloses an accurate auxiliary meningitis typing method based on a machine learning model, electronic equipment and a storage medium, and the method comprises the steps: selecting medical detection items as features, and combining the features to construct a feature subset; constructing a meningitis subdivision discrimination framework, and disassembling meningitis diagnosis requirements into nine mutually independent binary discrimination tasks; taking the feature subset as input, executing each binary discrimination task to construct a training task, and training an independent machine learning model; obtaining a binary discrimination task selected by a doctor and a binary discrimination task selected by the doctor; and respectively calling independent machine learning models for execution, and outputting auxiliary typing discrimination. According to the accurate meningitis typing method based on multi-task discrimination of the machine learning model, clinicians are helped to judge meningitis categories by using a machine learning method, so that accurate and effective diagnosis and treatment are provided for patients in time.

The present invention relates to the field of bioinformatics technology and discloses an HLA typing method, system, device, and medium based on third-generation full-length transcript sequencing data. By leveraging the technical advantages of third-generation sequencing's single-molecule long reads, the complete transcript sequence of the HLA gene is directly obtained, enabling full-length HLA typing without the need for PCR amplification and short-read splicing. This method effectively addresses the challenges of balancing cost, efficiency, and accuracy in traditional HLA typing techniques. It not only avoids PCR amplification bias and short-read assembly errors, significantly improving typing accuracy, but also reduces analytical complexity through optimized bioinformatics workflows. The present invention can also provide an efficient, cost-effective, and reliable solution for applications such as clinical transplant matching and disease association studies, possessing significant clinical application value and broad market prospects.

The invention belongs to the technical field of multi-level regional mountain torrent classification and classification methods, and provides a multi-level regional mountain torrent classification and classification method based on a graph neural network and a decision tree. The method comprises the following steps: firstly, collecting mountain torrent disaster-pregnancy data of a target area, and generating a standardized raster data set through resampling, cutting and standardization processing; secondly, introducing a hydrological connectivity relation to construct graph structure data, and defining a node effective neighborhood set; and evaluating the mountain torrent disaster risk by introducing a graph neural network model of an attention mechanism, calibrating an optimal risk threshold and dividing five risk levels. For high-risk and extremely-high-risk areas, a classification and classification method is constructed to divide primary classification and secondary classification, and an optimal classification and classification result is obtained by automatically screening and optimizing rules through comprehensive evaluation criteria. And finally, analyzing the contribution of the mountain torrent disaster-pregnancy factor based on a typing result, and realizing analysis of disaster forming mechanisms of different types of mountain torrents.

This invention discloses an intelligent typing method and system for M protein in immunofixation electrophoresis images, belonging to the field of immunofixation electrophoresis image analysis technology. This invention establishes a double-blind annotation process and an expert knowledge-driven annotation standard with an embedded annotation verification algorithm based on physical constraints of electrophoretic mobility. Vahadane staining normalization and dynamic ROI extraction techniques are used to standardize the images, and intelligent noise suppression is applied to the image data to improve data quality. Through a hybrid neural network deep learning algorithm, the AI ​​model can perform standardized interpretation of electrophoresis images, reducing the influence of human factors and enabling the model to reproduce the specificity and accuracy of expert-level interpretation. This solves the problems of low accuracy due to strong subjectivity in traditional visual interpretation, such as overlapping bands and weak positives, and the low efficiency of seeking expert consultation for complex and difficult cases.

The invention relates to the technical field of medical image detection, in particular to a child femoral neck fracture intelligent typing method and device based on WT and AM. According to the method, multi-dimensional child femoral neck fracture X-ray film image feature extraction is carried out through wavelet convolution, different features are captured in a targeted mode, meanwhile, self-adaptive weighting of a channel attention mechanism is combined, image weak signals are remarkably enhanced, and low-signal interference is restrained; further, through the fusion design of Focal Loss and Equalization Loss, the weight of feature learning is dynamically balanced, and the problem that the sample sizes of different fracture subtypes are unbalanced is solved; besides, high precision of the model is maintained, intelligent and accurate evaluation of Delbet-Colonna subtype images of the femoral neck fracture of children is realized by means of a single-stage detection framework, a new thought and method are provided for construction of intelligent evaluation models of other multi-classification disease images, and the method has a wide application prospect.

The present disclosure provides a machine learning based cell segmentation and typing method, device, instrument and medium, which includes: obtaining a metabolic image of at least one cell of a target object; performing single-cell image segmentation on the metabolic image of at least one cell by a machine learning segmentation model to obtain metabolic images of multiple single cells; extracting single-cell features for each metabolic image of the multiple single cells, and obtaining a single-cell image feature spectrum corresponding to the metabolic image of the single cell; combining the single-cell image feature spectrum corresponding to each metabolic image of the multiple single cells to obtain an image feature spectrum of a target object; and typing the cell by clustering the image feature spectrum of the target object.

The invention discloses a hypha detection typing method and device based on multi-label fusion. The method comprises the following steps that a fungus microscopic image is collected and preprocessed, then a data set is established, image preprocessing comprises the step of conducting multi-label manual labeling on a positive area in the fungus microscopic image, and multiple labels comprise bud spores, sporophores, whole hyphae, hypha ends and hypha diaphragms; constructing a network model and carrying out model training by adopting the training set data to obtain a detection typing model; and performing feature extraction and feature fusion on the fungus microscopic image of the user by using the detection typing model to obtain second feature data, performing multi-label statistical calculation on the second feature data, and performing hypha judgment and hypha typing according to a calculation result. By utilizing the method, hypha positive judgment and typing detection can be quickly and accurately carried out on a fungus sample, and meanwhile, the false positive rate of hypha detection is reduced.