39 results about "Diagnosis quality" patented technology

The invention relates to a method for automatic recognition and stage compression of medical image regions of interest based on an artificial neural network. Medical image files in a digital diagnostic system are generally larger, and due to the limitation by factors of bandwidth and the like, the transmission speed is low, the effect is not good, and the diagnosis quality is influenced. By the method, medical digital images are subjected to noise elimination, the tissue outline of a human body is recognized, tissue images are subjected to multiple times of overlay operation, image features of the regions of interest are strengthened, feature values are extracted, classification is performed by using an artificial neural network method, the regions of interest and corresponding levels are determined, and tagged image file format (TIFF) images are generated in different compression modes according to different levels of the regions of interest and non-regions of interest. By the method, the medical image files are greatly lessened, the transmission speed is increased, and effective necessary information used for diagnosis and treatment in the images is kept, so the method facilitates the reading of doctors, and can be applied to the digital diagnostic system and a remote medical system, and improve the diagnosis and treatment efficiency and effect.

The invention provides a digestive tract early cancer auxiliary diagnosis system based on depth learning and an examination device. The system comprises a feature extraction network, an image classification model, an endoscope classifier and an early cancer recognition model, wherein the feature extraction network is used for performing initial feature extraction on endoscope images according to aneural network model; the image classification model is used for extracting initial features and acquiring image classification features; the endoscope classifier is used for extracting initial features to obtain endoscope classification features and classifying gastroscope and coloscope images; the early cancer recognition model is used for splicing initial features, endoscope classification features and image classification features to obtain the probability of early cancer focuses of white light images, electronic straining images or chemical straining images corresponding parts or obtainwashing prompt or position recognition prompt of corresponding parts. The AI auxiliary diagnosis quality and digestive endoscopy diagnosis efficiency are improved.

The invention relates to a convolutional neural network-based low-dosage CT image noise inhibition method. The convolutional neural network-based low-dosage CT image noise inhibition method comprisesthe following steps: (1) performing normalization processing on the input original low-dosage CT image L by utilizing the low-dosage CT image obtained through low tube current tube voltage scanning, evaluating the mean value and the standard deviation of the gray level of all the pixels of the low-dosage CT image, and subtracting the mean value from the L and dividing the standard deviation to obtain a CT image L0; (2) taking the acquired preprocessed low-dosage CT image L0 as input of the convolutional neural network and predicting a noise CT image D0 corresponding to a low-dosage CT image I;and (3) subtracting the predicted noise image D0 from the L0, multiplying the standard deviation of the low-dosage CT image and adding the mean value of the low-dosage CT image to acquire the denoised image H0. The low-dosage CT image is subjected to denoising processing by the convolutional neural network, so that the image is guaranteed to meet the diagnosis quality, the irradiation dosage of asubject is reduced, the detection rate of the focus is increased and the disease is diagnosed early.

The invention provides a method for digitalizing a paper electrocardiogram. In the method, a digital image processing technology is combined to rebuild and store a large number of clinical paper electrocardiograms. The method comprises the following steps: scanning the paper electrocardiogram, and carrying out tilt correction on the grey level image of the obtained electrocardiogram; extracting an electrocardio (ECG) curve in the paper electrocardiogram; acquiring the time-voltage value of each discrete point on the curve; rebuilding an electrocardiogram curve and leading information; storing the time-voltage value of each discrete point in a database; and storing a rebuilt oscillogram in the database. In the method, the possibility of adding symptom information of the clinically acquired paper electrocardiogram to a digital ECG information management system is ensured, thereby enriching a case bank. The method is used for solving the problems that the paper electrocardiograms are easy to damage and lose (the electrocardiograms can not be recovered after being damaged or lost), are difficult to store, and easy to go wrong in trivial management; the method facilitates clinical analysis and scientific research, thus reducing the search time, and improving the efficiency; and the method can be applied to internet medical treatment and multiple expert consultation, thus improving the diagnosis quality.

The invention discloses a rapid fault diagnosis method used for a microgrid, which adopts a mode of step-by-step diagnosis and comprises the following steps that firstly, primary diagnosis is carried out by utilizing the switch information of a network, i.e. newly added passive sub-networks are judged as fault regions and fault elements according to the difference of before and after topology analysis results of faults, and for simple faults, a unique fault region and fault element can be determined. For complicated faults, a plurality of suspected fault solutions can be possibly presented in the result of the primary diagnosis of the switch information. At this moment, a second-step diagnosis is entered, and the diagnosis is carried out by utilizing the protection information of the network. A new target function is established in protection information diagnosis by utilizing the protection information of the elements; the fault diagnosis problem of the microgrid is expressed as the 0-1 integer programming problem; a genetic algorithm and tabu search mixed strategy is introduced to solve the target function; and the fault elements are determined by the optimal solution. The invention can effectively improve the fault diagnosis efficiency, reduces the time of fault diagnosis and improves the fault diagnosis quality.

The invention relates to a digital pathological full-slice retrieval method and belongs to the technical field of digital image processing techniques. Aiming at the problem that the conventional content-based digital pathological image method is difficultly applied to digital pathological full-slice retrieval, the invention provides a quick retrieval method which is applied to a database stored with a large number of digital pathological full-slices, adapts to large variation of querying image sizes, can provide accurate reference information for a doctor in clinical diagnosis, and effectively improves the diagnosis quality of the doctor in the pathology department.

The invention discloses an intelligent pathological diagnosis method and a system thereof. The method comprises the following steps of: a, performing sheet production and dyeing on a to-be-diagnosed sample, and then acquiring a sample image; b, uploading the sample image to an intelligent cell recognition auxiliary diagnosis system for screening a normal sample image, obtaining a residual problemsample image, performing preliminary diagnosis on the problem sample image by the intelligent cell recognition auxiliary diagnosis system, and obtaining a first diagnosis result; and c, transmitting the first diagnosis result to a remote expert consultation platform by the intelligent cell recognition auxiliary diagnosis system, selecting experts from an expert database for performing remote sheetreading consultation by the remote expert consultation platform, and finally performing gathering for obtaining a final diagnosis result. The intelligent pathological diagnosis method and the systemthereof have advantages of eliminating a pathological diagnosis obstacle, improving pathological diagnosis quality and reducing pathological diagnosis cost.

The invention provides an automatic biochemical analyzer remote equipment diagnosis strategy. The automatic biochemical analyzer remote equipment diagnosis strategy includes the following steps: 1) acquiring various physical signals of an automatic biochemical analyzer, including pressure, liquid level, flow, temperature, and position, and obtaining input parameters; 2) uploading the input parameters to a unified server, and performing evaluation of initial state on the automatic biochemical analyzer by means of one-sided characteristic quantity; 3) constructing an automatic biochemical analyzer fault diagnosis model based on a decision tree; and 4) loading the maintenance strategy. The automatic biochemical analyzer remote equipment diagnosis strategy can improve the diagnosis speed of system, can save the cost of service hospital equipment of an enterprise, and can improve the diagnosis quality.

The embodiment of the invention provides a diagnosis quality inspection method and device, electronic equipment and a storage medium. The method comprises the steps that a diagnosis result and a medical record text are determined; the diagnosis result and the medical record text are input into a diagnosis quality inspection model to obtain a quality inspection result output by the diagnosis quality inspection model; the diagnosis quality inspection model is obtained by training based on a sample diagnosis result, a sample medical record text, a sample quality inspection result and a diagnosisknowledge base, and the diagnosis knowledge base comprises medical knowledge related to diagnosis corresponding to various diseases; and the diagnosis quality inspection model is used for carrying outfeature fusion on diagnosis related features and medical record related features and carrying out diagnosis quality inspection based on the fused features; diagnosis related features are determined based on the diagnosis result and the diagnosis knowledge base, and the medical record related features are determined based on a medical record text. According to the method and device, the electronicequipment and the storage medium provided by the embodiment of the invention, the applicability and accuracy of the diagnosis and quality inspection method are improved.

The invention relates to the technical field of ultrasonic imaging, in particular to an ultrasonic system and a multi-image imaging method thereof. The ultrasonic system comprises a conventional scanning and processing module and a user interface assembly. The multi-image imaging method is implemented by adopting range customization of a display area, non-image content automatic concealment, single-image zooming and recovering. According to the method, the size of the display area is increased when the multi-image display or image depth is large, the problem that the resolution is lowered under normal conditions is avoided or reduced, and working efficiency and diagnosis quality of a doctor are improved; particularly, on the portable ultrasonic system, the size of the display screen is limited, the size of a display screen is reasonably utilized, and the method is of great significance in image display.

The invention provides a tumor image report diagnosis result and pathological result correspondence and evaluation system, which comprises: an image report screening module for screening all tumor image structured reports of image examination items of a patient in a preset time period, including pathological examination sampling parts, on the basis of pathological examination of the patient; a first extraction module which identifies the image examination part and the diagnosis result, and extracts the code of the image examination part and the code of the first diagnosis type; a second extraction module which is used for identifying a sampling part and a pathological result of pathological examination and extracting a code of the sampling part and a code of a second diagnosis type; a diagnosis quality judgment module which judges the conformity of the diagnosis result and outputs a judgment result based on a judgment rule; and a judgment result display module which displays the judgment result in a patient list. The invention further discloses a tumor image report diagnosis result and pathological result correspondence and evaluation method. According to the invention, the diagnosis result and the pathological result can automatically correspond to evaluate the image report, the efficiency is improved, and errors are reduced.

The invention relates to a remote electrocardio diagnosis quality control method and device and a management system. The method comprises the steps of conducting remote consultation on electrocardiogram data information uploaded by a primary medical institution, and marking critical value information; and after consultation, preferentially transmitting an electrocardiogram diagnosis report of theelectrocardiogram marked with the critical value information. Patients with electrocardiogram critical values can be treated in time; the aims of guaranteeing the life health of a patient and saving the medical cost are achieved, a primary medical institution synchronizes the received electrocardiogram diagnosis report to a shared cloud server in real time, a superior hospital obtains the distributed electrocardiogram diagnosis report through the cloud server and carries out remote quality control, and the quality control result is more rigorous.

The invention provides a fresh graduate resume quality diagnosis method which comprises the following steps of S1, inputting and configuring by a diagnosis system; S2, carrying out the willingness collection diagnosis initialization before diagnosis; S3, diagnosing and correcting; and S4, pushing, feeding back and filing the diagnosis reports, automatically generating the user-oriented resume diagnosis reports, automatically detecting the browsing duration of the user reports and the checking condition of the final report subdivision units, collecting the user diagnosis problem recognition degree feedback, automatically annotating the corresponding labels for talents, and filing the talent libraries and diagnosis conditions. According to the method, the diagnosis quality and the diagnosisefficiency of the fresh graduate resume problems can be remarkably improved, and a large-scale scheme support is provided for the guidance and popularization of the fresh graduate resumes.

The invention relates to a classification method for processing electronic medical record hybrid data based on a crowd network, wherein an existing numerical data processing method can be effectivelyutilized for improving classification efficiency of the hybrid data in the electronic medical record, and improving diagnosis quality and efficiency of a doctor. The method comprises the steps of 1, extracting an original electronic medical record dataset in an original electronic medical record database; 2, performing symbol type data determining on the cleaned electronic medical record dataset,and performing numerical data conversion on the symbol type data; 3, extracting a key characteristic field in the original electronic medical record dataset, and training a classification diagnosis model; and 4, extracting a key characteristic field in the to-be-diagnosed electronic medical record, inputting into the trained model, and outputting a classification result and a disease suffering probability. The method can effectively mine valuable information in the electronic medical record for helping the doctor in quick condition diagnosis, thereby realizing an important theoretical meaningand high application value.

The invention discloses a pathological intelligent diagnosis system through combination of pictures, characters and voice. The pathological intelligent diagnosis system comprises a computer, a pathological slice scanner, a pathological image data service station, a microphone and a printer. The computer is connected with the microphone and the printer through USB interfaces, and is connected withthe pathological slice scanner and the pathological image data service station through a network. The computer is provided with a diagnosis control system which comprises a data input module, an intelligent diagnosis module, a diagnosis correcting module, a data storage module and a data output module. The pathological slice scanner is used for converting a pathological slice to a digital pathological image. The pathological image data service station is used for receiving, storing and transmitting the pathological image, case information and a pathological diagnosis report which come from thepathological slice scanner and the network end. The microphone is used for inputting voice diagnosis information of a doctor. The printer is used for turning the pictures and characters of the diagnosis report to a paper document. The pathological intelligent diagnosis system improves working efficiency of a pathological doctor and pathological diagnosis quality.

The invention relates to an abnormal karyotype image library used in the medical field and a construction method for the same. Remainder adherent growth living cells used for chromosome disease diagnosis due to a diagnosis need and already confirmed to be provided with complicated chromosome abnormality are taken, and subjected to repeated generation amplification, cells are corrected, lowly-permeated, fixed and stored at minus 20 DEG C, then one type or more types of cell suspensions are taken and mixed according to the needed ratio, thus only one abnormal karyotype contained in each part of the cell suspensions is converted to various abnormal karyotypes with different ratios and easy to carry out misdiagnose, the image library is prepared through chromosome preparation and image capture, the difficulty and complexity of differential diagnosis and chimera diagnosis are improved by the prepared images, and more chromosome abnormal combined types of karyotype images can be prepared as needed; specimens are easy to get and waste redundant cells are used for teaching, technical examination, external quality assessment and resource sharing for chromosome analysis, and a remarkable effect is acted on timely discovery for diagnosis quality problems and improvement for a diagnosis level.

The invention relates to artificial intelligence, and provides a medical record quality control method and device based on natural language processing, computer equipment and a storage medium. The method comprises the steps: extracting chief complaint information and corresponding symptom relation attribute pairs in a to-be-detected medical record; inputting the chief complaint information and thesymptom relation attribute pair into a trained first natural language processing model to obtain a disease set matched with the chief complaint information; and matching the disease set with the diagnosis information in the to-be-detected medical record, and determining whether the diagnosis information of the to-be-detected medical record is misdiagnosed according to a matching result. The invention also relates to a blockchain technology, wherein the to-be-detected medical record can be stored in a blockchain. By adopting the method, whether the chief complaint information is consistent with the diagnosis information can be determined, and diagnosis quality control is realized.

The present invention discloses one kind of light source device for slit lamp microscope. The light source device contains a lighter, and condensing lens set, slit, diaphragm and projecting lens set in the light path of the lighter. The lighter is one multiple die LED with red light emitting LED die, blue light emitting LED die and green light emitting LED die. The light source device has simple structure, convenient operation, rich light colors, high light homogeneity and high color stability, and can result in improved diagnosis quality.

The invention relates to a diagnosis quality-control cell strain for common numerical abnormalities of chromosomes and a preparation method thereof. The invention is mainly characterized in that the preparation method comprises: taking residual attached living cells which are used for chromosomal disease diagnosis as needed by clinical diagnosis and treatment and are definitely diagnosed to have 21-trisomy, 18-trisomy, 13-trisomy, X or Y chromosome abnormalities, introducing, through transgenosis, SV40LTag-pcDNA3.1(-) plasmid constructed by SV40LTag DNA and pcDNA3.1(-) connected by T4DNA ligase and digested by BamHI, allowing the plasmid to integrate with the cell DNA, screening cell strains integrated with recons by G418, performing subculture amplification and cryopreservation, then extracting the cell strains with numerical abnormalities of chromosomes, mixing the cell strains according to a required ratio for quality control so as to convert each original cell strain with a single numerical abnormality of chromosomes into a chimera quality-control cell strain with a certain ratio of five numerical abnormalities of chromosomes. Therefore, the difficulty for differential diagnosis and chimera diagnosis is increased; the cell strain is used as a quality-control cell strain for diagnosis of common numerical abnormalities of chromosomes; samples are easily available; and waste residual cells are converted into effective immortalized quality-control cells.

The invention discloses a developmental hip joint abnormity ultrasonic image computer intelligent algorithm auxiliary discrimination system, which is used for discriminating whether an image is standard or not, and comprises the following specific technical lines: image preprocessing: for an ultrasonic hip joint image preprocessing part, an original image of an ultrasonic image needs to be acquired for processing in a currently commonly adopted technology, and the original image needs to be processed; processing and screening of ultrasonic images from other sources are not realized,algorithm creation and improvement of image recognition is carried out, an ultrasonic standard image screening algorithm is improved, and the algorithm execution efficiency and the algorithm universality are improved. The system can assist DDH ultrasonic screening work in the early stage, improve the screening work quality, reduce the discrimination difference of medical staff with different learning approaches and different experience bases on standard images, facilitate the improvement of the probability of obtaining the standard images by ultrasonic doctors, improve the screening diagnosis quality, and in the later stage, the creation is more automatic, and personnel can be prevented from mastering ultrasonic inspection details to obtain a high-quality inspection effect.

The invention relates to a fluorescence in situ hybridization hTERT transfected external quality assessment cell line for diagnosis quality control in medical genetics, and a preparation method thereof. The invention is mainly characterized in that the preparation method comprises: performing double digestion of plasmid pCIneo-hTERT and a carrier pLXSNneo by endonucleases of EcoR I and Xho I, connecting the digestion products of hTERT and pLXSNneo by Ligation Mix, constructing a pLXSNneo-hTERT recon, transfecting, by liposome, residual adherent living cells which are in logarithmic growth and are definitely diagnosed to have common numerical abnormalities of chromosomes as needed by clinical diagnosis and treatment, screening cell lines integrated with the recons by G418, performing subculture amplification and cryopreservation, then taking the cell lines, mixing the cell lines according to a required ratio for quality control so as to convert each original cell line with only one numerical abnormality of chromosomes into a chimera quality-control cell line with a certain ratio of common numerical abnormalities of chromosomes. Therefore, the difficulty for differential diagnosis and chimera diagnosis is increased; original cells are easily available; waste residual cells are converted into effective immortalized quality-control cells; external quality assessment is carried out by the difficult quality-control cells; and the cell line of the invention has important significance on in-time discovery and solution of quality problems, and diagnostic level improvement.

The invention relates to the technical field of information, and specifically relates to a medical information voice interaction method, a medical information voice interaction device, a storage medium and an electronic terminal. The method includes the following steps: doctor's advice voice information is received, identification is performed on the received doctor's advice voice information andthe doctor's advice voice information is converted into corresponding doctor's advice text information; structured analysis is performed on the doctor's advice text information and structured text data of the doctor's advice text information is obtained; verification is performed on the structured text data according to reference data of a preset database; and whether the doctor's advice voice information is inputted or not is judged combining a verification result. The doctor's advice information is input by voice with the provided method and device, and performing judgment on rationality andaccuracy of doctor's advice content is realized. Medical mistakes can be effectively reduced, and diagnosis quality is improved.

The invention relates to the technical field of digital electrocardiogram, in particular to a digital electrocardiogram acquisition method which includes the steps: acquiring electrocardiogram data; performing filtering processing on electrocardiogram data according to an electrocardiogram data filtering algorithm to filtered electrocardiogram data; performing dryness and baseline shift removing processing on the filtered electrocardiogram data to obtain electrocardiogram waveform data; transmitting the electrocardiogram waveform data to an upper computer to display the electrocardiogram waveform data. The invention further discloses a digital electrocardiogram acquisition device and a digital electrocardiogram acquisition system. According to the digital electrocardiogram acquisition method, remote electrocardiogram data are acquired, so that the electrocardiogram diagnosis quality of a lower-level medical institution can be controlled by an upper-level medical institution.

The invention discloses a clinical qualitative diagnosis device for a pathology department. The clinical qualitative diagnosis device for a pathology department comprises a bottom plate, wherein threaded holes in the rear side of the upper end of the bottom plate are in threaded connection with threaded holes uniformly distributed at the upper end of a fixed plate through bolts; a microscope is arranged at the upper end of the fixed plate; an objective table is arranged on the middle part of the front side of the microscope; and an adjusting device is arranged at the upper end of the objectivetable. The clinical qualitative diagnosis device for the pathology department is simple in structure, convenient to install and use, firm in fixation, capable of dyeing and observing pathological tissues, moreover, images observed by the microscope can be collected by a data acquisition module, processed and diagnosed by a PLC, and displayed on a display. Reasonable adjustment and moderate fixation of the pathological tissues are realized by an adjusting device and a fixing device, so that the occurrence of poor observation effect caused by shaking is avoided, the work burden of medical staffis reduced, the diagnosis quality is ensured, and the use efficiency of the qualitative diagnosis device is improved.

The invention is applicable to the technical field of medical services and provides a medical service method and system and terminal equipment. The method comprises the following steps of receiving medical detection data, wherein the medical detection data carries patient information; determining the information of physicians responsible for diagnosis and the information of physicians responsiblefor clinical reception according to the patient information; sending the medical detection data to a terminal for the physicians responsible for diagnosis according to the information of the physicians responsible for clinical reception and receiving a diagnostic analysis report sent by the terminal for the physicians responsible for diagnosis according to the medical detection data; sending the medical detection data and the diagnosis analysis report to a terminal for the physicians responsible for clinical reception according to the information of the physicians responsible for clinical reception; receiving a diagnosis and treatment scheme determined by the terminal for the physicians responsible for clinical reception according to the medical detection data and the diagnosis analysis report and sending the diagnosis and treatment scheme to the patient terminal according to the patient information. According to the method, the system and the terminal equipment, medical resources canbe reasonably configured, circulation of the medical detection data is realized, the diagnosis efficiency and the diagnosis quality are improved, and patients can see doctors conveniently.