55 results about "Imaging report" patented technology

A system uses imaging device orientation, location and inclination data to create a link between a medical report statement and a specific image or series of images enabling a user to view a patient imaging report of a patient automatically associating a patient image and a corresponding report statement. A system identifies an anatomical portion of a patient using positional data derived from an imaging device. The system includes an acquisition processor for acquiring positional data of a directional image acquisition unit oriented to acquire an image of a particular anatomical portion of a patient. The positional data corresponds to a particular orientation used to acquire a particular image of the particular anatomical portion of the patient. A repository of mapping data links positional data of the image acquisition unit with data identifying anatomical portions of a patient. An image data processor associates the particular image derived using the image acquisition unit with a particular anatomical portion of a patient using the mapping data.

A system and method that collects and converts raw data and other relevant information related to imaging procedures in order to provide medical personnel, patients, and other authorized parties with a comprehensive media rich report that can be accessed using a platform-independent interface. The invention facilitates the collection and conversion of audio, video, image, and textual data from various sources in order to produce a single comprehensive report that provides the user with maximum utility in evaluating the information derived from one or more the imaging procedures.

The invention discloses a nasopharyngeal carcinoma structured image report and data processing system and a nasopharyngeal carcinoma structured image report and data processing method. The system comprises a clinical data collection module, a fine image analysis and report module, a comprehensive processing module and a clinical decision module, is mainly used for inputting and analyzing nasopharyngeal carcinoma imaging diagnosis report data and comprehensively and systematically recording the nasopharyngeal carcinoma invasion surrounding anatomical structure and lymph node metastasis conditions in a structural data form, and establishes a nasopharyngeal carcinoma structural image report standard for constructing a nasopharyngeal carcinoma image big database and a nasopharyngeal carcinomaartificial intelligence prediction model. According to the system, an MR fine film reading database is established to standardize a nasopharyngeal carcinoma image report, and a set of a nasopharyngealcarcinoma online clinical decision platform is developed on the basis to further assist nasopharyngeal carcinoma staging and typing, treatment scheme recommendation and prognosis prediction, so thatclinicians are helped to well formulate a treatment scheme according to an MRI image evaluation result.

The invention discloses an establishment method of a solitary pulmonary nodule malignancy probability prediction model. The establishment method particularly includes the steps: acquiring basic information of patients and serum tumor marker levels 1-7 days before operation; dividing patient cases into one group with GGO (ground glass opacity) lesion proportion higher than or equal to 50% and another group with GGO lesion proportion lower than 50% according to the GGO lesion proportion and CT (computed tomography) imaging reports of the patients; setting experiment groups and validation groups in each group of cases according to the proportion of 3:1, performing single-factor analysis on relative data of cases of the experiment groups to initially screen independent risk factors; substituting the independent risk factors into multifactor analysis to obtain independent risk factors for judging benign and malignant SPNs (solitary pulmonary nodules); acquiring the SPN malignancy probability prediction model by the aid of Logistic regression; substituting case data of the validation groups into the model, and verifying the case data of the validation groups. The model is simple and easy to use, used indexes can be acquired by the aid of routine examination and are easy to use, and effective intermediate reference information can be provided for further diagnosis and treatment of doctors according to the model.

The invention relates to the technical field of computers. The invention particularly relates to an image recognition model training method, device and system, and an image recognition method, deviceand system. Each image is recognized according to the initial image recognition model, predicted lesion categories of the image images are respectively obtained, and the predicted lesion category is judged according to an image report associated with each image; the lesion category of each image is marked according to the judgment result; according to the marked image images and an initial training image sample set, iterative training is performed to obtain an image recognition model; and then the lesion category of the to-be-recognized image can be recognized based on the trained image recognition model, and the lesion category recognition result of the to-be-recognized image can be determined, so that iterative training is carried out by utilizing the image report, additional labeling cost does not need to be increased, the iterative rate is improved, and the recognition accuracy can be improved along with continuous iterative updating.

A system is disclosed using a data-driven approach to objectively measure the diagnostic accuracy and value of diagnostic imaging reports using data captured routinely as part of the electronic health record. The system further utilizes the evaluation of the diagnostic accuracy of individual radiologists (imagers), subspecialty sections, modalities, and entire departments based on a comparison against a “precision diagnosis” rendered by other clinical data sources such as pathology, surgery, laboratory tests, etc.

The invention provides an image report system. The image report system comprises a report inputting module, a report generating module, an editing module, an inquiring module and a displaying module; the report inputting module is used for inputting a disease type and a diagnosis result of a patient according to basic information of the patient; the report generating module is used for calling a corresponding template in a database according to the disease type of the patient and generating a diagnosis report of the patient according to the personal information and the diagnosis result of the patient; the editing module is used for editing the diagnosis report generated by the report generating module according to opinions of doctors with the permission level from high to low; the inquiring module is used for calling an image report associated with inquiring information in the database according to the inquiring information input by an operator, wherein the image report comprises the diagnosis report and image data; the displaying module is used for displaying the diagnosis report and the image data which are called by the inquiring module in the database and dynamically displaying the image data. According to the image report system, module refinement is achieved, the diagnosis report is automatically generated according to the diagnosis opinions of the doctors, therefore, the diagnosis level of the doctors is increased, and the image report displaying level is increased.

The invention relates to an image report based CT image emphysema automatic labeling method. The method includes the following steps: (1) accomplishing an image report, CT image sequence inputting andimage standardization preprocessing in an input module; (2) extracting the characteristic information, namely the information about emphysema description, in the image report in a phonetic and semantic extraction module according to the technical and rule pattern matching technology of a dictionary; (3) performing regional division on a lung in an emphysema focus extraction module, and performingcluster analysis in a lung area to extract emphysema focus; and (4) obtaining the CT threshold value of each area through calculation according to calculating results of the step 3, labelling the emphysema area of each area in an output and display module, displaying the emphysema areas in a CT image, and giving a quantitative analysis report of lung function. The advantages of the method are that processes during emphysema diagnosis and treatment can be simplified, and medical expenses of patients can be reduced.

The embodiment of the invention discloses an image report generation method and device, a terminal and a medium. The image report generation method comprises the steps: obtaining a target video, converting the target video into N picture frames, and enabling N to be a positive integer; filtering the low-quality pictures in the N picture frames to obtain W qualified pictures, the low-quality pictures including a low-resolution picture, a blurred picture, a hue abnormal picture and an overexposure and overexposure picture, the qualified pictures being filtered pictures, and W being a positive integer; performing identification processing on each qualified picture in the W qualified pictures to obtain W target picture target parts; traversing the target picture of the target part to obtain adetection result of the target part; and generating an image report according to the detection result of the target part. According to the embodiment of the invention, automatic image acquisition andautomatic image report generation can be realized, and the problem of low efficiency of manual image report making is solved.

The invention discloses an intelligent follow-up surveying method of a radiation image report, a system, equipment and a storage medium. The intelligent follow-up surveying method comprises the stepsof acquiring a pathological report of a patient, wherein the pathological report comprises a pathological report time and identity information of the patient; acquiring all image reports in a preset time period before the pathological report time according to the identity information; respectively extracting a pathological diagnosis attribute in the pathological report and an image diagnosis attribute in each image report; respectively matching each set of pathological diagnosis attributes with the image diagnosis attribute in each image report; if matching is unsuccessful, determining an error in the image diagnosis; if matching succeeds, determining a fact that the image diagnosis is correct; marking a label which represents a matching result on the image report; and performing follow-upsurveying on the corresponding patient according to the label. The intelligent follow-up surveying method realizes automatic determining for consistency between image diagnosis and pathological diagnosis, thereby realizing automatic and intelligent diagnosis to the radiation image report.

An embodiment of the invention discloses a method for outputting scanned target information in an ultrasonic imaging system. The method includes creating an imaging report template of a scanned target in an ultrasonic workstation; transmitting ultrasonic waves to the scanned target and receiving ultrasonic echo by an ultrasonic imaging device so as to acquire an ultrasonic image of the scanned target; acquiring the information of the scanned target according to the ultrasonic image; displaying the information of the scanned target on the ultrasonic imaging device; and filling the information of the scanned target into a corresponding position in the imaging report template. When in scanning of the scanned target, the acquired information of the scanned target is transmitted to the imaging report template in real time from the ultrasonic imaging device, a process of inputting the information of the scanned target into an imaging report manually is omitted, imaging report output efficiency is improved, and errors caused by manually inputting related information are avoided.

The invention discloses a medical image report information extraction method and device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the steps of obtaining text information of a medical image report; performing encoding processing on a word sequence in the text information to obtain a word vector corresponding to the word sequence, the word vector being fused with a semantic relationship between context words in the word sequence; carrying out entity information extraction on the word vectors to obtain a structured report text corresponding to the medical image report, the structured report text comprising entities contained in the text information and entity types to which the entities belong. By performing entity information extraction on the medical image report, a structured report text can be generated, writing habits of medical staff are reserved, and universality is achieved.

The invention provides a method for automatically generating a brain CT medical report based on weak supervised attention, relates to the three fields of medical images, computer vision and natural language processing, and designs a weak supervised attention mechanism WGAM to clearly guide an attention model to focus on a focus region so as to improve the accuracy of medical report generation. WGAM is a hierarchical structure and comprises two attention mechanisms of space attention and sequence attention, and the space attention is weakly supervised by a gradient weighted class activation mapping algorithm to obtain a better attention effect. A keyword-driven interactive loop network KIRN is designed as a language generation module to generate a brain CT medical report, a hidden layer state of the language generation module is activated through keyword information containing focus position information, and the accuracy of generating a brain CT image report is improved through dynamic interaction of LSTMword and LSTMsen. According to the method, the work of automatically generating the brain CT medical report is explored for the first time, and effectiveness is achieved.

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 discloses an image exercise data processing method and system and a storage medium, and the method comprises the steps: responding to an image exercise request instruction, and determining to-be-exercised data; receiving a to-be-evaluated image report of the trainee for the to-be-practiced image; obtaining a reference image report corresponding to the to-be-practiced image; and determining the operation quality of the to-be-evaluated image report based on the reference image report. The effective on-duty image exercise and exercise report quality automatic evaluation method is provided for trainees, the accuracy, reliability and efficiency of exercise quality evaluation results are improved, the training effect of image exercise is improved, and the film reading level of thetrainees is effectively improved.

The invention relates to a medical image report generation method and device, computer equipment and a storage medium. The method comprises the following steps: analyzing image data of a patient to obtain focus information and a disease type of the patient, obtaining a section image of a focus part of the patient according to the focus information and the image data, and obtaining pathological description information from a preset pathological knowledge base according to the disease type and the focus information, and finally, adding the pathological description information and the section image to the initial report template, obtaining an auditing result after auditing the added initial report template, and generating a medical image report of the patient according to the auditing result. In the process of generating the medical image report, due to the fact that the focus information, the disease type, the section image and the pathological description information are all obtained through automatic analysis of the medical terminal, the method can efficiently generate the medical image report, and the problem that the generated medical image report is inaccurate due to insufficient experience of doctors can also be solved.

The invention relates to an image report generation method and device and a storage medium. The method comprises the steps of obtaining a preliminary detection result obtained based on a medical imageof a to-be-detected object; based on the preliminary detection result, determining a target medical term and target detection content corresponding to the preliminary detection result in a preset first report database, wherein the first report database comprises a plurality of detection results and medical terms and detection contents corresponding to each detection result; and filling the targetmedical term and the target detection content into corresponding positions in an initial image report template by adopting a preset editing mode to obtain an image report of the to-be-detected object. By adopting the method, manpower and time can be saved.

The invention provides a medical image lesion position viewing method and system, equipment and a storage medium. The method comprises the following steps: acquiring user information currently looking up a medical image; associating and displaying the historical medical image and the historical image report according to the user information; acquiring a task of clicking certain focus description information on the historical image report; searching and positioning all historical images containing the lesion description information in historical medical images and historical image reports; and displaying the historical image containing the focus description information and the current consulted medical image on the same screen.

The invention relates to an imaging diagnosis report named entity recognition method based on multi-feature fusion, and belongs to the technical field of natural language processing. The method comprises the steps of firstly copying a chest X-ray film image report from a hospital information management system to serve as an experimental corpus, and preprocessing the corpus; inputting the preprocessed diagnosis report text data into a BI-LSTM network, and outputting an optimal word segmentation result; obtaining a feature vector of the optimal word segmentation result, then sending the featurevector to a CRF model to carry out named entity identification on the diagnosis report text, and training to obtain an image diagnosis report named entity identification model based on multi-feature fusion; and evaluating the obtained image diagnosis report named entity identification model, selecting an optimal model according to a test result, and performing image diagnosis report named entity identification according to the model. The named entity in the image report is effectively identified, and the final total F1 value reaches 88.03%.

The invention discloses a magnetic resonance intelligent imaging method, device and equipment and a storage medium. The method comprises the steps of scanning a preset part of a patient to obtain a first scanning image; selecting a first positioning point and a second positioning point in the first scanning image, and acquiring image information of the first positioning point and the second positioning point; determining a target imaging parameter corresponding to the optimal image information difference between the first positioning point and the second positioning point according to a preset target function, and/or determining a target radio frequency sequence function corresponding to the optimal image information difference between the first positioning point and the second positioning point according to a variational optimization method; and scanning the preset part of the patient again according to the target imaging parameter and/or the target radio frequency sequence function to obtain a second scanning image. The invention can solve the problem that small lesions are missed due to the fact that image analysis of magnetic resonance imaging needs to depend on manual recognition of clinicians; therefore, the diagnosis accuracy of magnetic resonance imaging and objectivity and standardization of image reports are improved, and the working efficiency of the clinicians is improved.

The invention provides an image quality evaluation system based on a structured template, and the system comprises an evaluation template configuration module which configures an image quality evaluation template based on an inspection item, and enables evaluation parameters to be distributed on an image quality evaluation interface in the form of a control, a patient information configuration module which arranges the examination information of the patient on an image quality evaluation interface in the form of a control to form a patient information template, an association module which embeds the image quality evaluation template and the patient information template corresponding to the examination item into an image report template under the examination item, generates an image qualityevaluation control and displays the image quality evaluation control on the image report template, and an evaluation generation module which is used for automatically displaying an image quality evaluation interface on the image report interface of the patient when the doctor clicks the image quality evaluation control. The invention further discloses an image quality evaluation method based on the structured template. According to the invention, a personalized scanning quality feedback scheme can be provided to carry out continuous iteration on the image scanning knowledge base, and continuous improvement of image scanning normative training of an image technician is realized.

The invention discloses an image report pushing method and device based on RPA and AI and a computing device, and the method comprises the steps: carrying out the segmentation of a to-be-detected lung medical image sent by an RPA robot through a preset lung segmentation model to obtain a target medical image only containing a lung region, detecting the target medical image by using a preset pulmonary nodule detection model to obtain attribute information of each suspected pulmonary nodule, and segmenting an area where each suspected pulmonary nodule is located by using a preset pulmonary nodule segmentation model to obtain three-dimensional contour information of each suspected pulmonary nodule; and generating a suspected lung nodule image report according to the attribute information and the three-dimensional contour information of each suspected lung nodule, and sending the suspected lung nodule image report to a hospital platform through the RPA robot. The lung nodules are detected through the AI image analysis technology to obtain the suspected lung nodule image report, and the suspected lung nodule image report is sent to the hospital platform through the RPA robot, so that the time for a doctor to distinguish the lung nodules is shortened, and the efficiency is improved.