66 results about "Medical report" patented technology

The invention discloses a medical report generation method, a model training method, equipment and a medium, and the model training method comprises the steps: constructing a medical report generation model framework which comprises a global semantic collaborative multi-modal enhancement module, a visual encoder, a text encoder, a medical insight analyzer and an LLM decoder; wherein the global semantic collaborative multi-modal enhancement module respectively enhances a medical image and a medical report by utilizing a selected image enhancement strategy and a text enhancement strategy, and the medical insight analyzer comprises a fine-grained structure learning device and a global context guide learning device which are connected in sequence so as to enhance the cross-modal alignment capability; and performing intelligent collaborative optimization by taking a strategy set formed by an image enhancement strategy and a text enhancement strategy and architecture configuration parameters of the medical insight analyzer as optimization targets to obtain an optimal medical report generation model. The medical report generation performance can be effectively improved.

The invention relates to the technical field of medical natural language processing, in particular to a medical report automatic analysis and structured generation method based on a multi-modal vision-language model. The method comprises the following steps: S1, acquiring a target medical image and an initial text report corresponding to the target medical image, and performing feature extraction and preprocessing to obtain a multi-level visual feature sequence and a text feature sequence; s2, obtaining at least one focus-description cluster corresponding to the independent clinical semantic unit according to the multi-level visual feature sequence and the text feature sequence; s3, for each focus-description cluster, the fuzzy medical description in the focus-description cluster is converted into structured attribute information with a deterministic state label; and S4, based on all the focus-description clusters and the corresponding structured attribute information, carrying out content assembly and generation under logic constraints, and outputting a structured medical report with a confidence identifier. According to the invention, deep understanding and high-reliability structured output of the medical report are realized.

The invention relates to the technical field of medical report generation, and discloses a medical image automatic annotation and report generation system which comprises a preprocessing module, a hierarchical feature extraction module, a semantic annotation module, a guide generation module, a diagnosis reasoning module and a man-machine cooperation interface. According to the method, through standardized preprocessing, hierarchical feature extraction and automatic generation of the annotation and the report, the processing efficiency is greatly improved, and the manual load is reduced; secondly, on the basis of hierarchical feature extraction and semantic and visual embedding alignment, feature support and semantic mapping precision of annotation and reporting are enhanced, and result accuracy and cross-scene consistency are improved; meanwhile, multi-modal alignment processing and multi-dimensional information fusion enhance the adaptability of the system to different image types, generate a structured report conforming to the clinical process and improve the clinical applicability; in addition, a man-machine cooperation feedback mechanism forms a parameter optimization closed loop, so that the system dynamically adapts to new scenes and specifications, and continuous improvement of generalization ability is realized.

The invention discloses a learnable radiology report generation method based on visual text alignment and fusion of retrieval enhancement. The method comprises the steps of collecting and respectively constructing a model training data set and an auxiliary data set, then constructing a visual text alignment and fusion model based on retrieval enhancement, and inputting the model training data set and the auxiliary data set into the visual text alignment and fusion model based on retrieval enhancement together for training. Constructing an inference model according to the trained visual text alignment and fusion model based on retrieval enhancement; and inputting the to-be-detected medical image and the auxiliary data set into the reasoning model for processing to obtain a radiology report corresponding to the to-be-detected medical image. According to the method, retrieval correlation is enhanced, meanwhile, a fine-grained vision-text alignment and fusion method is adopted to align and fuse features, and the problem that fine-grained region-sentence alignment is difficult due to weak supervision of an image report level in the medical report generation process is solved.

Examples of the present disclosure describe systems and methods for using AI to identify regions of interest (ROI) in medical images. In aspects, medical reports and images may be provided to a second environment. The second environment may use the medical report data / medical images to train a natural language processing (NLP)-based algorithm to identify the location in images of ROI described in the medical report data. The output of the NLP-based algorithm may be stored in an ROI repository in the second environment. After the NLP-based algorithm has been trained, a request to train a user-specific model may be received in a first environment. Data objects for the requested user-specific model may be provided to the second environment, which uses the ROI repository to train the model. The trained model may be provided to the first environment, where the trained user-specific model / algorithm may be tested and stored.

An apparatus for the generation of a medical report is disclosed. The apparatus includes at least processor and a memory communicatively connected to the processor. The memory instructs the processor to receive a user query. The memory instructs the processor to receive a user profile comprising a plurality of medical tests. The memory instructs the processor to generate testing data as a function of the plurality of medical tests using an encoder. The memory instructs the processor to generate textual data that is representative of the testing data using a querying transformer model (Q-former). The memory instructs the processor to generate a medical report as a function of the user query and the textual data using a report large language model (LLM).

The invention belongs to the technical field of image processing, and particularly relates to a medical report generation method based on dual-path multi-level semantic alignment, which comprises the following steps: constructing a dual-path multi-modal feature extraction network, fusing static-dynamic collaborative paths of MedCLIP and a context sensing module and universal visual representation of ViT, and generating a medical report based on multi-level semantic alignment. Specific feature extraction and wide visual semantic understanding in the medical field are coordinated and balanced. Through a CLIP-driven hierarchical cross-modal alignment mechanism, global coarse-grained mapping based on comparative learning and local fine-grained interaction based on bidirectional attention are cooperatively executed, and heterogeneous visual features and text semantics are accurately projected to a unified metric space. The problems that feature representation is deficient and cross-modal alignment granularity is single in the prior art are solved. And multi-level alignment loss and autoregression generation loss are integrated in an optimization target, so that the generated report is ensured to have high clinical fidelity and keep the continuity of language logic at the same time.

The invention relates to a computer-implemented method for providing a medical finding to a requesting entity, the method comprising a plurality of steps. A step is directed to obtaining at an evaluating entity, medical image data from a requesting entity, the requesting entity being remote from the evaluating entity. Another step is directed to determining, at the evaluating entity, at least one medical finding based on the obtained medical image data. Another step is directed to generating transmission image data. Another step is directed to embedding at least one of the determined medical findings as text in the transmission image data. Another step is directed to providing the at least one medical finding to the requesting entity by means of transmitting the transmission image data to the requesting entity.

The invention relates to the technical field of medicine safety monitoring, in particular to an individual case safety report automatic scoring system based on a large model. The system comprises a report receiving module, a deep semantic understanding module, a dynamic graph structure construction module, a graph neural network scoring module and an interpretability output module. Deep semantic analysis is carried out through a large language model pre-trained in the medical field, a multi-dimensional semantic graph with time sequence characteristics is constructed, a graph neural network based on an attention mechanism is utilized to carry out multi-round iterative reasoning to generate scores, and reasoning process interpretation based on a critical path is provided. According to the method, medical report semantics can be deeply understood, the dynamic relation between entities is accurately captured, the scoring accuracy and interpretability are improved, and reliable technical support is provided for drug safety monitoring.

Described herein are method, system, and apparatus for correlating medical images with a medical report. An apparatus may obtain a plurality of medical images of a patient and a medical report for the patient, wherein the plurality of medical images may be associated with respective sequence labels and respective view labels, and wherein the medical report may include multiple diagnoses. The apparatus may determine and fuse respective image-type embeddings and image-content embeddings for the plurality of medical images into a combined image feature representation. The apparatus may further encode the features of the medical report into a text feature representation and calculate a similarity score based on the image feature representation and the text feature representation to indicate a correlation between the medical images and the medical report.

The invention relates to an ultrasonic imaging medical report generation method and device and computer equipment. The method comprises the following steps: acquiring an inspection record description standard audio file of ultrasonic image inspection, and performing identification processing on the inspection record description standard audio file to obtain an inspection record text; obtaining ultrasonic examination doctor's advice information of ultrasonic image examination, and performing ultrasonic image medical report template matching processing according to the ultrasonic examination doctor's advice information to obtain a target ultrasonic image medical report template; and obtaining a target cue word, and inputting the examination record text, the target ultrasonic image medical report template and the target cue word into the large language model to obtain an ultrasonic image medical report of the ultrasonic image examination. By adopting the method, the efficiency and the accuracy can be improved.

Embodiments of the present specification relate to a method and device for generating a medical report based on evidence-based medicine, the method comprising: obtaining patient information and an original clinical question; inputting the patient information, the original clinical question and a first prompt word into a target model to generate a structured clinical question; the target model being a large language model in the medical field; retrieving a medical literature database according to the clinical question to obtain a plurality of medical literatures; inputting the target medical literature and a second prompt word into the target model to enable the target model to perform bias risk assessment on the target literature to generate a structured initial assessment result of the target literature; inputting the clinical question, each medical literature and its initial assessment result and a third prompt word into the target model to enable the target model to perform step-by-step reasoning based on a GRADE evaluation process in the third prompt word to generate a medical report; the medical report including a medical recommendation for the clinical question, a recommended strength of the medical recommendation and an evidence quality level.

A myocardial injury condition detection system based on image characteristics. The system comprises an image acquisition module, a feature extraction module, a data processing module and a report generation module, wherein the image acquisition module is used for acquiring high-resolution cardiac image data information; the feature extraction module is used for extracting, from the acquired image data information, feature information related to the cardiac structure and function; the data processing module is used for analyzing the extracted feature information, so as to identify myocardial-injury-related conditions; and the report generation module is used for generating a medical report of the myocardial-injury-related conditions for a doctor. By means of comprehensively analyzing cardiac image data information of a patient, a more comprehensive and accurate assessment of myocardial injury conditions is provided, thereby improving the accuracy and effectiveness of medical diagnosis.

One or more example embodiments of the present invention relates to methods and apparatuses for providing a medical report in a medical network having a front-end computing facility and a back-end computing facility.

The invention relates to the technical field of data processing, and particularly discloses an online multi-modal content data analysis method and system which are particularly suitable for scenes such as medical records and medical reports. In order to solve the problems that in the prior art, multi-modal data processing efficiency is low, defect recognition is not comprehensive, report generation is cumbersome, and the burden of doctor documents is heavy, the method comprises the steps that online multi-modal content data containing texts, images and structured data are obtained, and content defects such as logic errors, inconsistent formats and information missing are analyzed and recognized; based on defects, targeted optimization suggestions are generated, a structured report containing standardized formats and content abstracts is automatically generated according to the suggestions, the report is output, interactive revision is supported, and technologies such as cross-modal fusion, variable binding and quality verification are integrated in the process. According to the method, the multi-modal content processing efficiency and quality can be remarkably improved, the document workload of a physician is greatly reduced, and the physician is assisted to concentrate on precise treatment and deepen medical services.

1. The name of the design product: graphical user interface for electronic device AI to create health records. 2. The use of the design product: for electronic devices. 3. The design points of the design product: in the graphical user interface. 4. The picture or photo that best shows the design points: front view. 5. Common design, omit rear view, pitch view, left and right view. 6. The use of the graphical user interface: graphical user interface for electronic device AI to create health records. The front view is the uncompleted page of creating health records, and the user can choose different family identities of the member in the membership column. Slide up to enter interface change state figure 1 to view basic information. Click "AI helps me fill" in interface change state figure 1 to enter interface change state figure 2. Click "I know" to indicate that the user agrees and enters interface change state figure 3. In interface change state figure 3, the user can quickly upload the report or medical report to fill in the health records automatically by AI analysis. Click "Select file" to upload PDF format documents, which enters interface change state figure 4. Click the selected material to enter interface change state figure 5. Interface change state figure 5 is the AI analysis processing page after the successful uploading of the building record materials, which dynamically displays the analysis processing effect, and the analysis processing is completed into interface change state 6. Interface change state 6 is the confirmation page after the AI building record has identified the result, and the user can choose "not to record" or "to record". The "X" and single color block in the view are changeable text and pictures. Reference can be made to the use state reference figure 1-use state reference figure 6.

This invention discloses a method for identifying mental illnesses combining electronic medical records and electroencephalogram (EEG) signals, comprising: acquiring electronic medical records and the corresponding patient's raw EEG signals; labeling patients based on disease type, and combining the labels, electronic medical records, and raw EEG signals into a dataset; constructing an initial model based on a large language model and a prior mental illness knowledge base, wherein the initial model includes an agent scheduling module, a data processing module, and a prediction module; and training the initial model using the dataset to obtain a multimodal predictive agent model for mental illnesses used to generate medical reports. The method provided by this invention enables multi-scale, multi-channel, and multi-feature exploratory analysis of EEG signals at any specified time slice, and jointly reasoning with medical record features and a mental illness knowledge base to generate structured diagnostic conclusions and interpretable reports.

The invention discloses a medical image diagnosis method, device and system and a storage medium, and the method comprises the steps: carrying out the preliminary diagnosis of a medical image through a medical context big language model, and generating a medical report; quantifying the credibility of each sentence in the medical report by using an uncertainty measurement algorithm to obtain a credibility score; dynamically marking report contents by using color gradient mapping, and highlighting high-risk diagnosis entries; generating a structured visual thermodynamic diagram for each sentence of report by utilizing an explainable method based on explicit attribution and an attention mechanism; a React-based front-end interaction framework is utilized to integrate visual interpretation and report editing functions, explainable diagnosis decision basis and risk entry early warning are provided, and doctors are assisted in visual and rapid targeted verification; a continuous learning framework is adopted, feedback of doctors is collected, and sentence-level correction and a flexible training strategy are introduced to continuously optimize diagnosis precision. According to the invention, the interpretability and continuous learning ability of medical image diagnosis are improved.

The application provides a multi-modal medical report structured analysis method, system, device, medium and program product, and relates to the technical field of deep learning and medical image report analysis. The method comprises the following steps: identifying an input multi-modal file to obtain content information contained in the file; performing feature extraction on the content information to obtain a disease feature vector, and performing weighting processing on the disease feature vector to obtain corresponding disease information; performing weighted evaluation and marking on the disease data, and outputting the marked disease data. The application has the advantages of workflow context optimization and scalability based on modular skill units, noise robustness and illusion suppression in multi-modal data fusion, and disease extraction and missing detection avoidance with fine-grained context perception.

This invention discloses a method, system, device, and medium for patient self-service medical report interpretation and triage in public lobby scenarios. The method is applied to a physically isolated, independent, integrated self-service terminal without an external network module. The terminal deploys a local multimodal large-scale model and a composite local medical knowledge base. Upon responding to patient commands, the terminal generates a single-session token and establishes a transient isolation sandbox to reject concurrent requests, thereby acquiring and processing heterogeneous medical report data. Subsequently, the multimodal large-scale model is invoked to extract abnormal indicators and perform retrieval and matching, generating simplified interpretation text that masks complex mechanisms and offline department recommendations. Finally, after a one-way display of results, once the session ends, a hardware-level clear command is immediately triggered to completely erase the session data and inference cache. This invention effectively protects patient privacy, provides professional and easy-to-understand medical report interpretation in a network-free environment, and prevents data residue and leakage.

The invention relates to a method (500) for automatically generating a pre-consultation medical report, the method being implemented by computer and comprising: a step (510) of collecting data from a patient (P) via an adaptive electronic questionnaire (Q), proposing questions which are adapted as the answers are provided; a step (520) of structuring the collected data in graphs (G); a step (530) of pre-processing the collected data in order to eliminate errors and inconsistencies; a step (540) of predictive analysis of the pre-processed data by means of machine learning models (40), making it possible to extract from the graphs (G) information that is useful for a medical consultation; and a step (550) of automatically generating a specialised report (R), in medical language, intended for a healthcare practitioner (D).

The invention provides a medical report interpretation method and device, equipment and a storage medium, and relates to the technical field of computers, in particular to the technical field of AI medical treatment. According to the specific implementation scheme, an image of a medical report is acquired; structured processing is carried out on the image of the medical report, structured data corresponding to the medical report is obtained, and the structured data at least comprises all examination index items in the medical report and examination data of the examination index items; determining an abnormal index item from each inspection index item in the structured data; based on the abnormal index items in the structured data, generating an interpretation task instruction of a medical report interpretation model, the interpretation task instruction being used for instructing the medical report interpretation model to interpret the abnormal index items in the structured data; and inputting the interpretation task instruction into the medical report interpretation model to obtain an interpretation result. According to the method, the accuracy and high efficiency of the medical report interpretation process can be realized.

A computer-implemented system for automatically generating patient-specific medical reports includes a data collection module configured to obtain patient-specific information, including patient-specific diagnostic information and communication-related patient-specific meta information. The system further includes an artificial intelligence (AI) module configured to process the obtained patient-specific information to generate a patient-specific report in a format tailored to the patient's language, education, and expectation level, wherein the AI module includes a pre-trained language model trained using medical terms, texts, reports, and related images for different age, language, and educational level groups. The system further includes an output module configured to output the generated report.

This application discloses a training method for a data processing model, a data processing method, and an apparatus, belonging to the field of artificial intelligence technology. The method includes: determining first slice features and first report features based on a first slice image and a first medical report using a neural network model. The first slice features represent the feature content of the first slice image extracted under the guidance of the first medical report, and the first report features represent the feature content of the first medical report; determining a first prediction result based on the first slice features and the first report features, the first prediction result representing the probability of an event occurring in a first object; and training the neural network model based on the first prediction result to obtain a data processing model. Since both the first slice features and the first report features have high accuracy and can provide more comprehensive information, the data processing model has high accuracy and can obtain more accurate data processing results.

To provide a medical report generation method, a medical report generation system, and a program, which reduce a load on preparing a medical report.SOLUTION: A medical report generation method includes acquiring a medical image, performing first image processing on the medical image on the basis of a human body portion and clinical index information related to the medical image, and then generating and displaying a medical report preliminarily written. When a user inputs radiograph interpretation information on a new clinical index to the medical report, a radiograph interpretation information keyword is generated on the basis of the radiograph interpretation information, and a retrieval label that is sorted according to a matching degree between the radiograph interpretation information keyword and label description corresponding to a retrieval label, which matches the radiograph interpretation information keyword and is to be a candidate of the new clinical index, is presented to the user. The method includes performing second image processing corresponding to the retrieval label selected by the user on the medical image and complementing the medical report according to a detection result obtained by performing the second image processing.SELECTED DRAWING: Figure 2

The invention relates to a medical image report generation method and a program product. The method comprises the following steps: acquiring a medical image of a target object and a text cue word corresponding to the medical image; inputting the medical image and the text cue word into a medical report generation model for processing, and generating an initial medical report; inputting the medical image into a target disease classification model for target disease detection to obtain a detection result; and fusing the detection result into the initial medical report to form a medical image report of the target object. By adopting the method, the medical image report can be automatically generated, and the medical image report does not need to be written manually in the process, so that the generation efficiency of the medical image report can be improved. In addition, the accurate detection result and the initial medical report are fused in the medical image report, so that the accuracy of the medical image report can be improved.

The utility model provides a printing mechanism of a self-service inquiry machine, which relates to the technical field of medical report printing and comprises a self-service inquiry machine main body and a printing output module which is integrated at the top of the self-service inquiry machine main body and comprises a report printer and a report taking port communicated with a report outlet of the report printer, the report outlet of the report printer is located in the report taking opening, large-size reports and small-size reports are stored in a partitioned mode through the upper report taking hopper and the report taking opening, and the situation that multiple reports of different sizes are mixed, and when a patient takes the reports, the small-size reports clamped in the large-size reports slide outwards can be avoided; the problems that in the printing process of a plurality of mixed reports of different sizes, the reports of different sizes fall into a report taking opening in a mixed mode, and when a patient takes the reports, small-size reports clamped in large-size reports slide outwards and fall to the ground, so that the reports are contaminated are solved.

The disclosure provides a unified system and method for analyzing 3D medical images through probabilistic masking, multimodal embedding generation, anomaly detection, and reinforcement learning-based refinement. The methods comprise applying ailment-aware probabilistic masking to 3D medical scans using prior distributions of known abnormalities to retain diagnostically relevant voxel regions. The masked scans are encoded into latent vectors using a vision transformer encoder, while associated textual medical reports are encoded using a language model; both are mapped into a shared embedding space. Anomaly detection is performed through (1) a temporal comparison method based on differences in patient embeddings across time, and (2) a similarity-based method comparing current embeddings to a database of known abnormal cases using cosine similarity. Reinforcement learning is applied to refine embeddings using human expert feedback, including corrected annotations and textual clarifications, allowing dynamic adjustment of thresholds and encoder parameters. This adaptive framework supports efficient, scalable, and accurate medical diagnosis across a variety of imaging modalities.

Techniques regarding autonomously facilitating the optimization of medical information to generate structured medical information are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a receiving component that receives Fast Healthcare Interoperability Resources (FHIR) from a FHIR server. The computer executable components can also comprise an extraction component that extracts unstructured information for medical reports by using a tree of large language model (LLM) prompts and logic for navigating the tree as a function of prompt responses. The computer executable components can also comprise a generation component that generates JavaScript Object Notation (JSON) structured data, and integrates it into original FHIR resources.

A method includes visually displaying an electronically-formatted medical report, where the electronically-formatted medical report refers to a set of electronically-formatted images; collecting a set of the images in the electronic format; and linking the electronically formatted medical report with the set of electronically formatted images. A computing device (102) includes: a memory (108) having at least one computer readable instruction (106); and a processor (104) that executes the at least one computer readable instruction. The processor, in response to executing the at least one computer-readable instruction, visually displays an electronically-formatted medical report, where the electronically-formatted medical report refers to a set of electronically-formatted images; collecting a set of the images in the electronic format; and linking the electronically formatted medical report with the set of electronically formatted images.