55 results about "Lesion analysis" patented technology

The invention relates to the technical field of medical detection, in particular to a sacroiliac arthritis judgment method and system based on X-rays, and the method comprises the steps of multi-modal data synchronous collection, image data real-time optimization and control, cross-modal causal reasoning and three-dimensional reconstruction, and AI-based lesion preliminary analysis and dynamic grading and interpretability report generation. According to the method, a real-time image processing technology is integrated in a data acquisition stage, an original image is directly and dynamically optimized at an imaging end, and the image resolution and the detail definition are improved through an advanced enhancement algorithm; the problems of delay and detail loss caused by relying on post-processing in a traditional method are solved, so that a doctor can obtain a high-quality diagnosis image in real time; by means of the optimization, the requirement for repeated shooting is reduced, and the availability and diagnosis efficiency of images are remarkably improved.

The invention provides an image lesion attribute prediction model training method, a prediction method and a related device, and the method comprises the steps: carrying out the visual coding of a fundus image sample through a visual encoder, and obtaining a pseudo-image visual feature; performing text coding on each lesion attribute sub-category description text to obtain lesion attribute sub-category features; performing matching according to the visual features of the pseudo image and the lesion attribute sub-category features to obtain a pseudo matching probability; performing visual coding on the fundus image sample through the initial image lesion attribute prediction model to obtain initial image visual features; performing matching according to the initial image visual features and the lesion attribute sub-category features to obtain a predicted matching probability; carrying out loss calculation according to the pseudo matching probability and the predicted matching probability to obtain a target matching loss function; and updating the initial model based on the target matching loss function to obtain an image lesion attribute prediction model. In conclusion, the lesion analysis accuracy of the fundus image can be improved.

The present disclosure relates to a dental lesion detection method and a system to which the method is applied. A dental lesion information visualization method according to the present disclosure includes the steps of acquiring data of a lesion analysis model which outputs data on the type and location of a lesion included in a panoramic image obtained by capturing an image of the oral cavity of a patient, and inputting a panoramic image into the lesion analysis model to output data on the type and location of a lesion and a lesion detection confidence score.

The invention relates to a diabetic retinopathy fundus photography grading report system combined with a clinical guide, based on an artificial intelligence deep learning technology, and belongs to the field of fundus lesion analysis. The system accurately identifies and segments various lesions such as microhemangioma, bleeding, exudation and the like and symbolic structures such as optic discs, macular regions and the like by automatically analyzing fundus photographic images. The system adopts ICDR international standards to grade diabetic retinopathy, and provides diagnosis and treatment suggestions for lesion characteristics in combination with clinical guidelines of American ophthalmology institute in 2019. Through big data training, the system can generate detailed reports in real time, the early screening rate is remarkably improved, misdiagnosis and missed diagnosis are reduced, and the diagnosis speed and accuracy are improved. The system comprises a plurality of modules, such as an image pre-classification module, a deep learning focus recognition module, an ICDR grading module and a report generation module, efficient and accurate diabetic retinopathy diagnosis and grading are cooperatively achieved, and the clinical management level is improved.

The present invention discloses a deep learning-based method for automatic segmentation of intravascular lipid plaques. The method utilizes an improved U-Net++ network architecture to achieve high-precision segmentation of the inner and outer membranes of blood vessels. Based on this, a K-means clustering algorithm based on grayscale values, edge features, and texture features is then employed. By incorporating a memory mechanism, stability and consistency are ensured during the clustering process, enabling accurate classification of plaque types. By using an improved U-Net++ network for inner and outer membrane segmentation in ultrasound and photoacoustic images, the present invention can accurately distinguish between different structures of the vascular wall, thereby achieving accurate identification, high-precision segmentation, and classification of lipid plaques. The K-means clustering algorithm, optimized based on feature selection and a memory mechanism, achieves relatively accurate and stable classification results in virtual histology, providing a reliable foundation for further lesion analysis and clinical application.

The invention provides a throat reflux disease detection method and system based on a laryngoscope image and an RFS-Net algorithm, and relates to the technical field of medical image intelligent detection.The method comprises the following steps that a laryngoscope image sample is obtained and preprocessed, and a standard image is obtained; inputting the standard image into the RFS-Net model, and extracting spatial features and spectrum features; carrying out model training based on an improved Focal Loss function in combination with the extracted spatial features and spectrum features, and balancing sample distribution; fusing the shallow texture features and the deep semantic features of the image samples through a residual attention mechanism RAM; performing lesion analysis on the patient data in combination with clinical indexes and fusion features, and outputting a detection result; according to the method, multi-dimensional feature extraction and fusion are performed on the laryngoscope image through the RFS-Net model, spatial features and frequency spectrum features are covered, the features of the throat reflux disease can be identified more accurately in combination with the improved Focal Loss function optimization model training, and misdiagnosis and missed diagnosis conditions are reduced.

This invention relates to the field of medical information management technology, including an AI-based endometriosis management system. The system comprises a thickness dynamic monitoring module, an inflammation level assessment module, a lesion spread analysis module, a periodic lesion tracking module, and a disease progression analysis module. In this invention, AI is used to segment ultrasound image data, enabling dynamic monitoring of lesion areas. Lesion boundaries are extracted, and changes in local inflammatory marker concentrations are calculated, making the screening of abnormal inflammatory areas more accurate and enabling early identification of lesion development. The tracking of periodic lesions, combined with analysis of lesion contour changes and area increases / decreases, enhances the quantitative control of disease progression. The future development trend of lesions, combined with the calculation of periodic inflammatory pathways, makes the prediction of disease evolution more consistent with physiological changes. Multi-dimensional lesion analysis combined with AI intelligent calculation expands the diagnosis and treatment of endometriosis from static assessment to dynamic trend prediction, improving the adaptability of personalized treatment plans.

The application provides a blood vessel lesion determination method and device, electronic equipment and storage medium. The determination method comprises: inputting acquired no-label images and labeled images as input images into a blood vessel lesion analysis model in a single-alternating input manner; if the input image is a no-label image, training the blood vessel lesion analysis model according to a reconstruction loss function; if the input image is a labeled image, determining whether the reconstruction loss function, a lesion type loss function and a lesion degree loss function simultaneously satisfy a target condition, and if the target condition is satisfied, obtaining a trained blood vessel lesion analysis model; and determining a lesion type result and a lesion degree result of a blood vessel image according to the trained blood vessel lesion analysis model. The technical solution provided by the application can reduce manual labeling operations, reduce the workload of doctors, and ensure the accuracy of blood vessel lesion determination.

The application discloses an old person free breathing coronary artery scanning image lesion analysis system and relates to the technical field of scanning image lesion analysis. In order to solve the problem that the accurate condition of a patient cannot be obtained according to a scanning image. The application adopts a diameter method, an area method and a contrast agent filling condition to judge the stenosis degree and the hemodynamic change, analyzes the lesion from the morphological and functional double angles, provides comprehensive information for clinical decision-making, identifies the R wave peak value and divides the cardiac phase, matches the respiratory signal and the projection data in time, can accurately capture the characteristics of the heart in different motion states and the respiratory stage, effectively avoids the interference of the artifacts caused by the heart beat and the respiratory motion, makes the reconstructed image clearer and more accurate, sets the CT and the injector parameters in sequence from the scanning type confirmation, each link is closely related and the target is clear, improves the work efficiency, and is convenient for quality control and process management.

This invention discloses a kidney pathology image processing method integrating multi-tissue segmentation and quantitative lesion analysis, belonging to the field of medical image processing technology. The method includes the following steps: acquiring and preprocessing PAS-stained whole-slice images of kidney pathology; fine-tuning the segmentation model using an unsupervised domain adaptive strategy to address batch-to-batch staining differences; inputting the preprocessed image into a multi-class semantic segmentation neural network to obtain tissue segmentation results; training the network based on pixel-level annotations, employing a Class-Token mechanism, encoder-decoder architecture, and multi-scale feature fusion, and optimizing the Dice loss and binary cross-entropy loss based on joint weighting of categories and boundaries; performing statistical analysis based on the segmentation results and outputting quantitative analysis results. This invention provides an objective, reproducible, and intelligent auxiliary tool for the accurate assessment and large-scale clinical research of chronic kidney disease.

Disclosed is a method for analyzing a lesion based on a medical image performed by a computing device. The method may includes generating, by using a pre-processing module, an input image of a pre-trained detection module from the medical image. The method may include generating, by using the detection module, a probability value regarding a presence of a nodule in at least one region of interest and first location information about the at least one region of interest, based on the input image. The method may include determining, by using a post-processing module, second location information about a suspicious nodule present in the medical image from the first location information, based on the probability value regarding the presence of the nodule.

The invention relates to the technical field of artificial intelligence, in particular to a concept activation vector-based medical image lesion analysis and clinical decision interpretation system, which comprises a feature analysis module, a semantic mapping construction module, a concept activation extraction module, a boundary response fusion module and an interpretation path generation module. According to the method, the gradient direction and the gray abrupt change position of continuous elements in a focus area are detected, texture density and edge consistency are jointly judged to generate structured alignment mapping, microscopic image features are accurately captured, cross comparison is carried out on co-occurrence probability of lesion nouns and modifiers in phrase combinations and activation frequency of the same area, and therefore the accuracy of the lesion nouns and the modifiers in the phrase combinations is improved. Constructing a deep correlation map of pathological semantics and image features, screening an activation group according to continuous response of phrase pairs and image regions under case input change, generating a concept vector trigger track to dynamically track pathological feature evolution, and performing clinical consistency judgment; and an interpretable decision basis with strict logic support is output while subjective interference is eliminated.

The present application relates to a kind of multi-center medical image lesion typing methods based on federal spectrum clustering, belong to medical image analysis technical field, including the following steps: S1: multiple medical institutions are regarded as federal learning client, and the medical image data and supporting clinical data of each client local are obtained and stored in each client local;S2: feature extraction and multimodal feature fusion are carried out in each client local, and multimodal lesion feature set is obtained;S3: center server and each client pass through iteration communication, and the multimodal lesion feature set is jointly clustered using federal spectrum clustering algorithm, until global clustering center converges;Only transmission encrypted statistical parameters in communication process;S4: according to clustering result, output lesion typing information.The present application solves the pain points of difficult data sharing and high privacy leakage risk in traditional centralized lesion analysis, and improves the lesion typing accuracy in heterogeneous data scenario.

The invention provides a Mama-based membranous nephropathy multi-mode pathological image quantitative analysis system and method, and belongs to the crossing field of biomedical engineering and artificial intelligence. The problems that in an existing membranous nephropathy diagnosis system, the diagnosis process is high in subjectivity, single-mode analysis is limited, lesion feature quantification is insufficient, and model calculation is complex are solved. According to the technical scheme, the system comprises an image preprocessing module, the image preprocessing module is in communication connection with a macroscopic lesion analysis module, a microstructure analysis module and a thickness quantification module, and the macroscopic lesion analysis module and the thickness quantification module are both in communication connection with a feature fusion and prediction module. The macroscopic lesion analysis module, the microstructure analysis module, the thickness quantification module and the feature fusion and prediction module are all in communication connection with the result visualization module, and multi-modal pathological image quantitative analysis of membranous nephropathy is realized; the method is applied to multi-mode pathological image analysis of membranous nephropathy.

The invention relates to the technical field of machine learning, and discloses an oral cavity lesion analysis model training method and device, equipment and a medium, and the method comprises the steps: obtaining an oral cavity diagnosis and treatment text and an oral cavity lesion image of a user set, carrying out the text feature coding of the oral cavity diagnosis and treatment text, and obtaining a clinical text feature; performing multi-layer residual error convolution on the oral cavity lesion image to obtain image convolution features; performing channel attention and space attention calculation on the image convolution features to obtain target image features; performing feature fusion on the clinical text features and the target image features to obtain a feature set; calculating a multi-task loss value according to the feature set; and performing parameter optimization on the oral lesion analysis model by using the multi-task loss value to obtain a target oral lesion analysis model for identifying an oral mucosa lesion area in the oral diagnosis and treatment image. Through the implementation of the invention, the complementation of the characteristic modes can be realized, the loss function of a plurality of related tasks is optimized, and the prediction precision of the oral cavity lesion analysis model is improved.

Embodiments of the present disclosure provide systems and methods for analyzing medical images containing vascular structures using a sequential model. An example system includes a communication interface configured to receive the medical image and the sequential model. The sequential model includes a vessel extraction sub-model and a lesion analysis sub-model. The vessel extraction sub-model and the lesion analysis sub-model are trained independently or jointly. The example system further includes at least one processor configured to apply the vessel extraction sub-model to the received medical image to extract location information of the vascular structure. The at least one processor also applies the lesion analysis sub-model to the received medical image and the location information extracted by the vessel extraction sub-model to obtain a lesion analysis result of the vascular structure. The at least one processor further outputs the lesion analysis result of the vascular structure.

The embodiments of the present invention relate to the technical field of pathological image processing, and specifically disclose a pathological image processing method and system based on lesion target area selection. The embodiments of the present invention obtain a target pathological image and perform image preprocessing; perform fuzzy feature analysis to extract a suspicious lesion image; perform fine segmentation processing to extract a target lesion image; perform lesion classification, grading and quantitative analysis to obtain a lesion analysis report; based on the lesion analysis report, create a target lesion image and a background lesion image, synthesize and display a multi-dimensional lesion image. The system can perform image preprocessing, fuzzy feature analysis, fine segmentation processing, lesion classification, grading and quantitative analysis on the target pathological image, create a target lesion image and a background lesion image, synthesize and visualize a multi-dimensional lesion image, achieve standardized processing of pathological images, improve the integrity of pathological image processing, and the processing process is fully automatic, reducing annotation costs and promoting popularization and use.

The present application belongs to the technical field of image processing, and discloses an intelligent auxiliary processing system for abdominal cavity operation images, which comprises a data acquisition module, a data processing module, an intraoperative lesion diagnosis module, an intraoperative lesion analysis module, a clinical decision module and a scheme regulation module. The data acquisition module is used for acquiring laparoscope 3D optical molecular image data, RAL imaging data and device operation data. The data processing module is used for obtaining a comprehensive feature data set by processing the acquired laparoscope 3D optical molecular image data, RAL imaging data and device operation data. The intraoperative lesion diagnosis module is used for constructing an intraoperative lesion diagnosis model and predicting an optical feature index. The intraoperative lesion analysis module is used for comparing the predicted optical feature index with a preset optical feature index threshold value and judging whether there is a lesion. The clinical decision module is used for constructing a lesion degree prediction model and predicting a lesion severity. The scheme regulation module is used for implementing a corresponding tumor treatment scheme according to the lesion severity.

The application relates to the technical field of medical image processing, and particularly discloses a cavity image real-time lesion recognition and boundary segmentation system. A cross-sectional image sequence in a cavity is acquired through an interventional imaging catheter, and after shared features are extracted by using a deep network, pixel-level tissue boundary segmentation and overall lesion property recognition are synchronously performed. The core lies in that a dynamic gradient coordination mechanism is introduced, gradient direction conflicts between the segmentation and recognition double tasks are detected and resolved in real time during the training process, and adaptive projection transformation based on the task convergence state is used to fuse the gradients, so that the shared network can learn balanced features which are optimal for both tasks; the method realizes end-to-end real-time processing from image input to synchronous output of the segmentation and recognition results, and significantly improves the synergy, accuracy of lesion analysis and real-time auxiliary efficiency of clinical operation navigation.

The invention relates to the technical field related to oral treatment and diagnosis, and discloses a 3D modeling assisted oral disease diagnosis platform which comprises a three-dimensional scanning device, a multi-source data fusion module and a biomechanical simulation engine. According to the invention, an oral cavity digital model is constructed through three-dimensional scanning and real-time modeling, and multi-modal data analysis and a deep learning algorithm are integrated, so that automatic identification and quantitative evaluation of a focus are realized; through cooperation of a three-dimensional scanning device, a multi-source data fusion module, a biomechanical simulation engine, an AI focus diagnosis module and a visualization terminal, the problems of insufficient three-dimensional visualization, low early-stage lesion recognition rate, low diagnosis efficiency and poor result consistency of oral disease diagnosis can be effectively solved; therefore, efficient and accurate oral disease diagnosis and judgment and subsequent continuous treatment are achieved, real-time three-dimensional modeling and multi-scale lesion analysis are integrated on the same platform for the first time, and diagnosis accuracy is improved through geometric + gray bimodal data.

The image processing device 1X includes a first acquisition means 30X, a second acquisition means 31X, and an inference means 33X. The first acquisition means 30X acquires a set value of a first index indicating an accuracy relating to a lesion analysis. The second acquisition means 31X acquires, for each of plural models which make inference regarding a lesion, a predicted value of a second index, which is an index of the accuracy other than the first index, on an assumption that the set value of the first index is satisfied. The inference means 33X makes inference regarding the lesion included in an endoscopic image of an examination target, based on the predicted value of the second index and the plural models.

The application discloses a digestive tract lesion analysis method and system based on image recognition, belongs to the technical field of image recognition analysis, and utilizes an image acquisition module to acquire images of the digestive tract of a current patient, transmits data processed by an image processing module, including segmentation, extraction, recognition and statistics, to the image acquisition module and a lesion calculation module, utilizes the lesion calculation module to sequentially calculate and output a preliminary evaluation value WP, a related part influence value G and a comprehensive lesion risk value BF, displays results based on the comprehensive lesion risk value BF by using a result display module to perform analysis, after achieving multi-dimensional comprehensive evaluation of lesion characteristics, the application incorporates related part information and comprehensively evaluates lesion influence, thereby comprehensively considering multiple factors, improving the accuracy and comprehensiveness of analysis, and finally integrates factors in spatial dimensions and time dimensions to comprehensively and accurately evaluate the comprehensive risk degree of the digestive tract lesion.

The present application relates to a kind of medical image processing techniques based on machine learning, provide a kind of based on self-supervised learning and sparse annotation intravascular image lesion segmentation method.First, collect intravascular image data in clinic, and it is screened and preprocessed, then randomly selected small part of data is carried out with the way of interval several frames pixel-level sparse annotation;Through self-supervised learning, pre-training is carried out on a large number of unlabeled data, then the segmentation model is constructed by transfer learning, and fine-tuning training is carried out on sparse annotation data.Finally, the prediction of intravascular lesion is generated and quantitatively analyzed.The present application can be used for large-scale intravascular medical image data to quickly establish effective lesion analysis model.

This application relates to the field of medical image processing technology, and discloses a method and system for lesion analysis of SPECT and spectral CT fusion images. The method includes acquiring SPECT and spectral CT images; identifying at least one anatomical feature point in the spectral CT image and identifying a functional feature point corresponding to the anatomical feature point in the SPECT image; calculating the first spatial coordinates of the anatomical feature point in the spectral CT image and the second spatial coordinates of the functional feature point in the SPECT image; determining the deformation parameters of a local region in the SPECT image based on the difference between the first and second spatial coordinates; and performing spatial transformation processing on the functional distribution features of the local region in the SPECT image to spatially align the processed functional distribution features with the anatomical features in the spectral CT image, actively eliminating image misalignment caused by physiological motion and other factors, and achieving alignment of functional information with anatomical structures.

This invention discloses an oral ablation detection method and system, belonging to the field of oral detection technology, including: S1, oral tissue sampling; S2, motion compensation; S3, image reconstruction; S4, lesion analysis; S5, ablation planning; S6, ablation execution. This invention utilizes phase-amplitude joint displacement estimation, extracting depth-direction micro-displacement using phase difference and lateral displacement using amplitude centroid shift. This effectively compensates for non-rigid tissue peristalsis caused by swallowing and tongue movements without relying on external markers or high-frequency frame rates, ensuring that the subsequently reconstructed three-dimensional image and ablation target area localization are not distorted due to motion, thus improving the targeting consistency between detection and treatment. Texture analysis at different scales is applied along the oral mucosal epithelium, basement membrane zone, and lamina propria, and depth-adaptive weights are assigned based on the pathological sensitivity differences of each layer, highlighting the probabilistic response of early cancerous areas.

The present invention discloses a pulmonary endoscope image navigation and recognition method and system, which relates to the field of pulmonary endoscope technology and solves the problem that the physical signs associated with areas of different brightness within the original image cannot be strongly reflected. The present invention partitions the corresponding images, and then fuses some images with the same feature partitions. Different weight coefficients are assigned in the fusion process to obtain a fused image with the strongest physical signs. The corresponding areas in different images of three same-position areas are integrated to obtain a fused area with the best physical signs after integration, thereby obtaining a corresponding fused image, thereby achieving the best physical sign expression effect and facilitating subsequent lesion analysis.

The invention relates to the technical field of medical image analysis, and discloses a medical image identification device and a medical image identification method, and the method comprises the steps: collecting a lung image of a target patient, carrying out the preprocessing of the lung image of the target patient, judging whether the lung image of the target patient has a tumor feature or an inflammation feature or not, and carrying out the recognition of the tumor feature or the inflammation feature. According to the medical image identification device and the medical image identification method, when tumor characteristics or inflammation characteristics exist in a lung image, the specific position of the abnormal part in the lung is determined, the specific disease of the patient is judged, and a lung anatomical structure diagram of the patient is generated; therefore, specific diseases of the patient can be more accurately judged, monitoring items of the patient are reduced, the detection time of the patient is shortened, the workload of a doctor is reduced, the diagnosis and treatment efficiency is improved, meanwhile, the detection result is more accurate, the misdiagnosis rate is reduced, and unnecessary people flow of a hospital is reduced.

The invention discloses an automatic monitoring and early warning system and method for wheat scab, and relates to the technical field of computer processing, and the system comprises an image acquisition and preprocessing module which is used for obtaining image data of a wheat planting area and preprocessing the image data to obtain a first background image; the disease spot separation module is used for carrying out disease spot separation processing on the first background image and extracting a foreground disease spot region and a second background image; the disease spot analysis module is used for identifying and analyzing the foreground disease spot region, determining disease spot information and calculating a disease severity index; and the image comparison module is used for comparing the second background image with the first background image. According to the method, the disease index is calculated through image preprocessing, target separation and scab feature analysis, real-time accurate monitoring, environmental interference elimination and long-term disease early warning are realized in combination with a background change region anomaly type judgment and prediction model, and intelligent prevention and control of wheat scab are assisted.

The invention relates to a lesion assessment method and device. The method comprises the following steps: acquiring a current report text and a historical report text corresponding to a medical image obtained by scanning a patient twice; utilizing a preset focus analysis model to extract a focus described by the current image in the current report text, and determining structured information of the focus according to a description described by the historical image in the historical report text; and inputting the structural information of the focus and the historical examination conclusion description in the historical report text into a preset focus evaluation model, determining a target focus, evaluating the target focus according to a preset reference evaluation rule, and outputting an evaluation result of the target focus. The method can improve the accuracy of the lesion evaluation result.

The invention discloses a focus identification method and device based on a magnetic control capsule endoscopy image, and relates to the technical field of medical detection assistance, and the method comprises the following steps: collecting the magnetic control capsule endoscopy image, obtaining the movement position and speed of a capsule in real time, and screening out the endoscopy image in a high-speed movement time period as a target image set; reading gradient change data of the target image based on a Sobel algorithm, generating a saliency value, and obtaining a motion blur score through global average pooling to represent image definition; images which do not meet the definition requirement are screened out according to the scores, an image reconstruction device is constructed, the learning rate is dynamically adjusted, the image definition is enhanced, and an identification endoscope image is obtained; inputting the recognition endoscope image and the remaining image into the trained focus recognition model, and outputting an image containing a focus type and a region mark; the quality of the image finally input into the lesion analysis model is ensured, and the lesion identification accuracy is remarkably improved.