24 results about "Lesion analysis" patented technology

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 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 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 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.

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 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.

The invention discloses an endoscope image acquisition method and device based on voice and an automatic report generation method and system.The method comprises the steps that first data information obtained based on voice data is acquired, and the first data information comprises instruction information; acquiring first image information according to the instruction information; second image information is obtained according to the first image information and a pre-trained image analysis model, and the second image information comprises the first image information and lesion analysis information on the first image information. According to the voice-based endoscope image acquisition method, the instruction information for acquiring the image is obtained based on the voice data, so that hand interaction with the equipment is not needed, the operation of an operator on the endoscope equipment is not influenced, and the diagnosis efficiency can be effectively improved. And after the image information is obtained, the image information is automatically identified according to the image analysis model, so that automatic analysis and identification of the lesion part in the corresponding image can be realized, and the diagnosis efficiency is further improved.

Embodiments of the present application relate to the technical field of medical data processing, in particular to a multi-modal medical image data processing method and device. The method comprises: inputting multi-modal data of a target lesion into a trained multi-modal medical data processing model; performing multi-scale basic visual feature extraction on medical image data through a basic visual feature extraction network to obtain a multi-scale basic visual feature set; capturing a spatial structure of the multi-scale basic visual feature set through a structured image feature extraction network to obtain a structured image feature; performing semantic feature extraction on medical text data through a text feature extraction network to obtain a text semantic feature; and performing prior weighting fusion on the structured image feature and the text semantic feature through a cross-modal feature fusion network to obtain a matching probability of the multi-modal data and the target lesion. The technical solution of the present application can improve the reliability of lesion analysis results.

The application discloses a lung multi-anatomy analysis and three-dimensional reconstruction method, which comprises the following steps: acquiring and preprocessing chest CT scan images to obtain input tensors; identifying and outputting airway masks and lung blood vessel masks in the input tensors by using a connected structure segmentation network; identifying and outputing lung nodule masks in the input tensors by using a micro-lesion analysis network; determining spatial physical coordinates of foreground voxels of each mask in the chest CT scan images, and determining unique anatomy class labels of each voxel by using a dynamic clinical risk priority conflict resolution strategy to obtain a multi-anatomy voxel set; and sampling and reconstructing each anatomy based on an adaptive manifold sampling strategy based on morphological characteristics to obtain reconstructed lung multi-anatomy. The method can clearly show the spatial relationship among airways, blood vessels and lesions in a unified three-dimensional coordinate system, and provides an intuitive and accurate digital model for clinical diagnosis and treatment.

This invention relates to the field of medical imaging lesion analysis technology, specifically a multi-source point cloud fusion system and method for analyzing knee and lumbar spine lesions. The system includes: acquiring static medical imaging scan data and dynamic motion capture data of the target area; reconstructing anatomical structure point clouds from the static data in three dimensions; generating motion trajectory point cloud sequences through spatiotemporal registration and trajectory extraction of the dynamic data; establishing a spatial mapping field between the two and transferring motion vectors; driving the anatomical structure point cloud to deform under physical constraints to simulate and generate dynamic skeletal point clouds; calculating local curvature changes to form a curvature spatiotemporal evolution map; separating physiological low-frequency and pathological high-frequency components through multi-scale frequency domain decomposition; extracting abnormal vibration mode features and comparing them with a standard lesion knowledge base; and outputting a qualitative description of potential knee or lumbar spine lesions. This invention integrates static anatomical and dynamic motion data, accurately distinguishing between physiological and pathological vibrations, and improving the accuracy of lesion analysis.

1. Name of the product in this design: Medical Image AI Graphical User Interface for Electronic Devices. 2. Intended use of this design: for use in an electronic device. 3. The key design feature of this product is its graphical user interface. 4. The image or photograph that best illustrates the design's key features: the front view. 5. Applications of the graphical user interface: Through efficient design and human-computer interaction of functions such as AI list and lesion analysis, improve the efficiency of medical image reading. 6. Human-computer interaction method of graphical user interface: The main view is the interface for displaying medical images on the left; clicking the number button in the AI ​​results list on the right side of the main view enters the interface change state diagram 1, showing the user the location and marking of the lesion on the original image; clicking the lesion analysis button at the top of the interface change state diagram 1 enters the interface change state diagram 2, showing the user the VMIP image of the lesion and the results of related quantitative analysis; clicking the hide AI button at the top of the interface change state diagram 2 enters the interface change state diagram 3, showing the user the original medical image behind the hidden AI result marking box. In all the interfaces mentioned above, "X" represents replaceable text or numbers.

The invention discloses a microcirculation hemodynamic lesion analysis method based on pathological images. The method comprises the following steps: preprocessing a full-slice nephropathy image to obtain a cut image containing a glomerular target; inputting the cut image into a target detection network to obtain regional position information and structural information of the glomerular target; for the region position information and the structure information of the glomerular target, performing focus region segmentation and lesion degree quantification on the interior of the glomerulus by using an image segmentation network model, obtaining a focus region quantification result, and obtaining an identification result of whether sclerotic lesion and crescent lesion exist or not; and based on the focus area quantification result and the identification result, utilizing a discriminator to obtain a fine-grained classification result of the glomerular blood flow tissue lesion types. According to the method, accurate fine-grained classification of glomerular segmental sclerosis, globular sclerosis, crescent bodies and the like can be efficiently realized.

The invention relates to the technical field of nuclear medicine imaging, in particular to a diagnosis device and method based on radionuclide distribution imaging, and the device comprises a detection module, a data processing module, an image reconstruction module, a dose optimization module and a fusion diagnosis module. According to the device, the image reconstruction quality is improved through multi-physical modeling and a self-adaptive iteration strategy, scanning parameters are dynamically adjusted to achieve low-dose efficient collection, and a comprehensive diagnosis result is generated in combination with anatomical images. Noise, scattering and equipment response nonlinear influence can be effectively reduced, imaging precision and quantitative analysis capacity under the low-dose condition are remarkably improved, and high-resolution functional images and accurate focus analysis support are provided for clinical diagnosis.

The invention discloses an automatic tumor lesion analysis method and platform, a storage medium and computer equipment, and the method comprises the steps: determining a tumor minimum coverage graph region based on a tumor region marked by an ultrasonic image and a minimum coverage graph corresponding to a tumor type, and subtracting the tumor region from the tumor minimum coverage graph region to obtain a minimum coverage graph region; obtaining a peritumoral region; the method comprises the following steps: sequentially extracting features of a tumor region, a tumor minimum coverage pattern region and a peritumor region, constructing four feature input modes, respectively inputting the four feature input modes into each ML classifier for model training and evaluation, determining an optimal region selection mode on the basis of the feature input modes used when the ML classifiers are in optimal performance, and carrying out model evaluation on the optimal region selection mode. Therefore, a doctor can obtain a lesion analysis result through an optimal performance ML classifier based on the initially marked tumor area and the optimal area selection mode. Through multi-region feature extraction and classifier optimization, accurate analysis of benign and malignant tumors is realized, and ultrasonic image diagnosis efficiency and accuracy are improved.

The present application relates to the field of data enhancement, and more particularly to a data enhancement system and method for small sample medical image labeling, which comprises a lesion analysis module, a data processing module, a labeling interference module, and a data enhancement module, determines a plurality of organs affected by diseases and performs lesion analysis, calculates lesion occurrence characteristic values, determines lesion analysis organs, determines texture discrete characteristic values and organ covering characteristic values, determines organ adhesion areas based on the texture discrete characteristic values, analyzes the edge texture direction of the organ adhesion areas, obtains a reference path belt, determines an interference organ area, calculates a labeling interference coefficient, calls a data enhancement model to obtain an enhanced organ area, and completes medical image picture labeling of the enhanced organ area. The present application divides the adhesion area of organs that may be affected by diseases, determines the interference organ area, calls the data enhancement model according to the labeling interference coefficient, completes data labeling, and improves the accuracy and efficiency of data labeling.

The invention relates to the technical field of CT image prediction, in particular to a chronic obstructive pulmonary chest CT image prediction system based on adaptive neurograph reasoning, comprising: a space-time pathology mapping module used for acquiring chest CT sequence images and clinical follow-up visit data, and generating a four-dimensional space-time pathology tensor based on time registration and a spatial resampling algorithm; the self-adaptive neural inference module is used for performing feature extraction on the four-dimensional space-time pathological tensor to obtain a cognitive state vector, and performing dynamic inference to generate a cognitive map; the cross-modal intention alignment module is used for establishing a semantic consistency relationship and carrying out unified coding and fusion; the reversible explanation generation module is used for generating a focus analysis chart based on the cognitive map and a preset multi-stage reasoning model; and the self-evolution memory module is used for adaptively optimizing parameters of the multi-stage inference model. According to the method, accurate prediction and interpretable analysis of the pathology severity of the chronic obstructive pulmonary disease are realized through a self-adaptive neurogram inference mechanism.