11 results about "Abdominal ct" patented technology

The application discloses a kind of multi-modal gastric cancer risk prediction method and system based on gate attention mechanism, it is related to gastric cancer risk prediction technical field, including, to abdominal CT image, gastric organ recognition result and health text information preprocessing, fusion standardization CT image and gastric organ recognition result, construct organ priori enhancement image.To organ priori enhancement image and health text information extract image feature and text feature, respectively calculate self-attention and cross-attention, according to self-attention entropy and cross-attention peak value generation image and the gate fusion coefficient of text, the weighted fusion of the output of two kinds of attention obtains gate fusion feature, and then calculates self-attention and cross-attention and is added in equal proportion to obtain fusion feature, and the risk of target sample suffering from gastric cancer is classified and output.The application makes image feature and text feature complement each other, improves the accuracy and stability of gastric cancer risk prediction, is suitable for health management auxiliary, and is not used as clinical diagnosis basis.

The application discloses a pancreas image segmentation method and system based on deep learning. The method comprises the following steps: acquiring an abdominal CT image sequence and performing window width and window level adjustment, resampling and region of interest cropping; loading pre-trained and fixed weight encoder weight and joint segmentation network model parameter, performing single forward propagation inference on the preprocessed image to obtain a segmentation probability map and a predicted shape vector; post-processing the segmentation probability map to output a three-dimensional pancreas segmentation mask; loading shape prior knowledge base, and combining the predicted shape vector to perform offline confidence evaluation on the segmentation result. The application effectively solves the segmentation fracture problem caused by the fuzzy pancreas boundary by fusing global shape prior constraints, and quantifies the reliability of the result through the confidence evaluation mechanism, thereby improving the precision and clinical applicability of pancreas segmentation.

This invention discloses a method and system for assessing postoperative abdominal organ ischemia risk based on image analysis, belonging to the field of image analysis technology. The method includes acquiring enhanced abdominal CT images of the target patient and outputting them after standardization processing; employing an improved 3D U-Net++ architecture with multi-task collaborative learning to jointly segment the target patient's organs and target regions, integrating geometric priors and topological inference mechanisms; its key technical points are: using multi-task segmentation to focus RPPR calculation on the real ischemic area, avoiding average dilution of the signal across all organs, and topological correction to ensure that vascular features reflect the real anatomy; furthermore, through the joint analysis of low-perfusion area prediction masks and vascular VTIF, it reveals two ischemic subtypes: structural occlusion and functional hypoperfusion, promoting the individualization of clinical intervention strategies and defining the necessary vascular intervention or conservative treatment, making the overall solution both innovative and clinically applicable.

The application discloses a CT image enhancement processing method for tumor boundary recognition, and relates to the technical field of medical image processing. The method comprises the following steps: S1, performing multi-scale decomposition on an original abdominal CT image, and obtaining a preprocessed coarse scale component and a preprocessed fine scale component through a multi-scale feature decoupling network; S2, fusing the preprocessed coarse scale component and the preprocessed fine scale component, obtaining a corresponding CT enhanced image, and obtaining an initial boundary contour of the CT enhanced image; and S3, according to the initial boundary contour, obtaining an uncertainty score corresponding to each sampling point, determining a corresponding low-confidence boundary segment, and performing decomposition and enhancement processing on the low-confidence boundary segment to obtain a final tumor boundary contour. The application can specifically correct unreliable parts in the boundary contour, significantly improves the clinical reliability and robustness of the final tumor boundary contour, and avoids overall boundary errors caused by local blurring or noise.

The application discloses a chest CT image multi-abnormality recognition and positioning method and system based on deep learning, and the method comprises the following steps: customizing chest and abdominal CT abnormality labels, constructing a chest CT multi-abnormality positioning labeling data set according to the abnormality labels; based on the data set, training a YOLO model, and performing abnormality detection on a single tomographic image in an input CT sequence to output a preliminary detection result with a tomographic sequence number; extracting interlayer parameters of the CT sequence, and based on the interlayer parameters and the preliminary detection result, performing interlayer correlation verification and three-dimensional feature fusion to obtain a detection result after verification and fusion; and based on the detection result after verification and fusion, generating and outputting a final detection report containing abnormal three-dimensional information. The application can start from constructing a chest CT data set for multi-class abnormality positioning labeling, utilize a target recognition and positioning network in computer vision, and train an auxiliary diagnosis model capable of simultaneously recognizing and positioning common abnormal signs of chest CT.

The application provides a kind of diabetes nephropathy auxiliary identification method and system based on CT image, it is related to medical image processing and computer-aided diagnosis technical field, the method comprises: obtaining the abdominal CT image of target object;Segment kidney, perirenal fat and body composition region of interest;Extract radiomics features;Screening to obtain target radiomics features;Input radiomics model to obtain whether target object is identified result of suffering from diabetes nephropathy.The application extracts microcosmic image markers related to renal function damage from conventional CT images by comprehensively using multiple site radiomics features, realizes non-invasive, accurate auxiliary identification of diabetes nephropathy, significantly improves detection efficiency, and provides a reliable image-aided diagnosis tool for clinic.

This invention relates to the field of tumor detection technology. It proposes a method for differential diagnosis and prediction of xanthogranulomatous cholecystitis (XGC) based on preoperative enhanced CT images. The method includes: acquiring enhanced CT images of the gallbladder wall in the arterial and portal venous phases; performing image segmentation and feature extraction; performing dimensionality reduction on the arterial phase features, portal venous phase features, and the combined dual-phase features to obtain corresponding feature datasets, which are then divided into training and testing sets; training three machine learning prediction models based on the three training sets to obtain the optimal machine learning prediction model; validating the performance of the optimal machine learning prediction model using the testing set to obtain a differential diagnosis prediction model; and inputting the feature data of the enhanced abdominal CT image to be predicted into the differential diagnosis prediction model for identification. This invention establishes a better differential diagnosis prediction model by analyzing the imaging characteristics of XGC and thick-walled GBC, providing a basis for treatment decisions.

This invention discloses a deep learning-based method for predicting the disease evolution of hepatobiliary patients, belonging to the fields of medical imaging and deep learning technology. The invention first acquires multi-temporal abdominal CT images, time-series clinical laboratory indicators, and medical history follow-up data of hepatobiliary patients; it then uses a variant U-Net network with Lagrange pseudo-ordering structure constraints to accurately segment the CT images and extract radiomics features; based on the segmentation results, a three-dimensional model is constructed, and numerical simulations of hepatobiliary blood perfusion and bile fluid dynamics are performed using local entropy production theory to obtain dynamic biomechanical features; cross-dimensional feature alignment and fusion are achieved by fusing attention mechanisms and a multimodal network for complex community discovery, and then chaotic theory is introduced for phase space reconstruction to enhance dynamic features; this invention achieves an upgrade from statistical correlation to physiological causality in prediction, improving model generalization and clinical interpretability, and is suitable for prognostic assessment and intelligent early warning of disease progression in hepatobiliary diseases.

This invention proposes a method for analyzing muscle tissue in sarcopenia patients based on CT images. The method includes acquiring abdominal CT images of the same subject; performing pixel-level segmentation on the preprocessed CT images to distinguish and locate muscle, subcutaneous fat, and visceral fat regions; calculating changes in area and / or volume of each tissue and changes in HU value based on the output results of the same subject at different time points; performing longitudinal quantitative analysis and comparison based on a timeline; and outputting visualized labeled results. This invention assesses the tissue regions and changes of three core components: muscle, subcutaneous fat, and visceral fat. It quantifies the assessment results using multiple dimensions such as pixel count, actual physical area or volume, grayscale density, and standard deviation. The assessment is comprehensive, objective, and repeatable, meeting the needs of precise clinical assessment. It can intuitively identify key pathological changes such as muscle loss and fat infiltration, providing a reliable basis for early intervention.

The present application relates to the field of digital reconstruction and virtual angiography technology, and particularly relates to a virtual esophageal barium contrast generation method based on CT image segmentation and digital reconstruction X-ray image rendering, comprising the following steps: S1, collecting chest or upper abdominal CT images of a patient and preprocessing; S2, automatically segmenting an esophageal region from the original CT image; S3, dividing the entire esophageal region into three parts, namely, a lumen, a wall and a mucosa; S4, obtaining a segmentation result of a tumor; S5, mask calculation; S6, filling CT values for different parts of the esophagus to simulate the state of esophageal filling phase and mucosal phase under different barium doses; S7, fusing the original CT image with the filling phase image and the mucosal phase image respectively to obtain a fused three-dimensional CT image, modeling the propagation process of X-rays in the fused three-dimensional CT volume data by using a DRR technology, and generating a virtual esophageal barium meal image. The present application does not require the patient to swallow a barium meal, has no X-ray exposure risk, has low dependence on the experience of operators, and has stable and reliable image quality.

The application discloses a 3D abdominal multi-organ image segmentation method based on an improved EM-Net, and comprises the following steps: firstly, a data set is extracted and preprocessed; then, an improved network model is constructed based on an EM-Net model, an adaptive dynamic state space modulation module ADSSM is used to replace a feature enhancement module in an original EM-Net encoder; and an adaptive multi-scale feature interaction module AMFI is integrated in each stage of the EM-Net encoder to replace an original multi-scale fusion component; finally, an adaptive multi-modal context modulation module AMCM is used to replace a feature fusion module in an EM-Net decoder; secondly, the improved model is trained; the trained model is verified; finally, the improved network model is used for segmenting BTCV abdominal multi-organ images, and a segmented image is output. The application has strong feature expression capability and high segmentation precision, and is suitable for an abdominal CT multi-organ segmentation scene.