12 results about "Arterial tree" patented technology

An apparatus for performing a vascular assessment is disclosed. The apparatus creates a three-dimensional model that is representative of a coronary vessel tree of a patient based on at least two angiographic images. The apparatus estimates first blood flow resistance values for points along at least some vascular segments of the coronary vessel tree using vascular geometrical dimensions of the three-dimensional model. The apparatus also estimates second blood flow resistance values for the points along the at least some vascular segments of the coronary vessel tree using a volume of a crown of the vascular segment downstream from the respective point. The apparatus determines fractional flow reserve (“FFR”) by calculating a ratio of the first blood flow resistance values and the second blood flow resistance values at each of the points along the at least some vascular segments of the coronary vessel tree.

The invention provides a method for automatically segmenting a pulmonary artery tree and a tracheal tree on a CTPA image, and relates to the technical field of image processing, and the method comprises the steps: carrying out the data preprocessing of a pulmonary artery angiography image, and obtaining a preprocessed image; refining the preprocessed image to obtain a center line and a tubular structure radius; constructing three-dimensional Gaussian distribution according to the center line and the radius of the tubular structure, and obtaining a Gaussian distribution thermodynamic diagram according to the three-dimensional Gaussian distribution; inputting the preprocessed image into a first initial network to obtain an initial prediction result, and training the first initial network through the initial prediction result and a Gaussian distribution thermodynamic diagram to obtain a first segmentation network; inputting the preprocessed image into a first segmentation network to obtain a first segmentation result; and inputting the first segmentation result and the preprocessed image into a second segmentation network to obtain a final segmentation result. According to the method, the blood vessel segmentation technology is optimized through the Gaussian distribution thermodynamic diagram of the center line, and the recognition accuracy and segmentation precision of the model are improved.

The invention provides a multi-modal medical image intelligent analysis system and method based on a large language model, and the system comprises a key frame extraction module which carries out the key frame extraction through a multi-frame quality evaluation algorithm; the coronary artery blood vessel extraction module is used for realizing accurate extraction of a coronary artery tree structure through multi-scale blood vessel enhancement; the pathological recognition module adopts an improved DeepLabV3 + algorithm to construct a cardiac blood vessel blockage region segmentation model; the multi-modal diagnosis module adopts LLaVA-Med multi-modal diagnosis, integrates vision and language understanding ability, and combines DeepSeek to generate a standardized diagnosis report; the model optimization module is used for implementing model parameter iterative updating based on a near-end strategy optimization algorithm; and the visual interaction module is used for visually displaying the lesion position and the spatial relationship thereof, so that a doctor can conveniently carry out preoperative path planning and intraoperative navigation judgment. On the basis of a large language model and a multi-mode technology, full-process support from image uploading to diagnosis decision making is provided.

Methods are provided for estimating key reliably and accurately predicting cardiac output using a limited set of non-invasively monitored physiologic inputs, and a calibrated one-dimensional arterial tree model, a database of synthetic data generated from such a model, and an artificial intelligence module. Systems for estimating CO based on non-invasively measured physiologic inputs also are provided that may be implemented without the need for extensive real-time computing resources.

The present application relates to the field of detection equipment, and more particularly to a blood pressure detection device, method, and preparation method based on a bionic micro-nanostructure. The blood pressure detection device based on a bionic micro-nanostructure includes a first triboelectric pulse sensor and a second triboelectric pulse sensor. The first triboelectric pulse sensor is used to be placed at a first preset position on the patient's arterial tree to obtain first pulse wave data, and the second triboelectric pulse sensor is used to be placed at a second preset position on the arterial tree to obtain second pulse wave data, thereby achieving sleeveless, continuous, real-time dynamic detection of the patient's blood pressure. The pulse wave data output by the first and second triboelectric pulse sensors are input into a preset pulse wave-blood pressure model. The pulse wave-blood pressure model can adapt to the specific physiological characteristics of different patients to accurately deduce the patient's blood pressure value, thereby improving the adaptability of the blood pressure detection device and also improving the accuracy of the blood pressure detection device based on the bionic micro-nanostructure.

The present application relates to a method, computer device, readable storage medium and program product for obtaining the segmented position of an intracranial aneurysm in a blood vessel, comprising: obtaining the three-dimensional position coordinates of the aneurysm; obtaining a segmented intracranial arterial tree; combining the three-dimensional position coordinates of the aneurysm and the segmented intracranial arterial tree to obtain a three-dimensional intracranial vascular model including the intracranial arterial tree and aneurysm position information; establishing a standard intracranial vascular model and performing segmented annotation; spatially registering the three-dimensional intracranial vascular model with the standard intracranial vascular model to obtain a registered three-dimensional intracranial vascular model; on the registered three-dimensional intracranial vascular model, selecting pixel points on the aneurysm whose distance from the intracranial arterial tree is within a preset threshold range, obtaining mapping points corresponding to the pixel points on the standard intracranial vascular model, and obtaining the segmented position of the aneurysm on the intracranial arterial tree based on the positions of the mapping points.

A computer-implemented method includes obtaining, via a processing system comprising one or more processors, a three-dimensional (3D) coronary tree segmented from computed tomography (CT) cardiac scan data of a subject, wherein the 3D coronary tree is labeled. The computer-implemented method also includes obtaining, via the processing system, a standardized two-dimensional (2D) coronary base schematic representation of a generic coronary tree. The computer-implemented method further includes modifying, via the processing system, the standardized 2D coronary base schematic representation of the generic coronary tree based on the 3D coronary tree to generate a standardized 2D coronary personalized schematic representation of a coronary tree of the subject.

A computer-implemented method includes obtaining, via a processing system comprising one or more processors, a three-dimensional (3D) coronary tree segmented from computed tomography (CT) cardiac scan data of a subject, wherein the 3D coronary tree is labeled. The computer-implemented method also includes obtaining, via the processing system, a standardized two-dimensional (2D) coronary base schematic representation of a generic coronary tree. The computer-implemented method further includes modifying, via the processing system, the standardized 2D coronary base schematic representation of the generic coronary tree based on the 3D coronary tree to generate a standardized 2D coronary personalized schematic representation of a coronary tree of the subject.

An apparatus for performing a vascular assessment is disclosed. The apparatus creates a three-dimensional model that is representative of a coronary vessel tree of a patient based on at least two angiographic images. The apparatus estimates first blood flow resistance values for points along at least some vascular segments of the coronary vessel tree using vascular geometrical dimensions of the three-dimensional model. The apparatus also estimates second blood flow resistance values for the points along the at the least some vascular segments of the coronary vessel tree using a volume of a crown of the vascular segment downstream from the respective point. The apparatus determines fractional flow reserve (“FFR”) by calculating a ration of the first blood flow resistance values and the second blood flow resistance values at each of the points along the at least some vascular segments of the coronary vessel tree.

The invention relates to measurement systems and methods comprising at least one first transducer for generating measurement signals of a state variable representing a blood flow rate or pressure in an artery, an electrocardiograph for recording an electrocardiogram to allow for synchronization of multiple of said measurement signals, a software comprising an input comprising multiple of said measurement signals, each of said measurement signals contains a time domain signal of at least one state variable representing a blood flow rate or pressure within an artery at a single measurement point of multiple measurement points distributed throughout an arterial tree, wherein the software is capable of performing at least a first signal processing step and a second signal processing step on the measurement signals including the approximation or identification of at least one natural pulsation frequency and one pulsation mode shape of the state variable throughout the arterial tree.

Example medical systems and techniques are disclosed. An example medical system includes processing circuitry coupled to a memory. The processing circuitry is configured to determine a criminal lesion based on a computational model of the patient's vasculature. The processing circuitry is configured to virtually remove the criminal lesion from the computational model to generate a modified computational model. The processing circuit is configured to determine a plurality of shear stresses along an arterial wall in an arterial tree based on the modified computational model, and determine that at least one shear stress of the plurality of shear stresses satisfies at least one threshold in at least one location within the arterial tree. The processing circuitry is configured to identify the patient as a member of a first group of follow-up patients based on the at least one shear stress of the plurality of shear stresses satisfying the at least one threshold.

Systems and methods for vulnerable plaque assessment and outcome prediction in coronary artery disease. Medical imaging data is used to generate a coronary tree model of a coronary centerline of the patient. The coronary artery tree model includes a plurality of nodes representing locations in the coronary artery tree model. A feature embedding associated with each node is determined from a plurality of features derived from medical imaging data. The feature embedding is input into a trained graph neural network configured to output an assessment of vulnerable plaques at a node level, a segment level, and / or a coronary tree level.