9 results about "Vascular body" patented technology

The invention discloses a three-dimensional reconstruction model training method and a blood vessel three-dimensional reconstruction method and device. The training method of the three-dimensional reconstruction model comprises the following steps: acquiring a plurality of two-dimensional blood vessel body drawing training images, wherein the plurality of two-dimensional blood vessel body drawing training images are acquired from different acquisition angles; inputting a plurality of two-dimensional blood vessel volume rendering training images into the neural network model to obtain a three-dimensional blood vessel voxel model; reducing the three-dimensional blood vessel voxel model into a plurality of two-dimensional rendering images based on projection matrixes corresponding to the obtained two-dimensional blood vessel body drawing training images through a differentiable rendering method; calculating a loss value based on the plurality of two-dimensional blood vessel body drawing training images and the plurality of two-dimensional rendering images, adjusting model parameters of the neural network model based on the loss value, and obtaining a three-dimensional reconstruction model when the loss value meets a set condition, the trained three-dimensional reconstruction model can simply and efficiently generate a three-dimensional model of a blood vessel based on a blood vessel image with a limited angle.

An ultrasonic diagnostic imaging system measures volume flow. An ultrasound probe operating in biplane mode is used to acquire a blood vessel in a long axis view in a first Doppler image and simultaneously in a transverse view in a second Doppler image. Volume flow is calculated from the transverse view of the blood vessel. The plane of the second image is aligned with the Doppler angle of the first image so that angle correction determined for the first image can be used for angle correction in the volume flow calculation.

The application belongs to the field of intelligent medical treatment, and particularly relates to a method for constructing a refractory mycoplasma pneumoniae pneumonia prediction model and equipment. The method comprises the following steps: acquiring a baseline time data set and a follow-up time label of a mycoplasma pneumoniae patient; inputting the image data set into a lung blood vessel segmentation model to obtain a lung blood vessel network, obtaining a total lung blood vessel volume based on the lung blood vessel network, and obtaining a blood vessel volume of different cross-sectional areas based on a cross-sectional area of the lung blood vessel network; inputting a ratio of the blood vessel volume of different cross-sectional areas to the total lung blood vessel volume into a machine learning model to obtain a prediction label, and obtaining a refractory mycoplasma pneumoniae pneumonia prediction model after iterative optimization of the machine learning model based on a difference between the prediction label and the follow-up time label. The application segments a lung CT image to obtain a blood vessel network diagram, quantitatively obtains a percentage of a blood vessel volume of different thicknesses in a total lung blood vessel volume, and constructs a refractory mycoplasma pneumoniae pneumonia prediction model based on an innovative feature extraction method.

The invention relates to medical device (1) to be inserted in a defect blood vessel, body cavity, or body duct for treatment or pretreatment thereof. The medical device (1) comprises a hollow shaft (2) having the ability to slidably house an injection means (3), the hollow shaft (2) having a distal end (4) and a proximal end (5), and an elongated holding device (6) connected to the hollow shaft (2), the elongated holding device (6) having a distal end (7) and a proximal end (8). The invention also relates to a kit for the treatment, preferably ablation treatment, of defective blood vessels, body cavities, or body ducts.

The application discloses a method for motion interaction of liver parenchyma and intrahepatic blood vessels and blood in a virtual surgery scene, mainly comprising: generation of a visual liver body model and an intrahepatic blood vessel body model; generation of a liver parenchyma body model; generation of a dense mesh of the intrahepatic blood vessel body model by means of a gmsh software, and generation of an intra-blood vessel blood model composed of a blood flow particle set; establishment of a liver parenchyma motion model based on PBD, and motion trends of the liver parenchyma and the intrahepatic blood vessels under the action of an external force, which are used to represent the motion of the liver parenchyma under the action of the external force, and the motion of the blood vessels and the blood particles caused by the deformation of the liver parenchyma, and simultaneously contain the flow of the blood particles under the condition of cutting; and realization of the motion constraints between the intrahepatic blood vessels and the liver parenchyma, and the motion constraint conditions of the blood flow in the blood vessels under the action of the external force in the virtual surgery scene. The method fully considers the motion characteristics of the liver and the blood vessels under the action of the force.

The invention provides a blood vessel three-dimensional reconstruction method and system based on digital subtraction angiography, and relates to the technical field of medical image processing and three-dimensional reconstruction. The method comprises the following steps: performing frame-by-frame registration, subtraction processing and uniform sampling on a collected two-dimensional digital subtraction angiography DSA image sequence to obtain a frame sparse view; constructing and training a vessel three-dimensional reconstruction network based on the sparse view angle dynamic DSA, inputting the frame sparse view into the trained vessel three-dimensional reconstruction network based on the sparse view angle dynamic DSA, and generating geometric parameters and center attenuation values of all Gaussian kernels; calculating three-dimensional blood vessel volumes under all timestamps and performing voxelization averaging on the three-dimensional blood vessel volumes under all timestamps on the basis of the geometric parameters and the center attenuation values of all Gaussian kernels, and generating a static three-dimensional blood vessel model; and meanwhile, all Gaussian kernels are rendered to generate a synthesized DSA image under a new view angle. The invention aims to improve the integrity and the time sequence consistency of the micro blood vessel reconstruction under the sparse view angle.

The invention relates to the technical field of acupoint positioning and computer image processing, and discloses an auxiliary acupoint positioning method based on image fusion, which comprises the following steps: receiving an acupoint selection instruction input by a user, and confirming a target acupoint; acquiring a target area subcutaneous blood vessel distribution image and a body surface image of the target acupuncture point; fusing the subcutaneous blood vessel distribution image and the body surface image to obtain a blood vessel-body surface fusion model of the target area; based on the blood vessel-body surface fusion model and a blood vessel distribution-acupuncture point model, calculating a target acupuncture point prediction coordinate; and converting the calculated target acupuncture point prediction coordinate into a laser projection instruction, controlling a laser emitter to project a positioning light spot to the body surface, and outputting acupuncture point information.

The present disclosure relates to a device configured to move within a body cavity, such as the gastrointestinal tract, in particular, the small intestine, and methods of using the device. The presently disclosed device may be self-driving, e.g., through the use of one or more traction-motion element, and the articulation of a tip of the device may be controlled and fine-tuned. The presently disclosed device may be used in a variety of body cavities such as a vascular body lumen, a digestive body lumen, a respiratory body lumen, or a urinary body lumen, for example, for endoscopic purposes, for delivering a substance into the body cavity, for removing a substance or tissue from the body cavity, for capturing an image of the body cavity, and / or for performing an operation of a tissue or organ using the device.

An apparatus for delivering a drug to a vascular body lumen includes a pre-crimped stent configured to be disposed within a vascular body lumen and a coating. The stent is mounted on a balloon and includes a mesh-like configuration having multiple interconnected space regions defined by multiple strut components. Each of the strut components include an abluminal surface, a luminal surface, and a side surface. The balloon includes multiple portions exposed through the interconnected space regions. The coating bridges across the interconnected space regions of the stent and is configured to deform and extend in response to expansion of the balloon to form a continuous, homogenous cylindrical film. Expansion of the balloon within the vascular body lumen causes the homogenous cylindrical film to cover a continuous, circumferential area of the vascular body lumen.