31 results about "Fractional flow reserve" patented technology

A method and system for anatomical object detection using marginal space deep neural networks is disclosed. The pose parameter space for an anatomical object is divided into a series of marginal search spaces with increasing dimensionality. A respective deep neural network is trained for each of the marginal search spaces, resulting in a series of trained deep neural networks. Each of the trained deep neural networks can evaluate hypotheses in a current parameter space using discriminative classification or a regression function. An anatomical object is detected in a medical image by sequentially applying the series of trained deep neural networks to the medical image.

Bending stresses experienced by a pressure sensor mounted to a fractional flow reserve catheter when tracking the catheter through the vasculature creates a distortion of the sensor resulting in an incorrect pressure reading or bend error. In order to isolate the sensor from bending stresses, the sensor is mounted with one end coupled to the distal end of the shaft while the other end of the sensor is not coupled to the catheter so that a portion of the sensor is spaced apart from the distal end of the shaft.

The invention provides a system and method for using computational fluid mechanics to simulate and calculate fractional blood flow reserve. The system comprises a vascular tree model generation module, a computational grid generation module, a boundary condition setting module, an attribute setting module, a solver and an aftertreatment module, wherein the vascular tree model generation module acquires a medical image, executes segmentation and reestablishes a geometric model of a vascular tree of an individual, the computational grid generation module generates a computational grid for the geometric model and establishes a CFD model of the vascular tree, the boundary condition setting module sets corresponding inlet and outlet boundary conditions for the CFD model of the vascular tree, the attribute setting module sets the physical property and a flow equation of blood, the solver seeks solutions on the CFD model of the vascular tree based on the inlet and outlet boundary conditions so as to obtain fluid parameters around the vascular tree, the set physical property and the flow equation, and the aftertreatment module conducts aftertreatment on the fluid parameters so as to obtain the fractional blood flow reserve, and both the inlet boundary condition and outlet boundary condition have individual specificity. According to the system and method for using computational fluid mechanics to simulate and calculate the fractional blood flow reserve, the accuracy of a simulation result is guaranteed, and the calculation time acceptable to clinics can be achieved at the same time.

A method and system for non-invasive assessment of coronary artery stenosis is disclosed. A patient-specific real anatomical model of a diseased coronary artery of a patient is generated from medical image data of the patient. A hypothetical normal anatomical model is generated for the diseased coronary artery of the patient. Blood flow is simulated in each of the patient-specific real anatomical model of the diseased coronary and the hypothetical normal anatomical model for the diseased coronary artery. A hemodynamic index is calculated using simulated blood flow rates in the patient-specific real anatomical model of the diseased coronary and the hypothetical normal anatomical model for the diseased coronary artery. In particular, fractional flow reserve (FFR) for the diseased coronary artery is calculated as the ratio of the simulated blood flow rate in the patient-specific real anatomical model of the diseased coronary artery and the simulated blood flow rate in the hypothetical normal anatomical model for the diseased coronary artery.

The invention relates to an image processing method, an image processing apparatus, and a non-transitory computer readable medium. The method comprises the steps of obtaining a 3D center line of a blood vessel tree; obtaining a 2D center line and 2D blood vessel geometric information of the blood vessel tree; registering a 3D centerline of the blood vessel tree to a 2D centerline of the blood vessel tree; and based on a registration result, transferring the 2D blood vessel geometric information of each position on the 2D center line of the blood vessel tree to a corresponding position on the 3D center line of the blood vessel tree so as to construct a 3D model of the blood vessel tree. According to the method, when the fractional flow reserve (FFR) is calculated, the overall space information of the 3D image of the blood vessel tree and the blood vessel geometric information of the 2D image are combined, so that a more accurate 3D model of the blood vessel tree can be obtained.

The invention discloses a hemodynamic force simulation method and device. The method comprises the following steps: acquiring a blood vessel image of an artery blood vessel in a predetermined area of a target object; performing level set segmentation on an initial blood vessel model corresponding to the blood vessel image to obtain a segmented blood vessel model; acquiring a boundary condition for simulating a target blood vessel corresponding to the blood vessel model; performing central arterial pressure calculation on the target blood vessel to obtain an inlet pressure value of the target blood vessel; and performing hemodynamic simulation on the target blood vessel by using the boundary condition and the inlet pressure value. The technical problem that in the related technology, potential safety hazards exist in invasive fractional flow reserve measurement, and consequently the reliability of hemodynamic simulation is low is solved.

The invention discloses a method for processing a blood vessel image. The method comprises the following steps: acquiring image data of an interested blood vessel section; acquiring blood flow parameters of the interested blood vessel section; detecting and analyzing the image data of the interested blood vessel section to obtain reference information, wherein the reference information comprises lumen contour parameters and medial membrane contour parameters of the interested blood vessel section; obtaining reference lumen information according to the mesomembrane contour parameters; and calculating to obtain a fractional flow reserve value of the interested blood vessel section according to the blood flow parameters, the reference information and the reference lumen information. The bloodvessel image processing method disclosed by the invention can realize more accurate calculation of the blood vessel pressure difference. The invention further provides a blood vessel image processingsystem, calculation equipment and a storage medium.

The invention discloses a computer-aided surgery design system for coronary heart disease. The computer-aided surgery design system comprises a clinical examination module, a computer-aided module anda diagnosis and treatment module, which are sequentially connected, wherein the clinical examination module consists of a conventional inspection module 1 and a coronary angiography module 2 and is used for preliminarily judging whether the coronary heart disease or related heart diseases exist or not; the computer-aided module comprises a coronary vessel segmentation and reconstruction module 3and a vascular stenosis calculation module 4 and is used for performing segmentation and reconstruction on an angiography image and calculating coronary artery blood flow reserve fraction by applyinga computational fluid mechanics technology to quantitatively judge whether coronary artery interventional surgery treatment needs to be performed or not; and the diagnosis and treatment module consists of a doctor reexamination module 5 and an auxiliary surgery module 6, and the doctor reexamination module 5 feeds back a calculation result to enable the calculation result to be more credible. Thecomputer-aided surgery design system for the coronary heart disease can visually display a coronary artery anatomical structure and enable diagnosis of the coronary heart disease to be more visual andscientific.

The invention provides a system for calculating blood flow reserve fraction and a method for setting boundary conditions. The system includes: a vascular tree model generation module, which acquires medical images, executes segmentation and reconstructs the geometric model of the individual vascular tree; a calculation grid generation module, generates a calculation grid for the geometric model, and establishes a CFD model of the vascular tree; a boundary condition setting module , to set the corresponding inlet and outlet boundary conditions for the CFD model of the vascular tree; the attribute setting module, to set the physical properties of the blood and the flow equation; the solver, based on the inlet and outlet boundary conditions, the set physical properties and the flow equation, the blood vessel The CFD model of the tree is solved to obtain the fluid parameters throughout the vascular tree; and the post-processing module is used to post-process the fluid parameters to obtain the blood flow reserve fraction, and the inlet and outlet boundary conditions are individual-specific. The system and method achieve a clinically acceptable calculation time while ensuring the accuracy of the simulation results.

The heart data of the living body is processed by a processing unit, the processing unit comprising: a first fractional flow reserve (FFR) providing unit (11), which is used to provide a first FFR indicating the FFR of different arteries of the living body, wherein, The virtual FFR value is calculated according to the non-invasive imaging data of the artery of the living body; the second FFR providing unit (12) is used to provide the FFR value measured in the artery of the living body; the correction unit (13 ) configured to correct the first FFR value based on the second FFR value; and a display unit (14) configured to display at least the first and second FFR values ​​for corresponding locations in the coronary arteries. The first and second FFR values ​​are displayed to a cardiologist, which enables his course of action to be based on simulated and corrected values.

The invention discloses a fractional flow reserve measurement method and system based on intravascular ultrasound images, and the method comprises the steps: obtaining a batch of intravascular ultrasound images, dividing the batch of intravascular ultrasound images into a training set and a verification set, and obtaining a training set image and a verification set image; optimizing a preset modelbased on the training set image and the verification set image to obtain a machine learning model; acquiring a to-be-detected intravascular ultrasound image and performing image feature extraction toobtain feature data; and inputting the feature data into the machine learning model to obtain the fractional flow reserve of the ultrasonic image in the blood vessel to be detected. The system comprises a division module, an optimization module, a feature module and an output module. The FFR value can be calculated according to the IVUS image, and the invention has characteristics of high accuracy and low calculation requirement. The fractional flow reserve measurement method and system based on the intravascular ultrasound image can be widely applied to the field of medical image processing.