43 results about "Vascular anatomy" patented technology

The invention discloses a PICC (Peripherally Inserted Central Catheter) tip precise navigation fixing method and system based on electrocardiogram real-time positioning. High-precision positioning and safe fixing of a catheter tip are realized through a multi-modal data fusion and deep learning technology. The method comprises the following steps: collecting intracavity electrocardiosignals (ECG) in real time through a catheter built-in electrode, and obtaining blood vessel wall contact pressure and temperature data in combination with an optical fiber sensor; an improved wavelet threshold algorithm is adopted to dynamically suppress motion artifacts, and P-wave features are enhanced; the preprocessed ECG signals are input into a spatial-temporal feature fused Transformer model, a time attention layer is used for analyzing P-wave time sequence changes, a space attention layer integrates multi-lead space distribution features, and the positioning precision is optimized in combination with preoperative blood vessel anatomical data; the ECG positioning result and the optical fiber sensing data are fused through Kalman filtering, three-dimensional position information of the tip end of the catheter is generated, and real-time navigation is conducted on an augmented reality interface; and when the P wave amplitude reaches a CAJ threshold value, the contact pressure is safe and no abnormal temperature exists, a shape memory alloy (SMA) fixing ring is triggered to contract, and accurate fixing is achieved. The method solves the problems that a traditional method depends on X rays and is poor in anti-interference performance, has the advantages of being free of radiation, high in real-time performance and adaptive to blood vessel deformation, and is suitable for clinical P catheter implantation.

The utility model discloses a far-end protector, which belongs to the technical field of medical equipment and comprises a mandrel, an umbrella framework and an umbrella film, and first limiting structures are axially distributed on the mandrel; the closing end of the umbrella framework is fixedly connected to the near end of the core shaft, and the flaring end of the umbrella framework faces the far end of the core shaft; the umbrella membrane is provided with filtering holes for blood circulation, the opening end of the umbrella membrane is connected with the flaring end in a wrapping mode, the opening end faces the near end of the core shaft, the closed end of the umbrella membrane is connected with a sliding block, and the sliding block is provided with a second limiting structure matched with the first limiting structure. According to the utility model, the slide block slides on the mandrel, so that the size of the inner volume of the umbrella membrane can be changed, the umbrella membrane with the proper volume can be adjusted according to the blood vessel anatomical structures and lesion characteristics of different patients, and the safety and effectiveness of an operation are further improved.

The invention provides a medical image processing method and a medical image processing device, which can pre-construct a three-dimensional target path image in an occluded blood vessel and solve the technical blind area that the dissection path of a far-end blood vessel cannot be developed due to the fact that a contrast agent cannot pass through the occluded blood vessel in traditional DSA radiography. Moreover, the three-dimensional target path image and a three-dimensional angiography image obtained in the operation can be registered and fused based on a preset mark point to obtain a fused image, and the fused image and the two-dimensional perspective image of the focus area of the patient are registered and fused to obtain a fused image. Accurate space alignment and dynamic superposition of the preoperative three-dimensional target path image, the intraoperative three-dimensional angiography image and the intraoperative two-dimensional perspective image are achieved, a whole-process visible accurate space positioning reference is provided for instrument pushing and vascular access selection of an operator, and the accuracy of surgical operation is improved.

The present invention provides an artificial intelligence engine configured to a UNet model including an encoder and a decoder that can synthesize 3D MRA and MIP of MRA using acquired single contrast MR image (T1-w MR image) for the same subject while preserving the continuity of vascular anatomy and important vascular morphological features.

The present invention relates to the field of surgical forceps, and specifically to an inferior vena cava root vascular dissection and separation forceps for liver surgery. The present invention comprises a forceps body and a tubular body, wherein a pull rod is provided within the tubular body; a first support seat is fixedly connected to the inner wall of the tubular body, a transmission gear disc is rotatably connected to the first support seat, a hollow telescopic rod is fixedly connected to the middle of the transmission gear disc, the other end of the telescopic rod is connected to the forceps body, and the pull rod is used to pass through the telescopic rod and drive the forceps body to clamp by pulling; a second support seat is fixedly connected to the inner wall of the tubular body, the middle section of the pull rod is a serrated flexible strip structure, and the second support seat is provided with a lock hole and a first lock tooth for one-way engagement with the serrated flexible strip structure; a ratchet bar is slidably connected to the inner wall of the tubular body, the pull rod is provided with a second lock tooth for one-way engagement with the ratchet bar, and a driving member is provided on the end of the ratchet bar near the transmission gear disc. The technical solution of the present invention can control the clamping of the forceps body by pulling out the pull rod, and control the rotation of the forceps body by withdrawing the pull rod, thereby optimizing hand operation and improving control performance.

The invention discloses a micro-catheter control method for an acute cerebral infarction interventional thrombectomy, which comprises the following steps: a micro-catheter control system acquires current position state information of a micro-catheter, and drives the micro-catheter to move to a target position according to preset parameters; three-dimensional position coordinates of the microcatheter are obtained in real time through an information acquisition module; the signal processing unit compares the actual position of the microcatheter with a preset target position in real time, judges whether the microcatheter reaches the preset position or not, and receives manually input adjustment parameters when it is monitored that the resistance exceeds a threshold value or the position deviates from a path; and the signal processing unit regenerates a control instruction based on the updated parameters, and drives the microcatheter to continuously move according to the corrected parameter constraint. By acquiring the illness state and blood vessel anatomical structure information of a patient, setting the parameters such as the target position and the moving path of the microcatheter and combining the three-dimensional position coordinate information acquired by the position sensor, the microcatheter can be accurately controlled to reach the target position and move according to the preset path.

The imaging apparatus configured to assess and quantify motion associated with an object and, in a specific case of an eye—retinal vascular anatomy and hemodynamics and generate substantially contrast-free maps of retinal blood flow over a wide field-of-view at up to 590 fps and under short exposure durations (>50 μs), is applicable for diagnosis, study, and management of neurodegenerative conditions (i.e. mild cognitive impairment and Alzheimer's disease) and systemic cardiovascular diseases (i.e. athero- and arteriosclerosis, coronary artery occlusion, and hypertension). The apparatus employs a) a set of apertures substantially blocking light, delivered from a source of light to an illumination arm of the apparatus, from impinging onto an axial point of the front surface of the lens of the illumination arm, and b) polarization gating between the illumination and light-collecting arms of the apparatus. In one implementation, the apparatus is configured to allow for irradiation of the object with an optical field a degree of coherence and / or spectral content of which are varied delivered through the same optical train including the set of apertures.

A system for improving the function of a defective heart includes a tubular membrane, a replacement valve, a set of one or more inlets, and a set of one or more outlets. The tubular membrane encompasses (i) a first chamber of the system, shaped to conform to an interior region of a right atrium of the heart, and (ii) a second chamber of the system, shaped to conform to an interior region of a right ventricle of the heart. The replacement valve is configured to separate the first chamber from the second chamber, and has leaflets for providing flow in only one direction. The one or more inlets connect the first chamber with a first portion of cardiovascular anatomy, and the one or more outlets connect the second chamber with a second portion of cardiovascular anatomy.

This invention discloses an automatic liver segmentation method and system based on anatomical prior guidance of vascular flow direction, belonging to the fields of medical image processing, computer-aided diagnosis, computer vision, and artificial intelligence. The method includes acquiring liver medical images and vascular flow direction features, constructing a three-dimensional vascular direction vector field and vascular topology map, and extracting vascular anatomical prior features using a graph convolutional network; enhancing key vascular region features by combining an attention mechanism and fusing them with liver image features; outputting a liver segment probability map through a decoding network; training the model based on cross-entropy loss, boundary alignment loss, and region consistency loss to achieve end-to-end optimization; and finally outputting the liver segmentation result, which can be used for medical image visualization and surgical planning assistance. This invention improves the accuracy, robustness, and anatomical consistency of liver segmentation, and has good clinical application value.

An example method includes receiving ultrasound (US) data from an echocardiogram probe for a region of interest for of the intracardiac transcatheter procedure. The method also includes constructing a three-dimensional (3D) model of the region of interest based on the US data. The 3D model tracks a set of markers, and a marker of the set of markers has a position on the 3D model. The method additionally includes displaying an output image. The output image comprises an output US image of a portion of the region of interest, overlaid with a portion of the 3D model corresponding to the portion of the region of interest. The portion of the 3D model comprises the marker. In some examples, the marker tracks a stationary position such as a rapid pacing position associated with a feature, including while the feature is in motion.

In various examples, a skirt for creating a seal between an implantable vascular device and vascular anatomy of a patient includes a seamless tubular structure. The tubular structure is formed from a textile material. A plurality of protrusions extend radially outwardly from the tubular structure. The protrusions are formed within and integral with the tubular structure. Each protrusion including an initial shape, wherein the protrusions are configured to flatten with pressure applied in a radially inward direction with respect to the tubular structure and recoil with pressure at least partially removed to regain the initial shapes of the protrusions, such that the protrusions conform to the vascular anatomy to create the seal between the implantable vascular device and the vascular anatomy.

Exemplary methods can be used to modify a base part, form battery devices, or form devices with surface modification. Exemplary methods can form at least one junction in a base part, and devices can have at least one material junction therein. Exemplary devices, systems, and methods can deliver a drug to body tissue. Exemplary devices and methods can transmit a signal to, or receive the signal from, cardiovascular anatomy and / or a nervous system. Exemplary devices can interface with body tissue and methods can fixate a device to body tissue. Exemplary methods can use a microneedle device. Exemplary biopsy systems and methods can use a biopsy device, the biopsy device including a first tube and a second tube nested in the first tube. Exemplary devices, systems, and methods can cauterize target tissue within body tissue, ablate the target tissue, map electrical activity in the target tissue, or a combination thereof.

This invention discloses an independent drive and collaborative control method for a double-layer medical catheter, comprising the following steps: drive system configuration; sensing data acquisition; collaborative control model construction; drive command generation; drive execution and dynamic adjustment; and safety protection. This invention achieves high-precision independent drive of the two layers of catheters by configuring independent drive units and multi-dimensional sensing modules for the double-layer catheter. Combined with Kalman filtering and PID control algorithms, the positioning error of the inner catheter is controlled within 0.1mm, and the posture adjustment accuracy of the outer catheter is improved by 40%, significantly outperforming existing technologies. Through variable-parameter PID control and operation intention prediction adjustment, the drive response time is shortened to within 50ms, eliminating the lag defects of traditional control and achieving instant matching between the doctor's operation intention and catheter movement, improving the smoothness of surgical operations. The dynamic collaborative control model built based on reinforcement learning can adaptively adjust the collaborative relationship according to vascular anatomy, lesion location, and real-time load data.

The present application relates to the technical field of medical image processing, in particular to a BAD identification model construction method and a BAD identification method based on a small sample. In the present application, a first data set is first constructed as a training sample for model pre-training through data augmentation, then a simulated lesion conforming to the clinical pathological rule is generated in combination with the vascular anatomy features of the PPA region to obtain a second data set, and the pre-trained model is efficiently fine-tuned using the second data set to significantly improve the model generalization ability under the condition of a small sample. At the same time, the finally constructed BAD identification model can automatically analyze the image features and output a diagnosis result. Moreover, through the two-stage training strategy, the powerful feature extraction capability of the pre-trained model is retained, and the model is well adapted to the BAD diagnosis task through a small amount of parameter adjustment, thereby effectively improving the model performance and generalization ability under the condition of a small sample data.

The invention relates to systems and methods for generating patient-specific 3D anatomical models of cardiac and vascular anatomy for real-time, near-real time, and / or interactive catheter and interventional tool navigation and tracking.

The invention belongs to the technical field of medical diagnosis, and relates to an intravascular lesion precise positioning system based on quantum dot labeling and a method thereof, and the method comprises the following steps: enriching at a vascular wall lesion to form a labeled lesion after targeted combination; generating a blood vessel three-dimensional structure image representing a blood vessel anatomical structure; planning and generating candidate excitation point coordinates in the abnormal region; synchronously collecting a fluorescence signal returned by the environmental response type quantum dot probe, and generating a time sequence fluorescence response sequence; generating focus local structure parameters; calculating and generating a calibrated standard response curve; generating a quantitative lesion activity index representing the lesion danger level through comprehensive calculation; and fusing the quantitative lesion activity indexes corresponding to all the coordinate points and the image of the three-dimensional structure of the blood vessel to generate an integrated three-dimensional quantitative diagnosis report. According to the invention, the problem that the signal attenuation effect causes serious underestimation of the real signal of the deep focus is solved.

The invention relates to the field of operating forceps, in particular to a pair of inferior vena cava root blood vessel dissecting and separating forceps for liver surgery, which comprises a forceps body and a tube body, and a pull rod is arranged in the tube body; a first supporting seat is fixedly connected to the inner wall of the pipe body, a transmission fluted disc is rotationally connected to the first supporting seat, a hollow telescopic rod is fixedly connected to the middle of the transmission fluted disc, the other end of the telescopic rod is connected with the clamp body, and the pull rod penetrates through the telescopic rod and drives the clamp body to clamp by pulling; the inner wall of the pipe body is fixedly connected with a second supporting seat, the middle section of the pull rod is of a sawtooth flexible strip structure, and the second supporting seat is provided with a lock hole used for clamping the sawtooth flexible strip structure in a one-way mode and first lock teeth. The inner wall of the pipe body is slidably connected with a ratchet bar, the pull rod is provided with second locking teeth for unidirectionally clamping the ratchet bar, and a driving part is arranged at the end, close to the transmission fluted disc, of the ratchet bar. According to the technical scheme, the clamp body can be controlled to clamp by pulling out the pull rod, the clamp body can be controlled to rotate by pulling back the pull rod, hand operation is optimized, and control performance is improved.

COMPUTER-IMPLEMENTED METHOD FOR ESTIMATING THE FRACTION OF CORONARY RESERVE FLOW, SYSTEM Method for estimating the fraction of coronary reserve flow (FFR) of a vessel comprising: Acquisition (ACQ1) of a first image from an imaging system; Extraction (EXT1) of a first set of data (ENS1) defining anatomical descriptors of a first vessel; Acquisition (ACQ2) of a second set of data (ENS2) comprising at least the heart rate, systolic pressure and myocardial mass;Generation (GEN1) of an output (S1) defining a prediction of a quantity of coronary flow reserve fraction (FFR) by means of the execution of a first machine learning model (MLA1) to produce an output (S1), said first machine learning model (MLA1) implementing a parameterizable loss function including at least one first factor modeling at least one parameterized physical constraint optimized during the training of said model (MLA1), said parameterized physical constraint resulting in particular from a numerical model of hemodynamic equations (MOD1). Figure for the abstract: Fig.5;

The invention provides a branch stent system for reconstructing a visceral artery, and relates to the technical field of vascular intervention medical instruments, the branch stent system comprises a main stent module, the main stent module is provided with a side hole structure, and the side hole structure adaptively adjusts the size of an interface according to the diameter of a branch blood vessel; the branch support module is provided with a connecting structure, and the branch support module and the side hole structure form a connecting channel; and the conveying module comprises a conveying catheter and a release mechanism, and the conveying catheter bears and conveys the branch stent module. According to the branch stent system for reconstructing the visceral artery, accurate butt joint of the branch stent and the main stent is ensured by adjusting the size of the connector in a self-adaptive mode and adjusting the implanting angle and the releasing position in real time, the problems of deviation, untight attachment and the like caused by blood vessel anatomy difference in the prior art are solved, and the safety and the success rate of an operation are improved.

Potential treatment is planned by retrieving three-dimensional data including vascular anatomy and patient vasculature. Generating a post-treatment hemodynamic model based on a patient vasculature, the patient vasculature being modified based on a proposed treatment applicable to the patient vasculature; at least one lesion of the patient vasculature is introduced or enlarged in the post-treatment hemodynamic model to create a long-term hemodynamic model. Blood flow is simulated in a long-term hemodynamic model. A predicted physiological impact of the proposed treatment is generated based on the long-term hemodynamic model.

An angiogram is a study of blood vessels where an angiographic chemical contrast agent is injected while a sequence of images (typically x-rays) are obtained. The contrast pattern on the sequence of images provides information about the vascular anatomy and physiology. The discovery that contrast in blood vessels varies at cardiac frequency in magnitude and phase, which may be visualized as a spatiotemporal reconstruction of cardiac frequency angiographic phenomena, enables a set of processes for increasing the signal to noise ratio or equivalently the informational content of an angiogram. In this invention, the organization of cardiac frequency magnitude and phase enables equivalent information on anatomy and physiology to be obtained with less dose of injected chemical contrast agent, less x-ray dose, and / or less navigation of the injecting catheter within blood vessels. The cardiac frequency magnitude and phase is organized so that the arterial and venous subsystems of circulation have coherence at cardiac frequency. This enables processes for diagnosing deficits of circulation that involve alterations in the transit of blood from the arterial to the venous subsystems of circulation. Furthermore, the discovery of cardiac frequency magnitude and phase organization enables the design and manufacture of lighter and more portable angiography equipment.

The utility model discloses a blood vessel probe insertion assembly and an indwelling blood vessel probe insertion assembly, and the blood vessel probe insertion assembly comprises a slotted sleeve which comprises a sharp tip configured to be inserted into a blood vessel anatomical structure of a patient; and a sidewall extending proximally from the sharp tip and defining a slot; a split sheath shaped to surround at least a portion of the sidewall; a digital probe comprising: a sensor tip configured to generate sensor data indicative of operation of the vascular anatomy; and a shaft extending proximal to the sensor tip; and a data hub operatively coupled to the digital probe, where the data hub is configured to receive sensor data and transmit the sensor data to a monitoring system. Vascular probe insertion assemblies described in the present disclosure enable direct intravascular measurement of hemodynamic and blood-based critical patient parameters with minimal footprint on the patient's body.

A stent graft apparatus for endovascular treatment of aortic diseases includes a balloon-expandable section and a self-expanding section connected by radial sutures to form a unitary device. The balloon-expandable section comprises a metallic framework configured for deployment via balloon inflation and includes a plurality of radially equidistant radiopaque markers for fluoroscopic visualization. The self-expanding section comprises a shape-memory material configured to exert continuous radial force upon release. The connected sections are sequentially deployed through a catheter-based delivery system, allowing the balloon-expandable section to anchor the graft precisely at the treatment site before the self-expanding section is released to conform to the vessel anatomy. This configuration facilitates both accurate positioning and anatomical adaptability, reducing the risk of migration and improving fixation in complex aortic regions. The apparatus may be used to treat aneurysms, dissections, or injuries in various segments of the aorta.

Exemplary methods can be used to modify a base part, form battery devices, or form devices with surface modification. Exemplary methods can form at least one junction in a base part, and devices can have at least one material junction therein. Exemplary devices, systems, and methods can deliver a drug to body tissue. Exemplary devices and methods can transmit a signal to, or receive the signal from, cardiovascular anatomy and / or a nervous system. Exemplary devices can interface with body tissue and methods can fixate a device to body tissue. Exemplary methods can use a microneedle device. Exemplary biopsy systems and methods can use a biopsy device, the biopsy device including a first tube and a second tube nested in the first tube. Exemplary devices, systems, and methods can cauterize target tissue within body tissue, ablate the target tissue, map electrical activity in the target tissue, or a combination thereof.

The present disclosure provides an AI engine configured as a UNet model. The UNet model includes an encoder and a decoder, which can synthesize a 3D MRA image and its MIP image using a single contrast MR image (T1 weighted MR image) acquired for the same subject, while maintaining continuity of vascular anatomy and important vascular morphological features.

The invention relates to the technical field of medical instruments, and particularly discloses an adjustable bending sheathing canal system. In order to solve the problem that an operator is forced to replace sheathing canals of different specifications midway, the hemostasis device comprises a handle, a sheathing canal and a hemostasis valve assembly, the sheathing canal is provided with a fixed section and an adjustable bending section, a first bending adjusting ring and a second bending adjusting ring are arranged in the adjustable bending section at intervals, a first bending adjusting wire and a second bending adjusting wire are arranged in the sheathing canal in a penetrating mode, the first bending adjusting wire is connected with the first bending adjusting ring, and the second bending adjusting wire is connected with the second bending adjusting ring. The second bending adjusting wire is connected with the second bending adjusting ring, an adjusting assembly is arranged in the handle and comprises a first driving block and a second driving block, and the first driving block can pull the first bending adjusting wire to enable the adjustable bending section to bend with a first curvature radius; the second driving block can pull the second bending adjusting wire to enable the adjustable bending section to bend with a second curvature radius, and the first curvature radius is different from the second curvature radius. Different bending modes can be selected according to the anatomical form of the blood vessel without replacing instruments.

A vascular access guidance platform provides enhanced visualization and accuracy for medical procedures through an integrated extended reality system. The platform comprises an extended reality visualization system configured to display three-dimensional holograms overlaid on patient anatomy, a registration and tracking system for spatial alignment between virtual and physical anatomy, multiple imaging sensors including infrared cameras and ultrasound devices, and a processing system with coordinate transformation algorithms. The system captures anatomical imaging data, generates augmented representations of vascular anatomy, and aligns these representations with physical patient anatomy using registration techniques including optical markers, spatial mapping, and bony landmark registration. The platform maintains real-time tracking capabilities throughout procedures, accommodating patient movement and practitioner repositioning. Applications include intravenous therapy, hemodialysis access, and blood sampling procedures.

The invention relates to the technical field of medical image processing, in particular to a BAD recognition model construction method based on small samples and a BAD recognition method. According to the method, through data augmentation, the first data set is firstly constructed to serve as a training sample for model pre-training, then the simulated focus conforming to the clinical pathological law is generated in combination with the PPA area vascular anatomy features, the second data set is obtained, and the second data set is adopted to perform efficient fine tuning on the pre-training model; and the model generalization ability under the small sample condition is obviously improved. And meanwhile, the finally constructed BAD identification model can automatically analyze image features and output a diagnosis result. Moreover, according to the method, through a two-stage training strategy, the powerful feature extraction capability of the pre-training model is reserved, the model is enabled to well adapt to the BAD diagnosis task through a small amount of parameter adjustment, and the model performance and generalization capability under the condition of small sample data are effectively improved.

Exemplary methods can be used to modify a base part, form battery devices, or form devices with surface modification. Exemplary methods can form at least one junction in a base part, and devices can have at least one material junction therein. Exemplary devices, systems, and methods can deliver a drug to body tissue. Exemplary devices and methods can transmit a signal to, or receive the signal from, cardiovascular anatomy and / or a nervous system. Exemplary devices can interface with body tissue and methods can fixate a device to body tissue. Exemplary methods can use a microneedle device. Exemplary biopsy systems and methods can use a biopsy device, the biopsy device including a first tube and a second tube nested in the first tube. Exemplary devices, systems, and methods can cauterize target tissue within body tissue, ablate the target tissue, map electrical activity in the target tissue, or a combination thereof.