280 results about "Anatomical structures" patented technology

The present teaching relates to estimating 3D pose of an ultrasound probe. An ultrasound image is acquired by an ultrasound probe deployed at a three-dimensional (3D) probe pose during a medical procedure directed to a target organ. A mask for each two-dimensional (2D) anatomical structure is identified and a corresponding label is estimated from the ultrasound image to generate an ASM / label pair. If a sequence of prior 3D probe poses does not exist, an ASM / label representation for the ultrasound image is generated based on the ASM / label pairs from the ultrasound image and used to estimate the 3D pose of the probe via an ASM-pose mapping model. If the sequence of prior 3D probe poses exists, the 3D probe pose is predicted based on the sequence of prior 3D probe poses and an ASM / label representation is generated based on a virtual ultrasound image created based on the predicted 3D probe pose.

A method for analysing anatomical structure data such as, for example, arteriovenous fistula (AVF) data includes the following steps: Receiving 2D ultrasound images of the anatomical structure; genera

This invention discloses a medical image segmentation method based on inverse residual attention and multi-scale context. The method inputs the medical image to be segmented into an improved RAS-UNet segmentation network model. This model introduces an inverse residual attention module at the bottleneck feature of the deepest layer of the encoder, which suppresses background through an inverse weighting mechanism and enhances attention to blurred boundaries and weak response regions. Simultaneously, a hollow spatial pyramid pooling module is introduced into the decoding path, utilizing a parallel multi-branch structure to fuse multi-scale contextual information to adapt to lesions or anatomical structures of different sizes. Skip connections between the encoder and decoder achieve efficient fusion of detailed and semantic features. This invention can significantly improve the accuracy and boundary accuracy of segmenting medical targets such as polyps, breast tumors, and the hippocampus, providing a reliable tool for clinical auxiliary diagnosis.

A self-supervised learning (SSL) model to learn an anatomically consistent embedding from unlabeled medical images receives a plurality of unlabeled medical images including consistent large / global and small / local anatomical structures, and divides each of the plurality of unlabeled medical images into a grid of non-overlapping patches. Two random crops are extracted from each of the plurality of unlabeled medical images, wherein each of the two random crops comprises a subset of the grid of non-overlapping patches and shares with the other of the two random crops a partially overlapping region of the grid of non-overlapping patches. A global consistency branch is executed that captures discriminative macro-structures in the plurality of unlabeled medical images by extracting global embeddings. A local consistency branch is concurrently executed that learns fine-grained local anatomical details in the plurality of unlabeled medical images via composition and decomposition operations.

The application belongs to the field of medical devices, and particularly relates to a humeral shaft middle-distal fracture anterolateral MIPPO bone plate, which comprises a bone plate main body, a plurality of screw holes one are uniformly arranged on the proximal end to the middle end and the distal end of the bone plate main body, a plurality of screw holes two are arranged on the distal end of the bone plate main body, the diameter of the screw hole one is greater than the diameter of the screw hole two, the screw holes of the proximal end and the distal end of the bone plate are respectively provided with screw holes matched with screws of different diameters, the structure of the bone plate is designed on the basis of CT scanning data of humeral bones of a plurality of patients, and the bone plate is designed according to the structure of the reconstructed three-dimensional model of the humeral bone, so that the bone plate is more in line with the anatomical characteristics of the patient, and the bone plate is more suitable for anterolateral MIPPO surgery in cooperation with a matching device, indirect reduction of a fracture can be realized, the operation is further simplified, the operation time is saved, the amount of bleeding is reduced, and the surgical trauma is reduced.

This invention discloses an olfactory electrostimulation model for automatically generating current stimulation signals for an artificial nose, relating to the technical field of olfactory stimulation signal generation using biomimetic neural networks. The implementation steps include: First, constructing a biomimetic neural network framework. Based on the neuronal anatomical structure of the olfactory epithelium and olfactory bulb system, extracting the main neuron types, and organizing them according to their connection methods in biological systems; Second, using the Hindmarsh-Rose neuron model to model various neurons in the constructed network and simulate their dynamic firing behavior; Subsequently, setting the connection weights between neurons and the interlayer transmission current to realize the computational model of the entire biomimetic neural network; Finally, in the odor encoding and stimulation signal generation stage, the odor detection curve of the electronic nose is used as an external stimulus input to the biomimetic neural network. The network calculates and generates a series of peak signals, which are output as current stimulation signals to the olfactory bulb for stimulation, thereby realizing the olfactory induction function of the artificial nose.

The present application relates to the technical field of plant science, and particularly relates to a device and method for measuring the anatomical structure of plant fine roots without thin sectioning. By directly staining, stably positioning and microscopically observing the cross section of fine roots, clear and complete anatomical images of the cross section of fine roots can be obtained without dehydration, embedding and ultrathin sectioning, and reliable measurement of anatomical parameters can be realized. The steps of fixing, dehydrating, embedding and ultrathin sectioning are omitted, the sample preparation process is significantly simplified, the time from processing to imaging is shortened, the overall measurement efficiency is improved, and the device is suitable for multi-sample and batch analysis scenarios. Under the premise of ensuring the reliability of the identifiable and measurable anatomical structure, the process is simplified, the efficiency is improved and the cost is reduced, and the device has good technical value and application prospect.

Systems and methods are provided for providing adaptive and intelligent segmentation processes that support personalization during ultrasound scanning. In one example, an ultrasound imaging system includes a processing circuit having a processor coupled to a memory device storing instructions thereon that, when executed, cause the processing circuit to perform operations including generating an ultrasound image based on image data obtained by a transducer; segmenting an anatomical structure in the ultrasound image using a segmentation algorithm; presenting, on a display of the ultrasound imaging system, the ultrasound image including the segmentation of the anatomical structure; receiving, via the display, an input from a user, the input including an adjustment to the segmentation of the anatomical structure; adjusting the segmentation of the anatomical structure based on the input; presenting, via the display, the ultrasound image with the adjusted segmentation of the anatomical structure; and updating the segmentation algorithm based on the input.

The present application relates to the technical field of three-dimensional modeling, in particular to a cardiovascular three-dimensional reconstruction system based on multi-modal image data fusion. The present application determines the composite matching cost between the corresponding two points based on the position difference between the three-dimensional prediction contour point and the two-dimensional observation edge point at each time, the spatial constraint of anatomical structure and the consistency of direction characteristics, and determines the best matching pair set between the three-dimensional prediction contour point and the two-dimensional observation edge point. Based on the composite matching cost of the matching point pair in the best matching pair set, the geometric error cost after removing the influence of the spatial constraint of anatomical structure and the spatial constraint of anatomical structure are removed, the projection deviation between the matching point pair is adjusted, the position of the three-dimensional prediction contour point of the three-dimensional reference model is updated, and the three-dimensional reconstruction model is obtained. The present application realizes accurate reconstruction of the cardiovascular model under the irregular heart rhythm of atrial fibrillation by using multi-dimensional constraint composite cost accurate matching and based on the double constraint update strategy of geometric error and anatomical resistance.

The application relates to the technical field of orthopedic puncture, in particular to an orthopedic puncture navigation system; through the cooperation of a puncture positioning module and a control module, image data and a mechanical adjusting mechanism are organically combined, high-precision planning and positioning of a target puncture point, a puncture angle and a puncture depth are realized, the dependence on the experience of an operator in traditional puncture operation is significantly reduced, the problem of inaccurate positioning caused by artificial judgment deviation is effectively solved, the operation time is greatly shortened, so as to reduce the pain and operation risk of a patient, the puncture positioning module adopts a mechanical structure of a multi-degree-of-freedom adjustable machine, through the cooperation of a horizontal distance adjusting rod, a vertical distance adjusting rod and a positioning cylinder, flexible and accurate adjustment of the position and angle of a target puncture needle in a three-dimensional space is realized, the structure is compact and the adjusting logic is clear, the adaptability of the system to different anatomical structures and operation scenes is enhanced, and the flexibility and controllability of operation are improved.

A method for inserting a puncture device through the skin of a subject includes the steps of: applying a skin cover unit to the skin of the subject at the puncture site; imaging the anatomical structures and / or the puncture device beneath the skin of the subject at or near the puncture site using an ultrasound probe on the upper side of the base in a distal direction; and inserting the puncture device at the puncture site.

Systems and methods are described for segmenting medical images, such as magnetic resonance images, using a deep learning model that has been trained using random dropped inputs, standardized inputs, or both. Medical images can be segmented based on anatomy, physiology, pathology, other properties or characteristics represented in the medical images, or combinations thereof. As one example, multi-contrast magnetic resonance images are input to the trained deep learning model in order to generate multiple segmented medical images, each representing a different segmentation class.

This invention provides a video matching method for uncertainty-aware navigation in ophthalmic surgery, comprising: performing anatomical structure segmentation and neighboring frame fusion matching based on ophthalmic surgical video sequences to obtain a highly reliable neighboring frame matching library; performing motion analysis and frame pair selection and pairing based on a full-frame anatomical segmentation mask to obtain a globally selected set of difficult sample frame pairs; constructing a spatial lookup table to generate a pseudo-label training dataset; performing uncertainty-guided contrastive learning to obtain a final uncertainty-aware matching network; calculating the final filtered rotation angle using a reference frame and the current frame; and updating the incision position, capsulorhexis range, and intraocular lens implantation axis to obtain a real-time superimposed navigation visualization result. This invention can significantly reduce the algorithm training cost, enhance robustness in complex surgical environments, solve occlusion and deformation interference, effectively suppress error accumulation in semi-supervised learning, and improve the absolute accuracy of matching.

The present invention provides a system and method for a two-step registration procedure that enables complete surgical intervention by a robot. [Solution] A system for intraoperative navigation is provided, comprising a processing unit and a tracking device for real-time or near-real-time tracking of an object in a 3D coordinate system, wherein the processing unit is configured to receive an X-ray image depicting an anatomical structure including at least one bone, and to determine an incomplete registration of the position of the anatomical structure in the 3D coordinate system. The incomplete registration is determined based on a 3D dataset of the received anatomical structure and a plurality of virtual X-ray images generated from different directions based on the 3D dataset of the anatomical structure. The incomplete registration can be understood as an approximation of the position of the anatomical structure. Based on the incomplete registration, instructions for the navigation of the device are provided.

The application discloses a human vagina micro-ecological in-vitro model and a construction method and application thereof, and relates to the technical field of medicines.The application discloses a human vagina micro-ecological in-vitro model and a construction method and application thereof.Firstly, a mixed cell group of the vaginal epithelium containing a complete cell lineage and capable of long-term subculture is successfully established, a technical bottleneck that primary vaginal epithelial cells are difficult to expand is solved, and ideal seed cells are provided for model construction.Secondly, a highly-bionic vaginal mucosa model having a tight connection structure, rich layers and an orderly arrangement is constructed, and the physiological barrier and immune regulation functions of the vaginal mucosa are truly simulated.Finally, by introducing lactobacillus symbiosis and confirming the response to estrogen, a multi-element in-vitro research model integrating the anatomical structure of the vagina, resident flora, local immunity and endocrine regulation is constructed, and a reliable technical platform is provided for in-depth exploration of the mechanism of vaginal micro-ecological disorder and efficient screening of related drugs.

This invention provides a method for determining a global confidence index for 2D ultrasound images extracted from a 3D ultrasound volume, wherein the global confidence index indicates the suitability of the 2D ultrasound images for medical measurements. The method includes obtaining a 3D ultrasound volume of an object and extracting a set of at least one 2D ultrasound image from the 3D ultrasound volume. Then, a set of geometric indicators is obtained using a first neural network, wherein each geometric indicator indicates a geometric feature of an anatomical structure of the object. The set of 2D ultrasound images is then processed using a second neural network, wherein the output of the second neural network is a set of anatomical indicators, and wherein the anatomical indicators at least indicate the presence of anatomical landmarks. A global confidence index is determined for each 2D ultrasound image in the set of 2D ultrasound images based on the geometric indicators and the anatomical indicators.

This application discloses a method and electronic device for predicting intraocular lens (IOL) selection and rotation implantation, relating to the field of computer technology. This application acquires the user's ocular biological measurement parameters and constructs an intraocular geometric constraint region. The IOL is abstracted as a rectangular geometries, generating a set of candidate size-axis positions. Each candidate option satisfies the geometric constraints of the patient's intraocular anatomy in terms of implantation position and rotation angle. Based on this, by combining the geometric fit indices of the candidate options with individualized ocular biological parameters, the postoperative arch height, the probability of abnormal arch height, and postoperative refractive results are predicted. After post-processing and calibration, outputs with confidence intervals or risk probabilities are provided. This eliminates reliance on experience or rough estimates for surgical planning, effectively reducing the risk of arch height deviation or postoperative refractive errors, providing the optimal IOL option, and achieving individualized, quantifiable, and predictable implantation planning.

This invention provides a wearable myocardial oxygenation monitoring device based on optical path arrangement, comprising a detection component and a control component integrated into a flexible layer. The detection component includes multi-wavelength light sources arranged at an angle of 5° to 20° to the sagittal plane of the human body, detection components partitioned according to coordinate systems of 180° to 240° and 315° to 45°, and diagonally arranged electrocardiogram electrodes. The light sources correspond to the anatomical structure of the anterior interventricular groove of the heart. The control component achieves synchronous signal acquisition and processing via an FPC circuit board. Through precise anatomical positioning, partitioned detection, and flexible fit design, this invention solves the problem of difficulty in distinguishing the functional differences between the left and right ventricles in existing technologies. An adaptive light intensity modulation mechanism based on BMI ensures the optimal balance between signal quality and energy efficiency for different body types. Multi-data fusion enhances the early warning sensitivity of myocardial ischemia, making it suitable for people of different body types and providing a reliable tool for early screening of coronary heart disease.

The application discloses a fault scanning control method and device, a fault scanning equipment and a storage medium. The method comprises the following steps: identifying a key anatomical structure of an initial projection image based on a pre-trained trajectory planning model, generating a probability distribution map, determining a sparse scanning angle sequence and corresponding first scanning parameters, densely sampling and appropriately increasing a radiation dose in a high-weight area, and sparsely sampling and reducing a dose in a low-weight area; controlling the fault scanning equipment to perform scanning, obtaining first projection data and reconstructing the first projection data into a sparse reconstruction image; performing multi-modal fusion and scoring on the sparse reconstruction image and the current scanning parameters through an image quality evaluation model, adaptively optimizing scanning instructions according to the probability distribution map, a fusion feature vector, an image quality score, an equipment state and historical action data, generating second scanning parameters, making the scanning trajectory more continuous and smooth through an artificial intelligence technology, and realizing regional adaptive regulation and control of angles, doses and paths, so that the imaging resolution can be improved.

A system receives a set of two-dimensional projection images associated with respective projection angles from an imaging device. The projection images include projections of an anatomical structure, an anatomical target, and possibly fiducial markers, with a flexible elongate device disposed therein. The system can reconstruct a three-dimensional image from the set of two-dimensional projection images. In some examples, prior to reconstruction, the system can detect and repair pixels (within the projection images) associated with the fiducial markers, the flexible elongate device, and / or other objects. The system can enhance the reconstruction using a style transfer model. The system or another system can train the style transfer model by generating two-dimensional projections for a training set based on three-dimensional ground truth images.

Back-of-hand heat protection device, in particular for use when cutting meat on vertical grilling appliances, characterized by: a flat base made of heat-resistant silicone material, which is adapted to the anatomical shape of a human back of the hand; a textile air-mesh inlay arranged on the inside of the base for ventilation; and at least two fastening elements arranged on the outside of the base for receiving a heat-reflecting shield.

The application discloses a skull local point cloud registration method based on adaptive geometry-appearance joint cost, relates to the field of point cloud registration, and comprises the following steps: performing three-dimensional reconstruction on preoperative CT slices to obtain a skull CT point cloud model; performing semantic segmentation on RGB-D data of an intraoperative anatomical structure to obtain a target region mask; performing spatial back projection on depth in the target region mask to generate surface point cloud with color attributes; performing guided completion and filtering on missing and weak areas of the surface point cloud with color attributes according to an edge confidence map extracted from color and depth, to obtain a completed point cloud retaining important boundaries; and constructing an adaptive geometry-appearance joint cost to perform rigid registration on the skull CT point cloud model and the completed point cloud, so that accurate alignment of a spatial position of a patient during operation and the skull CT point cloud model is realized without using body surface calibration points.

This invention relates to the field of AI analysis technology for medical ultrasound images, specifically to an intelligent ultrasound image analysis method and system based on artificial intelligence. The method includes: acquiring ultrasound image sequences of a target patient and performing standardized preprocessing; extracting deep features through an anatomical structure recognition network to generate an anatomical structure description containing boundary contour coordinate sequences, tissue type classification identifiers, and spatial location depth information; using a lesion feature discrimination model to perform multi-dimensional feature fusion analysis on the three types of information to obtain preliminary lesion localization and attribute descriptions; then verifying spatiotemporal continuity based on adjacent frames of the image sequence to check the consistency of lesion evolution and generate a verification report; comparing the report with a medical knowledge base template to output an auxiliary diagnostic conclusion with diagnostic opinions and confidence ratings. This invention can enrich the dimensions of anatomical structure representation, improve the accuracy of lesion discrimination, ensure the temporal consistency of analysis results, and enhance the reliability of auxiliary diagnostic conclusions.

The application relates to the technical field of medical image processing, in particular to a three-dimensional medical image registration method and device, electronic equipment and a storage medium. The method comprises the following steps: determining target points matched with preset reference points on a reference image from a mobile image; wherein the reference points are preset with one or more, therefore, the target points also have one or more, so that the matching of the reference points on the reference image and the target points on the mobile image can be realized; determining a global displacement amount of the mobile image according to the displacement deviation of all the target points, so that all the target points in the mobile image can be constrained, and the spatial relationship among all the target points is established; and registering the mobile image according to the global displacement amount, so that the points in the registered mobile image can meet the requirements of an anatomical structure as much as possible.

This invention relates to an intelligent high-voltage pulsed electrical stimulation system and control method, addressing the problems of poor individual adaptability, low positioning accuracy, and weak safety in existing technologies. The system acquires body surface point clouds through a split scanning module (infrared / TOF) and achieves dynamic mapping of anatomical structures (error <1.2mm) by combining a medical image template library. It dynamically adjusts the high-voltage pulse (0-1200V) based on a BMI-impedance model and employs an improved KNN algorithm to match the discharge scheme. An innovative three-level safety protection system is implemented, using impedance mutation detection, displacement compensation, and phase cancellation (electric field attenuation >99.9%) to protect dangerous areas. Clinical validation shows a positioning accuracy of ±0.5mm, a pain relief rate of 92% in obese patients (BMI=32), and a false trigger rate of <0.01%. This invention achieves precise targeting and safe control, and is applicable to fields such as muscle rehabilitation and pain management.

The application discloses an interventional surgery instrument operation track intelligent planning dynamic navigation control method and system, and belongs to the technical field of minimally invasive interventional surgery intelligent navigation. A patient's preoperative three-dimensional medical image and intraoperative two-dimensional perspective image are acquired, and a digital twin model of a surgery region containing anatomical structures and physical properties is constructed; an initial optimal operation track is generated through a rapidly expanding random tree and convex optimization, and an anatomical structure displacement caused by physiological motion is compensated by adopting nonlinear elastic registration based on feature points; dynamic resistance feedback is calculated in combination with an instrument mechanical response model, track correction instructions and feedback signals are output, and a closed-loop navigation is realized by driving an executing mechanism and a main operating handle. The system contains five modules of image processing, track planning, registration compensation, control calculation and executing feedback, can effectively improve operation precision and safety in a complex blood vessel environment, solves problems of interventional surgery hand feeling loss, dynamic adaptation difference and navigation precision deficiency, and is suitable for various blood vessel interventional minimally invasive treatments.

The application discloses a CBCT metal artifact suppression method based on an unsupervised preoperative prior repair network and belongs to the technical field of computer image processing. The method comprises the following steps: inputting a preoperative prior CBCT image and a CBCT image to be repaired into a generator after registration, respectively extracting anatomical structure features and non-metal region detail features by using two encoders of a double-flow feature extraction network, fusing the features, and then performing repair reconstruction on the CBCT image by using a decoder; inputting the result into a discriminator to perform authenticity discrimination and metal region discrimination and generate a fused prediction image; taking the prediction image information as a supervision signal to optimize the adversarial loss between the generator and the discriminator and the image similarity loss between the repaired image and the image to be repaired, and performing joint adversarial training on the discriminator and the generator; and processing an intraoperative CBCT image to be repaired by using the trained generator to realize more efficient metal artifact suppression.

A computer-assisted surgery system allows a user to control movements of a surgical tool by providing, to a control unit, inputs in the form of measured displacements via a movable part of a handle while treating a region of interest with the tool. The control unit is configured to enable motion of the tool with respect to an anatomical structure only if a user moves the movable part, receive the measured displacement of the movable part, receive from a localization unit the relative position and orientation of the tool relative to the anatomical structure, based on the measured displacement, on the surgical plan and on the relative position and orientation of the tool relative to the anatomical structure, compute an instruction to send to a motorized joint to move a robotic arm to operate the tool according to an optimal trajectory, and send the computed instruction to the motorized joint.

The invention relates to adaptive signal processing for human voice control and acoustic feedback management. More particularly, it concerns a system and method for detecting and cancelling a person's own voice, as may be perceived through airborne, bone, and soft-tissue conduction. The invention also covers related calibration, adaptive filtering, and neural-network implementations for such systems. The present invention represents a system and method for cancelling a perception of a user's own voice as perceived through airborne, bone, and soft-tissue conduction paths. The suggested solution may operate with minimal latency, adapt to individual anatomical and environmental conditions, and maintain transparency to external sounds. Furthermore, the solution incorporates calibration routines to accurately model the transmission characteristics of these paths. It also allows to employ adaptive or machine-learning techniques to refine cancellation performance in real time.