58 results about "Anatomical feature" patented technology

A computer-implemented method of processing repeat B-scans of an imaged region of a body part, the imaged region including an anatomical feature in a first subregion and vasculature of interest in a second subregion of the imaged region, to generate cropped B-scans for use in generating OCT angiography data which provides a representation of the vasculature of interest, the method comprising processing each B-scan of the repeat B-scans by: selecting a subset of the data elements of the B-scan such that the selected data elements are distributed along a representation of the anatomical feature in the B-scan; using the selected data elements to define a respective subregion of interest in the B-scan, which includes OCT data acquired from the second subregion containing the vasculature of interest; and cropping the B-scan to leave the subregion of interest in the B-scan.

The present invention provides a magnetic resonance imaging (MRI) system that, when imaging the same subject multiple times with a time interval between images, accurately matches a specific position of the subject, which should be depicted at the center of the current image, to a specific position depicted at the center of past images. [Solution] When the same subject is imaged multiple times with a time interval between each image, the acquisition unit acquires a first image, which is a past image in which the subject's anatomical feature points are depicted, and a locator image, which is the current image (second image), in which the anatomical feature points are depicted. The calculation unit calculates the amount of tabletop movement required to move the tabletop on which the subject is placed, based on the difference between the position of the anatomical feature points depicted in the first image and the position of the anatomical feature points depicted in the locator image, so that a specific position of the subject depicted at the center of the first image is depicted at the center of the locator image. The bed control device controls the movement of the tabletop based on the amount of tabletop movement.

This application belongs to the field of image processing and relates to a skin extraction method and system. The method includes: performing nonlinear regression fitting on the prior anatomical features of skin tissue in historical oral images to obtain a skin cutting threshold; acquiring a CBCT image of the oral cavity to be processed; extracting boundary features from the cross-sectional image layers of the CBCT image to be processed based on the skin cutting threshold to obtain a dynamic candidate masking region feature map; applying inter-layer geometric consistency constraints to the dynamic candidate masking region feature map to generate a target skin masking region; extracting the original pixel values ​​within the target skin masking region and suppressing their background values; performing isosurface evolution processing on the suppressed original pixel values ​​to generate an isosurface grid; and performing patch validity screening on the isosurface grid to generate the skin extraction result. This application can reduce the interference of irrelevant data on the extraction result during the skin extraction process and ensure the quality of skin tissue extraction as much as possible.

Surgical planning based on a three-dimensional (3D) model includes obtaining a 3D model of an anatomical region, wherein the anatomical region includes the patient's anatomical features; identifying at least one deformity, wherein the at least one deformity is identified with respect to a target anatomical value of the patient's anatomical features, wherein the target anatomical value includes a desired range into which the anatomical measurement should fall; and using the anatomical measurement, determining at least one planar correction to be made to at least one anatomical structure of the patient. Generating a 3D model using two-dimensional (2D) imaging data may include performing anatomical context processing, which includes annotating the model, contours, edges, or surfaces of the anatomical structure, as well as performing 2D-to-3D reconstruction to optimize the orientation, placement, and scale of the 3D digital volume modeling the anatomical structure, resulting in a 3D anatomical representation of the anatomical region as a 3D model.

Methods and systems for programming stimulation parameters for assisting deep brain stimulation (DBS) in experimental patients are described. A cumulative database includes data from multiple historical adaptation / programming sessions. The data may include various sets of stimulation parameters tried for patients in the database; data relating to the position of electrode leads relative to the anatomical features of the patient's brain, such as alignment with the subthalamic nucleus (STN); scores indicating the therapeutic effectiveness of the stimulation parameters; and data relating to stimulation field models (SFM) of the various sets of stimulation parameters. This database can be used to predict stimulation parameter sets that may be therapeutically effective for experimental patients.

Described herein is a system and methods for planning an aesthetic procedure on a patient, the system including: a tracker configured to generate a three-dimensional image of a face of the patient; an ultrasound probe, the ultrasound probe configured to generate an ultrasound image of the face of the patient, wherein the ultrasound image and the three-dimensional image are registered into a patient-specific composite model; and a display, wherein the display shows the patient-specific composite model created by identification of anatomical features of the patient-specific composite model, wherein the display shows a risk map derived from the patient-specific composite model, the risk map including one or more safety regions and one or more risk regions, wherein the patient-specific composite model is configured to be evaluated to select one or more target locations on the face of the patient constrained by the risk map.

This invention provides a method and system for DR image quality control based on decoupled representation learning and multi-level feedback, belonging to the field of medical image processing technology. The method includes: acquiring DR images and DICOM metadata; automatically classifying areas if the examination site is missing; extracting mixed features using an adaptive anatomical perception network; obtaining anatomical, quality, and pathological features through orthogonal decoupling; guiding region-specific quality assessment based on anatomical features and inversely generating suggestions for adjusting imaging parameters. This invention achieves complete separation of lesion and quality information through orthogonal feature decoupling, avoiding interference from pathological features in quality assessment, while providing actionable parameter feedback, significantly improving the accuracy, robustness, and clinical applicability of DR image quality control.

A computer-implemented method for evaluating an image data set that is based on a medical imaging method, including: acquiring the image data set; acquiring a body region depicted in the image data set; processing the image data set using a processing algorithm, wherein at least one processing parameter of the processing algorithm is specified depending on the determined body region; and / or checking a trigger condition, whose fulfillment depends on whether, for at least one area of image data, which is reconstructed depending on the image data set, local geometric factors of the parallel magnetic resonance imaging used as the medical imaging method indicate a sufficiently strong local reduction in the signal-to-noise ratio, wherein an anatomical feature is assigned to the respective area depending on the body region and the image data set when the trigger condition is fulfilled.

An orthopaedic surgical instrument system includes a sensor adapter and multiple surgical instruments. The sensor adapter includes a housing with a force sensor positioned within the housing and a sensor contact configured to transfer force to the force sensor extending from the housing. Each surgical instrument includes a sensor connector configured to receive the sensor adapter at a predetermined location relative to the surgical instrument. Each sensor adapter further includes a registering feature to engage an anatomical feature of a patient or another surgical instrument. The surgical instruments may include a shim that may be attached to a gap assessment tool or a tibial insert trial. Methods associated with the surgical instrument system are also disclosed.

The application discloses a real-time image superimposition method and system for augmented reality surgery navigation, relates to the technical field of monitoring analysis, and comprises the following steps: performing coordinate comparison on a physical contact coordinate and an anatomical feature site in a virtual anatomical model, obtaining a spatial deviation vector, correcting a global coordinate transformation matrix according to the spatial deviation vector, calculating a feeding speed according to a real-time spatial displacement vector, calculating a predicted residual penetration distance in combination with a change gradient of a spectrum entropy density, superimposing and displaying a virtual anatomical model and a virtual model of a surgical power head according to the corrected global coordinate transformation matrix, generating a predicted precursor model along a feeding direction according to the predicted residual penetration distance, calculating an intersection space of the predicted precursor model and a dangerous anatomical structure in the virtual anatomical model, changing a display color value of the predicted precursor model according to the intersection space when the intersection space exists, and performing transparent rendering on a virtual anatomical model region corresponding to the intersection space. The application has the effect of improving image superimposition efficiency.

The application discloses a kind of space measurement benchmark construction methods based on three-dimensional organ model, to solve the problem of lack of anatomical explainability and insufficient robustness to biological individual differences due to dependence on external morphology or overall registration in prior art.Methods include: collecting voxel data of target three-dimensional organ model and coordinates and topological relationship of internal inherent anatomical feature points;Based on anatomical prior knowledge, define a hierarchical benchmark space network containing topological layer, geometric constraint layer and coordinate system layer;The anatomical feature point set of target model is mapped and adapted to the benchmark network, and the coordinate transformation relationship is established.The application constructs the benchmark by taking the internal stable anatomical structure network as the skeleton, significantly improves the adaptability to morphological variation, gives the spatial coordinates clear anatomical semantics, and realizes the whole traceability of the measurement process, providing a reliable foundation for precision medical research and multi-source biological space data integration.

A medical imaging apparatus (10) for examining a volume of an object (12) is disclosed. The medical imaging apparatus comprises an ultrasound acquisition unit (14) comprising an ultrasound probe for acquiring ultrasound image data of the object, an image interface (20) for receiving medical image data of the object, a position determination unit (30) for determining a position of the ultrasound probe. An alignment unit is provided for aligning the ultrasound image data and the medical image data based on an anatomical feature (32) of the object and the detected position of the ultrasound probe and for adjusting the alignment of the ultrasound image data and the medical image data based on a motion model. An image processing unit (18) is provided for processing the ultrasound image data and the medical image data to fuse the ultrasound image data and the medical image data into combined image data based on the alignment.

The present application relates to the technical field of image processing, in particular to a prostate puncture target point image accurate positioning system, which solves the technical problem that in the prior art, due to the neglect of the anisotropic deformation characteristics of the prostate and the failure to compensate for the influence of the rotation of the ultrasound probe, the two-dimensional navigation image and the three-dimensional lesion space layer position are confused in the positioning process, which easily leads to missed diagnosis of puncture. The system is used for: constructing an anatomical reference atlas containing directional deformation constraints according to preoperative magnetic resonance images; extracting ultrasound anatomical features and determining probe attitude deflection information according to real-time ultrasound images; projecting the directional deformation constraints to the real-time ultrasound coordinate system according to the probe attitude deflection information, and obtaining the depth coordinates of the real-time ultrasound section; reconstructing the anatomical background image according to the depth coordinates and the probe attitude deflection information, and displaying the puncture guidance information according to the spatial relationship between the depth coordinates and the preset lesion position.

An ultrasound imaging system computes real time physiological parameters from measurements of anatomical features in ultrasound image data using a neural network to identify the location of the anatomical features. In one embodiment, cardiac parameters are computed from endocardial wall tracings in M-mode ultrasound image data that are identified by the neural network.

A method for aligning a patient's anatomical features using augmented reality is provided. This includes a system for aligning a patient's anatomical features, comprising an imaging system, a tracking device, an augmented reality system, and a computer system. The imaging system can be configured to image the patient and generate an imaging dataset. The tracking device can be configured to generate a tracking device dataset. The augmented reality system can be configured to display an imaging volume hologram in augmented reality. The computer system can communicate with the augmented reality system, the imaging system, and the tracking device. The computer system can generate an imaging volume dataset based on a first and second axis plane, render the imaging volume dataset into an imaging volume hologram, and project the imaging volume hologram into augmented reality.

This application relates to the field of medical image processing technology, and discloses a method and system for lesion analysis of SPECT and spectral CT fusion images. The method includes acquiring SPECT and spectral CT images; identifying at least one anatomical feature point in the spectral CT image and identifying a functional feature point corresponding to the anatomical feature point in the SPECT image; calculating the first spatial coordinates of the anatomical feature point in the spectral CT image and the second spatial coordinates of the functional feature point in the SPECT image; determining the deformation parameters of a local region in the SPECT image based on the difference between the first and second spatial coordinates; and performing spatial transformation processing on the functional distribution features of the local region in the SPECT image to spatially align the processed functional distribution features with the anatomical features in the spectral CT image, actively eliminating image misalignment caused by physiological motion and other factors, and achieving alignment of functional information with anatomical structures.

This invention relates to the fields of computer vision and emotion computing, and discloses a method and apparatus for dynamic facial expression recognition based on feature decoupling and multi-order trajectory modulation. The method constructs a two-stream feature decoupling coding network, extracts facial anatomical features using a static facial structure encoder with frozen parameters, and extracts structure-independent muscle motion features using a dynamic emotion encoder with an embedded adapter. Multi-order dynamics modeling is performed on the dynamic emotion features, jointly calculating first-order velocity and second-order acceleration, and a time-series emotion evolution trajectory is generated through self-attention mechanism aggregation. Scaling and translation parameters are generated using this evolution trajectory, and affine transformation is performed on the static feature sequence through feature linear modulation to achieve lossless injection of dynamic emotion into static representation. Finally, the recognition result is output through a time-series classifier. This invention effectively overcomes static identity interference, finely characterizes the rate and intensity of expression evolution, and significantly improves cross-identity generalization ability and dynamic recognition accuracy.

The application discloses a kind of microfracture surgery and cavity bone combined injection apparatus.The microfracture instrument designed by the application can more accurately control the depth and angle of microfracture punching by using a level angle sensor and a depth sensor, and the operation result can be displayed in real time by using a liquid crystal display to provide intuitive and accurate operation feedback for doctors.In addition, by improving the unadjustable bending angle of the previous instrument, the drill bit part of the application can flexibly adjust the angle to adapt to various complex joint structures and anatomical features, making it possible to perform surgery in difficult-to-reach areas.The application simplifies the operation while providing a more favorable environment and conditions for cartilage repair, which is expected to improve the treatment effect, avoid the pain and discomfort caused by secondary puncture, and reduce the risk of infection and other surgical risks.

The present application proposes a chest and abdominal respiration signal decoupling and reconstruction method based on millimeter wave radar. Using a millimeter wave multiple-input multiple-output radar device, the radar echo is first mapped to a three-dimensional space using 3D beamforming technology, mapping the one-dimensional time domain signal to a spatial energy heat map containing distance, azimuth, and elevation three-dimensional information. Then, through spatial filtering strategy, the physiological vibration source signal clusters of the subjects with coupling relationship are separated. When the physiological vibration source includes the chest reflection area of the first anatomical site and the abdominal reflection area of the second anatomical site, combined with the adaptive best point selection algorithm, according to the anatomical features of the human body, the chest reflection area and the abdominal reflection area are physically located and distinguished in the three-dimensional space, and the independent breathing waveform is extracted from the body surface reflection to perform high-precision spatial separation and anti-interference waveform extraction operation of chest and abdominal respiration movement. The present application can realize high-precision spatial separation and anti-interference waveform extraction of chest and abdominal respiration movement.

This application provides a method for identifying suspicious regions based on PET and CT fusion. The method involves acquiring CT image data and PSMA-PET image data of the object under test; denoising and HU value standardization of the CT image data; SUV standardization of the PSMA-PET image data; and non-rigid registration. Feature extraction is then performed to determine CT anatomical features and PET metabolic features. Based on these features, cross-modal collaborative analysis is conducted to identify suspicious regions. These suspicious regions are then annotated and displayed at corresponding locations in the CT image data. This approach achieves deep collaboration between CT and PSMA-PET at both the feature and decision levels by extracting CT anatomical and PET metabolic features from the registered CT and PSMA-PET image data and performing cross-modal collaborative analysis, thus accurately identifying suspicious regions.

Disclosed herein is a medical system comprising: a memory storing machine executable instructions; a computing system, wherein execution of the machine executable instructions causes the computing system to perform a misalignment check comprising: receiving pose identification system data, wherein the pose identification system data comprises a set of subject coordinates and a set of coil coordinates described using a current coordinate system, wherein the set of subject coordinates describes anatomical features of a subject, wherein the set of coil coordinates describes coil positions of magnetic resonance imaging coils, wherein coil data associated with the magnetic resonance imaging coils comprises a predefined range of coil positioning coordinates with reference to the anatomical features; determining an allowed range of coil coordinates by mapping the predefined range of coil positioning coordinates to the current coordinate system using the set of subject coordinates and the anatomical features; and providing a warning signal in the event of a misalignment between the set of coil coordinates and the allowed range of coil coordinates.

The application discloses a sparse memory time sequence fusion method for lesion detection of an ultrasonic image, and comprises the following steps: acquiring a continuous dynamic ultrasonic video frame sequence, wherein the video frame sequence comprises a plurality of ultrasonic images; extracting global anatomical features and local lesion features of each ultrasonic image; performing feature fusion projection on the global anatomical features and the local lesion features to generate current frame fusion features of a current frame ultrasonic image; evaluating the current frame fusion features to obtain an evaluation result, and updating a sparse memory feature library according to the evaluation result; and performing dynamic fusion on the current frame fusion features and historical memory features in the sparse memory feature library to obtain spatio-temporal joint enhanced features. The method can improve the stability and precision of ultrasonic video stream detection of parts such as a breast, an axillary lymph node, an abdomen and a neck.

A method, a system, and a computer program for determining a visualization of content to be displayed to a surgeon on a display of a portable display device are provided. First pose data indicative a first pose of an anatomical feature of a patient in an operating room and second pose data indicative of a second pose of a portable display device in the operating room are obtained. Based on the first pose data and the second pose data, a third pose of a surgeon relative to the patient is estimated. Based on the estimated third pose, a visualization of content to be displayed to the surgeon on a display of the portable display device is determined.

This invention discloses a collision detection method and system based on hybrid bounding boxes and lung anatomical features. The method includes: constructing bounding boxes for the lung, lung lobes, and lung segments based on a three-dimensional finite element model of the lung; determining intersecting lung segment bounding boxes using a breadth-first traversal algorithm; determining intersecting lung lobule bounding boxes using a depth-first traversal algorithm; and accurately detecting the collision position of a surgical instrument proxy ball using fine intersection detection to obtain the collision detection result. The depth-first traversal order is calculated based on the predicted positions of the lung segment bounding boxes and the surgical instrument proxy ball. This invention avoids the problems of computational redundancy and poor real-time performance in collision detection.

An automatic segmentation method for sphenoid bone subregions using a cross-scale topologically constrained dual-path segmentation network is proposed. First, cranial CT or CBCT images are resampled, intensity normalized, and coarsely localized to obtain the target volume region of the sphenoid bone. Then, the target volume region is input into a dual-path encoding network. The global anatomical path is used to extract low-resolution, high-semantic features such as the overall morphology, spatial layout, and relative positions of subregions of the sphenoid bone, while the local boundary path is used to extract high-resolution detail features such as thin bone plates, fracturing boundaries, and protrusion junctions. Finally, a cross-scale coupling fusion module interactively gates and fuses the global anatomical features and local boundary features at multiple scales to obtain fused features that combine overall structural information and edge detail information. This invention significantly improves the automatic segmentation performance of complex subregions of the sphenoid bone.

This invention relates to the field of medical image processing and cardiac surgery support technology, and discloses a standardized method for constructing a 3D model of the pediatric aortic valve based on cardiac CTA images. The method includes: acquiring DICOM format pediatric cardiac CTA images and importing them into medical image processing software; identifying eight core anatomical features of the aortic valve based on cross-sectional planes; segmenting and labeling the valve structure layer by layer; performing operations such as cavity filling, thinning, and boundary modification through a 3D view; constructing a 3D model of the aortic root vessel wall; and finally completing the standardized 3D modeling. This invention solves the problems of insufficient spatial resolution and lack of standardization in pediatric aortic valve assessment and modeling in existing technologies, accurately reproducing valve anatomical features, providing preoperative planning and simulation support for surgery, and improving surgical outcomes.

A non-invasive biometric system includes a processor configured to control a scanner configured to scan and capture one or more anatomical images of a target person's body. The processor is also configured to identify one or more anatomical structures in the captured anatomical images and extract anatomical features from the identified anatomical structures. The processor is further configured to register the extracted anatomical features of the identified anatomical structures to the target person's posture and appearance. The processor is also configured to encode and utilize the extracted anatomical features as biometric data unique to the target person and usable for authentication of the target person.

A compression garment having one or more flex frames that can be shortened or lengthened to apply or release a compressive force to the limb or other anatomical feature of a user. The compression garment can have a wire made of shape memory material (shape memory alloy). A controller of the compression garment can supply an electrical input to the wire, generating heat that can cause the wire to contract such that the flex frame deflects to a shorter length to apply a compressive force to the limb or other anatomical feature of the user. The one or more flex frames can be contracted in unison or in sequence to direct the flow of bodily fluids in the limb or other anatomical feature of the user.