28 results about "Soft tissue deformation" patented technology

The invention relates to the technical field of medical image information processing, discloses an ICG fluorescence image and MRCP three-dimensional model registration fusion display method and system, effectively solves the problems of deep biliary tract structure blurring and form distortion caused by liver tissue scattering effect in intraoperative fluorescence imaging, uses a preoperative model as anatomical prior, and improves the accuracy of the intraoperative fluorescence imaging. A viewpoint correlation optical path depth field is constructed through reverse ray tracing, a spatial variation point spread function is generated accordingly, physical reverse recovery of scattering halo in a fluorescence image is achieved, non-specific background noise such as vascular leakage is effectively inhibited in combination with topological gravitational constraint of a central skeleton, and the detection accuracy is improved. The real pipe diameter and the center line position of the deep bile duct are accurately recovered, non-rigid registration correction is performed on the three-dimensional model based on the recovered high-fidelity image, and projection errors caused by respiratory movement and soft tissue deformation are eliminated.

The invention discloses an infant airway management system and method based on navigation and high-precision dynamic registration, and the method comprises the steps: constructing a personalized airway deformation model through a physical constraint-based few-sample transfer learning network, generating an optimal instrument matching scheme, and providing a semantic weighted tight coupling visual inertial odometer; the confidence coefficient of feature points is dynamically adjusted by segmenting airway anatomy semantics in real time, data are fused under a factor graph optimization framework, and sub-millimeter robust positioning is achieved. Based on the high-precision trajectory, the system introduces a space-time attention fusion network, captures a long-range time sequence dependency relationship between operation micro-actions and physiological parameters, calculates a real-time dynamic risk score, and compensates airway soft tissue deformation in real time through a non-rigid deformation field model. The technical problems that an existing navigation system is prone to being lost in a microcosmic dynamic environment and risk early warning lags behind are effectively solved, and the safety and the success rate of the infant airway management operation are remarkably improved.

The invention discloses a topological mapping monitoring and correcting method for abnormal scapular brachial rhythm after breast surgery, and belongs to the field of medical rehabilitation and computer vision. The method comprises the following steps: acquiring a trunk dynamic three-dimensional point cloud and infrared thermal imaging data; constructing a multi-layer collaborative dynamic topology network fusing a skeleton structure, soft tissue deformation and physiological activeness; extracting an intrinsic motion field and comparing the intrinsic motion field with the ideal model to generate deviation measurement; and calculating a dynamic instability index, comparing the dynamic instability index with a threshold value, and triggering optimization energy correction path calculation and instruction output. According to the method, the multi-dimensional topological mapping and dynamics prediction technology is adopted, accurate recognition and feed-forward early warning of motion abnormity under the influence of deep tissue adhesion after the breast surgery can be achieved, rehabilitation of a patient is guided through an energy consumption minimization path, and the accuracy of shoulder joint function remodeling and the individualized treatment effect are improved.

The invention discloses a dynamic self-adaptive garment pattern generation method and system based on soft tissue deformation and multi-posture human body measurement, and belongs to the field of intelligent garment design. The method comprises the steps of multi-posture human body data acquisition, data preprocessing and database construction, soft tissue layering mechanical modeling, dynamic version parameter calculation, version automatic adjustment, cloth simulation verification, iterative optimization and feedback correction. The system comprises a data acquisition module, a human body deformation modeling module, an automatic model optimization module and the like, the modules are connected through a specific communication mode, a layered mechanical model is established by acquiring three-dimensional data and soft tissue deformation data of six typical postures of a human body, and cloth physical simulation and feedback correction are combined, so that the model is optimized. According to the method, automatic optimization of garment cutting pieces, stitches and elastic areas is achieved, the fitness and comfort of the garment in a dynamic posture are ensured, the intelligent and personalized level of garment design is improved, and the method has remarkable practical value and popularization prospects.

The application discloses a cervical vertebra health monitoring method and system, and relates to the technical field of health monitoring.The method comprises the following steps: S1: scanning the cervical midline through a flexible tactile array, and positioning the spinous process vertex according to pressure peak feedback; S2: based on the spinous process vertex, performing multimodal sensor collaborative verification; S3: based on the multimodal sensor collaborative verification, synchronously triggering a displacement measurement unit to record the three-dimensional space coordinates of the probe; and S4: based on the collected three-dimensional space coordinates, fitting a cervical curve, and calculating the radius of curvature and the cervical lordosis angle.Combining tactile array pressure distribution analysis and IMU attitude correction, the multimodal sensor collaborative verification reduces errors caused by a single sensing mode, and improves the reliability of monitoring.By adopting a topology optimization algorithm and combining related formulas, soft tissue deformation and operation errors are compensated, the output dynamic bending data is more accurate, and the reliability of the monitoring result is improved.

The invention discloses a three-dimensional model manufacturing method based on additive printing. The three-dimensional model manufacturing method comprises the steps that standard model data and manufacturing demand data are acquired; performing biomechanical simulation optimization on the standard model data based on the manufacturing demand data to generate optimized data of the soft tissue deformation rule of the human body under the target posture; based on the optimization data, lattice filling design is conducted on the standard model data, an internal supporting structure with gradient density distribution is generated, and target model data is obtained; performing multi-material 3D printing slicing processing on the target model data to plan printing strategies corresponding to different body parts in the target model data; and based on the printing strategy, the multi-material 3D printing equipment is driven to print a plurality of body part models corresponding to the target model data, and the body part models are used for being assembled to form a three-dimensional model finished product. Parting line residues and flashes existing in a traditional process are eliminated, and structural stability and light weight are both considered.

The invention provides a digital human mouth shape prediction system and method based on a variational auto-encoder in smart agriculture, and relates to the technical field of artificial intelligence, and the method comprises the steps: receiving a voice signal of a smart agriculture scene, extracting multi-dimensional voice features, and fusing the multi-dimensional voice features to generate voice representation; inputting the voice representation into a model, and decoding the voice representation into a mouth shape key point sequence; performing semantic enhancement on the mouth shape key point sequence by combining agricultural proper nouns in the input voice and a preset mouth shape template, and simultaneously inhibiting mouth shape jitter and abnormal frames; and mapping the enhanced mouth shape key point sequence to a three-dimensional digital human face model, converting the enhanced mouth shape key point sequence into face soft tissue deformation data in combination with a face parameter of a target user, calculating a skeleton node position and a rotation parameter according to a preset corresponding relationship between the mouth shape and the skeleton, and generating a digital human mouth shape animation synchronized with the input voice through combined rendering. The stable and accurate voice synchronous digital human mouth shape can be generated in an intelligent agricultural scene.

The invention relates to the technical field of image processing, and discloses an operation scene real-time dynamic reconstruction method and system based on three-dimensional Gaussian sputtering. The method comprises the following steps: extracting spatial-temporal characteristics of a soft tissue deformation Gaussian subset through a HexPlane spatial-temporal encoder; fusing the decoded feature vectors to generate a soft tissue deformation parameter set; a deformation field Jacobian matrix of Gaussian elements in the soft tissue deformation Gaussian subset is calculated, a local volume strain rate is obtained through determinant operation, when the strain rate exceeds a preset threshold value, self-adaptive densification operation is executed, and new Gaussian elements inherit parent Gaussian element deformation parameters and are updated to a corresponding set; and combining the updated parameters to carry out probabilistic boundary allocation and transmissivity perception rendering to obtain a reconstruction result. The accuracy, the physical authenticity and the stability of real-time dynamic reconstruction of the operation scene are improved.

The application discloses a real-time puncture guiding evaluation system based on soft tissue deformation field, which comprises a registration system for registering CT images and real-time ultrasonic images in operation and forming a point cloud graph through interpolation point supplementing, a deformation field determination system for determining a soft tissue deformation field, a guiding line simulation system for forming a new preoperative planning puncture guiding line in combination with the soft tissue deformation field and the registration system according to a real puncture guiding line of preoperative planning, and a comparison system for comparing the deviation of the new preoperative planning line from the real puncture guiding line with a set deviation threshold value. The application can automatically judge whether a preoperative puncture path is feasible, improves the efficiency of operation, converts the preoperative planning path to a real-time intraoperative scene, facilitates the operation of doctors, accurately registers local soft tissue deformation and reduces the operation burden of doctors.

The application belongs to the technical field of soft tissue deformation simulation, and particularly relates to a soft tissue deformation simulation method and device based on a cell neural network. The method comprises the following steps: constructing a three-dimensional cell neural network model; applying an external force to the three-dimensional cell neural network model, and calculating a cell current of a cell in the three-dimensional cell neural network model according to the applied external force; calculating a state voltage of the cell according to the cell current; calculating a displacement of the cell according to the state voltage; and performing deformation simulation on the three-dimensional cell neural network model according to the displacement of the cell. The application has good generalization, and can realize fast modeling while maintaining simulation real-time performance and simulation effect.

The application provides a digital human mouth shape prediction system and method based on a variational autoencoder in smart agriculture, and relates to the technical field of artificial intelligence. The application receives a voice signal of a smart agriculture scene, extracts multi-dimensional voice features and fuses to generate a voice representation. The voice representation is input into a model and decoded into a mouth shape key point sequence. The agricultural specific terms in the input voice are combined with a preset mouth shape template to perform semantic enhancement on the mouth shape key point sequence, while suppressing mouth shape shaking and abnormal frames. The enhanced mouth shape key point sequence is mapped to a three-dimensional digital human face model, combined with face parameters of a target user to convert into face soft tissue deformation data, and then the preset corresponding relationship between the mouth shape and the skeleton is used to calculate the position and rotation parameters of the skeleton nodes. After combination and rendering, a digital human mouth shape animation synchronized with the input voice is generated, which can generate stable and accurate voice synchronized digital human mouth shapes in a smart agriculture scene.

The application discloses a navigation and high-precision dynamic registration-based infant airway management system and method, wherein a physical constraint-based few-sample transfer learning network is utilized to construct a personalized airway deformation model and generate an optimal instrument matching scheme, a semantic weighted tight coupling visual inertial odometer is proposed, feature point confidence is dynamically adjusted in real time through real-time segmentation of airway anatomical semantics, and data is fused under a factor graph optimization framework to realize sub-millimeter level robust positioning. Based on the high-precision trajectory, a space-time attention fusion network is introduced into the system to capture long-range time sequence dependency between operation micro-motions and physiological parameters, calculate real-time dynamic risk scores, and compensate airway soft tissue deformation in real time through a non-rigid deformation field model. The application effectively solves the technical problems that existing navigation systems are prone to be lost in a micro dynamic environment and risk early warning is lagged, and significantly improves the safety and success rate of infant airway management surgery.

The anesthesia puncture visual navigation system combining augmented reality with three-dimensional reconstruction belongs to the technical field of anesthesia puncture visual navigation, and comprises a physiological motion monitoring unit, which is used for simultaneously collecting respiratory motion cycle data and soft tissue elastic deformation information, and generating a comprehensive motion state data packet by calculating the correlation coefficient of the respiratory amplitude and the tissue elastic modulus change rate, so that the spatial deviation caused by the respiratory motion and the soft tissue deformation of the patient to the puncture navigation can be effectively compensated, the puncture precision is significantly improved compared with the traditional static navigation system under the normal respiratory state of the patient, the puncture failure rate and the complication risk are effectively reduced, the problem of further precision deterioration caused by the blind application of correction parameters of the traditional system when the registration quality deteriorates is avoided, the dependence on the personal experience of the doctor is reduced, and the problem of complete system failure caused by a single correction mode is avoided.

The application provides a surgery data dynamic registration method and system based on physical simulation and multi-modal constraint, and the method comprises the following steps: reconstructing a three-dimensional model of a target organ based on preoperative images and labeling feature points; predicting intraoperative deformation through physical simulation to obtain a prediction model; collecting surface point clouds at the beginning of surgery for rigid registration; constructing multi-modal constraint by fusing electromagnetic positioning and visual data in real time during surgery; driving model non-rigid deformation by using position dynamics method to realize dynamic registration. The application can compensate soft tissue deformation with high precision and physical reasonableness, has real-time response capability, does not need to implant markers, is suitable for various soft tissue surgery scenes, and improves the accuracy and safety of surgery navigation.

This utility model relates to the field of dental implant technology, and in particular to a high-precision guide plate for removable dental implant implantation, comprising a guide plate body, a positioning component, and an opening component; the upper end of the guide plate body is equipped with an opening component for preventing excessive drilling without repeated measurements, and the lower end of the guide plate body is equipped with a positioning component for rapid adsorption and alignment, preventing displacement of traditional guide plates due to soft tissue deformation. The positioning component includes patches, and two sets of patches are symmetrically arranged at the lower end of the guide plate body for pre-attaching to the patient's mouth. Multiple sets of neodymium magnets for use in patients with insufficient bone content or who fear invasive surgery are sequentially installed from left to right on the upper surface of the patches. A metal ring magnetically connected to the neodymium magnets is provided at the center of the lower surface of the guide plate body. This utility model provides a non-invasive fixation method by utilizing neodymium magnets, reducing the patient's fear and physical burden, and is also applicable to more types of cases.

This invention relates to the field of medical device automation technology, and in particular to an automatic ultrasound probe positioning method based on visual recognition. The method includes: acquiring macroscopic visual information containing a target body surface region; identifying at least one anatomical semantic region corresponding to the target body surface region based on the macroscopic visual information; controlling a robotic arm to move the ultrasound probe to an initial positioning position determined based on the anatomical semantic region; acquiring microscopic visual information of the contact area between the ultrasound probe and the body surface; extracting visual features reflecting the probe-body surface contact state based on the microscopic visual information; and generating control commands based on the difference between the visual features and the preset target state, and driving the robotic arm to adjust the ultrasound probe's pose. This invention employs a two-layer architecture combining macroscopic semantic coarse positioning and contact visual servo fine positioning. It does not rely on complex pre-calibration, can adapt to individual differences and soft tissue deformation, and can achieve adaptive adjustment after contact, thus achieving rapid, robust, and adaptive initial probe positioning.

This invention discloses a method, apparatus, storage medium, and device for simulating soft tissue deformation, belonging to the field of soft tissue deformation simulation technology. The method includes: firstly, performing positional correction on the surface vertices to be corrected in the initial 3D model based on geometric information to obtain a corrected 3D model; when the corrected 3D model undergoes deformation, calculating the Jacobian determinant of the volume element, and accordingly calculating the additional potential energy term and regularization force, mapping the regularization force to the equivalent internal force acting on each vertex of the volume element; finally, updating the corrected 3D model based on the equivalent internal force to obtain the final 3D model after deformation. This invention improves the propagation of boundary conditions and displacement fields by introducing positional correction based on geometric information, and introduces a volume constraint mechanism through the design of the additional potential energy term and regularization force to suppress the stability of the volume element deformation process, thereby achieving the synergy between geometric representation and numerical stability in the soft tissue deformation simulation process.

The application provides a training method, a soft tissue deformation estimation method, a device, equipment and a storage medium. The training method comprises: obtaining a training sample set, different samples in the training sample set comprising point clouds at different time points and velocity vectors of three-dimensional points in the point clouds; wherein, any sample is obtained based on depth estimation and optical flow estimation of four soft tissue images collected from two different directions at adjacent time points; and a preset neural network model is self-supervised trained by using the samples in the training sample set, to obtain a soft tissue deformation estimation model. In the embodiment, the soft tissue deformation estimation model aggregates semantic information and motion flow information, and improves the accuracy of soft tissue deformation estimation.

The invention provides a robot surgical navigation system and method based on soft tissue deformation model real-time registration, and relates to the technical field of medical robots, the system comprises an imaging device, a display device and a control device; the control device comprises a model management module used for acquiring a pre-constructed three-dimensional soft tissue deformation model associated with a target tissue; the feature extraction module is used for processing the real-time image and extracting surface contour features and deformation mechanical correlation features of the target tissue; the real-time registration module is used for performing real-time registration on the target tissue and the three-dimensional soft tissue deformation model; and the navigation generation module is used for fusing the registered three-dimensional soft tissue deformation model with a real-time image. According to the method, real deformation of the tissue in the operation can be adapted in real time through deformation driving of the three-dimensional soft tissue deformation model, high-precision registration of the three-dimensional soft tissue deformation model and the target tissue is achieved, and the registration relation can be kept stable and continuous when the tissue state or the imaging view changes.

The utility model discloses a cranio-maxillofacial positioning device for orthodontic imaging. The cranio-maxillofacial positioning device comprises a bottom plate; the two first vertical rods are arranged on the bottom plate in a spaced mode through a reciprocating motion mechanism, so that the two first vertical rods can move oppositely or away from each other; the lug fixing piece is connected with the first vertical rod through a rotating pair; the second vertical rod is arranged on the bottom plate; the face fixing assembly comprises a nose fixing piece and a forehead fixing piece which are connected with the second vertical rods through a telescopic mechanism, so that the nose fixing piece and the forehead fixing piece are located on the perpendicular bisector of the connecting line of the two first vertical rods and can move along the perpendicular bisector. According to the cranio-maxillofacial positioning device for orthodontic imaging, the head is fixed through the nose, the forehead and the ears of a patient, so that facial soft tissue deformation in the process of fixing the head of the patient is avoided, the CT imaging effect is guaranteed, and meanwhile the use requirements of people with different facial sizes can be met.

This invention provides a method for generating a three-dimensional model for predicting soft tissue morphology of the maxillofacial region after changes in oral occlusion. It relates to the field of three-dimensional modeling and includes: obtaining a postoperative jawbone model by acquiring preoperative three-dimensional data and an occlusion adjustment plan; performing rigid body transformation on the jawbone mesh to obtain a postoperative jawbone model; dividing the soft tissue into layers and calculating a thickness distribution map to determine the deformation transfer coefficient of each layer; calculating the deformation of each layer based on the differences in jawbone position and the transfer coefficient; applying muscle tension and gravity compensation to the chin soft tissue deformation to generate a correction amount; and finally reconstructing and rendering the postoperative soft tissue prediction model based on the deformation of each layer and the chin correction amount, achieving a visual effect that accurately predicts the soft tissue morphology after occlusion adjustment.

The invention relates to the field of medical image processing and surgical navigation, in particular to a nasal plastic surgery navigation system based on three-dimensional reconstruction, which comprises a data acquisition module, a manifold representation module, a transformation calculation module, an error optimization module and a navigation display module. A nose anatomical structure is regarded as a Riemannian manifold, a mixed transformation model containing global rigid transformation and local non-rigid transformation is constructed, accurate alignment of a virtual model and real-time collected data is achieved, anatomical feature points are extracted through multi-scale curvature analysis, an error metric function is constructed based on differential invariants to conduct self-adaptive optimization, and the real-time real-time analysis is achieved. The system has the advantages that the space positioning of millimeter-level precision is realized, the system can effectively treat the soft tissue deformation of the nose, the average error of the operation is reduced to 0.5-1.5 mm from the traditional 3-5mm, the precision of key aesthetic areas such as the nose tip and the nose wing is particularly improved by more than 60%, and the operation effect and the satisfaction degree of a patient are obviously improved.

The invention relates to the technical field of computer-aided surgical operations, and discloses an intraoperative multi-parameter analysis decision and auxiliary early warning system based on artificial intelligence, and the system employs a visual perception module to extract semantic masks and feature point displacement of an operation video stream; and a dynamic stiffness tensor field is inverted based on contact micro-deformation through an in-situ parameter calibration module. Wherein the neural network processor performs hardware-level optimization on tensor calculation, and is configured to convert a partial differential equation for controlling soft tissue deformation into a static calculation graph, and directly solve a global displacement vector meeting physical constraints by randomly sampling collocation points in a calculation domain. And the early warning decision module updates the space coordinates of the hidden structure, calculates the dynamic risk distance between the surgical instrument and the hidden structure and generates an early warning signal. According to the method, real-time physical solution of soft tissue deformation is realized through a heterogeneous computing architecture, and the real-time performance and accuracy of hidden structure navigation in minimally invasive surgery are improved.

Disclosed is a surgical robot resection navigation method based on multi-modal image registration. The method comprises: acquiring preoperative multi-modal medical images of a patient and reconstructing a three-dimensional model containing a lesion and a dangerous structure; acquiring real-time intraoperative images; using a first deep learning network to extract cross-modal invariant features from the preoperative and intraoperative images and establish an initial correspondence relationship; using a second deep learning network, based on the preoperative / intraoperative images and the initial correspondence relationship, and combining physical model constraints, to predict an initial non-rigid deformation field; tracking a surgical tool in real time, and using an incremental calculation strategy to update the non-rigid deformation field in real time; applying the updated deformation field to the preoperative three-dimensional model to generate a deformed model; mapping the tool position to the deformed model and generating navigation instructions. The application can accurately compensate for soft tissue deformation, effectively fuse multi-modal image information, and dynamically update navigation information in real time, significantly improving the accuracy and safety of robotic surgery.

The invention relates to the technical field of medical image analysis, and discloses an intelligent evaluation method and system for excision cleanliness in breast tumor minimally invasive rotary atherectomy, and the method comprises the steps: firstly obtaining preoperative and intraoperative ultrasonic images of a patient, matching a region of interest through a structural similarity index, and respectively intercepting a main image and a local patch; then, respectively extracting global features of the main image and texture features of local patches by using a deep neural network; performing spatial collaborative attention processing on the global features to establish spatial association between the preoperative image and the intraoperative image, and performing multi-instance pooling operation on the local features to aggregate key details; and the global and local features are adaptively fused through a gating network and then input into a classifier to output an evaluation result. The system further introduces a sample source weighting strategy and a man-machine cooperation closed-loop mechanism to optimize model training. According to the method, the problem of feature alignment caused by soft tissue deformation in an operation is effectively solved, and the objectivity and accuracy of excision cleanliness evaluation are remarkably improved.

The invention relates to the technical field of voice recognition, and discloses a voiceprint recognition identity verification method and system, and the method comprises the steps: collecting an original sound wave signal, and extracting a multi-dimensional acoustic feature set; constructing an elastic stress correlation model by combining the motion tremor frequency of the laryngeal muscles in the original sound wave signal, and generating a dynamic deformation track of the laryngeal organ; sending a random acoustic interference instruction to the user to trigger non-autonomous stress response of the laryngeal muscle, and synchronously collecting sound wave conduction phase offset; reversely analyzing sound channel soft tissue deformation amplitude according to the sound wave conduction phase offset, matching biomechanical transmission characteristics in the dynamic deformation track of the throat organ, and generating a dynamic physiological consistency coefficient; and when the dynamic physiological consistency coefficient and a preset physiological reference value meet an organ movement cooperative constraint condition, outputting an identity verification passing signal. According to the invention, the problem that voiceprint recognition identity verification cannot effectively defend high-fidelity recording playback can be solved.

The invention relates to the technical field of computer vision and biomechanical simulation, and discloses a personalized customization method and system for western-style clothes, which breaks through the limitation that motion deformation cannot be captured by traditional static measurement by constructing a dynamic volumetric model containing skeleton driving and soft tissue deformation, and improves the customization efficiency of the western-style clothes. The muscle expansion effect during limb movement can be accurately simulated, the proportion of fabric stretching to body compression is scientifically distributed on the basis of a mechanical balance principle in combination with a unique two-way rigidity displacement complementary mechanism, the accurate compensation amount which meets the movement requirement and is not excessively loose is calculated, and in addition, the energy-minimization-based grid deformation technology is utilized, so that the energy consumption is reduced. When the dynamic allowance is invisibly injected into the model, the contour line of the original design and the sewing completeness are kept, so that the contradiction that slimming and comfort are difficult to achieve at the same time in the traditional customization is solved, the wearing experience of static fit and non-compression in movement is realized, and the dependence on the tailoring experience is greatly reduced.

This invention relates to the field of image data processing technology and discloses an intelligent detection method and system for dentofacial deformities based on multimodal data. The method includes: acquiring three-dimensional skeletal data of the first modality and two-dimensional facial data of the second modality of the target object; extracting a set of skeletal feature points from the three-dimensional skeletal data; calculating a spatial mapping matrix and mapping the set of skeletal feature points to a two-dimensional plane according to the spatial mapping matrix to generate an anchor point mask matrix; obtaining an aligned facial feature tensor; performing planar fitting calculation on the target tooth coordinate set to obtain an occlusal plane normal vector; generating soft tissue deformation parameters; obtaining a fusion feature vector; and inputting the fusion feature vector into a pre-trained deformity classification network to output a deformity category label. This invention improves the accuracy, intelligence, and versatility of dentofacial deformity detection and achieves efficient identification of deformity categories.