411 results about "Bone structure" patented technology

Various embodiments of implant systems and related apparatus, and methods of operating the same are described herein. In various embodiments, an intermedullary implant for interfacing with a bone structure includes a web structure, including a space truss, configured to interface with human bone tissue. The space truss includes two or more planar truss units having a plurality of struts joined at nodes. Implants are optimized for the expected stress applied at the bone structure site.

The invention relates to the technical field of osteoporosis diagnosis, and discloses an osteoporosis diagnosis method based on image recognition. The method comprises the following steps: acquiring bone density image data of a target object and bone structure image data of a target area based on medical imaging equipment, and determining a bone trabecula distribution condition of the target area according to the bone structure image data; constructing a three-dimensional bone mineral density model of the target object according to the bone mineral density image data, and determining an image analysis strategy by combining the three-dimensional bone mineral density model and the bone trabecula distribution condition; and an image analysis module acquires bone structure feature data of the target area according to the strategy, and identifies the bone density grade and the osteoporosis degree of the target area according to the feature data to obtain diagnosis data. According to the method, related data of the bone mineral density and the bone structure are integrated, comprehensive analysis is carried out in combination with the image recognition technology, an efficient and reliable new mode is provided for clinical diagnosis, the accuracy and objectivity of osteoporosis diagnosis are improved, and misdiagnosis and missed diagnosis are reduced.

The invention provides an osteoporosis prediction method and system based on a centrum CT image, and the method comprises the steps: obtaining a patient centrum CT image, and carrying out the preprocessing of the image, and obtaining standardized three-dimensional voxel data; performing spatial resampling on the original data to a uniform resolution; constructing a hierarchical feature extraction network for centrum bone structure perception, and designing a non-uniform sampling mechanism for centrum density distribution; constructing an intervertebral biomechanical conduction diagram network; designing an osteoporosis specific loss function; and outputting a grading prediction result containing confidence, generating probability distribution of each grade through a softmax function, and generating a visual thermodynamic diagram of the lesion area. Through time sequence consistency constraint, the system can analyze image changes of the same patient at different time points and evaluate the treatment effect and the disease progress. The dynamic monitoring ability provides a powerful tool for long-term management of chronic osteoporosis, and is helpful for timely adjustment of treatment schemes and improvement of prognosis of patients.

The invention relates to the technical field of artificial intelligence, and discloses a teenager scoliosis intelligent quantitative evaluation system fused with multi-modal imaging. The system comprises a multi-modal data management module, a cross-modal registration fusion module, a dynamic quantitative analysis module, a risk prediction module, a three-dimensional reconstruction module, a report generation module and a system management module, and by setting a multi-modal registration verification mechanism, accurate matching of a bony structure and soft tissue is ensured. Key parameter calculation errors caused by registration failure are reduced, the three-dimensional reconstruction precision is greatly improved compared with traditional single-mode evaluation, a dynamic respiration compensation module is introduced, in the spine deformation parameter quantification stage, spine physiologic changes in a respiration movement period are automatically captured, measured values are corrected based on an individualized dynamic model, and the accuracy of three-dimensional reconstruction is improved. Pathological progression and physiological fluctuation are distinguished, the misjudgment risk caused by neglecting breathing phase change in traditional static measurement is avoided, and the reliability of scoliosis progression risk assessment is improved.

The invention relates to the technical field of medical informatics, in particular to a construction method of an osteoporotic fracture risk prediction model. The method comprises the following steps: acquiring an included angle between a foot and the ground, a step speed and a CT image of a target person in a monitoring process; dividing pixel points in the CT image into a plurality of bone tissue areas; according to the shape distribution characteristics of the edge lines in the bone tissue area, bone characteristic values of the bone structure are obtained; obtaining a posture control factor of each gait according to the included angles between the left and right feet of the target person in each gait and the ground; determining an abnormal posture index of each gait in combination with the posture control factor and the corresponding step speed; obtaining a control disorder coefficient of each time period according to the numerical distribution characteristics and the change characteristics of all the posture control factors in each time period; and determining an osteoporosis evaluation value by integrating the bone characteristic value and the disorder control coefficient of the skeleton structure. The accuracy of the bone comprehensive evaluation result of the target person is improved.

A computer-implemented method of pre-operatively evaluating bone structure for use of a bone graft in a surgical procedure can comprise generating a three-dimensional bone model of a bone of a patient for output in a video display unit, determining a volume of interest (VOI) on the three-dimensional bone model where a bone defect exists, adding an internal bone property for bone matter of the bone structure to the three-dimensional bone model at the volume of interest, analyzing the internal bone property in the volume of interest relative to a treatment for a bone defect, and outputting indicia on the video display unit that indicates utility of a bone graft for the treatment. A surgical planning system can comprise memory having instructions for implementing the computer-implemented method.

The invention relates to the technical field of model construction, in particular to a method for creating an image recognition model based on clinical disease data integration. The method comprises the following steps: acquiring a medical clinical orthopedic image set; the bone density and the bone form of the medical clinical orthopedic image set are extracted, bone structure division is carried out on the medical clinical orthopedic image set, bone structure division images are generated, and the bone structure division images comprise large bone structure images and small bone structure images; analyzing the bone layer thickness of the big bone structure image and performing physical layer thickness compensation reconstruction on the big bone structure image to generate big bone middle virtual slice data; and performing detail guide reconstruction on the small bone structure image to generate small bone fracture texture reconstruction data. According to the invention, through image resolution enhancement, multi-modal data integration, motion simulation and optimization model training, the accuracy of skeleton image dynamic identification is improved.

A vehicle is provided that includes an imaging device located on the vehicle and oriented to capture images, memory storing one or more pet profiles, and a controller processing the captured images to detect a pet and determining at least one of an estimated pose of the pet and a gait of the pet, wherein the processor determines a bone structure of the pet from the at least one estimated pose and gait and compares the bone structure to the one or more pet profiles to detect an authorized pet, the controller controlling one or more vehicle related features based on the detected authorized pet.

An orthopedic staple system and orthopedic staple are configured to facilitate bone healing through dynamic and adjustable compression. The system comprises the orthopedic staple having a bridge portion and one or more legs that anchor into bone structure. The bridge portion is configurable to include compression features, comprising a pre-compressed chevron, an “S” shaped deformable path, or other suitable geometries to enable active post-operative compression. The staple can be configured to accommodate a single screw or multiple screws, which interact with the bridge to apply targeted compressive forces. Screws can be seated in either fixed or translatable pockets within the bridge, facilitating variable angle adjustments and bone remodeling. This system is optimized for minimally invasive surgical applications, promoting healing and integration, and enhancing overall patient outcomes.

The invention relates to an oral implant positioning method and system based on deep learning. According to the method, three-dimensional point cloud data of an oral cavity is obtained and preprocessed, and a pre-trained three-dimensional deep learning segmentation model is utilized to automatically and accurately segment tooth, gingiva and alveolar bone structures. And based on the segmentation result, extracting key form and spatial relationship characteristics of the alveolar bone, and matching with an implant database to primarily select a candidate scheme. By integrating geometric constraint verification and biomechanical simulation, the candidate schemes are optimized and decided, and the optimal implant implantation position and posture meeting the safety and biomechanical requirements are calculated. And finally, automatically generating digital operation guide plate data completely matched with the gingival form of the patient according to the optimal scheme. According to the method, automation and intellectualization of the whole process from data collection to surgical guide plate generation are achieved, the defects that a traditional method depends on artificial experience, is high in subjectivity and low in efficiency are effectively overcome, and the precision, efficiency and reliability of implantation surgical planning are remarkably improved.

The invention discloses a self-adaptive bionic cancellous bone defect prosthesis and a design method thereof, and belongs to the technical field of medical prostheses, the prosthesis is composed of biological interface gradient microporous structure parts and a main body bionic truss supporting structure part, the biological interface gradient microporous structure parts are arranged at the two ends of the main body bionic truss supporting structure part, and the main body bionic truss supporting structure part is arranged on the main body bionic truss supporting structure part. The method is mainly used for reconstructing bone defects, bionically designing a truss part of a main body with consistent arrangement direction and form of human body bone trabecula through an established linear relation between CT gray value and bone density-elasticity modulus, adaptively matching mechanical conduction of a bone structure, reducing stress shielding effect, and improving bone defect reconstruction efficiency. Meanwhile, various complex mechanical working condition requirements of the prosthesis are met, the prosthesis failure risk is reduced, and the service life of the prosthesis is prolonged.

The invention relates to an occlusion guide plate designing and manufacturing method based on dentition mechanical analysis, which comprises the following steps: S1, acquiring oral cavity image data of a patient, and constructing a three-dimensional digital model comprising a dental crown, a tooth root and an alveolar bone structure; s2, calculating an overall mechanical reference point of a tooth root structure of an anterior maxillary tooth area; s3, acquiring an incisal edge midpoint of each incisal tooth and a cusp point of each canine tooth in the maxillary anterior tooth area, solving a geometric center, and connecting the geometric center with an overall mechanical reference point to form a dentition direction vector; s4, calculating the displacement relationship between the target dentition arrangement and the initial dentition arrangement in the lip-tongue direction; s5, calculating an included angle between the occlusal force direction of the maxillary anterior tooth area and the dentition direction vector; s6, determining key morphological parameters of the occlusion guide plate according to the calculation result of the included angle in S5; and S7, manufacturing the occlusion guide plate. Compared with the prior art, the method has the advantages of precise mechanical adaptation, quantitative treatment prediction, personalized design and the like.

The invention relates to a virtual human automatic binding method and device, a storage medium and electronic equipment, and relates to the technical field of computer animation, and the method comprises the steps: obtaining a target geometric shape of a three-dimensional human body model of a target virtual human; according to the target geometrical morphology, determining an adaptive skeleton structure corresponding to the target virtual human; based on the trained target machine learning model, determining at least one target skin weight corresponding to each model vertex in the three-dimensional human body model; determining at least one key part based on a target human body action of human body model distortion of a historical virtual human of the target role type and at least one corresponding target vertex; target skin weights of model vertexes in key parts of the three-dimensional human body model are verified, corresponding verified skin weights are obtained, and binding of the model vertexes and target bones is carried out based on the verified skin weights and the remaining skin weights. The method and the device have the effect of improving the authenticity of the action of the bound virtual human.

The invention discloses a hip replacement lower limb equal-length control system and method based on individualized three-dimensional modeling. The hip replacement lower limb equal-length control system comprises a data preprocessing module, a medical image processing module, a dynamic implantation simulation module, a biomechanical analysis module, a guide plate generation module and a postoperative evaluation module. The method comprises the following steps: acquiring bilateral lower limb CT data and carrying out multi-modal registration; segmenting a skeleton structure by using a deep learning model, and constructing a three-dimensional model; reconstructing a complete sphere through affected side femoral head multi-plane fitting, and determining a target femoral head center in combination with uninjured side mirror image data; dynamically adjusting the space posture of the prosthesis to enable the center of the prosthesis head to coincide with the center of the target; performing finite element analysis to optimize stress distribution; and generating a 3D printing file of the individualized osteotomy guide plate and the positioning pointer. According to the method, preoperative accurate planning, intraoperative real-time control and postoperative quantitative evaluation are achieved, the operation precision is effectively improved, and complications of unequal lengths of lower limbs are avoided.

A joint socket (2) for a joint prosthesis (1) that can be fixed in a bone structure (6) and has a socket insert (3) for receiving at least a partially spherical joint body, wherein the joint socket (2) has at least one projection (7) facing the bone structure (6) and designed to engage in a groove-shaped recess (9) of the bone structure (6) that is radially spaced from a recess (8) for the socket insert (3) in the bone structure (6), which surrounds the socket insert (3) circumferentially, in particular concentrically, and wherein the projection (7) has at least a partially convex outer surface (10) and a concave inner surface (11) so that the projection (7) can be inserted into the groove-shaped recess (9) in a form-fitting manner with the outer surface (10) and the inner surface (11), characterized in thatthat the socket (2) has a retaining frame (14) with a passage width (D) that is variable, in particular against an elastic restoring force, and is less than the great circle diameter of the socket insert (3), and two projections (7) which are spaced apart from each other in the circumferential direction within an annular area limited by the outer contour and by the inner contour, and the retaining frame (14) in turn has two projections (7') which are connected flush with the two projections (7) of the socket (2).

The invention relates to the technical field of bone biomechanical simulation, and discloses a bone biomechanical modeling method and system based on a multi-modal image, and the method comprises the steps: S1, collecting a CT image and an MRI image of a to-be-detected bone structure, and generating a multi-modal image; s2, adopting a depth variation inference algorithm to extract common features of the multi-modal images, adopting a generative adversarial network algorithm to optimize the common features, and performing information fusion on the multi-modal images to generate comprehensive image data; s3, reconstructing a three-dimensional bone structure model based on the comprehensive image data; s4, simulating mechanical property parameters of the three-dimensional bone structure model under different external loads and physiological states by adopting a nonlinear finite element method based on the three-dimensional bone structure model, and outputting mechanical properties of bone tissues; and S5, based on the three-dimensional bone structure model and the mechanical characteristics of the bone tissue, generating a personalized bone biomechanical model by using a depth variation inference algorithm. According to the method, an accurate personalized bone biomechanical modeling scheme can be provided.

The invention discloses a personalized orthopedic insole manufacturing method and device, equipment and a storage medium. The method comprises the steps that foot shape geometric data of a patient and a foot reference model of a flatfoot are obtained; constructing a scaling function based on the foot shape geometric data and the foot reference model, and scaling reference data in the foot reference model according to the scaling function to construct a foot complex finite element model of the patient; constructing an initial orthopedic insole model based on foot shape geometric data, importing the foot complex finite element model into the initial orthopedic insole model, and determining a final orthopedic insole finite element model in combination with model parameters input by a user; and manufacturing the orthopedic insole according to the final orthopedic insole finite element model. According to the method, the ankle internal skeleton structure of the patient can be obtained by scaling the foot reference model of the flatfoot, and then the orthopedic insole model is constructed, so that the acquisition of a large amount of foot MRI data of the patient is not needed, and the manufacturing of the orthopedic insole is more convenient and rapid.

The invention relates to a spine bone structure and bone mineral density automatic measurement method based on a CT image. The method comprises the following steps: performing CT scanning on a phantom with known bone mineral density to obtain a real bone mineral density calculation formula; all CT images in the DICOM format are read, DICOM analysis is carried out, and three-dimensional CT value data and other main information of all the images are obtained; performing outer contour segmentation on the whole spine in the CT image by using a deep learning network to obtain an outer contour of each vertebral body in the image; the method comprises the following steps: carrying out preliminary segmentation on cortical bones and cancellous bones by adopting a dynamic threshold method aiming at each vertebral body, selecting a preliminarily segmented cancellous bone region, using a maximum connected domain algorithm in a three-dimensional direction, retaining a maximum connected region, and further measuring the bone mineral density, namely calculating overall topology parameters, the bone mineral density and the bone mineral content of the current vertebral body; calculating the rubbing parameters, the bone mineral density and the bone mineral content of the current vertebral cortical bone and cancellous bone; and measuring the content of the cross section of the cone.

The invention relates to a fixation element (1) for the osteosynthesis of several bones or bone regions (2, 3) that, for example, adjoin one another along a fracture (5). For this purpose, the fixation element (1) has at least one hollow cylindrical projection that can be inserted into a groove-shaped recess in the bone structure (4) extending over both bone regions (2, 3). Because the holding force of the fixation element (1) acts parallel to the surface of the bone structure due to its ring shape, the bone regions (2, 3) can be fixed against each other with the desired compression even without the use of an osteosynthesis plate, requiring only a shallow depth in the bone structure (4).

In various embodiments, an implant for interfacing with a bone structure includes a web structure including a space truss. The space truss may have a plurality of struts joined at nodes and the web structure is configured to interface with human bone tissue. At least some struts may form an irregular pattern in the web structure. The space truss may include two or more planar truss units having a plurality of struts joined at nodes.

The invention discloses a live pig bone segmentation method based on a semi-supervised multi-scale diffusion model, which combines high-resolution image data with a deep learning network to form a method capable of accurately segmenting live pig bones on different spatial scales. The method comprises the following steps: firstly, acquiring image data of a skeleton in a live pig through CT scanning; after preprocessing, a denoising diffusion probability model is used for analysis. In order to improve the labeling efficiency, a semi-supervised learning strategy and a multi-scale feature extraction method are adopted, a model can be trained only through a small amount of labeling data, skeleton features under different spatial scales are analyzed, global information of an image is fully covered, local information is highlighted, the segmentation capability of a complex skeleton form is improved, and the method has the advantages of being high in practicability and easy to popularize. And precise segmentation of the skeleton structure of each part is realized. The technology provides a powerful tool for the research on the bones of the live pigs, and has a wide application prospect.

The invention is suitable for the field of meat processing and production, and provides an intelligent recognition method and system for the three-dimensional contour of boned meat based on image recognition, and the method comprises the steps: carrying out the multi-modal image collection of frozen boned meat, and capturing a surface crack pattern; analyzing the crack pattern to construct a topological network model; reconstructing a bone-meat three-dimensional holographic model based on the topological network model, and marking joint, marrow cavity and bone mineral density abnormal areas; identifying potential skeleton weak points; generating a double-path cutting guide line; cooperative operation and visual presentation of the guide lines are controlled through dynamic compensation. Precise recognition and intelligent cutting guide of the internal skeleton structure of the boned meat are achieved, the segmentation precision and efficiency are improved, and the method is suitable for the field of meat processing and the like.

The invention relates to the field of furniture control, and discloses an intelligent massage armchair control method based on posture recognition, comprising a multi-modal sensing fusion module which collects vision, pressure and millimeter-wave radar data through a sensor, constructs a three-dimensional body contour value of a user, and sends the three-dimensional body contour value to the multi-modal sensing fusion module; data are transmitted to an individual feature recording module based on the collected vision, pressure and millimeter wave radar data; and the individual feature analysis module is used for receiving the information acquired by the multi-modal sensing fusion module, judging the body shape of the user by using a K-means clustering algorithm according to the information, and then selecting a preset scheme according to the body shape information of the user to carry out matching judgment on the sitting posture of the current user. According to the invention, data of the infrared camera, the pressure sensor and the millimeter wave radar are integrated through the multi-modal sensing fusion module, multi-dimensional sensing of a visual contour, pressure distribution and a skeleton structure is realized, and the problem of key feature point extraction deviation caused by body type difference of a single camera is effectively solved.

The invention discloses a three-dimensional CBCT synthetic CT image model fusing feature enhancement and bone structure constraint and a method, and relates to the technical field of medical information. The model fuses a medical image generator of Resnet and a medical image generator of VIT, the Resnet is used for extracting local features reflecting image structure details, and the ViT is used for capturing global features reflecting image long-range dependency; global and local features are fused through a compression channel, so that the network can pay attention to local details and capture wide context information at the same time; in addition, according to the model FEB-CycleGAN, a bone profile mutual information loss function is introduced to constrain the structural similarity between the original CBCT and the synthetic CBCT, so that the synthetic CT has a better structure retention characteristic. According to the method, the effectiveness and design rationality of the model are comprehensively verified through experiments such as image quality evaluation, ablation, dose comparison and sensitivity analysis.

The invention relates to the technical field of medical implants, in particular to a 4D printing-based porous Niti alloy bionic bone gradient structure construction method, which comprises the steps of patient bone data acquisition, bionic gradient model design, NiTi powder preparation, 4D printing, thermal treatment activation of memory effect, surface functionalization treatment and mechanical / biological performance test. The method is characterized by comprising the following preparation steps: accurately acquiring bone structure data through CT / MRI, combining Mimics pretreatment and UG / NX modeling, designing aperture and porosity for differentiation of cortical bone (low porosity of 30%-40%) and cancellous bone (high porosity of 50%-70%), simulating typical load working conditions through ANSYS, enabling the elastic modulus (3-15 GPa) and compressive strength (80-200 MPa) to be close to natural bone, and finally obtaining the bone structure data through the CT / MRI, the pore diameter and porosity of the cortical bone (low porosity of 30%-40%) and the porosity of the cancellous bone (high porosity of 50%-70%). According to the design, the elastic modulus difference between the implant and the host bone is remarkably reduced, the bone resorption problem caused by stress shielding is avoided, meanwhile, continuous porosity transition is achieved through the power gradual change technology, and the structural stability under the complex load is improved.

The invention relates to a bone plate and a bone plate system, a through hole is formed in the bone plate, a plurality of clamping units extend from the hole wall surface of the hole to the center of the hole, and the multiple clamping units are arranged at intervals in the circumferential direction of the hole; one side, far away from the hole wall, of each clamping unit is provided with an end part, and each end part is provided with at least two clamping parts which are arranged at intervals; wherein the clamping part of at least one clamping unit is used for being clamped with the thread groove of the fixing piece. When the bone lamella and the bone lamella system are used for fixing and repairing a fractured bone structure, the bone lamella is firstly abutted against the bone structure, and then the fixing piece is screwed, so that the locking rod part of the fixing piece penetrates through the hole and is fixedly connected with the bone structure. Meanwhile, in the screwing process, the at least two clamping parts on each clamping unit can be clamped in the threaded grooves of the fixing pieces, the clamping units and the threaded grooves of the fixing pieces are locked stably, the situation of locking failure is not prone to occurring, the rehabilitation treatment effect of the bone structure after fracture is good, and the period is short.

An alveolar bone structure three-dimensional key point positioning method based on deep learning and rule constraint comprises the following steps: acquiring a maxillofacial region CBCT image data set, cutting CBCT data, manually marking the cut CBCT data, and dividing the CBCT data into a training set, a test set and a verification set; the data set is preprocessed, and data enhancement is carried out in a random intensity shifting and scaling mode; constructing an alveolar bone coordinate network model, wherein the network architecture mainly comprises an appearance branch and a spatial configuration branch; adopting the training set to train the alveolar bone coordinate network model, obtaining each parameter of the network model, and obtaining a trained alveolar bone coordinate network model; and testing the trained alveolar bone coordinate network model by adopting a test data set, and evaluating a test result. The method aims at solving the problems of anatomy prior deficiency, insufficient long-range dependence modeling and weak small sample generalization ability in the prior art, and high-precision alveolar bone key point positioning is realized.

The present disclosure belongs to the field of biomedical materials, and specifically relates to a medical tissue adhesive, and a preparation method therefor and the use thereof, and a composition and a kit for preparing the medical tissue adhesive. According to the medical tissue adhesive provided by the present disclosure, a three-dimensional net-shaped gel skeleton structure is formed by means of the mutual crosslinking of a polyethylene glycol derivative L a polyethylene glycol derivative H and trilysine. Moreover, the gel skeleton has a crosslinked network density and intermolecular interaction that can be improved, and accordingly has an improved structure bonding strength and mechanical strength. In addition, the medical tissue adhesive has the advantages of a reduced swelling rate, a high biocompatibility and biodegradability, can effectively adhere to tissues and seal wounds, reduces compression on tissues such as nerves, realizes wound sealing, tissue repair and blocking of postoperative liquids such as blood and tissue fluid, and has great clinical significance and wide application prospects.

A hardenable (e.g. dental) compositions is described comprising an encapsulated material. The encapsulated material comprises a basic core material and an inorganic shell material having certain viscosity criteria. Also described are dispensing devices and kits are described comprising a hardenable (e.g. dental) composition comprising a liquid material and an encapsulated material wherein the encapsulated material comprises a basic core material and an inorganic shell material comprising a metal oxide surrounding the core. The dispensing devices and kits can facilitate the methods of applying the hardenable composition. The hardenable or hardened (e.g. cured) composition can provide various technical effects such as a delayed release of a basic core material, a delayed increase in basicity, promoting remineralization of a tooth or bone structure, and increasing the average alkaline phosphatase (ALP) activity of pulp cells. In some embodiments, the composition is a dental (e.g. sealant) composition for application to a tooth structure.

The invention discloses an engineering construction composite artificial bone based on architectural engineering and a manufacturing method thereof.The engineering construction composite artificial bone comprises a bioactive material and a mechanical supporting scaffold, the bioactive material serves as a main body, the mechanical supporting scaffold is contained in the bioactive material, and the bioactive material and the mechanical supporting scaffold are tightly combined to form an artificial bone tissue complex; the mechanical support bracket can provide mechanical support for the artificial bone tissue complex so as to meet the load requirement in the bone repair process. The artificial bone tissue complex can further achieve one or more functions through surface modification and / or a carrying structure used for carrying a bone growth promoting material release system and / or a drug release system arranged in the artificial bone tissue complex so as to meet the clinical requirements of anti-inflammation, anti-infection, anti-tumor, anti-osteoporosis, bone integration promotion and the like. The bone integration performance and mechanical performance of the material are considered, and a new scheme is provided for large-area bone defect repair, bone structure filling and supporting and parts needing long-term load bearing.