14 results about "Spinal model" patented technology

The application relates to a spine dynamic diagnosis and reduction guiding system and method based on an intelligent 3D palpation film, and belongs to the technical field of medical diagnosis and treatment. The system mainly comprises a flexible palpation film, a data processing and intelligent diagnosis module and an interactive reduction guiding module. The flexible palpation film covers the C1 to S1 region of the spine, is internally provided with a high-density pressure sensor array, and is used for collecting palpation pressure data in real time; the data processing module receives data and constructs a real-time 3D spine model through an AI algorithm, and identifies abnormalities such as vertebral body deviation and rotation; and the guiding module displays reduction guiding information through a spine reduction program interactive interface, and dynamically calibrates an operation path according to real-time feedback data of the palpation film, so that closed-loop control is formed. The application solves the problems that traditional spine manual treatment relies on experience, cannot be quantified and lacks real-time guidance, and realizes the precision, visualization and standardization of diagnosis and reduction.

The invention relates to the technical field of operation planning navigation systems, in particular to a spinal operation intelligent planning and intraoperative navigation system which comprises a data input module, a spinal model building module, an operation planning module, a dynamic deformation tracking module, a navigation control module and a data output module. A spine is represented as a differential manifold through a manifold parameterization unit, a local coordinate construction unit is utilized to establish a multi-local coordinate system, a deformation field calculation unit calculates a spine deformation field based on optical mark point displacement, a deformation prediction unit generates a prediction deformation field, and a compensation parameter generation unit generates navigation compensation parameters. The system also comprises an operation path mathematical optimization algorithm and a scheme sharing mechanism based on a two-dimensional code, and is provided with a fault-tolerant processing module to ensure the stability of the system. According to the system, the navigation precision is improved from the traditional millimeter level to the submillimeter level, the accuracy and safety of spinal surgery are remarkably improved, and the system has wide clinical application prospects.

The invention discloses a multi-modal fusion spinal region puncture positioning method and system based on deep learning. The method comprises the following steps: acquiring a spine image containing a puncture part, and inputting the spine image into a trained image segmentation model to obtain an image segmentation result; inputting an image segmentation result into a trained target recognition model for target recognition to obtain target region information; obtaining two-dimensional slice data based on the spine image, converting each pixel point of the two-dimensional slice data into a three-dimensional voxel, and extracting a surface geometric model to obtain a three-dimensional reconstruction model; performing information enhancement and alignment on the model and a real-time ultrasonic sequence through a specific structure to generate a high-fidelity enhanced real-time spine model image; based on the real-time model, the optimal puncture path, angle and depth are intelligently recommended in combination with a preset puncture type. The method can accurately provide a puncture point and recommend a puncture path, improves the success rate of intraspinal puncture of a complex patient, and reduces the probability of occurrence of adverse events.

The application discloses a spine 3D model reconstruction method based on a multi-scale symmetric architecture learning, comprising the following steps: rotating a spine X-ray image to a set angle; repeating the rotated X-ray image D times and splicing to form a high-channel 3D volume; inputting the high-channel 3D volume into a generative adversarial network to obtain a 3D prediction model of the spine; calculating the standard deviation of different generated images of the 3D prediction model to evaluate the quality difference of the generated images, and selecting a global optimization or local optimization 3D prediction model of the generator based on the quality difference; and the 3D prediction model obtains a reconstruction model of the spine by minimizing the loss of the generator. The application solves the problem that the existing method for reconstructing the three-dimensional structure of the spine in the X-ray excessively depends on prior information, thereby reducing the fidelity.

The invention relates to a scoliosis simulation teaching aid and an operation method. The simulation teaching aid comprises a spine model, a gooseneck rod and an outer cover box. The spine model comprises a vertebra model; the gooseneck rod penetrates through each vertebra model according to a spine physiological curve and is fixedly connected with the vertebra models; the outer cover box comprises a cervical vertebra box body, a thoracic vertebra box body, a lumbar vertebra box body and a sacrum box body; each box body comprises a transparent corrugated pipe, a top shell and a bottom shell; the spine model passes through the middle of the top shell and the middle of the bottom shell; the part, penetrating through the top shell and the bottom shell, of the gooseneck rod is fixedly connected with the top shell and the bottom shell respectively; the lower end of the transparent corrugated pipe is connected with the bottom shell edge, and the upper end is detachably connected with the top shell edge corresponding to the bottom shell edge. The vertebra models can be accurately controlled, and normal displacement deflection is carried out; the transparent corrugated pipe can reflect the trend of in-vitro abnormity, and is beneficial for medical students to establish clearer cognition on scoliosis. The operation method is simple and convenient to operate, and can simulate more types of scoliosis conditions.

The invention relates to a spine three-dimensional imaging and lateral bending angle calculation method based on an AI vision algorithm, and belongs to the technical field of spine form detection. The method comprises the following steps: acquiring back image data, and positioning a plurality of spine key points from a back image by inputting a constructed key point detection model; the spine model is expressed as an energy balance system, then the spine key points are mapped to the spine model, and an energy balance equation of gravity and elastic potential energy is established; iteratively optimizing the energy balance equation by adopting an LM algorithm; three-dimensional coordinates of the gravity center of each cone are calculated through rotation matrix merging; and calculating a Cobb angle according to the obtained three-dimensional coordinates of the gravity center of each cone body. The spine key point is accurately detected through the back image, high-precision reconstruction from two dimensions to three dimensions is realized in combination with the energy balance principle and the optimization algorithm, the clinical Cobb angle is automatically calculated, and the problems of radiation risk, high cost and subjective error of traditional detection are solved.

The invention provides a high-intelligence spine adjuvant therapy system for spine surgery, which belongs to the technical field of spine adjuvant therapy and comprises a lying plate structure, and a two-end tension device, a vertebral column bottom pushing device, a vertebral column real-time scanning detector and a sensing unit are arranged on the lying plate structure. A three-dimensional model is constructed for the spine of a patient, then force applied in real time in the auxiliary treatment process is collected in real time, a scanner is used for scanning the real-time state of the spine, then the real-time state and the three-dimensional model are fused to form a three-dimensional dynamic spine model, and then the spine is determined according to optimal treatment scheme data of a hospital. And real-time optimal auxiliary treatment force can be applied to the three-dimensional dynamic spine model, so that the auxiliary treatment effect is better, and the extrusion position is controlled more accurately.

This invention provides a method and system for testing the positioning accuracy of a surgical robot system, comprising the following steps: Model fixing step: fixing a spinal model with a channel tube on a test table and importing the scanning data of the spinal model with the channel tube; Surgical planning step: performing surgical planning based on the scanning data of the spinal model with the channel tube to obtain the implantation trajectory; Calculation value acquisition step: according to the implantation trajectory, controlling the robotic arm to move the first test column at the end of the robotic arm to the corresponding position of the second test column in the channel tube, thereby obtaining the calculated value between the first test column and the second test column; Accuracy acquisition step: obtaining the positioning accuracy of the surgical robot system based on the calculated value. This invention no longer uses the single-layer calibration plate or the quantification tooling in the standard, but uses a spinal model instead of tooling, thus resulting in lower cost and higher reliability and accuracy.

A bionic spinal model, including: a base body; an enclosure; a bionic spinal body disposed on the base body and being radiopaque; a simulated muscle layer surrounding the bionic spinal body; and a simulated skin layer overlaying the simulated muscle layer. The bionic spinal body comprises an internal cavity and a bionic nerve body; the bionic nerve body is disposed in the internal cavity; and the bionic nerve body comprises a proximity-sensitive warning mechanism. The model successfully simulates key aspects of real spinal surgery, including X-ray imaging, internal anatomical structures, a surgical fluid environment, and neural proximity feedback, providing a realistic training platform to improve endoscopic spinal surgical skills.

The invention provides a training method and device of a lightweight multi-mode spine model with centrum segment perception, a terminal, a medium and an analysis method. According to the invention, low-cost localization deployment is realized by constructing the lightweight multi-mode architecture. Meanwhile, through specific data input and a progressive three-stage training strategy, a lightweight model with the spine specialized ability is constructed and trained, and then a more accurate spine image analysis result is obtained.

The present application relates to the technical field of spine image recognition, and particularly relates to a spine model recognition and positioning method, which determines the vertebra sub-contours of each vertebra in the first model image of the target object in a first pose state, and determines whether the recognition reliability of the vertebra sub-contours meets the standard according to the position distribution state of the contour recognition line; the recognition reference contour of the vertebra sub-contour whose recognition reliability does not meet the standard is determined, the pose change data is determined based on the coordinate change of the edge calibration point of the recognition reference contour, the pose change reference coordinates of the edge calibration point in the second model image are calculated, and whether the model image is effective is determined based on the actual coordinate difference of the edge calibration point in the second model image and the pose change reference coordinates, thereby, the verification scheme based on the associated image data and the model effectiveness determination means are provided for the vertebra sub-contours whose recognition reliability does not meet the standard, and the spine model recognition and positioning accuracy and effectiveness are improved.

The application discloses a vertebroplasty optimization method based on a patient-specific finite element model and related devices, wherein the method comprises the following steps: constructing a patient-specific three-dimensional spine model according to a vertebral bone structure and a vertebral soft tissue structure; discretizing the patient-specific three-dimensional spine model into a tetrahedral finite element grid, assigning bone material properties to each finite element unit according to pixel values of a CT scan image, and assigning soft tissue material properties to intervertebral disc and ligament soft tissue structures; determining an optimal bone cement injection path and an optimal bone cement injection amount of the tetrahedral finite element grid; simulating vertebroplasty in the tetrahedral finite element grid, predicting stress distribution of a vertebra after the vertebroplasty, rigidity of the vertebra, and stress changes of adjacent vertebrae, and presenting simulation results of the simulated vertebroplasty in a three-dimensional visual form. The application realizes individualized optimization and preoperative simulation of vertebroplasty by constructing a patient-specific finite element model, and provides an efficient auxiliary reference surgical plan for a surgeon.

This invention discloses a percutaneous spinal puncture positioning system based on robotic ultrasound imaging, comprising: a collaborative robot, a medical ultrasound machine, a motion control module, and an image processing system. The image processing system further includes a CT image-based three-dimensional spinal reconstruction module, an ultrasound data processing module, and a registration and fusion module. This invention can reconstruct a CT three-dimensional spinal model from thin-slice CT images, obtain an ultrasound three-dimensional spinal model through ultrasound image processing, and register and fuse the two models into a unified coordinate system. Using this invention, a "three-dimensional positioning + two-dimensional monitoring" navigation puncture positioning mode can be achieved, fully leveraging the advantages of robotic ultrasound imaging, minimizing labor costs and reliance on experience, and safely and reliably completing percutaneous spinal puncture positioning. This invention requires minimal consumables, provides intuitive results, and is radiation-free, making it suitable for widespread use.

The invention relates to the technical field of spine image recognition, in particular to a spine model recognition positioning method, which comprises the following steps of: determining a vertebra sub-contour of each vertebra in a first model image of a target object in a first pose state, and judging whether the recognition credibility of the vertebra sub-contours reaches the standard or not according to the position distribution state of contour recognition lines; the method comprises the following steps: determining an identification reference contour of a vertebra sub-contour of which the identification credibility does not reach the standard, determining pose change data based on coordinate change of an edge calibration point of the identification reference contour, and calculating pose change reference coordinates of the edge calibration point in a second model image; whether the model image is valid is judged based on the actual coordinate difference condition of the pose change reference coordinate and the edge calibration point in the second model image, so that a verification scheme based on associated image data and a model validity judgment means are provided for the vertebra sub-contour of which the identification credibility does not reach the standard; and the spine model identification positioning precision and effectiveness are improved.