8 results about "Paraspinal Muscle" patented technology

The application discloses a MRI paravertebral muscle segmentation method based on Bayesian fusion and probability shape modeling, and comprises the following steps: a) a Fourier-Gaussian process probability shape model is established to parameterize the muscle shape, the Fourier-Gaussian process probability shape model comprises radial modeling based on a Fourier basis function to represent a muscle cross-section profile, and axial modeling based on a Gaussian process to capture the axial variation law of the muscle shape; b) a muscle edge feature model based on a convolutional neural network is constructed to perform multi-scale feature extraction on the muscle edge in the MRI image; and c) a Bayesian segmentation framework is designed, and based on a maximum posterior estimation principle, online segmentation of the paravertebral muscle in the MRI image is realized. The application is customized according to the characteristics of the paravertebral muscle segmentation task through the idea of fusing high-quality artificial labeling and a powerful learning model, so that the application can achieve high segmentation and reconstruction quality under a small amount of interaction, and has strong shape change description capability.

The present invention reduces pain and improves function long-term in persons with back pain using electrical stimulation in the back. This approach involves an electrical stimulation device including at least one electrode adapted for insertion within an animal body with back pain and at least one pulse generator operatively coupled with the at least one electrode, wherein the pulse generator delivers electrical stimulation activating at least a nerve innervating at least a paraspinal muscle in a back of the animal body for pain relief.

The invention belongs to the technical field of biology, and particularly relates to a scoliosis rat model construction method which comprises the following steps: S1, obtaining an experimental animal, removing the forelimb and the tail of the experimental animal, enabling the gravity direction of the experimental animal to be parallel to the spine, and obtaining a biped animal; s2, performing excision treatment on a deep paravertebral muscle group on one side of the biped animal to obtain an experimental animal with muscle mechanics imbalance; and S3, performing exercise load stimulation treatment on the experimental animal with muscle mechanics imbalance to obtain the scoliosis animal model. According to the method disclosed by the invention, the scoliosis animal model capable of highly simulating human disease characteristics is constructed by combining axial gravity load under a two-foot standing posture, structural and mechanical unbalance caused by directional unilateral deep paravertebral muscle excision and regular movement stimulation; the method can accurately and controllably induce scoliosis in a specific direction opposite to a muscle resection side, and has a wide application prospect.

The invention provides a multifunctional device and method for scoliosis rehabilitation, and the device comprises a rehabilitation traction supporting platform, an array type electric air bag traction module, a warm magnetic therapy module, a low-frequency electrical stimulation module, an ultrasonic module and a central control system, the lifting device is used for carrying out directional lifting and drafting on a convex side thoracolumbar section of a target object; the warm magnetic therapy module is used for being started before traction is started and carrying out warm and magnetic field combined pretreatment on paravertebral muscles and fascia tissues of a target object; the low-frequency electrical stimulation module is used for performing electrical stimulation on the target muscle group when the convex side of the target object lies downwards; the ultrasonic module is used for performing ultrasonic debonding on the concave side body surface of the target object; and the central control system is used for controlling and coordinating the start-stop sequence, the working state and the output parameters. By means of the scheme, the problems that rehabilitation equipment is single in mode, low in function integration degree and insufficient in personalized adaptation capacity can be solved.

The utility model relates to the technical field of medical instruments, and discloses an expandable UBE working channel. Comprising a first dilation piece, a second dilation piece and an opening mechanism, the opening mechanism can drive the first dilation piece and the second dilation piece to be attached to form a first surgical operation space, and the opening mechanism can drive the first dilation piece and the second dilation piece to be separated to form a second surgical operation space; one end of the second dilation piece is provided with an overhanging part, and the overhanging part is connected with a traction part which extends towards one side of the second dilation piece and in the direction away from the first dilation piece. The UBE working channel can flexibly adjust the operation space in the operation process, the situation that paravertebral muscular tissue hinders operation tool entering and exiting and fusion cage implanting is effectively avoided, meanwhile, the water outlet smoothness is improved, and therefore it is ensured that the visual field under the endoscope is clear, and hydrops in muscle gaps are prevented. And the traction part on the second expansion piece can assist an operator in flexibly pulling nerves without assistance of an assistant, so that the safety and accuracy of an operation are improved, and the nervous tissues of a patient are protected.

Embodiments of the present application relate to a pedicle screw loosening evaluation method and device based on no phantom QCT bone density measurement. The method comprises: acquiring quantitative computed tomography (QCT) image data of a lumbar vertebra of a patient; based on a no phantom calibration technology, performing bone density calibration and measurement on CT values of paraspinal muscles and subcutaneous fat in the lumbar vertebra QCT image data; segmenting a vertebral body region and a pedicle screw channel region of the CT image sequence of the patient through a preset neural network model; determining the bone density of the pedicle screw channel region, combining with finite element biomechanical analysis to evaluate the pull-out force of the pedicle screw implantation; and determining a risk level according to the pull-out force and a preset loosening risk evaluation rule. The technical solution of the embodiments of the present application can evaluate the risk of postoperative screw loosening, pull-out and other complications without relying on external phantoms to evaluate local bone density.

The application belongs to the technical field of biomedical experimental animal model construction, and provides a rat severe spinal cord injury immediate decompression model construction method. The method establishes a standardized surgical procedure, including minimally invasive exposure through the paraspinal muscle gap, precise dura mater incision, warm saline low-pressure lavage debridement, and strict dura mater suture repair. The method realizes immediate and effective reduction of intrathecal pressure, removal of harmful substances in the injury area, and stabilization of the local microenvironment after severe spinal cord injury. The application solves the problems of instability, poor repeatability, and difficulty in simulating the clinical decompression effect caused by the non-standard dura mater incision, uncontrollable lavage, and high risk of secondary injury in the prior art. The model constructed by the method is highly standardized and has strong repeatability, and is suitable for in-depth study of the neuroprotective mechanism of dura mater incision decompression treatment for spinal cord injury.

The application provides a paravertebral muscle muscle image segmentation method and device, and belongs to the technical field of medical image processing. The method comprises the following steps: training an original image segmentation model by using sample paravertebral muscle muscle images, to obtain a trained original image segmentation model; the original image segmentation model at least comprises an image encoder, a prompt encoder and a mask decoder; the mask decoder in the trained original image segmentation model is improved, so that a double-layer upsampling module in the mask decoder is replaced by a Unet module, to obtain an improved image segmentation model; under the condition of freezing the parameters of the image encoder and the prompt encoder, the improved image segmentation model is trained by using the sample paravertebral muscle muscle images, to obtain a target image segmentation model; and an original paravertebral muscle muscle image to be segmented is input into the target image segmentation model, to obtain a segmented paravertebral muscle muscle image.