31 results about "Surgery training" patented technology

The invention discloses a neurosurgical operation virtual simulation training system based on multi-modal data fusion, and relates to the technical field of operation simulation. The data acquisition and preprocessing module acquires data such as images and force feedback, and standardized storage is performed after filtering and registration; the multi-modal data fusion module performs weighted fusion on the data by using an attention algorithm to generate a three-dimensional model; the virtual operation scene construction module generates a high-fidelity environment through ray tracing and a physical engine; the surgical operation interaction simulation module realizes accurate interaction through positioning tracking and force feedback; the training evaluation and feedback module quantifies operation performance and provides guidance; and the system management and iteration module guarantees operation and supports data updating and optimization. According to the method, a high-reality scene is constructed through multi-modal fusion, interaction and multi-dimensional evaluation help skill improvement, dynamic difficulty and personalized paths are adaptive to different users, collaborative training and privacy data collaboration are supported, operation training standardization is promoted, and the risk of errors in an operation is reduced.

The invention relates to the technical field of visual identification, and discloses an operation stage identification method based on a dynamic data balance strategy, and the method comprises the following steps: S1, collecting operation original data, and carrying out the annotation of the collected original data; s2, preprocessing the annotated original data by utilizing a dynamic data balance strategy so as to form a data set; s3, constructing an Xception-double flow LSTM (Long Short Term Memory) recognition model; and S4, training and optimizing the Xception-double-flow LSTM recognition model by using the data set. According to the method, the problem of bias learning is effectively relieved, the influence of data volume difference on a model learning process is effectively reduced, and deviation is reduced, so that higher classification performance is shown in an operation stage identification task; the method effectively improves the overall recognition precision of the operation stage, can provide more structured support for operation training, quality control and clinical decision making, and further lays a foundation for research and development of an intelligent operation auxiliary system.

An arrangement applied to a simulator for surgical training in ophthalmology that is anatomically similar to the human eye, and has the purpose of training and qualification in ophthalmological surgical processes. An artificial cataract for use in simulators for surgical training in ophthalmology.

The invention relates to the field of organ transplantation in biomedical technology, and particularly discloses normal-temperature perfusion protection liquid for thoracoscopic surgery training as well as a preparation method and application of the normal-temperature perfusion protection liquid. The components of the perfusion protection liquid mainly cover sodium chloride, carbohydrates, adenosine and dexamethasone. The perfusion protection liquid has the advantages that on one hand, the components of the protection liquid are simple, complex components of a traditional perfusion protection liquid are abandoned, and the raw material obtaining and economic cost is greatly reduced; and on the other hand, the perfusion protection liquid gets rid of the limitation of low-temperature storage and can be stably stored in a normal-temperature environment. Compared with the prior art, the perfusion protection liquid provided by the invention not only has simple components, but also breaks the constraint of cold chain transportation and low-temperature storage, solves the problems of complex components and harsh storage conditions of the existing protection liquid, provides a more convenient and efficient solution for thoracoscopic surgery training and even wider medical practice, and has broad application prospects. The method has a wide application prospect and an extremely high practical value.

The application relates to the technical field of medical data processing, and discloses a mixed reality surgery training collaboration method and system supporting multi-role interaction. The method comprises the following steps: realizing surgery stage identification and dynamically adjusting multi-role permissions through weighted fusion of videos and instrument features, realizing virtual-actual accurate registration through non-rigid interpolation deformation, enhancing interactive immersion through spatial distance and motion parameter driven haptic feedback, guaranteeing data security through differential encryption and chain hash storage, and intelligently allocating bandwidth and dynamically adjusting model precision through a deep Q network. The application solves the problems of fixed multi-role collaboration permissions, insufficient virtual-actual registration accuracy, lack of feedback for gesture operation, unsafe data transmission and unreasonable network bandwidth allocation in the prior art.

The invention discloses a blood vessel model collision force detection method for interventional operation training, which comprises the following steps: arranging a blood vessel model in a closed shell, and connecting the blood vessel model with an external flow pump to promote fluid to circularly flow in the blood vessel model; the closed shell outside the blood vessel model is filled with medium liquid, and the blood vessel model is completely immersed in the liquid medium; a plurality of pressure sensors connected with an external data processing unit are orderly distributed on the inner wall surface of the closed shell; during training, the guide wire extends into the blood vessel model for interventional operation, when the guide wire collides with the wall surface of the blood vessel model, the wall surface of the blood vessel model triggers the medium liquid to trigger the medium liquid in the closed shell to generate pressure field change, and the corresponding pressure sensor monitors pressure field data and feeds back the pressure field data to the data processing unit; the data processing unit obtains the pressure value and calculates and outputs the corresponding collision force, objective, quantitative and comprehensive data feedback of the collision force in interventional operation training is achieved, and the operation training effect is greatly improved and guaranteed.

To provide an endoscope surgery training device that can realize a specific part of an organ in the same manner as an actual organ.SOLUTION: A surgery training device can include: a training space that is formed inside the device to allow a user to conduct training for surgery; a housing that includes a support plate forming a bottom face of the training space; a holder for fixing a training target member; a driving unit that includes a holder support member to which the holder is coupled, and changes the position of the holder coupled to the holder support member in the training space through at least one or more degree of freedom motions, so that the training target member fixed to the holder to be changed to a specific copy position of an organ for training in the training space; a channel forming unit that is formed in the housing so that an approach route for an endoscope device entering the training space from the outside can be formed; and a control unit for controlling the driving unit.SELECTED DRAWING: Figure 1

The present invention discloses a laparoscopic ultrasound-endoscopic combined surgery training model which is convenient for replacing organ modules, comprising a mounting base, an organ module and a fixing device; the mounting base is provided with a first mounting position, the first mounting position is provided with a first card slot; the mounting base is provided with a slide slot; a lever is provided in the slide slot; the organ module is provided with a second mounting position, the second mounting position is provided with a second card slot; the first mounting block is provided with a driving member and a first card block; an elastic energy storage member is provided between the driving member and the first mounting block; the second mounting block is connected to the driving member; a slider is provided for sliding through the second mounting block; a first spring is provided between the slider and the second mounting block; the second mounting block is provided for sliding through the second card block; the organ module is conveniently disassembled and assembled, and the structure is more flexible so as to be adjusted according to different surgical requirements and adapt to the simulation of various surgical scenes to enhance the training effect of the model, and the installation is more firm and not easy to loosen or deviate, so as to ensure the accuracy and stability during the training process.

The present invention discloses a cesarean section surgery training method and system based on mixed reality. The method includes: acquiring medical image data of a pregnant woman's pelvis and abdomen, identifying and marking the boundaries and regions of key organizational structures, constructing a three-dimensional model of the key organizational structures, generating key indicators for cesarean section surgery training, importing the constructed three-dimensional model into the MR system, collecting motion data, generating real-time feedback prompts, receiving a training end signal, generating an evaluation result, recording operations that do not meet the evaluation criteria, and providing targeted improvement suggestions for the trainees. The present invention can effectively improve the quality and efficiency of surgery training. Through the precise processing of medical images, the efficient reconstruction of three-dimensional models, real-time feedback, and personalized operation evaluation, it not only provides a safe, efficient, and immersive training platform for trainees, but also can provide personalized guidance according to their performance, further improving the training effect of surgical skills.

Embodiments of the present invention provide GYN pathology simulation models for surgical training. These models are energy-compatible models emulating the tissue-based diseases of the female reproductive system to allow the surgical trainees and surgeons to practice advanced OB / GYN surgical skills. One simulated GYN model includes an electrically conductive elongated tube encapsulating a mass of non-conductive material. The elongated tube having a sidewall with an inner surface and outer surface extending between a proximal end and distal end. The sidewall is configured to have a cavity with a specific volume to yield an external protuberance when filled with the mass of non-conductive material. Another simulated GYN model includes a fluid-filled cystic body encapsulated within an electrically conductive bulbous hollow structure. The fluid-filled cystic body is selectively adhered to the bulbous hollow structure in at least one or more regions, thereby creating a plane for a combination of blunt and sharp dissection.

A single-port surgery training device according to one embodiment of the present disclosure comprises: a surgical tool including forceps, an incision tool, and at least one first sensor provided in the forceps and / or the incision tool so as to generate position information and orientation information of the forceps and / or the incision tool; a simulation module including a housing and a single port, which is provided at one side of the housing so that the forceps and the incision tool are inserted therein; and a host computer communicatively connected to the surgical tool and the simulation module, wherein the host computer can generate a virtual surgical environment.

The invention relates to the technical field of medical instruments, in particular to a heart model and coronary artery interventional operation training device.The heart model comprises a main body and a simulated blood vessel set, the blood vessel set is formed by sequentially connecting a coronary artery tube and first-level to third-level branch vein tubes, and the second-level branch vein tube is provided with a detachable lesion simulation module; the lesion simulation module is provided with simulation plaques such as calcification, a fiber cap or a lipid core and is used for simulating different stenosis lesions. The three-stage branch vein tube is additionally provided with a side branch tube and a multi-stage branch tube, so that the tortuosity and anatomy authenticity of the blood vessel are enhanced. The problems that an existing training device is simplified in branch, single in lesion and lack of key blood vessels and real tactile feedback are solved, the guide wire control ability and the operation proficiency of interventional doctors can be effectively improved, the learning period is shortened, and the clinical operation risk is reduced.

The utility model discloses a microscopic anastomosis training model, and relates to the technical field of medical teaching aids. Comprising a simulation model, a top cover is installed on the top of the simulation model, a pressure monitor, a liquid storage bin, a circulating pump, a flow meter and a pressure sensor are fixedly installed in the simulation model, and the pressure monitor, the liquid storage bin, the circulating pump and the flow meter are jointly connected with a blood simulation pipeline. A blood vessel model is detachably installed between the two ends of the blood simulation pipeline, the blood vessel model is attached to the top of the pressure sensor, the circulating pump is located at the top of the liquid storage bin, the input end of the circulating pump is communicated with the interior of the liquid storage bin, and the output end of the circulating pump is communicated with the blood simulation pipeline; the device can more intuitively show a training result, so that trainees in clinical operation training can experience a real environment and quickly grasp an operation process, and the device has remarkable significance.

The invention relates to the technical field of medical models, in particular to a medullary tooth model for training and researching an apical operation and a manufacturing method of the medullary tooth model. According to the method, after the model with the medullary teeth is manufactured, CBCT equipment is used for scanning the manufactured model with the medullary teeth again, in the scanned image, the teeth, the oral mucosa, the maxilla and the mandible respectively have three different developing degrees, the teeth can be accurately distinguished from the maxilla and the mandible according to the image, and the accuracy of the tooth identification is improved. The anatomical structures of real teeth, the maxilla and the mandible are simulated by using the model, and operation training and research are facilitated.

The invention provides an AI-based intelligent focus detection method in virtual hysteroscope operation training, and the method comprises the steps: obtaining an input feature sequence, constructing an operation process context recognition module based on an LSTM layer, a full connection layer and a Softmax activation function, processing the input feature sequence through the operation process context recognition module, obtaining an operation stage probability, and carrying out the recognition of the operation stage probability. And constructing a discrete cosine transform channel attention module based on a discrete cosine change mechanism, a full connection layer and a layer normalization mechanism, and processing the input feature sequence by using the discrete cosine transform channel attention module to obtain features subjected to channel attention weighting. According to the invention, the interactive perception feature approximation module is designed, and the interactive perception feature approximation module can reflect the operation behavior in the operation process and the change trend of the focus by analyzing the feature change between continuous frames and capturing the change dynamic information of the surgical operation or focus state, so that richer space-time dimension information is provided for focus detection.

An applicator device for training medical practitioners is provided. The applicator device is configured for practicing a surgical procedure for delivering a rod-like implant under the skin of a human or animal. The applicator device includes an actuator that retracts a needle to deploy an artificial implant loaded inside a lumen of the needle. The needle is locked in a retracted position to prevent injury from an accidental forward deployment of the needle. A reset mechanism releases the needle to allow the applicator device to be reset and reused for repeated training. The reset mechanism is unlocked when a needle cap is attached to prevent injury. A kit includes the applicator device and simulated tissue structures for practicing the procedure on the simulated tissue structures with the applicator device.

The utility model relates to the technical field of thoracic cavity simulation boxes, and discloses a thoracic cavity simulation box for cardiopulmonary surgery training, which comprises a silica gel simulation trunk and a bionic skeleton, and the bionic skeleton is arranged in the silica gel simulation trunk to support the silica gel simulation trunk. An alarm is further arranged at one end of the silica gel simulation trunk, the bionic skeleton has a deformation stroke in the vertical direction to simulate the chest of the human body, and a trigger mechanism is further arranged in the silica gel simulation trunk and electrically communicated with the alarm. According to the cardiopulmonary resuscitation device, the triggering stroke of the buzzer can be changed by adjusting the position of the adjusting screw sleeve, then medical staff can master experience in training every time, and cardiopulmonary resuscitation can be rapidly carried out as much as possible under the condition that the pressing degree is prevented from being too large.

The invention relates to the technical field of medical training, in particular to a vascular interventional operation training simulator system and an interactive imaging method based on virtuality and reality combination, and the method comprises the steps of data acquisition, cardiovascular model body construction, virtual angiography generation, physical training environment construction, ultrasonic guided puncture operation, interventional operation operation and real-time visual tracking. Multi-modal feature fusion processing, digital twin scene fusion and virtual DSA display are carried out. A physical training environment is constructed through the cardiovascular model body and the puncture module, an accurate dynamic mapping relation between a physical operation space and a virtual image space is established through real-time visual tracking and multi-modal feature fusion, a finally generated DSA radiography effect realizes personalized interventional surgery operation training with high simulation degree and consistent visual sense and force sense, and the training efficiency is improved. The problems of poor simulation performance and low effectiveness of training caused by lack of dynamic image feedback of an entity model and insufficient touch authenticity of pure virtual training are effectively solved.

The utility model relates to the field of surgery training models, and discloses a minimally invasive urinary tract surgery training model which comprises a main body frame, the upper end face of the main body frame is in threaded connection with a fixing plate, the upper end face of the fixing plate is fixedly provided with a spongy cushion, and the upper end face of the spongy cushion is movably provided with a bladder model. A urinary catheterization model is fixedly arranged on the front end face of the bladder model, a telescopic pipe is slidably arranged on the front end face of the urinary catheterization model, a rotating cover is hinged to one side of the bladder model, and a magnetic attraction block is fixedly arranged at the rear end of the rotating cover. According to the utility model, the fixing plate at the upper end of the main body frame can fix the sponge pad, the sponge pad can support the bladder model during use, the urinary catheterization model is arranged at the front end of the bladder model, and the telescopic tube is arranged at the front end of the urinary catheterization model, so that the length of the urinary catheterization model can be changed, and different urinary catheterization tube lengths of different persons can be simulated; and when the training personnel use the device, the device can simulate different crowds.

The invention discloses a high-simulation cardiac surgery skill training method, which comprises the following training steps: step 1, when a heart model is made by electronic skin and a scalpel performs surgery training on the surface of the heart model, the electronic skin can sense the contact position of the scalpel with the heart model, the applied force and the pain of the scalpel; 2, electronic skin, a curvature sensor and a vibration motor are additionally arranged in a cardiac surgery operation glove, and a somatosensory and tactile sensing glove is formed and used for sensing force control behaviors of a doctor during cardiac surgery and measuring the curvature of fingers. The cardiac surgery level of intern doctors is improved; teaching and training data and videos, stored in the training system, of deep-qualification doctors can be conveniently and remotely transmitted, so that the remote teaching ability is achieved, and the cardiac surgery skill training range and convenience are expanded; therefore, the single training content is reduced, the learning quality of each training is improved, and the training effect and efficiency of intern doctors are ensured.

The invention provides an ECMO operation training device which comprises the components of a base which is provided with a liquid storage tank; a vein system simulation unit and an artery system simulation unit, wherein the vein system simulation unit and the artery system simulation unit are respectively arranged on the base; the puncture block is arranged on the base, the puncture block is used for simulating the tissue structure of a puncture part, and the liquid inlet end of the vein system simulation unit is communicated with the liquid outlet end of the artery system simulation unit through a blood flow channel in the puncture block; the liquid outlet end of the pulsating pump is communicated with the liquid inlet end of the artery system simulation unit; the switching module is switched between a first state and a second state; when the switching module is in a first state, the liquid inlet end of the pulsating pump is communicated with the liquid outlet end of the liquid storage tank; when the switching module is in the second state, the liquid inlet end of the pulsating pump is communicated with the liquid outlet end of the venous system simulation unit.

The invention belongs to the technical field of medical simulation training and surgical education, and discloses a urinary surgery training method and system based on augmented reality simulation, electronic equipment and a storage medium. The method comprises the following steps: S1, constructing a virtual operation scene according to a preset three-dimensional anatomical model of the urinary system; s2, integrating a real-time interactive surgical instrument digital twinborn model in the virtual surgical scene; s3, according to a user operation input signal, driving the surgical instrument digital twin model to dynamically respond in the virtual surgical scene; s4, superposing the dynamically responded virtual operation process into a real training environment visual field through augmented reality display equipment; and S5, generating corresponding operation track data according to continuous operation behaviors of the user in the superposed visual field, and storing the operation track data in a training database. According to the method, the defect of scene splitting in traditional virtual reality training can be effectively overcome through high-precision space registration and real-time rendering.

The application belongs to the technical field of deep learning, and provides a cataract surgery evaluation method and system based on deep learning and a medium, comprising the following steps: S1, classifying the surgery stage in which a video frame is located by using the surgery instrument features in the video frame in combination with the eye background features; S2, training a general network according to the initial feature labels of each link of the surgery to extract evaluation features in the video frames corresponding to each link for surgery evaluation; and S3, obtaining the quantitative information of each link of the surgery according to the preset labels of the extracted evaluation features, and inputting the quantitative information into the trained preset classification evaluation network to perform classification evaluation on each link of the surgery. The application has the advantage that the quantitative relationship between the descriptive evaluation indexes in the ICO-OSCAR standard and the learnable surgery features of the deep learning network is established, so that the full-process participation of expert doctors in surgery training is replaced by artificial intelligence technology, and the objectivity, reliability and response speed of the training effect are improved.

The invention relates to a lumbar intervertebral disc puncture device based on three-dimensional CT and a puncture method.The lumbar intervertebral disc puncture device based on the three-dimensional CT comprises a transverse sliding rail, a longitudinal ruler and a puncture cannula, the transverse sliding rail is a long-strip-shaped sliding rail with scales, the longitudinal ruler is a long-strip-shaped ruler with scales, an arrow is arranged at one end of the longitudinal ruler, and the transverse sliding rail is a long-strip-shaped sliding rail with scales. The longitudinal scale is movably installed on the transverse sliding rail through a first connecting piece and can slide left and right on the transverse sliding rail, a second connecting piece at the end of one side of the transverse sliding rail is movably connected with a puncture cannula, and the puncture cannula can swing left and right or rotate front and back at the end of the transverse sliding rail. The designed device is simple and convenient, and the scheme is easy to learn; according to the method, the puncture point and the puncture angle can be conveniently found in the operation according to the pre-operation plan, the operation can be rapidly and accurately completed, low-age doctors can be helped to rapidly master operation skills by applying the method, and the method can be used for operation training.

The utility model relates to an implantation operation training model for a full subcutaneous implantable defibrillator, and relates to the technical field of medical teaching aids. The system comprises a simulated human body, the simulated human body comprises a simulated sternum and a simulated rib, the outer sides of the simulated sternum and the simulated rib are wrapped with simulated muscle tissue, the outer side of the simulated muscle tissue is provided with simulated skin tissue, and the simulated skin tissue is detachably provided with a skin replacement module corresponding to an S-ICD implantation operation position. The S-ICD operation training device has the effect of providing the S-ICD operation training device which is high in simulation degree and controllable in cost for doctors.

A surgical training console (10), comprising: a base (12); a restraint module (16) having an opening (28) allowing passage of at least a portion of at least one surgical simulation tool (100) intended to be manipulated by a user; a haptic arm (14) secured to the base (12) having a free end (26) configured to connect a surgical simulation tool. The haptic arm is movable and allows defining a working space (T) comprising all positions that can be occupied by the free end. The base and the constraining module (16) are arranged to define a free space defining a manipulation space (M), the manipulation space (M) being smaller than or equal to the working space (T), and the constraining module enabling the constraining of a position that the free end of the haptic arm can occupy to a position within said manipulation space.

The utility model discloses a headstock suitable for neurosurgery dissection training, and relates to the technical field of neurosurgery operation training equipment, the headstock comprises a pedestal which is a square plate, and a cylindrical support arm is arranged above one side of the pedestal; the head nail system is used for fixing the skull, is mounted on the cylindrical supporting arm and is adjustable in angle; according to the scheme, through cooperation of the head nail system, the traction system and the universal joint, the head nail system fixes the head and keeps the stability of the head, the universal joint is used for adjusting the position of the head nail system, then the position of the head is adjusted, the angle can be conveniently adjusted according to needs during training, and therefore the training efficiency is improved. And the traction system retracts the skin at the surgical incision, so that the deeper position of the skull can be operated conveniently, and the simulation effect of operation training is improved.

The invention relates to a 3D printing teaching model and method for maxillary sinus bone increment surgery training, and relates to the technical field of clinical medices.The 3D printing teaching model comprises an anatomical structure model, the anatomical structure model covers left and right maxillary bones, cheekbones and maxillary sinus opening anatomical structures, and the anatomical structure model is provided with a maxillary bone orbital bottom area of a windowing structure; a silica gel layer is arranged on the inner wall of the maxillary sinus, and the rear portion of the maxillary bone is connected with the connecting rod through a fixator to be fixed to the operation table. The windowing structure allows the inner wall of the maxillary sinus to be glued or sprayed through direct operation, and the maxillary sinus bone increment and the operation effect can be observed in real time through the windowing at the orbital bottom. Through innovative design, simulation, functionality and operability are integrated, and a more real and efficient teaching tool is provided for medical students and young doctors.

The invention relates to the field of medical education, and particularly discloses a bone joint MDT-VR teaching system. Comprising a dynamic pathology engine module which simulates contact stress and strain distribution under a joint load in real time by adjusting tibial plateau inclination angle (TPT), cam effect (CE) and tibial plateau femoral condyle coverage (TPCFC) anatomical parameters based on a parameterized finite element (FEA) simplified algorithm; when TPT is larger than or equal to 12.5 degrees, the contact stress of a tibial plateau is increased by 23%, when CE is larger than or equal to 1.9, the peak strain of cartilage is increased by 18%, and dynamic changes of tibia and femoral joint stress in the 0-130-degree buckling process of the knee joint (the stretching position is 10 MPa, the 30-90-degree buckling position is 6 MPa, and the 90-130-degree buckling position is 21 MPa) are supported. The invention further discloses a method applied to the teaching system. Through a dynamic pathology engine, interdisciplinary data interlocking and error thermodynamic diagram technology, a bone joint MDT-VR teaching system of biomechanical simulation-real-time cooperation-quantitative feedback is constructed, operation training precision and efficiency are significantly improved, and clinical risks are reduced.

The utility model provides a full femtosecond surgery practice model which comprises a simulated eyeball, a simulated cornea, a simulated matrix lens and a cover ring, the simulated cornea and the simulated matrix lens are sequentially stacked on the simulated eyeball, and the cover ring is arranged on the simulated cornea to tightly press the simulated cornea and the simulated matrix lens. The position, corresponding to the notch, of the imitated cornea is used for imitating a surgical incision, and the imitated surgical incision is used for taking out the imitated matrix lens. In a full femtosecond surgery learning stage, repeated practice can be performed through the practice model, so that the hand flexibility is improved, and surgery related complications possibly caused by unskilled operation are greatly reduced; and meanwhile, consumables required by the exercise model in use are low in price and easy to obtain, so that the cost is reduced.