1773 results about "Soft tissue" patented technology

The invention discloses a medical image enhancement method and system based on multi-modal fusion, and the method comprises the steps: obtaining medical image data which comprises a CT image, an MRI image, a PET image and an ultrasonic image; calculating a mutual information value of each semantic tag in the cross-modal feature vocabulary, and generating an inter-modal feature correlation matrix; performing non-rigid space registration on the unified dimension image set to generate a geometrically consistent multi-modal image set; extracting skeleton region features, soft tissue region features and high metabolism region features from the multi-modal image set, and generating a core feature set; a deep learning algorithm is adopted to train the core feature set, and a segmented image set containing a segmentation mask is generated; and dynamically adjusting the fusion weight according to the regional features of the segmented image set, and generating a fusion enhanced image. According to the invention, through feature extraction, spatial registration and deep learning fusion of the multi-modal medical image, effective integration of different-modal medical image information is realized.

The invention relates to a biological soft tissue virtual simulation method and system and a medium, and the method comprises the following steps: constructing a three-dimensional soft tissue model based on medical image data, dispersing the three-dimensional soft tissue model into a particle system, and binding initial constraint parameters; detecting collision between the particles and the surgical instrument based on a symbolic distance field technology, if collision is not detected, outputting the positions of the particles, generating a simulation result, if collision is detected, applying repulsive force to the particles to correct a deformation path, judging whether stress is balanced or the maximum number of iterations is reached, if yes, returning to perform collision detection, and if not, returning to perform collision detection. The particle speed is updated in real time, the particle motion trend is predicted through an implicit time integration algorithm, position constraint, volume constraint, shape constraint and physical constraint are solved in a coupling mode through a Gaussian-Seidel iteration method, constraint rigidity is dynamically adjusted to be matched with real organization characteristics, and the particle position is updated. Compared with the prior art, the method has the advantage that deformation accords with a real physical change rule.

The invention relates to the technical field of medical equipment, in particular to an ultrasonic soft tissue operation accessory intelligent recognition and energy regulation and control system and method.The ultrasonic soft tissue operation accessory intelligent recognition and energy regulation and control system comprises an intelligent recognition module used for recognizing the type, specification and real-time use state of an operation accessory to serve as an output result; the energy regulation and control module is connected with the intelligent identification module and dynamically adjusts the output parameters of the ultrasonic energy according to the output result of the intelligent identification module; and the man-machine interaction module is respectively connected with the intelligent identification module and the energy regulation and control module and is used for displaying the identification result, the energy parameters and the early warning information. According to the result of the intelligent recognition module, dynamic adjustment of ultrasonic energy output parameters is achieved through the energy regulation and control module, and smooth operation is ensured; when it is detected that the accessory temperature exceeds the preset threshold value or the impedance abnormally and suddenly rises, energy supply is rapidly cut off, the surgical risk caused by energy abnormity is effectively prevented, and the safety of a patient is guaranteed.

The invention belongs to the technical field of biomedical materials, and relates to ultrasonic response adhesion integrated hydrogel as well as a preparation method and application thereof, the hydrogel comprises a hydrogel matrix, an interface anchoring agent and a functional load component; the preparation method comprises the following steps: 1, preparing a hydrogel precursor solution, and preparing a hydrogel matrix into a solution; 2, carrying out mold molding or injection crosslinking on the solution prepared in the step 1 to form hydrogel; 3, preparing an interface anchoring agent solution, and dissolving or dispersing an interface anchoring agent in a solvent to prepare the interface anchoring agent solution; the ultrasonic responsive adhesive hydrogel platform provided by the invention can provide an efficient, controllable and universal solution for tissue adhesion, targeted therapy, wearable attachment and the like in a complex microenvironment, and is suitable for a plurality of clinical scenes such as chronic wound management, surgical postoperative closure, infection control, adhesive bioelectronic fixation, soft tissue engineering and the like.

A surgical planning system for use in surgical procedures to repair an anatomy of interest includes a preplanning system to generate a virtual surgical plan and a mixed reality system that includes a visualization device wearable by a user to view the virtual surgical plan projected in a real environment. The virtual surgical plan includes a 3D virtual model of the anatomy of interest. When wearing the visualization device, the user can align the 3D virtual model with the real anatomy of interest, thereby achieving a registration between details of the virtual surgical plan and the real anatomy of interest. The registration enables a surgeon to implement the virtual surgical plan on the real anatomy of interest without the use of tracking markers.

The invention provides a method for predicting the vibration reduction effect of exercise compression pants, and relates to the technical field of functional costume design, and the method comprises the steps: collecting a static costume pressure value of a lower limb target muscle group and soft tissue amplitude data in exercise, constructing a pressure-amplitude mathematical model through data processing, and verifying the model; constructing a human body-clothing finite element model, inputting fabric mechanical parameters into the model, and verifying the effectiveness of the model after iterative optimization; inputting fabric mechanical parameters into the verified finite element model, inputting a pressure prediction value output by the model into the pressure-amplitude mathematical model, and predicting soft tissue amplitude in a dynamic motion scene; according to the predicted soft tissue amplitude in the dynamic motion scene, the vibration reduction effect of the motion compression trousers in the target motion scene is evaluated. The method provided by the invention solves the problem that the vibration reduction effect evaluation of the traditional sports compression pants depends on a large number of repeated physical experiments and is difficult to realize accurate quantitative prediction.

The invention relates to the technical field of computers, discloses a tooth three-dimensional precision correction method and system based on multi-source oral data fusion, and aims to solve the problems of low registration precision, serious geometric distortion and lack of function oriented optimization of multi-modal oral data in the prior art. The method comprises the following steps: synchronously obtaining intraoral scanning, CBCT and face three-dimensional point cloud data; carrying out format conversion, denoising and grid simplification preprocessing; tooth surface morphology, root canal anatomy and soft tissue contour features are extracted and coded into uniform feature tensors; and multi-modal data space alignment is realized through staged rigid and non-rigid registration. By means of the scheme, the multi-source data fusion precision and the tooth form restoration accuracy are remarkably improved, full-process automatic efficient processing is achieved, and the clinical real-time performance and high-precision diagnosis and treatment requirements are met.

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 robot systems, and discloses a nerve plexus intelligent positioning anesthesia puncture robot system based on multi-modal fusion, which performs time-space synchronization on ultrasonic image flow and contact force data. The frequency domain analysis module extracts a main peak frequency by using optical flow field frequency domain transformation, and generates a probability mask for marking pulsatile tissues. The viscoelasticity verification module calculates phase lag parameters of visual deformation and contact force, identifies tissue rheological properties and calculates a dynamic damping coefficient. The deformation compensation module calculates a mechanical residual error based on a reference mechanical model, and inversely calculates the mechanical residual error into space deformation displacement of the tissue. The feedback control module combines the probability mask and the deformation displacement to generate a motion instruction. According to the invention, through multi-modal data fusion, precise identification of tiny blood vessels, dynamic identification of tissue attributes and real-time compensation of soft tissue conceding deformation are realized.

An orthopaedic knee prosthesis includes a tibial bearing component with articular features which operate to protect adjacent soft tissues of the natural knee, promote and / or accommodate desired articulation with an abutting femoral component, and facilitate expedient and effective implantation by a surgeon.

The invention relates to a protein-based phenylboronic acid ester dynamic crosslinking hydrogel material as well as a preparation method and application thereof. The preparation method comprises the following steps: dissolving a component A, namely a phenylboronic acid modified protein polymer derivative, in a biocompatible medium to obtain a solution A; dissolving a component B, namely a macromolecular derivative containing a vicinal diol group, into a biocompatible medium to obtain a solution B; and mixing the solution A and the solution B with a certain concentration for a certain time to obtain the protein-based phenylboronic acid ester dynamic crosslinking hydrogel material. The boric acid ester dynamic cross-linking bond belongs to reversible chemical cross-linking reaction, and the prepared protein-based hydrogel material has enough mechanical strength and cheap operability. The protein-based hydrogel material disclosed by the invention can provide the effects of cell adhesion, proliferation and differentiation promotion, tissue regeneration and the like, can load and slowly release beneficial components for promoting tissue repair, is an ideal tissue engineering scaffold material, and can be applied to defect regeneration and repair of soft tissues, cartilages, bones and the like.

Systems, devices, and methods described herein relate to generation and delivery of pulsed waveforms, e.g., for therapy delivery in soft tissue ablation procedures. In some embodiments, a pulse generator is configured to generate a voltage pulse train including a plurality of biphasic pulses, each biphasic pulse of the plurality of biphasic pulses including a positive pulse, a negative pulse, and an inter-phase delay separating the positive pulse and the negative pulse. In some embodiments, successive biphasic pulses of the plurality of biphasic pulses can be separated by a pulse-to-pulse delay such that the plurality of biphasic pulses is separated by a plurality of pulse-to-pulse delays, and the plurality of pulse-to-pulse delays can include increasing or decreasing sequences of pulse-to-pulse delays.

The invention provides an osteotomy path adjusting system in robot-assisted knee arthroplasty, and belongs to the technical field of knee joint detection. The system comprises a multi-modal data acquisition unit which comprises a knee joint pressure measuring gasket, an optical acquisition module and a kinematics data acquisition module, the knee joint pressure measuring gasket is used for acquiring knee joint pressure signals in an operation, and the optical acquisition module is used for acquiring relative poses of a femur and a tibia; the kinematics data acquisition module is used for acquiring kinematics data of the mechanical arm; the main control calculation unit comprises a data fusion module and a dynamic compensation module, and the data fusion module is used for constructing a synchronous spatio-temporal data set; and the dynamic compensation module is used for outputting a compensation instruction to the mechanical arm to adjust an osteotomy path based on the synchronous spatio-temporal data set, the preoperative predicted pressure prediction matrix and the soft tissue stiffness matrix. The pressure change in the operation can be responded in real time, the operation precision of the knee arthroplasty is improved, and the dependence on the experience of doctors can be reduced.

The invention relates to the technical field of maxillofacial deformity treatment, and discloses a maxillofacial deformity orthognathic post-operation follow-up visit system and method, the system comprises an image analysis model and a follow-up visit evaluation model, the image analysis model carries out multi-dimensional feature fusion processing on post-operation initial data, and the data comprises three-dimensional bone seam, occlusion function, soft tissue distribution and other feature data; and the follow-up assessment model performs dynamic interference suppression processing on the real-time physiological data stream and then inputs the feature generation layer to simulate a recovery track so as to generate a follow-up assessment instruction. The feature generation layer comprises an image preprocessing module and a dynamic feature generation module, and the dynamic feature generation module is obtained through combined training of multi-type historical postoperative data and real-time physiological parameters and comprises a feature analysis layer, a feature correction layer and an instruction triggering layer. According to the method, the system is applied, and multi-dimensional and intelligent follow-up assessment of postoperative recovery is achieved. According to the method, the accuracy and the real-time performance of follow-up visit are improved, and effective support is provided for postoperative recovery monitoring and intervention.

The utility model discloses an orthopedic drill bit with controllable drilling depth, which comprises a fixing sleeve for fixing a drill bit body, and a limiter and a locking component are mounted at the bottom of the fixing sleeve; a plurality of telescopic holes are formed in the bottom of the fixed sleeve; the limiting stopper comprises a limiting ring, a plurality of moving rods are installed at the top of the limiting ring, springs are further installed at the ends of the moving rods, and the moving rods, namely the springs, are all installed in the telescopic holes; by means of the limiting stopper and the scales, a user can accurately set and read the drilling depth according to needs, and the drilling accuracy and safety in the operation process are guaranteed; due to the design of the movable rod and the telescopic hole, the depth can be adjusted easily and rapidly, and the operation flexibility in the operation process is improved; the limiting ring and the locking assembly are combined for use, the drill bit can be effectively prevented from excessively drilling in, and therefore bone tissue and surrounding soft tissue of a patient are protected against damage.

The invention relates to the technical field of three-dimensional point cloud data processing, in particular to a digital denture model design method based on a jaw position relation. Based on comparison of the initial three-dimensional point clouds under different opening amplitudes, a soft tissue interference area where soft tissue movement possibly exists and a hard tissue boundary false displacement area corresponding to point cloud overlapping caused by a scanning view angle are obtained; according to the method, the movement trend of each point in the false displacement area of the hard tissue boundary is corrected in combination with the movement trend of the adjacent area in the oral cavity, so that the corrected three-dimensional point cloud obtained after correction is more accurate, the accuracy of recording according to the corrected three-dimensional point cloud is higher, and the accuracy of the generated digital denture is improved.

The invention discloses a real-time pose updating method based on feature prediction and point cloud registration, and belongs to the technical field of image registration, and the method comprises the steps: extracting a bone surface point cloud which at least covers a feature region and an adjacent region from a three-dimensional model of a bone tissue of a patient, the point cloud is used as a target point cloud for registration with a real-time ultrasonic image; an ultrasonic image collected by the ultrasonic patch in real time is obtained, and a two-dimensional ultrasonic image with a spatial position is obtained; predicting the two-dimensional ultrasonic image by using a pre-trained artificial intelligence model to obtain bone-soft tissue interface features, and extracting a plurality of points on a bone-soft tissue interface from the bone-soft tissue interface to form a source point cloud for registration; and registering the source point cloud to the target point cloud to realize real-time pose updating. According to the invention, the pose monitoring in the operation can be realized through the real-time image flow under the non-invasive condition.

The invention discloses a thoracoscope minimally invasive cardiac surgery navigation system based on multi-modal image fusion, and the system comprises the steps: constructing a 5D heart digital twin containing an anatomical structure, a soft tissue boundary, metabolic activity and electrophysiological information through fusing preoperative CT, MRI, PET and intraoperative ultrasonic images; real-time dynamic registration is realized by using an electrocardio gating driven biomechanical model; superposing the multi-color coding navigation information to the visual field of the thoracoscope through a wavelength selection type spectroscope; a dynamic risk scoring model is constructed based on the distance, the speed and the tissue vulnerability, and three-level grading intervention is triggered; a miniature force feedback actuator is integrated to realize closed-loop control; and pre-operation virtual drilling and post-operation federal learning optimization are supported. The system remarkably improves the surgical precision and safety, and is suitable for high-difficulty heart minimally invasive surgeries such as mitral valve repair and atrial fibrillation ablation.

This invention relates to an ultrasonic bone scalpel and an ultrasonic cutting device, belonging to the field of medical device technology. The ultrasonic bone scalpel is used to cut bone tissue from within the medullary cavity, and includes an ultrasonic scalpel body and a retaining assembly. The ultrasonic scalpel body includes a handle and a cutting head mounted on one end of the handle. The retaining assembly includes a pressure bladder mounted on the handle, with the pressure bladder and cutting head arranged radially opposite each other along the handle. The pressure bladder is capable of expanding or contracting. The ultrasonic bone scalpel provided by this invention utilizes the expansion of the pressure bladder to provide continuous cutting pressure based on the cutting action of the ultrasonic scalpel body, reducing the cutting wound on soft tissue, thereby protecting soft tissue while satisfying bone tissue cutting requirements. Furthermore, because this ultrasonic bone scalpel cuts from the inside out of the medullary cavity, it avoids external damage to soft tissue, thus reducing the cutting wound on soft tissue and further protecting it. Therefore, when the cutting wound on soft tissue is reduced, the risk of intraoperative infection is correspondingly reduced, and the healing time is shortened.

The invention discloses an alveolar bone noninvasive detection method based on a spatial offset Raman spectrum technology. The method comprises the following steps: S1, selecting a first near-infrared excitation wavelength and a second near-infrared excitation wavelength to form a multi-wavelength tunable excitation light beam; s2, synchronously acquiring a first group of original Raman spectrum signals under a plurality of spatial offset distances; s3, acquiring a second group of original Raman spectrum signals by using an acousto-optic composite modulation Raman enhancement mechanism; s4, inputting the soft tissue optical parameter set into a joint inversion equation; s5, obtaining a deep alveolar bone Raman characteristic spectrum data set; s6, training an alveolar bone tissue health recognition model; and S7, based on the alveolar bone tissue health recognition model, performing health state judgment on the deep alveolar bone Raman characteristic spectrum data set acquired in real time, and generating an alveolar bone health assessment result. The early screening and dynamic monitoring capabilities of alveolar bone diseases are greatly improved, and the clinical working efficiency of doctors and the doctor-seeing experience of patients are remarkably optimized.

The invention discloses a multi-task collaborative bone tumor CT image segmentation method, system and device, and relates to the technical field of bone tumor CT image segmentation. According to the multi-task collaborative bone tumor CT image segmentation method, a bone tumor CT image segmentation model is adopted to carry out bone tumor segmentation on a target bone tumor CT image; the bone tumor CT image segmentation model is trained and obtained through the following method: obtaining an original bone tumor CT image; according to the original bone tumor CT image, screening through a CT value range to obtain a bone image and a soft tissue image; marking a tumor area and a skeleton area in the bone image and the soft tissue image to form a training sample; constructing a multi-task learning network including a skeleton segmentation task and a tumor segmentation task; and training the multi-task learning network based on at least one group of training samples to obtain a bone tumor CT image segmentation model. According to the invention, the bone tumor can be identified more accurately, and the precision of bone tumor segmentation is improved.

Systems, devices, and methods described herein relate to generation and delivery of pulsed waveforms, e.g., for therapy delivery in soft tissue ablation procedures. In some embodiments, a pulse generator is configured to generate a voltage pulse train including a plurality of biphasic pulses, each biphasic pulse of the plurality of biphasic pulses including a positive pulse, a negative pulse, and an inter-phase delay separating the positive pulse and the negative pulse. In some embodiments, successive biphasic pulses of the plurality of biphasic pulses can be separated by a pulse-to-pulse delay such that the plurality of biphasic pulses is separated by a plurality of pulse-to-pulse delays, and the plurality of pulse-to-pulse delays can include increasing or decreasing sequences of pulse-to-pulse delays.

The invention relates to the technical field of medical information management, and discloses a skin soft tissue dilatation water injection period intelligent management system and method, and the system comprises a data collection module which obtains a patient shot image, a symptom self-report and a compliance record, and calls electronic medical record information; the feature extraction module is used for extracting expansion region features and skin features of the shot image, generating expansion change trend features and skin evolution state features in combination with historical expansion region features and historical skin features, and obtaining dynamic features; the risk prediction module integrates the dynamic characteristics, the symptom self-report, the compliance record and the electronic medical record information, and outputs a risk level through a complication risk prediction model; and the intelligent decision-making module is used for generating a personalized intervention scheme based on the risk level and a preset clinical rule base. The method can solve the problems that the patient in the water injection period of the skin soft tissue dilatation is insufficient in out-of-hospital monitoring, medical staff cannot continuously and objectively perceive dynamic changes and the like, and the complication risk prediction accuracy and efficiency are improved.

The invention discloses a soft tissue constitutive parameter calibration method in a soft tissue-skeleton bird body model for bird strike simulation, and the method comprises the construction of a soft tissue-skeleton bird body finite element model and finite element reverse analysis based on flat bird strike. Dividing wing bones, leg bones and head and neck parts in the bones of the bird body into hexahedral unit grids, dividing wishbones, pecking bones, fossil protrusions and ribs into shell units, and dividing soft tissues into SPH particles; further obtaining bone elastic-plastic constitutive parameters through a static compression test, and endowing the bone units with the bone elastic-plastic constitutive parameters; an objective function is set as a mean square error between a flat plate center point pressure-time curve obtained by a real bird body impact flat plate test and corresponding curve data calculated by soft tissue-skeleton bird body impact flat plate finite element simulation, and soft tissue constitutive model parameters are inversely calibrated by adopting a genetic algorithm; and model and material parameter support is provided for bird strike simulation of a high-fidelity aircraft structure.

An assembly for preparing bone stock includes a shell (52) comprising a base (54) having a support surface (56), and a lid (58). The base and lid have a void space (60) therebetween. A carriage (62) is disposed at least partially within the void space, and moveable across the support surface. The carriage comprises a wall (64), at least a portion (65) of which is resiliently deformable. The wall cooperates with the base to define a preparation chamber (66), and a removal element (68) configured to remove soft tissue from the bone stock is disposed at least partially therein. The resilient portion of the wall is configured to deform when bone stock is positioned between the removal element and the wall. The carriage is configured to receive power from a drive train to actuate movement of the carriage across the support surface, and the removal element is also configured to receive power from the drive train.

The invention discloses a deep learning algorithm-based spinal MRI precise synthesis CT image processing system and method for central axis type spinal arthritis, and the system comprises a data obtaining unit which is used for obtaining a three-dimensional T1 weighted multi-gradient echo sequence, a T2 weighted sequence and a water-fat separation sequence which are obtained through the magnetic resonance imaging of the spinal column of a target user; the spatial registration unit is used for inputting the multi-sequence data into a deformable registration network so as to carry out spatial registration on the multi-modal features; the feature processing unit is used for carrying out feature fusion on the registered multi-modal features and carrying out double-domain splitting based on an anatomical attention gating mechanism to obtain skeleton features and soft tissue features; and the image fusion unit is used for synthesizing a synthesized CT image with an HU value corresponding to the spine of the target user based on the skeleton features and the soft tissue features, so that radiation-free high-precision CT image acquisition is realized, the diagnosis grading requirement on the axis type spine joint in the spine can be met, and the influence of radiation on the target user can be reduced.

Devices, systems, and methods for predicting palatal geometry are provided. In some embodiments, a system for predicting an anatomy of a patient's palate includes one or more processors and a memory operably coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the system to perform operations including accessing a first digital representation including an initial geometry of soft tissue corresponding to a patient's palate, determining an initial geometry of hard tissue of the patient's palate, predicting a change in the hard tissue during a treatment, using the predicted change in the hard tissue to predict a change in the soft tissue during the treatment, and outputting a second digital representation including a predicted geometry of the patient's palate at a future treatment stage of a treatment plan, based on the predicted change in the soft tissue.

The invention relates to the technical field of functional composite probe material preparation, in particular to a three-core spinning technology-based bio-compatible gel probe and a preparation method thereof, and the three-core spinning technology-based bio-compatible gel probe comprises a composite skin layer and three functional core layers; the composite skin layer is composed of a sodium alginate-polydopamine-chitosan grafted copolymer in a mass ratio of 2: 1: 0.5, and contains # imgabs 0 # chondroitin sulfate and # imgabs 1 # polyoxyethylene; the three core layers are respectively a carbon nanotube-polyaniline # imgabs2 # hybrid material, a graphene-polypyrrole-boron nitride hybrid material and a # imgabs3 # polythiophene-hydroxyapatite hybrid material, and the mass ratio of the carbon material to the conductive polymer to the newly added nano material in each core layer is 1: 2: 0.3; and the diameter ratio of the skin layer to the three core layers is 1: 0.28: 0.22: 0.17. According to the invention, multichannel signal transmission is realized, the impedance is reduced by the hybrid material, and the conductivity is improved; the composite skin layer is matched with soft tissue mechanical properties, and interface bonding is stable; and the biocompatible component reduces inflammation, is suitable for acquiring nerve electrophysiological signals, and is easy for large-scale production.

The invention relates to the field of oral clinical orthodontics, and discloses a method for generating an oral correction scheme, comprising: acquiring a face composite model of an initial state of a patient, the face composite model comprising a dental jaw portion and a soft tissue portion; respectively obtaining P correction schemes of the patient, wherein each correction scheme corresponds to a target state of tooth jaw movement; correspondingly obtaining face prediction models of P target states according to the tooth jaw movement and deformation face composite models of the P correction schemes; and in the P correction schemes, selecting an optimal correction scheme as a target correction scheme according to evaluation of the face prediction model in the target state. The invention further discloses electronic equipment and a storage medium, the orthodontic scheme is determined by predicting the appearance, the predicted result is closer to the real effect after orthodontic treatment, more bases are provided for the patient to select the orthodontic scheme, the patient can conveniently determine the ideal orthodontic scheme from the face expression, and a more preferable orthodontic scheme is generated.

The invention discloses a liver tumor image real-time segmentation method and system based on a YOLO algorithm, and the method comprises the steps: obtaining CT images and MRI images, and calculating the contrast indexes and signal-to-noise ratio indexes of a plurality of CT images; preprocessing the CT image, and dynamically adjusting an image enhancement strategy; a residual attention module is added on the basis of the YOLOv8 network, a multi-scale mask branch is introduced, and an optimized YOLO-Med segmentation network is constructed; inputting the enhanced CT image into a segmentation network, and training the segmentation network in combination with a loss function; and when an MRI image is input, through a multi-modal feature fusion mechanism, features of the MRI image and the enhanced CT image are aligned and fused and then are input into the segmentation network, and the segmentation network outputs a pixel-level segmentation mask for real-time segmentation of the liver and the tumor. According to the invention, by fusing the density characteristic of CT and the soft tissue resolution capability of MRI, the small tumor (diameter lt; 5 mm).