83 results about "Coronal plane" patented technology

The present invention relates to the technical field of stomatology. Provided is an auxiliary dental implant generation method based on a diffusion model. The method in the present invention comprises: acquiring oral CBCT image data of historical patients, preprocessing the oral CBCT image data of the historical patients to obtain a CBCT image dataset, using the CBCT image dataset to train a multi-task segmentation network, and using the segmentation network to obtain an intraoral tissue segmentation result; using the intraoral tissue segmentation result to train detection networks from the three dimensions of a cross-sectional plane, a coronal plane and a sagittal plane, respectively; using the detection networks to obtain detection results in the three directions of the cross-sectional plane, the coronal plane and the sagittal plane; fusing the detection results in the three directions of the cross-sectional plane, the coronal plane and the sagittal plane, and using a majority voting algorithm to construct a three-dimensional bounding box, so as to acquire an edentulous area; and using the intraoral segmentation result and the edentulous area as prompt information to guide, by means of an iterative process, a network to generate a post-implantation effect. The implantation effect obtained by the present invention is highly accurate, thereby providing a more precise auxiliary tool for stomatology.

The invention relates to the technical field of robots, and discloses an electro-hydraulic hybrid driving and driven humanoid robot lower limb and waist assembly which serves as a connection foundation of lower limbs and a robot trunk. The near ends of the thigh assemblies are connected with the waist assembly through hip joints; the near end of the shank assembly is connected with the far end of the thigh assembly through a knee joint; the foot component is connected with the far end of the shank component through an ankle joint; the hip joint is provided with three rotational degrees of freedom, the knee joint is provided with one rotational degree of freedom, and the ankle joint is provided with two rotational degrees of freedom; the rotational degree of freedom of each joint in a sagittal plane is driven by an active hydraulic actuator and a passive hydraulic actuator; the rotational degree of freedom of each joint in a horizontal plane and a coronal plane is driven by a motor joint module; the advantages of electric drive and hydraulic drive are brought into full play, and the problems of high power consumption in the negative work stage, complex traditional hydraulic drive pipelines and the like are solved by adopting an active and passive combined distributed hydraulic drive technology.

The invention provides a knee joint dyskinesia function evaluation method and system. The method comprises the following steps: by collecting lower limb kinematics parameters, plantar pressure distribution data and gait rhythm parameter groups of a subject in a standard gait test, generating a knee joint motion trail map comprising sagittal plane, coronal plane and rotation trail components, dividing a dynamic phase window based on the gait rhythm parameters, calculating a fluctuation feature vector of a sagittal plane track component, performing nonlinear decomposition on a coronal plane and a rotation track component to separate an adduction and abduction motion principal component and a rotation coupling component, constructing a joint stability quantitative index, and performing dynamic space registration on a bilateral knee joint track map to obtain a joint stability quantitative index; and calculating a three-dimensional trajectory similarity weight matrix, and calculating a dynamic symmetry index in combination with the cross-side difference coefficient of the joint stability quantitative index. According to the technical scheme provided by the invention, a scientific basis is provided for personalized rehabilitation treatment.

The invention relates to a PET / CT (positron emission tomography / computed tomography) image breathing motion artifact correction method based on a triple subgroup convolutional network, and belongs to the field of nuclear medicine imaging. The invention provides a lightweight triple-subgroup convolution kernel, and the convolution kernel focuses on analyzing the rotation and translation characteristics of coronal planes, sagittal planes and cross sections closely related to PET / CT images so as to realize efficient detail analysis under the condition of clinical small samples. And then, a Transform-subgroup convolution fusion encoder and a pyramid network are constructed in combination, a constructed triple subgroup convolution registration network can combine sub-deformation fields of multiple dimensions to obtain a smooth deformation field, and the deformation field is used for spatial distortion transformation to achieve the purpose of artifact correction. According to the method, artifact correction experiment comparison is carried out by using pixel body membrane simulation data and clinical data, the superiority of the method in the aspects of robustness and generalization ability is proved, and the quality of PET / CT images is effectively improved.

The invention belongs to the technical field of robots, and provides a hip joint exoskeleton and a walking assistance control method.The hip joint exoskeleton comprises three active driving units, and a hip joint exoskeleton sagittal plane driving unit is used for achieving forward flexion / backward extension of a human hip joint; the hip joint exoskeleton coronal plane driving unit is used for realizing human hip joint adduction / abduction; the hip joint exoskeleton horizontal plane driving unit is used for realizing inward rotation / outward rotation of the hip joint of the human body; the hip joint exoskeleton sagittal plane driving unit, the hip joint exoskeleton coronal plane driving unit and the hip joint exoskeleton horizontal plane driving unit are connected through the remote rotating center mechanism, so that a rotating plane corresponding to the horizontal plane driving unit is aligned with a hip joint rotating center through a virtual axis. The hip joint exoskeleton is compact in structure and saves space. According to the control method, when the user wears the exoskeleton to walk, the exoskeleton can accurately assist the walking of the user without time delay.

The application belongs to the field of medical instrument imaging diagnosis equipment quality detection, and particularly relates to a phantom and a method for coronal plane transmission detection of a three-dimensional ultrasonic imaging device. The phantom comprises: an upper panel, an acoustic window, a target group, and an aggregate formed by background ultrasonic tissue simulation material. The upper panel is located above the acoustic window, and the upper panel and the acoustic window form an inner cavity after being connected. The target group and the aggregate formed by the background ultrasonic tissue simulation material are located in the inner cavity. When the coronal plane transmission imaging performance is detected, the phantom is suspended in the imaging area of a hemispherical ultrasonic array, and a degassed water body is also contained in the imaging area. Each target in the target group extends along the vertical direction and is perpendicular to the coronal plane of the breast to be imaged. In this way, the convenience and accuracy of the coronal plane transmission imaging performance detection are improved, and the utility is good.

This invention discloses a method for preparing a simulated heart model and the simulated heart model itself. The method for preparing the simulated heart model includes: dividing a digital heart model into two parts along its coronal plane; preparing corresponding molding molds according to the structural characteristics of the two parts, each molding mold including an outer molding mold and an inner cavity molding mold; applying silicone to the molding surfaces of the outer molding mold and the inner cavity molding mold to form the endocardium and epicardium; applying silicone to the portion of the inner cavity molding mold used for molding the valve to form the valve; assembling the outer molding mold and the inner cavity molding mold to form a cavity; sequentially injecting silicone of corresponding hardness into the regions of the cavity used for molding the atrial myocardium, interatrial septal myocardium, ventricular myocardium, and interventricular septal myocardium to form heart model halves; and bonding the heart model halves corresponding to the two molding molds together to obtain the simulated heart model.

This invention discloses a method for evaluating the scanning depth of breast ABUS images, belonging to the field of breast ABUS image technology. The method includes: S1: collecting three-dimensional DICOM data of breast ultrasound, annotating the ribs in the coronal images, and evaluating the scanning depth; S2: performing coronal slice processing and converting and generating model labels; S3: detecting the rib region based on a target detection architecture, and training a rib detection model capable of automatically locating the rib region in the image; S4: testing and evaluating the rib detection model; S5: establishing scanning depth judgment rules based on the number and position of rib frames to determine the scanning depth category. This invention solves the problems of significant differences in image coverage, lack of reliable reference, and difficulty in quickly determining the optimal scanning depth suitable for different breast sizes and shapes. This invention's automatic evaluation of ABUS image scanning depth enables standardization of ultrasound screening.

A method for using anatomical landmarks of a balance organ to construct a three-dimensional cephalometric coordinate system includes acquiring a CT image of a craniofacial region to be measured. The anatomical landmarks of the CT image are determined. On the basis thereof, a horizontal plane, and then a coronal plane and a median sagittal-plane plane are determined. The horizontal plane is a plane formed by certain of the anatomical landmarks. The coronal plane is determined using the horizontal plane and anatomical landmarks, and the median sagittal plane is determined using an anatomical landmark and both the horizontal and coronal. An intersection point of the three planes is used as the origin of a three-dimensional cephalometric coordinate system.

The application relates to the technical field of behavior feature recognition, and discloses an anti-crosstalk biological rehabilitation electrical signal safety control method and system in a high-density scene. The method comprises the following steps: calculating a bilateral average distance according to an environmental distance; calculating a surface electromyogram signal root mean square value according to an electromyogram original signal; analyzing a pelvis tilt angle standard deviation according to the pelvis tilt angle; calculating a hip joint adduction auxiliary torque according to the surface electromyogram signal root mean square value and a gait phase; calculating a hip joint coronal plane impedance value according to the gait phase and the pelvis tilt angle; calculating an intention state according to the surface electromyogram signal root mean square value, the pelvis tilt angle and a channel state; calculating a hip joint driving torque according to the hip joint adduction auxiliary torque and the hip joint coronal plane impedance value; and calculating a system mode according to the bilateral average distance, the surface electromyogram signal root mean square value and the pelvis tilt angle standard deviation. The application improves the lower limb rehabilitation training efficiency by adaptively adjusting the gait.

The invention discloses a fitting type adjustable gasket device for wedge-shaped high tibia osteotomy with an inner opening. The fitting type adjustable gasket device comprises an upper cover, a floating cover, a double-side different-curve cam, a worm gear-worm transmission pair and a base, the worm gear is driven by rotating the worm, and then the double-side different-curve cams are driven to rotate synchronously. The double-side different-curve cam is unique in design, and the curved surfaces of the cams on the two sides of the double-side different-curve cam have specific curvature radius difference. In the rotation process of the cam, the curvature radius difference is utilized to accurately drive the floating cover to stably lift in the vertical direction, and meanwhile, the floating cover can controllably rotate around a coronal shaft. The combined movement mechanism enables the device to accurately generate the required coronal plane angle beta at one time in the operation. By means of the design, accurate adjustment of the angle is achieved, more importantly, large-area and uniform face-face contact can be effectively promoted to be formed between the osteotomy face and the floating cover, and therefore the supporting stability is remarkably improved, the risk of bone face collapse caused by local stress concentration is thoroughly eliminated, and reliable structural support is provided for postoperative recovery.

The application provides a coronary artery calcification score calculation method and device, electronic equipment and a storage medium. The calculation method comprises: acquiring a plurality of 2D coronal plane CT images determined according to a 3D coronary artery plain CT image of a patient; for each 2D coronal plane CT image, inputting the 2D coronal plane CT image into a pre-constructed calcification classification model to determine calcification regions included in the image and coronary artery vessel type labels of each calcification region; performing matrix multiplication on the image corresponding to the determined calcification region and the 2D coronal plane CT image to determine a vessel calcification plaque including only the coronary artery vessel type label; performing calcification score calculation on the vessel calcification plaque including only the coronary artery vessel type label determined for each 2D coronal plane CT image to determine the total coronary artery calcification score of the patient. In this way, the coronary artery calcification score calculation based on the plain CT can be automatically and quickly and accurately completed.

A method for generating a reference system for kinematic alignment is performed by acquiring a 3D model of a patient's femur at a pre-operative stage and selecting a plurality of points on the anterior cortex (11C) of a distal end (10) of the femur, on a distal superficial portion of each condyle (11 A, 11 B), and on a posterior superficial portion of each condyle (11 A, 11 B). A provisional coronal plane (CP-CP) passing through the 3 reference points (12) and, for each condyle (11 A, 11 B), a distal approximating surface (15) and a posterior approximating surface (16) are then generated as a function of these points. The approximating surfaces are used to generate an axial plane (A-A) perpendicular to the provisional coronal plane (CP-CP), facing the distal superficial portions and tangent to each distal approximating surface (15) and a final coronal plane (C-C) perpendicular to the axial plane (A-A), facing the posterior superficial portions and tangent to each posterior approximating surface (16). The reference system is defined by the axial plane (A-A) and the final coronal plane (C-C).

The invention discloses a multi-anatomical structure space mapping method and system based on a medical image and a three-dimensional model, and relates to the technical field of medical image processing, and the method comprises the following steps: S1, obtaining a medical image data sequence according with a DICOM standard, analyzing and extracting DICOM header file information, automatically constructing a display interface of a multi-plane two-dimensional medical image view, and displaying the display interface of the multi-plane two-dimensional medical image view; the display interface at least comprises an axial plane view, a sagittal plane view and a coronal plane view which are mutually orthogonal; the external three-dimensional model is accurately aligned to the internal anatomical space of the patient by adopting the mapping and registering technology of the DICOM space information and the three-dimensional model in the general three-dimensional format, namely seamless loading and management of the medical image data and the general three-dimensional model in a unified platform are realized; and spatial alignment between three-dimensional models and medical images of different data sources is realized, so that the efficiency of consistent linkage display between a three-dimensional space and a two-dimensional section is greatly enhanced.

The invention provides radiotherapy equipment, a calibration die body and a positioning lamp calibration method. The radiotherapy equipment comprises an annular rack, three positioning lamps and support assemblies in one-to-one correspondence with the positioning lamps. The three sets of support assemblies are arranged in the circumferential direction of the annular rack at intervals, and each positioning lamp is arranged on the corresponding support assembly and is adjustable in posture. The postures of the three positioning lamps meet the condition that one positioning lamp emits a positioning light beam corresponding to the sagittal plane of the human body, and the other two positioning lamps are oppositely arranged and respectively emit two positioning light beams which are perpendicular to each other and correspond to the cross section and the coronal plane of the human body one to one; and positioning light beams emitted by the three positioning lamps are intersected at a set virtual isocenter. According to the radiotherapy equipment, the positioning lamp is directly arranged on the annular rack of the radiotherapy equipment, so that the distance between the positioning lamp and the virtual isocenter is reduced, the moving distance of a user can be reduced in the process of debugging and calibrating the positioning lamp by the user, and the debugging and calibrating efficiency of the positioning lamp is improved.

The invention discloses a personalized spine orthopedic pillow based on ergonomics and a using method thereof, and belongs to the technical field of medical auxiliary instruments. Based on the ergonomic design, the adaptation degree of the orthopedic pillow with the head and the neck and chest of the patient is improved; through a neck-chest combined biomechanical overall model, collaborative correction of cervical retrobow and scoliosis is achieved, and recovery of overall mechanical balance of the spine is promoted. The pressure value of the air bag in the orthopedic pillow can be quantitatively set according to the individual characteristics of the patient, the personalized correction requirements of different patients are met, and the comfort of the patient is improved. Through the combination of a cervical vertebra-thoracic vertebra biomechanical model, acting forces including supporting force acting on the cervical vertebra, coronal plane pressure acting on the thoracic vertebra scoliosis area and horizontal plane rotation removing force are applied to the cervical vertebra reverse arching area and the thoracic vertebra scoliosis area of a patient. Cooperative correction of cervical vertebra reverse arching and thoracic vertebra lateral bending is achieved, so that recovery of overall mechanical balance of the spine is facilitated, and the stability and the curative effect of spine malformation correction are improved.

The application discloses a gait real-time analysis method and system based on visual skeleton feature extraction, which comprises the following steps: collecting a user walking video through a single camera; extracting human key skeleton points in real time by using a lightweight AI model; calculating anatomical coronal plane, sagittal plane parameters and gait space-time parameters based on the skeleton point coordinates; superimposing the skeleton and parameters on the video in real time and providing voice feedback; starting and stopping through a gesture recognition non-contact control system; automatically storing data and generating a rehabilitation report; the system comprises a USB camera, an embedded processing end and a feedback end with display and audio; the application replaces expensive motion capture equipment with a low-cost single camera, realizes objective quantitative evaluation of gait training, real-time multi-modal feedback and automatic management, significantly reduces medical costs, improves the efficiency and effect of rehabilitation training, and is especially suitable for primary medical institutions.

The invention relates to the technical field of puncture path planning, in particular to a puncture path planning method for abdominal puncture drainage of severe acute pancreatitis. Firstly, a CT image and an MRI image are fused to construct an abdominal cavity three-dimensional model, tissue areas (an organ area, a blood vessel area and a focus area) are obtained through segmentation, and candidate paths are generated based on a target position and a preset body surface approach point; then, calculating a risk coefficient based on geometric features (including an included angle, a length and proximity to a tissue region) of the candidate path, and screening a preliminary optimal path; determining a puncture body position and a gravity component direction by combining a sagittal plane / coronal plane position relationship, analyzing tissue density distribution, and quantifying a tissue deformation interference index; finally, the risk coefficient and the deformation index are fused, re-screening of the paths is achieved, the optimal and alternative paths are determined, and therefore key tissue structures can be effectively avoided, the intraoperative displacement risk is reduced, and puncture accuracy and stability are improved.

Enhanced ultrasound imaging apparatus and associated methods of work flow are disclosed herein. In one embodiment, a method of ultrasound scanning includes receiving a first dataset representing ultrasonic scanning of a target anatomy of a patient in a two-dimensional mode and generating a two-dimensional ultrasound image of the scanned target anatomy based on the received first dataset. The method also includes accepting a definition of at least one of a sagittal plane, a transverse plane, and a coronal plane on the displayed two-dimensional ultrasound image. Thereafter, a second dataset representing ultrasonic scanning of the target anatomy in a three-dimensional mode is received and an ultrasound image at the coronal plane of the target anatomy is generated based on (1) the three-dimensional scanning and (2) the accepted definition of at least one of the sagittal plane, the transverse plane, and the coronal plane.

The invention relates to a method for measuring an alveolar bone of a missing tooth, which comprises the following steps of: a, controlling a sagittal axis to coincide with a central connecting line of cross sections of two adjacent teeth of the missing tooth on an axial plane, controlling a vertical axis to coincide with a connecting line of adjacent glaze cementum boundaries of the adjacent teeth on a sagittal plane, and controlling the sagittal axis to coincide with a tooth long axis of the adjacent teeth on a coronal plane, the coronal axis is controlled to coincide with the perpendicular line of the midpoint of the connecting line of the glaze cementum boundary of the adjacent tooth on the axial surface or the sagittal surface, the obtained coronal plane is determined as a measuring plane, and the sagittal axis, the perpendicular axis and the coronal axis are always kept in a mutually perpendicular state; and b, obtaining the width and height of the alveolar ridge of the missing tooth based on the measurement plane in the step a. The method for measuring the alveolar bone of the missing tooth has the advantages of being accurate in fixed point, small in measurement result difference, good in stability and high in repeatability.

The invention provides a multi-modal image processing method and device and electronic equipment, and can be applied to the technical field of medical image processing. The method comprises the following steps: based on a coronal plane segmentation image and a sagittal plane segmentation image which represent the current state of a target object, performing pose conversion on an intermediate conversion segmentation image which represents the historical moment state of the target object to obtain a target registration segmentation image which represents the current state of the target object, the intermediate conversion segmentation image is determined by the following steps: based on the first magnetic resonance segmentation image, performing three-dimensional pixel point mapping on the second magnetic resonance segmentation image to obtain an initial conversion segmentation image mapped to the space coordinates of the first magnetic resonance segmentation image; and based on the three-dimensional radiography segmented image, performing three-dimensional pixel point mapping on the initial conversion segmented image to obtain an intermediate conversion segmented image mapped to the space coordinates of the three-dimensional radiography segmented image.

Expandable intervertebral fusion implants, system, and methods for coronal correction. The implant may include top and bottom endplates configured to engage adjacent vertebrae, a dual actuator assembly including a rotatable drive screw actuator and a rotatable actuator nut concentric to the drive screw actuator, and driving ramps positioned along the shaft of the drive screw actuator and engaged with the top and bottom endplates via complementary ramped surfaces. When inserted in a disc space, the implant has an ipsilateral side and a contralateral side, and rotation of the drive screw actuator and / or the actuator nut causes movement of one or more of the driving ramps, thereby causing independent expansion in height of the contralateral and / or ipsilateral sides of the implant to correct the coronal deformity.

The utility model relates to the technical field of medical instruments, in particular to a thighbone greater trochanter fixator which comprises an embracing device and a fixing plate detachably arranged on one side of the embracing device. Wherein the fixing plate comprises a claw hook part, an upper fixing plate and a lower fixing plate; the claw hook part comprises two claw hooks fixedly arranged on the two sides of one end of the upper fixing plate respectively and a screw gasket fixedly arranged between the two claw hooks, and a through hole allowing a screw to pass through is formed in the screw gasket in the thickness direction. The claw hook part, the upper fixing plate and the lower fixing plate are matched with the longitudinal radian of the outer side wall of the thighbone greater trochanter; wherein the front and rear arm plates on the fixing plate are customized according to the radian of the outer side wall of the greater trochanter in the front-back direction, the arm plates can be tightly attached to the front and rear bone surfaces, particularly wrap and cover the coronal plane fracture of the rear wall of the greater trochanter, and screws are implanted into screw holes for fixing; and the embracing apparatus and the fixing plate cooperate, so that the reliability of overall fixation is further enhanced, the convenience of the operation is improved, and the operation risk of the patient is reduced.

The invention discloses a mammary gland ultrasound image splicing method and device, equipment, a medium and a product, and relates to the field of image processing, and the method comprises the steps: obtaining a resampling image based on a coronal plane image; nipple positioning is carried out according to the resampling image, and a nipple contour and nipple center coordinates are obtained; mapping the nipple contour and the nipple center coordinate to the coronal plane image to obtain a nipple center line; calculating deviation angles of different body positions relative to the median position according to the direction vector of the center line of the nipple; determining a splicing reference point of all coronal plane images in each body position according to an intersection point of the center line of the nipple and the coronal plane section frame number of the coronal plane images; calculating and removing overlapping areas of coronal plane images and median images of different body positions according to the splicing datum points; and performing longitudinal offset compensation according to the offset angle and the coronal plane image of which the overlapping region is removed, and then performing splicing to obtain a panoramic image of the mammary gland. According to the method, rapid, non-repeated and smooth splicing of the breast ultrasound images can be realized.

The invention discloses a redundant degree-of-freedom endoscope-holding auxiliary robot, belongs to the technical field of auxiliary operation instruments for medical surgical operations, and aims to solve the problems that an existing endoscope-holding auxiliary robot is insufficient in degree of freedom and poor in movement flexibility. A multi-degree-of-freedom coronal plane adjusting unit is rotationally connected to the execution end of the multi-degree-of-freedom sagittal plane adjusting unit and can be driven by the multi-degree-of-freedom sagittal plane adjusting unit to adjust working poses in a sagittal plane parallel to a human body; an endoscope clamping unit is rotationally connected to the executing end of the multi-degree-of-freedom coronal plane adjusting unit, and the multi-degree-of-freedom coronal plane adjusting unit can drive the endoscope clamping unit to adjust the working posture in a coronal plane parallel to the human body. The clamping end of the endoscope clamping unit is rotationally connected with an endoscope and drives the endoscope to circumferentially rotate around the axis of the endoscope. The invention is used as an auxiliary operating instrument of an endoscope in a medical surgical operation.

The present application relates to a kind of ankle joint prosthesis and ankle joint prosthesis system, the ankle joint prosthesis includes: tibial prosthesis, sliding core prosthesis and talus prosthesis, the sliding core prosthesis is arranged between the tibial prosthesis and the talus prosthesis, the sliding core prosthesis has concave spherical surface, the talus prosthesis has convex spherical surface, the convex spherical surface and the concave spherical surface sliding fit, in the projection parallel to the sagittal plane of the ankle joint prosthesis, the midpoint of the line of the front end of the tibial prosthesis and the rear end of the tibial prosthesis is P1, in the front-rear direction of the ankle joint prosthesis, the first coronal plane F1 passing through the center of the convex spherical surface has preset interval with P1, and the P1 is located in the rear side of the first coronal plane F1.The structure of the ankle joint prosthesis of the present application is stable after implantation, stress is uniform, can slow down prosthesis wear, is beneficial to patient postoperative recovery.

This application relates to the field of medical device testing technology, specifically a phantom and method for coronal plane reflection detection in a three-dimensional imaging device. The phantom includes: a top panel and a sealed space inside the acoustic window filled with a background tissue-like material; target lines embedded in the background tissue-like material; an acoustic window, a window for ultrasonic wave transmission, simulating the acoustic characteristics of human epidermal tissue; the background tissue-like material is a water-based polymer gel-based composite material; target lines, with their upper ends fixed in openings in the top panel and their lower ends free; used for quantitative measurement of imaging parameters in the coronal plane, where the coronal plane is a plane parallel to the horizontal plane when the human body is prone on the three-dimensional ultrasound imaging device; the imaging parameters include the lateral linearity, longitudinal linearity, axial image resolution, and lateral image resolution of the reflected image in the coronal plane; the center-to-center distance between two adjacent target lines is a predetermined distance; the predetermined distance is determined by the resolution of the three-dimensional ultrasound imaging device at the corresponding position in the coronal plane.

This application discloses a hybrid self-supervised learning method for determining the malignancy of a single pulmonary nodule based on CT images. The method includes: inputting a horizontal plane image of the pulmonary lesion into an encoder for feature extraction, obtaining a horizontal plane feature vector of the lesion; inputting a coronal plane image of the pulmonary lesion into a momentum encoder for feature extraction, obtaining a coronal plane feature vector of the lesion, and storing it in a dynamic dictionary; reconstructing the occluded portion of the horizontal plane image using the horizontal plane feature vector and the decoder to obtain a target image; calculating a loss value based on the horizontal plane feature vector, the coronal plane feature vectors in the dynamic dictionary, and the target image; and iteratively training the encoder, momentum encoder, and decoder together according to the loss value until preset conditions are met, thus constructing a preset classification model for pulmonary granulomatous nodules and solid pulmonary adenocarcinoma. This application can distinguish between a single atypical pulmonary granulomatous nodule and solid pulmonary adenocarcinoma.

The present disclosure relates to the technical field of beauty devices, and provides a skin care device, comprising: a left mask body; a right mask body; a nasal hanging component, the left mask body being connected to a first side of the nasal hanging component, and the right mask body being connected to a second side of the nasal hanging component; and physiotherapy components, arranged on inner surfaces of the left mask body and the right mask body. When the skin care device is in a wearing state, relative to a projection plane parallel to a coronal plane of a user, defining that the lowest point of the left mask body is point c1, the lowest point of the right mask body is point c2, the lowest point of the middle of the nasal hanging component is point o, and the included angle between line segments oc1 and oc2 is θ, θ is in a range of 55°-65°. By means of configuring the included angle between the lowest points of the left mask body, the right mask body, and a nose hanging assembly in the range of 55°-65°, the left mask body and the right mask body can effectively cover the muscle group in front of the cheekbone, and the physiotherapy components can provide accurate care for these specific areas and can effectively treat nasolabial folds according to the characteristics of the nasolabial folds, thereby effectively reducing the appearance of nasolabial folds.

A system for aligning vertebrae to correct spinal deformities, comprising two transverse arms translating on two elongate bodies coupled by a gear pair mounted on a center body with revolute joints and ratchet units. The transverse arms and center body are connected to one side of the spine with three telescopic arms using three end-effectors. Auxiliary arms and end-effectors are available to connect the system to the other side of the spine. Coronal plane deformity is corrected by manipulating the angle between the elongate bodies with two manipulating handles to translate the apex of the spinal curve toward the midline of the patient; adjusting the lengths of the telescopic and auxiliary arms to correct the sagittal and transverse plane deformities. The end-effector positions are locked by engaging the ratchet units to keep the achieved corrections while the spinal rods are fixed on the spine through bone-implants.