75 results about "Cone beam ct" patented technology

The invention discloses an intelligent eye control bonding system and method for an orthodontic appliance, and relates to the technical field of intelligent oral medical equipment. Comprising a pupil eye-control image positioning module, a bracket initial coordinate is generated through doctor pupil trajectory tracking and doctor head dynamic compensation, a patient three-dimensional oral cavity model is combined for mapping, a three-dimensional visual interface is constructed by integrating oral scanning instrument and cone beam CT data, and the three-dimensional visual interface is projected to an entity tooth surface through a laser positioning projection device. And the dynamic tracking module corrects the posture of the bracket in real time through rigid compensation and elastic compensation based on inertial sensing data. The path planning and control module adopts an improved RRT *-Connect algorithm, and an elastic map and an impedance-admittance hybrid control strategy are fused to optimize a motion path. And the mechanical arm execution module adopts a modular six-axis framework, integrates a triple-combination driving system and a double-cavity end effector, and completes submillimeter-level bonding operation in an oral cavity limited space. The positioning precision and the bonding efficiency of the bracket are improved.

The invention discloses a jaw cystic lesion recognition method, device and equipment, a medium and a product, and relates to the field of jaw cystic lesions. The method comprises the following steps: marking tooth and jaw regions in an oral cavity cone beam CT image, and selecting a region of interest to obtain an interested marked image; labeling cyst category labels generated by jaw cystic lesions in the interested labeling images, and forming a training set; constructing a deep learning model introducing an attention mechanism; the attention mechanism introduces relative positions of cysts and teeth as interested features; training a deep learning model by using the training set to obtain a jaw cystic lesion recognition model; and marking tooth and jaw regions in a to-be-identified oral cavity cone beam CT image of the patient with the jaw cystic lesion, inputting the marked image of interest after marking the tooth and jaw regions into the jaw cystic lesion identification model, and outputting the cyst category of the patient with the jaw cystic lesion. The accuracy and efficiency of jaw cystic lesion diagnosis can be improved.

The invention relates to a cone beam CT imaging scanning parameter determination method and imaging equipment, and the method comprises the steps: designing an optimization model for a microgravity environment, carrying out the optimization processing of the cone beam CT imaging scanning parameters based on a pre-constructed optimization model with the maximum imaging performance as a target, and obtaining the optimal parameters of the cone beam CT imaging. Wherein optimization problem modeling and solving are sequentially carried out in a projection domain and an image domain so as to obtain target scanning parameters meeting constraint conditions, and according to the technical scheme of the invention, aiming at factors such as scanning space and energy consumption in space, requirements of high spatial resolution, compact physical size of equipment, high image quality and low scanning dose are met, and the method and the device have the advantages of being high in efficiency and high in reliability. The method is applied to cone beam CT imaging in the space microgravity environment, and the comprehensive requirements of scientific research, health guarantee and medical service in the space environment are met.

The invention provides a cervical cancer self-adaptive radiotherapy assessment decision method and device, and relates to the technical field of medical artificial intelligence, and the method comprises the steps: obtaining a cone beam CT image and a plan CT image before radiotherapy of a patient to be subjected to radiotherapy on the day of radiotherapy, and extracting the structural quantitative features of the images; the method comprises the following steps: calculating a difference value of structured quantitative characteristics between a cone beam CT image on the day of radiotherapy and a plan CT image before radiotherapy to obtain multi-dimensional geometric change characteristics; and inputting the multi-dimensional geometric change features, the vectorized representation of the predetermined key region of the cone beam CT image and the clinical text information into a pre-trained clinical large language model, and outputting a self-adaptive radiotherapy demand tag. The problem that the prior art depends on manual analysis, and it is difficult to compare the change characteristics of the CT image between the radiotherapy day and the plan before radiotherapy to automatically analyze whether self-adaptive radiotherapy is executed on the radiotherapy day is solved.

The invention discloses a orthognathic surgery robot system, which comprises a multi-modal data fusion module, a cone beam CT (Computed Tomography) and intraoral scanning are integrated, a high-resolution three-dimensional bony structure image is acquired through the cone beam CT to reconstruct a three-dimensional anatomical model of maxillofacial skeletons, submillimeter details of tooth surfaces and occlusal relationships are captured through the intraoral scanning, and the submillimeter details of the tooth surfaces and occlusal relationships are acquired through the intraoral scanning; constructing a functional occlusion model; the navigation module is used for planning a navigation path through a preset self-adaptive path planning algorithm based on the three-dimensional anatomical model and the functional occlusion model of the maxillofacial skeleton of the target object; and the mechanical arm execution module is used for executing removal, osteotomy and fixation actions based on the navigation path. Through the multi-modal data fusion module, a personalized operation scheme can be formulated according to the specific anatomical structure and occlusal relationship of each patient.

The invention discloses a four-dimensional cone beam CT (Computed Tomography) reconstruction method based on an anatomical prior constraint diffusion model, which mainly solves the problem of poor quality of a reconstructed image in the prior art, and adopts the implementation scheme that the method comprises the following steps: acquiring CT original full-projection data of a batch of patients, and carrying out sparse sampling on the CT original full-projection data; performing data set division and reconstruction on the original full projection data and the sparse projection data to obtain a reference true value and a low-quality CT image containing a large number of artifacts; preliminarily enhancing the CT image containing a large number of artifacts by using the pre-trained ResViT network to obtain a CT image without artifacts; segmenting the CT image without artifacts by using a body segmentation network to obtain anatomical information of each organ; constructing a four-dimensional cone beam CT motion compensation reconstruction model based on anatomical prior constraints, and training and verifying the four-dimensional cone beam CT motion compensation reconstruction model; and inputting the tested data into the trained reconstruction diffusion model to obtain a reconstruction result. According to the method, artifacts of sparse cone beam CT in a specific organ area can be thoroughly eliminated, the reconstructed image is clear in details, and the method can be used for tracking and positioning tumor movement caused by respiration.

The invention provides a proton helium ion treatment device. The proton helium ion treatment device comprises an injector, an accelerator, a rotating rack, a treatment head, a beam distribution system and a six-dimensional treatment bed which are sequentially arranged in the conveying direction of a beam. The injector comprises a hydrogen ion source and a helium ion source which can be switched; the treatment head and beam distribution system comprises an integrated scanning magnet, a position ionization chamber, a dose ionization chamber, a ridge-shaped filter and a range shifter which are installed on a treatment head support and sequentially arranged in the beam conveying direction, and the integrated scanning magnet is used for beam deflection in the transverse X direction and the transverse Y direction at the same time. A cone beam CT system is further fixedly installed on the rotating rack, and precise positioning and positioning correction of a patient are achieved in combination with the six-dimensional mechanical arm treatment bed. The proton helium ion treatment device can meet the requirement for high precision of patient positioning in ion treatment, ion treatment with optional proton helium ions can be achieved, and the treatment system is more compact through the design of the integrated scanning magnet.

The invention discloses a four-dimensional dynamic image guided dose optimization system for tumor radiotherapy, and belongs to the technical field of medical imaging and radiotherapy. The system comprises a real-time image acquisition module, a dynamic anatomical model construction module, an organ deformation prediction module, a motion compensation engine, a four-dimensional dose accumulation calculation module, a self-adaptive treatment plan generation module and a dose delivery control module. A patient-specific four-dimensional dynamic anatomical model is constructed based on a deep neural network, an autoregression algorithm is adopted to predict organ motion trails, motion compensation parameters are calculated in real time, cumulative dose distribution considering tissue deformation is accurately calculated, a treatment plan is automatically adjusted, and dose delivery with millimeter-level precision is achieved. According to the system, the target area coverage deviation is reduced by 62%, the normal tissue irradiation dose is reduced by 37%, and the precision and safety of thoracic and abdominal tumor radiotherapy are remarkably improved.

Based on the traditional calibration method, a phantom method for calibrating the rotation center and SOD of the cone beam CT with high precision is provided, which is simple and efficient to improve the calibration precision of the parameters, the CT geometric parameters are calibrated by using the traditional method initially, after the calibration is completed, the steel needle phantom is used for CT scanning, image reconstruction, and the reconstructed image is post-processed, the rotation center and the distance from the ray source to the rotation center (SOD parameter) are fine-tuned, so that the imaging section of the steel needle obtained is small, the steel needle section characteristics are met, the center area is not distorted, and the distance between the steel needles meets the actual steel needle spacing.

The present invention relates to an apparatus (10) for estimation of Hounsfield unit values for voxels of a 3D cone beam CT image, the apparatus comprising: —a processing unit (20); and —an output unit (30). A 3D cone beam CT image comprises voxels with associated attenuation coefficient values. The processing unit is configured to calculate a histogram of at least some of the voxels of the 3D cone beam CT image representing a number of voxels having specific attenuation coefficient values or specific ranges of attenuation coefficient values. The processing unit is configured to identify a specific attenuation coefficient value or specific range of attenuation coefficient values associated with a first feature representative of a part of the 3D cone beam CT image, wherein the first feature is air or soft tissue or bone, and wherein the identification comprises utilization of the histogram. The processing unit is configured to determine an attenuation value to Hounsfield Unit converter, wherein the determination of the attenuation value to Hounsfield Unit converter comprises utilization of a correlation between the specific attenuation coefficient value or specific range of attenuation coefficient values associated with the first feature with a Hounsfield Unit for the first feature. The processing unit is configured to transform attenuation coefficient values of voxels in the 3D cone beam CT image to Hounsfield Units based on the attenuation value to Hounsfield Unit converter. The output unit is configured to output information relating to Hounsfield units of voxels of the 3D cone beam CT image.

The present invention relates to a device (10) for estimating Henry unit values for voxels of a 3D cone beam CT image, the device comprising: a processing unit (20); and an output unit (30). The 3D cone beam CT image includes voxels having associated attenuation coefficient values. The processing unit is configured to calculate a histogram of at least some of the voxels of the 3D cone beam CT image, the histogram representing a number of voxels having a particular attenuation coefficient value or a particular range of attenuation coefficient values. The processing unit is configured to identify a particular attenuation coefficient value or a particular range of attenuation coefficient values associated with a first feature representing a portion of the 3D cone beam CT image, where the first feature is air or soft tissue or bone, and where the identifying includes utilizing a histogram. The processing unit is configured to determine an attenuation value to a Hensi unit converter, where the determination of the attenuation value to the Hensi unit converter includes utilizing a correlation between a particular attenuation coefficient value or a particular attenuation coefficient value range associated with the first feature and a Hensi unit for the first feature. The processing unit is configured to transform attenuation coefficient values of voxels in the 3D cone beam CT image to Hunsler units based on the attenuation value-to-Hunsler unit converter. The output unit is configured to output information related to a Hensz unit of a voxel of the 3D cone beam CT image.

The application relates to a correction phantom and a correction method of a cone beam CT, and the method comprises the following steps: adjusting the pose of a correction phantom to obtain a first projection of the correction phantom; moving a detector by a first distance to obtain a second projection of the correction phantom; rotating the correction phantom by 180 degrees to obtain a third projection of the correction phantom; calculating geometric parameters according to the first projection, the second projection and the third projection; and correcting the cone beam CT according to the geometric parameters. The design of the correction phantom solves the CT system geometric deviation and the calculation error generated by placing the correction phantom in the prior art. The pose of the correction phantom is adjusted to adjust the imaging angle of the light beam and the phantom according to the projection shape of the first hole and the second hole, so that the calculation precision is improved. The multiple projections obtained by adjusting the correction phantom, the data obtained by different projections and the independent calculation of each geometric parameter can avoid the introduction of accumulated errors, and the precision of the geometric parameters is effectively improved.

The invention discloses an image reconstruction method, electronic equipment, a storage medium and a product, relates to the technical field of medical treatment, and is used for optimizing an image reconstruction effect and reducing the influence of shielding artifacts. The method comprises the following steps: acquiring a cone beam CT projection image shielded by a light beam blocking array; light beam blocking substances on the light beam blocking array are asymmetrically arranged about the first axis; the first axis is parallel to a rotating shaft of the cone beam CT and passes through a beam center in a cone beam CT projection image; reconstructing the cone beam CT projection image based on the symmetric projection points and the shadow points in the cone beam CT projection image to obtain a reconstructed image; the symmetric projection points are symmetric points of shadow points in the cone beam CT projection image.

The invention relates to a head positioning device and an oral cavity cone beam CT system, and relates to the technical field of medical instruments. The device comprises a forehead structure used for supporting the forehead of a patient and serving as a reference for connecting the device with an external frame; the supporting structure is connected to the forehead structure and used for providing vertical supporting and adjusting functions; the locking structure is mounted at the top of the supporting structure and used for applying constraining force to the head of the patient from the upper portion or the side portion; wherein the forehead gear structure, the supporting structure and the locking structure work together to achieve adjustable fixing of the head of a patient. Through cooperative work of the three parts of structures, multi-dimensional adjustment and precise fixation of the head of a patient can be achieved, pressure is effectively dispersed, local indentation and discomfort are avoided, meanwhile, the stability of a positioning reference is ensured, and the image quality is improved.

The invention relates to a geometric parameter estimation method for cone-beam CT, belongs to the technical field of cone-beam computed tomography, and solves the problems of high cost and low efficiency of a technical scheme for determining geometric parameters of cone-beam CT in the prior art. The geometric parameter estimation method comprises the following steps: extracting same preset sampling lines from projection images at all projection angles to obtain sinograms corresponding to all the preset sampling lines; determining a first transverse offset of each preset sampling line according to the sinogram corresponding to each preset sampling line, and performing linear fitting based on the first transverse offset of each preset sampling line to obtain a torsion angle of the cone beam CT; and performing rotation correction on the projection images at each projection angle by using the torsion angle of the cone beam CT, extracting a sinogram corresponding to the center line from the projection images at each projection angle after rotation correction, and taking the transverse offset of the center line as the transverse offset estimation value of the cone beam CT. And the geometric parameters of the cone beam CT can be quickly estimated.

The embodiment of the invention relates to the field of cone-beam CT imaging, and discloses a large-view-field cone-beam CT imaging method, device and equipment and a storage medium. A target is scanned around a scanning center according to a first sub-scanning path and a second sub-scanning path; in the scanning process, the main mechanical arm and the auxiliary mechanical arm drive the transmitting device and the receiving device to synchronously move, so that the center of the conical imaging beam is always perpendicular to the center of the receiving device; the first sub-scanning path comprises that the center of the transmitting device deflects for a preset angle from the center of the conical imaging beam to the scanning center to a preset direction and then rotates along a set track; the second sub-scanning path comprises that the center of the transmitting device rotates in the reverse direction of the set track after deflecting by two times of a preset angle in the reverse direction of the preset direction at the ending position of the first sub-scanning path; scanning data at the same position are combined and then subjected to back projection reconstruction, X-ray energy can be efficiently utilized without changing hardware equipment, and large-view cone beam CT imaging is achieved.

The application relates to a method, device and medium suitable for multi-energy cone beam CT projection interpolation completion. The method comprises the following steps: acquiring low-energy projection and high-energy projection of a multi-energy cone beam CT energy spectrum imaging system; performing preliminary iterative sparse reconstruction and material decomposition on the low-energy projection and the high-energy projection respectively to obtain a base material one reconstructed image and a base material two reconstructed image; performing an image enhancement operation on the base material one reconstructed image and the base material two reconstructed image respectively, then performing forward projection, and performing weighted processing by using pre-calibrated high-low energy spectrum information to obtain low-energy complete projection data and high-energy complete projection data under full viewing angle. Therefore, the image domain sparse reconstructed image is used to guide the projection domain high-low energy projection data to perform energy spectrum interpolation completion, the problem of inconsistent high-low energy projection angles of a fast kilovoltage switching energy spectrum CBCT is solved, and the image quality and material decomposition accuracy are greatly improved.

The present invention provides a multifunctional gamma knife treatment device with cone-beam CT detection. The multifunctional gamma knife treatment device with cone-beam CT detection is characterized in that the multifunctional gamma knife treatment device includes a cone-beam CT detection device and a gamma knife treatment device. The cone-beam CT detection device is arranged in front of the gamma knife treatment device. The cone-beam CT detection device includes a cone-beam CT detection frame, a head-body dual-purpose imaging tube device, and an imaging device detector. The head-body dual-purpose imaging tube device and the imaging device detector are symmetrically arranged on the cone-beam CT detection frame. The cone-beam CT detection frame includes a swivel support mechanism and a frame flip mechanism. The swivel support mechanism is flip-connected to the frame flip mechanism. By arranging the cone-beam CT detection device in front of the gamma knife treatment device and utilizing the flipping of the cone-beam CT detection device, both cone-beam CT detection and gamma knife treatment can be performed, thereby achieving multifunctional combined treatment and detection.

The present invention provides a method of matching data, which is performed by an apparatus for matching data, the method including synchronizing acquisition time points of cone beam computed tomography (CBCT) data and 3D scan data, conforming coordinate systems of the CBCT data and the 3D scan data, constructing a 3D scan image in which a motion is corrected by matching depth maps created each time the 3D scan data are acquired, and constructing a CBCT 3D image in which the motion is corrected from the CBCT data by applying motion information acquired by matching the depth maps.

The application provides an orthodontic tooth movement monitoring method and system based on wax occlusion records, which comprises the following steps: obtaining an intraoral scanning model and a cone beam CT tooth model at time T0, superimposing the two models to obtain a complete model of each tooth containing a tooth crown and a tooth root; obtaining a wax occlusion record at time T N , optically scanning the wax occlusion record to obtain a three-dimensional digital model of the occlusion record and uploading the three-dimensional digital model; matching the occlusion pits of the digital model of the occlusion record with the occlusal surfaces of the complete model of each tooth to restore a tooth position model at time T N ; superimposing the tooth position models at times T0 and T N , and establishing a local three-dimensional coordinate system for each tooth; calculating three-dimensional movement data of the teeth; and a doctor remotely monitors the tooth movement of a patient with high accuracy by obtaining accurate three-dimensional data of the tooth position changes, provides reliable data for subsequent correction, and guides the next treatment of the patient.

The invention provides a glioma image segmentation method and system based on multi-feature fusion, and relates to the technical field of medical image processing, and the method comprises the steps: carrying out the preprocessing of multi-modal image data, and obtaining the spatial alignment multi-modal image data; based on the spatially aligned multi-modal image data, respectively extracting texture and metabolism characteristics of a preoperative image, gray gradient and morphological characteristics of an intra-operative cone beam CT image and micro texture characteristics of an intra-operative optical coherence tomography image; fusing the morphological characteristics of the intra-operative cone beam CT image and the microscopic texture characteristics of the intra-operative optical coherence tomography image, and constructing a multi-modal spatial characteristic field; based on the multi-modal spatial feature field, determining a spatial assessment origin, a main assessment axis and an auxiliary assessment axis, and defining a dynamic spatial assessment sector accordingly; and arranging a series of spatial feature observation points in the dynamic space evaluation sector. According to the method, feature reliability quantification can be realized, so that adaptive precise feature fusion is completed, and the glioma subregion segmentation precision is improved.

The invention discloses a cone-beam CT arterial phase automatic scanning method and system based on forward projection, and relates to the technical field of medical image.The method comprises the steps that low-dose cone-beam CT pre-scanning is conducted on a target area when a contrast agent is not injected, a three-dimensional image is reconstructed, a to-be-monitored anatomical structure is selected on the three-dimensional image to form a three-dimensional area of interest, and the three-dimensional area of interest is obtained; the method comprises the following steps of: performing forward projection on a three-dimensional region of interest based on cone beam CT geometric parameters to obtain a two-dimensional monitoring region template corresponding to each rack angle, acquiring a real-time perspective image sequence in a contrast agent injection process, calling the corresponding two-dimensional monitoring region template for each frame of image to calculate a monitoring signal, acquiring a baseline value before contrast, calculating a difference value, and acquiring a real-time perspective image sequence; when the difference value reaches a preset threshold value, a trigger signal is output to start arterial phase cone beam CT scanning. Through three-dimensional pre-scanning targeted forward projection and real-time threshold monitoring, the arrival of a target focus contrast agent is accurately judged, the accuracy of the imaging opportunity in the arterial phase is improved, and the radiation dose is reduced.

The invention discloses a tooth long axis determination method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining oral cavity cone beam CT data, and segmenting tooth enamel; selecting a plurality of discrete points of the tooth enamel at the glaze cementum boundary of the tooth enamel, and obtaining coordinates of the discrete points; determining a tooth center coordinate and a glazed cementum boundary reference plane according to the coordinate of each discrete point; and determining a tooth long axis based on the tooth body center coordinate and the glazed cementum boundary reference plane. According to the scheme, the long axis of the tooth can be determined, so that the inclination angle and distance information of the tooth relative to the alveolar bone is determined, and reference is provided for oral operations such as implant repair; meanwhile, a three-dimensional digital measurement tooth reference plane and a three-dimensional coordinate system which are high in repeatability and have clinical significance are provided for manual measurement of cone beam CT clinical indexes and AI automatic identification measurement, and a solid theoretical foundation is laid for clinical research in the field of oral medicine AI automation.

A method for cone beam CT intensity correction such as for circular and other scanning geometries. The method comprises determining an intensity compensation for a selected scanning configuration and applying the intensity compensation to a reconstructed volume of interest to produce an intensity compensated volume, which is used to scale the volume of interest.

The application discloses a high-speed cone beam CT control method and device for continuous angle tracking, and the control method comprises the following steps: controlling a high-voltage generator to start a continuous exposure mode, and controlling a flat panel detector to start a continuous perspective mode; synchronously acquiring perspective image data with time stamps of the flat panel detector and angle data with time stamps of a CT rotating mechanism; determining integral angle intervals of each row according to the perspective image data and the angle data; performing back projection algorithm processing on perspective image data corresponding to the integral angle intervals of each row; and reconstructing to obtain cone beam CT images. The application adopts a mode of continuous exposure of a high-voltage generator and continuous perspective image acquisition of a flat panel detector, synchronously acquires relatively dense time-angle sequences, and performs preprocessing and back projection reconstruction on the cone beam CT reconstruction algorithm in units of rows, thereby removing the synchronous control logic required by pulse exposure, reducing or eliminating the frame interval of cone beam CT perspective images, improving the overall acquisition efficiency of the cone beam CT, and reducing the system complexity.

The application relates to a kind of cone beam CT imaging systems based on slip ring, belong to CT imaging technical field, by being detected by the first light curtain detection of being arranged in the entrance end of detection platform, the width domain of measured object, height domain is obtained, host computer is based on width domain, height domain obtains the lateral position deviation of measured object and detection height control detection platform and moves the center of measured object to detection position, then by the second light curtain detection, the more accurate positioning is realized to the moving distance of measured object;In the process of scanning imaging, the host computer sends scanning instruction to the slip ring through the first converter, the slip ring parses scanning instruction through the second converter and sends the face array detector and the ray source to start scanning and generate image and state data, and then it is sequentially returned to the host computer through the second converter, slip ring and first converter, which solves the problems of existing slip ring and face array detector general adaptability, difficulty in positioning the best detection position, causing a large amount of imaging redundant data, and unable to perform one-time through spiral cone beam CT imaging.

The invention discloses a scattering and hardening artifact eliminating method, system, device and equipment for turbine blade CT imaging and a medium, and relates to the field of aero-engine turbine blade CT detection. The method comprises the following steps: acquiring an original multicolor projection image and a scattering correction projection image of the turbine blade before and after placing a grating correction plate by using a cone beam CT (Computed Tomography) system; the aluminum strips arranged on the grating correction plate at intervals have inclined angles; according to the two images, determining a multi-color projection image for scattering removal of the turbine blade, and further utilizing a beam hardening correction model to obtain a single-color projection image of the turbine blade; weighting the monochromatic projection image and the scattering-removed multicolor projection image by adopting a weighted compensation enhancement correction algorithm which introduces a trade-off factor to obtain a projection image of which the cup artifact is eliminated; and finally, performing three-dimensional reconstruction by adopting a filtered back projection algorithm to obtain a projection correction slice image of the turbine blade. The method can effectively eliminate cup-shaped artifacts caused by scattering and hardening, and improves the image reconstruction quality.

The invention discloses an oral cavity cone beam CT-oriented central incisor and nasal palate neural tube structure pair segmentation method, which is applied to the technical fields of medical image processing, artificial intelligence and oral medicine, and aims at solving the problem that in the prior art, when a typical large-structure and small-tubular structure pair task of'central incisor and nasal palate neural tube 'is carried out, the segmentation efficiency is high. And a systematic method for joint segmentation, structure-to-geometric relationship constraint and structure-to-evaluation indexes is lacked. According to the method, a decoder and a boundary enhancement decoding branch are shared, and when the central incisor and the nasal palate neural tube are segmented, geometric constraints and special indexes oriented to structural pairs of the central incisor and the nasal palate neural tube are introduced; while the segmentation precision of the central incisor tooth is kept, the segmentation quality of the nasal palate neural tube is remarkably improved, the geometric consistency of the central incisor tooth and the nasal palate neural tube in a three-dimensional space is enhanced, and clinical indexes such as the safe distance between the root tip and the neural tube calculated based on the segmentation result are more reliable.

The application discloses a cone beam CT geometry correction method suitable for irregular tracks, adopts a new optimization constraint iteration method based on a back projection model to solve geometry parameters under each projection view, and most of existing correction methods all assume that the internal geometry relation of a reference point in a phantom is accurate and known, and rarely deeply study whether the phantom precision is suitable for the correction model. Through the disclosure of the application scheme, the correction method is a high-noise robust correction method, and high-precision correction can be realized even when the resolution of a system to be calibrated is twice that of a phantom measurement system.

The application discloses a kind of based on optical flat panel cone beam CT imaging component precision installation and method, including horizontal plate, the upper and lower ends of the inside of the horizontal plate are fixedly installed with mark card plate, the right end of the inside of the horizontal plate is fixedly installed with fixed plate, the upper and lower ends of the inside of the fixed plate are fixedly installed with driving rod, the inside of the driving rod is fixedly installed with light projector, the left end of the fixed plate is fixedly installed with detection plate, the upper and lower ends of the inside of the detection plate are fixedly installed with electric capacity device.One kind of based on optical flat panel cone beam CT imaging component precision installation and method, by being fixedly installed in the inside of fixed plate before installation and adjustment with light projector, then again fixedly installing detection plate in the inside of horizontal plate, finally cooperate with the light of light projector and judge whether it can be from one end of detection plate to the other end, to judge whether light projector is located on the center line of horizontal plate, to reach the effect of convenient adjustment level.