182 results about "Cbct imaging" patented technology

A general imaging scheme is proposed for applications of CBCT. The approach provides a superior CBCT image quality by effective scatter correction and noise reduction. Specifically, in its implementation of CBCT imaging for radiation therapy, the proposed approach achieves an accurate patient setup using a partially blocked CBCT with a significantly reduced radiation dose. The image quality improvement due to the proposed scatter correction and noise reduction also makes CBCT-based dose calculation a viable solution to adaptive treatment planning.

The invention discloses a positioning and locating device for radiotherapy and a positioning method of a dynamic target region. A therapy robot has an operating arm, wherein a compact linear electronic accelerator is arranged at one end of an operating arm of the therapy robot, and a secondary collimator is installed at one end of the compact linear electronic accelerator; a robot treatment table is arranged on a corresponding position of a double-image C-arm system, an C-arm sliding rail laser locator is arranged inside the double-image C-arm system, and a left side locator for an C-arm installation space is arranged on a corresponding position at the outer part of the double-image C-arm system. The positioning and locating device provided by the invention is provided with two groups of X-ray image systems, so as to realize binocular imaging; when the C-arm sliding rail rotates and a group of X-ray image systems is started, and CBCT (Cone Beam Computed Tomography) imaging can be realized; according to the positioning method, different imaging ways are adopted for a static target region and a dynamic target region, the rapidity and timeliness of the binocular imaging, the high quality, high definition and image registration of the CBCT imaging can be fully exerted.

The invention provides a temporomandibular joint movement reconstruction method and a system thereof. The method is characterized by collecting an image sequence of a mark point track of open and close mouth mandible movements of a photographed person; determining three-dimensional coordinates of all the mark points on an intraoral fixed mark device in each frame of image, acquiring a movement track of each mark point in a space, and collecting a CBCT image of the intraoral fixed mark device and collecting a CBCT image of the photographed person; registering the mark point of the CBCT image of the intraoral fixed mark device with the mark point acquired by a camera through photographing, and acquiring a transformation matrix of a mark point movement; and using the transformation matrix to carry out rigid body transformation on the CBCT image of the photographed person, acquiring a CBCT image sequence of the photographed person and acquiring a temporomandibular movement image. In the invention, real movement conditions of mandible condyle process and a temporal bone joint surface of a human-body temporomandibular joint can be acquired, the method and the system can be used for auxiliary diagnosis of a temporomandibular joint disease and dynamic analysis of joint motion, temporomandibular joint diagnosis means are increased, doctor diagnosis accuracy and efficiency can be increased, and medical quality and efficiency can be increased too.

The invention relates to a ring artifact elimination method for a CBCT image and belongs to the field of medical image processing. According to the invention, firstly, the CBCT image with a ring artifact is transformed from a Cartesian coordinate system to a polar coordinate system; then the CT image P in the polar coordinate system is subjected to smoothing processing by adopting an L0 norm filtering method; next, a smooth image P' obtained after filtering is subtracted from an original image P in the polar coordinate system to obtain an artifact information image Pk with partial original detail information, then the Pk is subjected to extraction and removal of an artifact template by using an OSTU multi-threshold segmentation method and a median method, and the rest of detail information is compensated into the filtered image P'; and finally, the image P' compensated with the detail information is transformed to the Cartesian coordinate system, so that a cone-beam CT image without the ring artifact can be obtained. Compared with the prior art, when detail and edge information in the cone-beam CT image is reserved to the greatest extent, the ring artifact on the CT image, which influences image quality and reality, are effectively removed without obvious residues.

The invention discloses an adaptive target area conversion method combining image segmentation and a deformation registration technology. According to the method, a threatening organ and a thoracic and abdominal tumor area are segmented automatically; multi-modal registration is performed on CBCT (Cone Beam Computed Tomography) images and planed CT (Computed Tomography) images by adopting a deformation registration algorithm; information on the planned CT is automatically transferred to the CBCT according to the calculated deformation area. After the rigid registration of the planed CT and the CBCT images, in order to compensate the deformation range which cannot recover, the transfer of a threatening organ, a tumor profile and a radiation treatment plan from the planned CT to CBCT is realized by adopting an orthogonal wavelet basis function-based deformation registration algorithm through the calculated deformation domain, so that a target position is accurately positioned.

The invention discloses a method for performing dentition segmentation on a cone beam CT image (CBCT). The method for performing dentition segmentation on a cone beam CT image comprises steps of defining an image structure according to an interest body image area in the cone beam CT image, obtaining a complete dentition through segmenting the CBCT image on the basis of a semi-supervised random walk algorithm and a soft constraint which is defined and registered by a three-dimensional deformable model, using the three-dimensional deformable model to introduce a soft constraint of a body image for processing noise in body image segmentation based on semi-supervised mark diffusion, adopting an iteration correction method to perform iteration solving problems on mark diffusion under the soft constrain and fitting on a surface voxel set by the three-dimensional model. The method for performing dentition segmentation on the cone beam CT image can effectively eliminate a segmentation error, improves dentition segmentation obtained through single time mark diffusion, improves segmentation accuracy and meets an accuracy requirement for clinic stomatology.

A method for analyzing a subject tooth. The method includes obtaining volume image data including at least the subject tooth and segments the subject tooth from within the volume data according to one or more operator instructions. An index is generated that is indicative of a suspected fracture or lesion identified for the segmented subject tooth. The subject tooth is displayed with the suspected fracture or lesion highlighted. The generated index also displays.

The invention discloses a guide plate for implantation of orthodontic micro-screw and a manufacturing method thereof. The method comprises: acquiring dental data from a CBCT image of a patient, rebuilding a three-dimensional image of jaw and teeth at an area to be subjected to implantation; acquiring a three-dimensional image of a to-be used micro-screw from a preset micro-screw three-dimensional image database, and regulating the three-dimensional image of the to-be used micro-screw at a preset position; establishing a first cylinder, enabling the direction of the cylinder to be same to the direction of the to-be used micro-screw and enabling the diameter of the cylinder to be larger than the diameter of a cuff part at the end of a screwdriver head; establishing a guiding part, namely forming a second cylinder at the periphery of the first cylinder along the axial direction, enabling the diameter of the second cylinder to be larger than the diameter of the first cylinder and enabling the two cylinders to be coaxial and same in height, and arranging a buffer distance between one end, facing to the phatnoma mucous membrane, of the cylinders and phatnoma mucous membrane; establishing a position-fixing part, namely painting the occlusion part and the occlusion surface at the appearance high point close to a tooth axial surface of the implantation part with an extended-crown preset-thickness coating; and establishing a connection part to connect the guiding part and the position-fixing part, so as to obtain a three-dimensional image of the guide plate, and printing.

The invention relates to a panoramic image acquisition method and system for oral cavity CBCT images. The panoramic image acquisition method for the oral cavity CBCT images comprises the steps that a two-dimensional oral cavity CBCT image containing a tooth structure image is selected from multiple continuous two-dimensional oral cavity CBCT images to serve as a target two-dimensional image; a dental arch curve is recognized on the target two-dimensional image, and dental arch curves of all the two-dimensional oral cavity CBCT images are determined according to the dental arch curve on the target two-dimensional image; equidistant sampling is performed on the dental arch curves of all the two-dimensional oral cavity CBCT images to obtain multiple sampling points on all the two-dimensional oral cavity CBCT images, and the sampling points at the same position on all the two-dimensional oral cavity CBCT images are determined as one group of sampling points; a sampling matrix corresponding to each group of sampling points is acquired, weighted forward projection operation is performed on each sampling matrix, and multiple weighted matrixes are obtained; and all the weighted matrixes are spliced according to order, and a panoramic image of the oral cavity CBCT images is acquired according to the splicing result.

The invention discloses a low-dose CBCT image reconstruction method based on a three-dimensional adversarial generation network, and belongs to the technical field of medical image processing. The method comprises the following steps: constructing a three-dimensional adversarial resistance generation network model; training a three-dimensional adversarial resistance generation network model through the sine image and the corresponding projection data; inputting the test image into the trained adversarial resistance generation network model, and predicting the missing part of the sine image of the incomplete projection data to obtain a sine image of complete projection; and reconstructing a CT image according to the sine image of the complete projection data. The method effectively shortens the acquisition time of the cone beam projection data, and improves the clinical diagnosis efficiency.

The invention discloses an image guide and breathing exercise analysis method. According to the image guide and breathing exercise analysis method, on the basis of two patient positioning ways of a cross positioning two-dimensional X-ray image and a three-dimensional CBCT (Cone Beam Computed Tomography) image, patient positioning and adaptive radiotherapy analysis can be quickly and precisely performed before treatment by utilizing the three-dimensional CBCT image, and online monitoring of the patient posture change and real-time tracing of moving tissues can be performed under treatment by utilizing the cross positioning two-dimensional X-ray image. In addition, an individualized positioning method can be established aiming at different patients and different treatment positions.

The present disclosure relates to systems, devices and methods for providing visual guidance for navigating inside a patient's chest. An exemplary method includes presenting a three-dimensional (3D) model of a luminal network, generating, by an electromagnetic (EM) field generator, an EM field about the patient's chest, detecting a location of an EM sensor within the EM field, determining a position of a tool within the patient's chest based on the detected location of the EM sensor, displaying an indication of the position of the tool on the 3D model, receiving cone beam computed tomography (CBCT) image data of the patient's chest, detecting the location of the tool within the patient's chest based on the CBCT image data, and updating the indication of the position of the tool on the 3D model based on the detected location.

The invention discloses a data fusion method for an oral cone beam CT (CBCT) image and laser scanning tooth grids, wherein the method belongs to the field of oral medical digitalization. Through quickly positioning a tooth part in the CBCT image data, and automatically dividing an upper jaw and a lower jaw by means of a least dividing method in a graph theory, interference of non-tooth part data (particularly teeth at the other side) in CBCT is eliminated, thereby greatly improving precision and stability in next-step initial aligning and accurate aligning. The data fusion method has advantages of simple process, higher efficiency, excellent stability, etc. Furthermore the data fusion method realizes higher user-friendly performance and higher convenience in point selection alignment based on user interaction. Firstly, the invention discloses a single-point mark alignment technique, thereby greatly reducing user interaction degree. Secondly, the data fusion method realizes no requirement for high accuracy in point selection by a user, thereby greatly reducing user interaction difficulty.

Techniques for generating an enhanced cone-beam computed tomography (CBCT) image using a trained model are provided. A CBCT image of a subject is received. a synthetic computed tomography (sCT) imagecorresponding to the CBCT image is generated, using a generative model. The generative model is trained in a generative adversarial network (GAN). The generative model is further trained to process the CBCT image as an input and provide the sCT image as an output. The sCT image is presented for medical analysis of the subject.

The invention discloses a tooth root extraction method based on an oral CBCT image, and the method comprises the following steps of S100, carrying out the optical scanning, obtaining a three-dimensional tooth jaw and dentition model, and building a projection image and a CBCT file sequence; S200, analyzing the CBCT file sequence through a Marching,Cube and a region growing algorithm; S300, based on the CBCT file sequence, distinguishing the upper tooth jaw and the lower tooth jaw, wherein the distinguishing process comprises the steps that the key frames of the occlusal plane and the sagittalplane are positioned through VTK, and a restrictive region growing algorithm is executed; S400, optimizing the segmentation effect of upper and lower tooth jaws, and manually cutting the tooth jaw model; and S500, removing the noise image of the cut tooth jaw model, and smoothing the noise image. According to the present invention, the surgical risk is reduced, and the surgical success rate is increased.

The invention discloses a CBCT image ring-like false shadow removing method. The method comprises the following steps of preprocessing collected original data and then reconstructing an original image; segmenting the original image so as to acquire a metal image; carrying out low-pass filtering of strength smoothness and normalization on the metal image so as to acquire a weight matrix; carrying out frequency division processing on the original image so as to acquire a high-frequency portion of the original image; carrying out normalized correction processing on the original image so as to acquire a corrected image; carrying out frequency division processing on the corrected image so as to acquire a high-frequency portion and a low-frequency portion of the corrected image; carrying out weight fusion on the high-frequency portion of the original image, the weight matrix, and the high-frequency portion and the low-frequency portion of the corrected image so as to acquire a final corrected image. A problem that an interpolation method can bring a new false shadow can be effectively solved and a problem that the interpolation method can cause nearby metal area information and skeleton information losses can also be solved.

The invention provides a method and a system for performing full-automatic segmentation on multiple tissues of an oral cavity CBCT image. According to the obtained original oral cavity three-dimensional CBCT data, a deep learning method is utilized to label the data, a deep learning method is utilized again to segment a new image, the image processing process is simple, excessive manual labeling and intervention are not needed, the difficulty of existing medical data annotation is overcome, and meanwhile human differences in the image annotation process are reduced. In the network training process, the adversarial network is generated for the training data, the training data volume is increased, and the universality of the network can be effectively improved. The establishment of the method greatly promotes the segmentation of a medical image technology, and provides an effective technical support for the automatic diagnosis and prognosis of oral diseases.

Method and apparatus for acquiring volumetric CBCT radiographies in an apparatus having a rotary supporting arm, at the ends of which at least an X-ray source and at least an X-ray sensor are positioned, the supporting arm rotating the at least one source and the at least one sensor around a patient. The method includes the steps of positioning a patient on the positioning device, and acquiring a CBCT image through a trajectory having an angular extension lower than 360°, wherein the rotation center of the trajectory of the X-ray sensor is never on the median sagittal plane defined by the patient positioned inside the apparatus and the trajectory is not symmetric to any of the possible sagittal planes of the patient.

The present invention provides a blocking optical grating optimization method and device for the scattering correction of a cone-beam CT (computed tomography) image. The method includes the following steps that: a blocking optical grating is scanned, and the swing model of the blocking optical grating is established; the initial coordinates of the blocking optical grating in the longitudinal direction of a detector in an initial projection are set, and an objective function between the data missing voxel value of the CBCT image and the coordinates of the blocking optical grating in the longitudinal direction of the detector is established; and the objective function is minimized by using a mesh adaptive direct search algorithm, so that the optimized coordinates of the blocking optical grating in the longitudinal direction of the detector can be generated. According to the brand new scattering correction method which does not require source compensation and is suitable for clinical CBCT in the present invention, mathematical optimization modeling is performed for data loss in an image field caused by the blocking optical grating; influence on a reconstructed image caused by the blocking device is quantitatively evaluated; the geometric optimal structure of the blocking device is solved by means of the mesh adaptive direct search method; and a solid theoretical basis is established for blocking device measurement-based scattering correction methods.

The invention discloses a GPU (graphics processing unit) acceleration CBCT image reconstruction method which comprises the following steps: reading projection data, and using an SART (simultaneous algebraic reconstruction technique) algorithm serving as an approximate item to update a body obtained by reconstruction in a GPU; minimizing a total variation of the body obtained by reconstruction by an adaptive gradient descent method; repeating the steps, performing iteration for N times until the algorithm is converged. According to the method disclosed by the invention, an image total variation minimization optical criterion and the SART algorithm are combined, so that the quality of an image which is reconstructed by purely adopting the SART algorithm is improved, and the image can be also reconstructed by fewer projection data; therefore radiation of X-rays to a human body in an imaging process is reduced, and the healing risk is reduced; meanwhile, a parallel algorithm is designed by an algorithm provided for GPU hardware, and the time for reconstructing an iteration image is effectively shortened.

The invention discloses a dental CBCT three-dimensional tooth segmentation method based on deep learning. According to the invention, the method includes performing semantic segmentation on teeth in each image in a CBCT image sequence, so that noise is removed; constructing a deep supervision coding-decoding network for denoising an oral CT image, mutually connecting coding and decoding sub-modules through a series of nested dense jump paths, and reducing semantic deficiency of feature maps in the coding and decoding sub-modules; the method specifically comprises the following four stages: stage 1, collecting and preprocessing a dental CBCT image; stage 2, constructing a model training set; stage 3, constructing a network segmentation model of a coding-decoding structure; and step 4, performing model training and evaluation. Experimental results show that the Dice similarity coefficient for individual three-dimensional tooth segmentation is 95.64%. Results show that the method provided by the invention provides an effective clinical application framework for digital dentistry.

The invention discloses a 4D-CBCT imaging method based on motion compensation, and belongs to the field of computed tomography. The method comprises the following steps: firstly, acquiring high-quality 4D-CBCT data of a patient, and dividing the high-quality 4D-CBCT data into samples and label data; then, requiring a motion compensation learning convolutional neural network of 4D-CBCT data to be constructed, wherein the network is used for establishing mapping between different phase images; secondly, training the network by taking the sample and the label data as inputs to obtain an optimal network parameter weight; and finally, reconstructing 4D-CBCT projection data under clinical scanning with the assistance of the network, and acquiring a high-quality reconstructed image. According tothe method, reconstruction blurring caused by respiratory movement and noise and artifacts caused by data acquisition angle loss can be reduced to a great extent, the scanning period can be shortened.The radiation damage to a subject can be reduced, the quality requirements of clinical analysis and diagnosis can be met, and the tracking efficiency of lung tumors can be improved.

The invention relates to the field of image processing, and provides a three-dimensional jawbone image segmentation method based on CBCT, and the method comprises the steps of extracting a plurality of image sub-sequences from a to-be-segmented CBCT image, inputting the image sub-sequences into a trained convolutional neural network model, and correspondingly obtaining a plurality of segmentationresults; integrating the segmentation results to obtain a three-dimensional jaw bone segmentation result of the CBCT image to be segmented, wherein the trained convolutional neural network model is obtained through the following steps: constructing a convolutional neural network model; preprocessing the CBCT image with the segmented and marked jawbone, extracting an image sub-sequence from the CBCT image as a training sample, and training the convolutional neural network model. Meanwhile, the invention further provides a corresponding three-dimensional jaw image segmentation device based on CBCT and terminal equipment. The embodiment provided by the invention is suitable for extracting the image of the three-dimensional jawbone region from the CBCT image.