69 results about "Bone segmentation" patented technology

An automatic contextual segmentation method which can be used to identify features in QCT images of femora, tibiae and vertebrae. The principal advantages of this automatic approach over traditional techniques such as histomorphometry are, 1) the algorithms can be implemented in a fast, uniform, non-subjective manner across many images allowing unbiased comparisons of therapeutic efficacy, 2) much larger volumes in the region of interest can be analyzed, and 3) QCT can be used longitudinally. Two automatic contextual segmentation algorithms relate to a cortical bone algorithm (CBA) and a whole bone algorithm (WBA). These methods include a preprocessing step, a threshold selection step, a segmentation step satisfying logical constraints, a pixel wise label image updating step, and a feature extraction step; with the WBA including whole bone segmentation, cortical segmentation, spine segmentation, and centrum segmentation. The algorithms are constructed to provide successful segmentations for known classes of bones with known topological constraints.

A method and apparatus for deep learning based automatic bone removal in medical images, such as computed tomography angiography (CTA) volumes, is disclosed. Bone structures are segmented in a 3D medical image of a patient by classifying voxels of the 3D medical image as bone or non-bone voxels using a deep neural network trained for bone segmentation. A 3D visualization of non-bone structures in the 3D medical image is generated by removing voxels classified as bone voxels from a 3D visualization of the 3D medical image.

A method of automatically identifying bone components in a medical image data set of voxels, the method comprising:a) applying a first set of one or more tests to accept voxels as belonging to seeds, wherein none of the tests examine an extent to which the image density has a local maximum at or near a voxel and falls steeply going away from the local maximum in both directions along an axis;b) applying a second set of one or more tests to accept seeds as bone seeds, at least one of the tests requiring at least one voxel belonging to the seed to have a local maximum in image density at or near said voxel, with the image density falling sufficiently steeply in both directions along at least one axis; andc) expanding the bone seeds into bone components by progressively identifying candidate bone voxels, adjacent to the bone seeds or to other previously identified bone voxels, as bone voxels, responsive to predetermined criteria which distinguish bone voxels from voxels of other body tissue.

The invention discloses an image processing method and system, and image processing model training method and system. The image processing method comprises: obtaining a to-be-detected image; inputtingthe to-be-detected image into a neural network model for processing to obtain a bone segmentation result, a bone center line segmentation result and a bone fracture detection result; wherein the neural network model is determined by machine training learning based on a training image. The bone segmentation, bone center line segmentation and bone fracture detection functions are achieved at the same time through the trained deep learning network, the total consumed time can be shortened by 50%, the memory space of the model can be saved by 40%, and meanwhile a doctor can be helped to reduce the film reading burden, accelerate the film reading time, reduce the missed diagnosis probability and reduce the contradiction between the doctor and the patient.

The invention provides a fever to-be-checked computer aided diagnosis method based on PET / CT images. Full-automatic analysis of the PET / CT bone images is achieved, and a doctor is assisted in diagnosing fever to-be-checked patients. Firstly, lossless interpolation of the PET images is conducted; secondly, hospital beds in the CT images are automatically removed; thirdly, full-automatic bone segmentation of the CT images is conducted; fourthly, bone segmentation is conducted on the whole-body CT images through an optimal active contour model of a CV active contour region; fifthly, after-treatment of the CT segmented images is conducted; sixthly, bone tissue information of the PET images is acquired; seventhly, bone tissue SUVs and bone tissue BSI values are acquired through calculation, wherein the SUVs of bones, marrow and bone cortices are acquired through calculation respectively, and the BSI values of the bones, the marrow and the bone cortices of the patients are acquired through calculation via the SUVs; eighthly, diagnosis is conducted based on the BSI values, wherein the SUVs and the BSI values are compared with SUVs and BSI values in an existing confirmed patient database, and a diagnosis report is made.

A computer implemented method for performing bone segmentation in imaging data of a section of a body structure is provided. The method includes: Obtaining the imaging data including a plurality of 2D images of the section of the body structure; and performing a multiphase local-based hybrid level set segmentation on at least a subset of the plurality of 2D images by minimizing an energy functional including a local-based edge term and a local-based region term computed locally inside a local neighborhood centered at each pixel of each one of the 2D images on which the multiphase local-based hybrid level set segmentation is performed, the local neighborhood being defined by a Gaussian kernel whose size is determined by a scale parameter (σ).

A method for segmenting bones on magnetic resonance (MR) images includes retrieving an MR image and performing an enhancement process on the MR image to generate a bone enhanced MR image. The bone enhanced MR image is then registered to a computer tomography (CT) based bone atlas. An MR image with bone segmentation is generated by segmenting the bone enhanced MR image using the CT based bone atlas as a mask. The MR image with bone segmentation may be presented on a display.

A method for segmenting bones on magnetic resonance (MR) images includes retrieving an MR image and performing an enhancement process on the MR image to generate a bone enhanced MR image. The bone enhanced MR image is then registered to a computer tomography (CT) based bone atlas. An MR image with bone segmentation is generated by segmenting the bone enhanced MR image using the CT based bone atlas as a mask. The MR image with bone segmentation may be presented on a display.

The invention discloses a whole-body bone imaging bone segmentation method based on atlas registration. The method comprises the following steps: acquiring original whole-body bone imaging data collected by professional equipment; subjecting the original whole-body bone imaging data to preprocessing including pollution detection processing, pollution repair processing, standardization processing,registration processing and regularization processing; and according to a deformation segmentation template stored in the system, carrying out segmentation processing on the preprocessed whole-body bone development image to obtain a segmentation result of whole-body bone development. By means of the method, bone positioning can be conducted on an image obtained through single whole-body bone scanning examination, a basis is provided for bone lesion positioning, development quality is improved by automatically reducing a difference through bone development pollution detection and a pollution repair algorithm, and the development difference between different whole-body bone scans is solved; and rapid, accurate and intelligent positioning of the whole-body bone imaging skeleton is achieved.

The invention is suitable for the field of the medical image technology, and provides a magnetic resonance image-based bone segmentation method and a system thereof. The method comprises the following steps: calculating step: calculating the Hessian matrix of each pixel and a characteristic value thereof in a first magnetic resonance image; extracting step: extracting the flake structure of the first magnetic resonance image and performing gray level enhancement on the flake structure of the first magnetic resonance image to obtain a second magnetic resonance image; optimization step: performing threshold connected calculation on the second magnetic resonance image, extracting a bone contour of the second magnetic resonance image, and carrying out smooth optimization to obtain a bone contour segmentation result of the second magnetic resonance image. Therefore by applying the magnetic resonance image-based bone segmentation method and the system thereof, a bone needing to be segmented is completely and independently segmented from the magnetic resonance image.

Multiple object segmentation is performed for three-dimensional computed tomography. The adjacent objects are individually segmented. Overlapping regions or locations designated as belonging to both objects may be identified. Confidence maps for the individual segmentations are used to label the locations of the overlap as belonging to one or the other object, not both. This re-segmentation is applied for the overlapping local, and not other locations. Confidence maps in re-segmentation and application just to overlap locations may be used independently of each other or in combination.

A method for segmenting bone in spectral image data is described herein. The spectral image data includes at least a first set of image data corresponding to a first energy and second set of image data corresponding to a second different energy. The method includes obtaining the spectral image data. The method further includes extracting a set of features for each voxel in spectral image data. The method further includes determining, for each voxel, a probability that each voxel represents bone structure based on the set of features. The method further includes extracting bone structure from the spectral image data based on the probabilities.

The invention discloses a three-dimensional broken bone segmentation method and device based on deep learning, and the method comprises the steps: extracting a vertex coordinate and a vertex normal vector based on an obtained three-dimensional broken bone grid model, and generating a broken bone point cloud model; inputting the generated broken bone point cloud model into a pre-trained Point Net ++ deep neural network, mapping the obtained vertex broken bone label probability to a corresponding three-dimensional broken bone grid model, and further performing segmentation optimization on the three-dimensional broken bone grid model by utilizing a graph cutting method to obtain a final broken bone segmentation result. According to the invention, the Point Net + + deep neural network in geometric deep learning is adopted to predict classification marks of broken cortical bones and cancellous bones; PointNet + + processes a point set sampled in a measurement space in a layering mode, a fine geometric structure captured by local features can be extracted, and broken cortical bone and cancellous bone segmentation is well achieved; and a segmentation result is improved by utilizing a graph cutting method according to the smoothness degree between the triangular patches, so the broken bone segmentation efficiency and the automation degree are improved.

The invention provides a limb bone segmentation method and device, an electronic device and a readable storage medium, and relates to the field of medical image processing. The method comprises the steps of performing image preprocessing on a to-be-segmented limb DR image when the to-be-segmented limb DR image is obtained; obtaining a target limb DR image, using a first skeleton segmentation modelto carry out skeleton region identification and image segmentation on the target limb DR image; obtaining a skeleton distribution area of the target limb DR image; performing image cutting on the target limb DR image according to the bone distribution area; obtaining a limb foreground image corresponding to the bone distribution area; and finally, carrying out limb bone category identification and image segmentation on each bone part in the limb foreground image by adopting a second bone segmentation model to obtain a segmentation image comprising a limb bone category distribution region of each bone part, thereby finishing high-precision image segmentation operation and obtaining a limb bone segmentation result with high segmentation precision.

The invention discloses a CBCT alveolar bone segmentation system and method based on deep learning, and relates to the technical field of artificial intelligence medical image processing and tooth correction, in particular to a CBCT alveolar bone segmentation system and method based on deep learning, and the method comprises the following steps: S1, obtaining and marking a dental CBCT data set; s2, preprocessing the CBCT image and the annotation sample; s3, constructing a deep semantic segmentation model; s4, performing model training and evaluation; and S5, segmenting and reconstructing the dental CBCT data. The invention aims to provide the deep learning method for automatically segmenting the alveolar bone of the CBCT image, a low-efficiency mode of manual segmentation of dentists and a low-precision method of a traditional threshold segmentation method are replaced, and the orthodontic efficiency and effectiveness are improved.

The invention relates to the field of bone joint replacement surgical robots, and discloses a three-dimensional reconstruction method for a CT image of a bone joint replacement surgical robot and a computer-assisted orthopedic surgery system based on augmented reality. The method comprises the steps of firstly, acquiring bone segmentation data of a CT image; then generating a three-dimensional skeleton model according to the obtained skeleton segmentation data of the CT image; a video image matching algorithm based on improved SURF feature points is adopted, matching tracking is carried out on a target of a video image, then the spatial attitude of the target is solved, corresponding spatial transformation is carried out on a virtual three-dimensional object, and therefore the effect of augmented reality is achieved. The main purpose of the invention is to provide a technology capable of establishing a sufficiently complex and accurate three-dimensional image for three-dimensional reconstruction of a CT image of a patient before an operation, so that a surgical robot can autonomously complete hip joint, knee joint and shoulder joint replacement orthopedic operations by means of the technology.

The invention provides a CT rib segmentation method and device, and the method comprises the steps: S1, obtaining training data, and generating two types of labels according to the training data; S2,training a full convolution image semantic segmentation model of two tasks according to the two types of labels to obtain a rib segmentation model; S3, acquiring to-be-segmented CT data, wherein the to-be-segmented CT data comprises all layers in CT; S4, reasoning a two-dimensional segmentation result and an adjacent layer relationship on each layer in the CT data to be segmented by using the trained rib segmentation model to acquire a rib contour of each layer by using a connected domain detection algorithm based on two-dimensional segmentation; S5, combining the rib contours of all layers according to the adjacent layer relationship to obtain a three-dimensional segmentation result; and S6, obtaining a CT rib segmentation result of the to-be-segmented CT data by using a post-processing algorithm. Compared with a traditional algorithm designed in a manual heuristic mode, the method is based on mass data and deep machine learning, and therefore the invention has the advantages in robustness, expandability and the like.

The invention provides a panorama constant-tooth identification method and device based on deep learning. The method comprises the following steps: inputting an original panoramic film into an alveolar bone line segmentation model based on deep learning to obtain an alveolar bone line segmentation result; generating an attached rectangular frame according to the alveolar bone segmentation result,generating an extended rectangular frame according to the attached rectangular frame, and cutting out periodontal region image blocks from the original panoramic sheet according to the extended rectangular frame; inputting the periodontal region image block into a constant tooth segmentation model based on deep learning to obtain a constant tooth segmentation result; and carrying out tooth numbermarking on each constant tooth in the constant tooth segmentation result.

The invention relates to a medical image segmentation method and a medical image segmentation device which are used to segment a bone from a medical image. The method is characterized by comprising the following steps: parameters for bone growth are set, including a first-level threshold, a second-level threshold and a boundary threshold, wherein the first-level threshold is a fixed parameter, and the second-level threshold and the boundary threshold are variable parameters; bone growth is carried out on a seed point by taking the first-level threshold, the second-level threshold and the boundary threshold as composite judging conditions to obtain the total number of bone tissue pixels; and whether the bone tissue growth rate is beyond a preset range is judged, bone growth is iterated multiple times until optimized parameters are obtained if the bone tissue growth rate is not beyond a preset range, and final bone growth is carried out to obtain a bone segmentation result.

The invention relates to the technical field of medical treatment, and discloses a navigation method and system for hip and knee joint replacement. The method comprises the following steps: acquiringa CT image; performing leg bone segmentation and reconstruction according to the CT image to obtain a leg bone model in model space; based on a leg bone marker, performing spatial pose registration onthe leg bone model and a real leg bone, and establishing a mapping relationship of the leg bone in the model space and the real space; tracking the leg bone marker; updating the real-time pose of theleg bone model; based on a cutting seam marker, performing spatial pose registration on a osteotomy guide block cutting seam model and the osteotomy guide block cutting seam, and establishing a mapping relationship of the osteotomy guide block cutting seam in the model space and the real space; tracking the cutting seam marker; updating the real-time pose of the osteotomy guide block cutting seammodel; and displaying the real-time poses of the osteotomy guide block cutting seam model and the leg bone model. The method improves the positioning accuracy.

The invention discloses a normal corrosion and random walk based fracture adhesion segmentation method, and aims at separating adhesion bones after fracture. The method comprises the following steps that (1) a model is preprocessed, the surface of the model is smoothed, and a calculating error of a normal vector is reduced; (2) a random walk area is selected interatively, and a voxel of an adhesion area is extracted; (3) on the basis of normal corrosion, whether a present point is corroded is determined according to the positional relation of a neighborhood voxel and the normal direction; (4)communicated areas are marked, and areas not communicated with each other after corrosion are marked; and (5) the segmentation areas are restored by expansion, and details of the original model are restored. According to the provided adhesion bone segmentation method, only voxels of higher curvature are corroded, oversegmentation can be prevented effectively, and adhesion broken bones can be separated more accurately.

The invention relates to a blood vessel segmentation method, an electronic device and a storage medium. The blood vessel segmentation method comprises the following steps: acquiring a medical image of a lower limb; acquiring a blood vessel segmentation image and a pelvic bone segmentation image according to the medical image; determining positions of an anterior superior spine vertex and a pubic tuberosity vertex according to the pelvis segmentation image; and according to the positions of the anterior superior spine vertex and the pubic tubercle vertex, segmenting the blood vessel segmentation image to obtain segmentation results of the iliac artery and the common femoral artery. Through the blood vessel segmentation method, the defect that the iliac artery and the common femoral artery cannot be accurately classified in the prior art is overcome, the blood vessel segmentation precision is improved, full-automatic blood vessel segmentation can be achieved through a computer, and the blood vessel segmentation efficiency is improved.

The invention provides a panoramic film impacted tooth recognition method and device based on deep learning. The method comprises the following steps: inputting an original panoramic film into an alveolar bone line segmentation model based on deep learning to obtain an alveolar bone line segmentation result; generating an attached rectangular frame according to the alveolar bone segmentation result, generating an extended rectangular frame according to the attached rectangular frame, and cutting out periodontal region image blocks from the original panoramic sheet according to the extended rectangular frame; and inputting the periodontal region image block into the deep learning-based obstructive tooth segmentation model to obtain an impacted tooth segmentation result.

The invention relates to a chest radiography image processing method and system, a readable storage medium and equipment, and belongs to the technical field of medical images. The method comprises thesteps: carrying out the chest radiography when medical equipment works, and acquiring chest radiography images shot by medical equipment; inputting the chest radiography images into a rib segmentation model and a lung field segmentation model respectively; obtaining a rib segmentation result and a lung field segmentation result respectively, wherein the rib segmentation result can comprise an identified rib sequence, whether a preset specific rib and a lung field are overlapped or not can be compared and judged by combining the two segmentation results, and whether the preset specific rib andthe lung field are overlapped or not decides the shooting quality of the chest radiography. Through analyzing and processing the shot chest radiography images, whether a preset specific rib in a chest radiography image is overlapped with a lung field or not can be judged; therefore, the chest radiograph shooting quality is determined, a doctor or a technician does not need to evaluate whether anexaminer is in a breath-holding state or not in the chest radiograph shooting process, the waiting time of the to-be-examined person can be directly determined through the chest radiograph shooting quality, the chest radiograph shooting effect is improved, and the chest radiograph shooting speed is increased.

The invention provides a panorama artificial tooth recognition method and device based on deep learning. The method comprises the following steps: inputting an original panoramic film into an alveolarbone line segmentation model based on deep learning to obtain an alveolar bone line segmentation result; Generating an attached rectangular frame according to the alveolar bone segmentation result, generating an extended rectangular frame according to the attached rectangular frame, and cutting out periodontal region image blocks from the original panoramic sheet according to the extended rectangular frame; Inputting the periodontal region image blocks into an artificial tooth body segmentation model based on deep learning to obtain an artificial tooth body segmentation result which comprisesan artificial restoration tooth body segmentation result and an artificial implant tooth body segmentation result.

The embodiment of the invention relates to the field of image processing, and discloses a bone segmentation method in a hip joint image, electronic equipment and a storage medium. The method comprises the steps: obtaining a to-be-segmented hip joint image; inputting the to-be-segmented hip joint image into a pre-trained segmentation model, and outputting a segmentation result, wherein a method for obtaining the segmentation model through pre-training comprises the following steps: creating an initial segmentation model, and obtaining a plurality of artificially labeled hip joint sample images to obtain a mask image; inputting the hip joint sample images into a self-attention transformation initial model and a convolutional neural network initial model to respectively obtain a first segmentation result and a second segmentation result; and calculating training loss, and returning the training loss to the initial segmentation model to obtain a final segmentation model. According to the embodiment of the invention, the segmentation result is accurate, the robustness is realized, and bone structures in the hip joint images can be efficiently and automatically segmented, so that clinical doctors are assisted in surgical planning, intraoperative navigation and postoperative evaluation.

The invention discloses a bone suppression image generation method and a device, a storage medium and electronic equipment. The method comprises the steps of obtaining a chest original image of a target object; processing the chest original image based on a pre-trained bone suppression model to obtain an initial bone suppression image and a bone segmentation image of the target object, the pre-trained bone suppression model comprising a bone suppression branch and a bone segmentation branch; and generating a target bone suppression image according to the bone position in the bone segmentationimage, the chest original image and the initial bone suppression image. According to the method provided by the embodiment of the invention, the obtained target bone suppression image can eliminate the bony contour of the pixel points of the skeleton region, can reserve the original image information of the non-skeleton region, improves the image definition, and reduces the distortion of the bonesuppression model in the chest original image processing process.

A method of automatically identifying bone components in a medical image data set of voxels, the method comprising: a) applying a first set of one or more tests to accept voxels as belonging to seeds, b) applying a second set of one or more tests to accept seeds as bone seeds, and c) expanding the bone seeds into bone components by progressively identifying candidate bone voxels, adjacent to the bone seeds or to other previously identified bone voxels, as bone voxels, responsive to predetermined criteria which distinguish bone voxels from voxels of other body tissue.

The invention belongs to the technical field of medical image analysis, and particularly relates to a method and system for abdominal bone segmentation in a medical image. The method for abdominal bone segmentation in the medical image includes the steps of: a. performing back-up on a CT image; b. selecting an initial seed point, and performing region growing segmentation on the CT image; and c. comparing the CT image after region growing segmentation with the backup image, judging whether a segmentation omission region exists, if a segmentation omission region exists, executing the Step b again, and if no segmentation omission region exists, outputting the segmented image. The method and system for abdominal bone segmentation in the medical image provided by an embodiment of the invention realize complete segmentation of an abdominal bone region with nonuniform gray level distribution in the medical image, can process complete segmentation of a connected region and an unconnected region at the same time, and compared with traditional existing threshold-based segmentation and region growing technology, the method has the advantages of strong robustness and stable segmentation.