26 results about "Bone segmentation" patented technology

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

The embodiment of the invention relates to an image registration method and device, equipment and a storage medium. The method comprises the following steps: acquiring an original two-dimensional image and an original three-dimensional image of a to-be-registered target bone structure; inputting the original two-dimensional image into a bone splitting model to obtain a local two-dimensional image of each substructure, and inputting the original three-dimensional image into a bone segmentation model to obtain a local three-dimensional image of each substructure; and performing registration processing on the local two-dimensional image and the local three-dimensional image of any substructure by using a preset registration algorithm to generate a registration result between the local two-dimensional image and the local three-dimensional image. Therefore, the registration efficiency and accuracy of the two-dimensional image and the three-dimensional image are improved.

This invention discloses a fully automated quality control method for knee joint DR radiographs based on multi-task deep learning and geometric quantization. The method includes: using DICOM format knee joint DR images as input data and performing data preprocessing; constructing a multi-task model architecture comprising a knee joint anteroposterior and lateral bone segmentation model, a knee joint anteroposterior and lateral keypoint detection model, a foreign object detection model, and a left / right marker detection model, defining the network infrastructure and input / output of each model; calculating quality control-related indicators based on the bone mask, keypoints, foreign object detection results, and left / right marker detection results output by the four models; formulating scoring rules to score the quality of knee joint DR images, and performing automatic quality control of knee joint DR images. This invention achieves objective, efficient, and quantifiable knee joint DR image quality assessment by automatically extracting anatomical structures, calculating geometric parameters, and executing scoring rules, providing a reusable technical paradigm.

The invention discloses a multi-model fusion-based foot arch damage degree intelligent evaluation method and system, and belongs to the technical field of medical image processing, and the method comprises the steps: obtaining a foot load X-ray side position film; a DeepLabv3 + image segmentation model is adopted to process the foot load X-ray lateral position film, and a foot bone segmentation image is obtained; based on the foot bone segmentation image, identifying key anatomical points required by foot arch evaluation through a YOLOv8 anatomical point positioning model; according to the spatial position relation of the key anatomical points, arch related angle data such as an inner side longitudinal arch angle, an outer side longitudinal arch angle, a front arch angle and a rear arch angle are calculated; based on the foot arch related angle data, determining a foot arch damage degree grade in combination with a forensic judicial appraisal and evaluation system; according to the method, automation and standardization of foot arch damage assessment are achieved through multi-model fusion, the assessment efficiency is remarkably improved, and the measurement precision is improved.

A neural network training apparatus for dental images through patient-specific data augmentation of the present disclosure includes a bone segmentation unit configured to segment a bone in a dental image to generate a bone mask, a tooth labeling unit configured to label a tooth into which a metal will be inserted in the bone mask to generate a labeled dental image, a metal mask generation unit configured to generate a metal mask in the labeled dental image and perform data augmentation with the metal mask to generate a plurality of augmented metal masks, and a metal-affected image processing unit configured to simulate polychromatic spectrum-based metal artifacts in the plurality of augmented metal masks and calculate a metal attenuation coefficient to generate a metal-affected dental image.

An automatic positioning method of upper anterior tooth implant based on alveolar bone segmentation, comprising the following steps: S1, inputting an original oral CBCT image to a segmentation model to obtain a tooth segmentation result I t and an alveolar bone segmentation result I e ; S2, generating an implant boundary according to the tooth segmentation result I t and the alveolar bone segmentation result I e , to obtain an implant reasonable implantation range of a surface set S p ; S3, generating an implant optimal axial direction according to the implant reasonable implantation range of the surface set S p , and obtaining visual data I p of the implant by slice-by-slice fitting. The present application realizes the alveolar bone segmentation of the upper anterior tooth for the CBCT data, and generates the implant optimal position prediction and the implant optimal image position for the immediate implant, and solves the problems of dependence on subjective experience of doctors, inaccurate implant and time-consuming in the current upper anterior tooth immediate implant surgery.

Methods and systems for automatically reconstructing a three-dimensional bone model from MRI data. In a training method, paired MRI and CT scans are prepared; ground-truth bone segmentations are obtained in CT and linked to CT data; the MRI data is fused with the linked CT data separately for each region of interest corresponding to movable bone parts to produce MRI-aligned ground-truth datasets; a neural network is trained to predict bone segmentation from MRI by estimating tentative outputs and backpropagating a loss. A computer-implemented method receives MRI data, computes separate segmentation datasets for at least first and second bone parts with a trained network, and reconstructs a model with the parts represented distinctly. The model may be used for virtual surgical planning and for manufacturing patient-specific implants or surgical guides. Also disclosed are a computer-readable medium storing instructions and a system implementing these functions.

Embodiments of the present application disclose an image segmentation method and device, a storage medium and an electronic device, and relate to the technical field of image processing. The method comprises: acquiring CTA image data; performing first bone segmentation processing on the image data to obtain a first bone segmentation result; performing cropping on the image data according to the first bone segmentation result to obtain first cropped image data comprising only a region above the shoulder; performing second bone segmentation processing on the first cropped image data to obtain a second bone segmentation result; and performing fusion processing on the first bone segmentation result and the second bone segmentation result to obtain a fused bone result. The present application significantly improves the segmentation accuracy of head and neck bone tissue by cascading two bone segmentation processing procedures with different precisions and different inputs.

The application relates to an image segmentation method and device, computer equipment and a storage medium. At least two different modalities of to-be-segmented images are obtained according to a brain perfusion image; the at least two different modalities of to-be-segmented images are input into a preset V-shaped self-attention mechanism network model to obtain a cerebrospinal fluid segmentation image of the brain perfusion image; and a skull segmentation image of the brain perfusion image is determined according to the cerebrospinal fluid segmentation image. The preset segmentation neural network model can be used to segment the to-be-segmented brain perfusion image to obtain the cerebrospinal fluid segmentation image and the skull segmentation image, so that the infarction area and the cerebrospinal fluid part and the skull part in the brain perfusion image can be distinguished in the subsequent process, and the volume of the core infarction and the penumbra area can be accurately calculated.

This application discloses an automatic analysis method for CT images of long bones in mice and rats, relating to the field of image processing technology. The method includes: acquiring a CT image sequence of the target long bone, extracting the three-dimensional spatial distribution of bone tissue, and performing pose alignment and three-dimensional cropping to obtain a standardized bone image sequence; then constructing candidate depth intervals based on butterfly-shaped anatomical features and key points of growth plate strip-shaped gaps, respectively, and obtaining a fine search range through intersection operation; subsequently identifying candidate slices of triangular fractures and determining the anatomical zero point; finally, mapping the target analysis region based on the anatomical zero point, completing cortical bone segmentation, medullary cavity segmentation, and trabecular bone extraction under closed mask constraints, and outputting quantitative parameters of bone tissue. This application achieves accurate positioning of the growth plate and unified analysis region mapping in long bone CT images, improving the accuracy of trabecular bone extraction and the consistency of bone tissue quantification results.

The invention discloses a mandible symmetry detection method and system. The method comprises the following steps: firstly, training a feature point position prediction model by using a jaw feature point training data set to obtain a trained jaw feature point positioning model; thirdly, training the mandible segmentation model by using the mandible segmentation training data set to obtain a trained mandible segmentation model; then, respectively inputting a three-dimensional CBCT maxillofacial region image to be processed into the trained jaw feature point positioning model and the trained mandible segmentation model to obtain a jaw feature point set and a mandible fine segmentation result; performing surface reconstruction according to a mandible fine segmentation result to obtain a triangular mesh mandible model; and finally, performing symmetry analysis on the mandible to obtain a symmetry analysis result. According to the method, the lower jawbone shape identification and feature point positioning can be performed on the CBCT maxillofacial region image, so that the quantitative analysis of the symmetry of the lower jawbone is realized.

The invention provides a 2D-to-3D image reconstruction method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an original 3D bone segmentation image corresponding to a 3D CT image, calculating and aligning the 3D bone segmentation image according to the original 3D bone segmentation image, a real projection parameter and a fixed projection parameter, and obtaining a 3D-to-3D image; the original 3D bone segmentation image is mapped through the real projection parameter to obtain a 2D real projection positive and lateral position X-ray image, and the 2D real projection positive and lateral position X-ray image is mapped through the fixed projection parameter to obtain a 2D fixed projection positive and lateral position X-ray image, and the 2D fixed projection positive and lateral position X-ray image is mapped through the fixed projection parameter to obtain the 3D bone segmentation image. Therefore, the change of the real projection parameters is converted into the change of the pose and the form of the shot object under the fixed projection parameters; and inputting the 2D real projection positive and lateral X-ray image into the trained three-dimensional reconstruction model to obtain a predicted 3D aligned bone segmentation image, and calculating a real 3D bone segmentation image according to the predicted 3D aligned bone segmentation image, thereby improving the accuracy of model prediction.

The application discloses a knee cartilage segmentation prediction visualization method based on Mamba and three-dimensional attention, and belongs to the fields of deep learning and medical image processing. The method comprises the following steps: standardizing and pre-processing knee MRI three-dimensional data sets and performing data enhancement to construct training samples; a three-dimensional segmentation network TriAttnMamba3D-Net with an encoder-decoder structure is constructed, the encoder of the three-dimensional segmentation network TriAttnMamba3D-Net is embedded with a balanced Mamba module to efficiently model long-range spatial dependence, a three-dimensional directional attention is integrated in a bottleneck layer to enhance the feature expression of thin layer boundaries and cartilage regions, the decoder is fused with multi-scale features through a skip connection, and a composite loss function is adopted for optimization; and the processed data is loaded into the network for end-to-end training to generate a segmentation model. The application has the advantages of advanced nature and clinical conversion value, and can guarantee the accuracy while improving the calculation efficiency in view of problems such as the thin layer structure of cartilage, low contrast and multiple tissue adhesions.

The present application provides an artificial-intelligence preoperative planning system for multiple orthopedic disease types, the system comprising: an import module, configured to import medical image data; a three-dimensional reconstruction module, configured to establish a corresponding three-dimensional image model on the basis of the medical image data; a bone segmentation module, configured to segment bones in the medical image data; and at least three of the following modules: a hip joint simulation module, a knee joint simulation module, a spinal joint simulation module, a sports medicine simulation module, and a trauma surgery simulation module. In the present disclosure, by providing multiple surgical simulation modules respectively corresponding to different types of orthopedic surgery, the coverage scope of the preoperative planning system is significantly increased.

The application provides a skeleton segmentation method and device, electronic equipment and storage medium. The method comprises the following steps: acquiring multi-energy spectrum data of a scanning object collected by a CT device; generating a virtual single-energy graph of a target single energy level based on the multi-energy spectrum data; and performing skeleton segmentation based on the virtual single-energy graph. The method solves the technical pain point that the conventional bone segmentation technology is highly sensitive to HU (Hounsfield Unit) value instability, uses the virtual single-energy graph generated by the multi-energy spectrum data as a skeleton segmentation data source, avoids the problem that the HU value in the conventional CT image is easily affected by the scanning protocol and device model and fluctuates, and improves the stability and accuracy of the skeleton segmentation. The virtual single-energy graph of the target single energy level can effectively improve the density differentiation degree of the bone tissue and the soft tissue, reduces the interference of the soft tissue, and makes the extraction of the skeleton region more accurate.

The application provides a knee cartilage segmentation method based on Mamba state space model and dynamic hypergraph feature modeling. The method comprises three stages of data preprocessing, three-dimensional feature learning and segmentation prediction. First, the knee MRI data is preprocessed, and the model generalization ability is improved by combining data enhancement. Then, a network is constructed, the convolution and Mamba module are fused in the encoding stage to extract local and long-range dependent features, and the VSS module is introduced to strengthen the global context information; in the decoding stage, multi-scale features are fused through the jump connection, and the gating mechanism is added in the high-level semantics to realize the adaptive selection of features. Further, the dynamic hypergraph module is introduced in the deep feature fusion to model the complex spatial topological relationship of the cartilage area and improve the fine-grained structure expression ability. The method effectively improves the problems of fuzzy cartilage boundary, complex structure and class imbalance, and significantly improves the segmentation accuracy and stability while ensuring the computing efficiency.

A three-dimensional bone segmentation method based on improved region growing includes: first, reading in three-dimensional CT bone data; second, using an adaptive threshold segmentation method to separate the bone area from the background area to obtain all bone areas; then using morphological operations to remove the adhesion between the broken bones to obtain the core area of ​​each broken bone; finally, using these core areas as seed points for region growth, and performing region growth on multiple areas at the same time, thereby ensuring the accuracy of bone segmentation while ensuring the efficiency of segmentation, that is, ensuring that each pixel point belongs to a unique area and is the area closest to the seed point. According to the above steps, the pixel points contained in all the broken bones of the three-dimensional bone image and the broken bone number to which each pixel point belongs can be determined. The present invention can be applied to three-dimensional bone segmentation to help complete disease diagnosis and treatment, lesion analysis, etc., and help doctors better complete diagnosis and understand the patient's condition.

The present application relates to a kind of spinal lamina autonomous cutting and its cut through and stop perception method and device, wherein the method comprises: obtaining initial lamina structure data set input to lamina bone segmentation network model, output lamina bone tissue segmentation result and probability distribution diagram of dural sac safety termination surface;According to lamina bone tissue segmentation result, rigid registration relationship constructs millimeter level cuttable feasible region;With probability distribution diagram as the insurmountable safety limit of millimeter level cuttable feasible region, generate six degrees of freedom tool center point motion trajectory, obtain cutting path planning data;According to cutting path planning data, execute autonomous cutting operation under impedance control;According to the determination result, trigger cut-through determination flag signal;Bottom motion controller responds to cut-through determination flag signal.The present application generates six degrees of freedom tool center point motion trajectory by setting probability distribution diagram of dural sac safety termination surface as insurmountable safety limit, significantly reduces the risk of surgery.

Embodiments of the present invention disclose a method, apparatus, device, and storage medium for alveolar bone segmentation. The method comprises: acquiring an original alveolar bone image; performing lower alveolar bone coarse segmentation and upper alveolar bone coarse segmentation on the original alveolar bone image based on a target lower alveolar bone coarse segmentation model and a target upper alveolar bone coarse segmentation model, respectively; performing lower alveolar bone fine segmentation on the lower alveolar bone coarse segmentation result image based on a target lower alveolar bone fine segmentation model; performing upper alveolar bone fine segmentation on the upper alveolar bone coarse segmentation result image based on a target upper alveolar bone fine segmentation model; and merging the lower alveolar bone fine segmentation result image and the upper alveolar bone fine segmentation result image based on the lower alveolar bone position information and the upper alveolar bone position information in the original alveolar bone image to determine a target segmentation result image having upper alveolar bone markers and lower alveolar bone markers. The technical solution of the embodiments of the present invention can achieve fully automatic alveolar bone segmentation, improving segmentation accuracy and efficiency.

The application discloses a kind of automatic segmentation methods of mandibular nerve tube based on multi-view guidance, and the application relates to the field of oral medical technology.The application comprises the following steps: collecting original oral CBCT image data, and pre-processing;The pre-processed image data is sent into the mandibular bone segmentation network, and the mandibular bone region containing the mandibular nerve tube is segmented;The contrast enhancement technique is used to the segmented mandibular bone region;The processed mandibular bone image is projected along the coronal plane, the sagittal plane and the orthogonal cross section of the cross section;The key point detection network trained is used to detect the key points of the mandibular nerve tube on the three projection planes, and the shape information of the mandibular nerve tube is obtained;And these features are combined with texture direction features and input into the three-dimensional CBCT mandibular nerve tube segmentation network for accurate 3D segmentation.The space information missing in two dimensions is avoided, so that the mandibular nerve tube segmentation is more complete and accurate.

A bone segmentation result correction method, device, equipment and medium, including direction correction on the bone region with orientation attribute in the bone segmentation result, obtaining the direction corrected bone segmentation result, when the number of connected domains of the rib mask image does not satisfy the normal rib number range, repairing each rib mask in the rib region of the direction corrected bone segmentation result according to the connected domain analysis result of the image region corresponding to each rib mask. When the number of connected domains of the image region corresponding to a certain vertebra mask is greater than a first threshold, repairing the vertebra mask according to the judgment result of which of the adjacent vertebra regions of the vertebra mask the abnormal connected domain in the image region corresponding to the vertebra mask should be fused with. When the number of connected domains in the upper limb region after completing the pixel value update meets the preset number, repairing the bone skeleton label of the abnormal bone skeleton mask in the upper limb region to the upper limb bone skeleton label. Improve the accuracy of correcting the bone segmentation result.

An image processing system and related method. The image processing system (ARS) may comprise an input interface (IN) for receiving a reconstructed current target image (V) of an object of interest (OI) subjectable to motion. A motion corrector (MC) corrects for motion artifact in the target image causable by said motion, based on information as per a reconstructed reference image (V0) of the object. The said reference image (V0) may include motion artifact, if any, to a lesser extent than the current target image (V). The system allows for improved, that is faster and / or more robust, reduction of motion artifacts in the current target image.

The invention discloses a knee joint DR plain film full-automatic quality control method based on multi-task deep learning and geometric quantization, and the method comprises the steps: taking a knee joint DR image in a DICOM format as input data, and carrying out the preprocessing of the data; constructing a multi-task model architecture comprising a knee joint positive and lateral bone segmentation model, a knee joint positive and lateral key point detection model, a foreign matter detection model and a left and right identification detection model, and defining a network infrastructure and input and output of each model; calculating quality control related indexes according to skeleton Mask, key points, foreign matter detection results and left and right identification detection results output by the four models; according to the knee joint DR image quality automatic control method, by automatically extracting the anatomical structure, calculating the geometric parameters and executing the scoring rule, objective, efficient and quantifiable knee joint DR image quality evaluation is achieved, and a reusable technical normal form is provided.

This invention belongs to the interdisciplinary field of medical image processing and artificial intelligence, and relates to a method for oral and maxillofacial bone segmentation based on multi-scale kernel cross-band interactive attention fusion. It involves acquiring hyperspectral images through a standardized hyperspectral oral and maxillofacial bone data acquisition platform and constructing a training dataset with pathological gold standard annotations. A multi-scale kernel cross-band interactive attention fusion segmentation model is constructed, integrating multi-scale feature extraction, hierarchical attention optimization, and multi-level complexity adaptation mechanisms. The model is trained based on the annotated dataset, and a converged hyperspectral oral and maxillofacial bone segmentation network is obtained through multi-scale supervision and loss function optimization. The trained model is deployed to clinical scenarios to segment hyperspectral oral and maxillofacial bone images and output results, providing support for diagnostic and treatment decisions. This invention effectively solves the problems of insufficient accuracy, limited deployment, and poor scenario adaptability in oral and maxillofacial bone segmentation, providing an efficient and reliable image analysis tool for oral and maxillofacial surgery.

The present invention discloses a method and system for detecting mandibular symmetry. The method includes the following steps: first, a feature point position prediction model is trained using a mandibular feature point training dataset to obtain a trained mandibular feature point positioning model; second, a mandibular segmentation model is trained using a mandibular segmentation training dataset to obtain a trained mandibular segmentation model; third, a three-dimensional CBCT maxillofacial image to be processed is input into the trained mandibular feature point positioning model and the trained mandibular segmentation model, respectively, to obtain a mandibular feature point set and a mandibular fine segmentation result; fourth, a surface reconstruction is performed based on the mandibular fine segmentation result to obtain a triangular mesh mandibular model; and finally, a mandibular symmetry analysis is performed to obtain a symmetry analysis result. The present invention can identify mandibular shape and locate feature points in CBCT maxillofacial images, thereby achieving quantitative analysis of mandibular symmetry.

This invention discloses a WTNet pediatric mandibular wisdom tooth germ segmentation network architecture method, mainly comprising an input enhancement module with a region feature enhancement module and a bone feature separation module. Independent scale-specific feature fusion modules are provided in the tooth segmentation branch and the bone segmentation branch of the bone feature separation module, respectively. For an input and its corresponding ground truth label, the input is first fed into the input enhancement module to generate a mask and supervised using the ground truth label; then, the input and mask are fed into the region feature enhancement module to obtain enhanced input; in the bone feature separation module, the enhanced input is fed into the scale-specific feature fusion modules of the tooth segmentation branch and the bone segmentation branch respectively after passing through a shared encoder, and then fed into the decoders of the two branches. The tooth and bone ground truth labels are used to complete the supervision of the two branches respectively, obtaining tooth segmentation masks and bone segmentation masks. The two masks are fused to obtain the final segmentation result.