44 results about "Bone segmentation" patented technology

The invention provides a cervical vertebra segmentation and key point detection method based on a diffusion model, and relates to the technical field of medical image processing, and the method carries out the denoising processing of a cervical vertebra image through the diffusion model, improves the image quality, and lays a foundation for the subsequent segmentation and key point detection. A cervical vertebra region and key point positions can be accurately extracted by combining a model of a deep learning technology, and reliable data support is provided for bone age staging; the bone age staging based on the results can objectively and quantitatively evaluate the growth and development degree of a patient and assist a doctor in making a personalized orthodontic treatment scheme, and in addition, in combination with a stress distribution diagram generated by a biomechanical model and a self-adaptive segmentation model of a preprocessed image, a segmentation strategy can be adjusted according to individual differences, so that the accuracy of bone age staging is improved. The precision and the robustness are improved; meanwhile, parameters such as blood flow velocity and temperature distribution are incorporated into a machine learning model, new indexes are provided for cervical vertebra bone age staging, and the individuation and accuracy of evaluation are enhanced.

The invention discloses an orthopedic 3D printing model construction method and device based on intelligent AI, and relates to the technical field of image.The method comprises the steps that a user database is collected, an image imaging scheme is configured, multi-view imaging is executed, and a DICOM format image data set is established; placing an image data set in the three-dimensional coordinate system and establishing registration mapping; after the image data set is preprocessed, skeleton segmentation is executed, and the segmentation trust degree is identified; carrying out image fusion reconstruction according to the registration mapping and the segmentation credibility, and generating a three-dimensional model for identifying the position complexity; printing placement fitting is carried out based on the three-dimensional model, the gravity direction is determined, and the geometrical shape is analyzed to determine a preliminary supporting area; according to the position complexity and the initial support area optimization support point, establishing a selection optimization result; and optimizing the three-dimensional model according to a selection optimization result, and generating an orthopedic 3D printing model of the user. Therefore, the technical effects of improving the modeling efficiency and precision and improving the printing stability are achieved.

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 invention discloses a live pig bone segmentation method based on a semi-supervised multi-scale diffusion model, which combines high-resolution image data with a deep learning network to form a method capable of accurately segmenting live pig bones on different spatial scales. The method comprises the following steps: firstly, acquiring image data of a skeleton in a live pig through CT scanning; after preprocessing, a denoising diffusion probability model is used for analysis. In order to improve the labeling efficiency, a semi-supervised learning strategy and a multi-scale feature extraction method are adopted, a model can be trained only through a small amount of labeling data, skeleton features under different spatial scales are analyzed, global information of an image is fully covered, local information is highlighted, the segmentation capability of a complex skeleton form is improved, and the method has the advantages of being high in practicability and easy to popularize. And precise segmentation of the skeleton structure of each part is realized. The technology provides a powerful tool for the research on the bones of the live pigs, and has a wide application prospect.

A bone segmentation result correction method, apparatus and device, and a medium, comprising: performing direction correction on a bone region having an orientation attribute in a bone segmentation result to obtain a bone segmentation result after direction correction, and when the number of connected domains of a rib mask image does not meet a normal rib number range, determining that the rib mask image is in the normal rib number range; and repairing each rib mask in the rib region in the bone segmentation result after direction correction according to the connected domain analysis result of the image region corresponding to each rib mask. And when the number of the connected domains of the image region corresponding to a certain vertebra mask is greater than a first threshold value, repairing the vertebra mask according to a judgment result that an abnormal connected domain in the image region corresponding to the vertebra mask should be fused with which one of the adjacent vertebra regions of the vertebra mask. And when the number of the connected domains in the upper limb region after the pixel value updating is completed accords with a preset number, repairing the skeleton label of the abnormal skeleton mask in the upper limb region into an upper limb skeleton label. And the accuracy of correcting the bone segmentation result 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.

The invention provides a knee joint skeleton segmentation method and device based on a deep learning network HuvNet. The method comprises the steps of collecting MRI image data containing knee joint skeletons of different patients; preprocessing the acquired MRI image data, and dividing according to a preset proportion to obtain a preprocessed training set and a preprocessed test set; constructing a skeleton segmentation prediction model based on a deep learning network HuvNet combined expression learning process; inputting the preprocessed training set into a skeleton segmentation prediction model for training to obtain a trained neural network model; and inputting the test set into the trained skeleton segmentation prediction model, predicting to obtain a segmentation result of the corresponding skeleton on the knee joint, and automatically segmenting the skeleton through a novel deep learning neural network structure HuvNet in combination with a representation learning process, so that the model prediction is simple and efficient, and the segmentation efficiency is improved.

The invention relates to an extraction method, in particular to a knee joint ROI extraction method and system. According to the method, the edge information of the lower bone is completely extracted, the consistency of ROI positions among samples is ensured, and a solid foundation is provided for analysis of machine learning or deep learning. The knee joint ROI extraction method comprises the following steps: extracting a skeleton segmentation mask for a to-be-processed knee joint image; extracting a skeleton edge line, and intercepting the edge line according to a threshold value; and stretching the edge line, and correcting the ROI region.

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.

The present invention discloses an image segmentation method, device, medium and product applicable to skeletal image data. The method includes: determining an initial point set corresponding to an initial active contour set in a skeletal CT image, where all bones in the skeletal CT image are within the initial active contour; determining a weight matrix of the skeletal CT image based on a weight function, the weight matrix including the weighted sum of the gray weight and the gradient weight of each pixel in the skeletal CT image, and the weight function including a gray term and a gradient term that are both monotonically decreasing functions; solving an iterative equation based on the initial point set, the weight matrix and a predetermined iteration step length to obtain a target active contour that coincides with the bone boundary, the iterative equation being the gradient flow equation for minimizing an energy functional, and the energy functional optimizing the active contour based on the weighted sum of the weighted perimeter and the weighted area of the active contour; and determining a bone segmentation result corresponding to the target active contour in the skeletal CT image. Embodiments of the present invention can improve the accuracy of the bone segmentation result.

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.

The present invention discloses an orthopedic 3D printing model construction method and device based on intelligent AI, which relates to the field of image technology. The method includes: collecting a user database, configuring an imaging scheme and performing multi-view imaging to establish a DICOM format image dataset; placing the image dataset in a three-dimensional coordinate system and establishing a registration mapping; after preprocessing the image dataset, performing bone segmentation and marking the segmentation confidence; performing image fusion and reconstruction according to the registration mapping and the segmentation confidence to generate a three-dimensional model marking the position complexity; performing printing placement fitting based on the three-dimensional model, determining the gravity direction, and analyzing the geometric shape to determine a preliminary support area; optimizing the support points according to the position complexity and the preliminary support area to establish a selection optimization result; and optimizing the three-dimensional model according to the selection optimization result to generate an orthopedic 3D printing model for the user. Furthermore, the technical effects of improving the modeling efficiency and accuracy and enhancing the printing stability are achieved.

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.

Disclosed are a method and an apparatus of processing image. The method includes: obtaining an initial bone segmentation result; and fusing the initial bone segmentation result based on characteristics of and correspondences between a plurality of bone segmentation results in the initial bone segmentation result, to obtain a target bone segmentation result. The initial bone segmentation result includes the plurality of bone segmentation results generated by a plurality of different deep learning models. Methods in the embodiments of the present application can improve precision of a fusion result of the plurality of bone segmentation results.

The invention discloses a bone segmentation method and device for an ankle joint CT image. The method comprises the following steps: acquiring a to-be-segmented ankle joint CT image and the number of feet in the ankle joint CT image; generating a skeleton structure image for reference and a seed image containing each skeleton structure and a corresponding label value according to the to-be-segmented ankle joint CT image through the technical means of threshold segmentation, connected domain analysis, image addition operation and the like in combination with the number of the feet; according to the skeleton structure image for reference and the seed image, obtaining a noisy label image having the same parameters as the to-be-segmented ankle joint CT image, and performing denoising and filling on the noisy label image, and obtaining label images containing label values corresponding to different skeleton structures and a three-dimensional model file of each skeleton structure. According to the method, the manpower and computing power requirements in the bone segmentation process are reduced, and the accuracy and efficiency are improved.

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.

The invention relates to the technical field of image processing, and discloses a lung parameter measurement system and method based on a lung CT cross section and a medium. The system comprises an image acquisition module used for acquiring a lung CT image; the left and right lung segmentation module is used for processing the lung CT image by using a deep learning model or an image processing algorithm to generate left and right lung segmentation masks; the bone segmentation module is used for processing the lung CT image by using a deep learning model or an image processing algorithm to generate a bone segmentation mask; the front-back diameter positioning module is used for positioning the front-back diameter of the front-back midline according to the left-right lung segmentation mask and the bone segmentation mask, and determining the front-back diameter of the left lung and the front-back diameter of the right lung; and the transverse diameter positioning module is used for positioning the thoracic transverse diameter according to the left and right lung segmentation masks, the skeleton segmentation masks and the front and back diameters of the front and back midlines, and determining the left lung transverse diameter and the right lung transverse diameter. The reliability of lung development parameter measurement is improved, and an accurate and consistent parameter measurement method is provided for children lung development research.

An upper anterior dental implant automatic positioning method based on alveolar bone segmentation comprises the following steps: S1, inputting an original oral cavity CBCT image into a segmentation model to obtain a tooth segmentation result It and an alveolar bone segmentation result Ie; s2, generating an implant boundary according to the tooth segmentation result It and the alveolar bone segmentation result Ie, and obtaining an implant reasonable implantation range curved surface set Sp; s3, according to the implant reasonable planting range curved surface set Sp, performing slice-by-slice fitting to generate the optimal axial direction of the implant, and obtaining visual data Ip of the implant. According to the method, the upper anterior tooth alveolar bone segmentation aiming at the CBCT data is realized, the optimal implant position prediction for immediate implantation and the generation of the optimal implant image position are carried out, and the problems that the current upper anterior tooth immediate implantation operation depends on the subjective experience of doctors, the implantation is inaccurate and the time is consumed are solved.

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 invention provides an aorta segmentation method and device based on a plain-scan CT image. The aorta segmentation method comprises the following steps: S1, preprocessing the plain-scan CT image; s2, carrying out spine skeleton segmentation; s3, acquiring an aorta distribution area; s4, performing enhancement processing on the aorta distribution area; and S5, performing joint segmentation based on multiple algorithms on the aorta distribution region after enhancement processing. According to the method, in the plain-scan CT image, the aorta distribution area is determined based on the spine skeleton, the data size needing to be processed is reduced, joint segmentation based on multiple algorithms is carried out on the aorta distribution area, the segmentation accuracy is improved through the segmentation models of different structures, and faster and more accurate aorta segmentation is achieved while the application range is expanded.