74 results about "Manual segmentation" patented technology

Modern retrofit construction practices use 3D point cloud data of the building envelope to obtain the as-built dimensions. However, manual segmentation by a trained professional is required to identify and measure window openings, door openings, and other architectural features, making the use of 3D point clouds labor-intensive. Automatic point Cloud Building Envelope Segmentation (Auto-CuBES) algorithms can significantly reduce the time spent during point cloud segmentation. The Auto-CuBES algorithm inputs a 3D point cloud generated by commonly available surveying equipment and outputs a dimensioned wire-frame model of the building envelope. By leveraging unsupervised machine learning methods in the Auto-CuBES methods facades, windows, and doors can be identified while keeping the number of calibration parameters low. Additionally, some embodiments of Auto-CuBES can generate a heat map of each facade indicating nonplanar characteristics that are valuable for optimization of connections used in overclad envelope retrofits.

The invention discloses a full-automatic rapid detection and segmentation method for photovoltaic cell defects, and the method employs a lightweight SSA-ViT image encoder to replace a heavy-weight ViT image encoder in SAM, employs a separable self-attention mechanism (SSA) to replace a multi-head attention mechanism (MHA), greatly reduces the complexity of the attention mechanism, reduces the calculation amount, and improves the detection efficiency. Compared with the prior art, the method reduces the reasoning time of a single-frame image from average 4099 ms to average 11.7 ms (350 times), greatly improves the detection efficiency of the model, takes the prediction result of the YOLOv10 model as a new segmentation normal form of YoMo-SAM prompt information, abandons the man-machine interaction segmentation normal form of the original SAM, and truly achieves the full-automatic target detection and segmentation task on the premise of guaranteeing the segmentation precision. Meanwhile, task generalization of zero samples is achieved, the problem of data shortage is solved while manual segmentation is avoided, and then the detection segmentation precision of the model is improved.

The embodiment of the invention discloses an ear canal CT image segmentation method based on improved nn-UNet, and the method comprises the steps: collecting and marking the ear canal CT data of a plurality of patients, and making a data set; preprocessing the data; training on a training set by using a model improved based on nn-UNet, dividing a data set for multiple times by using a five-fold cross validation method, then training and verifying each fold, and storing a training model after training is completed; reasoning and testing the trained model on the test set data which are not seen; post-processing is carried out, and an output result of the model is optimized; and formulating an evaluation scheme to evaluate the prediction result. According to the method, the segmentation efficiency and accuracy can be greatly improved, and subjective deviation and human resource waste possibly generated in the manual segmentation process can be effectively avoided.

Methods and systems are provided for identifying shape-based atypical segmentations. In one example, a method includes receiving a segmentation of a region of interest (ROI) of a medical image, the segmentation output by a segmentation model, calculating a confidence metric of the segmentation that indicates how well a shape of the segmentation can be encoded by an encoding of one or more principal modes of shape variation of a set of previously determined segmentations of the ROI, and responsive to the confidence metric meeting a predetermined condition relative to a threshold, displaying the segmentation, storing the segmentation, and / or using the segmentation in one or more downstream processes; otherwise, prompting a user to perform a manual segmentation.

The invention discloses a CCTA image-based left auricle filling defect automatic segmentation and classification method, which realizes automatic identification and segmentation of left auricle thrombus, and comprises the following steps: S1, data acquisition and preprocessing; step S21, segmenting and sketching the image; step S22, training a deep learning neural network model by using the three-dimensional region of interest obtained in the step S21; s3, verifying the deep learning neural network model in the step S22 by using an external verification set; step S41, feature extraction; step S42, constructing a classification model; and S5, verifying the classification effect and explaining the classification effect, through the method, compared with previous manual segmentation sketching, a large amount of time and manpower resources are saved, through the method, image features, radiomics features and deep learning features can be combined, and compared with previous independent radiomics feature modeling, multiple artificial intelligence methods are integrated, so that the modeling efficiency is improved. And a more accurate diagnosis model is constructed.

The invention discloses a thick cloud-thin cloud integrated detection method and system based on spectral features and a multi-scale depth model, and belongs to the technical field of remote sensing image processing, and the method comprises the steps: 1, training a plurality of scene-level models of different scales based on a cloud detection data set, generating a plurality of scene-level cloud probability graphs and scene-level binary cloud masks of different scales; step 2, based on a plurality of scene-level cloud probability graphs of different scales and dark pixel features of the image, pixel-level cloud probability graphs facing thick cloud and thin cloud are generated respectively; and step 3, combining the scene-level binary cloud mask, fusing the pixel-level cloud probability graphs facing the thick cloud and the thin cloud by adopting dark pixel gradient, and then combining an adaptive threshold and distance weighting to generate a pixel-level binary cloud mask so as to realize thick cloud-thin cloud integrated detection. According to the method, manual segmentation threshold setting is avoided, and fusion of the thick cloud probability graph and the thin cloud probability graph and full-automatic accurate detection of the thick cloud, the thin cloud and the cloud edge are realized.

The invention belongs to the technical field of building construction, and particularly relates to a three-dimensional point cloud virtual assembling method based on image recognition. A three-dimensional point cloud virtual splicing method based on image recognition comprises the steps that point cloud data of splicing plates and side cross beam splicing plates at the joints of side main beams, side box beams and steel truss web plates are collected through a base station type scanner, standard size frame lines are constructed by conducting manual segmentation, voxel filtering and Gaussian filtering on the point cloud data, an image is intercepted, and the three-dimensional point cloud virtual splicing method based on image recognition is obtained. Gray processing, threshold segmentation, perspective transformation and size identification are carried out on the image, two-dimensional coordinates of bolt hole groups and frame lines are obtained, a two-dimensional to three-dimensional coordinate system is constructed, three-dimensional coordinates in the bolt hole groups are obtained through conversion, and virtual splicing is carried out according to the corresponding relation between the bolt hole groups of different components. According to the method, the efficiency and the precision of virtual assembly are remarkably improved.

The invention relates to a dangerous rock mass automatic cutting and accurate model construction method based on point cloud data, and belongs to the field of dangerous rock mass segmentation and three-dimensional model construction. According to the method, the point cloud data obtained by the unmanned aerial vehicle and the inclination angle information of the joint surface are combined, the automatic method capable of achieving accurate segmentation of the joint surface of the dangerous rock mass and generating the accurate model is provided, and the real joint surface in the accurate model of the dangerous rock mass is a curved surface grid. The method aims at improving the modeling efficiency and accuracy of the three-dimensional model of the dangerous rock body, and complexity and errors caused by manual segmentation are avoided; the method can overcome the problem that a dangerous rock body model is inaccurate due to traditional plane structural plane cutting, and the accurate model can make statics analysis and dynamics research on the dangerous rock body more accurate, so that a guarantee is provided for the dangerous rock body to possibly bring human life and property safety risks.

A method for generating a transducer layout for delivering tumor treating fields to a subject includes presenting a user-selectable icon to display a slice through medical images, which can be MRI medical images and CT medical images registered together. The slice includes corresponding slices through the MRI and CT medical images overlaid on each other. The medical images include voxels. The method further includes presenting a user-selectable icon to manually segment the slice through the medical images to obtain a manually segmented slice through the medical images. The method further includes presenting a user-selectable icon to automatically clean up the manually segmented slice to obtain a cleaned up manually segmented slice through the medical images. The method further includes presenting a user-selectable icon to generate transducer layouts for application of tumor treating fields to the subject based on the cleaned up manually segmented slice through the medical images.

The invention provides a target boundary determination method, a three-dimensional mask generation method and electronic equipment. According to the method, the initial boundary curves sketched only on the two orthogonal anatomical planes by the user are received, the geometric constraint effect of the orthogonal cutting planes on the space boundary control points is utilized, and the image features of the medical image are combined to carry out real boundary calculation, so that the heavy operation burden of manual segmentation layer by layer is avoided, and the real boundary calculation efficiency is improved. The dependence of a deep learning model on specific training data is broken through, the tumor boundary recognition precision is ensured, the segmentation efficiency is remarkably improved, and finally the technical effect of efficiently obtaining a high-quality three-dimensional tumor segmentation result is achieved.

The invention provides a pancreas segmentation model construction method based on enhanced CT (Computed Tomography) and a three-dimensional mask. The pancreas segmentation model construction method comprises the following steps: S1, acquiring an enhanced CT image and preprocessing the enhanced CT image and data; s2, automatically segmenting the enhanced CT image to obtain a three-dimensional mask of the pancreas; s3, image omics features and semantic features are extracted from the three-dimensional mask; and S4, screening the features, and constructing a learning classification model based on the screened features. The pancreas segmentation is automatically carried out on the enhanced CT image through the deep learning technology, and compared with a traditional manual segmentation method, the pancreas boundary can be identified more accurately, and the segmentation accuracy is improved. The automatic process from image acquisition to pancreas segmentation, feature extraction and model construction is realized, the operation process is greatly simplified, the manual intervention degree is reduced, and the working efficiency is improved.

The invention discloses a method for automatically marking crack semantic segmentation and improving a segmentation effect. According to the method, the minimum value is continuously searched for the crack pixel in the image neighborhood after preprocessing, the preliminary semantic segmentation crack picture can be optimized, and the precision and efficiency of crack pixel segmentation are improved. In addition, the invention further provides an automatic labeling method, each pixel of the crack does not need to be manually labeled, and the efficiency of crack pixel segmentation is remarkably improved. And after the crack pixel list and the corresponding crack binary image are obtained, a crack segmentation scheme of axis extraction and watershed algorithm filling is adopted, so that the problems of strong subjectivity and insufficient refinement of crack edge pixel judgment when a deep learning algorithm is directly adopted for segmentation or manual segmentation is also avoided, and the crack pixel segmentation quality is improved.

The invention relates to a brain tumor segmentation method and device based on improved 3D U-Net, and electronic equipment, and the method comprises the steps: obtaining multi-modal brain tumor data, carrying out the preprocessing of the multi-modal brain tumor data, obtaining to-be-processed brain tumor data, constructing a brain tumor segmentation model of the multi-scale feature mining of the improved 3D U-Net, and obtaining the to-be-processed brain tumor data. And training the brain tumor segmentation model by using the to-be-processed brain tumor data, storing an optimal weight model in the training process, and performing model prediction and performance index calculation by using the optimal weight model. According to the method, feature information of different scales can be more effectively captured and integrated by introducing a multi-scale feature mining module, so that the accuracy and robustness of segmentation are improved. In addition, the method utilizes a deep learning technology to realize full-automatic segmentation of the brain tumor. Compared with a traditional manual segmentation method, the method has the advantages that the segmentation efficiency can be remarkably improved, the workload of doctors is relieved, and segmentation errors caused by human factors are reduced.

The invention provides methods and systems for identifying shape-based atypical segmentations. In one example, a method includes receiving a segmentation of a region of interest (ROI) of a medical image, the segmentation output by a segmentation model; computing a confidence measure for the segmentation, the confidence measure indicating how well a shape of the segmentation can be encoded by one or more dominant shape variation patterns of a set of predetermined segmentations of the ROI; and in response to the confidence measure satisfying a predetermined condition with respect to a threshold, displaying the segmentation, storing the segmentation, and / or using the segmentation for one or more downstream processes; otherwise, prompting a user to perform a manual segmentation.

The invention relates to the field of high-speed railway measurement, and relates to a three-dimensional laser point cloud power line and electric tower segmentation method and system, and the method comprises the steps: obtaining first information which comprises the point cloud data of the periphery of a to-be-segmented electric tower; performing gridding processing on the first information to obtain a first grid unit; positioning the electric tower in the first grid unit to obtain the position information of the electric tower; processing the position information of the electric tower to obtain electric tower point cloud data after coarse segmentation; processing the electric tower point cloud data after coarse segmentation to obtain electric tower point cloud data after fine segmentation; and processing the point cloud data of the power tower after fine segmentation to obtain the point cloud data of the power line after segmentation, so that the automatic segmentation technology of the power line and the power tower is realized, manual segmentation processing can be replaced to a great extent, and the labor cost is greatly reduced.

Embodiments of the present invention disclose a remote sensing image segmentation method, device, and electronic device based on semi-supervised learning. The method includes: obtaining an annotation set based on a preset remote sensing image, the annotation set including a training set and a validation set; training a target segmentation model using the training set; inputting the validation set into the target segmentation model to obtain a predicted segmentation result for the validation set; if the predicted segmentation result of the validation set does not meet the preset validation requirements, updating the training set with the validation images belonging to validation samples whose segmentation results in the validation set meet the preset prediction requirements and the predicted category labels corresponding to the validation samples; returning to the step of training at least one target segmentation model using the training set; and inputting a remote sensing image to be tested into at least one target segmentation model to obtain a predicted segmentation result for the remote sensing image to be tested. This solution can quickly and efficiently segment the remote sensing image to be tested, saving time for manual segmentation and annotation.

The invention relates to a glioma grading and molecular feature prediction deep learning method based on a multi-modal MRI image, and the method comprises the following steps: S1, carrying out the preprocessing and image processing of three MRI images T2, FLAIR and CET1, S2, constructing three independent neural networks, inputting the three MRI images into the three neural networks respectively, outputting 512-dimensional feature vectors by the neural networks, and carrying out the recognition of the feature vectors. S3, endowing slices corresponding to different 512-dimensional feature vectors with different weights based on an attention algorithm of a gating mechanism, and carrying out weighted summation on all slice features based on attention scores to obtain patient-level feature vectors, and S4, carrying out series fusion on the three patient-level feature vectors, carrying out multi-task joint classification through a full connection layer, and carrying out multi-task joint classification on the three patient-level feature vectors. Outputting prediction probability values of the three key tasks; the method has the advantages that manual segmentation is needed, the method is based on the multi-mode MRI sequence, and the multi-task prediction capability is achieved.

The present invention discloses a method for segmenting brain tumors in MRI images based on an improved 3D-UNet, which specifically includes: 1) preprocessing the brain MRI images in the dataset to obtain a training set; 2) constructing an improved 3D-UNet framework by combining dilated convolution, channel attention mechanism, and residual convolution; 3) training the improved 3D-UNet, the brain tumor segmentation network, with the training set data; 4) importing the test data of the brain MRI image to be segmented into the brain tumor segmentation network to obtain the segmented result. The present invention provides an automatic, accurate, and repeatable tumor segmentation algorithm, which can effectively solve the problems that the traditional manual segmentation method is time-consuming and overly dependent on the subjective experience of experts, and has a higher segmentation accuracy than the method for segmenting brain MRI images based on UNet. At the same time, the method proposed by the present invention can be further applied to other medical MRI image segmentation tasks.

The invention discloses a visible light region-of-interest and 3D point cloud mapping method, device, equipment and medium, and relates to the technical field of three-dimensional vision and biological recognition crossing. According to the method, a face ROI can be quickly recognized through a visible light image deep learning model (such as YOLO / UNet), manual segmentation is replaced, and the processing speed is increased by 80% or above; a pre-calibrated projection matrix is used to realize sub-pixel-level two-dimensional-three-dimensional mapping, and error accumulation caused by a complex registration process is effectively avoided.

The present invention discloses a sentinel lymph node ultrasound image semantic segmentation method based on deep learning, which relates to the technical field of image semantic segmentation. First, the present invention obtains a sentinel lymph node ultrasound image data set and preprocesses the data set to obtain a training set; then constructs a RA-U-Net++ network for image semantic segmentation, and tunes the network parameters based on the training set to obtain a medical image semantic segmentation model for target lesions; the network adopts a multi-layer U-shaped structure, and an encoding node using a residual atrous pyramid module is set at each level. The output feature map of the encoding node at the current level is downsampled and then input into the encoding node at the next level; decoding nodes are set from the first layer to the penultimate layer, and the number of decoding nodes decreases layer by layer. The decoding node at each level is located behind the encoding node, and the input of each decoding node includes the output feature maps of all previous nodes and the output feature map of the previous adjacent node in the next level; the final segmentation result is obtained based on the output feature map of the last decoding node in the first layer. The present invention realizes the automatic segmentation of sentinel lymph node ultrasound images, getting rid of the cumbersome, time-consuming and laborious manual segmentation; and has a good segmentation effect, and can obtain a high intersection over union IoU.

The invention provides a semi-supervised newborn movement type prediction method and system based on graph regularization loss, and the method comprises the steps: collecting an original video of the limb movement of a newborn, and carrying out the manual segmentation of the original video of the limb movement, and obtaining effective video segments of the limb movement; converting the limb action effective video segment into a limb joint point sequence; inputting the limb joint point sequence into a neural network to obtain a predicted action category of the newborn; obtaining a graph regularization loss based on the predicted action category and the real category, calculating a cross entropy loss and a ternary loss of the neural network, and carrying out weighted summation on the graph regularization loss, the cross entropy loss and the ternary loss to obtain a total loss function of the neural network; and training the neural network based on the total loss function, wherein the trained neural network is used for predicting the neonatal motion type. The image regularization is added into the loss function, the feature extraction effect is improved, and the classification accuracy is effectively improved.

The invention provides a construction scheme determination method, system and device for a steel structure building and a storage medium, and relates to the technical field of building engineering.The method comprises the steps that analysis is conducted according to building basic information and preset design information of a to-be-designed building, and design index information of the to-be-designed building is obtained; performing simulation calculation according to the design index information to obtain component information of the to-be-designed building; target preset design information meeting design and construction requirements is determined according to the component information; and determining a construction scheme of the to-be-designed building according to the target preset design information. Structural design, simulation verification and construction output are integrated into a closed-loop process, manual segmentation operation is replaced with a parameterized model and automatic calculation, and the construction efficiency and the construction quality are effectively improved.

The invention discloses a multi-task self-distillation facial expression recognition method and system based on a coarse-grained label, relates to artificial intelligence, and provides the scheme for solving the problems in the prior art. During expression recognition, the following operation steps are carried out: S1, feature pre-extraction; s2, fine-grained feature extraction; s3, coarse granularity feature extraction; s4, self-distillation loss; s5, performing feature alignment; s6, overall training loss. The method has the advantages that (1) multi-task learning is utilized to guide learning of fine-grained facial expression features through a relatively simple coarse-grained classification task, and learned non-expression related redundant features are reduced; in addition, self-distillation loss is introduced to further achieve knowledge migration from coarse to fine grain branches. And (2) the coarse-grained label is obtained through manual segmentation based on facial expression prior, so that extra expert labeling requirements are avoided. And (3) the coarse-grained facial expression features are mapped to a fine-grained feature space, so that the knowledge distillation effect is further improved.

The present invention discloses a multi-task self-distillation facial expression recognition method and system based on coarse-grained labels, which involves artificial intelligence and proposes this solution to solve the problems in the prior art. The following steps are performed during expression recognition: S1. Feature pre-extraction; S2. Fine-grained feature extraction; S3. Coarse-grained feature extraction; S4. Self-distillation loss; S5. Feature alignment; S6. Overall training loss. The advantages are: (1) Multi-task learning is used to guide the learning of fine-grained facial expression features through relatively simple coarse-grained classification tasks, thereby reducing the learned non-expression-related redundant features. In addition, self-distillation loss is introduced to further realize the knowledge transfer from coarse-grained to fine-grained branches. (2) Coarse-grained labels are based on facial expression priors and are obtained through manual segmentation, avoiding the need for additional expert labeling. (3) Coarse-grained facial expression features are mapped to fine-grained feature space, further improving the effect of knowledge distillation.

The application discloses a three-dimensional body construction method and device based on CT images, a storage medium and a terminal. A CT sequence image of a target object is acquired. In response to a user's manual contour segmentation operation on a first target CT image in the CT sequence image, the first target CT image is subjected to first contour segmentation, and a first contour image of the target object is obtained. Based on each first contour image, a second target CT image in the CT sequence image, except for the first target CT image, is subjected to second contour segmentation, and a second contour image of the target object is obtained. A three-dimensional body of the target object is constructed according to each first contour image and each second contour image. Since the second contour segmentation is active processing and calculation on the manually segmented first contour image, when the second contour image is obtained, manual operation on a large number of images can be avoided, human-computer interaction is reduced, the three-dimensional body construction efficiency is improved, and the accuracy of the three-dimensional body of the target object can be ensured by the manually segmented first contour image.

The present application relates to ear cartilage and its substructure image segmentation method and system based on matching and segmentation cascade deep learning network, which comprises: acquiring the magnetic resonance image of UTE sequence of the contour of the external ear; the acquired magnetic resonance image of UTE sequence of the contour of the external ear is pretreated; the pretreated UTE sequence image is used as input, a registration network is trained, a deformation field is obtained, the deformation field is applied to the manual label image of the reference image or the manual label image of the template image to obtain a coarse label image, and the obtained ear cartilage coarse label image and ear cartilage substructure coarse label image are used to train a segmentation network respectively, so that the ear cartilage and ear cartilage substructure are segmented respectively. Based on ear cartilage UTE sequence imaging and very small amount of manual segmentation results, the present application obtains the model of high-quality ear cartilage and substructure morphology of automatic segmentation through cascading deep learning network.

The present invention discloses a thymoma CT image segmentation method based on multi-scale feature extraction, comprising the following steps: combining a DBB structure based on convolutions of different complexities and scales in the encoder of a traditional UNet network to extract spatial features of tumors at different scales in thymoma CT images, and obtaining richer tumor information. Based on the compression excitation mechanism, the relationship between convolution kernel channels is constructed to achieve dimensionality reduction and recalibration of spatial features at different scales, and then the recalibrated spatial features are weightedly fused with the original spatial features pixel by pixel to obtain spatial features that are more relevant to the tumor area. The segmentation result of the present invention has a DICE coefficient of 88.90, an intersection-over-union ratio IOU of 80.15, a true positive rate TPR of 86.94, a false positive rate FPR of 8.61, and a precision rate Pre of 91.79, which is closer to the manual segmentation result of a doctor.

The application discloses an acute ischemic stroke prognosis prediction method based on CTA images, relates to the technical field of medical image processing, and fuses a three-dimensional visual transformer and a meta-learning strategy to train a target prognosis prediction model based on the three-dimensional visual transformer and matched with a target data acquisition condition.The target prognosis prediction model can effectively model a spatial dependence relationship in a three-dimensional CTA image across regions and layers, significantly improves the recognition ability of complex cerebral vascular structures and ischemic regions compared with a traditional convolution network which only depends on a local receptive field, and further more, the introduction of the meta-learning strategy can improve the model generalization ability under small samples and multiple data acquisition conditions, so that the target prognosis prediction model directly takes the CTA image to be predicted as input to realize automatic prognosis prediction, does not need manual segmentation or feature extraction, avoids the dependence on manual experience in the traditional method, and improves the standardization degree and repeatability of the model application.

The invention relates to the technical field of machine learning, in particular to a knee osteoarthritis assessment method based on machine learning, which comprises the following steps: acquiring knee joint T1 and T2 weighted images of a patient with knee osteoarthritis; manually segmenting the knee joint cartilage in the T1 weighted image and measuring the volume of the knee joint cartilage; cutting the T2 weighted image to obtain a meniscus image, manually segmenting the meniscus image to obtain annotation data, and constructing an image data set; training a meniscus automatic segmentation model, and segmenting the meniscus in the meniscus image; carrying out three-classification on meniscus pixels of the middle five layers of the meniscus image, and calculating a meniscus space specificity signal index; the performance of the meniscus space specific signal index in diagnosis of knee osteoarthritis is systematically evaluated. According to the knee joint meniscus damage diagnosis method, the knee joint T1 and T2 weighted images of a patient with knee osteoarthritis are collected, the meniscus automatic segmentation model and a meniscus space specificity signal index calculation method are applied, the damage condition of the knee joint meniscus is accurately evaluated, and knee osteoarthritis diagnosis is achieved. The process can provide a reliable diagnosis basis for orthopedists, so that clinical diagnosis of knee osteoarthritis is effectively assisted.

This invention relates to a thyroid gland and nodule segmentation method based on an improved U-Net network. Ultrasound is the preferred method for thyroid nodule examination; however, ultrasound images are noisy, and thyroid nodules vary in shape, posing a significant challenge to doctors' diagnosis. Current automatic thyroid nodule segmentation methods perform poorly on irregularly edged and small nodules. To overcome the shortcomings of inaccurate segmentation of thyroid gland edges and small nodules due to insufficient feature extraction from high-resolution data, unsatisfactory segmentation results for large and irregular targets, and the tedious and time-consuming nature of manual segmentation, this invention proposes a thyroid gland and nodule segmentation method based on an improved U-Net network. By introducing ResNeSt modules, Atrous Spatial Pyramid Pooling (ASPP), and Deformable Convolution (DC) v3 into the encoder and decoder of the U-Net network for feature extraction, a Deformable-Pyramid Split Attention Residual U-Net (DSRU-Net) is established. Experimental and methodological analyses show that using the DSRU-Net network can significantly improve the accuracy of thyroid gland and nodule segmentation.