27 results about "Bone age assessment" patented technology

The invention relates to the technical field of medical image processing, artificial intelligence and the like, and provides a bone age assessment method and system based on an AI model and a bone age instrument. A detected left wrist X-ray image is preprocessed through gray scale standardization, noise filtering and a self-supervised learning model, the ratio of the width of the distal radius epiphysis to the width of the metaphysis, the length of the metaphysis of the third palm bone and graded skeleton features of the maturity of auxiliary ossification points are extracted through a Vision Transform, and multi-modal data fusion is conducted on the extracted skeleton features and demographic information. And a multi-layer perceptron model is adopted to predict the fused multi-dimensional bone age related data, and a bone age evaluation report is output, so that errors in bone age prediction of children and teenagers are effectively reduced, and the detection efficiency is improved.

The invention belongs to the technical field of medical image processing, and particularly relates to a left-hand X-ray image double-stage bone age evaluation system based on cross-modal learning. The system comprises a data preparation module, a coarse granularity classification module, a fine granularity regression module and an output module. The method comprises the following steps: firstly, preprocessing a hand X-ray image, and constructing cross-modal feature input in combination with structured text description of a standard bone age map; through an SBA-CLIP + cross-modal learning model, alignment and fusion of image features and text features are realized, and coarse-grained classification of bone age intervals is completed; and according to a classification result, dynamically calling a fine classification sub-model of a corresponding interval, and realizing fine regression prediction of the bone age. In the process, a bimodal attention alignment module is introduced to enhance internal feature representation of images and texts, and cross-modal alignment and classification are improved in combination with a comparison loss function guided by cyclic consistency. According to the method, the prediction precision and interpretability are remarkably improved, and the method has wide application prospects and clinical value.

The invention discloses a bone age evaluation method based on phalanx and carpal bone adaptive relation learning, and belongs to the technical field of computer vision and image processing, and the method comprises the steps: S1, constructing a bone age regression model which comprises a target detection module, a feature extraction module and a regression module; s2, extracting a middle finger region and a carpal region of a target skeleton through the trained target detection module; s3, respectively extracting bone age features of the target bones through a feature extraction module, and splicing the bone age features into a bone feature map according to channels; and S4, adaptively learning the relationship among the skeleton features in the skeleton feature map through a regression module, and evaluating the bone age. According to the model architecture provided by the invention, development characteristics of bones such as phalanges and carpal bones in different age groups are adaptively learned by applying multiple attention mechanisms, the interpretability of the model is greatly improved, a more accurate bone age evaluation result is obtained, and the bone age evaluation result is closer to clinical medical experience and is more suitable for clinical application. The performance of the model is superior to that of a model using global images for learning and regression.

The application discloses a bone age prediction method and system based on a multi-modal large model and a computer readable storage medium, belongs to the technical field of artificial intelligence and medical image processing, and comprises the following steps: fusing a left-hand DR image and clinical indexes through an end-to-end mode, constructing a multi-modal large model fine-tuned according to a bone age field, and outputting image-observed description of each bone in a left-hand wrist and bone-by-bone structured results of maturity levels; calculating a total bone age value through a scoring rule of a bone age evaluation standard, and generating and outputting a bone age evaluation report containing the bone-by-bone image-observed description, the maturity levels and the total bone age value. The application solves the problems of insufficient utilization of clinical indexes, heavy report writing burden, easy hallucination of model output and insufficient compliance of bone age calculation in the prior art, improves the accuracy of bone age prediction, clinical compliance and evaluation efficiency, and can be widely applied to hospitals, primary medical institutions and children growth and development screening scenes.

The application relates to the technical fields of medical image processing and artificial intelligence, and provides a bone age evaluation method and system based on an AI model and a bone age instrument. The left wrist X-ray image of a subject detected in the bone age instrument is acquired, and the demographic information of the subject is recorded. The detected left wrist X-ray image is pretreated through gray standardization, noise filtering and a self-supervised learning model. The Vision Transformer is used to extract the distal radius epiphysis and metaphysis width ratio, the third metacarpal metaphysis length and the auxiliary ossification point maturity grading skeletal features, and the multi-modal data fusion is carried out with the demographic information. The multi-layer perception model is used to predict the fused multi-dimensional bone age related data, and a bone age evaluation report is output, so that the error in the bone age prediction of children and adolescents is effectively reduced, and the detection efficiency is improved.

The application provides a bone age evaluation method and device based on global and local feature cooperation, equipment and medium, relates to the field of image processing, and includes: establishing an initial evaluation model and training to obtain a target evaluation model; obtaining a bone image to be evaluated, and inputting the preprocessed bone image to the target evaluation model; performing feature extraction by using a first convolutional network to obtain global features; performing identification and cutting by using a pre-trained target detection model to obtain a plurality of sub-images containing ROI regions of preset categories; performing feature extraction on each sub-image by using a second convolutional network to obtain a plurality of local features; performing convolution and normalization on the global features and the local features to obtain global context local features; after fusing each local feature with the global context local features, connecting the global features and the local features, and processing through a fully connected layer, a bone age evaluation result is obtained, and the problem that there is no full-automatic bone age evaluation method for sufficiently mining data features is solved.

The present invention is a bone age assessment method executed by a bone age assessment device, which includes: (a) acquiring an X-ray image of the lateral side of the elbow; (b) dividing the olecranon region from the X-ray image; (c) analyzing the morphological characteristics of the olecranon ossification center in the divided olecranon region; and (d) determining bone age based on the analyzed morphological characteristics.

The invention belongs to the field of medical image processing and artificial intelligence, and particularly relates to a construction method and application of a bone age evaluation model based on label distribution learning, and the method comprises the steps: constructing a bone age evaluation model which comprises a sub-model A, K sub-models B, a selection unit and a convolutional network C; k corresponds to different age groups; training the sub-model A by adopting the training sample set, and training the model B of the corresponding age group by adopting the training sample set of each age group; the model A obtains predicted bone age label probability distribution A according to each input image; the selection unit is used for substituting the distribution A into a normal probability density function with the real bone age of the input image as the center, calculating a normal distribution probability value, selecting a sub-model B of an age group corresponding to the age of the input image, and predicting again according to the input image to obtain predicted bone age label probability distribution B; and the convolutional network C is used for integrating the distribution A and the distribution B to generate final bone age label probability distribution. The accuracy of bone age evaluation can be improved.

The present invention provides a bone age assessment method, device and computer-readable storage medium based on a deep convolutional neural network. The bone age assessment method includes: collecting wrist bone X-ray films marked with bone age information, constructing a first deep convolutional neural network based on the UNet algorithm to perform image segmentation on the wrist bone X-ray films to obtain a preprocessed image set, and selecting some images as training set images, and the remaining images as test set images; constructing a second deep convolutional neural network based on the DenseNet algorithm, and inputting the training set images to train the parameters of the second deep convolutional neural network, thereby obtaining a trained second deep convolutional neural network, and the trained second deep convolutional neural network has a learned network weight parameter; inputting the test set image into the trained second deep convolutional neural network, and outputting the bone age assessment result after the trained second deep convolutional neural network is iterated. After adopting the above technical solution, the bone age assessment result can meet the requirements of clinical application.

The invention relates to a deep learning and logic correction segmentation combined bone age assessment method, which aims at the problems of high joint extraction false drop rate, difficulty in epiphysis maturity grade classification and the like, through a logic correction segmentation mechanism of confidence ranking, a semi-supervised pseudo-label generation strategy and a global attention enhancement module based on normalization, the bone age is assessed. And the accuracy and clinical robustness of bone age evaluation are remarkably improved. The application scenarios of the method include but are not limited to the precise medical fields of children endocrine dysplasia screening, bone age lag or advance pathological diagnosis, orthopedic treatment scheme making, growth hormone intervention curative effect evaluation and the like.

The present invention discloses a method and system for evaluating children's bone age with autonomous learning ability. First, the YOLOv5 model is used for coarse-grained classification to locate the positions and categories of 13 bone regions from the original image, and the 13 bone regions are cropped out from the original image. Then, the CAP model is used for fine-grained classification to predict the bone age grade of each bone region. Finally, the bone age is calculated according to the Chinese 05 bone age scoring standard. The system includes two deep neural networks, namely the object detection model YOLOv5 for coarse-grained classification and the context-aware attention pooling model CAP for fine-grained classification, which perform data preprocessing, feature extraction, bone age grade classification and calculation on the input image. The model update module is used to automatically update the CAP model and perform incremental training on the CAP model by using the incremental learning method based on knowledge distillation. It has the ability of autonomous learning. It has high prediction accuracy and low prediction cost.

The present invention proposes a method and system for intelligent bone age assessment based on feature point detection. The method includes: preprocessing acquired hand X-ray images; inputting the preprocessed images into an epiphyseal detection model to detect bone key points in the images; the epiphyseal detection model includes: a local network and a global network; centered on the bone key points, the preprocessed images are cut with a fixed length and width to obtain epiphyseal ROI regions; the epiphyseal ROI regions are input into a classification model to obtain corresponding bone categories and developmental levels; and according to a curve chart, the final bone age assessment result is obtained based on the category and developmental level corresponding to each bone. The present invention utilizes a positioning network plus a classification network to replace the target detection network, greatly reducing the amount of data required for training. Furthermore, the data for training the positioning network does not require detailed annotation by professionals, saving annotation costs. The prediction accuracy and time required are basically the same as those of a target detection network trained with large amounts of data.

The invention relates to a bone age prediction method and device, equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring skeleton input data, and preprocessing the skeleton input data to obtain preprocessed skeleton input data; detecting all joints in the preprocessed skeleton input data through a target detection algorithm to obtain a key skeleton region detection result; target joint screening is carried out according to the key skeleton area detection result, and key skeleton joint screening features are obtained; and according to the key bone joint screening features, performing bone age grade prediction through a pre-trained deep neural network model, and outputting a bone age prediction result. By adopting the method, the bone age evaluation efficiency and the bone age evaluation accuracy can be improved.

The invention relates to a bone age evaluation method by a bone age evaluation device. The bone age evaluation method comprises the following steps: (a) acquiring an X-ray image of the side surface of an elbow; (b) segmenting an olecranon region from the X-ray image; (c) analyzing the morphological characteristics of the olecranon ossification center in the segmented olecranon ossification area; and (d) determining the bone age based on the analyzed morphological characteristics.

This invention belongs to the field of bone age assessment technology and discloses a bone age assessment method and system based on MRI and deep neural networks. The MRI- and deep neural network-based bone age assessment method includes: using deep learning algorithms to comprehensively analyze three weighted MRI images, constructing an automated, radiation-free bone age assessment model with multi-feature fusion, and using the bone age assessment model to automatically identify, extract, and fuse effective features from MRI three-dimensional images to obtain the bone age assessment result. This invention combines artificial intelligence with multimodal MRI three-dimensional information, fully leveraging the advantages of MRI—non-ionizing radiation, high resolution, and multi-layered structure—and maximizing the synergistic effects between different modalities. It is expected to discover effective features that are difficult for experts to notice, improve network feature learning, and enhance the accuracy and precision of bone age assessment. This will help realize an integrated configuration of green health examination, accurate bone age inference, and efficient automatic assessment in in vivo bone age identification practice, providing strong scientific evidence for court trials.

The application discloses an adaptive multi-modal deep learning bone age assessment method, belonging to the technical field of medical image processing, and comprising the following steps: carrying out anatomical perception preprocessing on a hand X-ray film, generating a binary skeleton mask by using a pre-training model, assigning differentiated mask probabilities to a skeleton and a background region and performing Bernoulli sampling, superimposing an antagonistic mask enhancement, and strictly prohibiting the shielding of a radius bone, a distal ulna bone and a metacarpal bone epiphysis; inputting the mask image into an asymmetric Swin-Base encoder, calculating only the features of unmasked blocks, fusing gender and age metadata mapped through an embedding layer, and outputting fused features through cross attention; constructing a localized reference library, obtaining an initial bone age based on the fused features through K nearest neighbors, calculating a shift coefficient by using a development shift predictor, dynamically shrinking a sliding window with the initial value as the center and iteratively correcting until convergence to output a preliminary point estimate. The scheme fuses anatomical masks and metadata priori, eliminates cross-population bias, is resistant to shielding artifacts and has improved precision.

The invention discloses a cascaded multi-factor bone age evaluation device, method and equipment based on a space-frequency conversion network and a medium, and the method comprises the steps: extracting a detection region pool of a skeleton marker composed of a plurality of predefined detection frames from a processed X-ray image, and for each predefined detection frame, screening out the skeleton marker through a space-frequency conversion network A; inputting a certain skeleton marker region into a space-frequency conversion network B, extracting region features, inputting various skeleton development influence factors into a factor feature extraction network to obtain factor features, and further determining multi-factor joint features; inputting the multi-factor joint features into a bone age scoring network to obtain a scoring result of the nth bone mark area, and adding the scoring results of all the bone mark areas to obtain a final bone age score; determining the bone physiological age according to the bone age score, and predicting the development trend of the bone based on the bone physiological age and the actual age. According to the method, the bone age evaluation precision and efficiency are remarkably improved.

The invention provides a children bone age comprehensive evaluation method based on deep learning. According to the technical scheme, the method comprises the steps that S1, a bone evaluation map is obtained according to the actual age of a target child; s2, obtaining a skeleton monitoring factor according to the skeleton image data of the target child; s3, inputting the skeleton monitoring factor of the target child into the skeleton evaluation map, and analyzing to obtain an abnormal monitoring factor and an abnormal factor parameter of the target child; s4, analyzing to obtain the abnormally influenced bone age of the target child and the evaluated bone age of the child; s5, transmitting the abnormal monitoring factor to an abnormal factor area, and analyzing to obtain a target feature factor, a target abnormal diagnosis factor and a bone age assessment symptom of the target child; and S6, transmitting the evaluated bone age of the child and the bone age evaluation symptom to an evaluation result area, and obtaining a comprehensive bone age evaluation result of the target child according to the evaluation result area. According to the invention, comprehensiveness and accuracy of children bone age evaluation results are improved.

The invention discloses a radius grade subdivision method and device based on deep clustering, and the method comprises the following steps: 1, carrying out the dimension reduction of original data through employing a principal component analysis (PCA), and carrying out the feature extraction of the radius through employing an auto-encoder in a deep learning method; 2, classifying the features extracted in the step 1 through a clustering algorithm (k-means) to finish subdivision of radius grades, and performing weighted summation on a reconstruction loss function and a clustering loss function of the auto-encoder in the step 1 to serve as joint loss; and step 3, endowing a corresponding score to a new grade generated after subdivision by using an interpolation method. Experimental results show that the method provided by the invention can effectively subdivide the radius, can improve the accuracy of bone age evaluation, and assists in clinical application.

The invention provides a bone age evaluation method and device, bone age detection equipment and a storage medium. The bone age evaluation method comprises the following steps: acquiring an ultrasonic image sequence of a plurality of to-be-detected parts; inputting the real-time ultrasonic image of each to-be-detected part into the coarse positioning model, and outputting the score of each section ultrasonic image in real time; selecting a section ultrasonic image subsequence according to each section ultrasonic image and the corresponding score thereof, inputting the subsequence into a fine positioning model, and identifying a standard section ultrasonic image; inputting a standard section ultrasonic image into the segmentation model to obtain a cartilage region and an ossification center region; and calculating the bone maturity according to the maximum diameter of the cartilage area and the maximum diameter of the ossification center area. The section ultrasonic image is positioned and marked based on the coarse positioning model and the fine positioning model, the accuracy of the evaluation result can be improved, rapid, continuous and quantitative evaluation is achieved, and the accuracy of clinical evaluation is improved.

The invention relates to a bone age prediction method and device, equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring skeleton input data, and preprocessing the skeleton input data to obtain preprocessed skeleton input data; extracting bone age prediction key features from the preprocessed bone input data through a deep convolutional neural network model combined with an attention mechanism; and according to the bone age prediction key features, performing bone age prediction through a pre-trained feedforward artificial neural network model, and outputting a bone age prediction result. By adopting the method, the bone age evaluation efficiency and the bone age evaluation accuracy can be improved.

The invention relates to the technical field of artificial intelligence and medical image interdiscipline, in particular to a metacarpal and phalangeal epiphysis classification-oriented multi-modal feature fusion lightweight system. The system comprises a construction module used for constructing a preset classification model which is a lightweight classification model; and the training module is used for taking the acquired metacarpal and phalanx images as input, taking the preset classification categories corresponding to the metacarpal and phalanx images as output, and training a preset classification model based on the improved loss function to obtain a target classification model. The lightweight classification model for classifying the metacarpal and phalanx images is small in parameter quantity and high in calculation speed. In addition, the lightweight classification model is trained by adopting an improved loss function to obtain a target classification model, so that the classification is more accurate, and the problems of low efficiency and high recognition error rate during bone age evaluation in the prior art can be solved.

This invention discloses a remote medical system for children's bone age assessment and growth monitoring, relating to the field of medical diagnostic technology. The system includes: user-end data acquisition compatible with home / hospital equipment and sensors, automatic collection reminders, and transmission identification; image preprocessing with filtering and enhancement; AI-based bone age assessment based on an age-specific model, switching between dual standards, outputting results and anomaly markers; growth analysis comparing with standard curves; a remote interactive encrypted platform, pushing results for annotation and diagnosis; data storage with double encryption, sorted by timeline, supporting retrieval and authentication; anomaly warning with three threshold levels, triggering multi-channel alerts and automatic appointment scheduling; human-computer interaction via touchscreen or APP, providing an entry point, with key operations requiring verification. This invention achieves convenient remote data acquisition and accurate bone age assessment, scientifically monitors growth trends and warns of anomalies, strengthens cross-institutional collaboration and personalized intervention, ensures data security, improves management efficiency and intervention effectiveness, and adapts to the needs of children throughout their growth cycle.

The application discloses an intelligent bone age evaluation method based on an attention mechanism, which comprises the following steps: performing data preprocessing and enhancement on an original image, detecting a region of interest of the image after processing and dividing the image into 14 bone blocks; performing network training on the 14 bone blocks; and obtaining a final bone age value by performing grade recognition on each bone of a to-be-tested picture and comparing a score table. The application firstly performs filtering technology, Gaussian noise reduction and binary processing, then performs region of interest detection and segmentation by using a YoloV5 network, accurately divides and segments 14 reference bone regions, then recognizes the grade by using a recognition network after adding an attention mechanism, and finally obtains a final bone age value by comparing a bone development staging score table and a CHN bone development maturity and bone age comparison table.

The invention discloses a bone age evaluation classification model training method, device and equipment and a storage medium, and the training method comprises the steps: obtaining a plurality of left palm and phalanx maps, recognizing a plurality of key points in the left palm and phalanx maps, correcting the palm and phalanx maps according to the key points, and obtaining a plurality of palm and phalanx part maps through interception, the metacarpal and phalanx part maps are classified and placed in a plurality of part folders, then the metacarpal and phalanx part maps in the part folders are classified and placed in sub-folders according to classification levels to form a plurality of part training sets, neural network models are set for the part training sets, and hyper-parameters, loss functions, optimizers and output levels of the neural network models are set. And carrying out data enhancement processing on the metacarpal and phalangeal part maps in the part training sets so as to train the part training sets by utilizing the set neural network model. According to the bone age assessment classification model training method, the classification model with high bone age assessment accuracy can be trained, and a large amount of ROI annotation data does not need to be used.

A bone age assessment method based on fine-grained image classification includes: step 1) obtaining an X-ray image of the left wrist bone; step 2) inputting a bone age assessment network based on fine-grained classification designed in the present invention to perform bone age assessment; step 3) obtaining a bone age assessment result. The present invention uses a fine-grained image classification method to perform bone age assessment on the left wrist bone X-ray, designs and implements a bone age assessment network based on fine-grained image classification. When performing bone age assessment, only the X-ray to be evaluated and the gender corresponding to the X-ray need to be input to obtain the assessed bone age value. For the input X-ray, the bone age assessment network can adaptively extract several interest regions containing the most feature information, and use the image features of these interest regions to perform accurate bone age assessment. The invention can accurately assess the bone age of the left wrist bone X-rays of adolescents aged 0 to 18, and has great application value.

The present application belongs to the technical field of deep learning bone age detection, and particularly relates to a child bone evaluation method based on multi-scale features and differentiable fuzzy sets, comprising the following steps: S1: image preprocessing and multi-channel fusion construction; S2: multi-scale semantic layered feature extraction; S3: feature channel alignment and spatial scale unification; S4: multi-scale adaptive attention weighted fusion; S5: visual feature and gender feature joint embedding fusion; S6: differentiable fuzzy set regression bone age prediction; S7: joint loss function construction and optimization; S8: conflict-free sample balancing training strategy; S9: model training smoothing and reasoning enhancement. The present application can realize high-precision, high-robustness and clinically close automatic bone age evaluation through three-scale feature layered extraction, cross-scale attention fusion, gender feature embedding and differentiable fuzzy set regression, in combination with exclusive sample balancing and training optimization strategies.