38 results about "Bone age" patented technology

The invention provides an orthodontic skull lateral film cervical vertebra image segmentation method and system. According to the method, an orthodontic skull side position film image to be processed is obtained, a target image area containing a second cervical vertebra, a third cervical vertebra and a fourth cervical vertebra is determined, then image preprocessing is carried out on the target image area to obtain a standardized input image, then the standardized input image is input into a CNN-Transformer fusion segmentation network for segmentation reasoning, and the image is obtained. According to the method, the centrum segmentation masks of the second cervical vertebra, the third cervical vertebra and the fourth cervical vertebra are output, and finally, the segmentation result is output based on the centrum segmentation masks, so that the segmentation result is output based on the centrum segmentation masks, and a repeatable and traceable objective basis can be provided for subsequent morphological parameter extraction and bone age / maturity quantitative evaluation; the subjective deviation and time cost of manual sketching are practically reduced, and the segmentation consistency and availability under the cross-individual and cross-equipment condition are improved.

The invention relates to the technical field of image processing, in particular to a metacarpal and phalanx image processing method and device. The method comprises the following steps: acquiring an initial metacarpal and phalanx image, and performing brightness processing on the initial metacarpal and phalanx image to obtain a first metacarpal and phalanx image; performing contrast processing on the first metacarpal and phalanx image to obtain a second metacarpal and phalanx image; constructing a preset convolution kernel, and performing definition processing on the second metacarpal and phalanx image based on the preset convolution kernel to obtain a metacarpal and phalanx target image; and inputting the metacarpal and phalanx target image into the bone age recognition model, and outputting a bone age recognition result. According to the method, dynamic image enhancement optimization can be carried out on metacarpal and phalanx X-ray images of different devices and different qualities through brightness, contrast and definition processing, so that the processed metacarpal and phalanx target images can highlight morphological characteristics of epiphysis, the bone age recognition accuracy is improved, and the bone age recognition efficiency is improved. The problem of low bone age recognition accuracy caused by different image qualities in the prior art is solved.

The utility model relates to the technical field of medical instruments and the like, and provides a portable bone age instrument which is provided with a machine body which comprises an X-ray detection box module, a machine body shell and a machine body upper cover. The machine body upper cover is assembled at the upper end of the machine body shell, and the X-ray detection box module is assembled in the machine body shell; a shell inlet is formed in the side wall of the upper end of the machine body shell, a detection opening and a detection channel are formed in the upper end of the X-ray detection box module, and the shell inlet, the detection opening and the detection channel are communicated; a main control module is arranged to control the X-ray detection box module to detect the bone age of the hand in the detection channel and obtain detection data for analysis and processing; and a main support frame is arranged to support the X-ray detection box module and the machine body shell, so that measurement by a user is facilitated, the size of the bone age instrument is reduced, the structure of the bone age instrument is simplified, the assembly difficulty of the bone age instrument is reduced, and the carrying convenience of the bone age instrument is improved.

This invention discloses a bone age-assisted diagnostic system and method based on multimodal clinical data fusion and retrieval enhancement. The system includes acquiring X-ray images of the subject's hand and multimodal clinical data containing endocrine indicators; extracting visual feature vectors from the images using a deep learning model and encoding the clinical data into clinical semantic feature vectors; deeply fusing visual and clinical features through a multimodal cross-attention mechanism to generate diagnostic fusion features; predicting bone age values ​​based on the fusion features; retrieving standard atlas descriptions from a medical knowledge base using visual features and retrieving disease risk warnings using the fusion features; and finally inputting the predicted values, atlas descriptions, and risk warnings into a generative large language model to generate a natural language diagnostic report containing imaging evidence and clinical recommendations. This invention solves the problem of existing technologies relying solely on images and being unable to interpret the basis for judgment.

A method for calculating a predicted adult height according to one embodiment of the present application includes generating a growth prediction model; and calculating a predicted adult height using the generated growth prediction model, wherein the generating the growth prediction model further includes acquiring input data and growth statistical data, including height information at the time of measurement, chronological age information at the time of measurement, bone age information at the time of measurement, and gender information; calculating an adult height based on the input data and the growth statistical data; and generating the growth prediction model based on the input data and the calculated adult height.

1. The name of the design product: micro-aging bone age instrument detection device. 2. The use of the design product: for human bone age determination. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view. 5. The bottom of the design product is not easy to see or not visible during use, omit the top view.

The invention discloses a bone age detection device and method, and relates to the technical field of bone age detection.The device comprises a solid sound conducting pad bracelet, an ultrasonic function module and a forearm fixing and position adjusting module; the ultrasonic function module comprises an ultrasonic image processing system and two ultrasonic probes; the ultrasonic image processing system is used for obtaining the maximum value of the transverse diameter of the ossification center and the maximum value of the transverse diameter of the epiphysis according to the ultrasonic data; according to the maximum value of the transverse diameter of the ossification center and the maximum value of the transverse diameter of the epiphysis, the ultrasonic epiphysis ossification rate is calculated; and comparing the ultrasonic epiphyseal ossification rate with the standard characteristic data to obtain the age corresponding to the ultrasonic epiphyseal ossification rate. According to the method, the bone age is detected in an ultrasonic mode, so that radioactive X-rays are prevented from being used, meanwhile, the calculated ultrasonic epiphyseal ossification rate is compared with the standard characteristic data, the corresponding age is obtained, and the objectivity and accuracy of bone age detection are guaranteed.

The invention provides a bone age AI prediction system based on MRI, and belongs to the technical field of medical image processing. The system comprises a data acquisition unit used for acquiring joint MRI image data; the data preprocessing unit is used for preprocessing the joint MRI image data; and the bone age prediction unit is used for performing bone age prediction according to the preprocessed joint MRI image data by utilizing the trained bone age prediction model and outputting a bone age differential diagnosis result. According to the system, MRI images are used for bone age prediction, radiation damage in the radiography process is avoided, meanwhile, MRI has the advantages that cartilage around epiphysis is accurately visualized, the contrast ratio is high, data are easy to store, the system is suitable for bone age prediction research, meanwhile, pure automatic prediction is adopted, human factor interference can be reduced, and accuracy is high.

The application provides a palate midline suture maturity prediction method based on deep learning, obtains a plurality of head lateral film image samples, respectively labels palate midline suture maturity information, and obtains a head lateral film image dataset; a palate midline suture maturity prediction model is constructed, the palate midline suture maturity prediction model comprises an image preprocessing module, a feature extraction module, a hybrid multi-scale attention convolutional neural network and a feature fusion module; the head lateral film image dataset is used to train the palate midline suture maturity prediction model, and a trained palate midline suture maturity prediction model is obtained; after a head lateral film image to be predicted is input into the trained palate midline suture maturity prediction model, a palate midline suture maturity prediction result is obtained; the application can reduce subjective differences of artificial interpretation, can improve the accuracy, consistency and reliability of bone age prediction, can realize non-invasive, objective and efficient palate midline suture maturity prediction, and provides a scientific basis for clinical expansion arch treatment decision-making.

The invention provides a training method of a bone age prediction model and a bone age prediction method and device. The invention relates to the technical field of computers, in particular to a bone age prediction model training method which comprises the steps that a plurality of first samples and a plurality of second samples are obtained, the first samples comprise hand bone image samples of human bodies in a first group, and the second samples comprise hand bone image samples of human bodies in a second group; the group scale of the first group is larger than that of the second group; and using the sequence knowledge of the relative ages contained in the plurality of first samples to assist the plurality of second samples to train the bone age prediction model to obtain a target bone age prediction model for the second group.

The invention relates to a remote artificial intelligence detection method and system for a bone age digital X-ray image, and the method comprises the following steps: remotely obtaining X-ray image data which are obtained through the transmission of a 5G private network in a desensitization encryption mode; carrying out normalization processing on the received X-ray image data; according to the X-ray image data after normalization processing, needed GPU computing power resources are judged, and at least one needed AI computing server is called based on the load balancing principle; acquiring a bone age detection result of the AI computing server, and generating a detection report; wherein the X-ray image data and the detection report are stored in an AI storage device, and the storage of the X-ray image data and the detection report follows an IHE integration specification. Compared with the prior art, the problems that bone age detection resources are deficient, the cost is high, privacy is prone to being leaked and the like in basic and remote areas are effectively solved, and the detection efficiency and the service coverage are improved.

The invention relates to a method for three-dimensionally printing bone organs and application, belongs to the technical field of three-dimensional printing, and provides a material composition for three-dimensionally printing the bone organs, the material composition comprises bio-ink, osteoblasts and osteoclasts, and the number ratio of the osteoblasts to the osteoclasts is 1: (2-3.5). Meanwhile, the invention provides a method for carrying out three-dimensional printing on a bone organoid by utilizing the material composition and a method for preparing a bone aging organoid. The bone organoid provided by the invention provides an ideal experimental platform for pathogenesis research of degenerative bone diseases, can be used for bone tissue engineering research, can also provide an important experimental basis for drug screening, treatment strategy optimization and the like of degenerative diseases such as osteoarthritis and the like, and has remarkable scientific value and application potential.

This invention discloses a self-activated NO nanopump, its construction method, and its application. The self-activated NO nanopump comprises a chemiluminescent substrate CPPO and a NO donor BNN6 encapsulated in DSPE-PEG-Mal. The DSPE-PEG-Mal surface is conjugated with a LepR antibody. The self-activated NO nanopump of this invention can specifically target LepR... + It accumulates in cells and releases intracellular NO, thereby effectively reversing cellular aging and differentiation fate. It rescues bone aging by upregulating the glycolysis pathway. It possesses strong H2O2 scavenging capacity, NO production capacity, and anti-aging ability. In vivo administration significantly reverses osteoporosis in OVX mice. The self-activated NO nanopump provided by this invention offers a novel strategy for the treatment of bone aging.

The invention discloses a bone age prediction method, device and equipment based on a deep learning model, and belongs to the technical field of medical image analysis, and the bone age prediction method comprises the steps: carrying out the preprocessing of an original hand bone image of a current user, and obtaining a target hand bone image; inputting the target hand bone image into a trained region cutting network to obtain a target segmentation region; inputting the target hand bone image marking the target segmentation region into a trained deep learning model, so as to enable the deep learning model to extract hand bone features of the current user from the target segmentation region; and predicting the bone features of the hand bones by using a regression model to obtain bone age prediction data of the current user. According to the method, accurate skeleton region segmentation is performed by using the segmentation network, and the bone age prediction is performed in combination with the deep learning model, so that the interference of background noise can be avoided while effective skeleton features are extracted, and the prediction accuracy and reliability are remarkably improved.

The utility model belongs to the technical field of medical instruments, and particularly relates to a digital X-ray bone age instrument for bone age detection, which comprises an outer protective box body, an X-ray generating component and a flat panel detector, an inner cavity of the outer protective box body is divided into a shooting space and an equipment mounting space, an extending opening for a hand to extend into is arranged on the outer protective box body, and the X-ray generating component is arranged on the outer protective box body. The outer side face of the outer protection box body is further provided with an extending opening, the extending opening is communicated with the shooting space in the inner cavity of the outer protection box body, the outer side face of the outer protection box body is further provided with an adjusting opening, the adjusting opening is communicated with the shooting space in the inner cavity of the outer protection box body, and the outer protection box body is further provided with an observation window. According to the utility model, the observation window and the adjusting port are arranged on the outer protective box body, so that a tested person can adjust the position and posture of a palm by himself / herself conveniently, other adults can stretch hands into a shooting space through the adjusting port conveniently, an infant whose palm is difficult to adjust to the correct position and posture by himself can be directly assisted to adjust, the use is more convenient, and the working efficiency is improved. And the use efficiency can be improved.

The invention provides a lifting type detection device based on bone age ultrasonic detection, and relates to the technical field of medical instruments. A group of moving frames are mounted on the base in a threaded manner, a group of moving arms are slidably mounted at the outer ends of the moving frames, a group of host machines are fixedly mounted at the tops of the outer ends of the moving frames, and limiting blocks at the outer ends of the bottoms of mounting seats are mounted on limiting grooves in the side ends of the ultrasonic detectors in an inserted manner; the device can realize height adjustment and angle fine adjustment, and an arc-shaped friction block is matched with a threaded rod to adjust the rotation tightness; the ultrasonic detector is quickly disassembled and assembled by utilizing a limiting block, a supporting rod and a second elastic piece; the movable arm is matched with the positioning groove through the guide block and the wedge-shaped block to realize position adjustment, so that the adjustability and the operation convenience of the device are integrally improved; the problems that the reliability of detection signals and results is influenced by inflexible adjustment, the accuracy comprehensiveness is reduced due to difficulty in adapting to various skeleton detection, the cost and time are increased due to tedious disassembly and maintenance of an ultrasonic detector, and the working continuity is influenced are solved.

The application discloses a coarse-to-fine bone age regression method based on multi-scale high-order self-attention, first extracts multi-scale features and multi-scale global self-attention response maps of the original hand bone image, fuses the latter and the down-sampling features of the original hand bone image to obtain fusion features, inputs the fusion features into a regression module, calculates an adaptive triad loss in the regression module to obtain a bone age regression value and an MSE loss for calculating the bone age, adjusts model parameters, trains the model on an original data set, then inputs the original data set into a backbone network, extracts high-dimensional representations of the image and inputs the high-dimensional representations into a K-means clustering algorithm, clusters the data set into multiple age stages, finally inputs the data in each age stage into multiple original backbone networks, trains multiple regression models, and obtains bone age prediction values in each age stage. The method can effectively perform left-hand bone regression detection of teenagers, and provides a general and efficient regression model and regression framework for a clinical computer bone age regression application scenario.

The invention relates to the technical field of medical imaging, in particular to an auxiliary positioning method and system for a dual-energy X-ray bone mineral density and bone age instrument. The method comprises the following steps: acquiring a real-time positioning image of a hand of a subject; dynamically adjusting the identification line template according to subject information to generate an individualized positioning identification line; image processing is conducted on the images collected in real time, whether the hand posture meets the preset standard or not is judged, the coincidence degree is judged, and if the coincidence degree is too low, an instruction is generated to conduct posture correction guiding; the positioning image and the individualized positioning identification line are displayed in a real-time overlapping mode; according to the generated prompt instruction, voice and character prompt is carried out, and the subject is guided to gradually adjust the hand position until the positioning requirement is met. According to the method, the individual hand structure difference is fully considered, the positioning mark line template is adaptively zoomed through the wrist width measurement result in the real-time image, and individualized matching of the template and the hand contour of the subject is achieved.

The invention discloses a children growth promoting preparation, which belongs to the technical field of traditional Chinese medicine preparations and comprises fructus alpiniae oxyphyllae, radix pseudostellariae, dried ginger, angelica sinensis, fructus amomi, radix inulae inula, pericarpium citri reticulatae, serissa serissoide, panax japonicus, rhizoma cibotii, radix scrophulariae and cattle bone powder. The preparation integrates the traditional Chinese medicine theory of tonifying spleen and kidney and regulating qi and blood, wherein the fructus alpiniae oxyphyllae, radix pseudostellariae, dried ginger and the like can tonify spleen and promote appetite, significantly improve the digestive function and improve the absorption rate of nutrient substances; the Tibet inula root and the fructus amomi regulate middle-jiao qi movement, relieve abdominal distension and qi stagnation and further optimize the absorption state; the panax japonicus, the rhizoma cibotii and the cattle bone powder directly act on a skeletal system to tonify kidney and strengthen bone, promote cartilage cell proliferation and bone longitudinal growth, and effectively improve height and growth speed. The formula gives consideration to intervention on growth disorder problems such as precocious puberty and the like, and through two-way regulation of nourishing yin and purging fire and tonifying kidney and replenishing essence, advanced bone age is delayed, and precious time is won for height increase.

The invention belongs to the field of bone age prediction, and particularly relates to an automatic bone age prediction method based on multi-modal feature matching. A hand bone X-ray image is obtained, and an enhanced hand region image is obtained through preprocessing; inputting the hand region into a segmentation network to obtain a plurality of local feature regions, and adding text tags according to the regions; corresponding image and text feature vectors are obtained through a feature matching network, and the weight of a feature extraction network is reserved; a targeted loss function is added in the training process; and finally performing fine tuning to obtain an automatic bone age prediction model. According to the method, the text labels are selected to carry out auxiliary feature matching, so that the feature positioning capability of the model on different local areas is improved. Through a cyclic feature matching mode, the generalization of the model on different data sets is improved, the effect of accurate prediction on different data sets through one model is achieved, the training overhead is saved, and the availability of the model is improved.

The application discloses a bone age prediction method, which comprises the following steps: pre-training a bone age prediction model through a preset training set, and using the bone age prediction model to predict the bone age. The technical scheme adds an attention mechanism according to the coupling degree of different convolution layer information in the bone age prediction model, improves the problem that the traditional attention mechanism is not easy to converge, and directly adds the gender information into the neural network model for end-to-end training, thereby optimizing the training process and further improving the accuracy of the bone age prediction. The bone age prediction model used in the bone age prediction method is verified through the attention mechanism, and the model pays more attention to the metacarpal part of the patient, thereby having a good prediction effect.

The invention discloses nutritional composite powder for promoting growth and bone age balance. The milk powder is prepared from the following raw materials in parts by weight: 30-50 parts of modified milk powder, 15-25 parts of whey protein concentrate, 5-10 parts of compound minerals, 0.3-0.7 part of gamma-aminobutyric acid, 0.1-0.3 part of L-lysine, 0.4-0.6 part of bone collagen peptide, 2-5 parts of hydrolyzed yolk powder, 1-3 parts of yolk globulin, 3-6 parts of milk minerals, 2-4 parts of yolk phospholipoprotein, 1-3 parts of compound vitamins and 1-2 parts of citrus fibers. The health food is prepared from 1-2 parts of poria cocos powder, 1-2 parts of Chinese yam powder, 0.5-1 part of endothelium corneum gigeriae galli powder, 0.3-0.5 part of taurine, 1-3 parts of lactic acid bacteria compound powder, 1-2 parts of inulin and 0.1-0.3 part of fructus momordicae powder. The invention belongs to the technical field of nutritional food, and particularly provides nutritional composite powder capable of promoting growth and bone age balance, which is comprehensive in nutritional ingredients, scientific in proportion, capable of effectively supplementing various nutrients required by growth and development of teenagers, capable of remarkably promoting skeletal development, capable of improving body immunity and capable of providing comprehensive nutritional support for healthy growth of the teenagers.

A method for calculating an expected adult height, according to an embodiment of the present application, comprises the steps of: generating a growth prediction model; and calculating an expected adult height by using the generated growth prediction model, wherein the step of generating the growth prediction model further comprises the steps of: acquiring growth statistics data and input data including height information at a point in time of measurement, chronological age information at the point in time of measurement, bone age information at the point in time of measurement, and gender information; calculating the adult height on the basis of the input data and the growth statistics data; and generating the growth prediction model on the basis of the input data and the calculated adult height.

The application discloses a kind of pediatric growth promoting preparation, belong to the technical field of traditional Chinese medicine preparation, including Fructus Schisandrae, radix pseudoginseng, dried ginger, angelica, amomum villosum, incense, dried tangerine or orange peel, June snow, Chir Chir, dog spine, and cow bone powder.The preparation of the present application combines the theory of traditional Chinese medicine for invigorating the spleen and kidney, regulating qi and blood, wherein Fructus Schisandrae, radix pseudoginseng, dried ginger and the like can invigorate the spleen and stimulate appetite, significantly improve the digestive function and improve the absorption rate of nutritional substances;Amomum villosum and amomum villosum regulate the middle-jiao qi movement, relieve abdominal distension and stagnation of qi, and further optimize the absorption state;Chir Chir, dog spine and cow bone powder directly act on the skeletal system, tonify the kidney and strengthen the bone, promote chondrocyte proliferation and longitudinal growth of the skeleton, and effectively improve the height growth speed.The formula takes into account the intervention of growth disorders such as precocious puberty, delays the bone age through the bidirectional regulation of nourishing yin and purging fire and tonifying the kidney and filling essence, and gains valuable time for height growth.

The utility model discloses a convenient bone age detector, and relates to the technical field of detection equipment, and the convenient bone age detector comprises a housing, a detector, an all-in-one computer and a printer. The shell is provided with a detection port; the detector is installed in the shell, and the detection port is connected with the detector and used for detecting the bone age. The all-in-one computer is installed on the side wall of the shell and used for controlling the detector to conduct bone age detection. And the printer is arranged in the shell, is positioned below the detector, is connected with the all-in-one computer and is used for printing bone age detection images. The bone age detector integrates the detector, the all-in-one computer and the printer, so that the whole detection process can be completed in one device. The integrated design greatly simplifies the operation process, and a user does not need to switch among a plurality of devices, so that the detection efficiency is improved. In addition, the instant detection function of the detector further improves the convenience of the detector, so that a user can quickly obtain a detection result.

A method and system for constructing a bone aging degree prediction model, a device and a medium. The method comprises: acquiring CT images of target groups; dividing each CT image into a background region and regions of interest; on the basis of grayscale values, performing region subdivision on the regions of interest on each CT image, so as to obtain a plurality of subdivided regions in the regions of interest, and obtain the area proportion of each subdivided region in the regions of interest; and, on the basis of the CT images of the target groups and the area proportion of each subdivided region in the regions of interest on each CT image, and by means of a deep learning model framework, training to obtain a bone aging degree prediction model. The method can intelligently and more accurately predict the degrees of osteoporosis of people under test and whether they suffer from osteoporosis.

The invention relates to the field of online intelligent medical treatment, in particular to a real-time online bone age prediction system and method of a WeChat applet. The method comprises the following steps: acquiring and preprocessing a public CT data set; processing the training image through a segmentation network to obtain a local feature image; the predicted bone age is obtained through the prediction network, and a development percentile and an important joint area are obtained through matching; the online bone age prediction platform builds a front end through a WeChat applet, and designs the front end and a rear end through an applet SDK (Software Development Kit); and generating a report and returning a result to a front end in a JSON format. The lightweight bone age prediction method has the advantages that the lightweight prediction model is obtained through standardized preprocessing, the lightweight bone age prediction model and a template comparison method, and the processing time is effectively shortened. A patient can rapidly obtain multiple standard predicted bone ages, general development conditions and growth problem areas through detailed reports, and then treatment or selective examination is selected in a targeted mode, so that the purposes of saving money and time and conducting preliminary evaluation are achieved.

The invention discloses a method and system for evaluating the bone age of a human body through a three-dimensional ultrasonic image and a medium, and belongs to the technical field of medical image processing and three-dimensional reconstruction. Comprising the following steps: acquiring a three-dimensional ultrasonic image of a human wrist bone; segmenting a bone tissue region of the three-dimensional ultrasonic image to generate a binary mask; converting a pixel region corresponding to the wrist bone tissue in the binary mask into a discrete three-dimensional point cloud; acquiring global features based on the three-dimensional ultrasonic image; the three-dimensional point cloud generates an initial bone surface through Gaussian distribution; iteratively generating a globally continuous UDF field through a UDF predictor; determining each point on the bone surface based on the UDF field, and outputting a smooth bone surface grid model; evaluating block-by-block epiphysis on the bone surface grid model in a grading manner, and calculating the bone age; according to the method, the bone age of the human body can be accurately predicted by using the ultrasonic image.

The invention relates to the technical field of medical image processing, in particular to a children wrist X-ray film bone age prediction system based on deep learning, which comprises a data acquisition module, a time sequence analysis module, a group classification module, a feature fusion module and a prediction optimization module which are in signal connection with one another, the carpal bone feature strengthening module is used for carrying out feature strengthening on a carpal bone time sequence of a gymnastic training group according to carpal bone feature strengthening weights, generating a weighted fusion time sequence, and outputting a dynamic carpal bone age vector and a dynamic RUS bone age vector by respectively capturing a time sequence dependency relationship between RUS bones and carpal bones; and the prediction optimization module is used for constructing a carpal bone dominant prediction channel and an RUS bone auxiliary prediction channel for the gymnastic training group according to the dual-channel deep learning model. According to the invention, through group classification and sequential dynamic feature fusion, in combination with a dual-channel deep learning model, differential bone age prediction and accurate evaluation of carpal development delay of common children and gymnastic training children are realized.

1. Name of the design product: bone age instrument base. 2. Use of the design product: the design product is used for detecting bone age. 3. Design points of the design product: combination of shape and pattern. 4. Picture or photo best indicating the design points: perspective view. 5. The bottom surface of the design product is the part that is not easy to see or cannot be seen during use, so the top view is omitted.