123 results about "Bone age" patented technology

The application relates to the technical field of bone maturity analysis, and in particular to a bone age recognition method and system and an electronic device. The bone age recognition method includes the a step a of inputting a bone image into a target bone position detection model, and detecting position coordinates of a target bone in the bone image through the target bone position detectionmodel; a step b of cutting out a target bone image according to the position coordinates of the target bone; and a step c of inputting the target bone image into a bone stage classification model forbone age recognition. The bone age recognition method and system and the electronic device in the application adopt deep learning to automatically classify and recognize ulna and radius images withoutmanual intervention, improve the effectiveness and efficiency of bone age recognition and have better performance than the prior art; and also eliminate the need for manual acquisition, save more time and efforts, and are highly efficient.

The invention discloses a web database based online bone age calculating and height predicating method. The method comprises the following steps: dividing hand wrist and bone age level; recording thebase information of testing people; inputting shot hand and wrist X ray images; decoding bone data; calculating the bone age; and calculating the predicated height. The method is applicable to professors with evaluation experience; the works such as general sheet checking, recording and summing can be saved; a computer supports. Therefore, the repeating workload can be greatly decreased; the calculation accuracy is improved; various hand wrist bone development standard data can be stored on the basis of the web database, so that the completeness, the safety and the handleability of the data can be ensured; in addition, different predication results can be examined and compared based on different bone age evaluation standards during use; the web database is adopted, so that the characteristics of high efficiency and expandability are met while a new bone age evaluation standard is added; and the method is high in application and popularization value and economic benefit.

The invention provides a bone age evaluation method based on a two-stage neural network, which comprises the following steps: 1. Adjusting the original input hand bone image size to 512x512, namely scaling according to scale, and adding edge information; 2, extract an image mask; 3, generate a training image; 4, respectively calculating two-dimensional single-scale wavelet transform and Canny operator edge extraction for the image generated in the step 3, and composing three channels of input samples together with the image equalized by the histogram; 5, carrying out data enhancement on the three-channel image generated in the step 4 to expand the data set size; 6. Prediction of bone age; By combining the image segmentation and bone age prediction, the detection method can suppress the noise and segment the hand bone area accurately, so as to evaluate the bone age. For other image processing fields such as target segmentation, target retrieval, target regression prediction and so on, it has practical application value.

The invention discloses an automatic bone age identification system based on an improved residual network, and aims at solving the problem that an automatic deep learning processing means lacks in bone age detection via X ray photos domestically. The method comprises that data enhancement is carried out on a training sample, normalization is carried out, a bone age classification network based onthe improved residual error network is trained, 16 different slide windows are used during test, 16 classification results are predicted, and a classification of highest frequency is obtained.

The invention discloses a bone age prediction method and device based on a deep regression network. The method comprises the following steps: inputting a to-be-processed bone age slice image; according to the multi-level key point detection deep convolutional network, obtaining a epiphyseal area image; and inputting the epiphysis region image into a preset deep learning regression network to obtain an epiphysis grade prediction result, and calculating the corresponding bone age. The technical problem that a bone age prediction method is poor in effect is solved. According to the method and thedevice, the epiphysis grade prediction result can be directly output without linking the epiphysis grade labeling database, and the bone age can be accurately predicted. According to the method, theepiphysis area obtained based on multi-level key point detection serves as input, the epiphysis level prediction result is output through the multi-branch deep regression network after the epiphysis area passes through the convolutional network, and the obtained prediction effect is good.

A method and device for classifying bone age pieces are provided in embodiments of the present application, in accordance with one embodiment of that present invention, The method comprises: obtaininga bone age piece of a user to be detected, Adjust the bones in the bone age pieces to the reference position, and then inputting the adjusted bone age pieces into the classification model to determine the types of bone age pieces. The classification model is determined after training the depth residual network with multiple bone age pieces of pre-labeled bone age pieces. The types of bone age pieces include left hand, right hand and non-hand. As a plurality of bone age pieces of a pre-marked bone age piece type are taken as a training sample, After the depth residual network is trained, the classification model is determined, and then the classification model is used to determine the type of bone age piece of the user to be detected, and the bone age piece of the left-handed type is usedto detect the bone age of the user to be detected, thus avoiding the problem of low detection accuracy caused by the non-standard bone age piece.

The invention discloses a bone age prediction method based on deep learning. The bone age prediction method comprises the following steps: step 1, obtaining the size of a target bone self-adaptive shear frame according to the age, gender and present height; step 2, performing automatic shearing according to the size of the shear frame and the coordinates of the target bone center point to obtain atarget bone picture; step 3, inputting the picture obtained in the step 2 into a bone development grade classification model for recognition to obtain a predicted development grade of each bone; andstep 4, referring to the score table of each bone development stage of a CHN method and a CHN method bone development maturity score and bone age comparison table to obtain a final bone age predictionresult. The invention also provides a bone age prediction system based on deep learning. The method has better stability and accuracy.

The invention relates to the field of image recognition, and discloses a bone age prediction method and device, a medium and electronic equipment. The method comprises the steps: acquiring to-be-predicted hand bone data; determining the gender of the to-be-predicted hand bone data; according to the gender, inputting the to-be-predicted hand bone data into a convolutional neural network model corresponding to the gender to obtain a predicted bone age output by the convolutional neural network model, wherein the convolutional neural network model is obtained by training in advance based on a triple loss function and a regression loss function. According to the method, the bone age prediction is carried out by utilizing the convolutional neural network model obtained by training based on thetriple loss function and the regression loss function, so that the bone age prediction efficiency is improved, the bone age prediction cost is reduced, and the bone age prediction accuracy is improved. In addition, the hand bone data of the corresponding gender is predicted specially by using the convolutional neural network model of the specific gender, so that the bone age prediction accuracy isfurther improved.

Embodiments of the present application provide a method and a device for detecting bone age, which relate to the technical field of machine learning. The method comprises the following steps: acquiring a bone age sheet of a user to be detected; and determining the position of each target epiphysis in the bone age sheet by using a positioning model. For each target epiphysis, the bone age score ofthe target epiphysis is determined according to the characteristics of the target epiphysis and the position of the target epiphysis, and finally, the bone age of the user to be detected is determinedaccording to the bone age score of each target epiphysis. Because the different forms of epiphysis represent different stages of bone age, there are also some differences in the shape of the epiphyses at different locations, as such, embodiment of that present application employ a positioning model to automatically determine the position of the target epiphysis, then, the bone age score is determined based on the characteristics of target epiphysis and the position of target epiphysis, and the bone age of the user to be detected is determined based on the bone age score, without artificial subjective judgment of bone age according to bone age slices, so that on the one hand, the precision of detecting bone age is improved, and on the other hand, the efficiency of detecting bone age is improved.

The invention provides a remote online bone age interpretation system capable of realizing remote online interpretation for bone age films, and belongs to the field of health assessment. The bone age refers to bone development age, can reflect body development situations objectively and has great significance in the aspects of bone age judgment in athletic contests, evaluation of adolescents' growth and development, prediction of adult height, selection of athletes, auxiliary diagnosis of metabolic diseases and the like. However, the bone age interpretation is required to be carried out by professionals, besides, the popularizing rate of special bone age equipment is lower, the probability of time delays between X-ray film shooting and the interpretation is high, and the process from the X-ray film shooting at hospital to the interpretation of a bone age result by the professionals is tedious, time-consuming and labor-consuming. The remote online bone age interpretation system can realize multiple functions such as digitization of bone age film collection, automatic film uploading, online interpretation of the bone age films, immediate feedback of the interpretation result and the like, greatly facilitates bone age testing, and has substantial significance for general survey of growth and development level, rapid interpretation of the bone age result and the like.

The embodiment of the invention provides a bone age detection method. The bone age detection method comprises the following steps: acquiring basic information of a target user provided by a client; acquiring hand skeleton image information of a target user; inputting the hand bone image information into a first bone age evaluation model so as to output a first probability corresponding to each first bone age stage through the first bone age evaluation model; determining the first bone age stage with the highest first probability as preliminary bone age information of the target user; inputtingthe basic information of the target user and the preliminary bone age information into a second bone age evaluation model so as to output a second probability corresponding to each second bone age stage through the second bone age evaluation model; and determining the second bone age stage with the highest second probability as the final bone age information of the target user, generating an electronic diagnosis form according to the final bone age information, and sending the electronic diagnosis form to the client. According to the embodiment of the invention, bone age detection efficiencyand detection accuracy are effectively improved.

The invention discloses an ultrasonic bone age detection system and method. The method includes the steps of 1, soaking to-be-detected tissue in a coupling medium, partially dipping a scanning windowinto the coupling medium to contact with the to-be-detected tissue, setting a contact pressure threshold and fixing the scanning window; 2, adjusting an ultrasonic probe in position and angle according to an ultrasonic image of the hand to allow the long axis of the ultrasonic probe to be perpendicular to the tangent plane of the to-be-tested tissue during scanning; 3, setting a scanning parameterand performing scanning to acquire an ultrasonic bone age image of the to-be-detected tissue. The image of a bone age feature area is acquired through the ultrasonic bone age detection system to assess the bone age of children, imaging quality is guaranteed after completion with one-time scanning, wide-field of view is achieved, and the problem about operator dependency is solved; a children's skeletal system has more cartilage compositions and ultrasonic imaging is superior to adults in terms of acoustic transmission, so that the ultrasonic bone age detection system and method is applicableto bone age detection in children.

A method of automatically assessing skeletal age of hand radiographs, comprising: providing a radiographic image of both two hands; cropping a first image of the left hand or the right hand; rotating the first image to make the fingertip of the medius point upwards the vertical; cropping a second image of the medius; segmenting the phalanges of the medius to acquire a third image; extracting a plurality of physiological features of the third image to acquire a first data; extracting a plurality of morphological features of the third image to obtain a second data; delivering the first data and the second data to a neural network for training; and outputting an assessment of the skeletal age.

Embodiments of the present application provides a method and apparatus for detecting bone age, and relates to the technical field of machine learning. The method comprises the following steps: acquiring a bone age slice of a user to be detected, adjusting each bone in the bone age slice to a reference position, determining a wrist bone region from the bone age slice, then determining the number ofossification centers in the wrist bone region by using a classification model, and finally determining the bone age of the user to be detected according to the number of ossification centers in the wrist bone region. Because the number of ossification centers in the carpal region represents different bone age stages, as such, embodiments of the present application employ classification models toautomatically determine the numb of ossification centers in the carpal region, then, the bone age of the user to be detected is determined according to the number of ossification centers in the wristbone region, without artificial subjective judgment of bone age according to bone age slices, so that on the one hand, the precision of detecting bone age is improved, and on the other hand, the efficiency of detecting bone age is improved.

The invention discloses an image processing method and device, an equipment storage medium and a growth and development evaluation system, and the method comprises the steps: obtaining a medical image; Inputting the medical image into a preset neural network-based image processing model for calculation to obtain an image processing result corresponding to the medical image, Wherein the image processing result comprises a bone age prediction result and / or a bone center positioning result. According to the method, the bone age prediction task and the calcanization center positioning task can belearned at the same time, the image processing result is obtained, and rapid and accurate bone age prediction is achieved.

The invention provides a random calibrating device of a digital measuring instrument of bone mass density and bone age. A built-in bone template is set in an X-ray channel. A light target of imaging mechanism of measuring instrument is provided with human bones to be measured and X-ray projection area of built-in bone template. The imaging mechanism outputs the gray scale digital quantity of the built-in bone template to a computerization system of the device, wherein the computerization system is provided with a display interface of dialog window for displaying the gray scale digital quantity and setting value of gray scale of bone mass density stored by correcting the computerization system based on the gray scale digital quantity of the built-in bone template. The built-in bone template provides a bone mass density calibrating value which is stochastically displayed for the measuring instrument, so that the corresponding level of the setting value of gray scale of bone mass density stored in the computerization system can be corrected at any moment based on the setting value and the corrected setting value is accurate contrast basis value under running circumference of the measuring instrument. The bone density value of the subject is contrasted with the accurate contrast basis value therefore the result is surely right. The invention has outstanding advantages, such as detecting and adjusting the test reference of the measuring instrument at any moment and being convenient to use.

The invention relates to an establishing method for a juvenile height predication model. The establishing method comprises the following steps of: tracking and testing height and bone ages per year of N juveniles from S years old to (S+M-1) years olds for M years, and recording life ages of the juveniles in those years; measuring height, at the age of (S+M) years old, of the N juveniles; constructing a sample set by utilizing the life ages, the height and the bone ages per year of the N juveniles from S years old to (S+M-1) years old; establishing a ternary linear-regression mathematical model by taking the life ages, the height and the bone ages per year of the N juveniles from S years old to (S+M-1) years olds as independent variables and utilizing the height, at the age of (S+M) years old, of the N juveniles as dependent variables; and utilizing a linear-regression analysis tool to obtain a ternary height predication model, at the age of (S+M) years old, of the juveniles through a least square method. The establishing method has the beneficial effects that: the condition that a height predication formula made by utilizing Chinese data is not provided in China for a long term is ended, so that the height predication model which is more suitable for the Chinese is obtained.

The invention provides mixed sizing for preparing a manmade beef bone button. The mixed sizing comprises sizing A and sizing B. The sizing A comprises, by weight, 20-100 parts of unsaturated polyester resin, 5-50 parts of pigment, 0.2-2 parts of accelerant and 0.4-2 parts of initiator. The sizing B comprises, by weight, 800-1200 parts of unsaturated polyester resin, 1.0-8.0 parts of pigment, 5.0-50 parts of soluble fine granular packing, 5.0-80 parts of styrene, 2.0-20 parts of accelerant and 4.0-20 parts of initiator. The prepared manmade beef bone button is made of the unsaturated polyester resin material which is wide in source and low in price, the manmade beef bone button has the bone stripe texture and the bone age texture like natural beef bone buttons, and the stability is controllable after the button is dyed.

The invention discloses a bone age prediction method. A preset training set is trained in advance to form a bone age prediction model, and the bone age prediction model is used for bone age prediction. According to the technical scheme, through a brand-new attention mechanism adding mode, tan attention mechanism is added in a targeted mode according to different convolution layer information coupling degrees in the bone age prediction model, and the problem that a traditional attention mechanism is not easy to converge is solved; gender information is directly added into the neural network model for end-to-end training, and the accuracy of bone age prediction is further improved while the training process is optimized; the bone age prediction model used in the bone age prediction method isvisually verified through the attention mechanism, it is reflected that the model more pays attention to the hand bone part where the development degree of a patient is presented in a centralized mode, and a good prediction effect is achieved.

The invention provides X-ray imaging equipment. The X-ray imaging equipment comprises an array X-ray source, a collimator and an X-ray flat panel detector, wherein the array X-ray source is used for emitting array X-ray beams; the collimator is used for collimating the emitted array X-ray beams and irradiating the collimated array X-ray beams to a test object; the X-ray flat panel detector is used for receiving the array X-ray beams penetrating through the test object, and an X-ray photography image is formed by utilization of the received array X-ray beams. By the adoption of the combination of the array X-ray source and the collimator, the X-ray beams approximating parallel and an area source is formed, and it is avoided that as hand bone images are easily overlapped, judgment of a doctor on the bone age is affected; compared with an ordinary X-ray DR technology, as the distance between the hand and the X source is not increased, the size of the whole equipment is reduced, and portability is improved; unnecessary radiation is reduced, and therefore injury to human health is reduced.

The embodiment of the present application provides a method and apparatus for detecting bone age. The method comprises: obtaining a bone age piece of a user to be detected, and adjusting the bones inthe bone age tablet to the reference position, determining a thumb bone region from that bone age slice, then identifying the medial thumb sesamoid in the thumb bone region by using the recognition model, which is determed by taking the bone age slices of the thumb bone region pre-marked with the medial thumb sesamoid as the training samples, and training the depth residual network after, finally,determining the bone age of the user to be detected according to the recognition results of the medial thumb sesamoid. Since the appearance of the medial thumb sesamoid represents a specific bone agestage, the recognition model is used to identify the medial thumb sesamoid bone, and the bone age of the user to be detected is determined according to the recognition result of the medial thumb sesamoid bone, so that the artificial subjective judgment of the bone age according to the bone age sheet is not required, thereby improving the precision of detecting the bone age on the one hand, and the efficiency of detecting the bone age on the other hand.

A digitalizing method and device for measuring the bone age features that a line scan technique is used to scan the various positions on human body in moving mode and the obtained scanned images can be further processed by computer. Its advantages are high sensitivity and efficiency, wide range, and low cost.

The invention discloses a key point extraction and bone age prediction method in a hip joint image, and the related key point extraction comprises the steps: carrying out the feature extraction of thehip joint image through a feature extraction network, and obtaining a thermodynamic diagram of a C channel through down-sampling; wherein the feature extraction network is trained in advance by utilizing hip joint images containing key point positions marked by experts; according to the thermodynamic values, detecting N positions with the highest thermodynamic values from the thermodynamic diagram of the C channel to serve as key points; wherein C and N are both natural numbers, and C is greater than N; and compensating the position deviation of the N key points caused in the down-sampling stage by predicting the key point deviation loss to obtain the final positions of the N key points. According to the method, the key points can be accurately and quickly extracted, the working intensityis greatly reduced, and bone age prediction can be realized.

The ultrasonic method of measuring bone age and bone growth plate development degree belongs to the field of measurement technology. The technological scheme includes sampling over 600 children of 1-10 years old as measuring check samples; measuring the sound velocity in the children's radius and treating the measured results to obtain the average children's bone sound velocity as the standard value of average children's bone sound velocity in the said age range; and measuring the bone sound velocity and bone growth plate sound velocity of the measured child and comparing with the standard value so as to evaluation result of the bone age and bone growth plate development degree of the measured child. The present invention avoids the jamming on the measurement process and opens one new way of judging child's bone age and bone growth plate development degree objectively and quantitatively.

The invention discloses an X-ray image bone age evaluation method based on non-downsampled contour wave transform and convolution neural network, includes such steps as non-downsampled contour wave transformation of normalized size X-ray image, The high-frequency directional subbands and a low-frequency coefficient map at several scales are obtained, and then they are input into a multi-channel convolutional neural network to obtain the characteristic maps at different scales. Finally, these characteristic maps are stacked together and input into a regression network composed of several connected layers to obtain the bone age prediction values. The above process is implemented in an end-to-end network structure, and error back propagation mechanism is used to achieve network training. Themethod of the invention utilizes the non-down sampling contour wave transform to pre-extract and separate the features of the original spatial domain image, can overcome the difficulty of network training of the existing depth learning method on the small-scale data set, improve the generalization performance of the network, and thus provides a more accurate and reliable evaluation method for clinical application.

The CHN method region of interest extraction method based on the shape information and the convolutional neural network comprises the steps of 1, determining the size of a boundary frame of a reference bone, and 2, positioning key points of the reference bone. The CHN method calculates the bone age by evaluating the maturity indications of 14 reference bones. The method conforms to the growth anddevelopment law of Chinese contemporary teenagers. According to the method, the high universality is ensured while the accurate extraction of the reference bone region of interest is ensured. The reference bone frame size is mainly used for determining the widths of fingers and wrists according to the shape information of the wrist part, and the boundary frame size of 14 reference bones is obtained according to different weights; in the positioning of the key points of the reference bone, regression prediction is carried out mainly through a self-built convolutional neural network model, and key point coordinates of 14 reference bones are obtained. After the frame size and the coordinates of the reference bone are obtained, the regions of interest of the reference bones can be extracted.

The invention provides a method and a detection device for skeletal age analysis. The device comprises a printer and a skeletal age analysis host both mounted in a control console, wherein a display screen is mounted at the top part of the control console and a film scanner and an interface convertor are respectively mounted on two sides of the display screen; and the interface convertor is connected with a network accessing end through a data cable. The method comprises the following steps: 1, early preparation; 2, scanning or transmission; 3, related information inputting; 4; pre-processing for all input information and data by the skeletal age analysis host; and 5, outputting analysis data by the skeletal age analysis host, displaying on the display screen, and printing out the analysis result by the printer. According to the invention, the method and the device exempt skeletal age evaluation from interference by factors including physician level, medical diagnosis condition and the like, and as a result, seeing a doctor of a rural patient is facilitated, at lower expense.

The invention discloses an intelligent adjusting air conditioner. The intelligent adjusting air conditioner comprises a machine shell, a negative oxygen ion generator, a sleep monitoring module and acontrol module, wherein the machine shell is provided with an air inlet and an air outlet; the negative oxygen ion generator is arranged in the machine shell; the sleep monitoring module is used for detecting the sleep state of a user in real time; the control module is in communication connection with the negative oxygen ion generator and the sleep monitoring module; and a bone age detection module is arranged in the control module. According to the intelligent adjusting air conditioner, the bone age detection module is arranged in the control module, meanwhile, the identity information and the like of the user are stored, whether the bone age of the user is backward in development or not can be easily judged, so that whether the negative oxygen ion generator is started or not is judged,and the deep sleep time of the user is prolonged; and on the other hand, the sleep state of the user is monitored in real time, so that the negative influence on the growth of bones due to long-time continuous release of negative oxygen ions is avoided.

The invention discloses a method for automatically identifying a bone age image after digital processing, which comprises the steps of image collection, image preprocessing, target prediction and result reporting, and is characterized in that according to a bone development grade standard of a CHN method, 14 target bone areas of an image sample are respectively marked by using an image marking tool in the target prediction; a bone grade identification model trained through deep learning is adopted to position, segment and classify 14 target bone areas, then according to physiological data of a testee and according to a score table of bone development stages of a CHN method, bone grades of all the target bone areas are converted into different scores and accumulated, and the scores of all the target bone areas are obtained. And finally, the corresponding bone age is calculated according to the comparison table of the bone development maturing score and the bone age of the CHN method, so that the problems of long time consumption and low precision of bone age film reading are solved, and favorable support is provided for rapid evaluation of the bone age.