35 results about "Bone age assessment" patented technology

The invention provides an X-ray film bone age prediction method and system based on deep learning. According to the invention, a bone age prediction result is finally formed through performing preprocessing on an X-ray image of a teenager, automatic segmentation of a hand bone area and bone age prediction. The method comprises a hand bone X-ray film preprocessing and sample data enhancement method, a hand bone X-ray film image block sampling method, a hand bone automatic segmentation algorithm and a transfer learning based hand bone X-ray film bone age assessment algorithm, and finally designsa hand bone X-ray film bone age prediction system taking Dicom data as input. Users only need to select a hand bone X-ray film with the bone age to be predicted, the segmentation and prediction process is completely automatic, and doctors are not required to perform region marking or selecting, and a powerful tool is provided for bone age assessment in scientific research and clinical practice.

The invention discloses a bone age mark identification assessment method and system based on deep learning and image omics. The bone age mark identification method includes the steps: performing preprocessing of window adjusting, alignment and standardization on the wrist bone image; using a bounding box to mark the bone age characteristic areas and mark the coordinates, wherein the bone age characteristic areas include a metacarphphalangeal group and a brachidium group according with a TW3 method; according to the requirement, performing augmentation processing, and inputting the wrist bone image data to a convolutional neural network of the area based on ResNet-101 to perform multi-task (positioning, classification and assessment) training at the same time; and based on the bone age characteristic areas, combining with the clinic information (demographic characteristics and inspection reports) to further train and improve the bone age assessment speed and accuracy. The bone age markidentification assessment method and system based on deep learning and image omics firstly utilize a small number of marked samples to perform preliminary training on the bone age model, and utilize the model with relatively higher positioning detection accuracy to automatically mark a large number of samples so as to realize automatic positioning, classification and bone age assessment of the bone age characteristic areas.

The invention discloses a bone age evaluation method based on bone and joint quantized-information integration of a hand bone X-ray film. The method comprises the following steps: step 1, collecting picture samples of hand bone X-ray films, and classifying the samples according to genders and age stages to obtain grouping information; step 2, labeling and dividing bone and joint positions of the samples; step 3, inputting preprocessed sample images and real position information into the convolutional neural network to carry out iteration training to obtain position information and feature mapsof bones and joints; step 4, calculating morphological feature parameters of the bones and the joints in the samples; step 5, fusing the feature maps and morphological features of the bones and the joints into mixed feature information, and inputting the same and the grouping information together into a convolutional neural network model for iteration training; and step 6, completing model training, and carrying out bone age evaluation application. By utilizing the invention, a bone age can be more simply, conveniently and quickly evaluated on the premise of reducing human factor interference.

The invention provides a hand bone X-ray film bone age assessment method and device, computer equipment and a storage medium. The method comprises the steps that a hand bone X-ray film with the bone age to be predicted is processed to be a hand bone photo with the specified pixel requirements; the hand bone photo is input into a preset convolutional-neural-network-based bone age assessment model for conducting calculation; a calculation result output by the bone age assessment model is obtained, wherein the result is the bone age of the hand bone. According to the hand bone X-ray film bone ageassessment method and device, the computer equipment and the storage medium, by means of the convolutional-neural-network-based bone age assessment model, bone age assessment can be conducted automatically, and the assessment accuracy rate is high.

A method and an apparatus for estimating bone age by at least one acoustic signal in an ossification-actuated skeletal structure. The apparatus includes an acoustic transmitter and an acoustic receiver positioned facing each other so that the structure is positioned between them. The structure has at least two bones. The transmitter is adapted for transmitting a signal to cross the structure transversely. An electronic moveable gantry is provided for adjusting the position of the acoustic transmitter and the acoustic receiver in relation to the structure. A computer system is enabled to perform one or more functions to position the moveable gantry; transmit the signal by the transmitter; control the signal transmitted by the transmitter; receive the transmitted signal by the receiver; and estimate bone age responsive to the received signal by at least one bone age calculation formula.

The invention discloses a bone age assessment method, which is characterized by comprising the steps of A, acquiring X-ray images of a plurality of target bone parts, and grading the acquired X-ray images according to the age group; B, performing feature extraction on a plurality of X-ray images in each grade, converting each grade of X-ray images into data by using a directional gradient histogram feature method, and building a mathematical model; and C, classifying the X-ray images in which the bone age is required to be assessed into the above grades by using a support vector machine classification algorithm. According to the bone age assessment method disclosed by the invention, an image processing technology and a computer vision technology are combined, and judgment for the bone maturity is realized through an interactive or automatic method.

The invention discloses a bone age evaluation method based on a convolutional neural network and a multiple attention mechanism. The method comprises the following steps: in a training stage, taking ametacarpal bone image as the input of a backbone network, obtaining a feature map F through a feature extractor, and obtaining a bone age regression value; taking the input of a multi-attention module as a feature map F, obtaining M sub-attention maps through compression operation and attention map splitting operation, conducting point multiplication of each sub-attention map with the feature mapF, and then obtaining a corresponding bone age regression value; combining a backbone network with the bone age regression value obtained by the multiple attention module, and training a neural network by adopting a multi-task learning strategy; and in a test stage: inputting a to-be-tested metacarpal bone image into the trained neural network, and obtaining a bone age evaluation value through the backbone network. The model can be trained end to end; meanwhile, an attention distribution diagram can be automatically generated, and better generalization is achieved; and in addition, based on the 2D convolutional neural network, the speed is high, the precision is high, and an average evaluation error is within 4.1 months.

The invention discloses a bone age evaluation method for realizing image segmentation and classification based on deep learning. The method comprises the following steps of: 1, processing a data set by using a digital image processing method to obtain sample data with higher quality; 2, manually marking a part of hand bone images, training an image segmentation network U-Net by using the part of images, then segmenting the data set by using the trained U-Net to obtain a background-removed data set, and making a training set, a verification set and a test set according to a certain proportion;3, training an improved image classification network VGG16 by using the processed data set; and 4, testing the trained model by using the test set and evaluating a result. Compared with an original bone age evaluation method, the improvement method provided by the invention effectively improves the accuracy of evaluating the hand bone image by the model, and has higher efficiency at the same time.

The present disclosure provides a bone age assessment and height prediction system including an image capturing unit and a non-transitory machine readable medium. The image capturing unit is for obtaining a target x-ray image data of a subject. The non-transitory machine-readable medium is for storing a program for assessing the development of the bones of a hand and the bone age of the subject, and predicting the adult height of the subject when executed by a processing unit. Therefore, the bone age assessment and height prediction system of the present disclosure can effectively improve the accuracy and sensitivity of the bone age assessment and the height prediction, and the time for assessing the bone age and predicting the height can be further shorten.

The invention relates to a bone age assessment method and system. The method is applied to Raspberry Pi and comprises the following steps of: receiving a bone age assessment request; acquiring a hand bone image and a user gender corresponding to the hand bone image according to the bone age assessment request; and performing cutting and histogram matching on the hand bone image, performing numerical conversion on the user gender, transmitting the user gender to a nerve calculation rod, and performing bone age assessment according to the hand bone image and the user gender through a pre-trained bone age assessment model deployed in the nerve calculation rod. By adopting the method, the safety can be improved, and meanwhile, the processing speed is increased to improve the assessment efficiency.

The invention discloses a hand bone X-ray image texture feature extraction method for bone age evaluation. The invention can obtain texture features corresponding to the contribution degree of the shape features by processing the bones including the radius, the ulna and the short bones. The invention reasonably samples the image texture, obtains the texture features containing rich growth information, and combines the shape features to remarkably improve the accuracy of bone age evaluation.

According to an embodiment of the present disclosure, a method of assessing bone age by using a neural network performed by a computing device is disclosed. The method includes receiving an analysis image which is a target of bone age assessment; and assessing bone age of the target by inputting the analysis image into a bone age analysis model comprising one or more neural networks. The bone age analysis model, which is trained by supervised learning based on an attention guide label, includes at least one attention module for intensively analyzing a main region of the analysis image.

The invention discloses an automatic hand bone segmentation method based on a template. At first, a bone age sample database is established. Then samples are trained and templates is created, in thesame period of time, templates are createdfor all segments of the bone respectively. Finally, hand bone segmentation is performed based on template. The method extracts intact bone shape features including epiphysis, and more bone development information is contained. At the same time, the method avoids falling into endless tuning parameters; And through the training set update method, the workload of manual annotation is effectively reduced. The invention solves the problem of hand bone segmentation and provides a powerful tool for subsequent bone age assessment.

The invention relates to a progressive bone age assessment method based on multi-granularity feature fusion. The granularity grading module based on a random puzzle mode is constructed, granularity information contained in an input picture is graded from fine to coarse, and rich local features of all parts of a hand bone are learned through a network; and by constructing a progressive multi-scale feature fusion module, the network is iterated for multiple times, so that global features and local features with most differentiated positions can be learned, other local features can be fused, features containing different granularity information can be learned finally, and the performance and generalization ability of a bone age evaluation model are greatly improved. According to the method, the most distinguished RoIs local features can be concerned, other local features with different granularities can be fused together in a collaborative mode, and higher robustness is achieved.

The invention discloses a hand bone key region acquisition method based on a convolutional neural network and multi-granularity attention. The method comprises the following steps: 1, acquiring a data set containing bone age information of a hand bone; 2, constructing a bone age evaluation network containing multi-granularity attention; 3, performing off-line training on the established bone age evaluation network; and 4, acquiring a key area of the hand bone by utilizing attention in the trained network. According to the method, the key region of the hand bone can be obtained only through the bone age label of the hand bone, the obtained key region is consistent with a key region used by a TW3 method, and the difficulty that an existing key region obtaining method depends on manual labels is overcome.

The invention discloses a bone age evaluation method based on feature region grade identification. The method comprises the following steps: segmenting 14 specific bones for bone age evaluation from each whole palm bone; using three data enhancement technologies to expand a data set and increase the generalization ability of the network; and introducing a double-attention convolution model to train each bone to obtain a bone maturation grade evaluation model. Different from a traditional evaluation intelligent model based on the whole palm, the method introduces an attention mechanism to carryout joint analysis on the cut local feature map, and the evaluation accuracy is further improved. The test result is superior to that of a bone age automatic evaluation method based on a whole palm bone image.

A bone age deriving device is proposed. The device, according to the present disclosure, may: determine, from a plurality of segmented images formed by segmenting an input image formed by capturing a human body, a highest-priority first segmented image of a first human body part among a plurality of human body parts; process each of a plurality of first pixels of the first segmented image on the basis of a reference value derived from all the pixels of the input image; select, from a reference image set, a first reference image for the first human body part; determine whether a partial region matching with the first reference image is present on the basis of the result of an operation between the first pixels, of the first segmented image, processed by the reference value, and second pixels, of the first reference image, corresponding to the first pixels; determine, on the basis of the first reference image, the bone age level of the first human body part represented by the partial region; and derive the bone age of the human body on the basis of the bone age level.

According to an embodiment of the present disclosure, a computer program stored in a computer readable storage medium is disclosed. The computer program includes instructions for causing one or more processors to estimate bone age from a bone image, and the instructions include: estimating a RUS score for each of one or more partial bone images using a partial bone RUS score estimation model comprising one or more layers, and wherein the one or more partial bone images are generated from a whole bone image; and estimating bone age corresponding to the whole bone image using one or more RUS scores estimated for each of the one or more partial bone images, in which the partial bone RUS score estimation model is trained by using a labeled partial bone image as training data, and is trained by adjusting feature values calculated from the one or more layers.

The invention discloses a weighted bone age evaluation method and system based on deep learning. The method comprises the following steps: preprocessing an X-ray image of a hand bone of a tester; then carrying out coarse segmentation to respectively obtain a carpal bone and radioulnar bone region-of-interest set and a region-of-interest set corresponding to different metacarpal and phalanx; inputting the roughly segmented region-of-interest set into a hand bone fine segmentation model to obtain a plurality of finely segmented hand bone regions-of-interest; inputting a hand bone classification rating model to obtain a classification and development grade corresponding to each hand bone; according to the metacarpal and phalanx and ulna development maturity evaluation chart, obtaining the bone age evaluated by the RUS-CHN method according to the classification and development grade corresponding to each hand bone; according to the wrist bone development maturity evaluation chart, obtaining the bone age evaluated by the TW3-C Carpal method according to the classification and development grade corresponding to each wrist bone; and carrying out weighted summation on the bone ages evaluated by the two methods to obtain a final bone age evaluation result of the testee.

The invention relates to a bone age evaluation model establishing method based on fuzzy labels. According to the method, one-hot tags are converted into Gaussian distribution fuzzy tags with different amplitudes, and meanwhile, the most distinguished local features are erased, so that the network not only can pay attention to the features of the most distinguished region, but also can efficiently extract the local features of other regions and fuse the local features, the evaluation performance of the model is improved, and the robustness of the model is enhanced.

The invention provides an X-ray film bone age prediction method and system based on deep learning. According to the invention, a bone age prediction result is finally formed through performing preprocessing on an X-ray image of a teenager, automatic segmentation of a hand bone area and bone age prediction. The method comprises a hand bone X-ray film preprocessing and sample data enhancement method, a hand bone X-ray film image block sampling method, a hand bone automatic segmentation algorithm and a transfer learning based hand bone X-ray film bone age assessment algorithm, and finally designsa hand bone X-ray film bone age prediction system taking Dicom data as input. Users only need to select a hand bone X-ray film with the bone age to be predicted, the segmentation and prediction process is completely automatic, and doctors are not required to perform region marking or selecting, and a powerful tool is provided for bone age assessment in scientific research and clinical practice.

The invention provides a double-bone age evaluation method based on joint global and local convolutional neural network features. The method comprises the following steps: acquiring a hand bone total graph and gender information corresponding to a tester, and an epiphysis area image corresponding to each epiphysis area to be rated extracted from the hand bone total graph; a bone age assessment task and an anatomical local epiphyseal area maturity rating task are combined to utilize global features and local features at the same time, so that the performance of the bone age assessment method is improved.

The invention discloses a bone age assessment method based on a convolutional neural network and a multiple attention mechanism, including: in the training stage, the backbone network input is a metacarpal bone image, a feature map F is obtained through a feature extractor, and then a bone age regression value is obtained; multiple The input of the attention module is the feature map F, and M sub-attention maps are obtained through the compression operation and the attention map splitting operation, and each sub-attention map is multiplied by the feature map F to obtain the corresponding bone age regression value; combined with the backbone network and multiple The bone age regression value obtained by the attention module is used to train the neural network with a multi-task learning strategy; in the test phase, the metacarpal image to be tested is input into the trained neural network, and the bone age evaluation value is obtained through the backbone network. The above model can be trained end-to-end; at the same time, it can automatically generate an attention distribution map, which has better generalization; in addition, based on a 2D convolutional neural network, it is fast and accurate, and the average evaluation error is within 4.1 months.

The invention discloses a bone age evaluation method based on fine-grained image classification. The bone age evaluation method comprises the following steps: 1) acquiring an X-ray film image of a left hand wrist bone; 2) inputting a bone age evaluation network based on fine-grained classification designed in the invention to carry out bone age evaluation; and step 3) obtaining a bone age evaluation result. According to the method, the bone age of the left hand wrist bone X-ray film is evaluated by utilizing a fine-grained image classification method, a bone age evaluation network based on fine-grained image classification is designed and realized, and during bone age evaluation, the to-be-evaluated X-ray film and the gender corresponding to the X-ray film only need to be input, so that the evaluated bone age value can be obtained. For an input X-ray film, the bone age evaluation network can adaptively extract a plurality of regions of interest containing most feature information, and accurate bone age evaluation is performed by using image features of the regions of interest. The method can be used for accurately evaluating the bone age of the left hand wrist bone X-ray film of the teenagers of 0-18 years old, and has a relatively high application value.

A method for bone age assessment of hand bone X-ray films based on heterogeneous data fusion network, comprising the following steps: Step 1, preprocessing the X-ray film images, extracting the wrist bone parts in the images; Step 2, constructing a convolutional neural network to extract Image features; Step 3, build a text feature extraction model; Step 4, build a fusion layer, merge image features and text features; Step 5, model training, after full convergence, save and export the model structure and weight parameters; use the fusion obtained from training Network for bone age assessment on x-rays of hand bones. The present invention can utilize the text information and the X-ray film image information to analyze the hand bone X-ray film to obtain accurate bone age.

The invention relates to a weakly supervised deep learning automatic bone age evaluation method which comprises the following steps: marking bone age physiological anatomy key points for each X-ray film by taking a hand X-ray film as image data; constructing and training a neural network model, wherein the neural network model comprises a Faster R-CNN model and a U-net model, the Faster R-CNN model extracts a palm skeleton region and joint regions, and the joint regions comprise phalanx joints and elbow joints of fingers and comprise 16 joint regions in total; the U-net model extracts hand features of a palm skeleton area and key point features of a finger area; and summing the scoring result prediction values of all the key points, and taking a sum value as a bone age prediction value. The method has the advantages that the doctor experience is gathered in the data set to form the doctor group experience to label the data set, the X-ray film (image data) used for prediction each timecan be used as a new element to be supplemented into the data set, and the data set can be continuously expanded and accumulated.

The invention discloses a bone age mark identification assessment method and system based on deep learning and image omics. The bone age mark identification method includes the steps: performing preprocessing of window adjusting, alignment and standardization on the wrist bone image; using a bounding box to mark the bone age characteristic areas and mark the coordinates, wherein the bone age characteristic areas include a metacarphphalangeal group and a brachidium group according with a TW3 method; according to the requirement, performing augmentation processing, and inputting the wrist bone image data to a convolutional neural network of the area based on ResNet-101 to perform multi-task (positioning, classification and assessment) training at the same time; and based on the bone age characteristic areas, combining with the clinic information (demographic characteristics and inspection reports) to further train and improve the bone age assessment speed and accuracy. The bone age markidentification assessment method and system based on deep learning and image omics firstly utilize a small number of marked samples to perform preliminary training on the bone age model, and utilize the model with relatively higher positioning detection accuracy to automatically mark a large number of samples so as to realize automatic positioning, classification and bone age assessment of the bone age characteristic areas.

The invention discloses a hand bone X-ray image texture feature extraction method for bone age assessment. The present invention processes bones including radius, ulna, and short bones, and can obtain texture features equivalent to the contribution of shape features. The invention reasonably samples the image texture, obtains texture features containing rich growth information, and can significantly improve the accuracy of bone age assessment in combination with shape features.

The invention relates to an X-ray medical imaging method and a system and a computer storage medium. According to one embodiment, the X-ray medical imaging method comprises the following steps: acquiring an X-ray image of an object to be detected; performing bone age evaluation based on the X-ray image; according to the bone age evaluation result, matching and taking out a preset number of pre-stored images in a preset image library according to a predefined rule; and generating an imaging result based on the X-ray image and the extracted pre-stored image. According to the invention, bone age evaluation can be realized in a conventional X-ray imaging process, a film reader can be assisted to evaluate the bone age condition, and the convenience and accuracy of bone age evaluation are improved.