CN113298780A - Child bone age assessment method and system based on deep learning - Google Patents
Child bone age assessment method and system based on deep learning Download PDFInfo
- Publication number
- CN113298780A CN113298780A CN202110564662.1A CN202110564662A CN113298780A CN 113298780 A CN113298780 A CN 113298780A CN 202110564662 A CN202110564662 A CN 202110564662A CN 113298780 A CN113298780 A CN 113298780A
- Authority
- CN
- China
- Prior art keywords
- hand bone
- image
- bone
- hand
- bone image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
Abstract
The invention discloses a child bone age assessment method and system based on deep learning. The method comprises the following steps: acquiring a hand bone image to be evaluated; preprocessing a hand bone image to be evaluated; inputting the preprocessed image into a trained hand bone segmentation model to obtain a segmented hand bone region mask; fusing the segmented hand bone region mask with the preprocessed image to obtain a hand bone image with background information removed; and inputting the hand bone image without the background information into a trained bone age evaluation model to evaluate the bone age. The invention solves the problems that the evaluation efficiency of the current hand bone X-ray image is too low, the hand bone X-ray image cannot be processed in batch and the like, and relieves the difficulty of a doctor in reading the film. The invention can effectively and automatically evaluate the bone age of the hand bone X-ray image of the child and provides favorable support for the subsequent evaluation of the bone development maturity.
Description
Technical Field
The invention relates to the technical field of bone age assessment, in particular to a children bone age assessment method and system based on deep learning.
Background
In the clinical field, bone age assessment is generally calculated from statistical rules and relatively quantitative indicators by observing the dimensions, structure and degree of closure of the bones in X-ray images of non-conventional hands (typically the left hand). According to the difference between the quantitative index and the identification method, the traditional bone age assessment method can be divided into the following steps: counting, atlas, scoring, etc. Commonly used include G & P atlas, TW2 scoring, TW3 scoring, and the like. The percentage counting method of plum fruit precious, the CHN method of Chinese staff carpal bone development standard, the leaf scoring method which directly quotes TW2 and the like are provided in China. Although all the methods can complete the bone age assessment task, the methods are excessively dependent on manual operation of a professional orthopedist, and the following two problems mainly exist:
first, the process of evaluation is relatively complex. No matter the counting method, the atlas method or the scoring method is adopted, the bone age assessment process is very complex and difficult, the requirement on the professional skills of a practitioner is very high, and the bone age assessment result can be obtained only by analyzing and comparing a large number of data indexes for a long time by the practitioner.
Second, the influence of subjective factors and random errors is large. Due to the complexity of the bone age evaluation process, the same bone age to-be-tested person may have difference in the two bone age evaluations of different doctors, and the personal subjective factors and the service level of the doctors directly influence the evaluation result; the results of two successive bone age evaluations of the same bone age person to be tested by the same doctor may also have differences, and the characteristics of large random error and poor repeatability of the traditional bone age evaluation method are reflected.
Disclosure of Invention
The invention aims to provide a children bone age assessment method and system based on deep learning, which can effectively and automatically assess the bone age of hand bones of children by X-ray images and provide favorable support for subsequent bone development maturity assessment.
In order to achieve the purpose, the invention provides the following scheme:
a children bone age assessment method based on deep learning comprises the following steps:
acquiring a hand bone image to be evaluated;
preprocessing a hand bone image to be evaluated;
inputting the preprocessed image into a trained hand bone segmentation model to obtain a segmented hand bone region mask;
fusing the segmented hand bone region mask with the preprocessed image to obtain a hand bone image with background information removed;
and inputting the hand bone image without the background information into a trained bone age evaluation model to evaluate the bone age.
Further, the preprocessing the hand bone image to be evaluated specifically includes:
the hand bone image to be evaluated enhances local contrast using histogram equalization.
Further, the training process of the hand bone segmentation model specifically includes:
establishing a hand bone image sample library; the hand bone image sample library comprises a plurality of hand bone image samples;
processing the hand bone image sample and labeling a hand bone contour to construct a first data set, wherein the data set comprises a hand bone image training set, a hand bone image verification set and a hand bone image test set;
training a Mask R-CNN model through a hand bone image training set to obtain a hand bone segmentation model;
and optimizing the hand bone segmentation model through the hand bone image test set and the hand bone image verification set.
Further, the training process of the bone age assessment model specifically includes:
segmenting the first data set through a hand bone segmentation model to obtain a hand bone region mask sample;
fusing the segmented hand bone region mask sample with the preprocessed hand bone image sample to construct a second data set; the second data set comprises a hand bone image training set after background information is removed, a hand bone image testing set after the background information is removed, and a hand bone image verification set after the background information is removed;
training the improved Xception model through the hand bone image training set after background information is removed to obtain a bone age evaluation model;
and optimizing the bone age evaluation model through the hand bone image test set after removing the background information and the hand bone image verification set after removing the background information.
The invention also provides a children bone age assessment system based on deep learning, which comprises:
the image acquisition module is used for acquiring a hand bone image to be evaluated;
the preprocessing module is used for preprocessing the hand bone image to be evaluated;
the first input module is used for inputting the preprocessed image into a trained hand bone segmentation model to obtain a segmented hand bone region mask;
the fusion module is used for fusing the segmented hand bone region mask with the preprocessed image to obtain a hand bone image with background information removed;
and the second input module is used for inputting the hand bone image without the background information into a trained bone age evaluation model to evaluate the bone age.
Further, the preprocessing module specifically includes:
and the equalization unit is used for enhancing the local contrast of the hand bone image to be evaluated by histogram equalization.
Further, still include:
the sample library establishing module is used for establishing a hand bone image sample library; the hand bone image sample library comprises a plurality of hand bone image samples;
the first data set construction module is used for processing the hand bone image samples, labeling hand bone contours and constructing a first data set, wherein the data set comprises a hand bone image training set, a hand bone image verification set and a hand bone image test set;
the first training module is used for training a Mask R-CNN model through a hand bone image training set to obtain a hand bone segmentation model;
and the first optimization module is used for optimizing the hand bone segmentation model through the hand bone image test set and the hand bone image verification set.
Further, still include:
the segmentation module is used for segmenting the first data set through a hand bone segmentation model to obtain a hand bone region mask sample;
constructing a second data set, fusing the segmented hand bone region mask sample with the preprocessed hand bone image sample, and constructing the second data set; the second data set comprises a hand bone image training set after background information is removed, a hand bone image testing set after the background information is removed, and a hand bone image verification set after the background information is removed;
the second training module is used for training the improved Xprediction model through the hand bone image training set after background information is removed to obtain a bone age evaluation model;
and the second optimization module is used for optimizing the bone age evaluation model through the hand bone image test set after background information is removed and the hand bone image verification set after the background information is removed.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a children bone age assessment method based on deep learning, which comprises the following steps: acquiring a hand bone image to be evaluated; preprocessing a hand bone image to be evaluated; inputting the preprocessed image into a trained hand bone segmentation model to obtain a segmented hand bone region mask; fusing the segmented hand bone region mask with the preprocessed image to obtain a hand bone image with background information removed; and inputting the hand bone image without the background information into a trained bone age evaluation model to evaluate the bone age. The invention solves the problems that the evaluation efficiency of the current hand bone X-ray image is too low, the hand bone X-ray image cannot be processed in batch and the like, and relieves the difficulty of a doctor in reading the film. The invention can effectively and automatically evaluate the bone age of the hand bone X-ray image of the child and provides favorable support for the subsequent evaluation of the bone development maturity.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flowchart of a method for assessing bone age of a child based on deep learning according to an embodiment of the present invention;
FIG. 2 is a diagram of an improved Xconcept structure according to an embodiment of the present invention;
FIG. 3 is a schematic view of loading a hand bone X-ray image
FIG. 4 is a schematic view of the present loading model;
fig. 5 is a view showing the evaluation result.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a children bone age assessment method and system based on deep learning, which can effectively and automatically assess the bone age of hand bones of children by X-ray images and provide favorable support for subsequent bone development maturity assessment.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1, the method for evaluating the bone age of a child based on deep learning provided by the invention comprises the following steps:
step 101: and acquiring an image of the hand bone to be evaluated.
Step 102: and preprocessing the hand bone image to be evaluated. The hand bone image to be evaluated enhances local contrast using histogram equalization.
Step 103: and inputting the preprocessed image into the trained hand bone segmentation model to obtain a segmented hand bone region mask.
Step 104: and fusing the segmented hand bone region mask with the preprocessed image to obtain the hand bone image with background information removed.
Step 105: and inputting the hand bone image without the background information into a trained bone age evaluation model to evaluate the bone age.
The training process of the hand bone segmentation model specifically comprises the following steps: establishing a hand bone image sample library; the hand bone image sample library comprises a plurality of hand bone image samples; processing the hand bone image sample and labeling a hand bone contour to construct a first data set, wherein the data set comprises a hand bone image training set, a hand bone image verification set and a hand bone image test set; training a Mask R-CNN model through a hand bone image training set to obtain a hand bone segmentation model; and optimizing the hand bone segmentation model through the hand bone image test set and the hand bone image verification set.
The detailed process is as follows:
(1) establishing a hand bone image sample library: collecting left-hand skeleton pieces of the X-ray images, converting the left-hand skeleton pieces into PNG format images, and establishing a hand skeleton image sample library;
(2) image preprocessing: utilizing histogram equalization to enhance local contrast of the image data collected in the step (1), firstly calculating a two-dimensional histogram of an original input image, then adjusting the gray distribution of the histogram through a gray conversion function to enable the histogram to be uniformly distributed in the whole gray level interval range (the gray level interval range is [0, L-1], wherein L is the gray level number of a gray level image), finally modifying the gray level value of the original input image according to the adjusted histogram to complete equalization operation, then utilizing a data labeling tool labelme tool to label the image with a hand bone contour, and dividing the image into a training set, a verification set and a test set;
(3) hand bone image processing
1) Constructing a hand bone segmentation model: inputting images in a training set into a Mask R-CNN model (a conventional model), automatically learning the characteristics of a hand bone region by using ResNet-50 and a characteristic pyramid network, correcting and extracting the deviation between the characteristics and the region of interest by using a RoIAlign layer, predicting and dividing a hand bone Mask by using a full convolution network, continuously adjusting the parameters (learning rate and batch size) of the model in the training process, enabling the model to learn the characteristics of more samples by using the training model to obtain a training model, inputting data in the verification set into each training model, predicting the data in the verification set by using the model, recording the accuracy of each training model, selecting the parameters corresponding to the training model with the best effect, and determining the hand bone division model; inputting the test set data into the hand bone segmentation model for evaluating the performance of the model and the segmentation capability of a target area, adding the images into a training set after the images to be evaluated are segmented, repeating the steps, finely adjusting the training model, continuously optimizing the structure of the training model, improving the generalization capability of the training model, and finally generating the hand bone segmentation model.
2) Hand bone segmentation: inputting the image data preprocessed in the step (2) into a hand bone segmentation model, accurately segmenting a hand bone region mask, and then carrying out image fusion on the hand bone region mask and the original hand bone image, namely after the original hand bone image is segmented by the hand bone segmentation model, the interested regions are white, which indicates that the pixel values of the interested regions are all non-0, and the non-interested regions are all black, which indicates that the pixel values of the non-interested regions are all 0, and carrying out and operation on the hand bone region mask and the original hand bone image to obtain an image only containing the interested regions, namely obtaining the hand bone image with background information removed;
the training process of the bone age assessment model specifically comprises the following steps: segmenting the first data set through a hand bone segmentation model to obtain a hand bone region mask sample; fusing the segmented hand bone region mask sample with the preprocessed hand bone image sample to construct a second data set; the second data set comprises a hand bone image training set after background information is removed, a hand bone image testing set after the background information is removed, and a hand bone image verification set after the background information is removed; training the improved Xception model through the hand bone image training set after background information is removed to obtain a bone age evaluation model; and optimizing the bone age evaluation model through the hand bone image test set after removing the background information and the hand bone image verification set after removing the background information.
The detailed process is as follows:
inputting the hand bone image with background information removed into an improved Xception model (as shown in fig. 2), wherein the improved Xception model is as follows: after the output of an original Xception network (1), firstly aggregating channel information of a feature map by using global maximum pooling (2) and global average pooling (3) to generate two different channel features, secondly sending the two different channel features into a multilayer perceptron (4), performing element-by-element addition on the outputs (5 and 6) of the two different channel features, and finally activating and generating channel attention mapping by a sigmoid function (7) to obtain a channel attention module (which is used for enhancing the feature extraction capability of channel dimensions); after the characteristics output by the channel attention module are input, firstly applying global maximum pooling (8) and global average pooling (9) operations on a channel axis to obtain two-dimensional spatial characteristics, splicing the two-dimensional spatial characteristics into a characteristic diagram, secondly reducing the dimension through a 7 multiplied by 7 convolution kernel (10), and finally activating (11) through a sigmoid function to generate channel attention mapping to obtain a spatial attention module (which is used for enhancing the characteristic extraction capability of spatial dimension); the output is switched into a global average pooling layer (12) and a gender input module is then created with binary gender information (13) as input, the binary gender information being "0" or "1", the male being "1" and the female being "0". The output image characteristic information and sex characteristic information are connected in series through a ReLU activated dense connection layer (14) with 32 neurons, two dense connection layers (15, 16) are connected, each layer is fed by a ReLU activated layer and a dropout (0.2) layer which are connected with 1024 neurons in a close mode, the last layer is formed by a linearly activated dense connection layer (17) with 1 neuron, and the bone age is predicted to obtain a bone age estimation value (18).
Continuously adjusting parameters of the model in the training process, enabling the model to learn characteristics of more samples by the training model to obtain a training model, inputting verification set data into each training model, predicting the data in the verification set by using the model, recording the accuracy of each training model, selecting parameters corresponding to the training model with the best effect, and determining a bone age regression model; inputting test set data into a bone age regression model for evaluating the performance of the model, adding images to be evaluated into a training set after bone age evaluation is carried out on the images, repeating the steps, carrying out fine adjustment on parameters of the training model, continuously optimizing the structure of the training model, improving the generalization capability of the training model, and taking the model with the best bone age evaluation effect as a bone age regression standard model;
specific example 1:
1. bone age X-ray image quantification as digital image
X-ray hand bone images of the left hand from 0 to 18 years of age were collected from various hospitals. In addition, the later marked image to be evaluated is continuously added into the hand bone image sample library.
2. Pretreatment of
Contrast enhancement is carried out on the bone age pictures collected in the step 1, and the hand bone area of the sample is subjected to contour marking by using a labelme tool. After the processing is finished, all the images are divided into a training set, a verification set and a test set according to the proportion of 7:2: 1.
3. Hand bone segmentation
3.1, inputting the images in the training set processed in the step 2 into a Mask R-CNN frame, automatically learning the features of the hand bone region by using ResNet-50 and a feature pyramid network, and correcting and extracting the deviation between the features and the region of interest by using a RoIAlign layer, so that the hand bone region can be accurately segmented by a subsequent full convolution network. Parameters of the model need to be continuously adjusted in the training process, the structure of the model is optimized, and the model is trained to enable the model to learn the characteristics of more samples.
And 3.2 after a plurality of models are trained, inputting the data of the verification set into each model, predicting the data in the verification set by using the models, recording the accuracy of each model, selecting the parameters corresponding to the model with the best effect, and determining the hand bone segmentation model.
3.3 inputting the test set data into the hand bone segmentation model to evaluate the performance of the model and the segmentation capability of the target region. After the images to be evaluated are segmented, the images are added into a training set, the work is repeated, model parameters are finely adjusted, the structure of the model is continuously optimized, the generalization capability of the model is improved, and finally the hand bone segmentation standard model is generated.
And 3.4, carrying out image fusion on the hand bone mask subjected to hand bone segmentation standard model segmentation and the original hand bone image to generate the hand bone image without background information.
4. Bone age assessment
4.1, inputting the hand bone image without the background information obtained in the step 3 into an improved Xcaption model, and firstly extracting the bottom layer characteristics of the image through an original Xcaption network; then, feature mapping is refined from two independent dimensions of a channel and a space through a channel attention module and a space attention module, and more effective features are extracted; and finally, balancing the hand bone development degree difference of different sexes through a gender input module to obtain a bone age estimation value. Parameters of the model need to be continuously adjusted in the training process, the structure of the model is optimized, and the model is trained to enable the model to learn the characteristics of more samples.
And 4.2 after a plurality of models are trained, inputting the data of the verification set into each model, predicting the data in the verification set by using the models, recording the accuracy of each model, selecting the parameters corresponding to the model with the best effect, and determining the bone age regression model.
4.3 input the test set data into bone age regression model to evaluate the performance of the model. And after bone age evaluation is carried out on the images to be evaluated, adding the images into a training set, repeating the work, finely adjusting model parameters, continuously optimizing the structure of the model, improving the generalization capability of the model, and finally generating a bone age regression standard model.
And 4.4, carrying out bone age evaluation on the unavaluated image by using the bone age regression standard model to obtain a bone age evaluation value.
Specific example 2:
as shown in fig. 3-5, the method of the present invention comprises the following steps:
the method comprises the following steps: a user firstly uses an X-ray bone density bone age tester to shoot left-hand bone images of children, all the images are converted into PNG format on the bone age tester, then the images are imported into the system, the system automatically carries out operations such as contrast enhancement, hand bone mask segmentation and image fusion on the images, and the generated hand bone images without background information are stored in a designated folder.
Step two: the user clicks the "select" button to load the hand bone X-ray image with the file path below the image, as shown in figure 3.
Step three: the user clicks the "load model" button to load the bone age regression model, and "model loading is complete.
Step four: the user clicks the "start recognition" button, and the evaluation result is displayed, divided into the recognition result and the predicted time, as shown in fig. 5.
According to the invention, the hand region is segmented by using Mask R-CNN, unnecessary background information can be filtered, noise interference is reduced, a bone age assessment technology is combined with deep learning, high-precision low-delay bone age assessment is realized, a channel attention module and a space attention module are embedded after an original Xconvergence network, feature mapping can be refined from two independent dimensions of a channel and a space, and more effective features are extracted; embedding gender information can balance the difference of hand bone development degrees of different genders through a network, and fine-grained attention is improved. The invention solves the problems that the evaluation efficiency of the current hand bone X-ray image is too low, the hand bone X-ray image cannot be processed in batch and the like, and relieves the difficulty of a doctor in reading the film. The invention can effectively and automatically evaluate the bone age of the hand bone X-ray image of the child and provides favorable support for the subsequent evaluation of the bone development maturity.
The invention also provides a children bone age assessment system based on deep learning, which comprises:
the image acquisition module is used for acquiring a hand bone image to be evaluated;
the preprocessing module is used for preprocessing the hand bone image to be evaluated;
the first input module is used for inputting the preprocessed image into a trained hand bone segmentation model to obtain a segmented hand bone region mask;
the fusion module is used for fusing the segmented hand bone region mask with the preprocessed image to obtain a hand bone image with background information removed;
and the second input module is used for inputting the hand bone image without the background information into a trained bone age evaluation model to evaluate the bone age.
Wherein, the preprocessing module specifically comprises:
and the equalization unit is used for enhancing the local contrast of the hand bone image to be evaluated by histogram equalization.
The child bone age assessment system provided by the invention further comprises:
the sample library establishing module is used for establishing a hand bone image sample library; the hand bone image sample library comprises a plurality of hand bone image samples;
the first data set construction module is used for processing the hand bone image samples, labeling hand bone contours and constructing a first data set, wherein the data set comprises a hand bone image training set, a hand bone image verification set and a hand bone image test set;
the first training module is used for training a Mask R-CNN model through a hand bone image training set to obtain a hand bone segmentation model;
and the first optimization module is used for optimizing the hand bone segmentation model through the hand bone image test set and the hand bone image verification set.
The child bone age assessment system provided by the invention further comprises:
the segmentation module is used for segmenting the first data set through a hand bone segmentation model to obtain a hand bone region mask sample;
constructing a second data set, fusing the segmented hand bone region mask sample with the preprocessed hand bone image sample, and constructing the second data set; the second data set comprises a hand bone image training set after background information is removed, a hand bone image testing set after the background information is removed, and a hand bone image verification set after the background information is removed;
the second training module is used for training the improved Xprediction model through the hand bone image training set after background information is removed to obtain a bone age evaluation model;
and the second optimization module is used for optimizing the bone age evaluation model through the hand bone image test set after background information is removed and the hand bone image verification set after the background information is removed.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. A children bone age assessment method based on deep learning is characterized by comprising the following steps:
acquiring a hand bone image to be evaluated;
preprocessing a hand bone image to be evaluated;
inputting the preprocessed image into a trained hand bone segmentation model to obtain a segmented hand bone region mask;
fusing the segmented hand bone region mask with the preprocessed image to obtain a hand bone image with background information removed;
and inputting the hand bone image without the background information into a trained bone age evaluation model to evaluate the bone age.
2. The deep learning-based child bone age assessment method according to claim 1, wherein the preprocessing of the hand bone image to be assessed specifically comprises:
the hand bone image to be evaluated enhances local contrast using histogram equalization.
3. The deep learning-based child bone age assessment method according to claim 1, wherein the training process of the hand bone segmentation model specifically comprises:
establishing a hand bone image sample library; the hand bone image sample library comprises a plurality of hand bone image samples;
processing the hand bone image sample and labeling a hand bone contour to construct a first data set, wherein the data set comprises a hand bone image training set, a hand bone image verification set and a hand bone image test set;
training a Mask R-CNN model through a hand bone image training set to obtain a hand bone segmentation model;
and optimizing the hand bone segmentation model through the hand bone image test set and the hand bone image verification set.
4. The deep learning-based child bone age assessment method according to claim 3, wherein the training process of the bone age assessment model specifically comprises:
segmenting the first data set through a hand bone segmentation model to obtain a hand bone region mask sample;
fusing the segmented hand bone region mask sample with the preprocessed hand bone image sample to construct a second data set; the second data set comprises a hand bone image training set after background information is removed, a hand bone image testing set after the background information is removed, and a hand bone image verification set after the background information is removed;
training the improved Xception model through the hand bone image training set after background information is removed to obtain a bone age evaluation model;
and optimizing the bone age evaluation model through the hand bone image test set after removing the background information and the hand bone image verification set after removing the background information.
5. A system for assessing bone age of children based on deep learning, comprising:
the image acquisition module is used for acquiring a hand bone image to be evaluated;
the preprocessing module is used for preprocessing the hand bone image to be evaluated;
the first input module is used for inputting the preprocessed image into a trained hand bone segmentation model to obtain a segmented hand bone region mask;
the fusion module is used for fusing the segmented hand bone region mask with the preprocessed image to obtain a hand bone image with background information removed;
and the second input module is used for inputting the hand bone image without the background information into a trained bone age evaluation model to evaluate the bone age.
6. The deep learning based child bone age assessment system according to claim 5, wherein the preprocessing module specifically comprises:
and the equalization unit is used for enhancing the local contrast of the hand bone image to be evaluated by histogram equalization.
7. The deep learning based child bone age assessment system according to claim 5, further comprising:
the sample library establishing module is used for establishing a hand bone image sample library; the hand bone image sample library comprises a plurality of hand bone image samples;
the first data set construction module is used for processing the hand bone image samples, labeling hand bone contours and constructing a first data set, wherein the data set comprises a hand bone image training set, a hand bone image verification set and a hand bone image test set;
the first training module is used for training a Mask R-CNN model through a hand bone image training set to obtain a hand bone segmentation model;
and the first optimization module is used for optimizing the hand bone segmentation model through the hand bone image test set and the hand bone image verification set.
8. The deep learning based child bone age assessment system according to claim 5, further comprising:
the segmentation module is used for segmenting the first data set through a hand bone segmentation model to obtain a hand bone region mask sample;
constructing a second data set, fusing the segmented hand bone region mask sample with the preprocessed hand bone image sample, and constructing the second data set; the second data set comprises a hand bone image training set after background information is removed, a hand bone image testing set after the background information is removed, and a hand bone image verification set after the background information is removed;
the second training module is used for training the improved Xprediction model through the hand bone image training set after background information is removed to obtain a bone age evaluation model;
and the second optimization module is used for optimizing the bone age evaluation model through the hand bone image test set after background information is removed and the hand bone image verification set after the background information is removed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110564662.1A CN113298780B (en) | 2021-05-24 | 2021-05-24 | Deep learning-based bone age assessment method and system for children |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110564662.1A CN113298780B (en) | 2021-05-24 | 2021-05-24 | Deep learning-based bone age assessment method and system for children |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113298780A true CN113298780A (en) | 2021-08-24 |
CN113298780B CN113298780B (en) | 2023-09-12 |
Family
ID=77324126
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110564662.1A Active CN113298780B (en) | 2021-05-24 | 2021-05-24 | Deep learning-based bone age assessment method and system for children |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113298780B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115661052A (en) * | 2022-10-13 | 2023-01-31 | 高峰医疗器械(无锡)有限公司 | Alveolar bone detection method, alveolar bone detection device, alveolar bone detection equipment and storage medium |
CN116342516A (en) * | 2023-03-17 | 2023-06-27 | 四川文理学院 | Model integration-based method and system for assessing bone age of X-ray images of hand bones of children |
CN116433607A (en) * | 2023-03-17 | 2023-07-14 | 四川文理学院 | Bone age assessment method and system for X-ray images of hand bones of children based on double weighted fusion of key region features |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107767376A (en) * | 2017-11-02 | 2018-03-06 | 西安邮电大学 | X-ray film stone age Forecasting Methodology and system based on deep learning |
WO2018057714A1 (en) * | 2016-09-21 | 2018-03-29 | The General Hospital Corporation | Systems, methods and media for automatically generating a bone age assessment from a radiograph |
CN109345508A (en) * | 2018-08-31 | 2019-02-15 | 北京航空航天大学 | A kind of Assessing Standards For Skeletal method based on two stages neural network |
CN111080579A (en) * | 2019-11-28 | 2020-04-28 | 杭州电子科技大学 | Bone age assessment method for realizing image segmentation and classification based on deep learning |
CN111161254A (en) * | 2019-12-31 | 2020-05-15 | 上海体育科学研究所 | Bone age prediction method |
US20200211187A1 (en) * | 2018-12-29 | 2020-07-02 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for ossification center detection and bone age assessment |
CN111985370A (en) * | 2020-08-10 | 2020-11-24 | 华南农业大学 | Crop pest and disease fine-grained identification method based on improved mixed attention module |
US20210142477A1 (en) * | 2018-08-01 | 2021-05-13 | China Medical University Hospital | Bone Age Assessment And Height Prediction Model, System Thereof And Prediction Method Thereof |
CN116342516A (en) * | 2023-03-17 | 2023-06-27 | 四川文理学院 | Model integration-based method and system for assessing bone age of X-ray images of hand bones of children |
-
2021
- 2021-05-24 CN CN202110564662.1A patent/CN113298780B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018057714A1 (en) * | 2016-09-21 | 2018-03-29 | The General Hospital Corporation | Systems, methods and media for automatically generating a bone age assessment from a radiograph |
CN107767376A (en) * | 2017-11-02 | 2018-03-06 | 西安邮电大学 | X-ray film stone age Forecasting Methodology and system based on deep learning |
US20210142477A1 (en) * | 2018-08-01 | 2021-05-13 | China Medical University Hospital | Bone Age Assessment And Height Prediction Model, System Thereof And Prediction Method Thereof |
CN109345508A (en) * | 2018-08-31 | 2019-02-15 | 北京航空航天大学 | A kind of Assessing Standards For Skeletal method based on two stages neural network |
US20200211187A1 (en) * | 2018-12-29 | 2020-07-02 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for ossification center detection and bone age assessment |
CN111080579A (en) * | 2019-11-28 | 2020-04-28 | 杭州电子科技大学 | Bone age assessment method for realizing image segmentation and classification based on deep learning |
CN111161254A (en) * | 2019-12-31 | 2020-05-15 | 上海体育科学研究所 | Bone age prediction method |
CN111985370A (en) * | 2020-08-10 | 2020-11-24 | 华南农业大学 | Crop pest and disease fine-grained identification method based on improved mixed attention module |
CN116342516A (en) * | 2023-03-17 | 2023-06-27 | 四川文理学院 | Model integration-based method and system for assessing bone age of X-ray images of hand bones of children |
Non-Patent Citations (2)
Title |
---|
JEREMIAH W.JOHNSON: "adapting mask-rcnn for automatic nucleus segmentation", ARXIV, pages 1 - 7 * |
董娜: "基于X光图像的骨龄评估系统设计与实现", 计算技术与自动化, vol. 29, no. 1, pages 67 - 72 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115661052A (en) * | 2022-10-13 | 2023-01-31 | 高峰医疗器械(无锡)有限公司 | Alveolar bone detection method, alveolar bone detection device, alveolar bone detection equipment and storage medium |
CN115661052B (en) * | 2022-10-13 | 2023-09-12 | 高峰医疗器械(无锡)有限公司 | Alveolar bone detection method, device, equipment and storage medium |
CN116342516A (en) * | 2023-03-17 | 2023-06-27 | 四川文理学院 | Model integration-based method and system for assessing bone age of X-ray images of hand bones of children |
CN116433607A (en) * | 2023-03-17 | 2023-07-14 | 四川文理学院 | Bone age assessment method and system for X-ray images of hand bones of children based on double weighted fusion of key region features |
CN116433607B (en) * | 2023-03-17 | 2024-03-15 | 四川文理学院 | Bone age assessment method and system for X-ray images of hand bones of children based on double weighted fusion of key region features |
CN116342516B (en) * | 2023-03-17 | 2024-04-16 | 四川文理学院 | Model integration-based method and system for assessing bone age of X-ray images of hand bones of children |
Also Published As
Publication number | Publication date |
---|---|
CN113298780B (en) | 2023-09-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113298780B (en) | Deep learning-based bone age assessment method and system for children | |
CN110059741B (en) | Image recognition method based on semantic capsule fusion network | |
CN109086799A (en) | A kind of crop leaf disease recognition method based on improvement convolutional neural networks model AlexNet | |
CN109948522B (en) | X-ray hand bone maturity interpretation method based on deep neural network | |
CN111784671A (en) | Pathological image focus region detection method based on multi-scale deep learning | |
TWI684997B (en) | Establishing method of bone age assessment and height prediction model, bone age assessment and height prediction system, and bone age assessment and height prediction method | |
CN111738363B (en) | Alzheimer disease classification method based on improved 3D CNN network | |
CN112508953B (en) | Meningioma rapid segmentation qualitative method based on deep neural network | |
Yang et al. | TTL-IQA: Transitive transfer learning based no-reference image quality assessment | |
CN112819821B (en) | Cell nucleus image detection method | |
TWI672637B (en) | Patern recognition method of autoantibody immunofluorescence image | |
CN112365497A (en) | High-speed target detection method and system based on Trident Net and Cascade-RCNN structures | |
CN113657449A (en) | Traditional Chinese medicine tongue picture greasy classification method containing noise labeling data | |
CN114511759A (en) | Method and system for identifying categories and determining characteristics of skin state images | |
CN114140437A (en) | Fundus hard exudate segmentation method based on deep learning | |
CN111340098B (en) | STA-Net age prediction method based on shoe print image | |
CN116452592B (en) | Method, device and system for constructing brain vascular disease AI cognitive function evaluation model | |
CN117557941A (en) | Video intelligent analysis system and method based on multi-mode data fusion | |
CN108805181A (en) | A kind of image classification device and sorting technique based on more disaggregated models | |
CN107944474A (en) | Multiple dimensioned cooperation table based on local auto-adaptive dictionary reaches hyperspectral classification method | |
CN116486156A (en) | Full-view digital slice image classification method integrating multi-scale feature context | |
CN115762756A (en) | Early cognitive disorder scale drawing result judging device | |
CN111612021B (en) | Error sample identification method, device and terminal | |
CN109886105B (en) | Price tag identification method, system and storage medium based on multi-task learning | |
CN113222887A (en) | Deep learning-based nano-iron labeled neural stem cell tracing method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |