CN108334899A - Quantify the bone age assessment method of information integration based on hand bone X-ray bone and joint - Google Patents
Quantify the bone age assessment method of information integration based on hand bone X-ray bone and joint Download PDFInfo
- Publication number
- CN108334899A CN108334899A CN201810080541.8A CN201810080541A CN108334899A CN 108334899 A CN108334899 A CN 108334899A CN 201810080541 A CN201810080541 A CN 201810080541A CN 108334899 A CN108334899 A CN 108334899A
- Authority
- CN
- China
- Prior art keywords
- bone
- joint
- ray
- information
- hand
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
- G06V2201/033—Recognition of patterns in medical or anatomical images of skeletal patterns
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Pathology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of bone age assessment methods quantifying information integration based on hand bone X-ray bone and joint, include the following steps:Step 1, the picture sample of hand bone X-ray is collected, and is classified to sample according to gender, age bracket, grouping information is obtained;Step 2, the bone of sample and joint position are labeled and are divided;Step 3, it is input in convolutional neural networks with actual position information after sample image being pre-processed, is iterated training, obtain bone and the location information and characteristic pattern in joint;Step 4, the morphological feature parameter of bone and joint in sample is calculated;Step 5, the characteristic pattern and morphological feature in bone and joint are fused to composite character information, are input to together with grouping information in convolutional neural networks model and are iterated training;Step 6, model training finishes, and carries out bone age assessment application.Using the present invention, can under the premise of reducing interference from human factor the more simple, fast assessment stone age.
Description
Technical field
The invention belongs to medical data excavation applications, are quantified based on hand bone X-ray bone and joint more particularly, to one kind
The bone age assessment method of information integration.
Background technology
It, can be with both at home and abroad it is believed that judging that the maturity of development individual is a kind of effective method by the stone age
More fully reflect body physiological state, be skeleton development process age description, represent specific normal population (race,
Domain, age) in each all ages and classes minor skeleton development general state.The identification of Assessing Standards For Skeletal or stone age are usually to use
X-ray after the same method to the hand bone at the same position of subject person shoot X ray image, then by skeletal form in image with
General skeletal form is compared.
Stone age is the important indicator of human body maturity, can understand the growth and development potentiality of children early by the stone age,
And it is sent out according to skeleton development Trend judgement if appropriate for a certain professional training specifically moved of receiving or to suitable bone itself
The professional direction development for educating trend, also has very great help to the diagnosis of some diseases by bone-age determination.
Traditional bone age assessment method is to be compared or stone age X-ray and standard diagram according to epiphysis by expert
Developmental testing gives a mark to complete.But it is more demanding to the professional knowledge for the people that scores, the bone to key position is needed when checking
Bone is carefully compared.By artificial read tablet it is more or less there are some read tablet errors, with increasing for diagosis amount, diagosis doctor
It is raw gradually can by the interference of the unfavorable factors such as fatigue the accuracy of impact evaluation.
Invention content
The present invention provides a kind of bone age assessment method quantifying information integration based on hand bone X-ray bone and joint, can be
The more simple, fast assessment stone age under the premise of reduction interference from human factor.
A kind of bone age assessment method being quantified information integration based on hand bone X-ray bone and joint, is included the following steps:
Step 1, the picture sample of hand bone X-ray is collected, and is classified to sample according to gender, age bracket, is divided
Group information;
Step 2, coordinate is labeled and preserved to the bone of sample and joint position, obtains actual position information, to mark
The bone of note and joint are split;
Step 3, actual position information is input to by pretreated sample image in convolutional neural networks, is changed
Generation training, obtains bone and the characteristic pattern in joint;
Step 4, the morphological feature parameter of bone and joint in sample is calculated;
Step 5, the characteristic pattern and morphological feature in bone and joint are fused to composite character information, with grouping information
It is input to together in convolutional neural networks model and is iterated training;
Step 6, model training finishes, and carries out bone age assessment application.
The present invention is handled by convolutional neural networks opponent's bone X-ray of design, learns hand bone key bone in X-ray
Simultaneously integrated information opponent's bon e formation more comprehensively recognizes characteristic information, to achieve the purpose that bone age assessment.
In step 2, the bone is mainly carpal bone.
Step 3 the specific steps are:
Step 3-1, after sample image is pre-processed and bone, joint markup information input convolution
Neural network carries out feature extraction.
Because in a practical situation, picture clarity that different film making equipment obtains and brightness etc. are without consistency, no
Same film making mechanism has certain auxiliary photographic device, these devices have certain interference for picture quality, in order to locate
The stability of reason needs to carry out certain pretreatment to input picture.
The pretreatment is to increase the contrast of image using gamma transformation method, and calculation is as follows:
I ' (x, y)=(I (x, y) * r)γ,r∈[0,1]
Wherein, I (x, y) is the gray value for inputting pixel, and I ' (x, y) is the gray value of output pixel, and γ is gamma factor,
By changing the value of γ, increase the contrast of image.
The Convolution Formula that the feature extraction uses is as follows:
Wherein, f (x, y) is input picture, and g (x, y) is convolution kernel function, and m and n respectively represents the length and width of convolution kernel.
The purpose of feature extraction is to extract image key message, such as texture, shape.Traditional feature extracting method
There is certain dependence to use environment, situation lacks certain adaptability for more complex in the case of.
Step 3-2, according to the feature of extraction through believing to the position in output bone and joint after transmission before convolutional neural networks
Breath, the error between location information and the location information of mark by calculating convolutional neural networks output, is grasped in back transfer
The parameter that convolutional layer is updated in work is trained the convolutional neural networks until model convergence, obtains bone and joint
Location information and feature..
In step 4, according to the segmentation figure computation of morphology characteristic parameter of mark bone and joint, the morphological feature
Parameter includes area, maximum gauge and Hu squares.
The maximum gauge uses Euclidean distance method, calculation formula as follows:
Wherein x, y are the coordinate values of pixel.
Hu squares have rotation, zooming and panning invariance to the feature description of two-dimensional bodies, and Hu squares are by normalizing center
It is worth to away from 2 ranks of rear calculating and 3 ranks, the calculation formula of the centre-to-centre spacing is as follows:
Wherein x, y are the coordinate values of pixel,It is the coordinate of target centroid, m, n are respectively the length of image and wide, p
It is 0,1,2,3 with the value range of q ..., p+q's and indicates rank square.
In step 5, the repetitive exercise is specially:Mistake between the prediction result and legitimate reading of continuous computation model
Difference, by the weight parameter in error update convolutional neural networks, until the increase with training iterations and error no longer
Reduce and illustrates that model is restrained.
The present invention is handled by convolutional neural networks opponent's bone X-ray of design, learns hand bone key bone in X-ray
Simultaneously integrated information opponent's bon e formation more comprehensively recognizes characteristic information, to achieve the purpose that bone age assessment, can reduce artificially
The more simple, fast assessment stone age under the premise of factor is interfered
Description of the drawings
Fig. 1 is the flow chart of the bone age assessment method of bone of the present invention and joint quantization information integration;
Fig. 2 is that bony segment and joint mark schematic diagram.
Specific implementation mode
To make technical scheme of the present invention and advantage be more clearly understood, the present invention is carried out below in conjunction with specific embodiment
It is further to be described in detail.
As shown in Figure 1, a kind of bone age assessment method quantifying information integration based on hand bone X-ray bone and joint, including
Following steps:
(1) according to relevant medical standard, the age of sample is limited to 0 to 18 years old, and a large amount of palms are collected according to the age
X-ray picture.In view of the difference of male and female skeleton development maturity, male and female need to be distinguished when making a collection of specimens collection
Sample.
(2) sample mark and bone segmentation.As shown in Fig. 2, needing to carry out the coordinate position of crucial bone and joint
Mark, the positions such as the carpal bone of hand bone and joint mainly by being manually labeled and preserving coordinate information by the present embodiment.Segmentation
A variety of methods, the present embodiment can be selected to select ostu methods to be split the bone of mark and joint, obtain sample image
Bone segmentation image.
(3) image of opponent's bone X-ray pre-processes.Because in a practical situation, the figure that different film making equipment obtains
Piece clarity and brightness etc. do not have consistency, and different film making mechanisms has certain auxiliary photographic device, these devices pair
There is certain interference in picture quality, in order to which the stability of processing needs to carry out certain pretreatment to input picture.
In specific implementation, increase the contrast of image using gamma transformation method, calculation is as follows:
I ' (x, y)=(I (x, y) * r)γ,r∈[0,1]
Wherein, γ values are boundary with 1, and value is smaller, stronger to the extension effect of low gray portion, and value is bigger, to high ash
The extension for spending part is stronger, and by different γ values, can reach enhances low gray scale or high gray portion to reach increase figure
The contrast of picture.The intensity value ranges of image are limited in [0,255] section in the specific implementation.
15 γ values are randomly selected within section [0.5,2.0], and contrast is all carried out to every image using 15 γ
Enhancing is handled and image is added in training set by treated.
(4) image characteristics extraction.Image data feature extraction is to carry out the basis of the advanced identification of image, feature extraction purpose
It is to extract image key message, such as texture, shape.Traditional feature extracting method has centainly use environment
Dependence, situation lacks certain adaptability for more complex in the case of.
The present embodiment extracts feature using convolution method, and the feature of extraction has certain regionality, filters out simultaneously
Noise, the feature after multilayer convolution contain more semantic informations and have preferable space-invariance, calculate public
Formula is as follows:
Wherein, f (x, y) is input picture, and g (x, y) is convolution kernel function, and x and y is pixel coordinate value, m and n generations respectively
The length and width of table convolution kernel, the pixel that image is traversed with convolution kernel are calculated.Because difference can be calculated in different convolution kernels
Feature, so different convolution kernel traverses image information to extract different characteristic informations.
(5) the position positioning of crucial bone and joint.The present invention in the specific implementation, passes through the feature of convolutional neural networks
It extracts and is realized with the method for positioning.Image obtains the spy in image bone and joint by the feature extraction layer of convolutional neural networks
Reference ceases, and is distinguished crucial bone and the characteristic information in joint with non-key bone and the characteristic information in joint using grader
It opens, then can obtain the coordinate information of the characteristic information in entire characteristic pattern in crucial bone and joint.
In specific implementation, in convolutional neural networks opponent's bone X-ray at the feature extraction and classification in crucial bone and joint
In the process of continuous training optimization, so its location information is also in continuous transformation and update.Because of the numerical value of target location coordinate
With continuity, the location information and actual position information of measurement convolutional neural networks output are calculated using the mode of recurrence
Error, calculation are as follows:
in which s.t.
Wherein, tuIndicate true location coordinate, v indicates the position coordinates of network output, using piecewise function, according to true
The range of difference x between prediction coordinate selects its corresponding calculation.
Calculate the error between the coordinate information and the true coordinate information marked by hand of convolutional neural networks output, error
It is smaller, illustrate that the positioning to target is more accurate.In the calculating in this stage, using above-mentioned loss function as convolutional Neural net
The convergence of the location model of network, when with training iterations increase and loss parameter no longer decline when, illustrate model
Convergence.
(6) computation of morphology characteristic parameter.The crucial bone of hand bone and joint are variant in different age level forms.
In order to quantify difference and the variation of form, its morphological feature is calculated using morphologic method in the present invention.Because of bone and joint
Form have diversity, selection calculate in physical characteristic comparatively apparent feature.
The bone obtained according to segmentation in specific implementation and joint, calculate the area, maximum gauge, Hu squares of target,
The calculating of middle maximum gauge uses common Euclidean distance method, calculation formula as follows:
Wherein x, y are the coordinate values of pixel.
Hu squares have rotation, zooming and panning invariance to the feature description of two-dimensional bodies, after normalizing centre-to-centre spacing
Calculate being worth to for 2 ranks and 3 ranks.Central moment is calculated first, then centre-to-centre spacing divided by 0 rank centre-to-centre spacing obtain normalization centre-to-centre spacing,
The calculation formula of centre-to-centre spacing is as follows:
Wherein x, y are the coordinate values of pixel,It is the coordinate of target centroid, m, n are respectively the length and width of image.
In the concrete realization, it calculates the morphological feature parameter of target using the method and parameter is formed into one group of parameter
Vector.
(7) comprehensive characteristics carry out model training.After step (5) is to crucial bone and joint orientation, while obtaining corresponding positions
The characteristic pattern set.The characteristic pattern and morphological feature of crucial bone and joint, two kinds of information all represent palm key bone and
Joint is showed in the feature of different viewing angles, each information all has important value.Both the above information is fused to
Composite character information, and will enter into convolutional neural networks model and be iterated training, continuous computation model in training process
Prediction result and legitimate reading between error, pass through the weight parameter in error update convolutional neural networks.When iteration time
Number is continuously increased, and it is to illustrate that model is restrained, and Semantic feature and the bone age assessment of quantitative information are obtained that error, which no longer reduces,
Model.
In specific application, the image of hand bone X-ray is passed to as input quantity in assessment models, is inputted automatically
Amount pre-processes and exports assessment result.
Claims (9)
1. a kind of bone age assessment method quantifying information integration based on hand bone X-ray bone and joint, which is characterized in that including with
Lower step:
Step 1, the picture sample of hand bone X-ray is collected, and is classified to sample according to gender, age bracket, grouping letter is obtained
Breath;
Step 2, coordinate is labeled and preserved to the bone of sample and joint position, obtains actual position information, to mark
Bone and joint are split;
Step 3, actual position information is input to by pretreated sample image in convolutional neural networks, is iterated instruction
Practice, obtains bone and the characteristic pattern in joint;
Step 4, the morphological feature parameter of bone and joint in sample is calculated;
Step 5, the characteristic pattern and morphological feature in bone and joint are fused to composite character information, together with grouping information
It is input in convolutional neural networks model and is iterated training;
Step 6, model training finishes, and carries out bone age assessment application.
2. the bone age assessment method according to claim 1 for quantifying information integration based on hand bone X-ray bone and joint,
It is characterized in that, in step 2, the bone is carpal bone.
3. the bone age assessment method according to claim 1 for quantifying information integration based on hand bone X-ray bone and joint,
Be characterized in that, step 3 the specific steps are:
Pretreated sample image and bone, joint markup information input convolutional neural networks are carried out feature and carried by step 3-1
It takes;
Step 3-2, according to the feature of extraction through, to the location information of output bone and joint after transmission, leading to before convolutional neural networks
The error between the location information and the location information of mark that calculate convolutional neural networks output is crossed, in back transfer operation more
The parameter of new convolutional layer is trained the convolutional neural networks until model convergence, obtains the position in bone and joint
Information and feature.
4. the bone age assessment method according to claim 3 for quantifying information integration based on hand bone X-ray bone and joint,
It is characterized in that, in step 3-1, the pretreatment is to increase the contrast of image using gamma transformation method, and calculation is such as
Under:
I ' (x, y)=(I (x, y) * r)γ,γ∈[0,1]
Wherein, I (x, y) is the gray value for inputting pixel, and I ' (x, y) is the gray value of output pixel, and γ is gamma factor, is passed through
The value for changing γ, increases the contrast of image.
5. the bone age assessment method according to claim 3 for quantifying information integration based on hand bone X-ray bone and joint,
It is characterized in that, in step 3-1, the Convolution Formula that the feature extraction uses is as follows:
Wherein, f (x, y) is input picture, and g (x, y) is convolution kernel function, and m and n respectively represents the length and width of convolution kernel.
6. the bone age assessment side according to claim 1 for quantifying information integration based on hand bone X-ray key bone and joint
Method, which is characterized in that in step 4, the morphological feature parameter includes area, maximum gauge and Hu squares.
7. the bone age assessment side according to claim 6 for quantifying information integration based on hand bone X-ray key bone and joint
Method, which is characterized in that the maximum gauge uses Euclidean distance method, calculation formula as follows:
Wherein x, y are the coordinate values of pixel.
8. the bone age assessment side according to claim 6 for quantifying information integration based on hand bone X-ray key bone and joint
Method, which is characterized in that the Hu squares after normalizing centre-to-centre spacing by calculating being worth to for 2 ranks and 3 ranks, the meter of the centre-to-centre spacing
It is as follows to calculate formula:
Wherein x, y are the coordinate values of pixel,The coordinate of target centroid, m, n be respectively image length with it is wide, p and q's
Value range is 0,1,2,3 ..., p+q and indicate rank square.
9. the bone age assessment side according to claim 1 for quantifying information integration based on hand bone X-ray key bone and joint
Method, which is characterized in that in step 5, the repetitive exercise is specially:The prediction result of continuous computation model and legitimate reading it
Between error, by the weight parameter in error update convolutional neural networks, until the increase with training iterations and mistake
Difference no longer reduces, and illustrates that model is restrained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810080541.8A CN108334899A (en) | 2018-01-28 | 2018-01-28 | Quantify the bone age assessment method of information integration based on hand bone X-ray bone and joint |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810080541.8A CN108334899A (en) | 2018-01-28 | 2018-01-28 | Quantify the bone age assessment method of information integration based on hand bone X-ray bone and joint |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108334899A true CN108334899A (en) | 2018-07-27 |
Family
ID=62926215
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810080541.8A Pending CN108334899A (en) | 2018-01-28 | 2018-01-28 | Quantify the bone age assessment method of information integration based on hand bone X-ray bone and joint |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108334899A (en) |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108968991A (en) * | 2018-05-08 | 2018-12-11 | 平安科技(深圳)有限公司 | Hand bone X-ray bone age assessment method, apparatus, computer equipment and storage medium |
CN108992082A (en) * | 2018-08-21 | 2018-12-14 | 上海臻道软件技术有限公司 | A kind of stone age detection system and its detection method |
CN109118487A (en) * | 2018-08-23 | 2019-01-01 | 合肥工业大学 | Bone age assessment method based on non-down sampling contourlet transform and convolutional neural networks |
CN109255786A (en) * | 2018-09-30 | 2019-01-22 | 杭州依图医疗技术有限公司 | A kind of method and device detecting the stone age |
CN109272002A (en) * | 2018-09-30 | 2019-01-25 | 杭州依图医疗技术有限公司 | A kind of classification method and device of stone age piece |
CN109949280A (en) * | 2019-03-06 | 2019-06-28 | 上海联影智能医疗科技有限公司 | Image processing method, device, equipment storage medium and growth and development assessment system |
CN109948522A (en) * | 2019-03-18 | 2019-06-28 | 浙江工业大学 | A kind of X-ray hand osseous maturation degree interpretation method based on deep neural network |
CN109984765A (en) * | 2019-03-06 | 2019-07-09 | 杭州津禾生物科技有限公司 | A kind of stone age evaluation and test GP2-TW evaluating system |
CN109998576A (en) * | 2019-03-05 | 2019-07-12 | 上海市儿童医院 | A kind of artificial intelligence stone age detection method |
CN109998577A (en) * | 2019-03-05 | 2019-07-12 | 上海市儿童医院 | A kind of artificial intelligence stone age detection terminal device |
CN110051376A (en) * | 2019-03-05 | 2019-07-26 | 上海市儿童医院 | A kind of stone age intelligent detecting method |
CN110335670A (en) * | 2019-06-10 | 2019-10-15 | 北京深睿博联科技有限责任公司 | Image processing method and device for the classification of epiphysis grade |
CN110517234A (en) * | 2019-08-16 | 2019-11-29 | 杭州依图医疗技术有限公司 | Feature bone method for detecting abnormality and device |
CN110634133A (en) * | 2019-09-04 | 2019-12-31 | 杭州健培科技有限公司 | Knee joint orthopedic measurement method and device based on X-ray plain film |
CN110660484A (en) * | 2019-08-01 | 2020-01-07 | 平安科技(深圳)有限公司 | Bone age prediction method, device, medium, and electronic apparatus |
WO2020024127A1 (en) * | 2018-08-01 | 2020-02-06 | 中国医药大学附设医院 | Bone age assessment and height prediction model, system thereof and prediction method therefor |
CN110782450A (en) * | 2019-10-31 | 2020-02-11 | 北京推想科技有限公司 | Hand carpal development grade determining method and related equipment |
CN110874834A (en) * | 2019-10-22 | 2020-03-10 | 清华大学 | Bone age prediction method and device, electronic equipment and readable storage medium |
WO2020062839A1 (en) * | 2018-09-30 | 2020-04-02 | 杭州依图医疗技术有限公司 | Method and apparatus for detecting bone age |
CN111142663A (en) * | 2019-12-27 | 2020-05-12 | 恒信东方文化股份有限公司 | Gesture recognition method and gesture recognition system |
CN111920430A (en) * | 2020-07-04 | 2020-11-13 | 浙江大学山东工业技术研究院 | Automatic bone age assessment method for weak supervised deep learning |
CN113436143A (en) * | 2021-05-24 | 2021-09-24 | 北京医准智能科技有限公司 | Joint detection method and device based on artificial intelligence and electronic equipment |
CN113436144A (en) * | 2021-05-24 | 2021-09-24 | 北京医准智能科技有限公司 | Joint rating method and device based on artificial intelligence and electronic equipment |
US11367181B2 (en) | 2018-12-29 | 2022-06-21 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for ossification center detection and bone age assessment |
CN117037221A (en) * | 2023-10-08 | 2023-11-10 | 腾讯科技(深圳)有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2003009758A1 (en) * | 2001-07-24 | 2003-02-06 | Sunlight Medical, Ltd. | Bone age assessment using ultrasound |
CN106156734A (en) * | 2016-06-28 | 2016-11-23 | 浙江工业大学 | Water flow velocity measurement method based on convolutional neural network image recognition |
CN107527333A (en) * | 2017-07-31 | 2017-12-29 | 湖北工业大学 | A kind of rapid image Enhancement Method based on gamma transformation |
CN107591200A (en) * | 2017-08-25 | 2018-01-16 | 卫宁健康科技集团股份有限公司 | Stone age marker recognition appraisal procedure and system based on deep learning and image group |
-
2018
- 2018-01-28 CN CN201810080541.8A patent/CN108334899A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2003009758A1 (en) * | 2001-07-24 | 2003-02-06 | Sunlight Medical, Ltd. | Bone age assessment using ultrasound |
CN106156734A (en) * | 2016-06-28 | 2016-11-23 | 浙江工业大学 | Water flow velocity measurement method based on convolutional neural network image recognition |
CN107527333A (en) * | 2017-07-31 | 2017-12-29 | 湖北工业大学 | A kind of rapid image Enhancement Method based on gamma transformation |
CN107591200A (en) * | 2017-08-25 | 2018-01-16 | 卫宁健康科技集团股份有限公司 | Stone age marker recognition appraisal procedure and system based on deep learning and image group |
Non-Patent Citations (3)
Title |
---|
CHAIBUBBLE: "图像不变性特征—hu矩", 《HTTPS://BLOG.CSDN.NET/CHAIPP0607/ARTICLE/DETAILS/70256892》 * |
KRIT SOMKANTHA等: "Bone Age Assessment in Young Children Using Automatic Carpal Bone Feature Extraction and Support Vector Regression", 《JOURNAL OF DIGITAL IMAGING》 * |
周啸: "虹膜识别关键技术研究及实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108968991A (en) * | 2018-05-08 | 2018-12-11 | 平安科技(深圳)有限公司 | Hand bone X-ray bone age assessment method, apparatus, computer equipment and storage medium |
JP6999812B2 (en) | 2018-08-01 | 2022-01-19 | 中國醫藥大學附設醫院 | Bone age evaluation and height prediction model establishment method, its system and its prediction method |
WO2020024127A1 (en) * | 2018-08-01 | 2020-02-06 | 中国医药大学附设医院 | Bone age assessment and height prediction model, system thereof and prediction method therefor |
JP2021504816A (en) * | 2018-08-01 | 2021-02-15 | 中國醫藥大學附設醫院China Medical University Hospital | Bone age evaluation and height prediction model, its system and its prediction method |
CN108992082A (en) * | 2018-08-21 | 2018-12-14 | 上海臻道软件技术有限公司 | A kind of stone age detection system and its detection method |
CN109118487B (en) * | 2018-08-23 | 2022-02-11 | 合肥工业大学 | Bone age assessment method based on non-subsampled contourlet transform and convolutional neural network |
CN109118487A (en) * | 2018-08-23 | 2019-01-01 | 合肥工业大学 | Bone age assessment method based on non-down sampling contourlet transform and convolutional neural networks |
CN109255786A (en) * | 2018-09-30 | 2019-01-22 | 杭州依图医疗技术有限公司 | A kind of method and device detecting the stone age |
CN109272002A (en) * | 2018-09-30 | 2019-01-25 | 杭州依图医疗技术有限公司 | A kind of classification method and device of stone age piece |
WO2020062839A1 (en) * | 2018-09-30 | 2020-04-02 | 杭州依图医疗技术有限公司 | Method and apparatus for detecting bone age |
US11367181B2 (en) | 2018-12-29 | 2022-06-21 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for ossification center detection and bone age assessment |
US11735322B2 (en) | 2018-12-29 | 2023-08-22 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for ossification center detection and bone age assessment |
US20220309663A1 (en) * | 2018-12-29 | 2022-09-29 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for ossification center detection and bone age assessment |
CN110051376A (en) * | 2019-03-05 | 2019-07-26 | 上海市儿童医院 | A kind of stone age intelligent detecting method |
CN109998577A (en) * | 2019-03-05 | 2019-07-12 | 上海市儿童医院 | A kind of artificial intelligence stone age detection terminal device |
CN109998576A (en) * | 2019-03-05 | 2019-07-12 | 上海市儿童医院 | A kind of artificial intelligence stone age detection method |
CN109949280B (en) * | 2019-03-06 | 2021-06-11 | 上海联影智能医疗科技有限公司 | Image processing method, image processing apparatus, device storage medium, and growth evaluation system |
CN109984765A (en) * | 2019-03-06 | 2019-07-09 | 杭州津禾生物科技有限公司 | A kind of stone age evaluation and test GP2-TW evaluating system |
CN109949280A (en) * | 2019-03-06 | 2019-06-28 | 上海联影智能医疗科技有限公司 | Image processing method, device, equipment storage medium and growth and development assessment system |
CN109948522A (en) * | 2019-03-18 | 2019-06-28 | 浙江工业大学 | A kind of X-ray hand osseous maturation degree interpretation method based on deep neural network |
CN110335670A (en) * | 2019-06-10 | 2019-10-15 | 北京深睿博联科技有限责任公司 | Image processing method and device for the classification of epiphysis grade |
CN110660484A (en) * | 2019-08-01 | 2020-01-07 | 平安科技(深圳)有限公司 | Bone age prediction method, device, medium, and electronic apparatus |
CN110517234A (en) * | 2019-08-16 | 2019-11-29 | 杭州依图医疗技术有限公司 | Feature bone method for detecting abnormality and device |
CN110634133A (en) * | 2019-09-04 | 2019-12-31 | 杭州健培科技有限公司 | Knee joint orthopedic measurement method and device based on X-ray plain film |
CN110874834A (en) * | 2019-10-22 | 2020-03-10 | 清华大学 | Bone age prediction method and device, electronic equipment and readable storage medium |
CN110782450A (en) * | 2019-10-31 | 2020-02-11 | 北京推想科技有限公司 | Hand carpal development grade determining method and related equipment |
CN111142663A (en) * | 2019-12-27 | 2020-05-12 | 恒信东方文化股份有限公司 | Gesture recognition method and gesture recognition system |
CN111142663B (en) * | 2019-12-27 | 2024-02-02 | 恒信东方文化股份有限公司 | Gesture recognition method and gesture recognition system |
CN111920430A (en) * | 2020-07-04 | 2020-11-13 | 浙江大学山东工业技术研究院 | Automatic bone age assessment method for weak supervised deep learning |
CN113436144A (en) * | 2021-05-24 | 2021-09-24 | 北京医准智能科技有限公司 | Joint rating method and device based on artificial intelligence and electronic equipment |
CN113436143A (en) * | 2021-05-24 | 2021-09-24 | 北京医准智能科技有限公司 | Joint detection method and device based on artificial intelligence and electronic equipment |
CN117037221A (en) * | 2023-10-08 | 2023-11-10 | 腾讯科技(深圳)有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
CN117037221B (en) * | 2023-10-08 | 2023-12-29 | 腾讯科技(深圳)有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108334899A (en) | Quantify the bone age assessment method of information integration based on hand bone X-ray bone and joint | |
CN111476292B (en) | Small sample element learning training method for medical image classification processing artificial intelligence | |
CN107610087B (en) | Tongue coating automatic segmentation method based on deep learning | |
CN107767376B (en) | X-ray bone age prediction method and system based on deep learning | |
Bi et al. | Automatic liver lesion detection using cascaded deep residual networks | |
CN109215013A (en) | Automatic stone age prediction technique, system, computer equipment and storage medium | |
CN107492095A (en) | Medical image pulmonary nodule detection method based on deep learning | |
CN108921851A (en) | A kind of medicine CT image dividing method based on 3D confrontation network | |
CN106340000A (en) | Bone age assessment method | |
CN107590797A (en) | CT image pulmonary nodule detection method based on three-dimensional residual error neural network | |
CN108364293A (en) | A kind of on-line training thyroid tumors Ultrasound Image Recognition Method and its device | |
CN107194937A (en) | Tongue image partition method under a kind of open environment | |
CN108171700A (en) | Medical image pulmonary nodule detection method based on confrontation network | |
CN107945182A (en) | Maize leaf disease recognition method based on convolutional neural networks model GoogleNet | |
CN110033019A (en) | Method for detecting abnormality, device and the storage medium of human body | |
CN108717693A (en) | A kind of optic disk localization method based on RPN | |
CN108629762A (en) | A kind of stone age evaluation and test model reduces the image pre-processing method and system of interference characteristic | |
CN107392929A (en) | A kind of intelligent target detection and dimension measurement method based on human vision model | |
CN107871316A (en) | A kind of X-ray hand bone interest region extraction method based on deep neural network | |
CN109741316A (en) | Medical image intelligently comments piece system | |
CN106897986A (en) | A kind of visible images based on multiscale analysis and far infrared image interfusion method | |
CN109448854A (en) | A kind of construction method of pulmonary tuberculosis detection model and application | |
CN112464915B (en) | Push-up counting method based on human skeleton point detection | |
CN112614133A (en) | Three-dimensional pulmonary nodule detection model training method and device without anchor point frame | |
CN110717894A (en) | Cancer targeted therapy curative effect evaluation method and device, equipment and storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180727 |