CN110211674A - Stone age test method and relevant device based on machine learning model - Google Patents
Stone age test method and relevant device based on machine learning model Download PDFInfo
- Publication number
- CN110211674A CN110211674A CN201910327391.0A CN201910327391A CN110211674A CN 110211674 A CN110211674 A CN 110211674A CN 201910327391 A CN201910327391 A CN 201910327391A CN 110211674 A CN110211674 A CN 110211674A
- Authority
- CN
- China
- Prior art keywords
- stone age
- bone
- ray
- attribute
- machine learning
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
Present invention discloses a kind of stone age test method, device, computer equipment and storage medium based on machine learning model, belong to machine learning techniques field, being somebody's turn to do the stone age test method based on machine learning model includes: the X-ray for receiving the image to be measured including bone;Identify that the attribute of multiple predetermined positions of bone constitutes the first attribute set from the image of the bone of X-ray;First attribute set is inputted into the first machine learning model and exported for the first stone age;The image of bone in X-ray is matched with the standard video of the people's bone of each stone age, is found with the stone age of the people's bone of the Image Matching of bone in X-ray as the second stone age;It scores to the attribute of each predetermined position in the first attribute set, total score is obtained according to the score of the attribute of each predetermined position, according to total score, export the third stone age;The weighted sum for exporting the first stone age, the second stone age, third stone age, as the stone age detected.This avoid detection errors caused by single stone age algorithm.
Description
Technical field
The present invention relates to machine learning techniques field, more particularly to based on machine learning model stone age test method,
Device, computer equipment and storage medium.
Background technique
Stone age detection system currently on the market can only use single algorithm, detect the stone age of sufferer, algorithm is not
Have and compare combination with a variety of stone age detection methods, it is possible that large error, there are delay patients under the scene of part
Diagnosis risk.
Summary of the invention
Based on this, the technical issues of to solve the single poor reliability of stone age test macro algorithm in the related technology, the present invention
Provide a kind of stone age test method, device, computer equipment and storage medium based on machine learning model.
In a first aspect, providing a kind of stone age test method based on machine learning model, comprising:
Receive the X-ray of the image to be measured including bone;
The attribute of multiple predetermined positions of bone, multiple reservations of the bone identified are identified from the image of the bone of X-ray
The attribute of position constitutes the first attribute set;
First attribute set is inputted into the first machine learning model, the first machine learning model exported for the first stone age;
The image of bone in X-ray is matched with the standard video of the people's bone of each stone age, is found and bone in X-ray
The stone age of the people's bone of Image Matching is as the second stone age;
It scores to the attribute of each predetermined position in the first attribute set, according to the meter of the attribute of each predetermined position
Get total score, according to total score, inquires total score and stone age mapping table, export the third stone age;
The weighted sum for calculating the first stone age, the second stone age, third stone age, as the stone age output detected.
First machine learning model is trained as follows in one of the embodiments:
The X-ray sample set of the image including bone is obtained, each X-ray sample in X-ray sample set posts in advance
Stone age label will identify that from the attribute of multiple predetermined positions of each X-ray specimen discerning bone in X-ray sample set
Attribute inputs the first machine learning model, the stone age that the output of the first machine learning model determines, compares with the stone age label posted,
It is such as inconsistent, then first machine learning model is adjusted, keeps the stone age of the machine learning model output consistent with label.
It is carried out in one of the embodiments, according to the image of bone in X-ray and the standard video of the people's bone of each stone age
Matching, finds with the stone age of the people's bone of the Image Matching of bone in X-ray as the second stone age, specifically includes:
The image of bone is extracted from X-ray;
By the pixel value of each pixel of the image of the bone extracted from X-ray and the standard video of the people's bone of each stone age
The pixel value of corresponding position subtracts each other and asks absolute value, obtains the pixel value absolute value of the difference of each pixel;
The pixel value absolute value of the difference of each pixel is averaging, average value is obtained;
Using the smallest standard video of the average value corresponding stone age as the second stone age.
The standard video of the people's bone of the image according to bone in X-ray and each stone age in one of the embodiments,
It is matched, finds with the stone age of the people's bone of the Image Matching of bone in X-ray as the step of the second stone age and include:
The X-ray is inputted into the second machine learning model, the second machine learning model exports the people's bone of each stone age
The similarity of standard video and the X-ray;
Using the stone age of the smallest standard video of the similarity as the second stone age.
Wherein, second machine learning model is trained as follows:
By each bone image sample in the set with bone image sample pair to inputting the second machine learning model, each bone
Image sample sticks similarity label in advance to including a pair of of bone image sample for a pair of bone image sample in advance, and described the
The similarity of the bone image sample pair of two machine learning models output judgement, is compared, if different with the label sticked
It causes, adjusts second machine learning model, the similarity for exporting the second machine learning model is consistent with label.
Carrying out score to the attribute of each predetermined position in the first attribute set in one of the embodiments, includes:
According to the attribute of each predetermined position, growth period mapping table belonging to attribute and bone position is searched, is obtained
The attribute corresponding growth period;
Growth period and score mapping table are searched, to find score corresponding with growth period.
Obtaining total score according to the score of the attribute of each predetermined position in one of the embodiments, includes:
The weighted sum for calculating the score of the attribute of each predetermined position, as total score.
The X-ray to be measured for receiving the image including bone in one of the embodiments, specifically includes:
In response to the operation to main display interface, the X-ray to be measured of the image including bone is received;
The X-ray is sent to main display interface;
The method is in the weighted sum for calculating the first stone age, the second stone age, third stone age, as the stone age output detected
Later, further includes:
The stone age reference set is sent to auxiliary display screen interface.
Second aspect provides a kind of stone age test device based on machine learning model, comprising:
Skeletal image receiving unit, for receiving the X-ray of the image to be measured including bone;
Bone Attribute Recognition unit, the attribute of multiple predetermined positions for identifying bone from the image of the bone of X-ray, knows
Not Chu bone multiple predetermined positions attribute constitute the first attribute set;
First stone age output unit, for the first attribute set to be inputted the first machine learning model, the first machine learning
Model exported for the first stone age;
Second stone age output unit, for according to the standard video of the people's bone of the image and each stone age of bone in X-ray into
Row matching, found with the stone age of the people's bone of the Image Matching of bone in X-ray as the second stone age;
Third stone age output unit is scored for the attribute to each predetermined position in the first attribute set, according to
The score of the attribute of each predetermined position obtains total score, according to total score, inquires total score and stone age mapping table, output
The third stone age forms stone age reference set together with the first stone age, the second stone age, for referring to when diagnosis.
The third aspect provides a kind of computer equipment, including memory and processor, is stored with meter in the memory
Calculation machine readable instruction, when the computer-readable instruction is executed by the processor, so that processor execution is described above
The step of stone age test method based on machine learning model.
Fourth aspect provides a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction
When being executed by one or more processors, so that one or more processors execute the bone described above based on machine learning model
The step of age test method.
The technical scheme provided by this disclosed embodiment can include the following benefits:
Above-mentioned stone age test method, device, computer equipment and storage medium based on machine learning model, by elder generation from
The attribute of multiple predetermined positions of bone, and the multiple predetermined positions for the bone that will identify that are identified in the image of the bone of X-ray to be measured
Attribute constitute the first attribute set after by the first attribute set input the first machine learning model, make the first machine learning model
Exported for the first stone age;Then it is matched, is found with the standard video of the people's bone of each stone age further according to the image of bone in X-ray
Stone age with the people's bone of the Image Matching of bone in X-ray is as the second stone age;Finally to each reservations in the first attribute set
The attribute of position is scored, and obtains total score according to the score of the attribute of each predetermined position, according to total score, inquires total score
With stone age mapping table, the third stone age is exported, has thus obtained three stone age inspections obtained from three kinds of distinct methods
It surveys as a result, being finally that this programme finally detects by the final result that these three stone age testing results are weighted and are calculated
Stone age out, the stone age testing result calculated in this way avoid detection error caused by single stone age algorithm, compared to original
That comes is more accurate, so that stone age testing result has more reliability.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
Fig. 1 is the implementation environment figure of the stone age test method based on machine learning model provided in one embodiment.
Fig. 2 is a kind of process of stone age test method based on machine learning model shown according to an exemplary embodiment
Figure.
Fig. 3 is step S140 in the stone age test method based on machine learning model shown in corresponding embodiment according to fig. 2
A kind of specific implementation flow chart.
Fig. 4 is step S140 in the stone age test method based on machine learning model shown in corresponding embodiment according to fig. 2
Another specific implementation flow chart.
Fig. 5 is step S150 in the stone age test method based on machine learning model shown in corresponding embodiment according to fig. 2
A kind of specific implementation flow chart.
Fig. 6 is step S110 in the stone age test method based on machine learning model shown in corresponding embodiment according to fig. 2
A kind of specific implementation flow chart.
Fig. 7 is the stream according to another stone age test method based on machine learning model shown in Fig. 6 corresponding embodiment
Cheng Tu.
Fig. 8 is a kind of frame of stone age test device based on machine learning model shown according to an exemplary embodiment
Figure.
Fig. 9 is the frame of another stone age test device based on machine learning model shown according to an exemplary embodiment
Figure.
Figure 10 schematically shows a kind of electronic equipment example block diagram for realizing above-mentioned distribution method of attending a banquet.
Figure 11 schematically shows a kind of computer readable storage medium for realizing above-mentioned distribution method of attending a banquet.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Fig. 1 is the implementation environment figure of the stone age test method based on machine learning model provided in one embodiment, such as
Shown in Fig. 1, in the implementation environment, including computer equipment 100 and terminal 200.
Computer equipment 100 is medical system equipment, for example, the computer equipments such as computer, server for using of doctor.
The X-ray of the image to be measured including bone is preserved in terminal 200.X-ray can be sent to calculating by terminal 200 by patient
Machine equipment 100, computer equipment 100 identify the attribute of multiple predetermined positions of bone from the image of the bone of X-ray, identify
The attribute of multiple predetermined positions of bone constitutes the first attribute set;First attribute set is inputted into the first machine learning model, the
One machine learning model exported for the first stone age;It is carried out according to the image of bone in X-ray and the standard video of the people's bone of each stone age
Matching, found with the stone age of the people's bone of the Image Matching of bone in X-ray as the second stone age;To each pre- in the first attribute set
The attribute for determining position is scored, and obtains total score according to the score of the attribute of each predetermined position, and according to total score, inquiry is total
Score value and stone age mapping table export the third stone age, finally further according to first stone age, the second stone age and third bone
Age does weighted sum calculating, exports the final result of calculating as the stone age detected.
It should be noted that terminal 200 and computer equipment 100 can be smart phone, tablet computer, notebook electricity
Brain, desktop computer etc., however, it is not limited to this.Computer equipment 100 and terminal 200 can pass through bluetooth, USB
(Universal Serial Bus, universal serial bus) or other communication connection modes are attached, and the present invention is herein not
It is limited.
As shown in Fig. 2, in one embodiment it is proposed that a kind of stone age test method based on machine learning model, it should
Stone age test method based on machine learning model can be applied in above-mentioned computer equipment 100, can specifically include with
Lower step:
Step S110 receives the X-ray of the image to be measured including bone.
When carrying out the detection of automatic stone age, need first to receive the X-ray of the image to be measured including bone, then according to X
Mating plate is judged.Wherein, the X-ray can be is directly transmitted by hospital's X-ray machine, is also possible to having by patient
Mobile phone, computer, the mobile hard disk of the equipment of store function such as patient sends over, and can also be the doctor crossed by patient assessment
What the server of institute sended over, the present invention is it is not limited here.
Step S120, from the image of the bone of X-ray identify bone multiple predetermined positions attribute, the bone identified it is more
The attribute of a predetermined position constitutes the first attribute set.
Wherein, the predetermined position is, for example, bone portion, Bones and joints, place most thin among bone etc..The attribute is for example
It is femoral head diameter, periosteum thickness etc..
First attribute set is inputted the first machine learning model, the first machine learning model output first by step S130
Stone age.
Wherein, first machine learning model is trained as follows:
The X-ray sample set of the image including bone is obtained, each X-ray sample in X-ray sample set posts in advance
Stone age label will identify that from the attribute of multiple predetermined positions of each X-ray specimen discerning bone in X-ray sample set
Attribute inputs the first machine learning model, the stone age that the output of the first machine learning model determines, compares with the stone age label posted,
It is such as inconsistent, then first machine learning model is adjusted, keeps the stone age of the machine learning model output consistent with label.
Since the stone age label posted on the sample is it is known that so the stone age of the sample is known.This is known
Result as desired output, the training machine learning model.The mode of study are as follows: under the stimulation of extraneous input sample not
The disconnected connection weight for changing network.The essence of study is to carry out dynamic adjustment to each connection weight.Since desired output is
Know, if the result of machine learning model output is not inconsistent with the desired output, with regard to each connection weight of adjust automatically, until obtaining
The output result arrived is consistent with desired output.In this way, just having trained the first machine learning model.When the first machine learning mould
After type training is enough to get well, as long as the first attribute set in the X-ray to be measured is inputted the first machine learning one by one
Model, the first machine learning model will export for the first stone age.
The adaptive method is a kind of method based on machine learning model, the basic principle is that passing through machine learning mould
Type, according to the developmental state of bone different characteristic position in X-ray, comprehensive descision goes out the stone age.Its basic principle is to extract X-ray
Bone image in bone multiple predetermined positions attribute, the attributive character of each predetermined position can embody the bone of the bone
The attribute of these predetermined positions is input to the first machine learning model by age size, and the first machine learning model is according to each
Predetermined position attribute characteristic comprehensive descision goes out the stone age of the bone.
Step S140 matches the image of bone in X-ray with the standard video of the people's bone of each stone age, finds and X
The stone age of the people's bone of the Image Matching of bone is as the second stone age in mating plate.
Second stone age is the stone age calculated using Atlas Method, the basic principle is that by X-ray to be measured and standard drawing
Spectrum is compared, and obtains stone age testing result.
In the method, can be compared by extracting the pixel of X-ray to be measured and standard diagram same position, obtain with
X-ray to be measured standard diagram the most similar, can also be obtained with X-ray to be measured most by extracting the image comparison of same position
For similar standard diagram, the present invention is it is not limited here.
Step S150 scores to the attribute of each predetermined position in the first attribute set, according to each predetermined position
The score of attribute obtain total score, according to total score, inquire total score and stone age mapping table, export the third stone age.
The third stone age is the stone age calculated using point-score, the basic principle is that according to all bone different growing periods
X-ray characteristic standard scoring value obtains stone age testing result.
It in the present invention, is the attribute of multiple predetermined positions of bone in the image by the bone of extraction X-ray, each is pre-
The attributive character for determining position can embody the development condition of the bone, be counted respectively to these predetermined positions according to development condition
Point, then all scores are summed, obtain the total score of bone, finally according to the total score of the bone, determine the stone age.
First stone age, the second stone age and third stone age can form stone age reference together in one of the embodiments
Set, for being referred to when diagnosis.In this way doctor can according to these three algorithms as a result, comprehensively considering after, show that oneself is examined
Disconnected stone age testing result avoids detection error caused by single stone age algorithm, so that stone age testing result is with more reference
Property, convenient for obtaining a more accurate result.
Step S160 calculates the weighted sum of the first stone age, the second stone age, third stone age, as the stone age detected.
In one of the embodiments, the first stone age, the second stone age, the third stone age weight be pre-assigned.For example,
The weight for distributing for the first stone age is 0.5, and the weight of the second stone age is 0.2, and the weight of third stone age is 0.3, when testing result is
When first 9 years old stone age, 9 years old the second stone age, 9.5 years old third stone age, it can determine that its stone age is 9.15 years old.
In another embodiment, the sum of weight of first stone age, the second stone age and third stone age is 1, described
The weight of first stone age, the second stone age and third stone age can determine as follows respectively, the determination of the weight of first stone age
Mode subtracts the sum of the second stone age and the weight of third stone age for 1.The method of determination of second stone age can be according to institute
It states X-ray and determines that determining concrete mode can be the X-ray with its direct similarity of standard diagram the most similar
Multiply 0.5 with its direct similarity of standard diagram the most similar.The method of determination of the third stone age can be score
Degree of error determines that determining concrete mode, which can be, first subtracts the degree of error of the score multiplied by 0.5 with 1.
The wherein X-ray and can be by described with the method for determination of its direct similarity of standard diagram the most similar
It X-ray and is obtained with the absolute value of the difference of the pixel value of its standard diagram the most similar divided by 255, it can also be by the X-ray
It piece and is obtained with the absolute value of the difference of the pixel value of its standard diagram the most similar divided by the pixel value of the X-ray, this hair
It is bright it is not limited here.
The mode that wherein degree of error of the score determines, which can be, obtains total score and total score and bone by the score
The absolute value of the difference of the median in the corresponding score value section of third stone age described in age mapping table is obtained divided by the score
Total score obtains, and is also possible to be obtained total score as the score divided by described in the total score and stone age mapping table the
The quotient of the maximum value in three stone ages corresponding score value section and the score obtain total score except the total score is corresponding with the stone age
The average value of the quotient of the maximum value in the corresponding score value section of third stone age described in relation table obtains, and the present invention does not limit herein
It is fixed.
According to the significance level of the first stone age, the second stone age, third stone age, different weights is distributed.In this way, weighted sum obtains
To the stone age detected compared with the prior art only by GP Atlas Method or TW3 detection method, determine that the means of stone age are more comprehensive,
The determining stone age is more acurrate.
Optionally, Fig. 3 is to walk in the stone age test method based on machine learning model shown in corresponding embodiment according to fig. 2
The datail description of rapid S140, should be based in the stone age test method of machine learning model, and step S140 may comprise steps of:
Step S141 extracts the image of bone from X-ray;
Step S142, by the people's bone of the pixel value of each pixel of the image of the bone extracted from X-ray and each stone age
The pixel value of the corresponding position of standard video subtracts each other and asks absolute value, obtains the pixel value absolute value of the difference of each pixel;
The pixel value absolute value of the difference of each pixel is averaging, obtains average value by step S143;
Step S144, using the smallest standard video of the average value corresponding stone age as the second stone age.
In Atlas Method, most basic principle is exactly to compare X-ray to be measured and every year old one standard diagram, choosing
Take the stone age with the stone age of the immediate standard diagram of X-ray to be measured as the X-ray to be measured.
In the present embodiment, the method compared is to extract the pixel of X-ray and standard diagram same position to be measured
Comparison obtains and X-ray to be measured standard diagram the most similar.Its specific practice be by X-ray each pixel and
The pixel value of same position pixel is compared on standard diagram, finds out its absolute value of the difference.Such as the picture in same position
On vegetarian refreshments, the pixel value of X-ray is 250, the 248 of standard diagram, then its absolute value of the difference is 2, this difference with regard to smaller, if
On the pixel of same position, the pixel value of X-ray is 250, and standard diagram 48, this is likely to be the position on X-ray
It has set one piece of bone to have grown out, but the bone does not germinate or develops on standard diagram corresponding position
For to the degree of bone on X-ray, this difference is with regard to bigger.Because the difference of pixel value can represent two in one dimension
Difference between a image can thus have a specific standard to state the difference of the X-ray Yu the standard diagram.
Then the addition of each absolute value is averaged again, can be thus counted the difference of entire X-ray and standard diagram
Wordization is shown, so that it may finally using the stone age of the smallest standard diagram of the average value as second stone age.
Optionally, Fig. 4 is to walk in the stone age test method based on machine learning model shown in corresponding embodiment according to fig. 2
The datail description of rapid S140, should be based in the stone age test method of machine learning model, and step S140 may comprise steps of:
The X-ray is inputted the second machine learning model by step S146, and the second machine learning model exports each stone age
People's bone standard video and the X-ray similarity;
Step S147, using the stone age of the smallest standard video of the similarity as the second stone age.
Wherein, second machine learning model is trained as follows:
By each bone image sample in the set with bone image sample pair to inputting the second machine learning model, each bone
Image sample sticks similarity label in advance to including a pair of of bone image sample for a pair of bone image sample in advance, and described the
The similarity of the bone image sample pair of two machine learning models output judgement, is compared, if different with the label sticked
It causes, adjusts second machine learning model, the similarity for exporting the second machine learning model is consistent with label.
Since the sample is it is known that so the similarity of two images is known to the similarity label above posted.It should
Known result is as desired output, the training machine learning model.The mode of study are as follows: in the stimulation of extraneous input sample
The lower connection weight for constantly changing network.The essence of study is to carry out dynamic adjustment to each connection weight.Due to desired output
It is known, if the result of machine learning model output is not inconsistent with the desired output, with regard to each connection weight of adjust automatically, directly
It is consistent with desired output to obtained output result.In this way, just having trained the second device learning model.When the first machine learning
After model training is enough to get well, as long as the X-ray is inputted the second machine learning model, the second machine learning mould one by one
Type will export the standard video of the people's bone of each stone age and the similarity of the X-ray.
The present embodiment be mainly rely on machine learning model judge each stone age people's bone standard video and the X-ray
Similarity degree, the judgment method of the machine learning can be the difference according to each pixel, be also possible to according to every
The difference of one comparison block, the comparison block is, for example, 3 made of averagely dividing in institute's standard video and the X-ray ×
3 blocks, the present invention is it is not limited here.
The above method can also realize by machine learning model, can by machine learning model contrast standard map
More accurately judge the legitimate reading of stone age, is convenient for subsequent auxiliary diagnosis.
Optionally, Fig. 5 is to walk in the stone age test method based on machine learning model shown in corresponding embodiment according to fig. 2
The datail description of rapid S150, should be based in the stone age test method of machine learning model, and step S150 may comprise steps of:
Step S151 searches attribute pass corresponding with growth period belonging to bone position according to the attribute of each predetermined position
It is table, obtains the attribute corresponding growth period;
Step S152 searches growth period and score mapping table, to find score corresponding with growth period.
For example, bone portion periosteum thickness is an attribute, such as attribute and bone position institute should be searched with a thickness of 0.6mm
The growth period mapping table of category obtains the thickness and belongs to 2 phases of development, is searching growth period and score mapping table, is obtaining
Developing the corresponding score of 2 phases is 60 points, and obtaining scoring accordingly is 60 points.
Optionally, obtaining total score according to the score of the attribute of each predetermined position includes:
The weighted sum for calculating the score of the attribute of each predetermined position, as total score.
The weight of the weighted sum can be set as the case may be, be directed to different human bodies using different point systems
Position can all cause weight to have differences, such as in one embodiment, can be by pea osseous part when being detected for hand bone
The weight of position is set as 0.2, and the weight at all phalanges positions is set as 0.5, and the weight at ulna and radius position is set as 0.2, other
Partial weight is set as 0.1 carry out total score calculating.
In this way, being weighted the score value after calculating, the bone stone age accurately judged on X-ray to be measured can be more integrated,
Avoid the deviation of score.
Optionally, Fig. 6 is to walk in the stone age test method based on machine learning model shown in corresponding embodiment according to fig. 2
The datail description of rapid S110, should be based in the stone age test method of machine learning model, and step S110 can also include following step
It is rapid:
Step S111 receives the X-ray to be measured of the image including bone in response to the operation to main display interface;
The X-ray is sent to main display interface by step S112.
In the present embodiment, it is existing so that PACS system, enables the surgeon to comparison side to pass through compatible hospital for the method
Just detection operation is carried out, specific method is, by the operation of doctor, computer equipment 100 starts to carry out stone age detection, is counting
While calculating the reception X-ray of machine equipment 100, the X-ray is sent in the computer main screen of doctor, convenient for doctor according to X-ray
Whether piece judges testing result correct, and gives and modify.
Therefore as shown in fig. 7, after the X-ray is sent to main display interface, the method after step S160,
Further include:
The stone age reference set is sent to auxiliary display screen interface by step S180.
Thus first stone age, the second stone age, third stone age doctor has all been shown to, while also not having interfered doctor
The details for observing the bone showed on X-ray to be measured, is more advantageous to doctor and makes and accurately judge that.
It is existing so that PACS system, easily can be sent directly to stone age detection system for X-ray by compatible hospital
System, and the result calculated is sent to auxiliary display screen, it is more convenient easily to carry out bone so that doctor carries out stone age judgement
Age detection, avoids the trouble using movable storage device.
As shown in figure 8, in one embodiment, a kind of stone age test device based on machine learning model is provided, it should
Stone age test device based on machine learning model can integrate in above-mentioned computer equipment 100, can specifically include: bone
Bone image receiving unit 110, bone Attribute Recognition unit 120, the first stone age output unit 130, the second stone age output unit
140, third stone age output unit 150.
Skeletal image receiving unit 110, for receiving the X-ray of the image to be measured including bone;
Bone Attribute Recognition unit 120, the category of multiple predetermined positions for identifying bone from the image of the bone of X-ray
Property, the attribute of multiple predetermined positions of the bone identified constitutes the first attribute set;
First stone age output unit 130, for the first attribute set to be inputted the first machine learning model, the first engineering
It practises model and exported for the first stone age;
Second stone age output unit 140, for the standard video according to the people's bone of the image and each stone age of bone in X-ray
It is matched, is found with the stone age of the people's bone of the Image Matching of bone in X-ray as the second stone age;
Third stone age output unit 150 is scored for the attribute to each predetermined position in the first attribute set, root
Total score is obtained according to the score of the attribute of each predetermined position, according to total score, inquires total score and stone age mapping table, it is defeated
The third stone age out forms stone age reference set together with the first stone age, the second stone age, for referring to when diagnosis.
The function of modules and the realization process of effect are specifically detailed in above-mentioned based on machine learning model in above-mentioned apparatus
Stone age test method in correspond to the realization process of step, details are not described herein.
Optionally, Fig. 9 is the block diagram of another declaration form distributor shown according to Fig. 8 corresponding embodiment, such as Fig. 9 institute
Show, the stone age test device based on machine learning model shown in Fig. 8 further includes but is not limited to: final bone age estimation unit 160.
Final bone age estimation unit 160, for calculating the weighted sum of the first stone age, the second stone age, third stone age, as inspection
The stone age measured.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/
Or a step is decomposed into execution of multiple steps etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, mobile terminal or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 500 of this embodiment according to the present invention is described referring to Figure 10.The electricity that Figure 10 is shown
Sub- equipment 500 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in Figure 10, electronic equipment 500 is showed in the form of universal computing device.The component of electronic equipment 500 can be with
Including but not limited to: at least one above-mentioned processing unit 510, at least one above-mentioned storage unit 520, the different system components of connection
The bus 530 of (including storage unit 520 and processing unit 510).
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 510
Row, so that various according to the present invention described in the execution of the processing unit 510 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 510 can execute step S110 as shown in Figure 2, receive to
The X-ray for the image including bone surveyed;Step S120 identifies the category of multiple predetermined positions of bone from the image of the bone of X-ray
Property, the attribute of multiple predetermined positions of the bone identified constitutes the first attribute set;Step S130 inputs the first attribute set
First machine learning model, the first machine learning model exported for the first stone age;Step S140, according to the image of bone in X-ray with
The standard video of the people's bone of each stone age is matched, and is found with the stone age of the people's bone of the Image Matching of bone in X-ray as
Two stone ages;Step S150 scores to the attribute of each predetermined position in the first attribute set, according to each predetermined position
The score of attribute obtains total score, according to total score, inquires total score and stone age mapping table, exports the third stone age;Step
S160 calculates the weighted sum of the first stone age, the second stone age, third stone age, as the stone age detected.
Storage unit 520 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 5201 and/or cache memory unit 5202, it can further include read-only memory unit (ROM) 5203.
Storage unit 520 can also include program/utility with one group of (at least one) program module 5205
5204, such program module 5205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 530 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 500 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 500 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 500 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 550.Also, electronic equipment 500 can be with
By network adapter 560 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 560 is communicated by bus 530 with other modules of electronic equipment 500.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 500, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
With reference to shown in Figure 11, the program product for realizing the above method of embodiment according to the present invention is described
600, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
Claims (10)
1. a kind of stone age test method based on machine learning model, which is characterized in that the described method includes:
Receive the X-ray of the image to be measured including bone;
The attribute of multiple predetermined positions of bone is identified from the image of the bone of X-ray, multiple predetermined positions of the bone identified
Attribute constitutes the first attribute set;
First attribute set is inputted into the first machine learning model, the first machine learning model exported for the first stone age;
The image of bone in X-ray is matched with the standard video of the people's bone of each stone age, finds the image with bone in X-ray
The stone age of matched people's bone is as the second stone age;
It scores to the attribute of each predetermined position in the first attribute set, according to scoring for the attribute of each predetermined position
Total score and stone age mapping table are inquired according to total score to total score, export the third stone age;
The weighted sum for calculating the first stone age, the second stone age, third stone age, as the stone age output detected.
2. the method as described in claim 1, which is characterized in that first machine learning model is trained as follows:
The X-ray sample set of the image including bone is obtained, each X-ray sample in X-ray sample set posts the stone age in advance
Label, from the attribute of multiple predetermined positions of each X-ray specimen discerning bone in X-ray sample set, the attribute that will identify that
The first machine learning model is inputted, the stone age that the output of the first machine learning model determines, is compared with the stone age label posted, if not
Unanimously, then first machine learning model is adjusted, it is consistent with label until the stone age of machine learning model output.
3. the method as described in claim 1, which is characterized in that according to the people's bone of the image of bone in X-ray and each stone age
Standard video is matched, and is found with the stone age of the people's bone of the Image Matching of bone in X-ray as the second stone age, is specifically included:
The image of bone is extracted from X-ray;
The pixel value of each pixel of the image of the bone extracted from X-ray is corresponding to the standard video of the people's bone of each stone age
The pixel value of position subtracts each other and asks absolute value, obtains the pixel value absolute value of the difference of each pixel;
The pixel value absolute value of the difference of each pixel is averaging, average value is obtained;
Using the smallest standard video of the average value corresponding stone age as the second stone age.
4. the method as described in claim 1, which is characterized in that the people of the image according to bone in X-ray and each stone age
The step of standard video of bone is matched, and is found with the stone age of the people's bone of the Image Matching of bone in X-ray as the second stone age
Include:
The X-ray is inputted into the second machine learning model, the second machine learning model exports the standard of the people's bone of each stone age
The similarity of image and the X-ray;
Using the stone age of the smallest standard video of the similarity as the second stone age.
Wherein, second machine learning model is trained as follows:
By each bone image sample in the set with bone image sample pair to inputting the second machine learning model, each bone image
Sample sticks similarity label, second machine in advance to including a pair of of bone image sample for a pair of bone image sample in advance
The similarity of the bone image sample pair of device learning model output judgement, is compared with the label sticked, if inconsistent, adjusts
Whole second machine learning model, the similarity for exporting the second machine learning model are consistent with label.
5. the method as described in claim 1, which is characterized in that carried out to the attribute of each predetermined position in the first attribute set
Score includes:
According to the attribute of each predetermined position, growth period mapping table belonging to attribute and bone position is searched, the category is obtained
Property corresponding growth period;
Growth period and score mapping table are searched, to find score corresponding with growth period.
6. the method as described in claim 1, which is characterized in that obtain total score according to the score of the attribute of each predetermined position
Include:
The weighted sum for calculating the score of the attribute of each predetermined position, as total score.
7. method according to claim 1 or 2, which is characterized in that receive the X-ray to be measured of the image including bone, specifically
Include:
In response to the operation to main display interface, the X-ray to be measured of the image including bone is received;
The X-ray is sent to main display interface;
The method exports it as the stone age detected in the weighted sum for calculating the first stone age, the second stone age, third stone age
Afterwards, further includes:
The stone age reference set is sent to auxiliary display screen interface.
8. a kind of stone age test device based on machine learning model, which is characterized in that described device includes:
Skeletal image receiving unit, for receiving the X-ray of the image to be measured including bone;
Bone Attribute Recognition unit, the attribute of multiple predetermined positions for identifying bone from the image of the bone of X-ray, is identified
Bone multiple predetermined positions attribute constitute the first attribute set;
First stone age output unit, for the first attribute set to be inputted the first machine learning model, the first machine learning model
Exported for the first stone age;
Second stone age output unit carries out for the standard video according to the people's bone of the image and each stone age of bone in X-ray
Match, finds with the stone age of the people's bone of the Image Matching of bone in X-ray as the second stone age;
Third stone age output unit is scored for the attribute to each predetermined position in the first attribute set, according to each
The score of the attribute of predetermined position obtains total score, according to total score, inquires total score and stone age mapping table, exports third
Stone age forms stone age reference set together with the first stone age, the second stone age, for referring to when diagnosis.
9. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, it is described
When computer-readable instruction is executed by the processor, so that the processor is executed as described in any one of claims 1 to 7
Method.
10. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes, so that one or more processors execute the method as described in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910327391.0A CN110211674B (en) | 2019-04-23 | 2019-04-23 | Bone age testing method and related equipment based on machine learning model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910327391.0A CN110211674B (en) | 2019-04-23 | 2019-04-23 | Bone age testing method and related equipment based on machine learning model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110211674A true CN110211674A (en) | 2019-09-06 |
CN110211674B CN110211674B (en) | 2023-06-27 |
Family
ID=67786122
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910327391.0A Active CN110211674B (en) | 2019-04-23 | 2019-04-23 | Bone age testing method and related equipment based on machine learning model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110211674B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111860662A (en) * | 2020-07-24 | 2020-10-30 | 南开大学 | Training method and device, application method and device of similarity detection model |
CN112785559A (en) * | 2021-01-05 | 2021-05-11 | 四川大学 | Bone age prediction method based on deep learning and formed by mutually combining multiple heterogeneous models |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090105958A1 (en) * | 2005-06-02 | 2009-04-23 | Hans Henrik Thodberg | Method for skeletal maturity determination |
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 |
US20180232603A1 (en) * | 2015-08-04 | 2018-08-16 | The Asan Foundation | Method and program for computing bone age by deep neural network |
CN108629762A (en) * | 2018-03-28 | 2018-10-09 | 浙江工业大学 | A kind of stone age evaluation and test model reduces the image pre-processing method and system of interference characteristic |
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 |
CN109242867A (en) * | 2018-08-09 | 2019-01-18 | 杭州电子科技大学 | A kind of hand bone automatic division method based on template |
CN109285154A (en) * | 2018-09-30 | 2019-01-29 | 杭州依图医疗技术有限公司 | A kind of method and device detecting the stone age |
-
2019
- 2019-04-23 CN CN201910327391.0A patent/CN110211674B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090105958A1 (en) * | 2005-06-02 | 2009-04-23 | Hans Henrik Thodberg | Method for skeletal maturity determination |
US20180232603A1 (en) * | 2015-08-04 | 2018-08-16 | The Asan Foundation | Method and program for computing bone age by deep neural network |
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 |
CN108629762A (en) * | 2018-03-28 | 2018-10-09 | 浙江工业大学 | A kind of stone age evaluation and test model reduces the image pre-processing method and system of interference characteristic |
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 |
CN109242867A (en) * | 2018-08-09 | 2019-01-18 | 杭州电子科技大学 | A kind of hand bone automatic division method based on template |
CN109285154A (en) * | 2018-09-30 | 2019-01-29 | 杭州依图医疗技术有限公司 | A kind of method and device detecting the stone age |
Non-Patent Citations (1)
Title |
---|
黄幼才\N\N\N,刘友光: "X光摄影测量在人体手腕骨骨龄评定中的应用", 武汉大学学报(信息科学版), no. 03, pages 68 - 71 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111860662A (en) * | 2020-07-24 | 2020-10-30 | 南开大学 | Training method and device, application method and device of similarity detection model |
CN111860662B (en) * | 2020-07-24 | 2023-03-24 | 南开大学 | Training method and device, application method and device of similarity detection model |
CN112785559A (en) * | 2021-01-05 | 2021-05-11 | 四川大学 | Bone age prediction method based on deep learning and formed by mutually combining multiple heterogeneous models |
CN112785559B (en) * | 2021-01-05 | 2022-07-12 | 四川大学 | Bone age prediction method based on deep learning and formed by mutually combining multiple heterogeneous models |
Also Published As
Publication number | Publication date |
---|---|
CN110211674B (en) | 2023-06-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110738263B (en) | Image recognition model training method, image recognition method and image recognition device | |
Wells et al. | Artificial intelligence in dermatopathology: Diagnosis, education, and research | |
US20190147360A1 (en) | Learned model provision method, and learned model provision device | |
CN114727766A (en) | System for collecting and identifying skin conditions from images and expert knowledge | |
US20110245623A1 (en) | Medical Diagnosis Using Community Information | |
CN104966327A (en) | System and method for monitoring health and registering attendance on basis of internet of things | |
Wang et al. | An automatic assessment system of diabetic foot ulcers based on wound area determination, color segmentation, and healing score evaluation | |
KR20190030151A (en) | Apparatus, method and computer program for analyzing image | |
CN105868524A (en) | Automatic ground truth generation for medical image collections | |
Fernandez et al. | Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist | |
US20220125360A1 (en) | Method and computer program for determining psychological state through drawing process of counseling recipient | |
WO2020177348A1 (en) | Method and apparatus for generating three-dimensional model | |
US20230097391A1 (en) | Image processing method and apparatus, electronic device, computer-readable storage medium, and computer program product | |
CN110211674A (en) | Stone age test method and relevant device based on machine learning model | |
CN114049683A (en) | Post-healing rehabilitation auxiliary detection system, method and medium based on three-dimensional human skeleton model | |
KR102030131B1 (en) | Continuous skin condition estimating method using infrared image | |
CN116705300A (en) | Medical decision assistance method, system and storage medium based on sign data analysis | |
CN113707304A (en) | Triage data processing method, device, equipment and storage medium | |
CN111640517B (en) | Medical record coding method and device, storage medium and electronic equipment | |
WO2021120589A1 (en) | Method and apparatus for abnormal image filtering for use on 3d images, device, and storage medium | |
CN109785941B (en) | Doctor recommendation method and device | |
Kumar et al. | A Critical Analysis on Vertebra Identification and Cobb Angle Estimation Using Deep Learning for Scoliosis Detection | |
CN112397195A (en) | Method, apparatus, electronic device, and medium for generating physical examination model | |
CN116230198A (en) | Multidimensional Tibetan medicine AI intelligent auxiliary decision-making device and system | |
CN114141358A (en) | Disease diagnosis apparatus based on knowledge map, computer device, 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |