CN107563997A - A kind of skin disease diagnostic system, construction method, diagnostic method and diagnostic device - Google Patents
A kind of skin disease diagnostic system, construction method, diagnostic method and diagnostic device Download PDFInfo
- Publication number
- CN107563997A CN107563997A CN201710735310.1A CN201710735310A CN107563997A CN 107563997 A CN107563997 A CN 107563997A CN 201710735310 A CN201710735310 A CN 201710735310A CN 107563997 A CN107563997 A CN 107563997A
- Authority
- CN
- China
- Prior art keywords
- grader
- skin disease
- skin
- image
- training image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of skin disease diagnostic system, construction method, diagnostic method and diagnostic device.Wherein, construction method includes:Training image is obtained, training image includes:The first corresponding dermopathic first training image, corresponding second of dermopathic second training image, and the third corresponding dermopathic 3rd training image;Using first nerves network, build for identifying the first dermopathic first grader, and the input data using above-mentioned three kinds of training images as the first nerves network, to be trained to the first grader;Using nervus opticus network, build for identifying second of dermopathic second grader, and the input data using above-mentioned three kinds of training images as nervus opticus network, to be trained to the second grader;Based on the first grader and second grader structure skin disease diagnostic system.The present invention is based on image recognition technology, constructs a kind of skin disease diagnostic system, can voluntarily diagnose skin disease.
Description
Technical field
The present invention relates to image recognition applied technical field, particularly relates to a kind of skin disease diagnostic system, construction method, examines
Disconnected method and diagnostic device.
Background technology
With the arrival in big data epoch, depth learning technology is applied in the application of image recognition more.It is deep
Degree study is a kind of powerful technology for coming from artificial neural network.And artificial neural network is then by the neutral net of nature biotechnology
Inspire, by building the neuron of multilayer, plus the repetition training of mass data, and then class is anthropoid accurately identifies figure
The ability of picture.
Current image recognition class product is more the identification to life images such as face, car plate, moving targets.For
Medical domain, particularly skin disease, image recognition class is not yet quoted to carry out unartificial diagnosis.
The content of the invention
It is an object of the invention to provide one kind to be based on image recognition technology, and realization voluntarily diagnoses dermopathic technical scheme.
To achieve the above object, on the one hand, embodiments of the invention provide a kind of construction method of skin disease diagnostic system,
Including:
Training image is obtained, the training image includes:The first corresponding dermopathic first training image, corresponding second
Dermopathic second training image of kind, and the third corresponding dermopathic 3rd training image;
Using first nerves network, build for identifying the first dermopathic first grader, and described first is instructed
Practice the input data of image, second training image and the 3rd training image as the first nerves network, with right
First grader is trained;
Using nervus opticus network, build for identifying second of dermopathic second grader, and described first is instructed
Practice the input data of image, second training image and the 3rd training image as the first nerves network, with right
Second grader is trained;
At least built based on first grader and second grader for diagnosing the first described skin disease, the
Two kinds of skin diseases and the third dermopathic skin disease diagnostic system.
Wherein, the construction method also includes:
Using third nerve network, the 3rd grader for distinguishing the first skin disease and second of disease is built, and
Input data using first training image and second training image as the third nerve network, with to described
Three graders are trained;
Wherein, the step of building the skin disease diagnostic system specifically includes:
Based on first grader, the second grader structure and the 3rd grader, build described for diagnosing
The first skin disease, second of skin disease and the third dermopathic skin disease diagnostic system.
The first wherein described skin disease, second of skin disease and the third skin disease are respectively following one of which
Disease of skin:
Melanoma, keratosis and mole.
Wherein, the construction method is after training image is obtained, and builds first grader, second grader
And before the 3rd grader, in addition to:
Pretreatment operation is carried out to the training image;
The pretreatment operation includes at least one of in the following manner:
The invalid identification region of training image is cut;
The display size of different training images is normalized.
Wherein, the construction method is after training image is obtained, and builds first grader, second grader
And before the 3rd grader, in addition to:
Data are carried out to the training image and strengthen operation;
The data, which strengthen operation, includes at least one of in the following manner:
Saturation degree and/or brightness and/or contrast to the training image optimize;
The training image is overturn and/or rotated.
On the other hand, embodiments of the invention also provide a kind of skin disease diagnostic system, the skin disease diagnostic system by
Above-mentioned construction method provided by the invention builds to obtain.
In addition, embodiments of the invention also provide a kind of dermopathic diagnostic method, applied to provided by the invention above-mentioned
Skin disease diagnostic system, including:
Obtain purported skin image to be diagnosed;
Using the purported skin image as the first grader in the skin disease diagnostic system and the second grader
Input data;
If first grader identifies that the purported skin image corresponds to the first skin disease, and second classification
The unidentified purported skin image of device corresponds to second of skin disease, then is diagnosed as with the first skin disease;
If the unidentified purported skin image of the first grader corresponds to the first skin disease, and described second point
Class device identifies that the purported skin image corresponds to second of skin disease, then is diagnosed as with second of skin disease;
If the unidentified purported skin image of the first grader corresponds to the first skin disease, and described second point
The unidentified purported skin image of class device corresponds to second of skin disease, then is diagnosed as with the third skin disease.
Wherein, the skin disease diagnostic system also includes the 3rd grader, and the diagnostic method also includes:
If first grader identifies that the purported skin image corresponds to the first skin disease, and second classification
Device identifies that the purported skin image corresponds to second of skin disease, then using the purported skin image as the described 3rd classification
The input data of device;
If the 3rd grader identifies that the purported skin image corresponds to the first skin disease, it is diagnosed as with the first
Skin disease.
If the 3rd grader identifies that the purported skin image corresponds to second of skin disease, it is diagnosed as with second
Skin disease.
In addition, embodiments of the invention also provide a kind of dermopathic diagnostic device, including:
Image capture module, for obtaining purported skin image to be diagnosed;
Data processing module, preserves computer program, and the computer program is used to perform diagnosis side as described above
Step in method.
Wherein, the diagnostic device also includes:
Diagnostic result output module, for exporting the confirmed result of the data processing module.
The such scheme of the present invention has the advantages that:
The solution of the present invention is based on image recognition technology, constructs a kind of skin disease diagnostic system, can voluntarily diagnose skin
Skin disease or auxiliary diagnosis skin disease, can reduce the probability of mistaken diagnosis, therefore have very high practicality in medical field
Value.
Brief description of the drawings
Fig. 1 is the step schematic diagram of the construction method of skin disease diagnostic system provided in an embodiment of the present invention;
Fig. 2 is the step schematic diagram of diagnostic method provided in an embodiment of the present invention;
Fig. 3 is the structural representation of skin disease diagnostic system provided in an embodiment of the present invention in actual applications;
Fig. 4 is the structural representation of diagnostic device provided in an embodiment of the present invention.
Embodiment
To make the technical problem to be solved in the present invention, technical scheme and advantage clearer, below in conjunction with accompanying drawing and tool
Body embodiment is described in detail.
The present invention provides a kind of based on the dermopathic technical scheme of image recognition technology diagnosis.
On the one hand, embodiments of the invention provide a kind of construction method of skin disease diagnostic system, as shown in figure 1, including:
Step 110, training image is obtained, training image includes:The first corresponding dermopathic first training image, correspondingly
Second of dermopathic second training image, and the third corresponding dermopathic 3rd training image.
In actual applications, training image is above-mentioned three kinds dermopathic case images, can be obtained from clinic,
It can be obtained by simulation making.
Step 120, using first nerves network, build for identifying the first dermopathic first grader, and by the
The input data of one training image, the second training image and the 3rd training image as nervus opticus network, to the first grader
It is trained.
Need exist for being described, it is prior art to build grader using neutral net, as current
CNN neural network models newest Inception-ResNet, GoogLeNet v3 etc. can build above-mentioned first grader,
Because this step is to need to carry out the parameter modification of some adaptability on the basis of existing neural network model, therefore detailed
Implementation process no longer carries out citing and repeated.
Step 130, using nervus opticus network, build for identifying second of dermopathic second grader, and by the
The input data of one training image, the second training image and the 3rd training image as first nerves network, to the second grader
It is trained;
Similarly, above-mentioned second grader can also be built using existing neural network model.
Step 140, at least built based on the first grader and second grader for diagnosing the first skin disease, the
Two kinds of skin diseases and the third dermopathic diagnostic model, to form skin disease diagnostic system.
The construction method of the present embodiment is used to build a kind of diagnosable dermopathic diagnostic system, can voluntarily diagnose skin
Disease or auxiliary diagnosis skin disease, can drop the probability of mistaken diagnosis, therefore have very high practical value in medical field.
Further, when by the skin disease diagnostic system that the present embodiment is inputted wait the purported skin image diagnosed, if the
One grader identification purported skin image corresponds to the first skin disease, and the unidentified purported skin image of the second grader is corresponding
For second of skin disease, then can be diagnosed as with the first skin disease;If the unidentified purported skin image pair of the first grader
The first skin disease is should be, and the second grader identification purported skin image corresponds to second of skin disease, then can be diagnosed as
With second of skin disease;If the unidentified purported skin image of the first grader corresponds to the first skin disease, and second
The unidentified purported skin image of grader corresponds to second of skin disease, then is diagnosed as with the third skin disease.
Diagnosis principle based on above-mentioned skin disease diagnostic system is it is recognised that first grader of the present embodiment and second point
Class device can be carried out double verification, three kinds of disease of skin are diagnosed so as to realize by assembled classification.That is, this implementation
The skin disease diagnostic system of example uses less grader, realizes the dermopathic diagnostic function to larger class.
Specifically, on above-mentioned basis, preferably, the construction method of the present embodiment also includes:
Step 131, using third nerve network, build for distinguish the first skin disease and second of disease the 3rd point
Class device, and by the input data that the first training image and second training image are third nerve network, with to the described 3rd
Grader is trained;
Wherein, in above-mentioned steps 140, the first grader, the second grader structure and the 3rd grader are specifically based on, is built
For diagnosing the first skin disease, second of skin disease and the third dermopathic skin disease diagnostic system.
In diagnostic application, if the first grader identification purported skin image corresponds to the first skin disease, and second point
Class device identifies that the purported skin image corresponds to second of skin disease, then using purported skin image as the defeated of the 3rd grader
Enter data;
If the 3rd grader identification purported skin image corresponds to the first skin disease, it is diagnosed as with the first skin
Disease.
If the 3rd grader identification purported skin image corresponds to second of skin disease, it is diagnosed as with second of skin
Disease.
Obviously, the 3rd grader of the present embodiment is exclusively used in distinguishing the first skin disease and second of skin disease.Therefore work as
First grader and the second grader simultaneously by purported skin image confirming examine for each self-corresponding skin disease when, can further by
Purported skin image inputs to the 3rd grader and carries out more accurate classification.3rd grader can distinguish purported skin image
The first corresponding skin disease still corresponds to second of skin disease, so as to ensure the accuracy rate of diagnosis.
In addition, in specific practical application, the present embodiment is using the training image of magnanimity to above-mentioned first grader, second
Grader and the 3rd grader are trained.
In order to ensure that the first grader and the second grader can be normally carried out training, preferably, the present embodiment
, can also be to training image after training image is obtained, and before the first grader of structure, the second grader and the 3rd grader
Pretreatment operation is carried out, the pretreatment operation includes at least one of in the following manner:
The invalid identification region of training image is cut;
The display size of different training images is normalized.
Obviously, based on above-mentioned pretreatment operation, the miscellaneous training image that can allow obtained by different acquisition approachs
With unified picture specification, in order to which the first grader and the second grader can keep the corresponding skin disease of identical standard training
Characteristics of image.
In addition, preferably, the present embodiment builds the first grader, the second classification after training image is obtained
Before device and the 3rd grader, data enhancing processing can also be carried out to training image, to strengthen the generalization ability of training image
With identified ability.
Specifically above-mentioned data enhancing processing mode can include following a kind of at least within:
By the image processing algorithm pre-seted, the data of the color of training image are strengthened, including the saturation degree of color,
Brightness and contrast etc. optimizes processing;
Pass through the image processing algorithm pre-seted, the upset or rotation carried out to training image, to optimize training image
Display view angle.
Explanation is needed exist for, above-mentioned data enhancing processing can be can be achieved by current image processing software,
Due to being prior art, no longer repeated herein.
In addition, in actual applications, the skin disease diagnostic system of the present embodiment can be used for detection melanoma, keratosis and
Mole.That is, above-mentioned the first skin disease, second of skin disease and the third skin disease for respectively melanoma, keratosis and mole its
A kind of middle disease of skin.
It is appreciated that feature of these three diseases of melanoma, keratosis and mole on skin is similar, amateur medical treatment
Personnel are difficult to distinguish, and then can be to these three skins based on the skin disease diagnostic system obtained by the present embodiment construction method
Skin disease carries out Accurate Diagnosis, helps patient to take correct remedy measures in time.
On the other hand, embodiments of the invention also provide a kind of skin disease diagnostic system, and the skin disease diagnostic system is by this
Obtained constructed by the construction method that above-mentioned offer is provided.
As can be seen that the skin disease diagnostic system of the present embodiment can voluntarily carry out diagnosing disease of skin or aid in doctor
Disease of skin is diagnosed, can drop the probability of mistaken diagnosis, therefore there is very high practical value in medical field.
In addition, embodiments of the invention also provide a kind of dermopathic diagnostic method, applied to provided by the invention above-mentioned
Skin disease diagnostic system, as shown in Fig. 2 including:
Step 210, purported skin image to be diagnosed is obtained.
Step 220, classify purported skin image as the first grader in the skin disease diagnostic system and second
The input data of device.
Step 230, if the first grader identification purported skin image corresponds to the first skin disease, and the second grader is not
Identification purported skin image corresponds to second of skin disease, then is diagnosed as with the first skin disease.
Step 240, if the unidentified purported skin image of the first grader corresponds to the first skin disease, and the second grader
Identification purported skin image corresponds to second of skin disease, then is diagnosed as with second of skin disease.
Step 250, if the unidentified purported skin image of the first grader corresponds to the first skin disease, and the second grader
Unidentified purported skin image corresponds to second of skin disease, then is diagnosed as with the third skin disease.
Diagnosis principle based on above-mentioned skin disease diagnostic system is it is recognised that first grader of the present embodiment and second point
Class device can be carried out double verification, three kinds of disease of skin are diagnosed so as to realize by assembled classification.
Specifically, in order to strengthen the accuracy being directed to, the skin disease diagnostic system that the present embodiment is applied also includes the 3rd
Grader, corresponding diagnostic method also include:
Step 260, if the first grader identification purported skin image corresponds to the first skin disease, and the second grader is known
Other purported skin image corresponds to second of skin disease, then the input data using purported skin image as the 3rd grader;
Step 270, if the 3rd grader identification purported skin image corresponds to the first skin disease, it is diagnosed as with the
A kind of skin disease.
Step 280, if the 3rd grader identification purported skin image corresponds to second of skin disease, it is diagnosed as with the
Two kinds of skin diseases.
Obviously, the 3rd grader of the present embodiment is exclusively used in distinguishing the first skin disease and second of skin disease.Therefore work as
First grader and the second grader simultaneously by purported skin image confirming examine for each self-corresponding skin disease when, can further by
Purported skin image inputs to the 3rd grader and carries out more accurate classification.3rd grader can distinguish purported skin image
The first corresponding skin disease still corresponds to second of skin disease, so as to ensure the accuracy rate of diagnosis.
With reference to a practical application, the diagnosis mechanism of the present embodiment is described in detail.
Exemplarily, the skin disease diagnostic system that the present embodiment is applied, for diagnose melanoma, keratosis and mole this three
Kind disease of skin.
That is, skin disease diagnostic system 300 includes:
Melanoma grader 301, it is above-mentioned three kinds dermopathic lesion images that it, which instructs it to practice data, and testing goal is differentiation
Melanoma and other lesions;
Keratosis grader 302, training data are above-mentioned three kinds dermopathic lesion images, and testing goal distinguishes keratosis
With other lesions;
Melanoma and keratosis grader 303, training data are the lesion image of melanoma and keratosis, and testing goal is
Distinguish melanoma and keratosis.
Melanoma grader 301 and keratosis grader 302 are combined first, by purported skin image to be diagnosed
It is input in melanoma grader 301 and keratosis grader 302 and is identified simultaneously, different places is carried out for classification results
Reason:
Melanoma grader is identified as melanoma, and keratosis grader is identified as other lesions, then output category result is
Melanoma.
Melanoma grader is identified as other lesions, and keratosis grader is identified as other lesions, then output category result
For mole.
Melanoma grader is identified as other lesions, and keratosis grader is identified as keratosis, then output category result is
Keratosis.
Melanoma grader is identified as melanoma, and keratosis grader is identified as keratosis, then inputs an image into melanocyte
Further identified and classified in knurl and keratosis grader 303;
Melanoma and keratosis grader 303 identify melanoma, then output category result is melanoma;Melanoma and angle
Change disease grader 303 and identify keratosis, then output category result is keratosis.
Wherein, above-mentioned classification results are diagnostic result.
In addition, embodiments of the invention also provide a kind of dermopathic diagnostic device 400, as shown in figure 4, including:
Image capture module 401, for obtaining purported skin image to be diagnosed;
Data processing module 402, preserves computer program, and the computer program is provided by the invention above-mentioned for performing
Step in diagnostic method;
Diagnostic result output module 403, the confirmed result for output data processing module.
In actual applications, the diagnostic device 400 of the present embodiment can be that special medicine equipment or user are whole
End equipment.
By taking subscriber terminal equipment as an example, then above-mentioned image capture module 401 can be the camera of subscriber terminal equipment, on
The processor that data processing module 402 can be subscriber terminal equipment is stated, processor is based on preset value calculating and program is realized, or
Person's treatment region is realized that above-mentioned diagnostic result is defeated based on the cloud processor or server with subscriber terminal equipment foundation connection
Go out the display that module 403 is subscriber terminal equipment.
Obviously, based on above-mentioned practical application, user can be to skin by the terminal device (such as mobile phone, PAD) of individual
Skin disease is diagnosed, so as to reduce diagnosis threshold.As can be seen here, the diagnostic device of the present embodiment has very high practicality.
Described above is the preferred embodiment of the present invention, it is noted that for those skilled in the art
For, on the premise of principle of the present invention is not departed from, some improvements and modifications can also be made, these improvements and modifications
It should be regarded as protection scope of the present invention.
Unless otherwise defined, the technical term or scientific terminology that the disclosure uses, which are should be in art of the present invention, to be had
The ordinary meaning that the personage for having general technical ability is understood." first ", " second " and the similar word used in the disclosure is simultaneously
Any order, quantity or importance are not indicated that, and is used only to distinguish different parts." comprising " or "comprising" etc.
Either object covers the element or object for appearing in the word presented hereinafter to the element that similar word means to occur before the word
And its it is equivalent, and it is not excluded for other elements or object.
Claims (10)
- A kind of 1. construction method of skin disease diagnostic system, it is characterised in that including:Training image is obtained, the training image includes:The first corresponding dermopathic first training image, corresponding second of skin Second training image of skin disease, and the third corresponding dermopathic 3rd training image;Using first nerves network, build for identifying the first dermopathic first grader, and the described first training is schemed Picture, the input data of second training image and the 3rd training image as the first nerves network, with to described First grader is trained;Using nervus opticus network, build for identifying second of dermopathic second grader, and the described first training is schemed Picture, the input data of second training image and the 3rd training image as the nervus opticus network, with to described Second grader is trained;At least based on first grader and second grader build for diagnose the first described skin disease, second Skin disease and the third dermopathic skin disease diagnostic system.
- 2. construction method according to claim 1, it is characterised in that also include:Using third nerve network, the 3rd grader for distinguishing the first skin disease and second of disease is built, and by institute The input data of the first training image and second training image as the third nerve network is stated, with to described 3rd point Class device is trained;Wherein, the step of building the skin disease diagnostic system specifically includes:Based on first grader, the second grader structure and the 3rd grader, build for diagnosing described first Kind skin disease, second of skin disease and the third dermopathic skin disease diagnostic system.
- 3. construction method according to claim 1 or 2, it is characterised in thatThe first described skin disease, second of skin disease and the third skin disease are respectively following one of which skin disease Disease:Melanoma, keratosis and mole.
- 4. construction method according to claim 2, it is characterised in that after training image is obtained, and build described first Before grader, second grader and the 3rd grader, in addition to:Pretreatment operation is carried out to the training image;The pretreatment operation includes at least one of in the following manner:The invalid identification region of training image is cut;The display size of different training images is normalized.
- 5. construction method according to claim 2, it is characterised in that after training image is obtained, and build described first Before grader, second grader and the 3rd grader, in addition to:Data are carried out to the training image and strengthen operation;The data, which strengthen operation, includes at least one of in the following manner:Saturation degree and/or brightness and/or contrast to the training image optimize;The training image is overturn and/or rotated.
- 6. a kind of skin disease diagnostic system, it is characterised in that the skin disease diagnostic system is as described in claim any one of 1-5 Construction method build to obtain.
- A kind of 7. dermopathic diagnostic method, applied to skin disease diagnostic system as claimed in claim 6, it is characterised in that Including:Obtain purported skin image to be diagnosed;Input using the purported skin image as the first grader and the second grader in the skin disease diagnostic system Data;If first grader identifies that the purported skin image corresponds to the first skin disease, and second grader is not Identify that the purported skin image corresponds to second of skin disease, be then diagnosed as with the first skin disease;If the unidentified purported skin image of the first grader corresponds to the first skin disease, and second grader Identify that the purported skin image corresponds to second of skin disease, be then diagnosed as with second of skin disease;If the unidentified purported skin image of the first grader corresponds to the first skin disease, and second grader The unidentified purported skin image corresponds to second of skin disease, then is diagnosed as with the third skin disease.
- 8. dermopathic diagnostic method according to claim 7, it is characterised in that the skin disease diagnostic system also includes 3rd grader, the diagnostic method also include:If first grader identifies that the purported skin image corresponds to the first skin disease, and second grader is known Not described purported skin image corresponds to second of skin disease, then using the purported skin image as the 3rd grader Input data;If the 3rd grader identifies that the purported skin image corresponds to the first skin disease, it is diagnosed as with the first skin Disease.If the 3rd grader identifies that the purported skin image corresponds to second of skin disease, it is diagnosed as with second of skin Disease.
- A kind of 9. dermopathic diagnostic device, it is characterised in that including:Image capture module, for obtaining purported skin image to be diagnosed;Data processing module, preserves computer program, and the computer program is used to perform as claimed in claim 7 or 8 Step in diagnostic method.
- 10. dermopathic diagnostic device according to claim 9, it is characterised in that also include:Diagnostic result output module, for exporting the confirmed result of the data processing module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710735310.1A CN107563997B (en) | 2017-08-24 | 2017-08-24 | Skin disease diagnosis system, construction method, classification method and diagnosis device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710735310.1A CN107563997B (en) | 2017-08-24 | 2017-08-24 | Skin disease diagnosis system, construction method, classification method and diagnosis device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107563997A true CN107563997A (en) | 2018-01-09 |
CN107563997B CN107563997B (en) | 2020-06-02 |
Family
ID=60976826
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710735310.1A Active CN107563997B (en) | 2017-08-24 | 2017-08-24 | Skin disease diagnosis system, construction method, classification method and diagnosis device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107563997B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108154509A (en) * | 2018-01-12 | 2018-06-12 | 平安科技(深圳)有限公司 | Cancer recognition methods, device and storage medium |
CN108198620A (en) * | 2018-01-12 | 2018-06-22 | 洛阳飞来石软件开发有限公司 | A kind of skin disease intelligent auxiliary diagnosis system based on deep learning |
CN109949272A (en) * | 2019-02-18 | 2019-06-28 | 四川拾智联兴科技有限公司 | Identify the collecting method and system of skin disease type acquisition human skin picture |
CN110648751A (en) * | 2019-10-30 | 2020-01-03 | 中南大学湘雅三医院 | System and method for delineating possible diseases by utilizing skin CT |
CN114269231A (en) * | 2019-06-18 | 2022-04-01 | 数字诊断公司 | Determining a diagnosis based on a patient's skin tone using a set of machine-learned diagnostic models |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101517602A (en) * | 2006-09-22 | 2009-08-26 | 皇家飞利浦电子股份有限公司 | Methods for feature selection using classifier ensemble based genetic algorithms |
CN101517614A (en) * | 2006-09-22 | 2009-08-26 | 皇家飞利浦电子股份有限公司 | Advanced computer-aided diagnosis of lung nodules |
CN102221363A (en) * | 2011-04-12 | 2011-10-19 | 东南大学 | Fault-tolerant combined method of strapdown inertial integrated navigation system for underwater vehicles |
CN102509122A (en) * | 2011-11-25 | 2012-06-20 | 广东威创视讯科技股份有限公司 | Intelligent pen color identifying method applied to interactive touch screen |
CN103246888A (en) * | 2012-02-03 | 2013-08-14 | 通用电气公司 | System and method for diagnosing lung disease by computer |
CN103914064A (en) * | 2014-04-01 | 2014-07-09 | 浙江大学 | Industrial process fault diagnosis method based on multiple classifiers and D-S evidence fusion |
WO2015054666A1 (en) * | 2013-10-10 | 2015-04-16 | Board Of Regents, The University Of Texas System | Systems and methods for quantitative analysis of histopathology images using multi-classifier ensemble schemes |
CN106971160A (en) * | 2017-03-23 | 2017-07-21 | 西京学院 | Winter jujube disease recognition method based on depth convolutional neural networks and disease geo-radar image |
CN107368670A (en) * | 2017-06-07 | 2017-11-21 | 万香波 | Stomach cancer pathology diagnostic support system and method based on big data deep learning |
-
2017
- 2017-08-24 CN CN201710735310.1A patent/CN107563997B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101517602A (en) * | 2006-09-22 | 2009-08-26 | 皇家飞利浦电子股份有限公司 | Methods for feature selection using classifier ensemble based genetic algorithms |
CN101517614A (en) * | 2006-09-22 | 2009-08-26 | 皇家飞利浦电子股份有限公司 | Advanced computer-aided diagnosis of lung nodules |
CN102221363A (en) * | 2011-04-12 | 2011-10-19 | 东南大学 | Fault-tolerant combined method of strapdown inertial integrated navigation system for underwater vehicles |
CN102509122A (en) * | 2011-11-25 | 2012-06-20 | 广东威创视讯科技股份有限公司 | Intelligent pen color identifying method applied to interactive touch screen |
CN103246888A (en) * | 2012-02-03 | 2013-08-14 | 通用电气公司 | System and method for diagnosing lung disease by computer |
WO2015054666A1 (en) * | 2013-10-10 | 2015-04-16 | Board Of Regents, The University Of Texas System | Systems and methods for quantitative analysis of histopathology images using multi-classifier ensemble schemes |
CN103914064A (en) * | 2014-04-01 | 2014-07-09 | 浙江大学 | Industrial process fault diagnosis method based on multiple classifiers and D-S evidence fusion |
CN106971160A (en) * | 2017-03-23 | 2017-07-21 | 西京学院 | Winter jujube disease recognition method based on depth convolutional neural networks and disease geo-radar image |
CN107368670A (en) * | 2017-06-07 | 2017-11-21 | 万香波 | Stomach cancer pathology diagnostic support system and method based on big data deep learning |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108154509A (en) * | 2018-01-12 | 2018-06-12 | 平安科技(深圳)有限公司 | Cancer recognition methods, device and storage medium |
CN108198620A (en) * | 2018-01-12 | 2018-06-22 | 洛阳飞来石软件开发有限公司 | A kind of skin disease intelligent auxiliary diagnosis system based on deep learning |
CN108154509B (en) * | 2018-01-12 | 2022-11-11 | 平安科技(深圳)有限公司 | Cancer identification method, device and storage medium |
CN109949272A (en) * | 2019-02-18 | 2019-06-28 | 四川拾智联兴科技有限公司 | Identify the collecting method and system of skin disease type acquisition human skin picture |
CN109949272B (en) * | 2019-02-18 | 2023-06-20 | 四川拾智联兴科技有限公司 | Data acquisition method and system for identifying skin disease types and acquiring human skin pictures |
CN114269231A (en) * | 2019-06-18 | 2022-04-01 | 数字诊断公司 | Determining a diagnosis based on a patient's skin tone using a set of machine-learned diagnostic models |
CN110648751A (en) * | 2019-10-30 | 2020-01-03 | 中南大学湘雅三医院 | System and method for delineating possible diseases by utilizing skin CT |
Also Published As
Publication number | Publication date |
---|---|
CN107563997B (en) | 2020-06-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107563997A (en) | A kind of skin disease diagnostic system, construction method, diagnostic method and diagnostic device | |
US11755121B2 (en) | Gesture information processing method and apparatus, electronic device, and storage medium | |
CN108553081B (en) | Diagnosis system based on tongue fur image | |
CN106909778A (en) | A kind of Multimodal medical image recognition methods and device based on deep learning | |
CN104274191B (en) | A kind of Psychological Evaluation method and system thereof | |
US11557400B2 (en) | Machine learning to identify locations of brain injury | |
JP2006305260A (en) | Expression diagnosis assisting apparatus | |
CN110428417A (en) | Property method of discrimination, storage medium and the Vltrasonic device of carotid plaques | |
CN111179258A (en) | Artificial intelligence method and system for identifying retinal hemorrhage image | |
CN110473176A (en) | Image processing method and device, method for processing fundus images, electronic equipment | |
CN117237351A (en) | Ultrasonic image analysis method and related device | |
CN110197722B (en) | AI-CPU system platform | |
CN112070737A (en) | Traditional Chinese medicine tongue observation and syndrome differentiation intelligent identification method based on tongue picture image processing | |
CN116824670A (en) | Micro-expression-based inquiry assisting method, device, equipment and medium | |
Sridhar et al. | Artificial intelligence in medicine: diabetes as a model | |
CN116230198A (en) | Multidimensional Tibetan medicine AI intelligent auxiliary decision-making device and system | |
John et al. | Classification of ovarian cysts using artificial neural network | |
CN111340778A (en) | Glaucoma image processing method and equipment | |
CN113796850A (en) | Parathyroid MIBI image analysis system, computer device, and storage medium | |
Meshram et al. | MCBM: Implementation Of Multiclass And Transfer Learning Algorithm Based On Deep Learning Model For Early Detection Of Diabetic Retinopathy | |
Hall et al. | Towards haptic performance analysis using k-metrics | |
Doan et al. | Implementation of complete glaucoma diagnostic system using machine learning and retinal fundus image processing | |
CN109767340A (en) | Blood disease submits an expense account access method, device, equipment and readable storage medium storing program for executing | |
CN109480757A (en) | Visual function detection method and system and device | |
Çelik | A novel deep learning model for pain intensity evaluation |
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 |