CN108596198A - A kind of recognition methods of pneumothorax x-ray image and system based on deep learning - Google Patents
A kind of recognition methods of pneumothorax x-ray image and system based on deep learning Download PDFInfo
- Publication number
- CN108596198A CN108596198A CN201710620039.7A CN201710620039A CN108596198A CN 108596198 A CN108596198 A CN 108596198A CN 201710620039 A CN201710620039 A CN 201710620039A CN 108596198 A CN108596198 A CN 108596198A
- Authority
- CN
- China
- Prior art keywords
- pneumothorax
- ray image
- rabat
- neural network
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 201000003144 pneumothorax Diseases 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000013135 deep learning Methods 0.000 title claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 30
- 210000004218 nerve net Anatomy 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 22
- 230000001537 neural effect Effects 0.000 claims description 8
- 238000007689 inspection Methods 0.000 abstract description 5
- 210000004072 lung Anatomy 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 210000001519 tissue Anatomy 0.000 description 3
- 210000000038 chest Anatomy 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 210000004224 pleura Anatomy 0.000 description 2
- 210000003281 pleural cavity Anatomy 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 208000030090 Acute Disease Diseases 0.000 description 1
- 206010003694 Atrophy Diseases 0.000 description 1
- 206010006458 Bronchitis chronic Diseases 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 206010014561 Emphysema Diseases 0.000 description 1
- 208000019693 Lung disease Diseases 0.000 description 1
- 208000002151 Pleural effusion Diseases 0.000 description 1
- 206010051986 Pneumatosis Diseases 0.000 description 1
- 230000037444 atrophy Effects 0.000 description 1
- 210000000621 bronchi Anatomy 0.000 description 1
- 206010006451 bronchitis Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 208000007451 chronic bronchitis Diseases 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003325 follicular Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 210000001370 mediastinum Anatomy 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 208000008128 pulmonary tuberculosis Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The recognition methods of pneumothorax x-ray image and system that the invention discloses a kind of based on deep learning, this programme trains a deep neural network by the sample largely manually marked, the depth nerve net identifies pneumothorax x-ray image by the image feature of study to pneumothorax with this.Thus the pneumothorax x-ray image identifying schemes constituted can realize the automatic identification to rabat, and recognition efficiency is high, and accuracy of identification is high, the phenomenon for effectively avoiding missing inspection unidentified, effectively solve the problems of prior art.
Description
Technical field
The present invention relates to image recognition technologys, and in particular to x-ray image identification technology.
Background technology
Pneumothorax refers to that gas enters pleural cavity, causes pneumatosis state, referred to as pneumothorax.Mostly because pulmonary disease or external force influence make
Lung tissue and visceral pleura rupture, or the subtle wind-puff follicular rupture close to lung surface, and air escapes into pleural cavity in lung and bronchus.
It is more common in male person between twenty and fifty or suffers with chronic bronchitis, pulmonary emphysema, pulmonary tuberculosis person.One of this Bing Shu lungs section acute disease, severe patient
Can threat to life, timely processing can cure.
X-ray inspection is to diagnose the important method of pneumothorax, and the X pieces of rabat, that is, chest are the inspections for being most commonly applied to diagnosis pneumothorax
Method.There is specific pneumothorax line mostly referring to Fig. 1, on pneumothorax rabat, is atrophy lung tissue and pleura intracavity gas boundary line, is in
Evagination lines shadow, pneumothorax line are outside the transparent area of no lung marking, are the lung tissue of compression in line；Visible mediastinum when a large amount of pneumothoraxs,
Heart is shifted to strong side；Merge visible gas-liquid face when pleural effusion.
However the identification of existing rabat, it is substantially by pure artificial diagosis, this is not only of high cost, efficiency is low, time-consuming；
And since pneumothorax lesion is that low brightness area sometimes can be ignored in manual identified diagosis, accuracy of identification is not high；Together
When manually carry out diagosis when, there is also fail to pinpoint a disease in diagnosis.
It can be seen that existing identify rabat generally existing inefficiency, the not high problem of precision based on artificial, therefore provide
The technical issues of a kind of efficient and high-precision pneumothorax rabat identification technology is this field urgent need to resolve.
Invention content
For the problems of existing pneumothorax rabat identification technology, a kind of efficient and high-precision pneumothorax rabat is needed to know
Other scheme.
For this purpose, technical problem to be solved by the invention is to provide a kind of, the pneumothorax x-ray image based on deep learning identifies
Method and system.
In order to solve the above technical problem, the present invention provides the pneumothorax x-ray image recognition methods based on deep learning, lead to
A large amount of samples manually marked are crossed to train a deep neural network, the image that the depth nerve net passes through study to pneumothorax
Feature, and pneumothorax x-ray image is identified with this.
Further, the sample includes the positive sample comprising pneumothorax patient's rabat and other people rabat samples, is being marked
Shi Shouxian filters out candidate samples from historical sample data, then is audited to candidate samples.
Further, deep neural network is formed using stochastic gradient descent model training, and accelerates training using GPU.
Further, the deep neural network includes 5 convolutional layers being alternately present, ReLU layers and pond layer and 2
A full articulamentum.
Further, the deep neural network carries out the image spy of autonomous learning pneumothorax by error back propagation model
Sign.
Further, the deep neural network identifies the image feature of pneumothorax in x-ray image using multithreading service.
Solution above-mentioned technical problem, the pneumothorax x-ray image identifying system provided by the invention based on deep learning, packet
It includes：
Sample database stores the samples largely manually marked in the sample database；
Neural metwork training module, the neural metwork training module obtain the sample by mark from sample database, and
It is trained to form deep neural network, deep learning pneumothorax image feature；
Identification module, the identification module call deep neural network to carry out pneumothorax image feature identification to rabat.
Further, in the identifying system further include rabat acquisition module, the rabat acquisition module and identification module
Rabat to be identified is reached identification module by data connection.
Further, in the identifying system further include an output module, the output module and identification module data company
It connects, exports the recognition result of identification module.
Thus the pneumothorax x-ray image identifying schemes constituted can realize the automatic identification to rabat, and recognition efficiency is high, know
Other precision is high, the phenomenon for effectively avoiding missing inspection unidentified, effectively solves the problems of prior art.
On this basis, this programme forms deep neural network by training, by the image feature of deep learning pneumothorax,
It can be accurately identified the image feature of pneumothorax in rabat, greatly improve accuracy of identification.
Description of the drawings
It is further illustrated the present invention below in conjunction with the drawings and specific embodiments.
Fig. 1 is the exemplary plot of pneumothorax rabat；
Fig. 2 is neural network structure schematic diagram in present example；
Fig. 3 is that when being identified for pneumothorax rabat in present example, the example of visual analyzing is carried out to neuron
Figure；
Fig. 4 is the pneumothorax x-ray image identifying system composition schematic diagram based on deep learning in present example.
Specific implementation mode
In order to make the technical means, the creative features, the aims and the efficiencies achieved by the present invention be easy to understand, tie below
Conjunction is specifically illustrating, and the present invention is further explained.
For the identification of pneumothorax rabat, this example approach carries out automatic identification, improves efficiency and effectively missing inspection is avoided not know
Other phenomenon；Deep learning method, autonomous learning pneumothorax image feature is used to realize and accurately identify have with this on this basis
Effect improves accuracy of identification.
Specifically, this programme trains a deep neural network by the sample largely manually marked, can independently learn
The image feature of pneumothorax is practised, thus identifies pneumothorax x-ray image.
Great amount of samples used herein includes the sample of the positive sample and other people rabats of pneumothorax patient's rabat, each sample
All it is labelled with the classification of image.
In this programme when carrying out sample mark, using the mode of man-computer cooperation, i.e., sieved from historical sample data first
Candidate pneumothorax sample is selected, then candidate samples are audited by doctor, to be confirmed whether it is pneumothorax, to greatly improve mark
Efficiency.
The sample so marked to form a deep neural network using stochastic gradient descent model (SGD) to train, together
When in the training process also utilize GPU accelerate training process.
Referring to Fig. 2 which shows the structural schematic diagram of deep neural network in this example.
As seen from the figure, deep neural network is formed more than 7 layers in this example, including 5 convolutional layers being alternately present, ReLU
Layer and pond layer and 2 full articulamentums.
Wherein, convolutional layer is to image (different data window data) and filtering matrix (one group of fixed weight：Due to
The weight of each neuron is fixed, so as to the Filter constant as one) doing inner product, (element multiplication is again one by one
Summation) operation, different Filters can obtain different output datas, such as edge and profile.
The ReLU layers of operation for taking absolute value to the handling result of convolutional layer makes it have the nonlinear spy of network
Sign.
Pond layer, for taking region average or maximum ReLU layers of handling result.
Thus the deep neural network of the layered structure constituted, each layer can be formed by training to respective image spy
The identification function of sign, and layer more rearward can more form more abstract and global feature recognition function.I.e. shallower layer can
Study is simply and the characteristics of image (edges in such as various directions) of part, deeper layer can then acquire more abstract and global spy
Sign.
Deep neural network in this example is specifically based on the shadow that error back propagation (BP) algorithm carrys out autonomous learning pneumothorax
As feature.
When the deep neural network carries out autonomous learning training, by from the direction for being input to output when calculating error output
It carries out, and adjusts weights and threshold value and then carried out from the direction for being output to input.When forward-propagating, input signal is made by hidden layer
It generates output signal by nonlinear transformation for output node and is transferred to mistake if reality output is not consistent with desired output
The back-propagation process of difference.Error-duration model is by hidden layer by output error to input layer successively anti-pass, and by error distribution
Give each layer all units, using from the error signal that each layer obtains as the foundation of adjustment each unit weights.
By adjusting input node and hidden node linking intensity and hidden node and output node linking intensity with
And threshold value, so that error is declined along gradient direction, trained by repetition learning, determines network parameter corresponding with minimal error
(weights and threshold value), training stop stopping.
Trained neural network can voluntarily handle output error minimum to the input information of similar sample at this time
By the information of non-linear conversion.
Accordingly, the deep neural network in this example identifies pneumothorax in x-ray image using high performance multithreading service
Image feature.
Referring to Fig. 3 which shows the deep neural network model provided in this example approach analyzes pneumothorax rabat
The exemplary plot of identification.
As seen from the figure, the visual analyzing by being carried out to a neuron in model, it is seen that it is to where pneumothorax line
Region is more sensitive, has very high accuracy of identification.
For the pneumothorax x-ray image identifying schemes based on deep learning that this example provides, may be used
The alternative solutions such as GoogLeNet, ResNet.
For the above-mentioned pneumothorax x-ray image identifying schemes based on deep learning, this example furthermore provides achievable
The identifying system of the pneumothorax x-ray image identifying schemes based on deep learning.
Referring to Fig. 4, it includes sample database 110, nerve to be somebody's turn to do the pneumothorax x-ray image identifying system 100 based on deep learning mainly
Network training module 120, identification module 130, rabat acquisition module 140 and output module 150.
Wherein, sample database 110, the sample largely manually marked for storing storage, for neural metwork training module 120
Training uses.As needed, the sample in sample database 100 can be according to being adjusted under actual conditions.
Neural metwork training module 120 obtains the sample by mark with 110 data connection of sample database from sample database
This, and is trained and to form deep neural network, the deep neural network can autonomous learning to pneumothorax image feature.
Identification module 130, respectively with neural metwork training module 120, rabat acquisition module 140 and output module
150 data connections.The identification module 130 receives the rabat to be identified sent in rabat acquisition module 140, calls depth nerve net
Network carries out pneumothorax image feature identification to rabat, and recognition result is reached output module 150.
Rabat acquisition module 140 is obtained with identification module and rabat capture apparatus data connection from rabat capture apparatus
Rabat to be identified is taken, and sends it to identification module.
Output module 150, with identification module data connection, the recognition result for exporting identification module.
Thus the pneumothorax x-ray image identifying system 100 based on deep learning constituted is before operation, by neural metwork training
Module 120 obtains the sample by mark from sample database 100, and is trained the image spy to be formed and be capable of autonomous learning to pneumothorax
The deep neural network model of sign.
When system operation, rabat to be identified is got by rabat acquisition module 140, and send it to identification module
130；
Identification module 130 will call deep neural network to carry out pneumothorax to rabat after the rabat to be identified got
Image feature identifies that pneumothorax image feature of the deep neural network based on autonomous learning carries out pneumothorax shadow to rabat to be identified
As feature recognition, and recognition result is reached into output module 150；
Output module 150, get identification module 130 transmission identification structure, will externally export, as picture realize,
Text importing, sound report etc..
Accordingly, the case where this system can help doctor effectively to avoid failing to pinpoint a disease in diagnosis in practical application, and effectively improve work.
In practical application, this system can be embedded in PACS system, when called upon, system, which can return to input picture, the general of pneumothorax
Rate；When probability is more than some threshold value, doctor can be reminded, further to be checked.
For example, this system is for the check to artificial diagosis result, to avoid failing to pinpoint a disease in diagnosis, implementation process is as follows.
Radiologist obtains rabat and carries out artificial diagosis, report；Report enters system, does not mention pneumothorax in report；
If this system identifies pneumothorax image feature for the rabat, doctor's diagosis again is prompted；Finally, doctor is as having found to truly have gas
Chest then changes report；Thus it can effectively avoid the case where failing to pinpoint a disease in diagnosis.
Furthermore this system directly carries out rabat identification, ensure that accuracy of identification and efficiency, implementation process are as follows.
System obtains and identifies rabat, if identifying pneumothorax image feature, is prompted on the corresponding image of rabat,
And Auto-writing partial report；The prompt that system provides is seen when doctor's diagosis, can quickly find lesion；Finally by doctor to certainly
The dynamic report generated is modified or is audited.
From the foregoing, it will be observed that this example approach can greatly improve accuracy of identification by the automatic study pneumothorax image feature of training
And recognition efficiency.Relevant experiment has been carried out for this programme, in testing the pneumothorax of the 439 of certain Grade A hospital rabat,
The AUC of this programme has reached 0.975, and accuracy of identification is high, and there are high promotion and application to be worth.
It is last it may be noted that said program, be pure software framework, tangible media can be laid in through program code, such as
Hard disk, floppy disk, disc or any machine-readable (such as smartphone, computer-readable) store media, work as machine
Loading procedure code and execution, if smartphone loads and executes, machine becomes to carry out the device of this programme.
Furthermore said program also can be with form of program codes through some transmission media, such as cable, optical fiber or any
Transmission kenel is transmitted, and when program code is received, loads and executed by machine, such as smartphone, machine becomes to reality
The device of row said program.
The basic principles, main features and advantages of the present invention have been shown and described above.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (9)
1. a kind of pneumothorax x-ray image recognition methods based on deep learning, which is characterized in that pass through the sample largely manually marked
Deep neural network is formed to train, the depth nerve net identifies gas by the image feature of study to pneumothorax with this
Chest x-ray image.
2. pneumothorax x-ray image recognition methods according to claim 1, which is characterized in that the sample includes comprising pneumothorax
The positive sample of patient's rabat and other people rabat samples, candidate samples are filtered out in mark from historical sample data first,
Candidate samples are audited again.
3. pneumothorax x-ray image recognition methods according to claim 1, which is characterized in that use stochastic gradient descent model
Training forms deep neural network, and accelerates training using GPU.
4. pneumothorax x-ray image recognition methods according to claim 1, which is characterized in that the deep neural network includes 5
A convolutional layer being alternately present, ReLU layers and pond layer and 2 full articulamentums.
5. pneumothorax x-ray image recognition methods according to claim 1, which is characterized in that the deep neural network passes through
Error back propagation model carries out the image feature of autonomous learning pneumothorax.
6. pneumothorax x-ray image recognition methods according to claim 1, which is characterized in that the deep neural network uses
Multithreading service identifies the image feature of pneumothorax in x-ray image.
7. a kind of pneumothorax x-ray image identifying system based on deep learning, which is characterized in that the system comprises：
Sample database stores the samples largely manually marked in the sample database；
Neural metwork training module, the neural metwork training module obtains the sample by mark from sample database, and carries out
Training forms deep neural network, deep learning pneumothorax image feature；
Identification module, the identification module call deep neural network to carry out pneumothorax image feature identification to rabat.
8. pneumothorax x-ray image identifying system according to claim 7, which is characterized in that further include in the identifying system
Rabat acquisition module, the rabat acquisition module and identification module data connection, identification module is reached by rabat to be identified.
9. pneumothorax x-ray image identifying system according to claim 7, which is characterized in that further include in the identifying system
One output module, the output module and identification module data connection, export the recognition result of identification module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710620039.7A CN108596198A (en) | 2017-07-26 | 2017-07-26 | A kind of recognition methods of pneumothorax x-ray image and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710620039.7A CN108596198A (en) | 2017-07-26 | 2017-07-26 | A kind of recognition methods of pneumothorax x-ray image and system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108596198A true CN108596198A (en) | 2018-09-28 |
Family
ID=63632934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710620039.7A Pending CN108596198A (en) | 2017-07-26 | 2017-07-26 | A kind of recognition methods of pneumothorax x-ray image and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596198A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109741823A (en) * | 2018-11-23 | 2019-05-10 | 杭州电子科技大学 | A deep learning-based auxiliary diagnosis method for pneumothorax |
| CN109859168A (en) * | 2018-12-28 | 2019-06-07 | 上海联影智能医疗科技有限公司 | A kind of X-ray rabat picture quality determines method and device |
| CN111950584A (en) * | 2020-06-16 | 2020-11-17 | 江西中科九峰智慧医疗科技有限公司 | An intelligent identification method and system for the integrity of parts in an X-ray chest film |
| CN112259197A (en) * | 2020-10-14 | 2021-01-22 | 北京赛迈特锐医疗科技有限公司 | Intelligent analysis system and method for acute abdomen plain film |
| US11436720B2 (en) | 2018-12-28 | 2022-09-06 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for generating image metric |
| US11727559B2 (en) | 2020-07-01 | 2023-08-15 | Merative Us L.P. | Pneumothorax detection |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001026026A2 (en) * | 1999-10-04 | 2001-04-12 | University Of Florida | Local diagnostic and remote learning neural networks for medical diagnosis |
| CN105160361A (en) * | 2015-09-30 | 2015-12-16 | 东软集团股份有限公司 | Image identification method and apparatus |
| CN105574871A (en) * | 2015-12-16 | 2016-05-11 | 深圳市智影医疗科技有限公司 | Segmentation and classification method and system for detecting lung locality lesion in radiation image |
| CN106780460A (en) * | 2016-12-13 | 2017-05-31 | 杭州健培科技有限公司 | A kind of Lung neoplasm automatic checkout system for chest CT image |
-
2017
- 2017-07-26 CN CN201710620039.7A patent/CN108596198A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001026026A2 (en) * | 1999-10-04 | 2001-04-12 | University Of Florida | Local diagnostic and remote learning neural networks for medical diagnosis |
| CN105160361A (en) * | 2015-09-30 | 2015-12-16 | 东软集团股份有限公司 | Image identification method and apparatus |
| CN105574871A (en) * | 2015-12-16 | 2016-05-11 | 深圳市智影医疗科技有限公司 | Segmentation and classification method and system for detecting lung locality lesion in radiation image |
| CN106780460A (en) * | 2016-12-13 | 2017-05-31 | 杭州健培科技有限公司 | A kind of Lung neoplasm automatic checkout system for chest CT image |
Non-Patent Citations (2)
| Title |
|---|
| 胡宝民等: "《河北省区域创新系统研究》", 28 February 2006, 河北科学技术出版社 * |
| 邓力，俞栋著；谢磊译: "《深度学习方法及应用》", 31 December 2015, 机械工业出版社 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109741823A (en) * | 2018-11-23 | 2019-05-10 | 杭州电子科技大学 | A deep learning-based auxiliary diagnosis method for pneumothorax |
| CN109859168A (en) * | 2018-12-28 | 2019-06-07 | 上海联影智能医疗科技有限公司 | A kind of X-ray rabat picture quality determines method and device |
| US11436720B2 (en) | 2018-12-28 | 2022-09-06 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for generating image metric |
| CN111950584A (en) * | 2020-06-16 | 2020-11-17 | 江西中科九峰智慧医疗科技有限公司 | An intelligent identification method and system for the integrity of parts in an X-ray chest film |
| CN111950584B (en) * | 2020-06-16 | 2024-05-14 | 江西中科九峰智慧医疗科技有限公司 | An intelligent identification method and system for part integrity in chest X-rays |
| US11727559B2 (en) | 2020-07-01 | 2023-08-15 | Merative Us L.P. | Pneumothorax detection |
| CN112259197A (en) * | 2020-10-14 | 2021-01-22 | 北京赛迈特锐医疗科技有限公司 | Intelligent analysis system and method for acute abdomen plain film |
| CN112259197B (en) * | 2020-10-14 | 2025-02-18 | 北京赛迈特锐医疗科技有限公司 | Intelligent analysis system and method for abdominal plain film of acute abdomen |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596198A (en) | A kind of recognition methods of pneumothorax x-ray image and system based on deep learning | |
| CN105678332B (en) | Converter steelmaking end point judgment method and system based on flame image CNN recognition modeling | |
| CN110378232B (en) | Improved test room examinee position rapid detection method of SSD dual-network | |
| CN110175993A (en) | A kind of Faster R-CNN pulmonary tuberculosis sign detection system and method based on FPN | |
| CN107730484A (en) | A kind of abnormal rabat intelligent identification Method and system based on deep learning | |
| CN115457006B (en) | Unmanned aerial vehicle inspection defect classification method and device based on similarity consistency self-distillation | |
| CN107368671A (en) | System and method are supported in benign gastritis pathological diagnosis based on big data deep learning | |
| CN111402209A (en) | U-Net-based high-speed railway steel rail damage detection method | |
| CN111627014B (en) | Root canal detection and scoring method and system based on deep learning | |
| CN110992349A (en) | Underground pipeline abnormity automatic positioning and identification method based on deep learning | |
| CN109830284A (en) | The analysis method and device of medical image | |
| CN109528230B (en) | Method and device for segmenting breast tumor based on multistage transformation network | |
| CN107633261A (en) | A kind of fire architecture drawing intelligent checks system and method based on artificial intelligence | |
| CN107729911A (en) | A kind of pulmonary tuberculosis intelligent identification Method and system based on DR | |
| CN109508741A (en) | Method based on deep learning screening training set | |
| CN111598868B (en) | Lung ultrasonic image identification method and system | |
| CN107578405A (en) | A kind of pulmonary nodule automatic testing method based on depth convolutional neural networks | |
| CN114119505B (en) | A method and device for detecting defects in chip adhesion area | |
| CN112581450A (en) | Pollen detection method based on expansion convolution pyramid and multi-scale pyramid | |
| CN114066804A (en) | Curved surface fault layer tooth position identification method based on deep learning | |
| CN114387261A (en) | An automatic detection method for bolt diseases of railway steel bridges | |
| CN108596868A (en) | Lung neoplasm recognition methods and system in a kind of chest DR based on deep learning | |
| CN111259844B (en) | Real-time monitoring method for examinees in standardized examination room | |
| CN115345858A (en) | Method, system and terminal device for evaluating quality of echocardiogram | |
| CN113205052A (en) | Spore identification method, system and medium based on residual error deep network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180928 |