CN106971198A - A kind of pneumoconiosis grade decision method and system based on deep learning - Google Patents
A kind of pneumoconiosis grade decision method and system based on deep learning Download PDFInfo
- Publication number
- CN106971198A CN106971198A CN201710123839.8A CN201710123839A CN106971198A CN 106971198 A CN106971198 A CN 106971198A CN 201710123839 A CN201710123839 A CN 201710123839A CN 106971198 A CN106971198 A CN 106971198A
- Authority
- CN
- China
- Prior art keywords
- pneumoconiosis
- grade
- neural network
- convolutional neural
- training
- 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
- 206010035653 pneumoconiosis Diseases 0.000 title claims abstract description 110
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000013135 deep learning Methods 0.000 title abstract description 28
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims description 35
- 238000005070 sampling Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 210000004072 lung Anatomy 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 5
- 238000013136 deep learning model Methods 0.000 claims description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 230000035945 sensitivity Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 239000000428 dust Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013526 transfer learning Methods 0.000 description 2
- 208000035939 Alveolitis allergic Diseases 0.000 description 1
- 229920000742 Cotton Polymers 0.000 description 1
- 208000027445 Farmer Lung Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 208000022195 farmer lung disease Diseases 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 208000005069 pulmonary fibrosis Diseases 0.000 description 1
- 238000009394 selective breeding Methods 0.000 description 1
- 230000009885 systemic effect 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
- G06F18/24—Classification techniques
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of pneumoconiosis grade decision method based on deep learning, methods described is classified and image enhaucament pretreatment to the medical image of Chest Radiograph in Pneumoconiosis, classification judgement is carried out to large batch of pneumoconiosis by the deep learning method of convolutional neural networks afterwards, it is final that the judgement treated and judge pneumoconiosis medical image is realized using obtained pneumoconiosis grade judgment models.The present invention has the beneficial effect that can quickly, accurately, efficiently carry out pneumoconiosis grade judgement.
Description
Technical Field
The invention relates to the technical field of information analysis, in particular to a pneumoconiosis grade judgment method based on deep learning.
Background
The canonical name of pneumoconiosis is pneumoconiosis, a systemic disease mainly characterized by diffuse fibrosis of lung tissue due to the prolonged inhalation of productive dust during professional activities and within the lung. Pneumoconiosis is classified into inorganic pneumoconiosis and organic pneumoconiosis according to the type of inhaled dust. The pneumoconiosis caused by the inhalation of inorganic dust in the production work is called inorganic pneumoconiosis. The majority of pneumoconiosis is inorganic pneumoconiosis. The pneumoconiosis caused by inhalation of organic dust is called organic pneumoconiosis, such as cotton pneumoconiosis, farmer's lung, etc.
At present, the examination process of the pneumoconiosis is complex and the population of the patients is huge, so that the relevant government, enterprise and medical institution costs a great amount of manpower, material resources and financial resources for the workers to perform the pneumoconiosis examination. Therefore, more and more scientific researches are focused on researching and using an artificial intelligence algorithm and a computer to assist doctors in solving the problem of accurate judgment of the pneumoconiosis grade. The determination of the pneumoconiosis grade is mostly based on an X-ray image shot by DR equipment, but because the shadow density in the X-ray image is uneven, a feature dictionary cannot be well expressed by using the traditional method based on texture or shape features, and finally the pneumoconiosis grade cannot be rapidly and accurately determined.
In recent years, with the development of computer hardware technology, deep learning has attracted more and more attention and attention. In the coming of big data era, more and more accurate medical projects urgently need deep learning to replace old semantic feature recognition methods and solve various medical image recognition and diagnosis problems. Under the push of the future internet, the medical industry data will show explosive trends.
In the prior art, a method based on a gray level co-occurrence matrix is provided in the application of a computer application and a software periodical to the judgment of the pneumoconiosis shadow density, so that four characteristic values are generated, the texture characteristics of the pneumoconiosis chest radiograph are effectively described, and the pneumoconiosis chest radiograph is classified through a BP (back propagation) neural network, so that the pneumoconiosis disease is effectively judged.
Although the technical solutions described in the above prior art solve the determination of pneumoconiosis grade to some extent, they have certain technical drawbacks: 1. the sample size of the pneumoconiosis medical image is small, which is not beneficial to accurately judging the effectiveness of the method; 2. the utilized feature method is single, and incompleteness of manually selecting features cannot be avoided.
Disclosure of Invention
In order to overcome the above problems or at least partially solve the above problems, the present invention provides a method and a system for determining a pneumoconiosis grade based on deep learning, which perform image enhancement preprocessing on pneumoconiosis medical images, and then perform a grade determination on a large number of pneumoconiosis by a deep learning method using a convolutional neural network.
According to one aspect of the present invention, there is provided a method for determining a pneumoconiosis level based on deep learning, comprising:
step 1, training by utilizing a convolutional neural network model based on a grade classification sample of a pneumoconiosis medical image to obtain a pneumoconiosis grade judgment model;
and 2, taking the medical image of the pneumoconiosis to be judged as input, and judging by using the pneumoconiosis grade judgment model to obtain the grade of the pneumoconiosis to be judged.
The method classifies and image-enhances the medical images of pneumoconiosis chest radiographs, then classifies and judges a large batch of pneumoconiosis through a deep learning method of a convolutional neural network, and finally judges the medical images of the pneumoconiosis to be judged by using the obtained pneumoconiosis grade judgment model. The invention has the beneficial effect of quickly, accurately and efficiently judging the grade of the pneumoconiosis.
Drawings
Fig. 1 is a schematic overall flowchart of a pneumoconiosis grade determination method based on deep learning according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Different from the general technical scheme of machine learning of big data based on semantic features and the like, the invention applies the latest deep learning technology and combines medical image big data to diagnose the pneumoconiosis and promote the construction of precise medical treatment.
The research carries out artificial intelligent diagnosis on lung medical images (such as X-ray pictures and the like) of patients with the pneumoconiosis by a method of a convolutional neural network deep learning model.
Fig. 1 shows a method for determining pneumoconiosis grade based on deep learning according to an embodiment of the present invention. In general, the method comprises the following steps: step 1, training by utilizing a convolutional neural network model based on a grade classification sample of a pneumoconiosis medical image to obtain a pneumoconiosis grade judgment model; and 2, taking the medical image of the pneumoconiosis to be judged as input, and judging by using the pneumoconiosis grade judgment model to obtain the grade of the pneumoconiosis to be judged.
In another embodiment of the present invention, a method for determining a pneumoconiosis grade based on deep learning further includes, before step 1: step 0, carrying out gray level conversion and image enhancement processing on the classified samples of the levels of the pneumoconiosis medical images; and converting the processed pneumoconiosis medical image into a matrix form and storing the matrix form. In the embodiment, the gray level transformation and the image enhancement processing are carried out on the image, so that the outline of the skeleton and the lung lobe area of the pneumoconiosis chest film in the diseased medical image is more obvious and clearer, and the subsequent characteristic acquisition is facilitated; the downsampling processing of the embodiment converts the image information into the convolutional neural network model which can be directly used as a matrix form of training input, so that the convolutional neural network can be read quickly.
In another embodiment of the present invention, a method for determining a pneumoconiosis grade based on deep learning further includes, before step 0: the pneumoconiosis medical images are classified according to the pneumoconiosis disease grade. In this embodiment, a large number of medical images of a diseased lung may be classified according to the pneumoconiosis level.
In another embodiment of the present invention, a method for determining a pneumoconiosis grade based on deep learning, the classification criteria for classifying pneumoconiosis medical images according to pneumoconiosis grade is determined as the criteria for diagnosing new GBZ 70-2015 occupational pneumoconiosis, where the category of diseases is classified into 3 categories, which are: first stage, second stage and third stage.
In another embodiment of the present invention, a method for determining a pneumoconiosis grade based on deep learning, wherein the step 1 further comprises: setting a convolution neural network, setting a learning rate and the size of an input medical image.
In another embodiment of the present invention, a method for determining a pneumoconiosis grade based on deep learning, wherein the step 1 further comprises: storing parameters of the convolutional neural network model in a parameter server; the process of training by utilizing the convolutional neural network model is carried out in a training server; and correspondingly modifying the parameters of the convolutional neural network model in the parameter server based on the gradient obtained in the training by the training server. Storing parameters of the convolutional neural network model in a parameter server; the process of training by utilizing the convolutional neural network model is carried out in a training server; the training task adopts distributed parallel computation, and the training speed and the stability can be greatly improved even if the data volume is overlarge.
In another embodiment of the present invention, a method for determining a pneumoconiosis grade based on deep learning, wherein the step 1 further comprises: training a convolutional neural network model by using a 10-fold intersection method; drawing an ROC curve graph based on the sensitivity and the specificity of the algorithm; and selecting the model corresponding to the maximum ROC curve area as the pneumoconiosis grade judgment model.
In another embodiment of the present invention, a method for determining a pneumoconiosis grade based on deep learning, wherein the step 0 further comprises:
s01, performing gray level transformation and image enhancement processing on the classified samples of the pneumoconiosis medical images by using a Gaussian pyramid method;
s02, performing down-sampling processing on the processed pneumoconiosis medical image;
and S03, converting the processed pneumoconiosis medical image into a matrix form and storing the matrix form according to the pneumoconiosis grade.
The gaussian pyramid (english) mentioned in the above embodiments of the present invention is a technique used in image processing, computer vision, and signal processing. The gaussian pyramid is essentially a multi-scale representation of the signal, i.e., the same signal or picture is gaussian blurred multiple times and down-sampled to generate multiple sets of signals or pictures at different scales for subsequent processing, e.g., in image recognition, the comparison of pictures at different scales can be used to prevent the contents to be searched from having different sizes on the pictures. The theoretical basis of the Gaussian pyramid is the scale space theory, and multi-resolution analysis is derived subsequently.
The down-sampling mentioned in the above embodiments of the present invention is a process of reducing the sampling rate of a specific signal, and is generally used to reduce the data transmission rate or the data size. Down-sampling is a process of reducing the sampling rate of a particular signal, typically used to reduce the data transmission rate or data size. The down-sampling factor (often denoted by the symbol M) is typically an integer or rational number greater than 1. This factor expresses that the sampling period becomes several times larger than before, or equivalently that the sampling rate becomes a fraction of before. Since down-sampling reduces the sampling rate, it is necessary to ensure that the nyquist sampling theorem still holds at the new lower sampling rate.
In another embodiment of the present invention, a pneumoconiosis grade determination method based on deep learning includes: the ResNet deep learning model and the inclusion deep learning model. The present invention is not limited to the use of the neural network model described above.
In another embodiment of the present invention, in a deep learning-based pneumoconiosis grade determination method, the activation function of the convolutional neural network model is a ReLu function.
In another embodiment of the present invention, a deep learning-based pneumoconiosis grade determination method, the activation function ReLu function formula is as follows: f (x) max (0, x)
The formula can also be adjusted as follows:
wherein x is an input value, and a dropout layer is added to the convolutional neural network, so that overfitting can be effectively prevented. In the training process, transfer learning is carried out on the basis of the training model of the ImageNet set, and the convergence rate of the convolutional neural network is effectively improved.
In another embodiment of the present invention, a method for determining a pneumoconiosis grade based on deep learning, wherein the training of the convolutional neural network model to obtain a pneumoconiosis grade determination model further comprises:
the convolutional neural network comprises four layers, which are respectively: an input layer, a convolution layer, a down-sampling layer and an output layer;
the input layer is used for processing the preprocessed pneumoconiosis medical image, and three channels are set to be 1;
the convolutional layers are characteristic extraction layers of CNNs, one convolutional layer is only used for extracting the characteristics in the previous layer, is convoluted by a learnable convolution kernel, and then the output characteristics can be obtained through an activation function, wherein the characteristics are as follows:
wherein,representing a set of a plurality of input feature matrixes corresponding to the jth output feature matrix of the ith layer of the lung chest film input, whereinBias terms representing various feature matrices input in M,representing a convolution kernel;
the down-sampling layer: selecting a maximum pool downsampling method by a downsampling method;
the output layer: and finally, extracting the last layer of the convolutional neural network, and putting the last layer into a classifier for classification, wherein the classifier is softmax.
In another embodiment of the present invention, a method for determining a pneumoconiosis grade based on deep learning, the training of the convolutional neural network model by using a 10-fold intersection method further includes: training a convolutional neural network model by using a 10-fold intersection method, wherein the proportion of a training set, a verification set and a test set is 8: 1: 1, the number of image samples per grade of pneumoconiosis is equal.
In another embodiment of the present invention, a method for determining a pneumoconiosis grade based on deep learning comprises the following steps:
data collection and pneumoconiosis chest radiograph preprocessing: firstly, carrying out labeling judgment on a chest film with large data volume; carrying out gray level transformation and image enhancement processing on the pneumoconiosis chest film by a Gaussian pyramid method, so that the outlines of the skeleton and the lung lobe area of the pneumoconiosis chest film are more obvious and clearer; then, 256 × 256 down-sampling is performed on the chest slices, and the chest slices are stored as a normal, first-stage, second-stage and third-stage matrix in an lmdb or protobuf database, so that the reading speed can be conveniently provided.
Detailed design of a model: designing a convolution neural network, and adjusting parameters such as learning rate and image input size. In consideration of the high efficiency of the algorithm and the stability of the precision, the image is not too large or too small. The method adopts ResNet and increment for training, the learning rate of a training model is set to be 0.0001, an activation function is selected to be ReLu, and the formula is as follows:
f(x)＝max(0,x)
the formula can also be adjusted as follows:
wherein x is an input value, and a dropout layer is added to the convolutional neural network, so that overfitting can be effectively prevented. In the training process, transfer learning is carried out on the basis of the training model of the ImageNet set, and the convergence rate of the convolutional neural network is effectively improved.
The method distributes a plurality of tasks on different machines which are provided with GPUs for distributed parallel computing. These machines are classified into two types, one being Parameter servers (ps) for storing computation model parameters and the other for computing the gradient of the loss equation. And returning the calculated gradient to the parameter server, and updating the corresponding model parameter.
Selecting a proper model based on the ROC curve: training is carried out through a 10-fold intersection method, and the proportion of a training set, a verification set and a test set is 8: 1: 1, a test is performed in which the number of images for each level of pneumoconiosis must be equalized. And according to the sensitivity and specificity of the algorithm, the ROC graph is displayed. And after the verification by a 10-fold cross method, selecting a model corresponding to the largest ROC curve area as a stage interpretation model of the pneumoconiosis of the method.
The invention has the following beneficial effects: 1. by means of the deep learning method, incompleteness of artificial selection features is avoided, identification precision of the pneumoconiosis chest radiograph is improved, and interpretation of doctors is assisted. 2. By means of the image enhancement method, the network of the training image is improved, and the convergence speed is improved. 3. The speed and the stability of the algorithm are improved by a distributed parallel computing method.
Finally, the method of the present application is only a preferred embodiment and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A pneumoconiosis grade determination method, comprising:
step 1, training by utilizing a convolutional neural network model based on a grade classification sample of a pneumoconiosis medical image to obtain a pneumoconiosis grade judgment model;
and 2, taking the medical image of the pneumoconiosis to be judged as input, and judging by using the pneumoconiosis grade judgment model to obtain the grade of the pneumoconiosis to be judged.
2. The method of claim 1, wherein step 1 is preceded by:
step 0, carrying out gray level conversion and image enhancement processing on the classified samples of the levels of the pneumoconiosis medical images; and performing down-sampling processing on the processed pneumoconiosis medical image, converting the processed pneumoconiosis medical image into a matrix form and storing the matrix form.
3. The method of claim 1, wherein step 0 is preceded by: the pneumoconiosis medical images are classified according to the pneumoconiosis disease grade.
4. The method of claim 1, wherein step 1 further comprises: setting a convolution neural network, setting a learning rate and the size of an input medical image.
5. The method of claim 1, wherein step 1 further comprises: storing parameters of the convolutional neural network model in a parameter server; the process of training by utilizing the convolutional neural network model is carried out in a training server; and correspondingly modifying the parameters of the convolutional neural network model in the parameter server based on the gradient obtained in the training by the training server.
6. The method of claim 1, wherein step 1 further comprises: training a convolutional neural network model by using a 10-fold intersection method; drawing an ROC curve graph based on the sensitivity and the specificity of the algorithm; and selecting the model corresponding to the maximum ROC curve area as the pneumoconiosis grade judgment model.
7. The method of claim 2, wherein step 0 further comprises:
s01, performing gray level transformation and image enhancement processing on the classified samples of the pneumoconiosis medical images by using a Gaussian pyramid method;
s02, performing down-sampling processing on the processed pneumoconiosis medical image;
and S03, converting the processed pneumoconiosis medical image into a matrix form and storing the matrix form according to the pneumoconiosis grade.
8. The method of claim 1, wherein the convolutional neural network model is: the ResNet deep learning model and the inclusion deep learning model.
9. The method of claim 2, wherein said step of training a convolutional neural network model to obtain a pneumoconiosis grade decision model further comprises:
the convolutional neural network comprises four layers, which are respectively: an input layer, a convolution layer, a down-sampling layer and an output layer;
the input layer is used for processing the preprocessed pneumoconiosis medical image, and three channels are set to be 1;
the convolutional layers are characteristic extraction layers of CNNs, one convolutional layer is only used for extracting the characteristics in the previous layer, is convoluted by a learnable convolution kernel, and then the output characteristics can be obtained through an activation function, wherein the characteristics are as follows:
wherein,representing a set of a plurality of input feature matrixes corresponding to the jth output feature matrix of the ith layer of the lung chest film input, whereinBias terms representing various feature matrices input in M,representing a convolution kernel;
the down-sampling layer: selecting a maximum pool downsampling method by a downsampling method;
the output layer: and finally, extracting the last layer of the convolutional neural network, and putting the last layer into a classifier for classification, wherein the classifier is softmax.
10. The method of claim 6, wherein the step of training the convolutional neural network model using a 10-fold intersection method further comprises: training a convolutional neural network model by using a 10-fold intersection method, wherein the proportion of a training set, a verification set and a test set is 8: 1: 1, the number of image samples per grade of pneumoconiosis is equal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710123839.8A CN106971198A (en) | 2017-03-03 | 2017-03-03 | A kind of pneumoconiosis grade decision method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710123839.8A CN106971198A (en) | 2017-03-03 | 2017-03-03 | A kind of pneumoconiosis grade decision method and system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106971198A true CN106971198A (en) | 2017-07-21 |
Family
ID=59330127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710123839.8A Pending CN106971198A (en) | 2017-03-03 | 2017-03-03 | A kind of pneumoconiosis grade decision method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106971198A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108022647A (en) * | 2017-11-30 | 2018-05-11 | 东北大学 | The good pernicious Forecasting Methodology of Lung neoplasm based on ResNet-Inception models |
| CN108399616A (en) * | 2018-02-11 | 2018-08-14 | 西安理工大学 | Orthopaedics disease lesion classification stage division based on depth residual error network |
| CN108428229A (en) * | 2018-03-14 | 2018-08-21 | 大连理工大学 | It is a kind of that apparent and geometric properties lung's Texture Recognitions are extracted based on deep neural network |
| CN108510489A (en) * | 2018-03-30 | 2018-09-07 | 四川元匠科技有限公司 | A kind of pneumoconiosis detection method and system based on deep learning |
| CN109902818A (en) * | 2019-01-15 | 2019-06-18 | 中国科学院信息工程研究所 | A kind of distributed accelerated method and system towards deep learning training mission |
| CN110009629A (en) * | 2019-04-12 | 2019-07-12 | 北京天明创新数据科技有限公司 | A kind of pneumoconiosis screening system and its data training method |
| CN110428896A (en) * | 2019-04-22 | 2019-11-08 | 应急总医院 | Occupational pneumoconiosis assists screening model of mind |
| CN110680326A (en) * | 2019-10-11 | 2020-01-14 | 北京大学第三医院（北京大学第三临床医学院） | Pneumoconiosis identification and grading judgment method based on deep convolutional neural network |
| CN110852350A (en) * | 2019-10-21 | 2020-02-28 | 北京航空航天大学 | Pulmonary nodule benign and malignant classification method and system based on multi-scale migration learning |
| CN110889847A (en) * | 2019-12-10 | 2020-03-17 | 苏州大学 | Nuclear radiation damage assessment system and method based on infrared imaging |
| CN111275121A (en) * | 2020-01-23 | 2020-06-12 | 北京百度网讯科技有限公司 | Medical image processing method and device and electronic equipment |
| CN111524579A (en) * | 2020-04-27 | 2020-08-11 | 北京百度网讯科技有限公司 | Lung function curve detection method, device, equipment and storage medium |
| CN113255889A (en) * | 2021-05-26 | 2021-08-13 | 安徽理工大学 | Occupational pneumoconiosis multi-modal analysis method based on deep learning |
| WO2022000360A1 (en) * | 2020-07-01 | 2022-01-06 | 深圳市职业病防治院 | Method for selection, labelling, and verification of chest radiographs for artificial intelligence screening of pneumoconiosis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886318A (en) * | 2014-03-31 | 2014-06-25 | 武汉天仁影像科技有限公司 | Method for extracting and analyzing nidus areas in pneumoconiosis gross imaging |
| CN104834943A (en) * | 2015-05-25 | 2015-08-12 | 电子科技大学 | Brain tumor classification method based on deep learning |
| CN106056595A (en) * | 2015-11-30 | 2016-10-26 | 浙江德尚韵兴图像科技有限公司 | Method for automatically identifying whether thyroid nodule is benign or malignant based on deep convolutional neural network |
| CN106096616A (en) * | 2016-06-08 | 2016-11-09 | 四川大学华西医院 | Magnetic resonance image feature extraction and classification method based on deep learning |
| CN106372390A (en) * | 2016-08-25 | 2017-02-01 | 姹ゅ钩 | Deep convolutional neural network-based lung cancer preventing self-service health cloud service system |
-
2017
- 2017-03-03 CN CN201710123839.8A patent/CN106971198A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886318A (en) * | 2014-03-31 | 2014-06-25 | 武汉天仁影像科技有限公司 | Method for extracting and analyzing nidus areas in pneumoconiosis gross imaging |
| CN104834943A (en) * | 2015-05-25 | 2015-08-12 | 电子科技大学 | Brain tumor classification method based on deep learning |
| CN106056595A (en) * | 2015-11-30 | 2016-10-26 | 浙江德尚韵兴图像科技有限公司 | Method for automatically identifying whether thyroid nodule is benign or malignant based on deep convolutional neural network |
| CN106096616A (en) * | 2016-06-08 | 2016-11-09 | 四川大学华西医院 | Magnetic resonance image feature extraction and classification method based on deep learning |
| CN106372390A (en) * | 2016-08-25 | 2017-02-01 | 姹ゅ钩 | Deep convolutional neural network-based lung cancer preventing self-service health cloud service system |
Non-Patent Citations (2)
| Title |
|---|
| EIICHIRO OKUMURA 等: "Computerized Classification of Pneumoconiosis on Digital Chest Radiography Artificial Neural Network with Three Stages", 《JOURNAL OF DIGITAL IMAGING》 * |
| MARIOS ANTHIMOPOULOS 等: "Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network", 《IEEE TRANSACTIONS ON MEDICAL IMAGING》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108022647B (en) * | 2017-11-30 | 2022-01-25 | 东北大学 | Lung nodule benign and malignant prediction method based on ResNet-inclusion model |
| CN108022647A (en) * | 2017-11-30 | 2018-05-11 | 东北大学 | The good pernicious Forecasting Methodology of Lung neoplasm based on ResNet-Inception models |
| CN108399616A (en) * | 2018-02-11 | 2018-08-14 | 西安理工大学 | Orthopaedics disease lesion classification stage division based on depth residual error network |
| CN108399616B (en) * | 2018-02-11 | 2021-11-16 | 西安理工大学 | Orthopedics disease lesion classification and classification method based on depth residual error network |
| CN108428229B (en) * | 2018-03-14 | 2020-06-16 | 大连理工大学 | Lung texture recognition method based on appearance and geometric features extracted by deep neural network |
| CN108428229A (en) * | 2018-03-14 | 2018-08-21 | 大连理工大学 | It is a kind of that apparent and geometric properties lung's Texture Recognitions are extracted based on deep neural network |
| CN108510489A (en) * | 2018-03-30 | 2018-09-07 | 四川元匠科技有限公司 | A kind of pneumoconiosis detection method and system based on deep learning |
| CN108510489B (en) * | 2018-03-30 | 2021-08-03 | 四川元匠科技有限公司 | Pneumoconiosis detection method and system based on deep learning |
| CN109902818A (en) * | 2019-01-15 | 2019-06-18 | 中国科学院信息工程研究所 | A kind of distributed accelerated method and system towards deep learning training mission |
| CN109902818B (en) * | 2019-01-15 | 2021-05-25 | 中国科学院信息工程研究所 | Distributed acceleration method and system for deep learning training task |
| CN110009629A (en) * | 2019-04-12 | 2019-07-12 | 北京天明创新数据科技有限公司 | A kind of pneumoconiosis screening system and its data training method |
| CN110428896B (en) * | 2019-04-22 | 2023-09-08 | 应急总医院 | Occupational pneumoconiosis auxiliary screening intelligent model |
| CN110428896A (en) * | 2019-04-22 | 2019-11-08 | 应急总医院 | Occupational pneumoconiosis assists screening model of mind |
| CN110680326A (en) * | 2019-10-11 | 2020-01-14 | 北京大学第三医院（北京大学第三临床医学院） | Pneumoconiosis identification and grading judgment method based on deep convolutional neural network |
| CN110680326B (en) * | 2019-10-11 | 2022-05-06 | 北京大学第三医院（北京大学第三临床医学院） | Pneumoconiosis identification and grading judgment method based on deep convolutional neural network |
| CN110852350A (en) * | 2019-10-21 | 2020-02-28 | 北京航空航天大学 | Pulmonary nodule benign and malignant classification method and system based on multi-scale migration learning |
| CN110889847A (en) * | 2019-12-10 | 2020-03-17 | 苏州大学 | Nuclear radiation damage assessment system and method based on infrared imaging |
| CN111275121A (en) * | 2020-01-23 | 2020-06-12 | 北京百度网讯科技有限公司 | Medical image processing method and device and electronic equipment |
| CN111275121B (en) * | 2020-01-23 | 2023-07-18 | 北京康夫子健康技术有限公司 | Medical image processing method and device and electronic equipment |
| CN111524579B (en) * | 2020-04-27 | 2023-08-29 | 北京百度网讯科技有限公司 | Lung function curve detection method, device, equipment and storage medium |
| CN111524579A (en) * | 2020-04-27 | 2020-08-11 | 北京百度网讯科技有限公司 | Lung function curve detection method, device, equipment and storage medium |
| WO2022000360A1 (en) * | 2020-07-01 | 2022-01-06 | 深圳市职业病防治院 | Method for selection, labelling, and verification of chest radiographs for artificial intelligence screening of pneumoconiosis |
| CN113255889A (en) * | 2021-05-26 | 2021-08-13 | 安徽理工大学 | Occupational pneumoconiosis multi-modal analysis method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106971198A (en) | A kind of pneumoconiosis grade decision method and system based on deep learning | |
| Al-Haija et al. | Breast cancer diagnosis in histopathological images using ResNet-50 convolutional neural network | |
| CN108921851B (en) | Medical CT image segmentation method based on 3D countermeasure network | |
| CN109544518B (en) | Method and system applied to bone maturity assessment | |
| Carvalho et al. | Automated microfossil identification and segmentation using a deep learning approach | |
| CN112581450B (en) | Pollen detection method based on expansion convolution pyramid and multi-scale pyramid | |
| Alahmari et al. | A comprehensive review of deep learning-based methods for COVID-19 detection using chest X-ray images | |
| CN115294075A (en) | OCTA image retinal vessel segmentation method based on attention mechanism | |
| CN110443105A (en) | The immunofluorescence image kenel recognition methods of autoimmunity antibody | |
| Varghese et al. | INFOPLANT: Plant recognition using convolutional neural networks | |
| CN107133626A (en) | Medical image classification method based on partial average stochastic optimization model | |
| CN113361353A (en) | Zebrafish morphological scoring method based on DeepLabV3Plus | |
| CN116778482A (en) | Embryo image blastomere target detection method, computer equipment and storage medium | |
| Kotiyal et al. | Diabetic retinopathy binary image classification using PySpark | |
| Al-Haija et al. | Development of breast cancer detection model using transfer learning of residual neural network (resnet-50) | |
| CN114511733A (en) | Fine-grained image identification method and device based on weak supervised learning and readable medium | |
| Hamida et al. | Data balancing through data augmentation to improve transfer learning performance for skin disease prediction | |
| CN114295967A (en) | Analog circuit fault diagnosis method based on migration neural network | |
| Abdalla et al. | Transfer learning models comparison for detecting and diagnosing skin cancer | |
| Escorcia-Gutierrez et al. | Computer-aided diagnosis for tuberculosis classification with water strider optimization algorithm | |
| CN116091828A (en) | Chromosome image interpretable analysis method, device, equipment and storage medium | |
| Kapoor et al. | Lung Cancer Detection Using VGG16 and CNN | |
| Abbas et al. | Transfer learning-based computer-aided diagnosis system for predicting grades of diabetic retinopathy | |
| CN113313158A (en) | Method for calculating modal contribution degree based on multi-modal deep learning classification model | |
| Bhartiya et al. | Pneumonia detection using CNN and ANN based on deep learning approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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: 20170721 |