CN110689112A - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN110689112A CN110689112A CN201910825532.1A CN201910825532A CN110689112A CN 110689112 A CN110689112 A CN 110689112A CN 201910825532 A CN201910825532 A CN 201910825532A CN 110689112 A CN110689112 A CN 110689112A
- Authority
- CN
- China
- Prior art keywords
- image data
- data
- preset
- neural network
- deep neural
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 238000003062 neural network model Methods 0.000 claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000003745 diagnosis Methods 0.000 claims abstract description 21
- 201000010099 disease Diseases 0.000 claims abstract description 19
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 19
- 238000013135 deep learning Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 55
- 230000006870 function Effects 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 19
- 238000002591 computed tomography Methods 0.000 claims description 17
- 238000002372 labelling Methods 0.000 claims description 14
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000002595 magnetic resonance imaging Methods 0.000 claims description 10
- 230000003902 lesion Effects 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000009466 transformation Effects 0.000 description 4
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 3
- 201000005202 lung cancer Diseases 0.000 description 3
- 208000020816 lung neoplasm Diseases 0.000 description 3
- 208000024827 Alzheimer disease Diseases 0.000 description 2
- 206010056342 Pulmonary mass Diseases 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000002427 irreversible effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002685 pulmonary effect Effects 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Images
Classifications
-
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- 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
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30061—Lung
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Pathology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The application discloses a data processing method and device. The method comprises the steps of obtaining image data, wherein the image data is medical image data; carrying out uncertainty judgment on the image data based on a preset deep neural network model to obtain a judgment result; the preset deep neural network model is an end-to-end deep learning framework capable of identifying image data which can not determine a disease diagnosis result according to the image data. The method and the device solve the problem that the performance of the relevant machine learning algorithm for identifying the uncertain data is low.
Description
Technical Field
The application relates to the field of medicine, in particular to a data processing method and device.
Background
In recent years, lung cancer has become one of the most prevalent cancers with morbidity and mortality, and early diagnosis and treatment of lung cancer is particularly important to improve patient survival. But at an early stage of disease development, image-based disease prediction, due to lack of sufficient information, may have difficulty in giving certain case-specific "disease/normal" labels, and we refer to such samples as "uncertain" data. It is also common practice in clinical diagnosis to label these data as inconclusive and then recommend the patient for follow-up examination to avoid irreversible medical accidents or losses due to the lack of careful prediction. However, most of the current machine learning methods ignore "uncertain" data, and mainly model two types of sample data, namely "disease and normal", so that the "uncertain" data cannot be better identified and determined.
Disclosure of Invention
The application mainly aims to provide a data processing method and device to solve the problem that the performance of relevant machine learning algorithms for identifying uncertain data is low.
To achieve the above object, according to a first aspect of the present application, there is provided a method of data processing.
The data processing method comprises the following steps:
acquiring image data, wherein the image data is medical image data;
carrying out uncertainty judgment on the image data based on a preset deep neural network model to obtain a judgment result; the preset deep neural network model is an end-to-end deep learning framework capable of identifying image data which can not determine a disease diagnosis result according to the image data.
Further, before the image data is subjected to uncertainty judgment based on the preset deep neural network model to obtain a judgment result, the method further includes:
acquiring a training sample, wherein the training sample comprises a preset amount of sample data and corresponding sample marking data, the preset amount of sample data is medical image sample data containing a focus, the sample marking data is image data for performing type marking on the preset amount of sample data, and the type comprises determination and uncertainty;
and training a preset deep neural network algorithm based on the training sample to obtain a preset deep neural network model.
Further, training a preset deep neural network algorithm based on the training sample to obtain a preset deep neural network model further includes:
setting a loss function by combining preset cost sensitive parameters and preset strategy selection parameters, wherein the preset strategy selection parameters comprise conservative control parameters and aggressive control parameters;
and training the model based on the loss function to obtain a preset deep neural network model.
Further, the trunk network of the preset deep neural network model is a three-dimensional densely connected convolutional network 3D DenseNet.
Further, the medical image data is CT image data which is CT image data of an electronic computer tomography or MRI image data.
In order to achieve the above object, according to a second aspect of the present application, there is provided an apparatus for data processing.
The data processing device according to the application comprises:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring image data which is medical image data;
the judging unit is used for judging the uncertainty of the image data based on a preset deep neural network model to obtain a judging result; the preset deep neural network model is an end-to-end deep learning framework capable of identifying image data which can not determine a disease diagnosis result according to the image data.
Further, the apparatus further comprises:
a second obtaining unit, configured to obtain a training sample before the image data is subjected to uncertainty judgment based on the preset deep neural network model and a judgment result is obtained, where the training sample includes a preset number of sample data and sample labeling data corresponding to the sample data, the preset number of sample data is medical image sample data including a lesion, the sample labeling data is image data obtained by performing type labeling on the preset number of sample data, and the type includes certainty and uncertainty;
and the training unit is used for training a preset deep neural network algorithm based on the training sample to obtain a preset deep neural network model.
Further, the training unit comprises:
the setting module is used for setting a loss function by combining preset cost sensitive parameters and preset strategy selection parameters, wherein the preset strategy selection parameters comprise conservative control parameters and aggressive control parameters;
and the training module is used for training the model based on the loss function to obtain a preset deep neural network model.
Further, the trunk network of the preset deep neural network model is a three-dimensional densely connected convolutional network 3D DenseNet.
Further, the medical image data is CT image data which is CT image data of an electronic computer tomography or MRI image data.
To achieve the above object, according to a third aspect of the present application, there is provided a non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of data processing of any one of the above first aspects.
In the embodiment of the application, the data processing method and the data processing device can firstly acquire image data, wherein the image data is medical image data; then, the image data is judged to be uncertain based on a preset deep neural network model, and the preset deep neural network model is an end-to-end deep learning framework capable of identifying the image data of which the disease diagnosis result cannot be determined according to the image data, so that the image data of which the diagnosis result cannot be determined can be identified by using the model, namely the uncertain data can be better identified, and the problem that the existing machine algorithm cannot pay attention to and identify the uncertain data is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a flow chart of a method of data processing provided according to an embodiment of the present application;
FIG. 2 is a flow chart of another method of data processing provided in accordance with an embodiment of the present application;
FIG. 3 is a block diagram of a predetermined deep neural network according to an embodiment of the present disclosure;
FIG. 4 is a comparison result of probability values of the preset deep neural network model and other models in recognizing "uncertain" data ("type 0 samples) in the present embodiment;
FIG. 5 is a block diagram of a data processing apparatus according to an embodiment of the present application;
fig. 6 is a block diagram of another data processing apparatus according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
According to an embodiment of the present application, there is provided a data processing method, as shown in fig. 1, the method including the steps of:
s101, image data are obtained.
Wherein the image data is medical image data. The commonly used medical image data mainly includes Computed Tomography (CT) image data or Magnetic Resonance Imaging (MRI) image data. Such as CT image data of lung nodules, brain CT image data, brain MRI image data, and the like. It should be noted that, in practical applications, the medical image data directly acquired by the device is image data in a relatively large range, and in order to improve accuracy of subsequent data processing, the medical image data generally needs to be preprocessed, where the specific preprocessing is to cut the medical image data, select small-range image data including a focus, and the size of the specific cut range is determined according to practical situations, and this embodiment is not limited in this embodiment.
And S102, carrying out uncertainty judgment on the image data based on a preset deep neural network model to obtain a judgment result.
The preset deep neural network model is an end-to-end deep learning framework capable of identifying image data which can not determine a disease diagnosis result according to the image data. "the image data is subjected to uncertainty judgment based on a preset deep neural network model to obtain a judgment result", that is: and inputting the preprocessed medical image data obtained in the step S101 into a preset deep neural network model, and outputting to obtain a result of judging uncertainty of the image data. The judgment result includes that the image data is determined data or the image data is uncertain data. The determination data and the indeterminate data are defined as to whether or not a disease diagnosis can be determined from the image data. "determine" means that a disease diagnosis can be determined from the image data; "uncertain" means that the disease diagnosis cannot be determined from the image data.
The preset deep neural network model in the embodiment can judge whether the image data is 'uncertain' image data, namely, the image data of which the diagnosis result cannot be determined can be better identified. Accurate identification of the 'uncertain' image data enables patients who cannot determine the diagnosis result to be determined after further examination, thereby effectively avoiding irreversible medical accidents or loss caused by incautious prediction.
From the above description, it can be seen that, in the data processing method in the embodiment of the present application, image data can be first obtained, where the image data is medical image data; then, the image data is judged to be uncertain based on a preset deep neural network model, and the preset deep neural network model is an end-to-end deep learning framework capable of identifying the image data of which the disease diagnosis result cannot be determined according to the image data, so that the image data of which the diagnosis result cannot be determined can be identified by using the model, namely the uncertain data can be better identified, and the problem that the existing machine algorithm cannot pay attention to and identify the uncertain data is solved.
In addition to the above embodiments and refinements, the present application provides another data processing method, as shown in fig. 2, the method includes:
first, in this embodiment, the data processing method in fig. 1 is supplemented and described by taking CT image data and MRI image data, which are two most commonly used medical image data, as an example.
S201, obtaining a training sample.
The training samples are sample data for training a preset deep neural network algorithm. In this embodiment, the training samples include a preset number of sample data and corresponding sample labeling data, where the preset number of sample data is medical image sample data, and the sample labeling data is image data obtained by performing type labeling on the preset number of sample data. The types in the present embodiment include definite and indefinite, and the specific "definite" means that a disease diagnosis result can be determined from the image data; "uncertain" means that the disease diagnosis cannot be determined from the image data. In practical applications, the determination can be specifically divided into normal determination and abnormal determination. This embodiment gives a way of labeling, for example, label the sample data that is determined to be normal as "-1", label the sample data that is determined to be abnormal as "1", and label the sample data that is not determined to be normal as "0".
In practical applications, the training samples may be obtained through a public data set, for example, if the training samples are applied to the field of lung cancer, the training samples may be obtained through a LIDC-IDRI data set, and if the training samples are applied to the field of alzheimer's disease, the training samples may be obtained through an ADNI data set. In addition, it should be noted that the preset number may be customized according to actual requirements, and this embodiment is not limited.
S202, training a preset deep neural network algorithm based on the training samples to obtain a preset deep neural network model.
In the embodiment, when model training is performed, a loss function is set by combining preset cost sensitive parameters and preset strategy selection parameters; and then training the model based on the loss function to obtain a preset deep neural network model. The preset strategy selection parameters comprise a conservative control parameter and an aggressive control parameter, and the conservative and aggressive strategies are executed through the preset strategy selection parameters. In the training process, for example, for labeling of the aforementioned sample types, the samples determined to be normal should be trained by a conservative strategy (high-precision detection), and the samples determined to be abnormal should be trained by an aggressive strategy (high-recall detection).
Specifically, this embodiment provides a structure diagram of a preset deep neural network, as shown in fig. 3, a three-dimensional densely connected convolutional network 3D DenseNet is adopted as a backbone network to train a nonlinear transformation function f, where f is a function for converting input image data into an output result. The specific training process is described below with reference to fig. 3.
Suppose that the training samples are N, denoted as
Wherein xiIs the sample image, yiThe method is used for marking the sample image. We assume yi-1 denotes determination of normal samples, y i1 denotes identifying an abnormal sample, yi0 denotes an indeterminate sample. The nonlinear transformation function of the training is fw(xi) The loss function is defined as:
Loss(w，λ，ξ，γ)＝l(w，λ，ξ，γ)+ρ1max(c1-γ1，0)+ρ-1max(c-1-γ-1，0)
wherein w is a parameter of the nonlinear transformation function, λ is an offset parameter for determining normal and abnormal categories, ξ is a cost sensitive parameter, and Y and c are strategy selection parameters; g (xi)-1，1)、h(Y-1，1) Represents the corresponding arc arrows in the two axis diagrams of fig. 3Threshold of two connected line segments.
c1And c-1Is a preset policy selection parameter, c1As a conservative control parameter, c-1Is an aggressive control parameter; the second term and the third term in the above formula are used to penalize samples that do not comply with a predetermined policy. The definition of l (w, λ, ξ, γ) in the above equation is as follows:
wherein 1 is an indicator function, w is a parameter of a neural network, P1(xi) And P-1(xi) The probability value indicating that the sample is judged to be abnormal and normal is specifically defined as follows:
P1(xi)＝G(-fw(xi)+λ1+logξ1+γ1)
P-1(xi)＝G(-fw(xi)+λ-1+logξ-1-γ-1)
where G is the probability distribution density function of obedience of the assumed error, fw(xi) Is the nonlinear transformation function to be trained.
F is obtained after training based on the loss function and the 3D DenseNetw(xi)。
In addition, the performance of the preset deep neural network model is verified. The embodiment of the invention performs experiments on the public data set LIDC-IDRI data set and the ADNI data set. The results of comparing the model of this example with other models (Possion-based model, NSB-based model, Mean Squared Error (MSE) loss function-based model, and Cross inversion (CE) loss function-based) on LIDC-IDRI dataset and ADNI dataset are also presented. As shown in tables 1 and 2. The present embodiment uses precision and recall for each class to measure performance on both deterministic and non-deterministic data. Wherein the last two rows in tables 1 and 2 are the result data of this example. In addition, we introduce
TABLE 1 comparison of the model of this example with other models on LIDC-IDRI datasets
Table 2 comparison of the model of this example with other models on ADNI data set
From the comparison result, it can be seen that the preset deep neural network model in the embodiment obtains a good result in the performance of identifying "uncertain" data (a "0" type sample) in the diagnosis process of the pulmonary nodules and the alzheimer disease.
In addition, fig. 4 shows the comparison result of the probability values of the preset deep neural network model and other models in recognizing "uncertain" data ("0" type samples) in the embodiment. The boxes in fig. 4 are labeled nodules, and it can be seen that the model of the embodiment of the present invention performs better.
S203, image data are obtained.
The implementation of this step is the same as that of step S101 in fig. 1, and is not described here again.
Specifically, if the CT image data is determined, the CT image data is acquired, and if the MRI image data is determined, the MRI image data is acquired.
And S204, predicting the signs of the lung nodules in the image data based on a preset deep neural network model to obtain a prediction result.
The implementation of this step is the same as that of step S102 in fig. 1, and is not described here again.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present application, there is also provided an apparatus for data processing implementing the methods described in fig. 1 and fig. 2, as shown in fig. 5, the apparatus includes:
a first acquiring unit 31, configured to acquire image data, where the image data is medical image data;
the judging unit 32 is configured to judge uncertainty of the image data based on a preset deep neural network model to obtain a judgment result; the preset deep neural network model is an end-to-end deep learning framework capable of identifying image data which can not determine a disease diagnosis result according to the image data.
Specifically, the specific process of implementing the functions of each module in the apparatus in the embodiment of the present application may refer to the related description in the method embodiment, and is not described herein again.
From the above description, it can be seen that the data processing apparatus in the embodiment of the present application can first acquire image data, where the image data is medical image data; then, the image data is judged to be uncertain based on a preset deep neural network model, and the preset deep neural network model is an end-to-end deep learning framework capable of identifying the image data of which the disease diagnosis result cannot be determined according to the image data, so that the image data of which the diagnosis result cannot be determined can be identified by using the model, namely the uncertain data can be better identified, and the problem that the existing machine algorithm cannot pay attention to and identify the uncertain data is solved.
Further, as shown in fig. 6, the apparatus further includes:
a second obtaining unit 33, configured to obtain a training sample before the image data is subjected to uncertainty judgment based on the preset deep neural network model to obtain a judgment result, where the training sample includes a preset number of sample data and sample labeling data corresponding to the sample data, the preset number of sample data is medical image sample data including a lesion, the sample labeling data is image data obtained by performing type labeling on the preset number of sample data, and the type includes certainty and uncertainty;
and the training unit 34 is configured to train a preset deep neural network algorithm based on the training samples to obtain a preset deep neural network model.
Further, as shown in fig. 6, the training unit 34 includes:
a setting module 341, configured to set a loss function according to a preset cost-sensitive parameter and a preset policy selection parameter, where the preset policy selection parameter includes a conservative control parameter and an aggressive control parameter;
the training module 342 is configured to perform model training based on the loss function to obtain a preset deep neural network model.
Further, the trunk network of the preset deep neural network model is a three-dimensional densely connected convolutional network 3D DenseNet.
Further, the medical image data is CT image data which is CT image data of an electronic computer tomography or MRI image data.
Specifically, the specific process of implementing the functions of each module in the apparatus in the embodiment of the present application may refer to the related description in the method embodiment, and is not described herein again.
There is also provided, in accordance with an embodiment of the present application, a non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the method of data processing of fig. 1 or 2.
It will be apparent to those skilled in the art that the modules or steps of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present application is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method of data processing, the method comprising:
acquiring image data, wherein the image data is medical image data;
carrying out uncertainty judgment on the image data based on a preset deep neural network model to obtain a judgment result; the preset deep neural network model is an end-to-end deep learning framework capable of identifying image data which can not determine a disease diagnosis result according to the image data.
2. The data processing method of claim 1, wherein before the determining the uncertainty of the image data based on the preset deep neural network model to obtain the determination result, the method further comprises:
acquiring a training sample, wherein the training sample comprises a preset amount of sample data and corresponding sample marking data, the preset amount of sample data is medical image sample data containing a focus, the sample marking data is image data for performing type marking on the preset amount of sample data, and the type comprises determination and uncertainty;
and training a preset deep neural network algorithm based on the training sample to obtain a preset deep neural network model.
3. The method of claim 2, wherein training the preset deep neural network algorithm based on the training samples to obtain the preset deep neural network model further comprises:
setting a loss function by combining preset cost sensitive parameters and preset strategy selection parameters, wherein the preset strategy selection parameters comprise conservative control parameters and aggressive control parameters;
and training the model based on the loss function to obtain a preset deep neural network model.
4. The data processing method of claim 3, wherein the backbone network of the preset deep neural network model is a three-dimensional densely connected convolutional network 3D DenseNet.
5. The method of data processing according to claim 1, wherein the medical image data is CT image data that is computed tomography CT image data or magnetic resonance imaging MRI image data.
6. An apparatus for data processing, the apparatus comprising:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring image data which is medical image data;
the judging unit is used for judging the uncertainty of the image data based on a preset deep neural network model to obtain a judging result; the preset deep neural network model is an end-to-end deep learning framework capable of identifying image data which can not determine a disease diagnosis result according to the image data.
7. The data processing apparatus of claim 6, further comprising:
a second obtaining unit, configured to obtain a training sample before the image data is subjected to uncertainty judgment based on the preset deep neural network model and a judgment result is obtained, where the training sample includes a preset number of sample data and sample labeling data corresponding to the sample data, the preset number of sample data is medical image sample data including a lesion, the sample labeling data is image data obtained by performing type labeling on the preset number of sample data, and the type includes certainty and uncertainty;
and the training unit is used for training a preset deep neural network algorithm based on the training sample to obtain a preset deep neural network model.
8. The data processing apparatus of claim 7, wherein the training unit comprises:
the setting module is used for setting a loss function by combining preset cost sensitive parameters and preset strategy selection parameters, wherein the preset strategy selection parameters comprise conservative control parameters and aggressive control parameters;
and the training module is used for training the model based on the loss function to obtain a preset deep neural network model.
9. The apparatus of claim 8, wherein the backbone network of the predetermined deep neural network model is a three-dimensional densely connected convolutional network 3D DenseNet.
10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of data processing according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910825532.1A CN110689112A (en) | 2019-09-02 | 2019-09-02 | Data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910825532.1A CN110689112A (en) | 2019-09-02 | 2019-09-02 | Data processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110689112A true CN110689112A (en) | 2020-01-14 |
Family
ID=69108804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910825532.1A Pending CN110689112A (en) | 2019-09-02 | 2019-09-02 | Data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110689112A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022146080A1 (en) * | 2020-12-31 | 2022-07-07 | 서울대학교산학협력단 | Algorithm and method for dynamically changing quantization precision of deep-learning network |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN107016665A (en) * | 2017-02-16 | 2017-08-04 | 浙江大学 | A kind of CT pulmonary nodule detection methods based on depth convolutional neural networks |
| CN107346430A (en) * | 2017-06-29 | 2017-11-14 | 济南浪潮高新科技投资发展有限公司 | A kind of nuclear magnetic resonance image auto-screening method |
| CN107644419A (en) * | 2017-09-30 | 2018-01-30 | 百度在线网络技术（北京）有限公司 | Method and apparatus for analyzing medical image |
| CN109003260A (en) * | 2018-06-28 | 2018-12-14 | 深圳视见医疗科技有限公司 | CT image pulmonary nodule detection method, device, equipment and readable storage medium storing program for executing |
| CN109124668A (en) * | 2018-08-21 | 2019-01-04 | 广州大学 | A kind of good Malignant Nodules diagnostic instrments of lung CT based on full convolutional neural networks |
| CN109544510A (en) * | 2018-10-24 | 2019-03-29 | 广州大学 | A kind of three-dimensional Lung neoplasm recognition methods based on convolutional neural networks |
| CN110013264A (en) * | 2019-04-29 | 2019-07-16 | 北京青燕祥云科技有限公司 | X-ray image recognition methods, device, electronic equipment and storage medium |
| CN110110600A (en) * | 2019-04-04 | 2019-08-09 | 平安科技（深圳）有限公司 | The recognition methods of eye OCT image lesion, device and storage medium |
-
2019
- 2019-09-02 CN CN201910825532.1A patent/CN110689112A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN107016665A (en) * | 2017-02-16 | 2017-08-04 | 浙江大学 | A kind of CT pulmonary nodule detection methods based on depth convolutional neural networks |
| CN107346430A (en) * | 2017-06-29 | 2017-11-14 | 济南浪潮高新科技投资发展有限公司 | A kind of nuclear magnetic resonance image auto-screening method |
| CN107644419A (en) * | 2017-09-30 | 2018-01-30 | 百度在线网络技术（北京）有限公司 | Method and apparatus for analyzing medical image |
| CN109003260A (en) * | 2018-06-28 | 2018-12-14 | 深圳视见医疗科技有限公司 | CT image pulmonary nodule detection method, device, equipment and readable storage medium storing program for executing |
| CN109124668A (en) * | 2018-08-21 | 2019-01-04 | 广州大学 | A kind of good Malignant Nodules diagnostic instrments of lung CT based on full convolutional neural networks |
| CN109544510A (en) * | 2018-10-24 | 2019-03-29 | 广州大学 | A kind of three-dimensional Lung neoplasm recognition methods based on convolutional neural networks |
| CN110110600A (en) * | 2019-04-04 | 2019-08-09 | 平安科技（深圳）有限公司 | The recognition methods of eye OCT image lesion, device and storage medium |
| CN110013264A (en) * | 2019-04-29 | 2019-07-16 | 北京青燕祥云科技有限公司 | X-ray image recognition methods, device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| BOTONG WU ET AL: "《Learning with Unsure Data for Medical Image Diagnosis》", 《HTTPS://WWW.SEMANTICSCHOLAR.ORG/》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022146080A1 (en) * | 2020-12-31 | 2022-07-07 | 서울대학교산학협력단 | Algorithm and method for dynamically changing quantization precision of deep-learning network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10755411B2 (en) | Method and apparatus for annotating medical image | |
| CN108280477B (en) | Method and apparatus for clustering images | |
| CN110059697B (en) | Automatic lung nodule segmentation method based on deep learning | |
| CN113159147B (en) | Image recognition method and device based on neural network and electronic equipment | |
| CN111915609B (en) | Focus detection analysis method, apparatus, electronic device and computer storage medium | |
| CN112465060A (en) | Method and device for detecting target object in image, electronic equipment and readable storage medium | |
| CN111932547B (en) | Method and device for segmenting target object in image, electronic device and storage medium | |
| KR20210038987A (en) | System for automatic tumor detection and classification | |
| CN107729928B (en) | Information acquisition method and device | |
| US11471096B2 (en) | Automatic computerized joint segmentation and inflammation quantification in MRI | |
| CN110941978B (en) | Face clustering method and device for unidentified personnel and storage medium | |
| CN112102959A (en) | Server, data processing method, data processing device and readable storage medium | |
| CN110706200B (en) | Data prediction method and device | |
| CN110706121B (en) | Method and device for determining medical insurance fraud result, electronic equipment and storage medium | |
| Pushparaj et al. | Dental radiographs and photographs in human forensic identification | |
| EP3044756A1 (en) | Method and apparatus for generating image alignment data | |
| CN111462203B (en) | DR focus evolution analysis device and method | |
| CN110689112A (en) | Data processing method and device | |
| WO2019109410A1 (en) | Fully convolutional network model training method for splitting abnormal signal region in mri image | |
| CN114511569B (en) | Tumor marker-based medical image identification method, device, equipment and medium | |
| CN116309465A (en) | Tongue image detection and positioning method based on improved YOLOv5 in natural environment | |
| CN114943695A (en) | Medical sequence image anomaly detection method, device, equipment and storage medium | |
| CN112580505B (en) | Method and device for identifying network point switch door state, electronic equipment and storage medium | |
| CN111192679B (en) | Method, device and storage medium for processing image data abnormality | |
| CN114266777A (en) | Segmentation model training method, segmentation device, electronic device, and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200114 |
|
| RJ01 | Rejection of invention patent application after publication |