CN113592842B - Sample serum quality identification method and identification equipment based on deep learning - Google Patents
Sample serum quality identification method and identification equipment based on deep learning Download PDFInfo
- Publication number
- CN113592842B CN113592842B CN202110910127.7A CN202110910127A CN113592842B CN 113592842 B CN113592842 B CN 113592842B CN 202110910127 A CN202110910127 A CN 202110910127A CN 113592842 B CN113592842 B CN 113592842B
- Authority
- CN
- China
- Prior art keywords
- biochemical sample
- neural network
- network model
- convolutional neural
- deep convolutional
- 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.)
- Active
Links
- 210000002966 serum Anatomy 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000013135 deep learning Methods 0.000 title claims abstract description 14
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 145
- 238000012549 training Methods 0.000 claims abstract description 82
- 206010018910 Haemolysis Diseases 0.000 claims abstract description 68
- 206010023126 Jaundice Diseases 0.000 claims abstract description 68
- 230000008588 hemolysis Effects 0.000 claims abstract description 67
- 239000000523 sample Substances 0.000 claims description 293
- 238000012795 verification Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 22
- 238000003062 neural network model Methods 0.000 claims description 7
- 239000012472 biological sample Substances 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 5
- 230000035945 sensitivity Effects 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 5
- 238000013461 design Methods 0.000 description 20
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 230000009466 transformation Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 3
- 210000004369 blood Anatomy 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 150000002632 lipids Chemical class 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 235000012434 pretzels Nutrition 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- 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
- G06N3/048—Activation functions
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Investigating Or Analysing Biological Materials (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The application discloses a sample serum quality identification method and identification equipment based on deep learning, wherein the method comprises the following steps: acquiring a pretreated biochemical sample image dataset; constructing a deep convolutional neural network model frame, and performing learning training on the deep convolutional neural network model frame based on the preprocessed biochemical sample image data set to obtain a deep convolutional neural network model; acquiring a biochemical sample image to be identified, inputting the biochemical sample image to be identified into a deep convolutional neural network model, and acquiring the probability of hemolysis, jaundice and lipidemia of a first biochemical sample corresponding to the biochemical sample image to be identified; based on the probability of hemolysis, jaundice and lipidemia of the first biochemical sample, determining the corresponding judgment conditions of hemolysis, jaundice and lipidemia of the first biochemical sample. The method can improve the sensitivity and specificity of recognizing the serum quality, can obtain good anti-interference capability, and can improve the recognition effect of the serum quality.
Description
Technical Field
The application relates to the technical field of medical detection, in particular to a sample serum quality identification method and identification equipment based on deep learning.
Background
Poor sample quality is one of the main causes of clinical test errors, and sample failure accounts for 60% of the pre-analysis error, so a high degree of emphasis is required on how to identify failed samples.
In serum quality identification, the conditions such as hemolysis, jaundice and blood lipid of a sample are required to be highly emphasized. Currently, visual assessment of sample quality is widely used in clinical laboratories, but visual assessment results from individual to individual are greatly different due to the influence of environmental and physiological factors (such as daltons), which tends to result in low accuracy. At present, part of sample preprocessing equipment adopts a traditional image segmentation algorithm to combine with a color difference model to identify the serum quality.
However, when the traditional image segmentation algorithm is combined with a color difference model to identify the serum quality, the problems of poor specificity, weak anti-interference capability and the like exist, so that the identification effect of the serum quality is poor.
Disclosure of Invention
Based on the method, the application provides a sample serum quality recognition method and recognition equipment based on deep learning, which are used for improving the recognition effect of serum quality.
In a first aspect, an embodiment of the present application provides a method for identifying quality of serum of a sample based on deep learning, including:
Acquiring a preprocessed biochemical sample image dataset, wherein the preprocessed biochemical sample image dataset comprises: a plurality of biochemical sample images and serum indexes corresponding to the biochemical sample images respectively;
Constructing a deep convolutional neural network model frame, and performing learning training on the deep convolutional neural network model frame based on the preprocessed biochemical sample image data set to obtain a deep convolutional neural network model;
Acquiring a biochemical sample image to be identified, inputting the biochemical sample image to be identified into the deep convolutional neural network model, and acquiring the probability of hemolysis, jaundice and lipidemia of a first biochemical sample corresponding to the biochemical sample image to be identified;
Determining the corresponding conditions of hemolysis, jaundice and lipidemia of the first biochemical sample based on the probabilities of hemolysis, jaundice and lipidemia of the first biochemical sample;
and determining that the first biological sample is a qualified sample or a disqualified sample based on the judging condition.
In one possible design, learning training the deep convolutional neural network model framework based on the preprocessed biochemical sample image dataset to obtain a deep convolutional neural network model comprises:
Randomly dividing the preprocessed biochemical sample image data set into a biochemical sample training data set and a biochemical sample verification data set according to a preset proportion;
Training the deep convolutional neural network model frame based on the biochemical sample training data set to obtain an initial deep convolutional neural network model;
Respectively inputting biochemical sample images in the biochemical sample verification data set into the initial deep convolutional neural network model, and carrying out probability accuracy verification on the initial deep convolutional neural network model;
and if the probability precision of the initial deep convolutional neural network model meets the preset requirement, taking the initial deep convolutional neural network model as the deep convolutional neural network model.
In one possible design, training the deep convolutional neural network model framework based on the biochemical sample training dataset to obtain an initial deep convolutional neural network model comprises:
setting tensorfow system parameters of a system, wherein the system parameters comprise an initial learning rate and iteration parameters of the initial learning rate;
performing image enhancement processing on the biochemical sample training data set to obtain a processed biochemical sample training data set;
and training the deep convolutional neural network model frame on the tensorfow system based on the processed biochemical sample training data set to obtain the initial deep convolutional neural network model.
In one possible design, training the deep convolutional neural network model framework on the tensorfow system based on the processed biochemical sample training dataset to obtain the initial deep convolutional neural network model comprises:
Training the deep convolutional neural network model framework on the tensorfow system based on the processed biochemical sample training data set to obtain the probability of hemolysis, jaundice and lipidemia corresponding to the biochemical sample image in the processed biochemical sample training data set;
Determining the probability sum among the probabilities of hemolysis, jaundice and lipidemia corresponding to the biochemical sample images in the processed biochemical sample training data set based on a preset classification network;
And determining model parameters of the deep convolutional neural network model framework for judging hemolysis, jaundice and lipidemia based on the probability sum, and obtaining the initial deep convolutional neural network model.
In one possible design, the preset classification network is a classification network of Sigmoid activation functions.
In one possible design, constructing a deep convolutional neural network model framework includes:
Adopting 1*1 convolution kernel to combine with residual network to construct 782 initial deep convolution neural network model frame;
Adding a global average pool 2D layer and a final output layer after the initial convolutional neural network model frame to construct the deep convolutional neural network model frame; wherein,
The global average pool 2D layer is used for outputting a characteristic map of an input biochemical sample image of the deep convolutional neural network model, and the final output layer is used for outputting the probability of hemolysis, jaundice and lipidemia of the biochemical sample.
In one possible design, acquiring a preprocessed image dataset of a biochemical sample comprises:
Acquiring an original biochemical sample image dataset;
Manually marking a biochemical sample image with interference information in a serum part in the original biochemical sample image data set to obtain a biochemical sample image data set marked with the interference information;
And setting the image division rate of the biochemical sample images in the biochemical sample image dataset after marking the interference information as N x M x Z, and N, M, Z as an integer greater than 1 to obtain the biochemical sample image dataset after preprocessing.
In a second aspect, an embodiment of the present application provides an identification apparatus, including:
A processing unit for: acquiring a preprocessed biochemical sample image dataset, wherein the preprocessed biochemical sample image dataset comprises: a plurality of biochemical sample images and serum indexes corresponding to the biochemical sample images respectively;
Constructing a deep convolutional neural network model frame, and performing learning training on the deep convolutional neural network model frame based on the preprocessed biochemical sample image data set to obtain a deep convolutional neural network model;
A judging unit configured to: acquiring a biochemical sample image to be identified, inputting the biochemical sample image to be identified into the deep convolutional neural network model, and acquiring the probability of hemolysis, jaundice and lipidemia of a first biochemical sample corresponding to the biochemical sample image to be identified; determining the corresponding conditions of hemolysis, jaundice and lipidemia of the first biochemical sample based on the probabilities of hemolysis, jaundice and lipidemia of the first biochemical sample; and determining that the first biological sample is a qualified sample or a disqualified sample based on the judging condition.
In one possible design, the processing unit is specifically configured to:
Randomly dividing the preprocessed biochemical sample image data set into a biochemical sample training data set and a biochemical sample verification data set according to a preset proportion;
Training the deep convolutional neural network model frame based on the biochemical sample training data set to obtain an initial deep convolutional neural network model;
Respectively inputting biochemical sample images in the biochemical sample verification data set into the initial deep convolutional neural network model, and carrying out probability accuracy verification on the initial deep convolutional neural network model;
and if the probability precision of the initial deep convolutional neural network model meets the preset requirement, taking the initial deep convolutional neural network model as the deep convolutional neural network model.
In one possible design, the processing unit is specifically configured to:
setting tensorfow system parameters of a system, wherein the system parameters comprise an initial learning rate and iteration parameters of the initial learning rate;
performing image enhancement processing on the biochemical sample training data set to obtain a processed biochemical sample training data set;
and training the deep convolutional neural network model frame on the tensorfow system based on the processed biochemical sample training data set to obtain the initial deep convolutional neural network model.
In one possible design, the processing unit is specifically configured to:
Training the deep convolutional neural network model framework on the tensorfow system based on the processed biochemical sample training data set to obtain the probability of hemolysis, jaundice and lipidemia corresponding to the biochemical sample image in the processed biochemical sample training data set;
Determining the probability sum among the probabilities of hemolysis, jaundice and lipidemia corresponding to the biochemical sample images in the processed biochemical sample training data set based on a preset classification network;
And determining model parameters of the deep convolutional neural network model framework for judging hemolysis, jaundice and lipidemia based on the probability sum, and obtaining the initial deep convolutional neural network model.
In one possible design, the preset classification network is a classification network of Sigmoid activation functions.
In one possible design, the processing unit is specifically configured to:
Adopting 1*1 convolution kernel to combine with residual network to construct 782 initial deep convolution neural network model frame;
Adding a global average pool 2D layer and a final output layer after the initial convolutional neural network model frame to construct the deep convolutional neural network model frame; wherein,
The global average pool 2D layer is used for outputting a characteristic map of an input biochemical sample image of the deep convolutional neural network model, and the final output layer is used for outputting the probability of hemolysis, jaundice and lipidemia of the biochemical sample.
In one possible design, the processing unit is specifically configured to:
Acquiring an original biochemical sample image dataset;
Manually marking a biochemical sample image with interference information in a serum part in the original biochemical sample image data set to obtain a biochemical sample image data set marked with the interference information;
And setting the image division rate of the biochemical sample images in the biochemical sample image dataset after marking the interference information as N x M x Z, and N, M, Z as an integer greater than 1 to obtain the biochemical sample image dataset after preprocessing.
In a third aspect, an embodiment of the present application provides an identification apparatus, including: at least one memory and at least one processor;
the at least one memory is used for storing one or more programs;
The method of any one of the possible designs described above is implemented when the one or more programs are executed by the at least one processor.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing at least one program; the method according to any one of the possible designs described above is implemented when the at least one program is executed by a processor.
The beneficial effects of the application are as follows:
In the technical scheme provided by the application, the method for acquiring the pretreated biochemical sample image data set comprises the following steps: the serum indexes respectively corresponding to the biochemical sample images; constructing a deep convolutional neural network model frame, and performing learning training on the deep convolutional neural network model frame based on the preprocessed biochemical sample image data set to obtain a deep convolutional neural network model; acquiring a biochemical sample image to be identified, inputting the biochemical sample image to be identified into a deep convolutional neural network model, and acquiring the probability of hemolysis, jaundice and lipidemia of a first biochemical sample corresponding to the biochemical sample image to be identified; based on the probability of hemolysis, jaundice and lipidemia of the first biochemical sample, determining the corresponding judgment conditions of hemolysis, jaundice and lipidemia of the first biochemical sample. In this way, when the serum quality of the biochemical sample image is identified, the sensitivity and the specificity for identifying the serum quality can be improved, so that the good anti-interference capability for identifying the serum quality can be obtained, and the identification effect of the serum quality can be improved.
Drawings
Fig. 1 is a schematic flow chart of a sample serum quality recognition method based on deep learning according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of acquiring a pretreated image dataset of a biochemical sample according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a learning training process for a deep convolutional neural network model according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a pass sample and a fail sample according to an embodiment of the present application;
FIG. 5 is a schematic diagram of classification of a defective biochemical sample according to an embodiment of the present application;
FIG. 6a is a schematic diagram of an ROC curve corresponding to a hemolysis classification according to an embodiment of the present application;
fig. 6b is a schematic diagram of ROC curves corresponding to jaundice classification according to an embodiment of the present application;
FIG. 6c is a schematic view of an ROC curve corresponding to a lipid blood classification according to an embodiment of the present application;
FIG. 6d is a schematic diagram of a ROC curve corresponding to calculating the sum of the classification probabilities of hemolysis, jaundice and lipidemia according to the embodiment of the present application;
Fig. 7 is a schematic structural diagram of an identification device according to an embodiment of the present application;
Fig. 8 is a schematic structural diagram of an identification device according to an embodiment of the present application.
Detailed Description
In order to facilitate understanding of the technical solution provided by the embodiments of the present application, the technical solution of the present application is described in detail below with reference to the accompanying drawings.
The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of methods consistent with aspects of the application as detailed in the accompanying claims.
Before describing embodiments of the present application, some of the terms used in the present application will be explained first to facilitate understanding by those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items. It will also be understood that the term "at least one" as used herein includes one or more, "a plurality" includes two and more, and "a plurality" includes two and more.
Unless stated to the contrary, the embodiments of the present application refer to the ordinal terms "first" through "third" as distinguishing between multiple objects and not to limit the order, timing, priority, or importance of the multiple objects.
Any biochemical sample referred to herein includes both plasma and serum. For example, referring to fig. 4, a biochemical sample may include two parts, plasma and serum.
The method for identifying the quality of sample serum based on deep learning according to the embodiment of the application will be specifically described with reference to fig. 1 to 6 d.
Fig. 1 is a schematic flow chart of a sample serum quality recognition method based on deep learning according to an embodiment of the application. The execution subject of the method flow shown in fig. 1 is an identification device. As shown in fig. 1, the method flow may include the steps of:
s101, acquiring a preprocessed biochemical sample image dataset.
In some embodiments, the pre-processed biochemical sample image dataset may comprise: the plurality of biochemical sample images and the serum index corresponding to each of the plurality of biochemical sample images. The serum indexes corresponding to the biochemical sample images can be used for representing the serum quality of the biochemical samples corresponding to the biochemical sample images.
In some embodiments, as shown in fig. 2, performing step S101 may specifically include the following flow steps:
S201, acquiring an original biochemical sample image data set.
In some embodiments, a plurality of biochemical sample images and serum indices corresponding to each of the plurality of biochemical sample images of a certain hospital or hospitals over a certain period of time may be collected as the original biochemical sample image dataset. For example, 10667 biochemical sample images and a serum index corresponding to each of 10667 biochemical sample images of an emergency department of a hospital within three months may be collected as the original biochemical sample image dataset.
S202, manually marking a biochemical sample image with interference information in a serum part in the original biochemical sample image data set to obtain a biochemical sample image data set marked with the interference information.
In some embodiments, the interference information may include, but is not limited to: labels, handwriting, decals, etc.
In some embodiments, the biochemical sample image with interference information in the serum part in the original biochemical sample image data set can be marked manually, so that when the deep convolutional neural network model is trained according to the obtained biochemical sample image data set marked with the interference information, the sensitivity of the interference information on the deep convolutional neural network model and the influence degree of the interference information on the anti-interference capability of the deep convolutional neural network model can be judged.
S203, setting the image division rate of the biochemical sample images in the biochemical sample image dataset after marking the interference information as N, M and Z, N, M, Z as an integer greater than 1, and obtaining the biochemical sample image dataset after preprocessing.
Illustratively, N x M x Z may be set to 120 x 500 x 32.
In the embodiment of the application, the image division rate of the biochemical sample image in the biochemical sample image data set after the marking of the interference information is N.M.Z, so that the subsequent training of the deep convolutional neural network model can be facilitated.
S102, constructing a deep convolutional neural network model frame, and performing learning training on the deep convolutional neural network model frame based on the preprocessed biochemical sample image data set to obtain a deep convolutional neural network model.
In some embodiments, a 1*1 convolution kernel can be combined with a residual network to construct an initial deep convolution neural network model frame of 782 layers, and a global average pool 2D layer and a final output layer are added after the initial convolution neural network model frame to construct the deep convolution neural network model frame. The global average pool 2D layer may be used to output a feature map of the input biochemical sample image of the deep convolutional neural network model. The final output layer may be used to output the probability of hemolysis, jaundice, and lipidemia of the biochemical sample.
In some embodiments, as shown in fig. 3, after the deep convolutional neural network model framework is constructed, the learning training process for the deep convolutional neural network model framework may include the following steps:
S301, randomly dividing the preprocessed biochemical sample image data set into a biochemical sample training data set and a biochemical sample verification data set according to a preset proportion.
In some embodiments, the preset ratio may be 8:2.
In some embodiments, the preprocessed biochemical sample image dataset may be randomly divided into the biochemical sample training dataset and the biochemical sample verification dataset by Keras (an open source artificial neural network library written by Python) automatically according to a preset ratio.
S302, training a deep convolutional neural network model frame based on a biochemical sample training data set to obtain an initial deep convolutional neural network model.
In some embodiments, tensorfow system (a data stream programming based symbol math system) may be employed as a back-end for learning training of the deep convolutional neural network model framework.
In a specific implementation, system parameters of tensorfow systems may be set. For example, the initial learning rate of tensorfow systems can be set to be 0.0001, the iteration parameter of the initial learning rate is 1/2 of the iteration parameter of every 10 cycles (epoch), then the training time of the deep convolutional neural network model frame can be 120 cycles, and the algorithm iteration time is short.
In a specific implementation process, the image enhancement processing can be performed on the biochemical sample training data set, and the processed biochemical sample training data set is obtained. For example, the image enhancement processing may be performed on the biochemical sample training data set by using a geometric transformation (including translation, flipping, rotation, scaling, etc.) method, so as to obtain a processed biochemical sample training data set. In the geometric transformation method, one or more combination of rotation/reflection transformation, turnover transformation, scaling transformation, translation transformation, scale transformation, contrast transformation, noise disturbance (pretzel noise and Gaussian noise can be adopted), miscut transformation and other image enhancement modes can be adopted. Of course, other image enhancement methods may be used to perform image enhancement processing on the training data set of the biochemical sample, and embodiments of the present application are not limited. Other image enhancement processing methods may include, but are not limited to: a random brightness adjustment method, a random contrast adjustment method, and the like. In a specific implementation process, the image enhancement processing of the biochemical sample training data set by adopting a corresponding image enhancement method can be realized by adopting ImageDataGenerator functions in the open source code library Keras. It should be appreciated that the processed biochemical sample training dataset contains a greater number of biochemical sample images than the biochemical sample training dataset.
In a specific implementation process, the deep convolutional neural network model framework can be trained on a tensorfow system based on the processed biochemical sample training data set to obtain an initial deep convolutional neural network model.
For example, as shown in fig. 5, a biochemical sample may have overlapping portions when hemolysis, jaundice, and lipidemia classification are performed, for example, a certain biochemical sample may be a hemolysis-jaundice-combined sample. According to the embodiment of the application, the deep convolutional neural network model framework can be trained on the tensorfow system based on the processed biochemical sample training data set, so that the probability of hemolysis, jaundice and lipidemia corresponding to the biochemical sample image in the processed biochemical sample training data set is obtained. The sum of probabilities between the probabilities of hemolysis, jaundice, and lipidemia corresponding to the biochemical sample images in the processed biochemical sample training dataset may then be determined based on a preset classification network (e.g., a two-classification network of Sigmoid activation functions). And then, based on the probability sum, determining model parameters of the deep convolutional neural network model framework for judging hemolysis, jaundice and lipidemia, and obtaining an initial deep convolutional neural network model, thereby improving the sensitivity of the deep convolutional neural network model and enhancing the anti-interference capability of the deep convolutional neural network model.
In the learning and training process of the deep convolutional neural network model framework provided by the embodiment of the present application by using the 10667 biochemical sample images of the above example, the ROC curve corresponding to the hemolysis probability may be shown in fig. 6a, the ROC curve corresponding to the jaundice probability may be shown in fig. 6b, the ROC curve corresponding to the lipidemia probability may be shown in fig. 6c, and the ROC curve corresponding to the calculation of the sum of the hemolysis, jaundice and lipidemia probabilities may be shown in fig. 6 d.
With reference to fig. 6a to fig. 6d, when the serum quality of the biochemical sample image is identified by the deep convolutional neural network model provided by the embodiment of the application, although the biochemical sample image dataset for learning and training the deep convolutional neural network model has interference information, higher sensitivity and specificity can be obtained, which indicates that the influence of the interference information on the sensitivity of the deep convolutional neural network model and the interference resistance of the enhanced deep convolutional neural network model is not great, and the interference resistance of the deep convolutional neural network model is better.
S303, respectively inputting the biochemical sample images in the biochemical sample verification data set into the initial deep convolutional neural network model, and carrying out probability accuracy verification on the initial deep convolutional neural network model.
In a specific implementation, a probability accuracy threshold of the initial deep convolutional neural network model may be set. When the biochemical sample images in the biochemical sample verification data set are respectively input into the initial deep convolutional neural network model, the probability of hemolysis, jaundice and lipidemia corresponding to the second biochemical sample corresponding to the biochemical sample image in the biochemical sample verification data set can be predicted and obtained. And then, the probability of hemolysis, jaundice and lipidemia corresponding to the second biochemical sample, which is obtained based on the actual judgment of the serum indexes of hemolysis, jaundice and lipidemia corresponding to the second biochemical sample, is compared with the probability of hemolysis, jaundice and lipidemia corresponding to the second biochemical sample, which is obtained through prediction, so that the probability precision of the initial deep convolutional neural network model can be obtained. And then, comparing the probability precision of the initial deep convolutional neural network model with a probability precision threshold value, and verifying whether the probability precision of the initial deep convolutional neural network model meets the preset requirement.
And S304, if the probability precision of the initial deep convolutional neural network model meets the preset requirement, taking the initial deep convolutional neural network model as the deep convolutional neural network model.
In a specific implementation, an allowable error range of probability accuracy may be set. If the error between the probability precision of the deep convolutional neural network model and the probability precision threshold is within the allowable error range, the probability precision of the initial deep convolutional neural network can be determined to pass verification, and the preset requirement is met.
In a specific implementation process, if the error between the probability precision of the deep convolutional neural network model and the probability precision threshold is not within the allowable error range, it can be determined that the probability precision of the initial deep convolutional neural network is not verified and does not meet the preset requirement. When the probability accuracy of the initial deep convolutional neural network does not pass the verification, step S101 may be performed back until the probability accuracy of the initial deep convolutional neural network passes the verification.
S103, acquiring a biochemical sample image to be identified.
It should be noted that, in a specific implementation process, the embodiment of the present application is not limited to the execution sequence between the steps S101-S102 and the step S103, for example, the identifying device may execute the steps S101-S102 first and then execute the step S103, or may execute the step S103 first and then execute the steps S101-S102, or may execute the steps S101-S102 and the step S103 simultaneously.
S104, inputting the biochemical sample image to be identified into a deep convolutional neural network model, and obtaining the probability of hemolysis, jaundice and lipidemia of the first biochemical sample corresponding to the biochemical sample image to be identified.
S105, based on the probability of hemolysis, jaundice and lipidemia of the first biochemical sample, determining the corresponding judgment conditions of hemolysis, jaundice and lipidemia of the first biochemical sample.
In some embodiments, the determination may include a determination that the first biochemical sample is a qualified biochemical sample or a non-qualified biochemical sample, and if the first biochemical sample is a non-qualified biochemical sample, whether it is a biochemical sample that has one or more of hemolysis, jaundice, and lipidemia combined.
In a specific implementation process, the probability of hemolysis, jaundice and lipidemia of the first biochemical sample may be compared with preset probability thresholds of hemolysis, jaundice and lipidemia, respectively. When one or more of the probabilities of hemolysis, jaundice, and lipidemia of the first biological sample is determined to be greater than or equal to the respective probability threshold, the first biological sample may be determined to be a biochemical sample that is a combination of one or more of hemolysis, jaundice, and lipidemia. When it is determined that any of the probabilities of hemolysis, jaundice, and lipidemia of the first biochemical sample is less than the respective probability threshold, the first biochemical sample may be determined to be a biochemical sample that is a combination of one or more of hemolysis, jaundice, and lipidemia.
As can be seen from the above description, in the technical solution provided in the embodiments of the present application, obtaining a preprocessed biochemical sample image dataset includes: the serum indexes respectively corresponding to the biochemical sample images; constructing a deep convolutional neural network model frame, and performing learning training on the deep convolutional neural network model frame based on the preprocessed biochemical sample image data set to obtain a deep convolutional neural network model; acquiring a biochemical sample image to be identified, inputting the biochemical sample image to be identified into a deep convolutional neural network model, and acquiring the probability of hemolysis, jaundice and lipidemia of a first biochemical sample corresponding to the biochemical sample image to be identified; based on the probability of hemolysis, jaundice and lipidemia of the first biochemical sample, determining the corresponding judgment conditions of hemolysis, jaundice and lipidemia of the first biochemical sample. In this way, when the serum quality of the biochemical sample image is identified, the sensitivity and the specificity of identifying the serum quality can be improved, so that good anti-interference capability can be obtained, and the identification effect of the serum quality can be improved.
Based on the same inventive concept, an embodiment of the present application further provides an identification apparatus, as shown in fig. 7, the identification apparatus 600 may include:
a processing unit 601, configured to: acquiring a preprocessed biochemical sample image dataset, wherein the preprocessed biochemical sample image dataset comprises: a plurality of biochemical sample images and serum indexes corresponding to the biochemical sample images respectively;
Constructing a deep convolutional neural network model frame, and performing learning training on the deep convolutional neural network model frame based on the preprocessed biochemical sample image data set to obtain a deep convolutional neural network model;
A judging unit 602, configured to: acquiring a biochemical sample image to be identified, inputting the biochemical sample image to be identified into the deep convolutional neural network model, and acquiring the probability of hemolysis, jaundice and lipidemia of a first biochemical sample corresponding to the biochemical sample image to be identified; determining the corresponding conditions of hemolysis, jaundice and lipidemia of the first biochemical sample based on the probabilities of hemolysis, jaundice and lipidemia of the first biochemical sample; and determining that the first biological sample is a qualified sample or a disqualified sample based on the judging condition.
In one possible design, the processing unit 601 is specifically configured to:
Randomly dividing the preprocessed biochemical sample image data set into a biochemical sample training data set and a biochemical sample verification data set according to a preset proportion;
Training the deep convolutional neural network model frame based on the biochemical sample training data set to obtain an initial deep convolutional neural network model;
Respectively inputting biochemical sample images in the biochemical sample verification data set into the initial deep convolutional neural network model, and carrying out probability accuracy verification on the initial deep convolutional neural network model;
and if the probability precision of the initial deep convolutional neural network model meets the preset requirement, taking the initial deep convolutional neural network model as the deep convolutional neural network model.
In one possible design, the processing unit 601 is specifically configured to:
setting tensorfow system parameters of a system, wherein the system parameters comprise an initial learning rate and iteration parameters of the initial learning rate;
performing image enhancement processing on the biochemical sample training data set to obtain a processed biochemical sample training data set;
and training the deep convolutional neural network model frame on the tensorfow system based on the processed biochemical sample training data set to obtain the initial deep convolutional neural network model.
In one possible design, the processing unit 601 is specifically configured to:
Training the deep convolutional neural network model framework on the tensorfow system based on the processed biochemical sample training data set to obtain the probability of hemolysis, jaundice and lipidemia corresponding to the biochemical sample image in the processed biochemical sample training data set;
Determining the probability sum among the probabilities of hemolysis, jaundice and lipidemia corresponding to the biochemical sample images in the processed biochemical sample training data set based on a preset classification network;
And determining model parameters of the deep convolutional neural network model framework for judging hemolysis, jaundice and lipidemia based on the probability sum, and obtaining the initial deep convolutional neural network model.
In one possible design, the preset classification network is a classification network of Sigmoid activation functions.
In one possible design, the processing unit 601 is specifically configured to:
Adopting 1*1 convolution kernel to combine with residual network to construct 782 initial deep convolution neural network model frame;
Adding a global average pool 2D layer and a final output layer after the initial convolutional neural network model frame to construct the deep convolutional neural network model frame; wherein,
The global average pool 2D layer is used for outputting a characteristic map of an input biochemical sample image of the deep convolutional neural network model, and the final output layer is used for outputting the probability of hemolysis, jaundice and lipidemia of the biochemical sample.
In one possible design, the processing unit 601 is specifically configured to:
Acquiring an original biochemical sample image dataset;
Manually marking a biochemical sample image with interference information in a serum part in the original biochemical sample image data set to obtain a biochemical sample image data set marked with the interference information;
And setting the image division rate of the biochemical sample images in the biochemical sample image dataset after marking the interference information as N x M x Z, and N, M, Z as an integer greater than 1 to obtain the biochemical sample image dataset after preprocessing.
The identification device 600 in the embodiment of the present application and the sample serum quality identification method based on deep learning shown in fig. 1 are based on the same concept, and by the foregoing detailed description of the sample serum quality identification method based on deep learning, those skilled in the art can clearly understand the implementation process of the identification device 600 in the embodiment, so that the description is omitted herein for brevity.
Based on the same inventive concept, an embodiment of the present application further provides an identification apparatus, as shown in fig. 8, the identification apparatus 700 may include: at least one memory 701 and at least one processor 702. Wherein:
at least one memory 701 is used to store one or more programs.
The deep learning-based sample serum quality identification method illustrated in fig. 1 described above is implemented when one or more programs are executed by the at least one processor 702.
The identification device 700 may also preferably include a communication interface (not shown in fig. 8) for communicating with external devices and for data interactive transmissions.
It should be noted that the memory 701 may include a high-speed RAM memory, and may further include a nonvolatile memory (nonvolatile memory), such as at least one magnetic disk memory.
In a specific implementation process, if the memory, the processor, and the communication interface are integrated on a chip, the memory, the processor, and the communication interface may complete communication with each other through the internal interface. If the memory, processor, and communication interface are implemented independently, the memory, processor, and communication interface may be interconnected and communicate with each other via a bus.
Based on the same inventive concept, an embodiment of the present application also provides a computer readable storage medium, where at least one program may be stored, and when the at least one program is executed by a processor, the sample serum quality identification method based on deep learning shown in fig. 1 is implemented.
It should be appreciated that a computer readable storage medium is any data storage device that can store data or a program, which can thereafter be read by a computer system. Examples of the computer readable storage medium include: read-only memory, random access memory, CD-ROM, HDD, DVD, magnetic tape, optical data storage devices, and the like.
The computer readable storage medium can also be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion.
Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, radio Frequency (RF), or the like, or any suitable combination of the foregoing.
The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the claims. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application.
Claims (7)
1. The method for identifying the quality of the sample serum based on the deep learning is characterized by comprising the following steps of:
Acquiring a preprocessed biochemical sample image dataset, wherein the preprocessed biochemical sample image dataset comprises: a plurality of biochemical sample images and serum indexes corresponding to the biochemical sample images respectively;
Constructing a deep convolutional neural network model frame, and randomly dividing the preprocessed biochemical sample image dataset into a biochemical sample training dataset and a biochemical sample verification dataset according to a preset proportion;
setting tensorfow system parameters of a system, wherein the system parameters comprise an initial learning rate and iteration parameters of the initial learning rate;
performing image enhancement processing on the biochemical sample training data set to obtain a processed biochemical sample training data set;
Training the deep convolutional neural network model framework on the tensorfow system based on the processed biochemical sample training data set to obtain the probability of hemolysis, jaundice and lipidemia corresponding to the biochemical sample image in the processed biochemical sample training data set;
Determining the probability sum among the probabilities of hemolysis, jaundice and lipidemia corresponding to the biochemical sample images in the processed biochemical sample training data set based on a preset classification network;
determining model parameters of the deep convolutional neural network model framework for judging hemolysis, jaundice and lipidemia based on the probability sum, and obtaining an initial deep convolutional neural network model;
Respectively inputting biochemical sample images in the biochemical sample verification data set into the initial deep convolutional neural network model, and carrying out probability accuracy verification on the initial deep convolutional neural network model;
if the probability precision of the initial deep convolutional neural network model meets the preset requirement, using the initial deep convolutional neural network model as the deep convolutional neural network model;
Acquiring a biochemical sample image to be identified, inputting the biochemical sample image to be identified into the deep convolutional neural network model, and acquiring the probability of hemolysis, jaundice and lipidemia of a first biochemical sample corresponding to the biochemical sample image to be identified;
and determining the judgment conditions of the hemolysis, the jaundice and the lipidemia corresponding to the first biochemical sample based on the probability of the hemolysis, the jaundice and the lipidemia of the first biochemical sample.
2. The method of claim 1, wherein the predetermined classification network is a classification network of Sigmoid activation functions.
3. The method of claim 1 or 2, wherein constructing a deep convolutional neural network model framework comprises:
Adopting 1*1 convolution kernel to combine with residual network to construct 782 initial deep convolution neural network model frame;
Adding a global average pool 2D layer and a final output layer after the initial convolutional neural network model frame to construct the deep convolutional neural network model frame; wherein,
The global average pool 2D layer is used for outputting a characteristic map of an input biochemical sample image of the deep convolutional neural network model, and the final output layer is used for outputting the probability of hemolysis, jaundice and lipidemia of the biochemical sample.
4. The method of claim 1 or 2, wherein acquiring the preprocessed image dataset of the biochemical sample comprises:
Acquiring an original biochemical sample image dataset;
Manually marking a biochemical sample image with interference information in a serum part in the original biochemical sample image data set to obtain a biochemical sample image data set marked with the interference information;
And setting the image division rate of the biochemical sample images in the biochemical sample image dataset after marking the interference information as N x M x Z, and N, M, Z as an integer greater than 1 to obtain the biochemical sample image dataset after preprocessing.
5. An identification device, comprising:
A processing unit for: acquiring a preprocessed biochemical sample image dataset, wherein the preprocessed biochemical sample image dataset comprises: a plurality of biochemical sample images and serum indexes corresponding to the biochemical sample images respectively; constructing a deep convolutional neural network model frame, and randomly dividing the preprocessed biochemical sample image dataset into a biochemical sample training dataset and a biochemical sample verification dataset according to a preset proportion; setting tensorfow system parameters of a system, wherein the system parameters comprise an initial learning rate and iteration parameters of the initial learning rate; performing image enhancement processing on the biochemical sample training data set to obtain a processed biochemical sample training data set; training the deep convolutional neural network model framework on the tensorfow system based on the processed biochemical sample training data set to obtain the probability of hemolysis, jaundice and lipidemia corresponding to the biochemical sample image in the processed biochemical sample training data set; determining the probability sum among the probabilities of hemolysis, jaundice and lipidemia corresponding to the biochemical sample images in the processed biochemical sample training data set based on a preset classification network; determining model parameters of the deep convolutional neural network model framework for judging hemolysis, jaundice and lipidemia based on the probability sum, and obtaining an initial deep convolutional neural network model; respectively inputting biochemical sample images in the biochemical sample verification data set into the initial deep convolutional neural network model, and carrying out probability accuracy verification on the initial deep convolutional neural network model; if the probability precision of the initial deep convolutional neural network model meets the preset requirement, using the initial deep convolutional neural network model as the deep convolutional neural network model;
A judging unit configured to: acquiring a biochemical sample image to be identified, inputting the biochemical sample image to be identified into the deep convolutional neural network model, and acquiring the probability of hemolysis, jaundice and lipidemia of a first biochemical sample corresponding to the biochemical sample image to be identified; determining the corresponding conditions of hemolysis, jaundice and lipidemia of the first biochemical sample based on the probabilities of hemolysis, jaundice and lipidemia of the first biochemical sample; and determining that the first biological sample is a qualified sample or a disqualified sample based on the judging condition.
6. An identification device, comprising: at least one memory and at least one processor;
the at least one memory is used for storing one or more programs;
the method of any of claims 1-4 is implemented when the one or more programs are executed by the at least one processor.
7. A computer-readable storage medium, wherein the computer-readable storage medium stores at least one program; the method according to any of claims 1-4 is implemented when said at least one program is executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110910127.7A CN113592842B (en) | 2021-08-09 | 2021-08-09 | Sample serum quality identification method and identification equipment based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110910127.7A CN113592842B (en) | 2021-08-09 | 2021-08-09 | Sample serum quality identification method and identification equipment based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113592842A CN113592842A (en) | 2021-11-02 |
| CN113592842B true CN113592842B (en) | 2024-05-24 |
Family
ID=78256524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110910127.7A Active CN113592842B (en) | 2021-08-09 | 2021-08-09 | Sample serum quality identification method and identification equipment based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113592842B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114638803A (en) * | 2022-03-15 | 2022-06-17 | 四川大学华西医院 | Serum index intelligent interpretation method and system based on deep learning |
| CN114878844A (en) * | 2022-05-20 | 2022-08-09 | 上海捷程医学科技有限公司 | Method, system and equipment for automatically detecting quality of centrifuged blood sample |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766780A (en) * | 2018-12-20 | 2019-05-17 | 武汉理工大学 | A kind of ship smog emission on-line checking and method for tracing based on deep learning |
| CN110199172A (en) * | 2016-11-14 | 2019-09-03 | 美国西门子医学诊断股份有限公司 | For detecting the haemolysis of sample, jaundice, piarhemia or method, equipment and the quality inspection module of normality |
| CN110573859A (en) * | 2017-04-13 | 2019-12-13 | 美国西门子医学诊断股份有限公司 | Method and apparatus for HILN characterization using convolutional neural networks |
| CN110573883A (en) * | 2017-04-13 | 2019-12-13 | 美国西门子医学诊断股份有限公司 | Method and apparatus for determining tag count during sample characterization |
| CN111223088A (en) * | 2020-01-16 | 2020-06-02 | 东南大学 | Casting surface defect identification method based on deep convolutional neural network |
| CN111462076A (en) * | 2020-03-31 | 2020-07-28 | 湖南国科智瞳科技有限公司 | Method and system for detecting fuzzy area of full-slice digital pathological image |
| CN112639482A (en) * | 2018-06-15 | 2021-04-09 | 美国西门子医学诊断股份有限公司 | Sample container characterization using single depth neural networks in an end-to-end training manner |
| CN112673261A (en) * | 2018-09-20 | 2021-04-16 | 美国西门子医学诊断股份有限公司 | Method and apparatus for HILN determination using a deep adaptation network for both serum and plasma sampling |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11386291B2 (en) * | 2018-01-10 | 2022-07-12 | Siemens Healthcare Diagnostics Inc. | Methods and apparatus for bio-fluid specimen characterization using neural network having reduced training |
-
2021
- 2021-08-09 CN CN202110910127.7A patent/CN113592842B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110199172A (en) * | 2016-11-14 | 2019-09-03 | 美国西门子医学诊断股份有限公司 | For detecting the haemolysis of sample, jaundice, piarhemia or method, equipment and the quality inspection module of normality |
| CN110573859A (en) * | 2017-04-13 | 2019-12-13 | 美国西门子医学诊断股份有限公司 | Method and apparatus for HILN characterization using convolutional neural networks |
| CN110573883A (en) * | 2017-04-13 | 2019-12-13 | 美国西门子医学诊断股份有限公司 | Method and apparatus for determining tag count during sample characterization |
| CN112639482A (en) * | 2018-06-15 | 2021-04-09 | 美国西门子医学诊断股份有限公司 | Sample container characterization using single depth neural networks in an end-to-end training manner |
| CN112673261A (en) * | 2018-09-20 | 2021-04-16 | 美国西门子医学诊断股份有限公司 | Method and apparatus for HILN determination using a deep adaptation network for both serum and plasma sampling |
| CN109766780A (en) * | 2018-12-20 | 2019-05-17 | 武汉理工大学 | A kind of ship smog emission on-line checking and method for tracing based on deep learning |
| CN111223088A (en) * | 2020-01-16 | 2020-06-02 | 东南大学 | Casting surface defect identification method based on deep convolutional neural network |
| CN111462076A (en) * | 2020-03-31 | 2020-07-28 | 湖南国科智瞳科技有限公司 | Method and system for detecting fuzzy area of full-slice digital pathological image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113592842A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200334457A1 (en) | Image recognition method and apparatus | |
| CN109583332B (en) | Face recognition method, face recognition system, medium, and electronic device | |
| CN113592842B (en) | Sample serum quality identification method and identification equipment based on deep learning | |
| US11120297B2 (en) | Segmentation of target areas in images | |
| WO2020056995A1 (en) | Method and device for determining speech fluency degree, computer apparatus, and readable storage medium | |
| CN113012114B (en) | Blood vessel identification method and device, storage medium and electronic equipment | |
| CN113011509B (en) | Lung bronchus classification method and device, electronic equipment and storage medium | |
| CN113763371B (en) | Pathological image cell nucleus segmentation method and device | |
| CN112419268A (en) | Method, device, equipment and medium for detecting image defects of power transmission line | |
| CN116385380A (en) | Defect detection method, system, equipment and storage medium based on depth characteristics | |
| CN113674288A (en) | Automatic segmentation method for non-small cell lung cancer digital pathological image tissues | |
| CN114494215A (en) | Transformer-based thyroid nodule detection method | |
| CN110472673B (en) | Parameter adjustment method, fundus image processing device, fundus image processing medium and fundus image processing apparatus | |
| US10922569B2 (en) | Method and apparatus for detecting model reliability | |
| CN109977400B (en) | Verification processing method and device, computer storage medium and terminal | |
| CN110826616A (en) | Information processing method and device, electronic equipment and storage medium | |
| WO2023280229A1 (en) | Image processing method, electronic device, and storage medium | |
| CN116228731A (en) | Multi-contrast learning coronary artery high-risk plaque detection method, system and terminal | |
| CN114266777A (en) | Segmentation model training method, segmentation device, electronic device, and medium | |
| CN111160346A (en) | Ischemic stroke segmentation system based on three-dimensional convolution | |
| CN115631370A (en) | Identification method and device of MRI (magnetic resonance imaging) sequence category based on convolutional neural network | |
| CN115346084A (en) | Sample processing method, sample processing apparatus, electronic device, storage medium, and program product | |
| CN114565617A (en) | Pruning U-Net + + based breast tumor image segmentation method and system | |
| CN115080864A (en) | Artificial intelligence based product recommendation method and device, computer equipment and medium | |
| CN110968690B (en) | Clustering division method and device for words, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |