CN111242922A - Protein image classification method, device, equipment and medium - Google Patents
Protein image classification method, device, equipment and medium Download PDFInfo
- Publication number
- CN111242922A CN111242922A CN202010030899.7A CN202010030899A CN111242922A CN 111242922 A CN111242922 A CN 111242922A CN 202010030899 A CN202010030899 A CN 202010030899A CN 111242922 A CN111242922 A CN 111242922A
- Authority
- CN
- China
- Prior art keywords
- protein
- image
- classification
- category
- classified
- 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
- 108090000623 proteins and genes Proteins 0.000 title claims abstract description 305
- 102000004169 proteins and genes Human genes 0.000 title claims abstract description 305
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000013145 classification model Methods 0.000 claims abstract description 93
- 238000012549 training Methods 0.000 claims description 38
- 238000010186 staining Methods 0.000 claims description 20
- 238000011176 pooling Methods 0.000 claims description 16
- 230000004927 fusion Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 210000004027 cell Anatomy 0.000 description 2
- 210000002472 endoplasmic reticulum Anatomy 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 102000003839 Human Proteins Human genes 0.000 description 1
- 108090000144 Human Proteins Proteins 0.000 description 1
- 102000029749 Microtubule Human genes 0.000 description 1
- 108091022875 Microtubule Proteins 0.000 description 1
- 101710192597 Protein map Proteins 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 210000000805 cytoplasm Anatomy 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 210000005260 human cell Anatomy 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000007762 localization of cell Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000004949 mass spectrometry Methods 0.000 description 1
- 238000000386 microscopy Methods 0.000 description 1
- 210000004688 microtubule Anatomy 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
Images
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
-
- 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
- G06T2207/10024—Color image
-
- 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
- G06T2207/10056—Microscopic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a medium for classifying protein images, wherein the method comprises the following steps: acquiring an original protein image, and generating a protein image to be classified according to the original protein image; inputting the protein image to be classified into a protein classification model trained in advance to obtain a classification result output by the protein classification model; and determining the category of the original protein image according to the classification result. The protein image classification method provided by the embodiment of the invention can automatically determine the type of the protein image and improve the accuracy of protein type determination.
Description
Technical Field
The embodiment of the invention relates to the field of image processing, in particular to a protein image classification method, a device, equipment and a medium.
Background
Protein profiling aims at mapping all human proteins in cells, tissues and organs using various omics techniques including antibody imaging, mass spectrometry-based proteomics, transcriptomics and system biology. Images visualizing proteins in cells are commonly used for biomedical research, however, due to advances in high-throughput microscopy, the speed of generation of these protein images far exceeds the speed of manual evaluation. Therefore, there is a need for automated biomedical image analysis to accelerate the understanding of human cells and diseases that is greater than ever before. In protein image analysis, how to accurately and automatically determine the category of a protein image is a technical problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention provides a protein image classification method, a device, equipment and a medium, which are used for accurately and automatically determining the category of a protein image.
In a first aspect, an embodiment of the present invention provides a protein image classification method, including:
acquiring an original protein image, and generating a protein image to be classified according to the original protein image;
inputting the protein image to be classified into a protein classification model trained in advance to obtain a classification result output by the protein classification model;
and determining the category of the original protein image according to the classification result.
In a second aspect, an embodiment of the present invention further provides a protein image classification apparatus, including:
the to-be-classified image generation module is used for acquiring an original protein image and generating a to-be-classified protein image according to the original protein image;
the classification result acquisition module is used for inputting the protein image to be classified into a protein classification model trained in advance to obtain a classification result output by the protein classification model;
and the image category determining module is used for determining the category of the original protein image according to the classification result.
In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a protein image classification method as provided by any embodiment of the invention.
In a fourth aspect, embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the protein image classification method provided in any embodiment of the present invention.
According to the embodiment of the invention, an original protein image is obtained, and a protein image to be classified is generated according to the original protein image; inputting the protein image to be classified into a protein classification model trained in advance to obtain a classification result output by the protein classification model; and determining the category of the original protein image according to the classification result, thereby realizing accurate and automatic determination of the category of the protein image.
Drawings
FIG. 1a is a flowchart of a protein image classification method according to an embodiment of the present invention;
FIG. 1b is a schematic flow chart of a protein classification method according to an embodiment of the present invention;
FIG. 2a is a flowchart of a protein image classification method according to a second embodiment of the present invention;
FIG. 2b is a schematic structural diagram of a protein classification model in the protein image classification method according to the second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a protein image classification device according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1a is a flowchart of a protein image classification method according to an embodiment of the present invention. This embodiment is applicable to the case when the protein image class is identified. The method may be performed by a protein image classification apparatus, which may be implemented in software and/or hardware, for example, and may be configured in a computer device. As shown in fig. 1a, the method comprises:
and S110, acquiring an original protein image, and generating a protein image to be classified according to the original protein image.
In this embodiment, the original protein image may be a protein image marked by four channels, depicted by nuclear, microtubule, and living cell Endoplasmic Reticulum (ER) staining. After the original protein images are obtained, the original protein images are combined into the protein images to be classified for inputting the protein classification model through a preset image combination method.
In one embodiment of the present invention, the original protein image includes four stain images, the stain images are three-channel images, the stain images include a first stain image, a second stain image, a third stain image and a fourth stain image, and the protein image to be classified is generated according to the original protein image, including: selecting a first channel image from the first staining image, selecting a second channel image from the second staining image, selecting a third channel image from the third staining image, selecting a fourth channel image from the fourth staining image, and combining the first channel image, the second channel image, the third channel image and the fourth staining image to generate the protein image to be classified.
Optionally, the raw protein image comprises four stain images. Illustratively, the original protein image includes a red-stained image, a green-stained image, a blue-stained image, and a yellow-stained image, each of which is an RGB image, which is a three-channel image. Wherein, generating the protein image to be classified according to the original combustion thermal image may be: taking an R channel image in the red staining image, taking a G channel image in the green staining image, taking a B channel image in the blue staining image, taking any one channel image in the yellow staining image, combining the four channel images taken out into a four-channel image, and taking the combined four-channel image as a protein image to be classified. In order to make the classification result of the original protein image more accurate, the B channel image in the yellow stain image can be removed for image merging.
And S120, inputting the protein image to be classified into a pre-trained protein classification model to obtain a classification result output by the protein classification model.
In this example, the protein map imaged by the high-throughput microscope was identified by a deep learning method to distinguish the proteomic cell localization pattern. Specifically, the protein image to be classified is input into a protein classification model trained in advance, and a classification result output by the protein classification model is obtained. Optionally, the protein classification model is constructed based on a neural network. The neural network is a module constructed based on an artificial neural network. In this embodiment, the neural network may be a convolutional neural network, a generative countermeasure network, or other form of neural network model. Preferably, a protein classification model may be constructed based on the acceptance v4 model. Optionally, the classification result output by the protein classification model may be a probability value corresponding to each class in the protein image to be classified.
In this embodiment, a single-scale protein classification model may be trained, and the class of the protein image to be classified may be determined according to the fixed protein classification model. And training protein classification models of multiple scales, and determining the class of the protein image to be classified according to the protein classification models of different scales. The determination of the protein image category according to the fixed protein classification model can simplify the calculation amount, and the determination of the protein image category according to the protein classification models with different scales can make the determination of the protein category more accurate.
In an embodiment of the present invention, the inputting the protein image to be classified into a pre-trained protein classification model to obtain a classification result output by the protein classification model includes: converting the protein image to be classified into at least two scales of converted protein images; and respectively inputting the converted protein images into protein classification models corresponding to the scales of the converted protein images to obtain classification results output by the protein classification models.
Optionally, in order to make protein classification more accurate, the protein image to be classified may be converted into converted protein images of multiple scales, the converted protein images are classified respectively, and the protein classes contained in the converted protein images are determined. Specifically, corresponding protein classification models are trained for protein images of different scales, and the converted protein images are classified by using the protein classification models corresponding to the image scales of the converted protein images, so that the classification results of the converted protein images are obtained. Optionally, the classification result of the transformed protein image may be probability values corresponding to the classes in the transformed protein image. For example, assuming that the resolution of the protein image to be classified is 1024 × 1024, the protein image to be classified can be converted into converted protein images of three scales, 512 × 512, 650 × 650, and 800 × 800.
Fig. 1b is a schematic flow chart of a protein classification method according to an embodiment of the present invention, and as shown in fig. 1b, a 1024x1024 protein image to be classified is scaled into a 512x512 converted protein image, a 650x650 converted protein image, and an 800x800 converted protein image, each scale image is respectively input into a protein classification model corresponding to a scale, probabilities of 28 classes are predicted, and finally, the prediction results of each class in the classification results output by 3 protein classification models are averaged, and the probability of each class is output.
And S130, determining the category of the original protein image according to the classification result.
And after the classification result output by the protein classification model is obtained, determining the category of the original protein image according to the classification result. It should be noted that the original protein image may include a plurality of classes of proteins, and thus, the original protein image may also include a plurality of classes. In this embodiment, the category of the protein is used to indicate the location of the protein, such as the nucleus, cytoplasm, etc.
In an embodiment of the present invention, the determining the class of the original protein image according to the classification result includes: and fusing the classification results output by the protein classification models corresponding to different scales, and determining the category of the protein image to be classified according to the fusion result. And when the proteins to be classified of different scales are classified according to the protein classification models of multiple scales, fusing the classification results output by the protein classification models of different scales, and determining the category of the protein image to be classified according to the fusion result. Optionally, fusing the classification results output by the protein classification models with different scales may be: for each class, calculating the probability average value of the class output by the protein classification model with different scales.
On the basis of the above scheme, the fusion result includes probability values corresponding to the categories, and the determining the category of the protein image to be classified according to the fusion result includes: for each of the categories, comparing the probability value for the category to a threshold for the category; and if the probability value of the category is not less than the threshold value of the category, taking the category as the category of the protein image to be classified. Alternatively, a threshold value may be set for each category, and for each category, when the probability value of the category is higher than the set threshold value, the category is taken as the prediction result of the original protein image.
According to the embodiment of the invention, an original protein image is obtained, and a protein image to be classified is generated according to the original protein image; inputting the protein image to be classified into a protein classification model trained in advance to obtain a classification result output by the protein classification model; and determining the category of the original protein image according to the classification result, thereby realizing accurate and automatic determination of the category of the protein image.
Example two
Fig. 2a is a flowchart of a protein image classification method according to a second embodiment of the present invention. The present embodiment is optimized based on the above embodiments. As shown in fig. 2a, the method comprises:
s210, obtaining a sample protein image and a category corresponding to the sample protein image, and generating a training sample pair based on the sample protein image and the category corresponding to the sample protein image.
S220, training the pre-constructed protein classification model by using the training sample pair to obtain the trained protein classification model.
Optionally, a sample protein image may be obtained, the categories included in the sample protein image are marked in a manual marking manner, training sample pairs are generated based on the sample protein image and the categories marked in the sample protein image, and a large number of training sample pairs are used to train a pre-constructed protein classification model, so as to obtain a trained protein classification model.
In an embodiment of the present invention, the training of the pre-constructed protein classification model using the training sample pair to obtain the trained protein classification model includes: filtering the training sample pairs by using a weight sample sampler to obtain training sample pairs with balanced categories; and training the preferentially constructed protein classification model by using the class-balanced training sample pair to obtain the trained protein classification model.
Due to the particularity of the samples, the classes in the sample protein images are unbalanced, that is, the difference between the number of samples corresponding to different classes is large, in this embodiment, in order to avoid inaccurate model training caused by unbalanced samples, after the sample protein images are labeled, the weight sample sampler is used for filtering the constructed training sample pairs, and the filtered samples are used for training the pre-constructed protein classification model. Alternatively, different sampling weights may be set for each class in the weighted sample sampler to equalize the number of samples of the different classes. Illustratively, the weight of each category may be calculated by the following formula:
wherein A isiIs a weight of class i, NiNumber of samples of class i, NkFor the class identification to be calculated, 28 is the total number of classes.
In one embodiment of the present invention, the construction of the protein classification model includes: and obtaining a network basic model, and adding a pooling layer after the last convolution layer of the network basic model to obtain the constructed protein classification model, wherein the pooling layer comprises a global mean pooling layer and/or a global maximum pooling layer.
In the embodiment, in order to make the prediction result of the model more accurate, improvement is made on the basis of the network basic model to construct a model suitable for protein classification. Optionally, the inception v4 model can be used as a network base model, and a protein classification model is constructed on the basis of the inception v4 model. Fig. 2b is a schematic structural diagram of a protein classification model in the protein image classification method according to the second embodiment of the present invention. As shown in fig. 2b, after the last convolutional layer of the inceptionv4 model, a global-average-pooling (GAP) layer and a Global Maximum Pooling (GMP) layer are added in parallel, global-average pooling and global maximum pooling are performed on the convolutional layer, the pooled features are spliced, and then the two full-link layers are passed through, and then the softmax processing layers are connected, so as to obtain the constructed protein classification model.
It should be noted that after the training sample pair and the protein classification model are constructed, the sample protein images in the training sample pair can be converted into converted sample protein images of different scales, so as to obtain protein classification models corresponding to different scales through training.
And S230, acquiring an original protein image, and generating a protein image to be classified according to the original protein image.
S240, inputting the protein image to be classified into a pre-trained protein classification model, and obtaining a classification result output by the protein classification model.
And S250, determining the category of the original protein image according to the classification result.
According to the technical scheme of the embodiment of the invention, the operations of constructing the protein classification model and training the constructed protein classification model according to the training sample pair are added, and the accuracy of protein classification is improved by constructing the protein classification model suitable for protein classification.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a protein image classification device according to a third embodiment of the present invention. The protein image classification device can be implemented in software and/or hardware, for example, the protein image classification device can be configured in a computer device. As shown in fig. 3, the apparatus includes an image to be classified generating module 310, a classification result obtaining module 320, and an image category determining module 330, wherein:
the to-be-classified image generation module 310 is configured to obtain an original protein image, and generate a to-be-classified protein image according to the original protein image;
a classification result obtaining module 320, configured to input the protein image to be classified into a pre-trained protein classification model, and obtain a classification result output by the protein classification model;
an image class determination module 330, configured to determine a class of the original protein image according to the classification result.
According to the embodiment of the invention, an original protein image is obtained through an image generation module to be classified, and the protein image to be classified is generated according to the original protein image; the classification result acquisition module inputs the protein image to be classified into a protein classification model trained in advance to obtain a classification result output by the protein classification model; the image category determining module determines the category of the original protein image according to the classification result, so that the category of the protein image is determined accurately and automatically.
Optionally, on the basis of the foregoing scheme, the original protein image includes four stain images, the stain images are three-channel images, the stain images include a first stain image, a second stain image, a third stain image and a fourth stain image, and the to-be-classified image generation module 310 is specifically configured to:
selecting a first channel image from the first staining image, selecting a second channel image from the second staining image, selecting a third channel image from the third staining image, selecting a fourth channel image from the fourth staining image, and combining the first channel image, the second channel image, the third channel image and the fourth staining image to generate the protein image to be classified.
Optionally, on the basis of the above scheme, the classification result obtaining module 320 is specifically configured to:
converting the protein image to be classified into at least two scales of converted protein images;
and respectively inputting the converted protein images into protein classification models corresponding to the scales of the converted protein images to obtain classification results output by the protein classification models.
Optionally, on the basis of the foregoing scheme, the image category determining module 330 is specifically configured to:
and fusing the classification results output by the protein classification models corresponding to different scales, and determining the category of the protein image to be classified according to the fusion result.
Optionally, on the basis of the above scheme, the fusion result includes probability values corresponding to the categories, and the image category determining module 330 is specifically configured to:
for each of the categories, comparing the probability value for the category to a threshold for the category;
and if the probability value of the category is not less than the threshold value of the category, taking the category as the category of the protein image to be classified.
Optionally, on the basis of the above scheme, the apparatus further includes a model training module, configured to:
acquiring a sample protein image and a category corresponding to the sample protein image, and generating a training sample pair based on the sample protein image and the category corresponding to the sample protein image;
and training the pre-constructed protein classification model by using the training sample pair to obtain the trained protein classification model.
Optionally, on the basis of the above scheme, the model training module is specifically configured to:
filtering the training sample pairs by using a weight sample sampler to obtain training sample pairs with balanced categories;
and training the preferentially constructed protein classification model by using the class-balanced training sample pair to obtain the trained protein classification model.
Optionally, on the basis of the above scheme, the apparatus further includes a model building module, configured to:
and obtaining a network basic model, and adding a pooling layer after the last convolution layer of the network basic model to obtain the constructed protein classification model, wherein the pooling layer comprises a global mean pooling layer and/or a global maximum pooling layer.
The protein image classification device provided by the embodiment of the invention can execute the protein image classification method provided by any embodiment, and has the corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary computer device 412 suitable for use in implementing embodiments of the present invention. The computer device 412 shown in FIG. 4 is only one example and should not impose any limitations on the functionality or scope of use of embodiments of the present invention.
As shown in FIG. 4, computer device 412 is in the form of a general purpose computing device. Components of computer device 412 may include, but are not limited to: one or more processors 416, a system memory 428, and a bus 418 that couples the various system components (including the system memory 428 and the processors 416).
Computer device 412 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 412 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 428 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)430 and/or cache memory 432. The computer device 412 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage 434 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, and commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 418 by one or more data media interfaces. Memory 428 can include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 440 having a set (at least one) of program modules 442 may be stored, for instance, in memory 428, such program modules 442 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. The program modules 442 generally perform the functions and/or methodologies of the described embodiments of the invention.
The computer device 412 may also communicate with one or more external devices 414 (e.g., keyboard, pointing device, display 424, etc.), with one or more devices that enable a user to interact with the computer device 412, and/or with any devices (e.g., network card, modem, etc.) that enable the computer device 412 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 422. Also, computer device 412 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) through network adapter 420. As shown, network adapter 420 communicates with the other modules of computer device 412 over bus 418. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the computer device 412, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processor 416 executes programs stored in the system memory 428 to perform various functional applications and data processing, such as implementing a protein image classification method provided by an embodiment of the present invention, the method including:
acquiring an original protein image, and generating a protein image to be classified according to the original protein image;
inputting the protein image to be classified into a protein classification model trained in advance to obtain a classification result output by the protein classification model;
and determining the category of the original protein image according to the classification result.
Of course, those skilled in the art will understand that the processor may also implement the technical solution of the protein image classification method provided in any embodiment of the present invention.
EXAMPLE five
The fifth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the protein image classification method provided in the fifth embodiment of the present invention, where the method includes:
acquiring an original protein image, and generating a protein image to be classified according to the original protein image;
inputting the protein image to be classified into a protein classification model trained in advance to obtain a classification result output by the protein classification model;
and determining the category of the original protein image according to the classification result.
Of course, the computer-readable storage medium provided by the embodiments of the present invention, on which the computer program is stored, is not limited to the method operations described above, and may also perform related operations in the protein image classification method provided by any embodiments of the present invention.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (11)
1. A protein image classification method is characterized by comprising the following steps:
acquiring an original protein image, and generating a protein image to be classified according to the original protein image;
inputting the protein image to be classified into a protein classification model trained in advance to obtain a classification result output by the protein classification model;
and determining the category of the original protein image according to the classification result.
2. The method of claim 1, wherein the original protein image comprises four stain images, the stain images being three-channel images, the stain images comprising a first stain image, a second stain image, a third stain image, and a fourth stain image, the generating a protein image to be classified from the original protein image comprising:
selecting a first channel image from the first staining image, selecting a second channel image from the second staining image, selecting a third channel image from the third staining image, selecting a fourth channel image from the fourth staining image, and combining the first channel image, the second channel image, the third channel image and the fourth staining image to generate the protein image to be classified.
3. The method according to claim 1, wherein the inputting the protein image to be classified into a pre-trained protein classification model to obtain the classification result output by the protein classification model comprises:
converting the protein image to be classified into at least two scales of converted protein images;
and respectively inputting the converted protein images into protein classification models corresponding to the scales of the converted protein images to obtain classification results output by the protein classification models.
4. The method of claim 3, wherein said determining a class of said original protein image based on said classification comprises:
and fusing the classification results output by the protein classification models corresponding to different scales, and determining the category of the protein image to be classified according to the fusion result.
5. The method according to claim 4, wherein the fusion result includes probability values corresponding to the categories, and the determining the category of the protein image to be classified according to the fusion result includes:
for each of the categories, comparing the probability value for the category to a threshold for the category;
and if the probability value of the category is not less than the threshold value of the category, taking the category as the category of the protein image to be classified.
6. The method of claim 1, further comprising:
acquiring a sample protein image and a category corresponding to the sample protein image, and generating a training sample pair based on the sample protein image and the category corresponding to the sample protein image;
and training the pre-constructed protein classification model by using the training sample pair to obtain the trained protein classification model.
7. The method of claim 6, wherein the training a pre-constructed protein classification model using the training sample pairs to obtain a trained protein classification model comprises:
filtering the training sample pairs by using a weight sample sampler to obtain training sample pairs with balanced categories;
and training the preferentially constructed protein classification model by using the class-balanced training sample pair to obtain the trained protein classification model.
8. The method of claim 6, wherein the constructing of the protein classification model comprises:
and obtaining a network basic model, and adding a pooling layer after the last convolution layer of the network basic model to obtain the constructed protein classification model, wherein the pooling layer comprises a global mean pooling layer and/or a global maximum pooling layer.
9. A protein image classification device, comprising:
the to-be-classified image generation module is used for acquiring an original protein image and generating a to-be-classified protein image according to the original protein image;
the classification result acquisition module is used for inputting the protein image to be classified into a protein classification model trained in advance to obtain a classification result output by the protein classification model;
and the image category determining module is used for determining the category of the original protein image according to the classification result.
10. A computer device, the device comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the protein image classification method of any one of claims 1-8.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method for protein image classification according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010030899.7A CN111242922A (en) | 2020-01-13 | 2020-01-13 | Protein image classification method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010030899.7A CN111242922A (en) | 2020-01-13 | 2020-01-13 | Protein image classification method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111242922A true CN111242922A (en) | 2020-06-05 |
Family
ID=70864105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010030899.7A Pending CN111242922A (en) | 2020-01-13 | 2020-01-13 | Protein image classification method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111242922A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270727A (en) * | 2020-10-23 | 2021-01-26 | 内蒙古民族大学 | Method for drawing strain protein image based on AI technology |
| CN112397138A (en) * | 2020-09-21 | 2021-02-23 | 内蒙古民族大学 | AI technology-based method for drawing strain protein two-dimensional spectrum |
| WO2022178949A1 (en) * | 2021-02-26 | 2022-09-01 | 平安科技（深圳）有限公司 | Semantic segmentation method and apparatus for electron microtomography data, device, and medium |
| WO2023108412A1 (en) * | 2021-12-14 | 2023-06-22 | 深圳先进技术研究院 | Rapid recognition and quantification method for target protein |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1205742A2 (en) * | 2000-09-29 | 2002-05-15 | Deutsches Krebsforschungszentrum | Automated classification of cellular structures |
| CN109740560A (en) * | 2019-01-11 | 2019-05-10 | 济南浪潮高新科技投资发展有限公司 | Human cellular protein automatic identifying method and system based on convolutional neural networks |
-
2020
- 2020-01-13 CN CN202010030899.7A patent/CN111242922A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1205742A2 (en) * | 2000-09-29 | 2002-05-15 | Deutsches Krebsforschungszentrum | Automated classification of cellular structures |
| CN109740560A (en) * | 2019-01-11 | 2019-05-10 | 济南浪潮高新科技投资发展有限公司 | Human cellular protein automatic identifying method and system based on convolutional neural networks |
Non-Patent Citations (2)
| Title |
|---|
| SHAO XIANG ET AL.: "AMC-Net: Asymmetric and multi-scale convolutional neural network for multi-label HPA classification", 《COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE》 * |
| 张康康: "HPAIC人类蛋白质图谱分类挑战赛金牌经验分享", 《雷锋网》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112397138A (en) * | 2020-09-21 | 2021-02-23 | 内蒙古民族大学 | AI technology-based method for drawing strain protein two-dimensional spectrum |
| CN112397138B (en) * | 2020-09-21 | 2024-02-13 | 闽南师范大学 | Method for drawing two-dimensional spectrum of strain protein based on AI technology |
| CN112270727A (en) * | 2020-10-23 | 2021-01-26 | 内蒙古民族大学 | Method for drawing strain protein image based on AI technology |
| CN112270727B (en) * | 2020-10-23 | 2022-09-23 | 内蒙古民族大学 | Method for drawing strain protein image based on AI technology |
| WO2022178949A1 (en) * | 2021-02-26 | 2022-09-01 | 平安科技（深圳）有限公司 | Semantic segmentation method and apparatus for electron microtomography data, device, and medium |
| WO2023108412A1 (en) * | 2021-12-14 | 2023-06-22 | 深圳先进技术研究院 | Rapid recognition and quantification method for target protein |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111242922A (en) | Protein image classification method, device, equipment and medium | |
| CN112151179B (en) | Image data evaluation method, device, equipment and storage medium | |
| CN110020144B (en) | Recommendation model building method and equipment, storage medium and server thereof | |
| CN112613569A (en) | Image recognition method, and training method and device of image classification model | |
| CN110659601A (en) | Depth full convolution network remote sensing image dense vehicle detection method based on central point | |
| CN113052295A (en) | Neural network training method, object detection method, device and equipment | |
| CN113420768A (en) | Core category determination method and device, electronic equipment and storage medium | |
| CN116823793A (en) | Device defect detection method, device, electronic device and readable storage medium | |
| CN111161884A (en) | Disease prediction method, device, equipment and medium for unbalanced data | |
| CN111124863A (en) | Intelligent equipment performance testing method and device and intelligent equipment | |
| CN112861867A (en) | Pointer type instrument panel identification method, system and storage medium | |
| CN115527083B (en) | Image annotation method and device and electronic equipment | |
| CN116964588A (en) | Target detection method, target detection model training method and device | |
| CN114219804B (en) | Small sample tooth detection method based on prototype segmentation network and storage medium | |
| CN116415020A (en) | Image retrieval method, device, electronic equipment and storage medium | |
| CN115984640A (en) | Target detection method, system and storage medium based on combined distillation technology | |
| US11842165B2 (en) | Context-based image tag translation | |
| CN112287144B (en) | Picture retrieval method, equipment and storage medium | |
| CN114972530A (en) | Method, device and equipment for calibrating camera based on virtual scene and storage medium | |
| CN114067164A (en) | Method and device for detecting embryo development stage, electronic equipment and storage medium | |
| CN114723683A (en) | Head and neck artery blood vessel segmentation method and device, electronic device and storage medium | |
| CN114186090A (en) | Intelligent quality inspection method and system for image annotation data | |
| CN111125272B (en) | Regional characteristic acquisition method, regional characteristic acquisition device, computer equipment and medium | |
| CN113869144A (en) | Target detection method, target detection device, electronic equipment and computer-readable storage medium | |
| CN111753625B (en) | Pedestrian detection method, device, equipment 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200605 |