CN115440314B - Agarose gel electrophoresis performance detection method and related equipment - Google Patents
Agarose gel electrophoresis performance detection method and related equipment Download PDFInfo
- Publication number
- CN115440314B CN115440314B CN202211083432.4A CN202211083432A CN115440314B CN 115440314 B CN115440314 B CN 115440314B CN 202211083432 A CN202211083432 A CN 202211083432A CN 115440314 B CN115440314 B CN 115440314B
- Authority
- CN
- China
- Prior art keywords
- target
- molecules
- spatial
- electrophoresis
- various types
- 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
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
Abstract
The embodiment of the invention provides an electrophoresis performance detection method of agarose gel, which comprises the following steps: acquiring an electrophoresis image sequence of agarose gel under a target sample; based on the electrophoresis image sequence, extracting the space-time distribution characteristics of various types of molecules in the target sample; and detecting the electrophoresis performance of the agarose gel based on the space-time distribution characteristics of various types of molecules in the target test sample. The space-time distribution characteristics of various types of molecules in the target sample are extracted through the electrophoresis image sequence of the agarose gel under the target sample, the electrophoresis performance of the agarose gel is detected based on the space-time distribution characteristics of various types of molecules in the target sample, and the electrophoresis performance of the agarose gel can be detected according to the space-time dimension, so that the electrophoresis performance detection efficiency and accuracy of the agarose gel are improved.
Description
Technical Field
The invention relates to the technical field of biological detection, in particular to an electrophoresis performance detection method of agarose gel and related equipment.
Background
Agarose gel is a gel prepared by taking agarose as a supporting medium, the melting point of the agarose is between 62 and 65 ℃, the agarose gel can maintain the liquid state for several hours at 37 ℃ after being melted, and the agarose gel is solidified into gel at 30 ℃. Agarose gel has a large pore size, and is therefore often used for separation and detection of biomolecules such as macromolecular proteins and DNA. The electrophoresis water area refers to a method that a charged test substance (such as protein, nucleotide and other generation molecules) is subjected to electrophoresis in an inert support medium (such as paper, cellulose acetate, agarose gel, polyacrylamide gel and the like) at respective speeds towards the corresponding electrode directions under the action of an electric field, so that components are separated into narrow zones, and the electrophoresis zone map of the components is recorded or the percentage content of the components is calculated. Agarose is chain polysaccharide prepared by separating agar, and a plurality of agarose are mutually coiled to form rope agarose bundles according to the action of hydrogen bond and other forces, so as to form large-mesh gel. Agarose gels are not themselves charged, and therefore, agarose gels are useful for the separation, identification and purification of immune complexes, nucleic acids and nucleoproteins. However, agarose is mutually coiled to form a rope-shaped agarose bundle by virtue of hydrogen bonds and other forces, so that the formation process is complex, quality difference cannot be avoided in the agarose gel production process, the factory quality of the agarose gel is affected, the concentration of agarose in the agarose gel is only controlled and detected by the existing agarose gel, and the whole electrophoresis performance of the agarose gel cannot be measured.
Disclosure of Invention
The embodiment of the invention provides a method for detecting the electrophoresis performance of agarose gel, which aims to solve the problem that the electrophoresis performance of agarose gel cannot be detected, extracts the space-time distribution characteristics of various types of molecules in a target sample to be detected through an electrophoresis image sequence of agarose gel under the target sample to be detected, detects the electrophoresis performance of agarose gel based on the space-time distribution characteristics of various types of molecules in the target sample to be detected, and can detect the electrophoresis performance of agarose gel according to the space-time dimension, thereby improving the electrophoresis performance detection efficiency and accuracy of agarose gel.
In a first aspect, an embodiment of the present invention provides a method for detecting electrophoresis performance of agarose gel, the method comprising the steps of:
acquiring an electrophoresis image sequence of agarose gel under a target sample;
based on the electrophoresis image sequence, extracting the space-time distribution characteristics of various types of molecules in the target sample;
and detecting the electrophoresis performance of the agarose gel based on the space-time distribution characteristics of various types of molecules in the target test sample.
Optionally, the extracting the space-time distribution characteristics of each type of molecule in the target sample based on the electrophoresis image sequence includes:
And extracting spatial characteristics of each electrophoresis image in the electrophoresis image sequence according to the time sequence of the electrophoresis image sequence to obtain the spatial-temporal distribution characteristics of various types of molecules in the target sample.
Optionally, the extracting spatial features of each electrophoresis image in the electrophoresis image sequence according to the time sequence of the electrophoresis image sequence to obtain the spatial-temporal distribution features of various types of molecules in the target sample, including:
performing target detection on each electrophoresis image in the electrophoresis image sequence according to the time sequence of the electrophoresis image sequence to obtain a target detection frame, and obtaining first spatial characteristics of various types of molecules in the target sample based on the target detection frame;
extracting a target area from the corresponding electrophoresis image according to the target detection frame, and performing semantic segmentation on the target area to obtain second spatial features of various types of molecules in the target sample;
and carrying out first feature fusion on the first spatial features of the various types of molecules in the target sample and the second spatial features of the various types of molecules in the target sample according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution features of the various types of molecules in the target sample.
Optionally, extracting a target area from the corresponding electrophoresis image according to the target detection frame, and performing semantic segmentation on the target area to obtain a second spatial feature, where the method includes:
expanding the target area in a preset direction to obtain a first expansion area;
performing first semantic segmentation on the first expansion region to obtain first semantic segmentation features;
combining the first expansion areas in the preset direction to obtain a second expansion area;
performing second semantic segmentation on the second expansion region to obtain second semantic segmentation features;
and carrying out second feature fusion on the first semantic segmentation feature and the second semantic segmentation feature to obtain the second spatial feature.
Optionally, the first feature fusion is performed on the first spatial feature of each type of molecule in the target sample to be tested and the second spatial feature of each type of molecule in the target sample to be tested according to the time sequence of the electrophoresis image sequence, so as to obtain the space-time distribution feature of each type of molecule in the target sample to be tested, including:
splicing the first spatial characteristics of various types of molecules in the target sample in each electrophoresis image with the second spatial characteristics of various types of molecules in the target sample to obtain spatial splicing characteristics of each electrophoresis image;
And carrying out channel fusion on the space splicing characteristic of each electrophoresis image according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution characteristic of various molecules in the target sample.
Optionally, the first spatial feature of each type of molecule in the target sample to be tested includes a first position feature, the second spatial feature of each type of molecule in the target sample to be tested includes a second position feature, and the stitching the first spatial feature of each type of molecule in the target sample to be tested in each electrophoresis image with the second spatial feature of each type of molecule in the target sample to be tested to obtain a spatial stitching feature of each electrophoresis image includes:
calculating a characteristic distance between a first spatial characteristic of each type of molecule in the target test sample and a second spatial characteristic of each type of molecule in the target test sample according to the first position characteristic and the second position characteristic;
and according to the characteristic distance, splicing the first spatial characteristics of various types of molecules in the target sample to be tested in each electrophoresis image with the second spatial characteristics of various types of molecules in the target sample to be tested to obtain the spatial splicing characteristics of each electrophoresis image.
Optionally, the detecting the electrophoresis performance of the agarose gel based on the space-time distribution characteristics of various types of molecules in the target test sample comprises:
according to the space-time distribution characteristics of various types of molecules in the target test sample, calculating electrophoresis migration information of various types of molecules in the target test sample;
and detecting the electrophoresis performance of the agarose gel according to electrophoresis migration information of various types of molecules in the target sample to be tested.
In a second aspect, an embodiment of the present invention provides an apparatus for detecting electrophoresis performance of agarose gel, the apparatus comprising:
the acquisition module is used for acquiring an electrophoresis image sequence of the agarose gel under the target sample;
the extraction module is used for extracting the space-time distribution characteristics of various types of molecules in the target sample for test based on the electrophoresis image sequence;
and the detection module is used for detecting the electrophoresis performance of the agarose gel based on the space-time distribution characteristics of various types of molecules in the target sample to be tested.
In a third aspect, an embodiment of the present invention provides an electronic device, including: the method comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the steps in the method for detecting the electrophoresis performance of agarose gel provided by the embodiment of the invention are realized when the processor executes the computer program.
In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the method for detecting the electrophoresis performance of agarose gel provided in the embodiment of the present invention.
In the embodiment of the invention, an electrophoresis image sequence of agarose gel under a target sample for sample feeding is obtained; based on the electrophoresis image sequence, extracting the space-time distribution characteristics of various types of molecules in the target sample; and detecting the electrophoresis performance of the agarose gel based on the space-time distribution characteristics of various types of molecules in the target test sample. The space-time distribution characteristics of various types of molecules in the target sample are extracted through the electrophoresis image sequence of the agarose gel under the target sample, the electrophoresis performance of the agarose gel is detected based on the space-time distribution characteristics of various types of molecules in the target sample, and the electrophoresis performance of the agarose gel can be detected according to the space-time dimension, so that the electrophoresis performance detection efficiency and accuracy of the agarose gel are improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for detecting the electrophoresis performance of agarose gel according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an apparatus for detecting electrophoresis performance of agarose gel according to the embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, fig. 1 is a flowchart of a method for detecting electrophoresis performance of agarose gel according to an embodiment of the invention, as shown in fig. 1, the method includes the following steps:
101. a sequence of electrophoretic images of agarose gel under a target sample is obtained.
In the embodiment of the present invention, the agarose gel may be a sample extracted from a finished agarose gel without leaving the factory, and the target sample may be any biomolecule mixture (such as immune complex, a biomolecule mixture of nucleic acid and protein, etc.) capable of electrophoresis on the agarose gel.
And (3) carrying out an electrophoresis test on the target sample to be tested on agarose gel, and continuously shooting the electrophoresis test to obtain an electrophoresis image sequence. Specifically, the sample to be tested can be spotted and electrophoresed on agarose gel according to standard electrophoresis steps, and in the electrophoresis process, the electrophoresis process is continuously shot through ultraviolet irradiation, so as to obtain an electrophoresis image sequence.
In the above-mentioned electrophoresis image sequence, each electrophoresis image corresponds to one photographing time, and the electrophoresis images in the current image sequence are arranged according to the order of photographing time.
102. Based on the electrophoresis image sequence, extracting the space-time distribution characteristics of various types of molecules in the target sample.
In the embodiment of the invention, each electrophoresis image corresponds to the spatial distribution state of various types of molecules in the target sample, and the electrophoresis image sequence corresponds to the continuous spatial distribution state change in time of various types of molecules in the target sample. Because the sizes of different types of molecules are different, the migration rates of the different types of molecules on agarose gel in the electrophoresis process are different, the different types of molecules can be separated along with the increase of electrophoresis time, and the different types of molecules are distributed in the form of bands at different positions. Under the action of the indicator, the obtained electrophoresis image sequence can display the banded distribution of different types of molecules through ultraviolet light irradiation. The above-mentioned various types of molecules can be immune complex, nucleic acid and protein, etc.
And extracting the characteristics of the electrophoresis image sequence through a trained characteristic extraction model, and extracting the space-time distribution characteristics of various types of molecules in the target sample to be tested. Specifically, the electrophoresis images in the electrophoresis image sequence can be sequentially input into the feature extraction model according to the sequence of shooting time, so that the space-time distribution features of various types of molecules in the target sample can be extracted.
Specifically, the feature extraction model extracts a strip feature under the action of an indicator, specifically, the feature extraction model can be constructed based on a deep convolution network, and specifically, the feature extraction model can be constructed based on a YOLO-V series network. And performing supervised training on the feature extraction model through a sample data set to obtain a trained feature extraction model, wherein the sample data set comprises a sample image and corresponding labels, the sample image comprises banded distribution under the action of an indicator, and the labels are labels on the banded distribution under the action of the indicator in the sample image. The banded distribution characteristics in the electrophoresis image can be extracted as the space distribution characteristics through the trained characteristic extraction model, and the space distribution characteristics with time sequence attributes, namely the space distribution attributes, can be obtained through the characteristic extraction of the electrophoresis image sequence through the trained characteristic extraction model. The spatial distribution characteristics of various types of molecules in the target sample can represent the spatial distribution state of various types of molecules in the target sample; the spatial-temporal distribution characteristics of the various types of molecules in the target test sample can represent the spatially-continuous changes in the spatial distribution state of the various types of molecules in the target test sample.
103. The electrophoresis performance of agarose gel is detected based on the space-time distribution characteristics of various types of molecules in the target sample.
In the embodiment of the invention, the space-time distribution characteristics of the various types of molecules in the target sample can represent the time-continuous space distribution state change of the various types of molecules in the target sample, and whether the electrophoresis performance of the agarose gel meets the factory requirement can be detected through the time-continuous space distribution state change of the various types of molecules in the target sample. For example, the migration rate and the dispersity of each type of molecule in the target sample can be calculated according to the change of the time-continuous spatial distribution state of each type of molecule in the target sample to judge whether the migration rate and the dispersity meet the delivery requirements. The electrophoresis performance of the agarose gel can be regarded as qualified in detection when meeting the factory requirements, and the electrophoresis performance of the agarose gel can be regarded as unqualified in detection when not meeting the factory requirements.
In the embodiment of the invention, an electrophoresis image sequence of agarose gel under a target sample for sample feeding is obtained; based on the electrophoresis image sequence, extracting the space-time distribution characteristics of various types of molecules in the target sample; and detecting the electrophoresis performance of the agarose gel based on the space-time distribution characteristics of various types of molecules in the target test sample. The space-time distribution characteristics of various types of molecules in the target sample are extracted through the electrophoresis image sequence of the agarose gel under the target sample, the electrophoresis performance of the agarose gel is detected based on the space-time distribution characteristics of various types of molecules in the target sample, and the electrophoresis performance of the agarose gel can be detected according to the space-time dimension, so that the electrophoresis performance detection efficiency and accuracy of the agarose gel are improved.
Optionally, in the step of extracting the space-time distribution characteristics of the various types of molecules in the target sample based on the electrophoresis image sequence, the space-time distribution characteristics of the various types of molecules in the target sample may be obtained by extracting the space characteristics of each electrophoresis image in the electrophoresis image sequence according to the time sequence of the electrophoresis image sequence.
In the embodiment of the present invention, in the above-mentioned sequence of electrophoretic images, each electrophoretic image corresponds to one photographing time, the electrophoretic images in the current image sequence are arranged according to the order of the photographing time, and the time sequence of the sequence of electrophoretic images is the order of the photographing time.
Specifically, extracting spatial features of each electrophoresis image to obtain spatial features a of various molecules in each electrophoresis image m Wherein m represents a molecule of the mth type. Spatial characteristics a of various types of molecules in target test samples according to each electrophoresis image m Obtaining the space-time distribution characteristics a of various types of molecules in the target test sample of all the electrophoresis images n,m N represents an nth Zhang Dianyong image in which the imaging times are sequentially ordered.
Feature extraction can be carried out on each electrophoresis image of the electrophoresis image sequence through a trained feature extraction model, so that the space-time distribution feature a of various molecules in the target sample can be extracted n,m . Specifically, the electrophoresis images in the electrophoresis image sequence can be sequentially input into the feature extraction model according to the sequence of shooting time, so as to extract the space-time distribution feature a of various molecules in the target sample n,m 。
Optionally, in the step of extracting spatial features of each electrophoretic image in the sequence of electrophoretic images according to the time sequence of the sequence of electrophoretic images to obtain spatial-temporal distribution features of various types of molecules in the target sample, the target detection may be performed on each electrophoretic image in the sequence of electrophoretic images according to the time sequence of the sequence of electrophoretic images to obtain a target detection frame, and the first spatial features of various types of molecules in the target sample may be obtained based on the target detection frame; extracting a target area from the corresponding electrophoresis image according to the target detection frame, and performing semantic segmentation on the target area to obtain second spatial features of various types of molecules in the target sample; and carrying out first feature fusion on the first spatial features of the various types of molecules in the target sample and the second spatial features of the various types of molecules in the target sample according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution features of the various types of molecules in the target sample.
In the embodiment of the invention, the target detection algorithm can be used for detecting each electrophoresis image in the electrophoresis image sequence according to the time sequence of the electrophoresis image sequence, the detection of the target detection algorithm is a fluorescent target under the action of an indicator, and the target detection frame is represented by (x, y, w, h and delta), wherein (x, y) represents the position of the center point of the target detection frame in the electrophoresis image, w represents the width of the target detection frame, h represents the height of the target detection frame and the confidence of the delta target detection frame. The first spatial characteristics of the various types of molecules in the target sample in each of the electrophoresis images can be obtained by expressing the first spatial characteristics of the various types of molecules in the target sample in the (x, y, w, h, δ) above.
Extracting a target region from the corresponding electrophoresis image according to the target detection frame, segmenting the target region by adopting a semantic segmentation algorithm to obtain a background region and a foreground region, wherein the foreground region is a fluorescent region, and the geometric center and the area of the fluorescent region are used as second spatial features to obtain second spatial features of various types of molecules in the target sample to be tested in each electrophoresis image.
And correlating the first spatial feature with the second spatial feature through the target detection frame to obtain a pair of the first spatial feature and the second spatial feature, and performing first feature fusion on the pair of the first spatial feature and the second spatial feature according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution feature of various molecules in the target sample. The first feature fusion can be channel fusion, namely, the first spatial feature and the second spatial feature of various types of molecules in the target sample in each electrophoresis image are used as a channel, and the channels corresponding to each electrophoresis image are channel fused according to the time sequence of the electrophoresis image sequence, so that the space-time distribution feature of various types of molecules in the target sample in the electrophoresis image sequence is obtained.
Optionally, in the step of extracting the target area from the corresponding electrophoresis image according to the target detection frame and performing semantic segmentation on the target area to obtain the second spatial feature, the target area may be expanded in a preset direction to obtain a first expansion area; performing first semantic segmentation on the first expansion region to obtain first semantic segmentation features; combining the first expansion areas in a preset direction to obtain a second expansion area; performing second semantic segmentation on the second expansion region to obtain second semantic segmentation features; and carrying out second feature fusion on the first semantic segmentation feature and the second semantic segmentation feature to obtain a second spatial feature.
In the embodiment of the invention, as the target detection has a certain error rate, when the target area is subjected to semantic segmentation, the target area can be expanded in the preset direction, so that more image information is acquired during the semantic segmentation, and the accuracy of the semantic segmentation is improved. The preset direction is the parallel direction of the sample application line.
Specifically, the first extension region has more image information than the target region, and the first semantic segmentation may be a single-target semantic segmentation. By performing first semantic segmentation on the first extension region, first semantic segmentation features of each type of molecule can be obtained, wherein the first semantic segmentation features represent local spatial distribution of each type of molecule.
The second extension area is obtained by combining the first extension areas in the preset direction on the basis of the first extension area, the second semantic segmentation can be multi-target semantic segmentation, and the second extension area can comprise target areas corresponding to a plurality of target detection frames, so that the sample application lines have intervals due to the fact that the same type of molecules possibly have a broken belt condition in the electrophoresis process or the sample application lines are formed by loading samples through spaced sample application holes. By combining the first extension regions in the preset direction, the fluorescent regions of the same type of molecules can be combined, which corresponds to the global distribution of one type of molecules. And obtaining second semantic segmentation features of each type of molecule by carrying out second semantic segmentation on the second expansion region, wherein the second semantic segmentation features represent global spatial distribution of each type of molecule.
And carrying out second feature fusion on the first semantic segmentation features and the second semantic segmentation features to obtain second spatial features, so that the second spatial features of each type of molecules have global semantics and local semantics. The second feature fusion may be feature stitching, and stitching the first semantic segmentation feature and the second semantic segmentation feature to obtain a second spatial feature.
Optionally, in the step of performing first feature fusion on the first spatial features of the various types of molecules in the target sample to be tested and the second spatial features of the various types of molecules in the target sample to be tested according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution features of the various types of molecules in the target sample to be tested, the first spatial features of the various types of molecules in the target sample to be tested in each electrophoresis image and the second spatial features of the various types of molecules in the target sample to be tested can be spliced to obtain the spatial splicing features of each electrophoresis image; and carrying out channel fusion on the space splicing characteristic of each electrophoresis image according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution characteristic of various molecules in the target sample.
In the embodiment of the invention, the first spatial features of various types of molecules in the target test sample are represented by the (x, y, w, h, delta), and the first spatial features and the second spatial features are spliced in pairs by taking the geometric center (i, j) and the area S of the fluorescent region as the second spatial features, so that the spatial splicing features (x, y, w, h, delta, i, j, S) can be obtained m 。
In one possible embodiment, i=λ as described above 1 i 0 +λ 2 i 1 ，j＝λ 1 j 0 +λ 2 j 1 Wherein (i) 0 ，j 0 ) Representing the average geometric center of fluorescence regions in a plurality of first semantically segmented features corresponding to the same type of molecule, (i) 1 ，j 1 ) Representing the geometric center of the fluorescence region in the second semantic segmentation feature. Lambda as above 1 And lambda (lambda) 2 Represents the weight coefficient, lambda 1 ＝S/wh，λ 2 ＝1－λ 1 . S denotes the area of the fluorescence region in the second semantic segmentation feature.
Features (x, y, w, h, delta, i, j, S) of spatial stitching m Channel fusion is carried out according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution characteristics (x, y, w, h, delta, i, j, S) of various types of molecules in the target sample n,m 。
Optionally, the first spatial feature of each type of molecule in the target sample includes a first position feature, the second spatial feature of each type of molecule in the target sample includes a second position feature, and in the step of stitching the first spatial feature of each type of molecule in the target sample in each electrophoresis image with the second spatial feature of each type of molecule in the target sample to obtain a spatial stitching feature of each electrophoresis image, a feature distance between the first spatial feature of each type of molecule in the target sample and the second spatial feature of each type of molecule in the target sample may be calculated according to the first position feature and the second position feature; and according to the characteristic distance, splicing the first spatial characteristics of various types of molecules in the target sample-supplying object in each electrophoresis image with the second spatial characteristics of various types of molecules in the target sample-supplying object to obtain the spatial splicing characteristics of each electrophoresis image.
In the embodiment of the invention, the first position feature is (x, y), the second position feature is (i, j), the feature distance d between (x, y) and (i, j) is calculated, the feature distance d between the first position feature and the second position feature is smaller for the same type of molecule, and in each electrophoresis image, the first space feature with smaller feature distance d and the second space feature are spliced, so that the space splicing features of the same type of molecule and the space splicing features of different types of molecules are sequenced according to the size of the molecule to obtain the space splicing features (x, y, w, h, delta, i, j, S) of each electrophoresis image m 。
Optionally, in the step of detecting the electrophoresis performance of the agarose gel based on the space-time distribution characteristics of the various types of molecules in the target sample, electrophoresis migration information of the various types of molecules in the target sample can be calculated according to the space-time distribution characteristics of the various types of molecules in the target sample; and detecting the electrophoresis performance of the agarose gel according to electrophoresis migration information of various types of molecules in the target sample to be tested.
In the embodiment of the present invention, the electrophoresis migration information may include migration rate and dispersity of each type of molecule, and may be based on the space-time distribution characteristics (x, y, w, h, δ, i, j, S) n,m (x, y, delta, i, j) m The migration rate of each type of molecule is calculated, specifically, the migration rate of each type of molecule is shown in the following formula:
the Vm represents the migration rate of the mth type of molecules, N represents the number of electrophoretic images in the sequence of electrophoretic images, and T represents the time length of the sequence of electrophoretic images.
Can be based on the space-time distribution characteristics (x, y, w, h, delta, i, j, S) n,m (w, h, delta, S) m The dispersity of each type of molecule is calculated, specifically, the dispersity of each type of molecule is shown in the following formula:
the above-mentioned phi m represents the dispersity of the m-th type of molecules, and U represents the area of the electrophoretic image.
The migration rate and the dispersity of the various types of molecules in the target sample can be calculated according to the time-continuous spatial distribution state change of the various types of molecules in the target sample so as to judge whether the migration rate and the dispersity meet the delivery requirements. The electrophoresis performance of the agarose gel can be regarded as qualified in detection when meeting the factory requirements, and the electrophoresis performance of the agarose gel can be regarded as unqualified in detection when not meeting the factory requirements.
It should be noted that the method for detecting the electrophoresis performance of agarose gel provided by the embodiment of the invention can be applied to devices such as smart phones, computers, servers and the like.
Optionally, referring to fig. 2, fig. 2 is a schematic structural diagram of an apparatus for detecting electrophoresis performance of agarose gel according to the embodiment of the present invention, as shown in fig. 2, the apparatus includes:
an acquisition module 201, configured to acquire an electrophoresis image sequence of agarose gel under a target sample;
an extraction module 202, configured to extract spatial-temporal distribution characteristics of various types of molecules in the target sample for sample based on the electrophoresis image sequence;
and the detection module 203 is used for detecting the electrophoresis performance of the agarose gel based on the space-time distribution characteristics of various types of molecules in the target test sample.
Optionally, the extracting module 202 is further configured to extract spatial features of each electrophoresis image in the electrophoresis image sequence according to the time sequence of the electrophoresis image sequence, so as to obtain spatial-temporal distribution features of each type of molecule in the target sample.
Optionally, the extracting module 202 is further configured to perform target detection on each of the electrophoresis images in the electrophoresis image sequence according to the time sequence of the electrophoresis image sequence, obtain a target detection frame, and obtain first spatial features of each type of molecules in the target sample based on the target detection frame; extracting a target area from the corresponding electrophoresis image according to the target detection frame, and performing semantic segmentation on the target area to obtain second spatial features of various types of molecules in the target sample; and carrying out first feature fusion on the first spatial features of the various types of molecules in the target sample and the second spatial features of the various types of molecules in the target sample according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution features of the various types of molecules in the target sample.
Optionally, the extracting module 202 is further configured to expand the target area in a preset direction to obtain a first expanded area; performing first semantic segmentation on the first expansion region to obtain first semantic segmentation features; combining the first expansion areas in the preset direction to obtain a second expansion area; performing second semantic segmentation on the second expansion region to obtain second semantic segmentation features; and carrying out second feature fusion on the first semantic segmentation feature and the second semantic segmentation feature to obtain the second spatial feature.
Optionally, the extracting module 202 is further configured to splice a first spatial feature of each type of molecule in the target sample to be tested in each of the electrophoresis images with a second spatial feature of each type of molecule in the target sample to be tested, so as to obtain a spatial splice feature of each of the electrophoresis images; and carrying out channel fusion on the space splicing characteristic of each electrophoresis image according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution characteristic of various molecules in the target sample.
Optionally, the first spatial feature of each type of molecule in the target sample includes a first position feature, the second spatial feature of each type of molecule in the target sample includes a second position feature, and the extraction module 202 is further configured to calculate a feature distance between the first spatial feature of each type of molecule in the target sample and the second spatial feature of each type of molecule in the target sample according to the first position feature and the second position feature; and according to the characteristic distance, splicing the first spatial characteristics of various types of molecules in the target sample to be tested in each electrophoresis image with the second spatial characteristics of various types of molecules in the target sample to be tested to obtain the spatial splicing characteristics of each electrophoresis image.
Optionally, the detection module 203 is further configured to calculate electrophoresis migration information of each type of molecule in the target test sample according to the spatial-temporal distribution characteristics of each type of molecule in the target test sample; and detecting the electrophoresis performance of the agarose gel according to electrophoresis migration information of various types of molecules in the target sample to be tested.
It should be noted that, the behavior detection device provided by the embodiment of the invention can be applied to devices such as a smart phone, a computer, a server and the like which can detect the electrophoresis performance of agarose gel.
The behavior detection device provided by the embodiment of the invention can realize each process realized by the agarose gel electrophoresis performance detection method in the method embodiment, and can achieve the same beneficial effects. In order to avoid repetition, a description thereof is omitted.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 3, including: a memory 302, a processor 301, and a computer program stored on the memory 302 and executable on the processor 3401 for a method of detecting the electrophoretic performance of an agarose gel, wherein:
the processor 301 is configured to call a computer program stored in the memory 302, and perform the following steps:
Acquiring an electrophoresis image sequence of agarose gel under a target sample;
based on the electrophoresis image sequence, extracting the space-time distribution characteristics of various types of molecules in the target sample;
and detecting the electrophoresis performance of the agarose gel based on the space-time distribution characteristics of various types of molecules in the target test sample.
Optionally, the extracting, by the processor 301, the spatial-temporal distribution characteristics of each type of molecule in the target sample based on the sequence of electrophoresis images includes:
and extracting spatial characteristics of each electrophoresis image in the electrophoresis image sequence according to the time sequence of the electrophoresis image sequence to obtain the spatial-temporal distribution characteristics of various types of molecules in the target sample.
Optionally, the extracting spatial features of each electrophoretic image in the sequence of electrophoretic images according to the time sequence of the sequence of electrophoretic images by the processor 301 to obtain the spatial-temporal distribution features of each type of molecules in the target sample includes:
performing target detection on each electrophoresis image in the electrophoresis image sequence according to the time sequence of the electrophoresis image sequence to obtain a target detection frame, and obtaining first spatial characteristics of various types of molecules in the target sample based on the target detection frame;
Extracting a target area from the corresponding electrophoresis image according to the target detection frame, and performing semantic segmentation on the target area to obtain second spatial features of various types of molecules in the target sample;
and carrying out first feature fusion on the first spatial features of the various types of molecules in the target sample and the second spatial features of the various types of molecules in the target sample according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution features of the various types of molecules in the target sample.
Optionally, the extracting, by the processor 301, a target area from the corresponding electrophoresis image according to the target detection frame, and performing semantic segmentation on the target area to obtain a second spatial feature, where the extracting includes:
expanding the target area in a preset direction to obtain a first expansion area;
performing first semantic segmentation on the first expansion region to obtain first semantic segmentation features;
combining the first expansion areas in the preset direction to obtain a second expansion area;
performing second semantic segmentation on the second expansion region to obtain second semantic segmentation features;
and carrying out second feature fusion on the first semantic segmentation feature and the second semantic segmentation feature to obtain the second spatial feature.
Optionally, the performing, by the processor 301, the first feature fusion between the first spatial feature of each type of molecule in the target test sample and the second spatial feature of each type of molecule in the target test sample according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution feature of each type of molecule in the target test sample includes:
splicing the first spatial characteristics of various types of molecules in the target sample in each electrophoresis image with the second spatial characteristics of various types of molecules in the target sample to obtain spatial splicing characteristics of each electrophoresis image;
and carrying out channel fusion on the space splicing characteristic of each electrophoresis image according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution characteristic of various molecules in the target sample.
Optionally, the first spatial feature of each type of molecule in the target sample includes a first position feature, the second spatial feature of each type of molecule in the target sample includes a second position feature, and the stitching, performed by the processor 301, the first spatial feature of each type of molecule in the target sample in each of the electrophoresis images with the second spatial feature of each type of molecule in the target sample to obtain a spatial stitching feature of each of the electrophoresis images includes:
Calculating a characteristic distance between a first spatial characteristic of each type of molecule in the target test sample and a second spatial characteristic of each type of molecule in the target test sample according to the first position characteristic and the second position characteristic;
and according to the characteristic distance, splicing the first spatial characteristics of various types of molecules in the target sample to be tested in each electrophoresis image with the second spatial characteristics of various types of molecules in the target sample to be tested to obtain the spatial splicing characteristics of each electrophoresis image.
Optionally, the detecting the electrophoresis performance of the agarose gel based on the spatial-temporal distribution characteristics of the various types of molecules in the target test sample performed by the processor 301 includes:
according to the space-time distribution characteristics of various types of molecules in the target test sample, calculating electrophoresis migration information of various types of molecules in the target test sample;
and detecting the electrophoresis performance of the agarose gel according to electrophoresis migration information of various types of molecules in the target sample to be tested.
It should be noted that, the electronic device provided by the embodiment of the invention can be applied to devices such as a smart phone, a computer, a server and the like which can detect the electrophoresis performance of agarose gel.
The electronic equipment provided by the embodiment of the invention can realize each process realized by the agarose gel electrophoresis performance detection method in the method embodiment, and can achieve the same beneficial effects. In order to avoid repetition, a description thereof is omitted.
The embodiment of the invention also provides a computer readable storage medium, and a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the method for detecting the electrophoresis performance of the agarose gel or the method for detecting the electrophoresis performance of the agarose gel at the application end provided by the embodiment of the invention is realized, and the same technical effects can be achieved, so that repetition is avoided, and no redundant description is provided here.
Those skilled in the art will appreciate that the processes implementing all or part of the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, and the program may be stored in a computer readable storage medium, and the program may include the processes of the embodiments of the methods as above when executed. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM) or the like.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (8)
1. A method for detecting the electrophoretic properties of an agarose gel, comprising the steps of:
acquiring an electrophoresis image sequence of agarose gel under a target sample;
performing target detection on each electrophoresis image in the electrophoresis image sequence according to the time sequence of the electrophoresis image sequence to obtain a target detection frame, and obtaining first spatial characteristics of various types of molecules in the target sample based on the target detection frame;
extracting a target area from the corresponding electrophoresis image according to the target detection frame, and performing semantic segmentation on the target area to obtain second spatial features of various types of molecules in the target sample;
carrying out first feature fusion on the first spatial features of various types of molecules in the target sample to be tested and the second spatial features of various types of molecules in the target sample to be tested according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution features of various types of molecules in the target sample to be tested;
And detecting the electrophoresis performance of the agarose gel based on the space-time distribution characteristics of various types of molecules in the target test sample.
2. The method of claim 1, wherein extracting a target region from the corresponding electrophoretic image according to the target detection frame, and performing semantic segmentation on the target region to obtain a second spatial feature, includes:
expanding the target area in a preset direction to obtain a first expansion area, wherein the preset direction is the parallel direction of the sample application line;
performing first semantic segmentation on the first expansion region to obtain first semantic segmentation features, wherein each target region corresponds to one first expansion region;
combining the first expansion areas in the preset direction to obtain a second expansion area, wherein the second expansion area comprises target areas corresponding to a plurality of target detection frames and is equivalent to global distribution of one type of molecules;
performing second semantic segmentation on the second expansion region to obtain second semantic segmentation features;
and carrying out second feature fusion on the first semantic segmentation feature and the second semantic segmentation feature to obtain the second spatial feature.
3. The method of claim 1, wherein said performing a first feature fusion of a first spatial feature of each type of molecule in said target test sample with a second spatial feature of each type of molecule in said target test sample in time order of said sequence of electrophoretic images to obtain a spatiotemporal distribution feature of each type of molecule in said target test sample comprises:
splicing the first spatial characteristics of various types of molecules in the target sample in each electrophoresis image with the second spatial characteristics of various types of molecules in the target sample to obtain spatial splicing characteristics of each electrophoresis image;
and taking the space splicing characteristic of each electrophoresis image as a channel, and arranging the space splicing characteristic of each electrophoresis image according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution characteristic of various molecules in the target sample.
4. The method of claim 3, wherein the first spatial feature of each type of molecule in the target sample comprises a first position feature and the second spatial feature of each type of molecule in the target sample comprises a second position feature, and wherein the stitching the first spatial feature of each type of molecule in the target sample in each of the electrophoresis images with the second spatial feature of each type of molecule in the target sample to obtain the spatial stitching feature of each of the electrophoresis images comprises:
Calculating a characteristic distance between a first spatial characteristic of each type of molecule in the target test sample and a second spatial characteristic of each type of molecule in the target test sample according to the first position characteristic and the second position characteristic;
and according to the characteristic distance, splicing the first spatial characteristics of various types of molecules in the target sample to be tested in each electrophoresis image with the second spatial characteristics of various types of molecules in the target sample to be tested to obtain the spatial splicing characteristics of each electrophoresis image.
5. The method of any one of claims 1 to 4, wherein detecting the electrophoretic properties of the agarose gel based on the spatiotemporal distribution characteristics of the various types of molecules in the target test sample comprises:
according to the space-time distribution characteristics of various types of molecules in the target test sample, calculating electrophoresis migration information of various types of molecules in the target test sample;
and detecting the electrophoresis performance of the agarose gel according to electrophoresis migration information of various types of molecules in the target sample to be tested.
6. An apparatus for detecting the electrophoretic properties of an agarose gel, said apparatus comprising:
The acquisition module is used for acquiring an electrophoresis image sequence of the agarose gel under the target sample;
the extraction module is used for carrying out target detection on each electrophoresis image in the electrophoresis image sequence according to the time sequence of the electrophoresis image sequence to obtain a target detection frame, and obtaining first spatial characteristics of various types of molecules in the target sample based on the target detection frame; extracting a target area from the corresponding electrophoresis image according to the target detection frame, and performing semantic segmentation on the target area to obtain second spatial features of various types of molecules in the target sample; carrying out first feature fusion on the first spatial features of various types of molecules in the target sample to be tested and the second spatial features of various types of molecules in the target sample to be tested according to the time sequence of the electrophoresis image sequence to obtain the space-time distribution features of various types of molecules in the target sample to be tested;
and the detection module is used for detecting the electrophoresis performance of the agarose gel based on the space-time distribution characteristics of various types of molecules in the target sample to be tested.
7. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the method for detecting the electrophoretic performance of an agarose gel according to any one of claims 1 to 5 when the computer program is executed.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps in the method for detecting the electrophoretic performance of an agarose gel according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211083432.4A CN115440314B (en) | 2022-09-06 | 2022-09-06 | Agarose gel electrophoresis performance detection method and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211083432.4A CN115440314B (en) | 2022-09-06 | 2022-09-06 | Agarose gel electrophoresis performance detection method and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115440314A CN115440314A (en) | 2022-12-06 |
| CN115440314B true CN115440314B (en) | 2023-08-15 |
Family
ID=84247566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211083432.4A Active CN115440314B (en) | 2022-09-06 | 2022-09-06 | Agarose gel electrophoresis performance detection method and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115440314B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4920498A (en) * | 1985-08-17 | 1990-04-24 | Olympus Optical Co., Ltd. | Method of processing and analyzing electrophoretic image, and method of displaying electrophoregram and a medium for recording electrophoregram |
| JP2005147845A (en) * | 2003-11-14 | 2005-06-09 | Toppan Printing Co Ltd | New electrophoretic analysis method, electrophoretic analyzer for performing method, and optically transparent base material used therefor |
| CN101535800A (en) * | 2006-08-29 | 2009-09-16 | 贝克顿迪肯森公司 | Method and apparatus for carrier-free deflection electrophoresis |
| CN101671731A (en) * | 2009-08-05 | 2010-03-17 | 邹桂花 | Simple, rapid and efficient agarose gel electrophoresis method for detecting plant molecular marker |
| CN102656448A (en) * | 2009-08-24 | 2012-09-05 | 生命技术公司 | Gel electrophoresis, imaging, and analysis methods, devices, systems, and materials |
| CN105624314A (en) * | 2016-03-16 | 2016-06-01 | 西北农林科技大学 | Method for detecting goat TMEM95 gene subtle copy number variation through PCR technology and application thereof |
| CN110009008A (en) * | 2019-03-18 | 2019-07-12 | 四川大学 | The method that immunofixation electrophoresis figure feature based on extraction classifies automatically to it |
| CN110741250A (en) * | 2017-06-13 | 2020-01-31 | 基因微器件有限公司 | Electrophoresis method with electric field change |
| CN111260691A (en) * | 2020-01-18 | 2020-06-09 | 温州大学 | Spatio-temporal canonical correlation filtering tracking method based on context-aware regression |
| CN113674839A (en) * | 2021-07-22 | 2021-11-19 | 清华大学 | Combined detection system for noninvasive imaging screening and minimally invasive sampling nucleic acid typing |
| CN113869367A (en) * | 2021-08-26 | 2021-12-31 | 北京旷视科技有限公司 | Model capability detection method and device, electronic equipment and computer readable medium |
| CN114360639A (en) * | 2022-01-11 | 2022-04-15 | 平安科技（深圳）有限公司 | Artificial intelligence-based method and device for determining action relationship of drug target |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018112349A1 (en) * | 2016-12-15 | 2018-06-21 | University Of Cincinnati | Simplified method for size-purification of small oligonucleotides via gel electrophoresis |
| WO2018183971A1 (en) * | 2017-04-01 | 2018-10-04 | Massachusetts Institute Of Technology | Systems and methods for manufacturing biologically-produced products |
| WO2019092269A1 (en) * | 2017-11-13 | 2019-05-16 | F. Hoffmann-La Roche Ag | Devices for sample analysis using epitachophoresis |
-
2022
- 2022-09-06 CN CN202211083432.4A patent/CN115440314B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4920498A (en) * | 1985-08-17 | 1990-04-24 | Olympus Optical Co., Ltd. | Method of processing and analyzing electrophoretic image, and method of displaying electrophoregram and a medium for recording electrophoregram |
| JP2005147845A (en) * | 2003-11-14 | 2005-06-09 | Toppan Printing Co Ltd | New electrophoretic analysis method, electrophoretic analyzer for performing method, and optically transparent base material used therefor |
| CN101535800A (en) * | 2006-08-29 | 2009-09-16 | 贝克顿迪肯森公司 | Method and apparatus for carrier-free deflection electrophoresis |
| CN101671731A (en) * | 2009-08-05 | 2010-03-17 | 邹桂花 | Simple, rapid and efficient agarose gel electrophoresis method for detecting plant molecular marker |
| CN102656448A (en) * | 2009-08-24 | 2012-09-05 | 生命技术公司 | Gel electrophoresis, imaging, and analysis methods, devices, systems, and materials |
| CN105624314A (en) * | 2016-03-16 | 2016-06-01 | 西北农林科技大学 | Method for detecting goat TMEM95 gene subtle copy number variation through PCR technology and application thereof |
| CN110741250A (en) * | 2017-06-13 | 2020-01-31 | 基因微器件有限公司 | Electrophoresis method with electric field change |
| CN110009008A (en) * | 2019-03-18 | 2019-07-12 | 四川大学 | The method that immunofixation electrophoresis figure feature based on extraction classifies automatically to it |
| CN111260691A (en) * | 2020-01-18 | 2020-06-09 | 温州大学 | Spatio-temporal canonical correlation filtering tracking method based on context-aware regression |
| CN113674839A (en) * | 2021-07-22 | 2021-11-19 | 清华大学 | Combined detection system for noninvasive imaging screening and minimally invasive sampling nucleic acid typing |
| CN113869367A (en) * | 2021-08-26 | 2021-12-31 | 北京旷视科技有限公司 | Model capability detection method and device, electronic equipment and computer readable medium |
| CN114360639A (en) * | 2022-01-11 | 2022-04-15 | 平安科技（深圳）有限公司 | Artificial intelligence-based method and device for determining action relationship of drug target |
Non-Patent Citations (1)
| Title |
|---|
| Unsupervised 2D gel electrophoresis image segmentation based on active contours;Michalis A. Savelonas, et.al;《Pattern recognition》;第45卷(第2期);第720-731页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115440314A (en) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11003941B2 (en) | Character identification method and device | |
| CN106530320B (en) | End-to-end image segmentation processing method and system | |
| Li et al. | DLBI: deep learning guided Bayesian inference for structure reconstruction of super-resolution fluorescence microscopy | |
| Wijetunge et al. | EXIMS: an improved data analysis pipeline based on a new peak picking method for EXploring Imaging Mass Spectrometry data | |
| JP2021500901A5 (en) | ||
| CN107103616B (en) | Target tracking method and system | |
| US9633446B2 (en) | Method, apparatus and computer program product for segmentation of objects in media content | |
| CN112529005B (en) | Target detection method based on semantic feature consistency supervision pyramid network | |
| CN110751215B (en) | Image identification method, device, equipment, system and medium | |
| CN109376757B (en) | Multi-label classification method and system | |
| CN115440314B (en) | Agarose gel electrophoresis performance detection method and related equipment | |
| CN109685847B (en) | Training method and device for visual target detection model | |
| CN114005019B (en) | Method for identifying flip image and related equipment thereof | |
| US20190164009A1 (en) | Method and system for visual change detection using multi-scale analysis | |
| CN111444834A (en) | Image text line detection method, device, equipment and storage medium | |
| CN105321178A (en) | Image segmentation method and apparatus based on sparse principal component analysis | |
| CN116311234A (en) | Semen quality assessment method based on deep learning | |
| CN112348102A (en) | Query-based bottom-up video positioning method and system | |
| CN114998800A (en) | Video detection method, device, equipment and computer readable storage medium | |
| CN113382283B (en) | Video title identification method and system | |
| CN114005054A (en) | AI intelligence system of grading | |
| US20230268032A1 (en) | Method for generating trained model, method for determining base sequence of biomolecule, and biomolecule measurement device | |
| CN109145424A (en) | It is a kind of for the bridge data recognition methods of Coherent Noise in GPR Record and system | |
| CN115950888B (en) | quality detection method of qPCR pore plate and related equipment | |
| CN115731497A (en) | Target 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |