CN115937052B - Gel electrophoresis image processing method, device, equipment and medium - Google Patents
Gel electrophoresis image processing method, device, equipment and medium Download PDFInfo
- Publication number
- CN115937052B CN115937052B CN202310241033.4A CN202310241033A CN115937052B CN 115937052 B CN115937052 B CN 115937052B CN 202310241033 A CN202310241033 A CN 202310241033A CN 115937052 B CN115937052 B CN 115937052B
- Authority
- CN
- China
- Prior art keywords
- gel electrophoresis
- target
- image
- electrophoresis image
- connected domain
- 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
Images
Abstract
The application discloses a processing method, a device, equipment and a medium of gel electrophoresis images, which relate to the technical field of image recognition and comprise the following steps: denoising the gel electrophoresis image to obtain a denoised image, and rotating the denoised image to obtain a preprocessed gel electrophoresis image; determining a target connected domain in the pretreated gel electrophoresis image, determining an index of an area where the target connected domain is located, and then setting the index to zero to obtain a screened gel electrophoresis image; setting the boundary of the gel electrophoresis image after sieving out to zero according to the proportion to obtain a gel electrophoresis image after setting zero, and equally dividing the gel electrophoresis image after setting zero to obtain all lanes; determining the lanes where the internal reference markers are located and the types of the internal reference markers, and marking the lanes where the internal reference markers are located based on the base pair values corresponding to the types of the internal reference markers. Therefore, the method and the device realize automatic identification and labeling of the gel electrophoresis image based on the technical means of computer graphics, and improve the identification efficiency and accuracy.
Description
Technical Field
The present invention relates to the field of computer image recognition technologies, and in particular, to a method, an apparatus, a device, and a medium for processing a gel electrophoresis image.
Background
Gel electrophoresis (Gel Electrophoresis), also known as colloidal electrophoresis, is a technique used for the separation and analysis of macromolecules (e.g., DNA, RNA, proteins). This technique passes a current through a gel containing the target molecule. Depending on their size and charge, molecules will move in the gel in different directions or at different speeds, thereby separating them from each other, and are commonly used by scientists to separate molecules with different physical properties (size, charge, isoelectric point). The position of the separated polymer bands is determined by staining the polymer in a sample staining apparatus and imaging the gel in a separation imaging apparatus, and finally a digital gray scale image representing the quantitative representation of the protein in terms of size, position and darkness is output. In general, in order to check the result and confirm the position of each strip, it is necessary to manipulate the image obtained from the imaging apparatus. The mobility of other polymers can be determined by comparing the distance traveled by a particular band with the known mobility of the tracer dye and polymer. Thus, the size of the polymer can be calculated. The existing electrophoresis method requires a plurality of time-consuming steps and a plurality of large-sized devices for electrophoresis, gel staining, imaging and image processing and analysis, and better image recognition and quantitative analysis means are needed for recognition in the prior art.
The gel image generated in the existing gel electrophoresis experiment process needs to be manually detected and marked (processed, cut and marked) through a third party tool, and the positions, the brightness and the sizes of bands need to be manually compared with, for example, DNA bands to assist molecular analysis, after the gel electrophoresis image shown in fig. 1 is obtained, an experimenter needs to manually mark each lane, the marked image is shown in fig. 2, 1-5, 1-6, 1-7 and the like in fig. 2 are lane marks of lanes where an internal reference marker is located, and the numerical values of 100, 250, 500 and the like in fig. 2 are bp (Base Pair, complementary two nucleotides) information corresponding to the lanes where the internal reference marker is located.
The prior art automated gel electrophoresis analysis method is as follows: the background is first denoised, i.e. subtracted, as in fig. 3, a different background level is subtracted from each volumetric frame. The background level of the band is calculated by averaging the pixels immediately outside the volumetric frame. Lanes and bands are further segmented, as in FIG. 4, the lane frames can also be manually drawn and outlined to match the actual lanes on the blot.
In the prior art, the problems of low efficiency and low speed (5-10 minutes are required for processing a glue pattern) exist in the process of marking and identifying and analyzing gel electrophoresis strips, and the accuracy is low due to the fact that the manual identification capability is relied on, so that an improper result is generated.
Therefore, how to automatically identify and mark gel electrophoresis images and improve the processing efficiency and accuracy is a problem to be solved in the art.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, a device and a medium for processing a gel electrophoresis image, which can automatically identify and mark the gel electrophoresis image and improve the processing efficiency and accuracy, and the specific scheme is as follows:
in a first aspect, the present application discloses a method for processing a gel electrophoresis image, comprising:
denoising the target gel electrophoresis image to obtain a denoised image, and performing rotation operation on the denoised image based on an affine transformation algorithm to obtain a preprocessed target gel electrophoresis image;
determining a target connected domain in the preprocessed target gel electrophoresis image, determining an index of an area where the target connected domain is located, and then setting the index to zero so as to screen out the target connected domain, thereby obtaining the screened target gel electrophoresis image; the target connected domain is a connected domain with the area of the connected domain smaller than that of a preset connected domain;
setting the boundary of the target gel electrophoresis image after screening out to zero according to a preset proportion to obtain the target gel electrophoresis image after setting zero, and equally-spaced dividing the target gel electrophoresis image after setting zero to obtain all lanes;
and determining the lanes where the internal reference markers are located, determining the types of the internal reference markers, and marking the lanes where the internal reference markers are located based on the base pair values corresponding to the types of the internal reference markers so as to finish the processing of the target gel electrophoresis image.
Optionally, the denoising processing for the target gel electrophoresis image includes:
removing salt and pepper noise in the target gel image through median filtering to obtain a first denoising processing result;
and carrying out local weighted smoothing processing on the first denoising processing result by using Gaussian filtering to obtain a denoised image.
Optionally, the rotating operation of the denoised image based on the affine transformation algorithm includes:
extracting contour information of the denoised image based on a findContours function, and determining a target contour according to the contour information; the target contour is the maximum contour of a negative film comprising the target gel electrophoresis image;
and calculating the minimum circumscribed rectangle of the target outline, calculating the included angle between the width of the minimum circumscribed rectangle and the horizontal plane, and then performing rotation operation on the minimum circumscribed rectangle based on the affine transformation algorithm and the included angle between the width of the minimum circumscribed rectangle and the horizontal plane.
Optionally, after the rotation operation is performed on the denoised image based on the affine transformation algorithm, the method further includes:
judging whether the contour area of the target contour meets the preset area size or not, and judging whether the contour aspect ratio of the target contour is in the preset aspect ratio range or not;
if yes, executing the step of determining the target connected domain in the preprocessed target gel electrophoresis image and determining the index of the region where the target connected domain is located;
if not, cutting the rotated image, and taking the cut image as the preprocessed target gel electrophoresis image.
Optionally, the determining the index of the area where the target connected domain is located in the preprocessed target gel electrophoresis image, and setting the index to zero, so as to screen out the target connected domain, further includes:
carrying out corrosion operation treatment on the target gel electrophoresis image after the target connected domain is screened out by using a preset asymmetric template;
and performing expansion operation treatment on the target gel electrophoresis image subjected to the corrosion operation treatment based on the asymmetric template.
Optionally, the determining the lane in which the internal reference marker is located includes:
determining the number of bands of each lane, and sequencing the number of bands of each lane;
and determining the lanes of the internal reference marker according to the sequencing result.
Optionally, the determining the type of the internal reference marker includes:
determining the interval information of all strips of lanes where the internal reference marker is located, and carrying out normalization operation on the interval information to obtain normalized interval information;
and comparing the normalized interval information with the interval information of a preset reference strip, and determining the type of the internal reference marker according to a comparison result.
In a second aspect, the present application discloses a processing device for a gel electrophoresis image, comprising:
the image preprocessing module is used for denoising the target gel electrophoresis image to obtain a denoised image, and rotating the denoised image based on an affine transformation algorithm to obtain a preprocessed target gel electrophoresis image;
the connected domain screening module is used for determining a target connected domain in the preprocessed target gel electrophoresis image, determining an index of an area where the target connected domain is located, and then setting the index to zero so as to screen the target connected domain, thereby obtaining the screened target gel electrophoresis image; the target connected domain is a connected domain with the area of the connected domain smaller than that of a preset connected domain;
the boundary zeroing module is used for zeroing the boundary of the screened target gel electrophoresis image according to a preset proportion to obtain the zeroed target gel electrophoresis image;
the lane segmentation module is used for equally spacing and segmenting the target gel electrophoresis image after zero setting to obtain all lanes;
and the image marking module is used for determining lanes where the internal reference markers are located, determining the types of the internal reference markers, and marking the lanes where the internal reference markers are located based on base pair values corresponding to the types of the internal reference markers so as to finish the processing of the target gel electrophoresis image.
In a third aspect, the present application discloses an electronic device comprising:
a memory for storing a computer program;
a processor for executing the computer program to realize the processing method of the gel electrophoresis image disclosed in the foregoing.
In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein the computer program when executed by a processor implements the method of processing gel electrophoresis images disclosed above.
It can be seen that the present application proposes a method for processing gel electrophoresis images, comprising: denoising the target gel electrophoresis image to obtain a denoised image, and performing rotation operation on the denoised image based on an affine transformation algorithm to obtain a preprocessed target gel electrophoresis image; determining a target connected domain in the preprocessed target gel electrophoresis image, determining an index of an area where the target connected domain is located, and then setting the index to zero so as to screen out the target connected domain, thereby obtaining the screened target gel electrophoresis image; the target connected domain is a connected domain with the area of the connected domain smaller than that of a preset connected domain; setting the boundary of the target gel electrophoresis image after screening out to zero according to a preset proportion to obtain the target gel electrophoresis image after setting zero, and equally-spaced dividing the target gel electrophoresis image after setting zero to obtain all lanes; and determining the lanes where the internal reference markers are located, determining the types of the internal reference markers, and marking the lanes where the internal reference markers are located based on the base pair values corresponding to the types of the internal reference markers so as to finish the processing of the target gel electrophoresis image. Therefore, the method and the device realize automatic identification and labeling of the gel electrophoresis image based on the technical means of computer graphics, and greatly improve the efficiency and accuracy of the prior art in the process of identifying and labeling the gel electrophoresis image.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic illustration of a gel electrophoresis image;
FIG. 2 is a schematic illustration of an image after manual marking of a gel electrophoresis image;
FIG. 3 is a schematic illustration of local background subtraction of bands;
FIG. 4 is a schematic illustration of lanes and band segmentation;
FIG. 5 is a flow chart of a method of processing a gel electrophoresis image disclosed herein;
FIG. 6 is a schematic illustration of a denoised image disclosed herein;
FIG. 7 is a schematic representation of the maximum profile of a gel electrophoresis image disclosed herein;
FIG. 8 is a schematic illustration of a rotated image disclosed herein;
FIG. 9 is a schematic illustration of a cropped image of the present disclosure;
the left image in fig. 10 is the target gel electrophoresis image after the target connected domain is screened out, and the right image is the image after corrosion;
FIG. 11 is a schematic illustration of an image prior to boundary zeroing disclosed herein;
FIG. 12 is a schematic illustration of an image after zeroing the boundary, as disclosed herein;
FIG. 13 is a flowchart of a specific method for processing gel electrophoresis images disclosed herein;
FIG. 14 is a flow chart for determining the type of an internal reference marker disclosed herein;
FIG. 15 is a schematic view of the structure of analysis of gel electrophoresis images in various ways;
FIG. 16 is a schematic view showing the structure of a gel electrophoresis image processing apparatus disclosed in the present application;
fig. 17 is a block diagram of an electronic device disclosed in the present application.
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.
In the prior art, the problems of low efficiency and low speed exist in the process of marking and identifying and analyzing gel electrophoresis strips, the manual identification capability is relied on, the accuracy is low, and improper results are generated.
Therefore, the embodiment of the application provides a processing scheme of the gel electrophoresis image, which can realize automatic identification and marking of the gel electrophoresis image and improve the processing efficiency and accuracy.
The embodiment of the application discloses a processing method of a gel electrophoresis image, which is shown in fig. 5, and comprises the following steps:
step S11: denoising the target gel electrophoresis image to obtain a denoised image, and rotating the denoised image based on an affine transformation algorithm to obtain the preprocessed target gel electrophoresis image.
In this embodiment, the denoising processing for the target gel electrophoresis image specifically includes: removing salt and pepper noise in the target gel image through median filtering to obtain a first denoising processing result; and carrying out local weighted smoothing processing on the first denoising processing result by using Gaussian filtering to obtain a denoised image. It should be noted that if gaussian filtering is used for local weighted smoothing, then possible salt and pepper noise will interfere with the denoising result and be incorporated into the image information, and this part of the information cannot be removed by subsequent median filtering.
In this embodiment, firstly, contour information of the denoised image is extracted based on a findContours function in opencv, and a target contour is determined according to the contour information, wherein the denoised image is shown in fig. 6, and the target contour is shown in fig. 7; the target contour is the maximum contour of a negative film comprising the target gel electrophoresis image; it should be noted that, since the obtained contour may be irregular, the present application needs to further perform a rotation operation on the target contour, specifically, calculate a minimum bounding rectangle of the target contour, calculate an angle between a width of the minimum bounding rectangle and a horizontal plane, and then perform a rotation operation on the minimum bounding rectangle based on the affine transformation algorithm and the angle between the width of the minimum bounding rectangle and the horizontal plane, and it should be noted that, after the rotation operation, the minimum bounding rectangle of the target contour rotates into a horizontal rectangle, and an image after rotation is shown in fig. 8.
In this embodiment, after the image is rotated, the rotated image needs to be cut, but since the image may have a problem that the edge of the negative film is unclear, the correct contour cannot be extracted, and if the image is directly cut, the information is lost, and the subsequent analysis cannot be performed, so that the present application needs to determine whether the target contour is correct, further determine whether the cutting needs to be performed, which is as follows: judging whether the contour area of the target contour meets the preset area size or not, and judging whether the contour aspect ratio of the target contour is in the preset aspect ratio range or not; if so, the step of cutting the rotated image, determining a target connected domain in the preprocessed target gel electrophoresis image and determining the index of the region where the target connected domain is located is not needed; if not, clipping the rotated image, and taking the clipped image as the preprocessed target gel electrophoresis image, wherein the clipped image is shown in fig. 9.
Step S12: determining a target connected domain in the preprocessed target gel electrophoresis image, determining an index of an area where the target connected domain is located, and then setting the index to zero so as to screen out the target connected domain, thereby obtaining the screened target gel electrophoresis image; the target connected domain is a connected domain with the area of the connected domain smaller than that of a preset connected domain.
It should be noted that, the target connected domain is a connected domain with a smaller connected domain area determined according to an empirical value, in this embodiment, indexes of regions where all the target connected domains are located are determined through a for loop, and then all the indexes are set to zero.
In this embodiment, since the threshold value of the screening target connected domain is difficult to be adaptive, there may be a small connected domain that is not screened out after screening. On the other hand, since the internal reference Marker (Marker) is further identified, the gel electrophoresis strip is characterized in that the two ends of the gel electrophoresis strip have longer upward "tentacles", which may contact with the strip thereon to form a connected domain, and erroneous judgment is easily caused. Therefore, in this embodiment, after the index of the target connected domain is set to zero, the corrosion operation is performed on the target gel electrophoresis image after the target connected domain is screened out by using the preset asymmetric template, the left image in fig. 10 is the target gel electrophoresis image after the target connected domain is screened out, and the right image in fig. 10 is the corroded image, so that vertical branches in the transverse image can be better eliminated, smaller and larger connected domains can be further screened out, and finally the expansion operation is performed on the target gel electrophoresis image after the corrosion operation based on the asymmetric template. It should be noted that the preset asymmetric templates include, but are not limited to, 7×1 asymmetric templates.
Step S13: setting the boundary of the target gel electrophoresis image after screening out to zero according to a preset proportion to obtain the target gel electrophoresis image after setting zero, and equally-spaced dividing the target gel electrophoresis image after setting zero to obtain all lanes.
It should be noted that, after the above processing is performed on the image, the interference of the background noise in the image can be removed and most of the strip information is remained, but there are still some interference items such as the negative film boundary or the notch on the negative film at the edge of the image, as shown in fig. 11, for these interference, the embodiment zeroes the boundary of the gel electrophoresis chart according to a certain proportion, and the image after zeroing is shown in fig. 12, in a specific embodiment, the upper, lower, left and right parts of the image are zeroed according to the proportion of 1/4,1/8,1/32,1/16, respectively.
In this embodiment, after the boundary of the target gel electrophoresis image after screening is zeroed, the zeroed target gel electrophoresis image needs to be equally divided to obtain all lanes.
Step S14: and determining the lanes where the internal reference markers are located, determining the types of the internal reference markers, and marking the lanes where the internal reference markers are located based on the base pair values corresponding to the types of the internal reference markers so as to finish the processing of the target gel electrophoresis image.
In this embodiment, the specific process of determining the lane in which the internal reference marker is located is: determining the number of bands of each lane, and sequencing the number of bands of each lane; determining lanes where the internal reference markers are located according to the sorting result, specifically, determining the lane with the largest number of bands as the lane where the internal reference markers are located according to the sorting result aiming at the principle that the number of bands of the lanes where the internal reference markers are located is large.
In this embodiment, after determining the lane in which the reference marker is located, determining the type of the reference marker, and labeling the lane in which the reference marker is located based on the base pair value corresponding to the type of the reference marker, so as to complete the processing of the target gel electrophoresis image.
It can be seen that the present application proposes a method for processing gel electrophoresis images, comprising: denoising the target gel electrophoresis image to obtain a denoised image, and performing rotation operation on the denoised image based on an affine transformation algorithm to obtain a preprocessed target gel electrophoresis image; determining a target connected domain in the preprocessed target gel electrophoresis image, determining an index of an area where the target connected domain is located, and then setting the index to zero so as to screen out the target connected domain, thereby obtaining the screened target gel electrophoresis image; the target connected domain is a connected domain with the area of the connected domain smaller than that of a preset connected domain; setting the boundary of the target gel electrophoresis image after screening out to zero according to a preset proportion to obtain the target gel electrophoresis image after setting zero, and equally-spaced dividing the target gel electrophoresis image after setting zero to obtain all lanes; and determining the lanes where the internal reference markers are located, determining the types of the internal reference markers, and marking the lanes where the internal reference markers are located based on the base pair values corresponding to the types of the internal reference markers so as to finish the processing of the target gel electrophoresis image. Therefore, the method and the device realize automatic identification and labeling of the gel electrophoresis image based on the technical means of computer graphics, and greatly improve the efficiency and accuracy of the prior art in the process of identifying and labeling the gel electrophoresis image.
The embodiment of the application discloses a specific processing method of gel electrophoresis images, and compared with the previous embodiment, the embodiment further describes and optimizes the technical scheme. Referring to fig. 13, the method specifically includes:
step S21: denoising the target gel electrophoresis image to obtain a denoised image, and rotating the denoised image based on an affine transformation algorithm to obtain the preprocessed target gel electrophoresis image.
Step S22: determining a target connected domain in the preprocessed target gel electrophoresis image, determining an index of an area where the target connected domain is located, and then setting the index to zero so as to screen out the target connected domain, thereby obtaining the screened target gel electrophoresis image; the target connected domain is a connected domain with the area of the connected domain smaller than that of a preset connected domain.
Step S23: setting the boundary of the target gel electrophoresis image after screening out to zero according to a preset proportion to obtain the target gel electrophoresis image after setting zero, and equally-spaced dividing the target gel electrophoresis image after setting zero to obtain all lanes.
Step S24: determining lanes where the internal reference markers are located, determining interval information of all bands of the lanes where the internal reference markers are located, carrying out normalization operation on the interval information to obtain normalized interval information, comparing the normalized interval information with band interval information of preset reference bands, and determining the types of the internal reference markers according to comparison results.
Because the distances between the reference bands are different, in this embodiment, the distance information of all bands in the lanes where the reference markers are located is calculated, normalized operation is performed on the distance information to obtain normalized distance information, then the normalized distance information is compared with the normalized distance information of the known reference marker type, and if the comparison result has the smallest difference, the type of the reference marker is determined, in this embodiment, the known reference marker types are more, and the types of several main current reference markers that can be identified at present are DL5000 (area 1% (first reference marker type), area 2% (second reference marker type)), DL10000 (third reference marker type).
It should be noted that, since the lowermost bands of the reference bands are easily displayed and the missing bands directly affect the judgment of the program, the present embodiment adopts a relatively complex logic system, and for the reference bands with missing bands, the present embodiment finds the brightest band as the initial position, calculates the distance information between the brightest band and the surrounding bands, and returns the aforementioned comparison procedure with the normalized distance information of the known reference band types. In a specific embodiment, referring to fig. 14, the lane stripe pitch and the brightest stripe position where the internal reference marker is located are obtained first, then it is determined whether the number of lanes where the internal reference marker is located is equal to 9, if the number of lanes is equal to 9, it is determined whether the difference from the internal reference marker is less than 0.1, if the difference from the internal reference marker is less than 0.1, it is determined that the type corresponding to the internal reference marker is the differential 1, if the difference from the differential 1 is not less than 0.1, it is determined whether the difference from the differential 2 is less than 0.1, if the difference from the differential 2 is less than 0.1, it is determined that the type of the internal reference marker is the differential 2, and if the difference from the differential 2 is not less than 0.1, the type of the internal reference marker with the smallest difference is taken; if the number of bands is not equal to 9, judging whether the number of bands is equal to 7, if the number of bands is not equal to 7, taking the internal reference marker type with the smallest difference, if the number of bands is equal to 7, judging whether the difference with DL10000 is smaller than 0.1, if the difference with DL10000 is smaller than 0.1, judging that the internal reference marker type is DL10000, and if the difference with DL10000 is not smaller than 0.1, taking the internal reference marker type with the smallest difference.
Step S25: labeling the lanes where the internal reference markers are based on the base pair values corresponding to the types of the internal reference markers, so as to finish the processing of the target gel electrophoresis image.
The more specific processes of step S21, step S22, step S23 and step S25 are described with reference to the above disclosed embodiments, and are not described herein in detail.
It can be seen that the present application proposes a method for processing gel electrophoresis images, comprising: denoising the target gel electrophoresis image to obtain a denoised image, and performing rotation operation on the denoised image based on an affine transformation algorithm to obtain a preprocessed target gel electrophoresis image; determining a target connected domain in the preprocessed target gel electrophoresis image, determining an index of an area where the target connected domain is located, and then setting the index to zero so as to screen out the target connected domain, thereby obtaining the screened target gel electrophoresis image; the target connected domain is a connected domain with the area of the connected domain smaller than that of a preset connected domain; setting the boundary of the target gel electrophoresis image after screening out to zero according to a preset proportion to obtain the target gel electrophoresis image after setting zero, and equally-spaced dividing the target gel electrophoresis image after setting zero to obtain all lanes; determining lanes where the internal reference markers are located, determining interval information of all strips of the lanes where the internal reference markers are located, carrying out normalization operation on the interval information to obtain normalized interval information, comparing the normalized interval information with strip interval information of preset reference strips, and determining the types of the internal reference markers according to comparison results; the lanes where the internal reference markers are located are marked based on the base pair values corresponding to the types of the internal reference markers so as to finish the processing of the target gel electrophoresis images, so that the automatic identification and marking of the gel electrophoresis images are realized based on the technical means of computer imaging, and the efficiency and the accuracy of the prior art in the process of identifying and marking the gel electrophoresis images are greatly improved.
Referring to fig. 15, fig. 15 is a schematic structural diagram of analysis of gel electrophoresis images in various manners, in which: automatically preprocessing and marking the gel electrophoresis image by a default marking mode; the second mode, namely the processing method of the gel electrophoresis image provided by the application, realizes the processing of the gel electrophoresis image through intelligent analysis, and supports the self-editing parameters, self-modification and the like of a user after the processing; third, by manually marking an electrophoretic image, the data generated by the marking is stored in unstructured form, is difficult to preserve, difficult to manage, and does not have an effective way to reduce trial and error and repetition costs.
According to the method, lanes and strip information in the gel electrophoresis chart are automatically sketched through a computer image technology means, efficiency of the prior art in the gel electrophoresis strip marking and identifying analysis process is greatly improved, the performance improvement ratio is 30-60 times as high as 10s at present, lanes and strip information can be objectively and accurately identified through the opencv-based computer image identification technology, identification accuracy is effectively improved, and meanwhile identification results can be stored in a structured data form, so that tracing, searching, storing and managing are facilitated.
Correspondingly, the embodiment of the application also discloses a processing device of the gel electrophoresis image, referring to fig. 16, the device comprises:
the image preprocessing module 11 is used for denoising the target gel electrophoresis image to obtain a denoised image, and performing rotation operation on the denoised image based on an affine transformation algorithm to obtain a preprocessed target gel electrophoresis image;
a connected domain screening module 12, configured to determine a target connected domain in the preprocessed target gel electrophoresis image, determine an index of an area where the target connected domain is located, and then set the index to zero so as to screen the target connected domain, thereby obtaining a screened target gel electrophoresis image; the target connected domain is a connected domain with the area of the connected domain smaller than that of a preset connected domain;
the boundary zeroing module 13 is used for zeroing the boundary of the screened target gel electrophoresis image according to a preset proportion to obtain the zeroed target gel electrophoresis image;
the lane segmentation module 14 is used for equally spacing and segmenting the target gel electrophoresis image after zero setting to obtain all lanes;
the image labeling module 15 is configured to determine a lane in which the internal reference marker is located, determine a type of the internal reference marker, and label the lane in which the internal reference marker is located based on a base pair value corresponding to the type of the internal reference marker, so as to complete processing of the target gel electrophoresis image.
The more specific working process of each module may refer to the corresponding content disclosed in the foregoing embodiment, and will not be described herein.
It can be seen that the present application proposes a method for processing gel electrophoresis images, comprising: denoising the target gel electrophoresis image to obtain a denoised image, and performing rotation operation on the denoised image based on an affine transformation algorithm to obtain a preprocessed target gel electrophoresis image; determining a target connected domain in the preprocessed target gel electrophoresis image, determining an index of an area where the target connected domain is located, and then setting the index to zero so as to screen out the target connected domain, thereby obtaining the screened target gel electrophoresis image; the target connected domain is a connected domain with the area of the connected domain smaller than that of a preset connected domain; setting the boundary of the target gel electrophoresis image after screening out to zero according to a preset proportion to obtain the target gel electrophoresis image after setting zero, and equally-spaced dividing the target gel electrophoresis image after setting zero to obtain all lanes; and determining the lanes where the internal reference markers are located, determining the types of the internal reference markers, and marking the lanes where the internal reference markers are located based on the base pair values corresponding to the types of the internal reference markers so as to finish the processing of the target gel electrophoresis image. Therefore, the method and the device realize automatic identification and labeling of the gel electrophoresis image based on the technical means of computer graphics, and greatly improve the efficiency and accuracy of the prior art in the process of identifying and labeling the gel electrophoresis image.
Further, the embodiment of the application also provides electronic equipment. Fig. 17 is a block diagram of an electronic device 20, according to an exemplary embodiment, and the contents of the diagram should not be construed as limiting the scope of use of the present application in any way.
Fig. 17 is a schematic structural diagram of an electronic device 20 according to an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. Wherein the memory 22 is used for storing a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the method for processing a gel electrophoresis image disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in the present embodiment may be specifically an electronic computer.
In this embodiment, the power supply 26 is used to provide an operating voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and an external device, and the communication protocol to be followed is any communication protocol applicable to the technical solution of the present application, which is not specifically limited herein; the input/output interface 24 is used for obtaining external input data or outputting external output data, and the specific interface type thereof may be selected according to the specific application needs, which is not limited herein.
The memory 22 may be a read-only memory, a random access memory, a magnetic disk, an optical disk, or the like, and the resources stored thereon may include the computer program 221, which may be stored in a temporary or permanent manner. Wherein the computer program 221 may further comprise a computer program for performing other specific tasks in addition to the computer program for performing the method of processing a gel electrophoresis image performed by the electronic device 20 as disclosed in any of the foregoing embodiments.
Further, the embodiment of the application also discloses a computer readable storage medium for storing a computer program; wherein the computer program when executed by a processor implements the method of processing gel electrophoresis images disclosed above.
For specific steps of the method, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and no further description is given here.
In this application, each embodiment is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same or similar parts between the embodiments refer to the devices disclosed in the embodiments, so that the description is relatively simple because it corresponds to the method disclosed in the embodiments, and the relevant parts refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above describes in detail a method, apparatus, device and storage medium for processing gel electrophoresis images provided in the present application, and specific examples are applied to illustrate the principles and embodiments of the present application, where the above examples are only used to help understand the method and core ideas of the present application; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (9)
1. A method for processing a gel electrophoresis image, comprising:
denoising the target gel electrophoresis image to obtain a denoised image, and performing rotation operation on the denoised image based on an affine transformation algorithm to obtain a preprocessed target gel electrophoresis image;
determining a target connected domain in the preprocessed target gel electrophoresis image, determining an index of an area where the target connected domain is located, and then setting the index to zero so as to screen out the target connected domain, thereby obtaining the screened target gel electrophoresis image; the target connected domain is a connected domain with the area of the connected domain smaller than that of a preset connected domain;
setting the boundary of the target gel electrophoresis image after screening out to zero according to a preset proportion to obtain the target gel electrophoresis image after setting zero, and equally-spaced dividing the target gel electrophoresis image after setting zero to obtain all lanes;
determining lanes where the internal reference markers are located, determining the types of the internal reference markers, and marking the lanes where the internal reference markers are located based on base pair values corresponding to the types of the internal reference markers so as to finish the processing of the target gel electrophoresis image;
wherein the determining the type of the internal reference marker comprises: determining the interval information of all strips of lanes where the internal reference marker is located, and carrying out normalization operation on the interval information to obtain normalized interval information; and comparing the normalized interval information with the interval information of a preset reference strip, and determining the type of the internal reference marker according to a comparison result.
2. The method for processing a gel electrophoresis image according to claim 1, wherein the denoising of the target gel electrophoresis image comprises:
removing salt and pepper noise in the target gel image through median filtering to obtain a first denoising processing result;
and carrying out local weighted smoothing processing on the first denoising processing result by using Gaussian filtering to obtain a denoised image.
3. The method for processing a gel electrophoresis image according to claim 1 wherein the rotating operation of the denoised image based on an affine transformation algorithm comprises:
extracting contour information of the denoised image based on a findContours function, and determining a target contour according to the contour information; the target contour is the maximum contour of a negative film comprising the target gel electrophoresis image;
and calculating the minimum circumscribed rectangle of the target outline, calculating the included angle between the width of the minimum circumscribed rectangle and the horizontal plane, and then performing rotation operation on the minimum circumscribed rectangle based on the affine transformation algorithm and the included angle between the width of the minimum circumscribed rectangle and the horizontal plane.
4. A method of processing a gel electrophoresis image according to claim 3 wherein after the rotating operation of the denoised image based on affine transformation algorithm, further comprising:
judging whether the contour area of the target contour meets the preset area size or not, and judging whether the contour aspect ratio of the target contour is in the preset aspect ratio range or not;
if yes, executing the step of determining the target connected domain in the preprocessed target gel electrophoresis image and determining the index of the region where the target connected domain is located;
if not, cutting the rotated image, and taking the cut image as the preprocessed target gel electrophoresis image.
5. The method for processing a gel electrophoresis image according to claim 1, wherein determining an index of an area where a target connected domain is located in the preprocessed target gel electrophoresis image, and setting the index to zero so as to screen out the target connected domain, further comprises:
carrying out corrosion operation treatment on the target gel electrophoresis image after the target connected domain is screened out by using a preset asymmetric template;
and performing expansion operation treatment on the target gel electrophoresis image subjected to the corrosion operation treatment based on the asymmetric template.
6. The method for processing gel electrophoresis images according to claim 1, wherein determining the lane in which the internal reference marker is located comprises:
determining the number of bands of each lane, and sequencing the number of bands of each lane;
and determining the lanes of the internal reference marker according to the sequencing result.
7. A processing apparatus for a gel electrophoresis image, comprising:
the image preprocessing module is used for denoising the target gel electrophoresis image to obtain a denoised image, and rotating the denoised image based on an affine transformation algorithm to obtain a preprocessed target gel electrophoresis image;
the connected domain screening module is used for determining a target connected domain in the preprocessed target gel electrophoresis image, determining an index of an area where the target connected domain is located, and then setting the index to zero so as to screen the target connected domain, thereby obtaining the screened target gel electrophoresis image; the target connected domain is a connected domain with the area of the connected domain smaller than that of a preset connected domain;
the boundary zeroing module is used for zeroing the boundary of the screened target gel electrophoresis image according to a preset proportion to obtain the zeroed target gel electrophoresis image;
the lane segmentation module is used for equally spacing and segmenting the target gel electrophoresis image after zero setting to obtain all lanes;
the image marking module is used for determining lanes where the internal reference markers are located, determining the types of the internal reference markers, and marking the lanes where the internal reference markers are located based on base pair values corresponding to the types of the internal reference markers so as to finish the processing of the target gel electrophoresis image;
the image annotation module is specifically configured to: determining the interval information of all strips of lanes where the internal reference marker is located, and carrying out normalization operation on the interval information to obtain normalized interval information; and comparing the normalized interval information with the interval information of a preset reference strip, and determining the type of the internal reference marker according to a comparison result.
8. An electronic device, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the method of processing a gel electrophoresis image according to anyone of claims 1 to 6.
9. A computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements a method of processing a gel electrophoresis image according to anyone of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310241033.4A CN115937052B (en) | 2023-03-14 | 2023-03-14 | Gel electrophoresis image processing method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310241033.4A CN115937052B (en) | 2023-03-14 | 2023-03-14 | Gel electrophoresis image processing method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115937052A CN115937052A (en) | 2023-04-07 |
| CN115937052B true CN115937052B (en) | 2023-05-16 |
Family
ID=85823803
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310241033.4A Active CN115937052B (en) | 2023-03-14 | 2023-03-14 | Gel electrophoresis image processing method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115937052B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2057670A1 (en) * | 1990-12-19 | 1992-06-20 | Nobuhiro Minato | Method of and apparatus for inspecting transparent object for defect |
| US9230185B1 (en) * | 2012-03-30 | 2016-01-05 | Pierce Biotechnology, Inc. | Analysis of electrophoretic bands in a substrate |
| CN107102007A (en) * | 2017-06-19 | 2017-08-29 | 成都汇智远景科技有限公司 | Pattern uniformity recognition methods in cloth detection |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0677823B1 (en) * | 1994-04-15 | 2000-05-24 | Fuji Photo Film Co., Ltd. | Image analyzing apparatus |
| JP3224352B2 (en) * | 1997-02-21 | 2001-10-29 | 出光興産株式会社 | Multicolor light emitting device |
| DE10339743B4 (en) * | 2003-08-28 | 2007-08-02 | Infineon Technologies Ag | A method of comparing a test fingerprint with a stored reference fingerprint and apparatus suitable for performing the method |
| US20110042217A1 (en) * | 2009-08-24 | 2011-02-24 | Life Technologies Corporation | Electrophoresis gel cassette and comb |
| US20120247958A1 (en) * | 2011-04-01 | 2012-10-04 | Life Technologies Corporation | Gel processing systems for electrophoresis, imaging, and analysis, software and methods |
| JP6281805B2 (en) * | 2013-06-05 | 2018-02-21 | 国立大学法人東京工業大学 | Electrophoresis visualization apparatus, electrophoresis tank, electrophoresis visualization system, electrophoresis visualization method, analysis method of separation target mixture, separation method of separation target mixture, and manufacturing method of separation |
| WO2022188696A1 (en) * | 2021-03-08 | 2022-09-15 | 南京金斯瑞生物科技有限公司 | Method for automatically identifying and analyzing gel image |
| CN113112432A (en) * | 2021-05-13 | 2021-07-13 | 广州道一科学技术有限公司 | Method for automatically identifying image strips |
| CN115393364B (en) * | 2022-11-01 | 2023-08-01 | 长春理工大学 | Chemiluminescent blotting lane recognition method |
-
2023
- 2023-03-14 CN CN202310241033.4A patent/CN115937052B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2057670A1 (en) * | 1990-12-19 | 1992-06-20 | Nobuhiro Minato | Method of and apparatus for inspecting transparent object for defect |
| US9230185B1 (en) * | 2012-03-30 | 2016-01-05 | Pierce Biotechnology, Inc. | Analysis of electrophoretic bands in a substrate |
| CN107102007A (en) * | 2017-06-19 | 2017-08-29 | 成都汇智远景科技有限公司 | Pattern uniformity recognition methods in cloth detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115937052A (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106875381B (en) | Mobile phone shell defect detection method based on deep learning | |
| CN107392141B (en) | Airport extraction method based on significance detection and LSD (least squares distortion) line detection | |
| CN109978890B (en) | Target extraction method and device based on image processing and terminal equipment | |
| CN111145209A (en) | Medical image segmentation method, device, equipment and storage medium | |
| CN111598856A (en) | Chip surface defect automatic detection method and system based on defect-oriented multi-point positioning neural network | |
| CN112734729B (en) | Water gauge water level line image detection method and device suitable for night light supplement condition and storage medium | |
| CN106778754A (en) | A kind of industrial ammeter digit recognition method of robust | |
| CN111986183A (en) | Chromosome scattergram image automatic segmentation and identification system and device | |
| CN112348122A (en) | Method and device for marking drivable area and electronic equipment | |
| CN114998815B (en) | Traffic vehicle identification tracking method and system based on video analysis | |
| CN113780110A (en) | Method and device for detecting weak and small targets in image sequence in real time | |
| CN113160185A (en) | Method for guiding cervical cell segmentation by using generated boundary position | |
| Wei et al. | Detection of lane line based on Robert operator | |
| CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
| CN115294377A (en) | System and method for identifying road cracks | |
| CN115841669A (en) | Pointer instrument detection and reading identification method based on deep learning technology | |
| CN112396618B (en) | Grain boundary extraction and grain size measurement method based on image processing | |
| CN115937052B (en) | Gel electrophoresis image processing method, device, equipment and medium | |
| Chen et al. | Image segmentation based on mathematical morphological operator | |
| CN113393454A (en) | Method and device for segmenting pathological target examples in biopsy tissues | |
| Arora et al. | An algorithm to straighten the bent human chromosomes | |
| Danilescu et al. | Road anomalies detection using basic morphological algorithms | |
| CN108319927B (en) | Method for automatically identifying diseases | |
| CN116824135A (en) | Atmospheric natural environment test industrial product identification and segmentation method based on machine vision | |
| Khan et al. | Segmentation of single and overlapping leaves by extracting appropriate contours |
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 |