Method and apparatus for analyzing biochip image, computer device, and storage medium
A method for analyzing a biochip image is provided, including: (S 1 ) acquiring and preprocessing the biochip image to obtain a preprocessed image; (S 2 ) performing a correction for angle deflection on the preprocessed image to obtain a deflection-corrected image; and (S 3 ) performing an enhancement processing on the deflection-corrected image, and identifying a positive or negative of an area of interest in the preprocessed image according to an image on which the enhancement processing has been performed. An apparatus ( 100 ) for analyzing a biochip image, a method for analyzing an image, a computer device ( 200 ) and a storage medium are disclosed.
1 . A method for analyzing a biochip image, comprising:
acquiring and preprocessing the biochip image to obtain a preprocessed image;
performing a correction for angle deflection on the preprocessed image to obtain a deflection-corrected image; and
performing an enhancement processing on the deflection-corrected image, and identifying a positive or negative of an area of interest in the preprocessed image according to an image on which the enhancement processing has been performed;
wherein the performing a correction for angle deflection on the preprocessed image to obtain a deflection-corrected image comprises:
selecting a preset number of detection areas in the preprocessed image;
detecting a center and a radius of each area of interest in each detection area by using a Hough circle transformation; and
forming a circle according to the center and the radius of each area of interest, to determine the area of interest and segment the area of interest;
wherein the performing a correction for angle deflection on the preprocessed image to obtain a deflection-corrected image comprises:
performing an expansion processing on the segmented image to connect adjacent areas of interest in a preset direction;
performing a principal component analysis on a contour of the detection area having a maximum contour in the image on which the expansion processing is performed, to obtain a contour direction; and
determining an image deflection angle according to the contour direction, to correct the preprocessed image and to obtain the deflection-corrected image;
wherein the performing a correction for angle deflection on the preprocessed image to obtain a deflection-corrected image comprises:
enlarging the selected area by a preset proportion, to randomly select the preset number of detection areas in the preprocessed image again; and
repeatedly and iteratively detecting the image deflection angle until the image deflection angle is smaller than a preset angle threshold, to obtain the deflection-corrected image;
wherein a range of the preset angle threshold is determined by a following conditional expression:
cos
θ
-
(
max
{
m
,
n
}
-
1
)
·
sin
θ
>
2
rad
dist
where θ is the preset angle threshold, dist is the area interval of the areas of interest, rad is an area radius of the area of interest, m is the number of rows of the areas of interest in each detection area, and n is the number of columns of the areas of interest in each detection area.
2 . The method according to claim 1 , wherein the performing a correction for angle deflection on the preprocessed image to obtain a deflection-corrected image comprises:
enlarging the selected area by a preset proportion, to randomly select the preset number of detection areas in the preprocessed image again; and
repeatedly and iteratively detecting the image deflection angle for a preset number of times, to obtain the deflection-corrected image.
3 . The method according to claim 1 , wherein the performing an enhancement processing on the deflection-corrected image, and identifying a positive or negative of an area of interest in the preprocessed image according to an image on which the enhancement processing is performed comprises:
constructing a notch filter; and
filtering the deflection-corrected image by using the notch filter, to obtain an image with enhanced periodic patterns.
4 . The method according to claim 3 , wherein the performing an enhancement processing on the deflection-corrected image, and identifying a positive or negative of an area of interest in the preprocessed image according to an image on which the enhancement processing is performed comprises:
performing a smooth filtering processing on the image with enhanced periodic patterns by using a box filter;
integrating pixel values of the image on which the smooth filtering processing is performed in a horizontal direction and a vertical direction, to obtain a first integral curve in the horizontal direction and a second integral curve in the vertical direction, respectively, and taking a set of minimum points of the first integral curve and the second integral curve to determine a grid spacing line; and
dividing grid areas according to the grid spacing line.
5 . The method according to claim 4 , wherein a length or width of an operator of the box filter satisfies a following conditional expression:
⌈
d
i
s
t
2
-
rad
⌉
<
b
<
⌈
d
i
s
t
2
⌉
where b is the length or width of the operator of the box filter; dist is the area interval of the areas of interest, rad is an area radius of the area of interest.
6 . The method according to claim 4 , wherein the performing an enhancement processing on the deflection-corrected image, and identifying a positive or negative of an area of interest in the preprocessed image according to an image on which the enhancement processing is performed comprises:
throughout the grid areas, solving a mean square error of pixel values of each grid area corresponding to the preprocessed image;
marking the corresponding sample of the area of interest as positive in response to the mean square error being greater than a mean square error threshold; and
marking the corresponding sample of the area of interest as negative in response to the mean square error being not greater than the mean square error threshold.
7 . The method according to claim 1 , further comprising:
outputting an identification result for the positive or negative of the area of interest.
8 . A non-transitory computer-readable storage medium storing computer programs thereon, wherein the computer programs, when executed by one or more processors, implement the method for analyzing a biochip image according to claim 1 .
9 . The method according to claim 1 , wherein the acquiring and preprocessing the biochip image to obtain a preprocessed image comprises:
acquiring an original image, a camera intrinsic parameter matrix and a distortion coefficient; and
correcting the original image according to the camera intrinsic parameter matrix and the distortion coefficient to obtain the biochip image.
10 . The method according to claim 9 , further comprising:
calibrating the camera for shooting by using a calibration plate and by adopting a traditional calibration method, to obtain the camera intrinsic parameter matrix and the distortion coefficient.
11 . The method according to claim 9 , wherein the original image is a fluorescent image of a biochip in which a biochemical reaction has occurred.
12 . The method according to claim 1 , wherein the preprocessed image comprises an image having a high-frequency component, and the acquiring and preprocessing the biochip image to obtain a preprocessed image comprises:
performing a Gaussian filtering processing on the biochip image to obtain an image having a low-frequency component; and
subtracting the image having the low-frequency component from the biochip image to obtain the image having the high-frequency component.
13 . The method according to claim 1 , wherein the selecting a preset number of detection areas in the preprocessed image comprises:
selecting a corresponding detection area within a predetermined area of the preprocessed image.
14 . The method according to claim 1 , wherein each detection area is a rectangular area, and comprises at least two rows or at least two columns of areas of interest.
15 . An apparatus for analyzing a biochip image, comprising:
an acquisition module configured to acquire and preprocess the biochip image to obtain a preprocessed image;
a correction module configured to perform a correction for angle deflection on the preprocessed image to obtain a deflection-corrected image; and
a processing module configured to perform an enhancement processing on the deflection-corrected image, and identify a positive or negative of an area of interest in the preprocessed image according to an image on which the enhancement processing has been performed;
wherein the correction module is further configured to:
select a preset number of detection areas in the preprocessed image;
detect a center and a radius of each area of interest in each detection area by using a Hough circle transformation; and
form a circle according to the center and the radius of each area of interest, to determine the area of interest and segment the area of interest;
wherein the correction module is further configured to:
perform an expansion processing on the segmented image to connect adjacent areas of interest in a preset direction;
perform a principal component analysis on a contour of the detection area having a maximum contour in the image on which the expansion processing is performed, to obtain a contour direction; and
determine an image deflection angle according to the contour direction, to correct the preprocessed image and to obtain the deflection-corrected image;
wherein the correction module is further configured to:
enlarge the selected area by a preset proportion, to randomly select the preset number of detection areas in the preprocessed image again; and
repeatedly and iteratively detect the image deflection angle until the image deflection angle is smaller than a preset angle threshold, to obtain the deflection-corrected image;
wherein a range of the preset angle threshold is determined by a following conditional expression:
cos
θ
-
(
max
{
m
,
n
}
-
1
)
·
sin
θ
>
2
rad
d
i
s
t
where θ is the preset angle threshold, dist is the area interval of the areas of interest, rad is an area radius of the area of interest, m is the number of rows of the areas of interest in each detection area, and n is the number of columns of the areas of interest in each detection area.
16 . A computer device, comprising a processor and a memory, wherein the memory stores computer programs thereon which, when executed by the processor, implement the method for analyzing a biochip image according to claim 1 .
17 . The apparatus according to claim 15 , wherein the acquisition module is further configured to:
acquire an original image, a camera intrinsic parameter matrix and a distortion coefficient; and
correct the original image according to the camera intrinsic parameter matrix and the distortion coefficient to obtain the biochip image.
18 . The apparatus according to claim 17 , wherein the original image is a fluorescent image of a biochip in which a biochemical reaction has occurred.
19 . The apparatus according to claim 15 , wherein the correction module is further configured to:
select a corresponding detection area within a predetermined area of the preprocessed image.
20 . The apparatus according to claim 15 , wherein each detection area is a rectangular area, and comprises at least two rows or at least two columns of areas of interest.