WO2022178653A1 - 生物芯片图像的分析方法及装置、计算机设备和存储介质 - Google Patents

生物芯片图像的分析方法及装置、计算机设备和存储介质 Download PDF

Info

Publication number
WO2022178653A1
WO2022178653A1 PCT/CN2021/077355 CN2021077355W WO2022178653A1 WO 2022178653 A1 WO2022178653 A1 WO 2022178653A1 CN 2021077355 W CN2021077355 W CN 2021077355W WO 2022178653 A1 WO2022178653 A1 WO 2022178653A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
biochip
interest
region
analyzing
Prior art date
Application number
PCT/CN2021/077355
Other languages
English (en)
French (fr)
Inventor
吴琼
侯孟军
马相国
耿凯
刘祝凯
Original Assignee
京东方科技集团股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 京东方科技集团股份有限公司 filed Critical 京东方科技集团股份有限公司
Priority to PCT/CN2021/077355 priority Critical patent/WO2022178653A1/zh
Priority to CN202180000294.6A priority patent/CN115335854A/zh
Priority to US17/927,025 priority patent/US20230230229A1/en
Priority to EP21927101.2A priority patent/EP4141787A4/en
Publication of WO2022178653A1 publication Critical patent/WO2022178653A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/80—Geometric correction
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G01N21/645—Specially adapted constructive features of fluorimeters
    • G01N21/6456—Spatial resolved fluorescence measurements; Imaging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration using local operators
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/77—Determining position or orientation of objects or cameras using statistical methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G01N21/645—Specially adapted constructive features of fluorimeters
    • G01N21/6452—Individual samples arranged in a regular 2D-array, e.g. multiwell plates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10064—Fluorescence image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20048—Transform domain processing
    • G06T2207/20061—Hough transform
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20224—Image subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30072—Microarray; Biochip, DNA array; Well plate

Definitions

  • the present application relates to the technical field of biological detection, and more particularly, to a method and device for analyzing an image of a biological chip, an image analyzing method, computer equipment and a storage medium.
  • array biochip technology is an important tool for accurate genetic analysis and disease diagnosis. It can overcome the drawbacks of traditional methods that require repeated tests, effectively save manpower, sample volume, and improve detection accuracy. It is one of the important means of biological sample detection in the modern biomedical field. Using automatic detection to detect biochips usually extracts image features, independently obtains the number and position of chips, and detects and analyzes the negative and positive of sample points.
  • the existing solutions generally analyze and process images of ideal scenes with high signal-to-noise ratios, but there is no effective processing method for high-throughput and low-signal-to-noise ratio images.
  • Embodiments of the present application provide a method for analyzing an image of a biochip, a device for analyzing an image of a biochip, a method for analyzing an image, a computer device, and a storage medium.
  • a method for analyzing a biochip image includes: acquiring a biochip image and performing preprocessing to obtain a preprocessed image; performing angular deflection correction on the preprocessed image to obtain a deflection corrected image; The image is enhanced, and the negative and positive of the region of interest in the preprocessed image are identified according to the enhanced image.
  • the acquiring the biochip image to process the pre-processed image comprises: acquiring the original image, the camera intrinsic parameter matrix and the distortion coefficient; and performing the processing on the original image according to the camera intrinsic parameter matrix and the distortion coefficient Correction to obtain the biochip image.
  • the method for analyzing the biochip image includes: using a calibration plate to calibrate a camera for shooting by using a traditional calibration method, so as to obtain the camera internal parameter matrix and the distortion coefficient.
  • the original image is a fluorescent image of a biochip undergoing biochemical reactions.
  • the preprocessed image includes a high frequency component image
  • the acquiring the biochip image to process the preprocessed image includes: performing Gaussian filtering on the biochip image to obtain a low frequency component image; and using The low frequency component image is subtracted from the biochip image to obtain the high frequency component image.
  • the performing angle deflection correction on the preprocessed image to obtain the deflection corrected image comprises: selecting a preset number of detection regions in the preprocessed image; detecting the detection using Hough circle transform the center and radius of the region of interest within the region; and making a circle according to the center and radius of the region of interest to determine the region of interest and segment the region of interest.
  • the selecting a preset number of detection regions in the preprocessed image comprises: selecting the corresponding detection regions within a predetermined region of the preprocessed image.
  • the detection area is a rectangular area, and the detection area includes at least two rows or at least two columns of part of the region of interest.
  • the performing angle deflection correction on the preprocessed image to obtain the deflection corrected image comprises: performing dilation processing on the segmented image to connect the adjacent regions of interest in a preset direction; taking the dilation process After processing, the largest contour of the cavity detection area is subjected to principal component analysis to obtain contour directions; and an image deflection angle is determined according to the contour directions to correct the preprocessed image to obtain the deflection corrected image.
  • the performing angle deflection correction on the preprocessed image to obtain the deflection corrected image comprises: increasing a selection area with a preset ratio and reselecting a preset number of the detections in the preprocessed image and repeating iteratively detecting the image deflection angle until the image deflection angle is smaller than a preset angle threshold to obtain the deflection corrected image.
  • the range of the preset angle threshold value can be determined by the following conditional formula: Wherein, ⁇ is the preset angle threshold, dist is the area distance of the interest area, rad is the area radius of the interest area, m is the number of rows of the interest area in the detection area, and n is the The number of columns of the region of interest within the detection region.
  • the performing angle deflection correction on the preprocessed image to obtain the deflection corrected image comprises: increasing a selection area with a preset ratio and reselecting a preset number of the detections in the preprocessed image and repeating iteratively detecting the deflection angle of the image for a preset number of times to obtain the deflection corrected image.
  • the performing enhancement processing on the deflection corrected image and identifying the negative and positive of the region of interest in the preprocessed image according to the enhanced image comprises: constructing a notch filter; and using the The notch filter performs filtering processing on the deflection corrected image to obtain a periodic pattern enhanced image.
  • the performing enhancement processing on the deflection corrected image and identifying the positives and negatives of the region of interest in the preprocessed image according to the enhanced image comprises: using a box filter to analyze the period Perform smooth filtering processing on the image enhanced by the characteristic schema; perform the pixel value integration in the horizontal direction and the vertical direction on the smoothed image to obtain the first integration curve in the horizontal direction and the second integration curve in the vertical direction, take a minimum point set of the first integration curve and the second integration curve to determine grid interval lines; and dividing grid regions according to the grid interval lines.
  • the length and width of the operator of the box filter satisfy the following conditional expressions: Wherein, b is the length and width of the operator of the box filter, dist is the region spacing of the region of interest, and rad is the region radius of the region of interest.
  • the performing enhancement processing on the deflection correction image and identifying the positives and negatives of the region of interest in the preprocessed image according to the enhanced image comprises: traversing the grid area, Calculate the mean square error of pixel values for each grid area corresponding to the preprocessed image; when the mean square error is greater than the variance threshold, mark the corresponding sample of the region of interest as positive; and when the mean square error is not greater than the variance When the threshold is set, the sample corresponding to the region of interest is marked as negative.
  • the method for analyzing the biochip image includes: outputting the positive and negative identification results of the region of interest.
  • Embodiments of the present application further provide an image analysis method, including the steps of the biochip image analysis method described in any of the above embodiments.
  • Embodiments of the present application further provide an apparatus for analyzing a biochip image, including an acquisition module, a correction module, a processing module, and an identification module, where the acquisition module is used to acquire a biochip image and perform preprocessing to obtain a preprocessed image; the correction The module is used for performing angle deflection correction on the preprocessed image to obtain a deflection correction image; the processing module is used for performing periodic pattern enhancement processing on the deflection correction image and dividing the chamber grid; and on the deflection correction image The corrected image is enhanced, and the negative and positive of the region of interest in the preprocessed image are identified according to the enhanced image.
  • Embodiments of the present application further provide a computer device, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for analyzing a biochip image in any of the foregoing embodiments is implemented, Or the image analysis method described in the above embodiment.
  • Embodiments of the present application further provide a storage medium on which a computer program is stored, and when the computer program is executed by one or more processors, implements the method for analyzing a biochip image described in any of the foregoing embodiments, or the above The image analysis method described in the embodiment.
  • the biochip image analysis method and device, computer equipment, and storage medium of the embodiments of the present application can effectively identify the matrix-type biochip fluorescence image with high throughput and low signal-to-noise ratio.
  • the improved processing method is achieved by Filtering solves the problem of uneven fluorescence illumination of microchips; automatic analysis of chamber location positioning and sample positive and negative judgment is successfully achieved through grid division.
  • FIG. 1 is a schematic flowchart of a method for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 2 is a schematic block diagram of an apparatus for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 3 is another schematic flowchart of a method for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 4 is another schematic flowchart of the method for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 5 is a schematic flow chart of still another method for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 6 is another schematic flowchart of the method for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 7 is a schematic outline view of a divided reaction chamber after expansion processing according to an embodiment of the present application.
  • FIG. 8 is a schematic flowchart of still another method for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 9 is a schematic flow chart of still another method for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 10 is a schematic flow chart of still another method for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 11 is a schematic diagram of the amplitude of the Fourier transform of the biochip image to the frequency domain according to the embodiment of the present application.
  • FIG. 12 is a schematic diagram of constructing a filter according to an embodiment of the present application.
  • FIG. 13 is a schematic flow chart of still another method for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 14 is a schematic flow chart of still another method for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 15 is a schematic flow chart of still another method for analyzing a biochip image according to an embodiment of the present application.
  • FIG. 16 is a schematic block diagram of a computer device according to an embodiment of the present application.
  • a method for analyzing a biochip image identifies a matrix biochip fluorescence image with high throughput and low signal-to-noise ratio, realizes the location of the chamber, and determines whether the sample is negative or positive. automated analysis.
  • the biochip image analysis method of the embodiment of the present application can be used in the biochip image analysis apparatus 10 of the embodiment of the present application, that is, the biochip image analysis apparatus 10 of the embodiment of the present application can use the biochip image of the embodiment of the present application.
  • the chip image analysis method identifies the matrix biochip fluorescence image with high throughput and low signal-to-noise ratio, and realizes the automatic analysis of chamber location positioning and sample negative and positive judgment.
  • biochip analysis includes:
  • Step S1 acquiring a biochip image and performing preprocessing to obtain a preprocessed image
  • Step S2 performing angle deflection correction on the preprocessed image to obtain a deflection corrected image
  • Step S3 performing enhancement processing on the deflection correction image and identifying the positive and negative of the region of interest in the preprocessed image according to the enhanced image.
  • the biochip image analysis device 10 includes an acquisition module 11 , a correction module 12 and a processing module 13 .
  • Step S1 can be implemented by the acquisition module 11
  • step S2 can be implemented by the correction module 12
  • step S3 can be implemented by the processing module 13 .
  • the acquisition module 11 can be used to acquire the biochip image for processing to obtain the preprocessed image.
  • the correction module 12 can be used to randomly select the detection area and detect the reaction chambers within the detection area to process the deflection corrected image.
  • the processing module 13 can be used to perform enhancement processing on the deflection corrected image and identify the negative and positive of the region of interest in the preprocessed image according to the enhanced image.
  • the improved processing method solves the problem of microscopic chips through filtering
  • the problem of uneven fluorescence illumination; automatic analysis of chamber location positioning and sample negative and positive judgment can be realized through image enhancement processing.
  • step S1 includes:
  • Step S11 obtaining the original image, the camera intrinsic parameter matrix and the distortion coefficient
  • Step S12 correcting the original image according to the camera internal parameter matrix and the distortion coefficient to obtain a biochip image.
  • step S11 and step S12 may be implemented by the obtaining module 11 . That is to say, the acquisition module 11 can be used to acquire the original image, the camera intrinsic parameter matrix and the distortion coefficient, and to correct the original image according to the camera intrinsic parameter matrix and the distortion coefficient to obtain the biochip image.
  • the distortion generated in the original image collected by the camera can be corrected by acquiring the camera internal parameter matrix and the distortion coefficient, so that the corrected biochip image can more truly display the characteristics of the biochip. In this way, it can be beneficial to ensure the validity and accuracy of the biochip analysis.
  • the biochip may be quadrilateral, and a plurality of reaction chambers are arranged in an array on the biochip. It should be noted that, in the embodiments of the present application, the region where the reaction chamber is located in the biochip image is used as the region of interest for description.
  • the method for analyzing the biochip image includes: using a calibration plate to calibrate the camera used for shooting by using a traditional calibration method, so as to obtain the camera's internal parameter matrix and distortion coefficient.
  • the biochip image analysis device 10 may include a calibration module 15, and the calibration module 15 may be used for calibrating a camera for shooting by using a calibration board and a traditional calibration method to obtain the camera internal parameter matrix and distortion coefficient.
  • the calibration plate when the camera parameters are calibrated by the calibration plate, the calibration plate may have a predetermined pattern, such as a grid pattern or a black and white square pattern, etc., and the camera captures an image of the calibration plate at a certain shooting distance. The image is compared with the pattern of the calibration plate. According to the offset of the corresponding feature points in the image of the calibration plate and the pattern of the calibration plate, combined with the shooting distance, the camera internal parameter matrix and distortion parameters related to the camera shooting are obtained.
  • a predetermined pattern such as a grid pattern or a black and white square pattern, etc.
  • the camera internal parameter matrix and the distortion coefficient may be pre-calibrated and pre-stored in the camera or biochip image analysis device 10.
  • the bioanalysis device can obtain the corresponding camera internal parameter matrix from the camera. and distortion coefficient, or determine the camera intrinsic parameter matrix and distortion coefficient according to the serial number or model of the camera.
  • the biochip image analysis device 10 may also detect the camera internal parameter matrix and distortion coefficient corresponding to the corresponding camera before each acquisition of the biochip image. In this way, the camera internal parameter matrix and distortion coefficient can be guaranteed. effectiveness.
  • the original image is a fluorescent image of the biochip in which the biochemical reaction has occurred.
  • the fluorescence image of the corresponding biochip can be collected by using a specific device. It can be understood that, in the fluorescence image, the color and brightness displayed by different reaction chambers may be the same or different.
  • the preprocessed image includes a high-frequency component image
  • step S1 includes:
  • Step S13 performing Gaussian filtering on the biochip image to obtain a low-frequency component image
  • step S14 the low-frequency component image is subtracted from the biochip image to obtain the high-frequency component image.
  • steps S13 and S14 may be implemented by the obtaining module 11 . That is to say, the acquisition module 11 can be used to perform Gaussian filtering on the biochip image to obtain a low-frequency component image, and to subtract the low-frequency component image from the biochip image to obtain a high-frequency component image.
  • Gaussian filtering is used to obtain a low-frequency component image, and then the low-frequency component in the biochip image is subtracted to obtain a high-frequency component image, so as to achieve high-frequency filtering, thereby solving the problem of uneven fluorescence illumination of the microchip.
  • the preprocessed images may not be limited to the high-frequency component images discussed above, and grayscale images, low-frequency component images, edge detection images, etc. may be obtained according to actual requirements.
  • the grayscale image can be obtained according to the grayscale processing of the image
  • the low-frequency component image can be obtained by the low-frequency component extraction process
  • the edge detection image can be obtained by the image edge extraction process.
  • the preprocessed image can also be obtained by processing one or more of the above processing methods in a preset order, which is not specifically limited here.
  • step S2 includes:
  • Step S21 selecting a preset number of detection areas in the preprocessed image
  • Step S22 utilize the Hough circle transform to detect the center and radius of the region of interest in the detection region.
  • Step S23 making a circle according to the center and radius of the region of interest to determine the region of interest and segment the region of interest.
  • step S21 , step S22 and step S23 may be implemented by the correction module 12 . That is to say, the correction module 12 can be used to select a preset number of detection regions in the preprocessed image, and to detect the center and radius of the region of interest in the detection region by using Hough circle transform, and to detect the center and radius of the region of interest in the detection region according to the Make a circle with the center and radius to determine and segment the region of interest.
  • the region of interest as the region where the reaction chambers are located in the image as an example, when detecting the arrangement of the reaction chambers, it is necessary to determine the positions of the reaction chambers in the detection area. Since the reaction chambers are generally circular, so, through Hough The transformation can realize the detection of the center and radius of the chamber, and further, after the position of the reaction chamber is determined according to the center and radius of the chamber, the segmentation of the reaction chamber can be realized.
  • step S21 includes: selecting a corresponding detection area within a predetermined area of the preprocessed image.
  • the correction module 12 may be used to select a corresponding detection area within a predetermined area of the preprocessed image.
  • the preset area may be set by the user according to experience, or automatically selected according to an algorithm.
  • the detection area may also be an area randomly selected in the preprocessed image, which is not specifically limited here.
  • the detection area is a rectangular area, and the detection area includes part of the region of interest in at least two rows or at least two columns.
  • the deflection angle of the high frequency component image needs to be determined. Because the reaction chambers on the biochip are generally arranged in an array, that is, the regions of interest are generally arranged in an array, so the detection of the image deflection angle can be realized by the arrangement direction of the chambers, and the use of a rectangular area is conducive to determining the long side direction of the selected detection area. The relative deflection angle to the alignment direction of the reaction chambers.
  • the detection area includes at least two rows or at least two columns of part of the region of interest, which can ensure the detection of the arrangement direction of the reaction chambers.
  • the size of the detection area can be flexibly configured according to the area spacing of the area of interest and the radius of the area of interest, etc., which is not specifically limited here.
  • the shape of the detection area may not be limited to the rectangle discussed above, and other suitable shapes such as square, triangle, circle, parallelogram, etc. may be selected according to actual needs, which are not specifically limited here.
  • the preset number of detection areas selected each time may be multiple, and the directions of the multiple detection areas may be different, thereby improving the efficiency and accuracy of image deflection angle detection.
  • the preset number of detection regions selected each time may be nine.
  • step S2 includes:
  • Step S24 performing expansion processing on the segmented image to connect adjacent interest regions in a preset direction
  • Step S25 take the largest contour in the detection area after the expansion processing and carry out principal component analysis to obtain the contour direction
  • Step S26 Determine the deflection angle of the image according to the contour direction to correct the preprocessed image to obtain a deflection corrected image.
  • Steps S25 and S26 may be implemented by the correction module 12 . That is to say, the correction module 12 can be used to perform dilation processing on the segmented images to connect adjacent regions of interest in a preset direction, and to take the largest contour in the detection area after the dilation processing and perform principal component analysis to obtain The contour direction is used to determine the deflection angle of the image according to the contour direction to correct the preprocessed image to obtain a deflection corrected image.
  • the segmented region of interest may be expanded in a preset direction, so that the contour of the region of interest extends along the preset direction, so that the contours of adjacent regions of interest are connected to each other.
  • the preset direction may be the long side direction of the rectangular detection area.
  • Fig. 7 shows a schematic diagram of the outline obtained by expanding the regions of interest in the nine chambers in a preset direction when there are nine detection regions.
  • the largest contour in the detection region is selected to perform PCA principal component analysis to obtain the contour direction.
  • the obtained contour direction can be used as the arrangement direction of the reaction chambers. In particular, when there are multiple detection areas, you can perform PCA principal component analysis on the largest contour in the multiple detection areas to obtain the contour direction.
  • step S25 can determine the image deflection angle of the biochip image and the preprocessing image according to the contour direction, and perform deflection angle correction on the biochip image and/or the preprocessing amount image to obtain a deflection corrected image.
  • the present application can solve the problem of deflection angle detection by adjoining the same-direction region of interest to form the largest contour and then using the PCA principal component analysis method.
  • step S2 includes:
  • Step S27 increasing the selection area with a preset ratio and randomly selecting a preset number of detection areas in the preprocessed image.
  • Step S28 iteratively detect the deflection angle of the image until the deflection angle of the image is smaller than a preset angle threshold to obtain a deflection corrected image.
  • steps S26 and S27 may be implemented by the correction module 12 . That is to say, the correction module 12 can be used to increase the selection area in a preset ratio to randomly select the detection area again, and to repeatedly and iteratively detect the image deflection angle until the image deflection angle is smaller than the preset angle threshold to obtain a deflection corrected image.
  • the image deflection angle is repeatedly and iteratively detected through detection regions of different sizes, thereby ensuring the accuracy of the image deflection angle.
  • the preset angle threshold value range can be determined by the following conditional formula:
  • ⁇ is the preset angle threshold
  • dist is the area distance of the area of interest
  • rad is the area radius of the area of interest
  • m is the number of rows of the area of interest in the detection area
  • n is the number of columns of the area of interest in the detection area.
  • the biochip image can be accurately aligned with the help of hardware equipment during shooting, so that the deflection correction image can be directly determined according to the biochip image shot after accurate alignment. In this case, it can be omitted.
  • a marker bit may also be set on the biochip entity. After the biochip image is acquired, a relative coordinate system can be constructed by identifying the marker bit on the biochip, and the deflection angle of the chip relative to the camera can be obtained, and then the deflection correction can be obtained by correction. image.
  • the angle deflection correction may not be limited to the above-discussed embodiments, and an appropriate correction method may be selected according to the actual situation, so that the biochip image analysis device 10 can determine, according to the deflection correction image, that the region of interest on the chip satisfies the horizontal or vertical alignment relative to each other.
  • the location is not specifically limited here.
  • step S2 includes:
  • Step S27' increasing the selection area with a preset ratio and randomly selecting a preset number of detection areas in the preprocessed image
  • Step S28' repeating the iterative detection of the deflection angle of the image for a preset number of times to obtain a deflection corrected image.
  • step S26' and step S27' can be implemented by the correction module 12. That is to say, the correction module 12 can be used to increase the selection area at a preset ratio to randomly select the detection area, and to repeat iteratively detect the deflection angle of the image for a preset number of times to obtain a deflection corrected image.
  • the preset number of times may be preset by the system or set by a user according to actual conditions, for example, the preset number of times may be 6 times.
  • step S3 includes:
  • Step S31 constructing a notch filter
  • step S32 a notch filter is used to filter the deflection correction image to obtain a periodic pattern enhanced image.
  • steps S31 and S32 may be implemented by the processing module 13 . That is to say, the processing module 13 can be used for constructing a notch filter, and for filtering the deflection correction image by using the notch filter to obtain a periodic pattern enhanced image.
  • a notch filter can make the time and space complexity of the algorithm of the biochip image analysis method of the embodiment of the present application lower, and the performance requirements of the hardware device are more relaxed, thereby reducing the cost and improving the operation while ensuring the effect. efficiency.
  • step S33 includes:
  • Step S331 using a box filter to perform smooth filtering processing on the periodic pattern enhanced image
  • Step S332 Integrate the pixel values in the horizontal direction and the vertical direction on the smoothed image to obtain the first integration curve in the horizontal direction and the second integration curve in the vertical direction, and take the poles of the first integration curve and the second integration curve. set of small value points to determine grid interval lines; and
  • Step S333 dividing grid regions according to grid interval lines.
  • step S331 , step S332 and step S333 may be implemented by the processing module 13 . That is to say, the processing module 13 can be used to perform smoothing filtering on the periodic pattern enhanced image by using a box filter, and to integrate the pixel values in the horizontal direction and the vertical direction on the smoothed image to obtain the horizontal image.
  • the first integral curve in the direction and the second integral curve in the vertical direction taking the minimum point set of the first integral curve and the second integral curve to determine the grid interval line, and for dividing the grid according to the grid interval line area.
  • box filter smoothing can help to reduce other noise in the image interfering with the image, and then divide the grid area.
  • the length and width of the operator of the box filter satisfy the following conditional expressions:
  • b is the length and width of the box filter operator
  • dist is the region spacing of the region of interest
  • rad is the region radius of the region of interest.
  • step S3 includes:
  • Step S34 using Hough circle transform to detect the region of interest in the deflection corrected image.
  • Step S35 draw a circle according to the detected region of interest to make an approximation to divide it into a grid region.
  • steps S34 and S35 can be implemented by the processing module 13, that is, the processing module 13 can be used to detect the region of interest in the deflection corrected image by using the Hough circle transform, and to draw the region of interest according to the detected region of interest.
  • the circle is approximated to divide the grid area.
  • the Hough original transform can also be used to detect the area of interest in the deflection correction image, and then draw a circle according to the detected area of interest to approximate the grid area, so as to achieve Grid area division.
  • division of the grid area may not be limited to the above-discussed embodiments, and other division methods may be used for division as required, which is not specifically limited here.
  • step S4 includes:
  • Step S41 traverse the grid area, and obtain the mean square error of pixel values for each grid area corresponding to the preprocessed image
  • Step S42 when the mean square error is greater than the variance threshold, mark the corresponding region of interest sample as positive;
  • Step S43 when the mean square error is not greater than the variance threshold, mark the sample corresponding to the region of interest as negative.
  • step S41 , step S42 and step S43 may be implemented by the identification module 14 . That is to say, the identification module 14 can be used to traverse the grid area, obtain the mean square error of pixel values for each grid area corresponding to the preprocessed image, and be used to mark the corresponding area of interest when the mean square error is greater than the variance threshold. The sample is positive, and is used to mark the corresponding region of interest sample as negative when the mean variance is not greater than the variance threshold.
  • the mean square error of the pixel values of each grid is compared with the variance threshold, thereby realizing the division of positive and negative.
  • the method for analyzing the biochip image includes: outputting the positive and negative identification results of the reaction chamber.
  • the biochip image analysis device 10 includes an output module (not shown in the figure), and the output module can be used to output the positive and negative identification results of the reaction chamber.
  • Embodiments of the present application further provide an image analysis method, including the steps of the biochip image analysis method in any of the above embodiments.
  • the effective identification of the matrix biochip fluorescence image with high throughput and low signal-to-noise ratio can be realized.
  • the solution is solved by high-frequency filtering.
  • the problem of uneven fluorescence illumination of microchips is solved;
  • the problem of deflection angle detection is solved by the maximum profile PCA principal component analysis method of adjacent chambers;
  • the periodic pattern prior of matrix biochips is used to construct a notch filter.
  • the noise caused by surface stains, sample injection process, and reaction process is reduced to the greatest extent, and the automatic analysis of chamber location positioning and sample negative and positive judgment is successfully realized.
  • an embodiment of the present application further provides a computer device 100, including a processor 110 and a memory 120, the memory 120 stores a computer program 122, and the computer program 122 is executed by the processor 110.
  • a computer device 100 including a processor 110 and a memory 120
  • the memory 120 stores a computer program 122
  • the computer program 122 is executed by the processor 110.
  • computer program 122 when executed by processor 110, implements the following steps:
  • Step S1 acquiring a biochip image for processing to obtain a preprocessed image
  • Step S2 randomly select a detection area and detect a reaction chamber in the detection area to process a deflection correction image
  • Step S3 performing enhancement processing on the deflection correction image and identifying the negative and positive of the region of interest in the preprocessed image according to the enhanced image.
  • the computer device 100 of the embodiment of the present application executes the computer program 122 through the processor 110, and can effectively identify the matrix-type biochip fluorescence image with high throughput and low signal-to-noise ratio.
  • the improved processing method solves the problem of microscopic problems through filtering.
  • Embodiments of the present application further provide a storage medium on which a computer program is stored, and when the computer program is executed by one or more processors, implements the method for analyzing a biochip image in any of the foregoing embodiments.
  • references to the terms “one embodiment,” “some embodiments,” “illustrative embodiments,” “examples,” “specific examples,” or “some examples” and the like are meant to incorporate embodiments A particular feature, structure, material, or characteristic described or exemplified is included in at least one embodiment or example of the present application.
  • schematic representations of the above terms do not necessarily refer to the same embodiment or example.
  • the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
  • each functional unit in each embodiment of the present application may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.
  • the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Medical Informatics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Processing (AREA)

Abstract

一种生物芯片图像的分析方法包括：(S1)获取生物芯片图像并进行预处理以得到预处理图像；(S2)对预处理图像进行角度偏转校正以得到偏转校正图像；(S3)对偏转校正图像进行增强处理并根据增强处理后的图像对预处理图像中兴趣区域的阴阳性进行识别。此外，还公开了一种生物芯片图像的分析装置(100)、图像的分析方法、计算机设备(200)及存储介质。

Description

生物芯片图像的分析方法及装置、计算机设备和存储介质 技术领域
本申请涉及生物检测技术领域，更具体而言，涉及一种生物芯片图像的分析方法及装置、图像的分析方法、计算机设备和存储介质。
背景技术
在生物医疗领域中，阵列型生物芯片技术是对基因分析及疾病进行精确诊断的一种重要工具，能够克服传统方法需要多次重复试验的弊端，有效节约人力、样本量，提高了检测精度，是现代生物医疗领域中进行生物样本检测的重要手段之一。使用自动检测的方式对生物芯片进行检测通常是通过提取图像特征，自主得到芯片行列数目、位置信息，对样本点的阴阳性进行检测和分析。现有方案一般是针对信噪比较高的理想场景图像进行分析处理，然而对于高通量低信噪比图像还没有有效处理方法。
发明内容
本申请实施方式提供一种生物芯片图像的分析方法及生物芯片图像的分析装置、图像的分析方法、计算机设备和存储介质。
本申请实施方式的一种生物芯片图像的分析方法包括：获取生物芯片图像并进行预处理以得到预处理图像；对所述预处理图像进行角度偏转校正以得到偏转校正图像；对所述偏转校正图像进行增强处理并根据增强处理后的图像对所述预处理图像中兴趣区域的阴阳性进行识别。
在某些实施方式中，所述获取生物芯片图像以处理得到预处理图像包括：获取原始图像、相机内参矩阵和畸变系数；和根据所述相机内参矩阵和所述畸变系数对所述原始图像进行校正以得到所述生物芯片图像。
在某些实施方式中，所述生物芯片图像的分析方法包括：利用标定板，采用传统标定法标定拍摄用的相机，以获得所述相机内参矩阵和所述畸变系数。
在某些实施方式中，所述原始图像为发生了生物化学反应的生物芯片的荧光图像。
在某些实施方式中，所述预处理图像包括高频分量图像，所述获取生物芯片图像以处理得到预处理图像包括：对所述生物芯片图像进行高斯滤波处理以得到低频分量图像；和利用所述生物芯片图像减去所述低频分量图像以得到所述高频分量图像。
在某些实施方式中，所述对所述预处理图像进行角度偏转校正以得到偏转校正图像包括：在所述预处理图像中选择预设数量的检测区域；利用霍夫圆变换检测所述检 测区域内的所述兴趣区域的中心和半径；和根据所述兴趣区域的中心和半径做圆以确定所述兴趣区域并对所述兴趣区域进行分割。
在某些实施方式中，所述在所述预处理图像中选择预设数量的检测区域包括：在所述预处理图像的预定区域内选择相应的所述检测区域。
在某些实施方式中，所述检测区域为长方形区域，所述检测区域中包括至少两行或至少两列的部分所述兴趣区域。
在某些实施方式中，所述对所述预处理图像进行角度偏转校正以得到偏转校正图像包括：对分割的图像进行膨胀处理以在预设方向上连通相邻的所述兴趣区域；取膨胀处理后所述腔检测区域的最大轮廓进行主成分分析以得到轮廓方向；和根据所述轮廓方向确定图像偏转角度以对所述预处理图像进行校正得到所述偏转校正图像。
在某些实施方式中，所述对所述预处理图像进行角度偏转校正以得到偏转校正图像包括：以预设比例增大选择区域重新在所述预处理图像中选择预设数量的所述检测区域；和重复迭代检测所述图像偏转角度直至所述图像偏转角度小于预设角度阈值以得到所述偏转校正图像。
在某些实施方式中，所述预设角度阈值取值范围可以通过下列条件式确定：
Figure PCTCN2021077355-appb-000001
其中，θ为所述预设角度阈值，dist为所述兴趣区域的区域间距，rad为所述兴趣区域的区域半径，m为所述检测区域内所述兴趣区域的行数，n为所述检测区域内所述兴趣区域的列数。
在某些实施方式中，所述对所述预处理图像进行角度偏转校正以得到偏转校正图像包括：以预设比例增大选择区域重新在所述预处理图像中选择预设数量的所述检测区域；和重复迭代检测所述图像偏转角度达到预设次数以得到所述偏转校正图像。
在某些实施方式中，所述对所述偏转校正图像进行增强处理并根据增强处理后的图像对所述预处理图像中兴趣区域的阴阳性进行识别包括：构建陷波滤波器；和利用所述陷波滤波器对所述偏转校正图像进行滤波处理得到周期性图式增强图像。
在某些实施方式中，所述对所述偏转校正图像进行增强处理并根据增强处理后的图像对所述预处理图像中兴趣区域的阴阳性进行识别包括：采用盒式滤波器对所述周期性图式增强图像进行平滑滤波处理；对平滑后的图像进行水平方向和竖直方向的像素值积分以获得所述水平方向的第一积分曲线和所述竖直方向的第二积分曲线，取所述第一积分曲线和所述第二积分曲线的极小值点集以确定网格间隔线；和根据所述网格间隔线划分网格区域。
在某些实施方式中，所述盒式滤波器的算子的长宽满足下列条件式：
Figure PCTCN2021077355-appb-000002
Figure PCTCN2021077355-appb-000003
其中，b为所述盒式滤波器的算子的长宽，dist为所述兴趣区域的区域间距， rad为所述兴趣区域的区域半径。
在某些实施方式中，所述对所述偏转校正图像进行增强处理并根据增强处理后的图像对所述预处理图像中兴趣区域的阴阳性进行识别包括：遍历所述网格区域，对所述预处理图像对应的每个所述网格区域求取像素值均方差；在所述均方差大于方差阈值时，标记对应的所述兴趣区域样本为阳性；和在所述均方差不大于方差阈值时，标记对应的所述兴趣区域样本为阴性。
在某些实施方式中，所述生物芯片图像的分析方法包括：输出所述兴趣区域的阴阳性识别结果。
本申请实施方式还提供一种图像的分析方法，包括上述任一实施方式所述的生物芯片图像的分析方法的步骤。
本申请实施方式还提供一种生物芯片图像的分析装置包括获取模块、校正模块、处理模块和识别模块，所述获取模块用于获取生物芯片图像并进行预处理以得到预处理图像；所述校正模块用于对所述预处理图像进行角度偏转校正以得到偏转校正图像；所述处理模块用于对所述偏转校正图像进行周期性图式增强处理并划分腔室网格；和对所述偏转校正图像进行增强处理并根据增强处理后的图像对所述预处理图像中兴趣区域的阴阳性进行识别。
本申请实施方式还提供一种计算机设备，包括处理器和存储器，所述存储器存储有计算机程序，所述计算机程序被所述处理器执行时实现上述任一实施方式的生物芯片图像的分析方法，或上述实施方式所述的图像的分析方法。
本申请实施方式还提供一种存储介质，其上存储有计算机程序，当所述计算机程序被一个或多个处理器执行时实现上述任一实施方式所述的生物芯片图像的分析方法，或上述实施方式所述的图像的分析方法。
本申请实施方式的生物芯片图像的分析方法及装置、计算机设备和存储介质中，能够实现对高通量低信噪比的矩阵型生物芯片荧光图像的有效识别，具体的，改进的处理方法通过滤波解决了微观芯片的荧光光照不均问题；通过网格划分成功实现腔室位置定位、样本阴阳性判定的自动化分析。
本申请的实施方式的附加方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本申请的实施方式的实践了解到。
附图说明
本申请的上述和/或附加的方面和优点从结合下面附图对实施方式的描述中将变得明显和容易理解，其中：
图1是本申请实施方式的生物芯片图像的分析方法的流程示意图。
图2是本申请实施方式的生物芯片图像的分析装置的模块示意图。
图3是本申请实施方式的生物芯片图像的分析方法的另一流程示意图。
图4是本申请实施方式的生物芯片图像的分析方法的又一流程示意图。
图5是本申请实施方式的生物芯片图像的分析方法的再一流程示意图。
图6是本申请实施方式的生物芯片图像的分析方法的再一流程示意图。
图7是本申请实施方式的对分割的反应腔室进行膨胀处理后的轮廓示意图。
图8是本申请实施方式的生物芯片图像的分析方法的再一流程示意图。
图9是本申请实施方式的生物芯片图像的分析方法的再一流程示意图。
图10是本申请实施方式的生物芯片图像的分析方法的再一流程示意图。
图11是本申请实施方式的生物芯片图像傅里叶变换到频域的幅值示意图。
图12是本申请实施方式的构建滤波器的示意图。
图13是本申请实施方式的生物芯片图像的分析方法的再一流程示意图。
图14是本申请实施方式的生物芯片图像的分析方法的再一流程示意图。
图15是本申请实施方式的生物芯片图像的分析方法的再一流程示意图。
图16是本申请实施方式的计算机设备的模块示意图。
具体实施方式
下面详细描述本申请的实施方式，所述实施方式的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施方式是示例性的，仅用于解释本申请，而不能理解为对本申请的限制。
请参阅图1和图2，本申请实施方式的一种生物芯片图像的分析方法，对高通量低信噪比的矩阵型生物芯片荧光图像进行识别，实现腔室位置定位、样本阴阳性判定的自动化分析。
本申请实施方式的生物芯片图像的分析方法可以用于本申请实施方式的生物芯片图像的分析装置10，也即是说，本申请实施方式的生物芯片图像的分析装置10可以采用实施方式的生物芯片图像的分析方法对高通量低信噪比的矩阵型生物芯片荧光图像进行识别，实现腔室位置定位、样本阴阳性判定的自动化分析。
在某些实施方式中，生物芯片分析包括：
步骤S1，获取生物芯片图像并进行预处理以得到预处理图像；
步骤S2，对预处理图像进行角度偏转校正以得到偏转校正图像；
步骤S3，对偏转校正图像进行增强处理并根据增强处理后的图像对预处理图像中 兴趣区域的阴阳性进行识别。
具体地，生物芯片图像的分析装置10包括获取模块11、校正模块12和处理模块13，步骤S1可以由获取模块11实现，步骤S2可以由校正模块12实现，步骤S3可以由处理模块13实现。也即是说，获取模块11可以用于获取生物芯片图像以处理得到预处理图像。校正模块12可以用于随机选择检测区域并检测检测区域内的反应腔室以处理得到偏转校正图像。处理模块13可以用于对偏转校正图像进行增强处理并根据增强处理后的图像对预处理图像中兴趣区域的阴阳性进行识别。
本申请实施方式的生物芯片图像的分析方法及装置中，能够实现对高通量低信噪比的矩阵型生物芯片荧光图像的有效识别，具体的，改进的处理方法通过滤波解决了微观芯片的荧光光照不均问题；通过图像增强处理实现腔室位置定位、样本阴阳性判定的自动化分析。
请参阅图3，在某些实施方式中，步骤S1包括：
步骤S11，获取原始图像、相机内参矩阵和畸变系数；和
步骤S12，根据相机内参矩阵和畸变系数对原始图像进行校正以得到生物芯片图像。
具体地，步骤S11和步骤S12可以由获取模块11实现。也即是说，获取模块11可以用于获取原始图像、相机内参矩阵和畸变系数，以及用于根据相机内参矩阵和畸变系数对原始图像进行校正以得到生物芯片图像。
可以理解，通过获取相机内参矩阵以及畸变系数可以校正相机采集的原始图像中产生的畸变，从而使得校正后的生物芯片图像可以更真实地显示出生物芯片的特性。如此，可以有利于保证生物芯片分析的有效性和准确性。
在一些例子中，生物芯片可以为四边形，生物芯片上呈阵列排布有多个反应腔室。需要说明的是，在本申请实施方式中以生物芯片图像中反应腔室所在的区域为兴趣区域进行说明。
在某些实施方式中，生物芯片图像的分析方法包括：利用标定板，采用传统标定法标定拍摄用的相机，以获得相机内参矩阵和畸变系数。
具体地，生物芯片图像的分析装置10可以包括标定模块15，标定模块15可以用于利用标定板，采用传统标定法标定拍摄用的相机，以获得相机内参矩阵和畸变系数。
其中，通过标定板对相机参数进行标定时，标定板可以具有预定的图案，例如网格图案或黑白方块图案等，相机在一定的拍摄距离下拍摄标定板的图像，如此，可以将标定板的图像与标定板的图案进行对比，根据标定板图像和标定板的图案中对应特征点的偏移，结合拍摄距离得到相机拍摄相关的相机内参矩阵和畸变参数。
需要说明的是，在一些实施方式中，相机内参矩阵和畸变系数可以是预先标定好 并预存在相机或生物芯片图像的分析装置10中，如此，生物分析装置可以从相机获取对应的相机内参矩阵和畸变系数，或者根据相机的编号或型号确定相机内参矩阵和畸变系数。当然，在其他实施方式中，生物芯片图像的分析装置10还可以是每次获取生物芯片的图像之前，均检测相应相机对应的相机内参矩阵和畸变系数，如此，可以保证相机内参矩阵和畸变系数的有效性。
在某些实施方式中，原始图像为发生了生物化学反应的生物芯片的荧光图像。
其中，当待检测的生物样本被加载到生物芯片上，并发生了生物化学反应后，利用特定的设备，可以采集到对应的生物芯片的荧光图像。可以理解，荧光图像中，通常不同的反应腔室显示的色彩、亮度可以相同或不相同。
请参阅图4，在某些实施方式中，预处理图像包括高频分量图像，步骤S1包括：
步骤S13，对生物芯片图像进行高斯滤波处理以得到低频分量图像；和
步骤S14，利用生物芯片图像减去低频分量图像以得到高频分量图像。
具体地，步骤S13和步骤S14可以由获取模块11实现。也即是说，获取模块11可以用于对生物芯片图像进行高斯滤波处理以得到低频分量图像，以及用于利用生物芯片图像减去低频分量图像以得到高频分量图像。
如此，利用高斯滤波得到低频分量图像，然后将生物芯片图像中的低频分量减去得到高频分量图像，从而实现高频滤波，从而解决微观芯片的荧光光照不均问题。
当然，在其他实施方式中，预处理图像可以不限于上述讨论的高频分量图像，而可以根据实际需求获取灰度图像、低频分量图像和边缘检测图像等。其中灰度图像可以根据图像灰度化处理得到，低频分量图像可以通过低频分量提取处理得到，边缘检测图像可以通过图像边缘提取处理得到。此外，预处理图像还可以上述处理方法中的一种或多种处理方法按预设顺序处理得到，在此不做具体限定。
请参阅图5，在某些实施方式中，步骤S2包括：
步骤S21，在预处理图像中选择预设数量的检测区域；
步骤S22，利用霍夫圆变换检测检测区域内的兴趣区域的中心和半径；和
步骤S23，根据兴趣区域的中心和半径做圆以确定兴趣区域并对兴趣区域进行分割。
具体地，步骤S21、步骤S22和步骤S23可以由校正模块12实现。也即是说，校正模块12可以用于在预处理图像中选择预设数量的检测区域，及用于利用霍夫圆变换检测检测区域内的兴趣区域的中心和半径，以及用于根据兴趣区域的中心和半径做圆以确定兴趣区域并对兴趣区域进行分割。
以兴趣区域为图像中反应腔室所在的区域为例，在检测反应腔室的排列时，需要确定检测区域内的反应腔室的位置，由于反应腔室一般为圆形，如此，通过霍夫变换 可以实现腔室中心和半径的检测，进一步地，根据腔室中心和半径确定反应腔室的位置后，可以实现对反应腔室的分割。
在某些实施方式中，步骤S21包括：在预处理图像的预定区域内选择相应的检测区域。
校正模块12可以用于在预处理图像的预定区域内选择相应的检测区域。
其中，预设区域可以是用户根据经验进行设定的，或根据算法自动选择的。当然，检测区域还可以是在预处理图像中随机选取的区域，在此不做具体限定。
在某些实施方式中，检测区域为长方形区域，检测区域中包括至少两行或至少两列的部分兴趣区域。
可以理解，对高频分量图像进行偏转校正得到偏转校正图像时，需要确定高频分量图像的偏转角度。由于生物芯片上的反应腔室一般呈阵列设置，即兴趣区域一般呈阵列设置，如此，通过腔室的排列方向可实现图像偏转角度的检测，采用长方形区域有利于确定选择的检测区域长边方向与反应腔室排列方向的相对偏转角度。
其中，检测区域中包括至少两行或至少两列的部分兴趣区域可以保证反应腔室排列方向的检测。
需要说明的是，检测区域的尺寸可以根据兴趣区域的区域间距以及兴趣区域的半径等灵活配置，在此不做具体限定。
当然，在其他实施方式中，检测区域的形状可以不限于上述讨论的长方形，而可以根据实际需要选择正方形、三角形、圆形、平行四边形等其他合适的形状，在此不做具体限定。
在某些实施方式中，每次选取的检测区域的预设数量可以是多个，多个检测区域的方向可以不同，从而提高图像偏转角度检测的效率和准确性。例如，每次选取的检测区域的预设数量可以是9个。
请参阅图6和图7，在某些实施方式中，步骤S2包括：
步骤S24，对分割的图像进行膨胀处理以在预设方向上连通相邻的兴趣区域；
步骤S25，取膨胀处理后检测区域内的最大轮廓进行主成分分析以得到轮廓方向；和
步骤S26，根据轮廓方向确定图像偏转角度以对预处理图像进行校正得到偏转校正图像。
具体地，步骤S24。步骤S25和步骤S26可以由校正模块12实现。也即是说，校正模块12可以用于对分割的图像进行膨胀处理以在预设方向上连通相邻的兴趣区域，及用于取膨胀处理后检测区域内的最大轮廓进行主成分分析以得到轮廓方向，以及用 于根据轮廓方向确定图像偏转角度以对预处理图像进行校正得到偏转校正图像。
在步骤S24中，可以将分割后的兴趣区域按预设方向进行膨胀处理，使得兴趣区域的轮廓沿预设方向延伸，从而相邻的兴趣区域的轮廓相互连通。在一个例子中，预设方向可以是长方形的检测区域的长边方向。图7示出了检测区域为9个时，对9个腔室内的兴趣区域按预设方向进行膨胀处理后得到的轮廓示意图。
兴趣区域的轮廓相连通后，步骤S25中选择检测区域内的最大轮廓进行PCA主成分分析以得到轮廓方向。可以理解，由于最大轮廓一般为相邻的多个兴趣区域连通形成，在一个例子中，得到的轮廓方向即可以作为反应腔室的排列方向。特别地，有多个检测区域时，可以去多个检测区域中的最大轮廓进行PCA主成分分析以得到轮廓方向。
从而步骤S25可以根据轮廓方向确定生物芯片图像和预处理图像的图像偏转角度，以及对生物芯片图像和/或预处理量图像进行偏转角度校正得到偏转校正图像。
如此，本申请可以通过邻接同向兴趣区域形成最大轮廓然后利用PCA主成分分析法解决偏转角度检测的问题。
请参阅图8，在某些实施方式中，步骤S2包括：
步骤S27，以预设比例增大选择区域重新在预处理图像中随机选择预设数量的检测区域；和
步骤S28，重复迭代检测图像偏转角度直至图像偏转角度小于预设角度阈值以得到偏转校正图像。
具体地，步骤S26和步骤S27可以由校正模块12实现。也即是说，校正模块12可以用于以预设比例增大选择区域重新随机选择检测区域，以及用于重复迭代检测图像偏转角度直至图像偏转角度小于预设角度阈值以得到偏转校正图像。
如此，通过不同大小的检测区域重复迭代检测图像偏转角度，从而保证图像偏转角度的准确性。
在某些实施方式中，预设角度阈值取值范围可以通过下列条件式确定：
Figure PCTCN2021077355-appb-000004
其中，θ为预设角度阈值，dist为兴趣区域的区域间距，rad为兴趣区域的区域半径，m为检测区域内兴趣区域的行数，n为检测区域内兴趣区域的列数。
需要说明的是，在一些实施例中，生物芯片图像可以在拍摄时借助硬件仪器设备进行精确对准，从而可以根据精确对准后拍摄的生物芯片图像直接确定偏转校正图像，此时，可省略检测图像偏转角度的过程。在另一些实施例中，生物芯片实体上还可以设置标志位，获取生物芯片图像后，可以通过识别生物芯片上的标志位来构建相对坐标系，获取芯片相 对摄像头偏转角度，进而校正得到偏转校正图像。
当然，角度偏转校正可以不限于上述讨论的实施方式，而可以根据实际情况选择合适的校正方法，使得生物芯片图像的分析装置10可以根据偏转校正图像确定芯片上的兴趣区域满足横向或纵向排列相对位置，在此不做具体限定。
请参阅图9，在某些实施方式中，步骤S2包括：
步骤S27’，以预设比例增大选择区域重新在预处理图像中随机选择预设数量的检测区域；和
步骤S28’，重复迭代检测图像偏转角度预设次数以得到偏转校正图像。
具体地，步骤S26’和步骤S27’可以由校正模块12实现。也即是说，校正模块12可以用于以预设比例增大选择区域重新随机选择检测区域，以及用于重复迭代检测图像偏转角度预设次数以得到偏转校正图像。
如此，通过不同大小的检测区域重复迭代检测图像偏转角度预设次数，同样可以保证图像偏转角度的准确性。在一个例子中，预设次数可以由系统预设或有用户根据实际情况进行设置，例如，预设次数可以是6次。
请参阅图10、图11和图12，在某些实施方式中，步骤S3包括：
步骤S31，构建陷波滤波器；和
步骤S32，利用陷波滤波器对偏转校正图像进行滤波处理得到周期性图式增强图像。
具体地，步骤S31和步骤S32可以由处理模块13实现。也即是说，处理模块13可以用于构建陷波滤波器，以及用于利用陷波滤波器对偏转校正图像进行滤波处理得到周期性图式增强图像。
如此，利用矩阵型生物芯片的周期性图式先验，通过构建陷波滤波器，最大程度减弱了表面污渍、进样过程、反应过程造成的噪声。
在一个例子中，如图10所示的生物芯片图像傅立叶变换到频域得到的幅值图中，大部分图像信息集中于低频部分，因而通过滤除中央部分的图像信息能够去除大部分图像噪声，同时，位于中央竖直和中央水平方向的信息是最易滤出的周期性图式信息，如此，步骤S31中构建陷波滤波器可以如图11所示，以用于去除非周期性图式的图像噪声。
采用陷波滤波器可以使得本申请实施方式的生物芯片图像的分析方法的算法的时间、空间复杂度更低，对硬件设备的性能要求更宽松，从而在保证效果的同时降低了成本、提高运行效率。
请参阅图13，在某些实施方式中，步骤S33包括：
步骤S331，采用盒式滤波器对周期性图式增强图像进行平滑滤波处理；
步骤S332，对平滑后的图像进行水平方向和竖直方向的像素值积分以获得水平方向的第一积分曲线和竖直方向的第二积分曲线，取第一积分曲线和第二积分曲线的极小值点集以确定网格间隔线；和
步骤S333，根据网格间隔线划分网格区域。
具体地，步骤S331、步骤S332和步骤S333可以由处理模块13实现。也即是说，处理模块13可以用于采用盒式滤波器对周期性图式增强图像进行平滑滤波处理，及用于对平滑后的图像进行水平方向和竖直方向的像素值积分以获得水平方向的第一积分曲线和竖直方向的第二积分曲线，取第一积分曲线和第二积分曲线的极小值点集以确定网格间隔线，以及用于根据网格间隔线划分网格区域。
如此，采用盒式滤波器平滑可以有利于减弱图像中存在的其他噪声干扰影像，进而划分网格区域。
在某些实施方式中，盒式滤波器的算子的长宽满足下列条件式：
Figure PCTCN2021077355-appb-000005
其中，b为盒式滤波器的算子的长宽，dist为兴趣区域的区域间距，rad为兴趣区域的区域半径。
请参阅图14，在其他实施方式中，步骤S3包括：
步骤S34，利用霍夫圆变换检测偏转校正图像中的兴趣区域；和
步骤S35，根据检测到的兴趣区域画圆做近似以划分得到网格区域。
具体地，步骤S34和步骤S35可以由处理模块13实现，也即是说，处理模块13可以用于利用霍夫圆变换检测偏转校正图像中的兴趣区域，以及用于根据检测到的兴趣区域画圆做近似以划分得到网格区域。
也即是说，对于网格区域的划分，还可以采用霍夫原变换的方式检测偏转校正图像中的兴趣区域，然后根据检测到的兴趣区域室画圆做近似以得到网格区域，从而实现网格区域的划分。
当然，对于网格区域的划分，可以不限于上述讨论的实施方式，而可以根据需要采用其他的划分方法进行划分，在此不做具体限定。
请参阅图15，在某些实施方式中，步骤S4包括：
步骤S41，遍历网格区域，对预处理图像对应的每个网格区域求取像素值均方差；
步骤S42，在均方差大于方差阈值时，标记对应的兴趣区域样本为阳性；和
步骤S43，在均方差不大于方差阈值时，标记对应的兴趣区域样本为阴性。
具体地，步骤S41、步骤S42和步骤S43可以由识别模块14实现。也即是说，识别模块14可以用于遍历网格区域，对预处理图像对应的每个网格区域求取像素值均方差， 及用于在均方差大于方差阈值时，标记对应的兴趣区域样本为阳性，以及用于在均方差不大于方差阈值时，标记对应的兴趣区域样本为阴性。
如此，根据各个网格的像素值均方差与方差阈值进行比较，从而实现阴阳性的划分。
在某些实施方式中，生物芯片图像的分析方法包括：输出反应腔室的阴阳性识别结果。
具体地，生物芯片图像的分析装置10包括输出模块(图未示出)，输出模块可以用于输出反应腔室的阴阳性识别结果。
本申请实施方式还提供一种图像的分析方法，包括上述任一实施方式的生物芯片图像的分析方法的步骤。
本申请实施方式的生物芯片图像的分析方法和生物芯片图像的分析装置10中，能够实现对高通量低信噪比的矩阵型生物芯片荧光图像的有效识别，具体的，通过高频滤波解决了微观芯片的荧光光照不均问题；通过邻接同向腔室最大轮廓PCA主成分分析法解决了偏转角度检测的问题；利用矩阵型生物芯片的周期性图式先验，通过构建陷波滤波器最大程度减弱了表面污渍、进样过程、反应过程造成的噪声，成功实现腔室位置定位、样本阴阳性判定的自动化分析。
请参阅图16，本申请实施方式还提供一种计算机设备100，包括处理器110和存储器120，存储器120存储有计算机程序122，计算机程序122被处理器110执行时实现上述任一实施方式的生物芯片图像的分析方法。
在一个例子中，计算机程序122被处理器110执行时实现以下步骤：
步骤S1，获取生物芯片图像以处理得到预处理图像；
步骤S2，随机选择检测区域并检测检测区域内的反应腔室以处理得到偏转校正图像；
步骤S3，对偏转校正图像进行增强处理并根据增强处理后的图像对预处理图像中兴趣区域的阴阳性进行识别。
本申请实施方式的计算机设备100通过处理器110执行计算机程序122，能够实现对高通量低信噪比的矩阵型生物芯片荧光图像的有效识别，具体的，改进的处理方法通过滤波解决了微观芯片的荧光光照不均问题；通过网格划分成功实现腔室位置定位、样本阴阳性判定的自动化分析。
本申请实施方式还提供一种存储介质，其上存储有计算机程序，当计算机程序被一个或多个处理器执行时实现上述任一实施方式的生物芯片图像的分析方法。
在本说明书的描述中，参考术语“一个实施方式”、“一些实施方式”、“示意性实施方式”、 “示例”、“具体示例”、或“一些示例”等的描述意指结合实施方式或示例描述的具体特征、结构、材料或者特点包含于本申请的至少一个实施方式或示例中。在本说明书中，对上述术语的示意性表述不一定指的是相同的实施方式或示例。而且，描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施方式或示例中以合适的方式结合。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现定制逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分，并且本申请的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本申请的实施例所属技术领域的技术人员所理解。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。
此外，在本申请各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。上述提到的存储介质可以是只读存储器，磁盘或光盘等。
尽管上面已经示出和描述了本申请的实施方式，可以理解的是，上述实施方式是示例性的，不能理解为对本申请的限制，本领域的普通技术人员在本申请的范围内可以对上述实施方式进行变化、修改、替换和变型。

Claims (21)

  1. 一种生物芯片图像的分析方法，其特征在于，包括：
    获取生物芯片图像并进行预处理以得到预处理图像；
    对所述预处理图像进行角度偏转校正以得到偏转校正图像；和
    对所述偏转校正图像进行增强处理并根据增强处理后的图像对所述预处理图像中兴趣区域的阴阳性进行识别。
  2. 根据权利要求1所述的生物芯片图像的分析方法，其特征在于，所述获取生物芯片图像以处理得到预处理图像包括：
    获取原始图像、相机内参矩阵和畸变系数；和
    根据所述相机内参矩阵和所述畸变系数对所述原始图像进行校正以得到所述生物芯片图像。
  3. 根据权利要求2所述的生物芯片图像的分析方法，其特征在于，所述生物芯片图像的分析方法包括：利用标定板，采用传统标定法标定拍摄用的相机，以获得所述相机内参矩阵和所述畸变系数。
  4. 根据权利要求2所述的生物芯片图像的分析方法，其特征在于，所述原始图像为发生了生物化学反应的生物芯片的荧光图像。
  5. 根据权利要求1所述的生物芯片图像的分析方法，其特征在于，所述预处理图像包括高频分量图像，所述获取生物芯片图像以处理得到预处理图像包括：
    对所述生物芯片图像进行高斯滤波处理以得到低频分量图像；和
    利用所述生物芯片图像减去所述低频分量图像以得到所述高频分量图像。
  6. 根据权利要求1所述的生物芯片图像的分析方法，其特征在于，所述对所述预处理图像进行角度偏转校正以得到偏转校正图像包括：
    在所述预处理图像中选择预设数量的检测区域；
    利用霍夫圆变换检测所述检测区域内的所述兴趣区域的中心和半径；和
    根据所述兴趣区域的中心和半径做圆以确定所述兴趣区域并对所述兴趣区域进行分割。
  7. 根据权利要求6所述的生物芯片图像的分析方法，其特征在于，所述在所述预处理图像中选择预设数量的检测区域包括：
    在所述预处理图像的预定区域内选择相应的所述检测区域。
  8. 根据权利要求6所述的生物芯片图像的分析方法，其特征在于，所述检测区域为长方形区域，所述检测区域中包括至少两行或至少两列的部分所述兴趣区域。
  9. 根据权利要求6所述的生物芯片图像的分析方法，其特征在于，所述对所述预处理图像进行角度偏转校正以得到偏转校正图像包括：
    对分割的图像进行膨胀处理以在预设方向上连通相邻的所述兴趣区域；
    取膨胀处理后所述检测区域内的最大轮廓进行主成分分析以得到轮廓方向；和
    根据所述轮廓方向确定图像偏转角度以对所述预处理图像进行校正得到所述偏转校正图像。
  10. 根据权利要求9所述的生物芯片图像的分析方法，其特征在于，所述对所述预处理图像进行角度偏转校正以得到偏转校正图像包括：
    以预设比例增大选择区域重新在所述预处理图像中选择预设数量的所述检测区域；和
    重复迭代检测所述图像偏转角度直至所述图像偏转角度小于预设角度阈值以得到所述偏转校正图像。
  11. 根据权利要求10所述的生物芯片图像的分析方法，其特征在于，所述预设角度阈值取值范围可以通过下列条件式确定：
    Figure PCTCN2021077355-appb-100001
    其中，θ为所述预设角度阈值，dist为所述兴趣区域的区域间距，rad为所述兴趣区域的区域半径，m为所述检测区域内所述兴趣区域的行数，n为所述检测区域内所述兴趣区域的列数。
  12. 根据权利要求9所述的生物芯片图像的分析方法，其特征在于，所述对所述预处理图像进行角度偏转校正以得到偏转校正图像包括：
    以预设比例增大选择区域重新在所述预处理图像中选择预设数量的所述检测区域；和
    重复迭代检测所述图像偏转角度达到预设次数以得到所述偏转校正图像。
  13. 根据权利要求1所述的生物芯片图像的分析方法，其特征在于，所述对所述偏转校正图像进行增强处理并根据增强处理后的图像对所述预处理图像中兴趣区域的阴阳性进行识别包括：
    构建陷波滤波器；和
    利用所述陷波滤波器对所述偏转校正图像进行滤波处理得到周期性图式增强图像。
  14. 根据权利要求13所述的生物芯片图像的分析方法，其特征在于，所述对所述偏转校正图像进行增强处理并根据增强处理后的图像对所述预处理图像中兴趣区域的阴阳性进行识别包括：
    采用盒式滤波器对所述周期性图式增强图像进行平滑滤波处理；
    对平滑后的图像进行水平方向和竖直方向的像素值积分以获得所述水平方向的第一积分曲线和所述竖直方向的第二积分曲线，取所述第一积分曲线和所述第二积分曲线的极小值点集以确定网格间隔线；和
    根据所述网格间隔线划分网格区域。
  15. 根据权利要求14所述的生物芯片图像的分析方法，其特征在于，所述盒式滤波器的算子的长宽满足下列条件式：
    Figure PCTCN2021077355-appb-100002
    其中，b为所述盒式滤波器的算子的长宽，dist为所述兴趣区域的区域间距，rad为所述兴趣区域的区域半径。
  16. 根据权利要求14所述的生物芯片图像的分析方法，其特征在于，所述对所述偏转校正图像进行增强处理并根据增强处理后的图像对所述预处理图像中兴趣区域的阴阳性进行识别包括：
    遍历所述网格区域，对所述预处理图像对应的每个所述网格区域求取像素值均方差；
    在所述均方差大于方差阈值时，标记对应的所述兴趣区域样本为阳性；和
    在所述均方差不大于方差阈值时，标记对应的所述兴趣区域样本为阴性。
  17. 根据权利要求1所述的生物芯片图像的分析方法，其特征在于，所述生物芯片图 像的分析方法包括：
    输出所述兴趣区域的阴阳性识别结果。
  18. 一种图像的分析方法，其特征在于，包括权利要求1-17任一项所述的生物芯片图像的分析方法的步骤。
  19. 一种生物芯片图像的分析装置，其特征在于，包括：
    获取模块，所述获取模块用于获取生物芯片图像并进行预处理以得到预处理图像；
    校正模块，所述校正模块用于对所述预处理图像进行角度偏转校正以得到偏转校正图像；
    处理模块，所述处理模块用于对所述偏转校正图像进行增强处理并根据增强处理后的图像对所述预处理图像中兴趣区域的阴阳性进行识别。
  20. 一种计算机设备，其特征在于，包括处理器和存储器，所述存储器存储有计算机程序，所述计算机程序被所述处理器执行时实现权利要求1-17任一项所述的生物芯片图像的分析方法，或权利要求18所述的图像的分析方法。
  21. 一种存储介质，其特征在于，其上存储有计算机程序，所述计算机程序被一个或多个处理器执行时实现权利要求1-17任一项所述的生物芯片图像的分析方法，或权利要求18所述的图像的分析方法。
PCT/CN2021/077355 2021-02-23 2021-02-23 生物芯片图像的分析方法及装置、计算机设备和存储介质 WO2022178653A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
PCT/CN2021/077355 WO2022178653A1 (zh) 2021-02-23 2021-02-23 生物芯片图像的分析方法及装置、计算机设备和存储介质
CN202180000294.6A CN115335854A (zh) 2021-02-23 2021-02-23 生物芯片图像的分析方法及装置、计算机设备和存储介质
US17/927,025 US20230230229A1 (en) 2021-02-23 2021-02-23 Method and apparatus for analyzing biochip image, computer device, and storage medium
EP21927101.2A EP4141787A4 (en) 2021-02-23 2021-02-23 METHOD AND DEVICE FOR ANALYSIS OF BIOCHIP IMAGES, COMPUTER DEVICE AND STORAGE MEDIUM

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/077355 WO2022178653A1 (zh) 2021-02-23 2021-02-23 生物芯片图像的分析方法及装置、计算机设备和存储介质

Publications (1)

Publication Number Publication Date
WO2022178653A1 true WO2022178653A1 (zh) 2022-09-01

Family

ID=83048558

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/077355 WO2022178653A1 (zh) 2021-02-23 2021-02-23 生物芯片图像的分析方法及装置、计算机设备和存储介质

Country Status (4)

Country Link
US (1) US20230230229A1 (zh)
EP (1) EP4141787A4 (zh)
CN (1) CN115335854A (zh)
WO (1) WO2022178653A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116528042A (zh) * 2023-06-29 2023-08-01 深圳市巨龙创视科技有限公司 一种远端摄像机的控制方法及系统
CN117671677A (zh) * 2024-02-02 2024-03-08 吉林省星博医疗器械有限公司 一种荧光微阵列识别分析方法及系统

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116704011B (zh) * 2023-08-04 2024-03-05 深圳市凯立特光电科技有限公司 一种基于数据处理的led显示屏像素校正分析系统
CN117893611B (zh) * 2024-03-14 2024-06-11 浙江华诺康科技有限公司 一种图像传感器的脏污检测方法、装置和计算机设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1570649A (zh) * 2004-04-29 2005-01-26 南京大渊生物技术工程有限责任公司 生物芯片的检测方法
WO2011073386A1 (de) * 2009-12-18 2011-06-23 Biotype Diagnostic Gmbh Eine vorrichtung zur bestimmung molekularer wechselwirkungen, sowie eine folie zur herstellung einer solchen
CN103236065A (zh) * 2013-05-09 2013-08-07 中南大学 基于主动轮廓模型和细胞神经网络的生物芯片分析方法
CN107274349A (zh) * 2017-06-05 2017-10-20 新疆大学 生物芯片荧光图像倾斜角度的确定方法及装置
CN109234158A (zh) * 2018-10-08 2019-01-18 北京京东方技术开发有限公司 生物芯片及其制造方法、操作方法、生物检测系统
CN110310334A (zh) * 2018-03-20 2019-10-08 深圳华大基因软件技术有限公司 生物芯片定位方法、基因测序仪及系统、存储介质
CN111257296A (zh) * 2020-03-20 2020-06-09 京东方科技集团股份有限公司 一种检测生物芯片样本的方法、装置及存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6931870B2 (ja) * 2017-02-15 2021-09-08 国立研究開発法人理化学研究所 細胞の再プログラム化を検出するための方法及び装置
CN110047107B (zh) * 2018-01-13 2021-04-13 深圳华大智造科技股份有限公司 相机标定方法及图像配准方法、基因测序仪及系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1570649A (zh) * 2004-04-29 2005-01-26 南京大渊生物技术工程有限责任公司 生物芯片的检测方法
WO2011073386A1 (de) * 2009-12-18 2011-06-23 Biotype Diagnostic Gmbh Eine vorrichtung zur bestimmung molekularer wechselwirkungen, sowie eine folie zur herstellung einer solchen
CN103236065A (zh) * 2013-05-09 2013-08-07 中南大学 基于主动轮廓模型和细胞神经网络的生物芯片分析方法
CN107274349A (zh) * 2017-06-05 2017-10-20 新疆大学 生物芯片荧光图像倾斜角度的确定方法及装置
CN110310334A (zh) * 2018-03-20 2019-10-08 深圳华大基因软件技术有限公司 生物芯片定位方法、基因测序仪及系统、存储介质
CN109234158A (zh) * 2018-10-08 2019-01-18 北京京东方技术开发有限公司 生物芯片及其制造方法、操作方法、生物检测系统
CN111257296A (zh) * 2020-03-20 2020-06-09 京东方科技集团股份有限公司 一种检测生物芯片样本的方法、装置及存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4141787A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116528042A (zh) * 2023-06-29 2023-08-01 深圳市巨龙创视科技有限公司 一种远端摄像机的控制方法及系统
CN116528042B (zh) * 2023-06-29 2023-10-27 深圳市巨龙创视科技有限公司 一种远端摄像机的控制方法及系统
CN117671677A (zh) * 2024-02-02 2024-03-08 吉林省星博医疗器械有限公司 一种荧光微阵列识别分析方法及系统
CN117671677B (zh) * 2024-02-02 2024-04-30 吉林省星博医疗器械有限公司 一种荧光微阵列识别分析方法及系统

Also Published As

Publication number Publication date
US20230230229A1 (en) 2023-07-20
EP4141787A1 (en) 2023-03-01
CN115335854A (zh) 2022-11-11
EP4141787A4 (en) 2023-08-09

Similar Documents

Publication Publication Date Title
WO2022178653A1 (zh) 生物芯片图像的分析方法及装置、计算机设备和存储介质
CN111243032B (zh) 一种棋盘格角点全自动检测方法
US11721018B2 (en) System and method for calculating focus variation for a digital microscope
JP5920994B2 (ja) マイクロプレートのウェル壁境界を識別するための方法及びシステム
WO2018068600A1 (zh) 图像处理方法及系统
CN112991306B (zh) 一种基于图像处理的卵裂期胚胎细胞位置分割和计数方法
WO2020037572A1 (zh) 检测图像上的亮斑的方法和装置、图像配准方法和装置
WO2021195873A1 (zh) 识别sfr测试卡图像中感兴趣区域的方法及装置、介质
CN114677525A (zh) 一种基于二值图像处理的边缘检测方法
CN116563298B (zh) 基于高斯拟合的十字线中心亚像素检测方法
CN111257296B (zh) 一种检测生物芯片样本的方法、装置及存储介质
CN111553927B (zh) 棋盘格角点检测方法、检测系统、计算机装置及存储介质
CN107529962B (zh) 图像处理装置、图像处理方法和记录介质
CN116597016A (zh) 一种光纤内窥镜图像标定方法
CN113670865B (zh) 分辨率板、分辨率评估方法及相关设备
CN114511522A (zh) 一种荧光免疫法、胶体金法试剂自动判定方法
CN114693539A (zh) 一种基于荧光图片的pcr数据处理与曲线拟合方法及pcr仪器
TW201419171A (zh) 樹葉辨識方法
WO2021143700A1 (zh) 生物芯片的数据处理方法、装置、终端及可读介质
CN114943775A (zh) 图像全局自动标定方法、装置及相关设备
CN118099012A (zh) 一种aoi晶圆表面缺陷检测方法
CN116309491A (zh) 一种评估荧光图像清晰度和点圆度的方法
CN114882122A (zh) 图像局部自动标定方法、装置及相关设备
Nguyen Methods and algorithms of segmentation and deconvolution for quantitative analysis of Tissue Microarray images
CN115018919A (zh) 摄像模组的解析力测试方法及其测试装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21927101

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021927101

Country of ref document: EP

Effective date: 20221123

NENP Non-entry into the national phase

Ref country code: DE