Method, system and equipment for identifying single bacteria based on lensless imaging, medium and drug sensitivity detection method

Abstract

The invention provides a method, a system and equipment for identifying single bacteria based on lensless imaging, a medium and a drug sensitivity detection method, and belongs to the technical field of biological image processing. The single bacterium identification method based on lens-free imaging comprises the steps of gray processing, edge detection, single bacterium identification and the like, and further comprises the steps of background removal, abnormal pixel correction, signal enhancement, outlier screening and the like. The method, the system, the equipment and the medium are used for identifying the single bacteria, the speed is high, and the precision is high. The method is further used for detecting the drug sensitivity of bacteria, the proliferation condition of the bacteria can be obtained in a short time, then the minimum inhibitory concentration of antibiotics is obtained, and the method has very high application value.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of biological image processing, and in particular to a method and system for single-bacterium identification based on lens-free imaging, a device, a medium and a drug sensitivity detection method. BACKGROUND

[0002] Traditional antimicrobial susceptibility testing (AST), such as paper disc diffusion, agar dilution, broth microdilution, etc., requires culturing, isolating and enriching bacteria in clinical samples, and then observing the inhibitory effect of antibiotics on bacterial growth to obtain the drug sensitivity result of the bacteria. The process is complex and time-consuming (2-4 days).

[0003] In recent years, rapid phenotypic drug sensitivity detection technology has been applied to clinical diagnosis and treatment, which can significantly shorten the drug sensitivity report time and reduce the mortality rate of infected patients. Among them, the rapid drug sensitivity detection technology based on optical imaging has the advantage of high sensitivity of single-bacterium imaging, which can shorten the drug sensitivity detection time to 1 hour or even less, such as a microscope imaging system based on microfluidics, a Raman imaging system, etc.

[0004] However, such technology often requires a complex and precise optical imaging structure, which is high in cost and complex in operation. SUMMARY

[0005] To solve at least one of the above technical problems, the technical solution adopted by the present application is as follows.

[0006] The first aspect of the present application provides a method for single-bacterium identification based on lens-free imaging, which processes a microscopic image of a bacterial solution obtained based on lens-free imaging to identify single bacteria, comprising the following steps: gray processing: performing gray processing on the microscopic image to obtain a gray image; edge detection: using a Sobel operator to perform edge detection on the image: single-bacterium identification: first smoothing the image using a second Gaussian filter, and then using a Laplacian filter to convolve the smoothed image to obtain the target bacteria in the image.

[0007] Lens-free imaging technology is a high-throughput microscopic imaging technology that does not require any lens and directly images the object to be tested by placing it on or close to the surface of the image sensor. Due to its small size and low cost, it is suitable for application in POCT (Point of Care Testing) technology.

[0008] In some embodiments of the present application, the following formula is used for gray processing:

[0009] wherein, represents the original gray value of a pixel point with coordinate , R , G and B represent the R value, G value and B value of the pixel point respectively.

[0010] Further, the application utilizes the improved Sobel operator to perform edge detection on the image:

[0011]

[0012]

[0013] wherein, and are defined as the convolution kernel function of the Sobel operator, represents the edge gray value of the pixel point.

[0014] In some embodiments of the application, the single bacteria identification step is specifically:

[0015]

[0016]

[0017]

[0018] wherein, the kernel parameter of the first Gaussian filter is , the diameter of the target bacteria.

[0019] In some embodiments of the application, after the gray processing step and before the edge detection step, the following step is further included: background removal: a first Gaussian filter is used to perform convolution on the image to obtain a background gray value, and a foreground gray value is obtained by difference operation with the original gray value, specifically:

[0020]

[0021] wherein, represents the estimated background gray value of a pixel point with coordinate , represents the first Gaussian kernel function with a standard deviation of , , , Indicates the calculated foreground grayscale value of the pixel point, at this time: .

[0022] In some embodiments of the present application, after the background removal step and before the edge detection step, the following steps are further included: Abnormal pixel correction: For each pixel, obtain the grayscale values ​​of all pixels in the area around it that is no larger than the size of the target bacteria and calculate the median and standard deviation to determine the size of the following two values: ① The absolute value of the difference between the grayscale value of the pixel and the median; ② The product of the standard deviation and the first preset threshold, If ①>②, the pixel is judged as an outlier and replaced by the median.

[0023] In some specific embodiments of the present application, a circular sampling window is formed for each pixel. ( ) to calculate the median and the standard deviation:

[0024]

[0025] in, The coordinates are The median grayscale value of the foreground pixel point, Represents the standard deviation of the foreground grayscale value of the pixel point, and then uses the following method to replace or remove abnormal pixels:

[0026] in, Indicates the corrected grayscale value of the pixel after outlier replacement. represents a first preset threshold value. In some preferred embodiments of the present application, The value ranges from 4 to 5. at this time,

[0027] In some embodiments of the present application, after the edge detection step and before the single bacteria identification step, the following steps are further included: Signal enhancement: For any edge pixel, binarization is performed based on the comparison between its grayscale value and a second preset threshold; then closing and opening operations are performed to obtain an enhanced edge.

[0028] In some embodiments of the present application, the purpose of binarization is to highlight the edges of bacteria, specifically:

[0029] in, Indicates the edge gray value of the pixel. Indicates the second preset threshold. The value of is determined by following the steps below: for Set an initial value and use the above formula to perform binarization; The bright spots in the binarized image are divided into two types: bright spots with smaller areas (background noise spots) and bright spots with larger areas and ring-shaped outer rings (target bacteria spots); If the setting If the radius of the background noise point is not greater than 2 pixels, and the radius difference between the outer circle and the inner circle of the target bacteria point is not greater than 4 pixels, then this value is selected as the second preset threshold, otherwise, Add 1 to the current value and repeat the above steps until the radius of the background noise point is no more than 2 pixels and the radius difference (ring width) between the outer and inner circles of the target bacterial point is no more than 4 pixels.

[0030] In some embodiments of this application, the radius of a background noise point is calculated using the perimeter or radius. As long as the perimeter or area is no greater than 4π, the radius can be no greater than 2 pixels. Similarly, the annular width can be calculated using the perimeter or area of ​​the inner and outer rings. In one specific embodiment of this application, the perimeter is used: annular width = (outer ring perimeter - inner ring perimeter) / 2π.

[0031] In some embodiments of the present application, the background noise is a small particle, i.e., a small area, and the edge of the target bacteria is a ring (caused by light refraction). If the value is small, the background noise point area will be larger during binarization, and the ring width of the target bacteria point will also be larger. The noise points will be included in the subsequent counting, thus affecting the counting accuracy. The value is gradually increased. When the above two requirements are met (i.e., the radius of the background noise point is no more than 2 pixels, and the ring width of the target bacterial point is no more than 4 pixels), the background noise point can be eliminated in the subsequent morphological calculation, and the target bacterial point only changes the edge image without changing the original image of the bacterial center when enhancing the edge.

[0032] To eliminate background noise and enhance edges, set a 2-pixel disk and perform a closing operation followed by an opening operation:

[0033]

[0034] in, represents the closed operation gray value after the low brightness is complemented, represents the open operation gray value after the redundant white point noise is removed, and represents a disc structure with a radius of 2 pixels; Finally, the current image gray value is subtracted by the open operation gray value to obtain an enhanced gray value .

[0035] In some embodiments of the present application, after the single bacterial identification step, the following steps are further included: Outlier screening: by setting a threshold for at least one of signal-to-noise ratio, contrast, minimum brightness and brightness variance, false target bacteria are removed.

[0036] The second aspect of the present application provides a system for single bacterial identification based on lensless imaging, comprising the following modules: An image acquisition module is used to obtain a microscopic image of a bacterial solution based on lensless imaging; A gray processing module is connected to the image acquisition module and is used to gray the microscopic image to obtain a gray image; An edge detection module is connected to the gray processing module and is used to perform edge detection on the image using a Sobel operator; A single bacterial identification module is connected to the edge detection module and is used to first convolve the image using a Gaussian filter and then calculate the Laplacian of the image to obtain the target bacteria in the image.

[0037] The third aspect of the present application provides a computer device, comprising: a memory for storing a computer program; a processor for executing the computer program to realize the steps of the method according to any one of the first aspect of the present application.

[0038] The fourth aspect of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps of the method according to any one of the first aspect of the present application.

[0039] The fifth aspect of the present application provides a bacterial drug sensitivity detection method, comprising the following steps: Exposing the bacteria to be tested to different concentrations of antibiotics in a detection chamber, wherein a lensless image sensor is placed at the bottom of the detection chamber; Before and after the bacteria to be tested are exposed to different concentrations of antibiotics for a period of time, microscopic images of the bacterial solution in each detection chamber are obtained using the lensless image sensor; The method of any one of the first aspect of the present application, the system of any one of the second aspect of the present application, the computer device of any one of the third aspect of the present application or the computer readable storage medium of any one of the fourth aspect of the present application is used to identify single bacteria in the microscopic image and count; If the proliferation rate of the bacteria to be tested before exposure to the antibiotic at a concentration higher than a certain concentration and after exposure for a period of time is less than a third preset threshold, and the proliferation rate of the bacteria to be tested before exposure to the antibiotic at a concentration lower than the certain concentration and after exposure for a period of time is not less than the third preset threshold, the concentration is the minimum inhibitory concentration of the antibiotic to the bacteria.

[0040] In some embodiments of the present application, the antibiotic is selected from at least one of β-lactams, aminoglycosides, macrolides, tetracyclines, quinolones, sulfonamides, glycopeptides, lincosamides, nitroimidazoles and polypeptide antibiotics.

[0041] Among them, β-lactams further include penicillins, cephalosporins and carbapenems, penicillins include but are not limited to penicillin G (Penicillin G), ampicillin (Ampicillin) and piperacillin (Piperacillin); cephalosporins include but are not limited to cefazolin (Cefazolin), ceftriaxone (Ceftriaxone), ceftazidime (Ceftazidime) and cefotaxime (Cefotaxime); carbapenems include but are not limited to imipenem (Imipenem), meropenem (Meropenem) and ertapenem (Ertapenem).

[0042] Aminoglycosides include but are not limited to gentamicin (Gentamicin), tobramycin (Tobramycin) and amikacin (Amikacin).

[0043] Macrolides include but are not limited to erythromycin (Erythromycin), azithromycin (Azithromycin) and clarithromycin (Clarithromycin).

[0044] Tetracyclines include but are not limited to tetracycline (Tetracycline), doxycycline (Doxycycline) and minocycline (Minocycline).

[0045] Quinolones include but are not limited to ciprofloxacin (Ciprofloxacin), levofloxacin (Levofloxacin) and moxifloxacin (Moxifloxacin).

[0046] Sulfonamides include, but are not limited to, sulfamethoxazole / trimethoprim (SMZ-TMP).

[0047] Glycopeptides include, but are not limited to, vancomycin and teicoplanin.

[0048] Lincosamides include, but are not limited to, clindamycin and lincomycin.

[0049] Nitroimidazoles include, but are not limited to, metronidazole.

[0050] Polypeptides include, but are not limited to, polymyxin B and colistin.

[0051] Of course, the present application can also be applied to the drug sensitivity detection of other antibiotics such as linezolid, daptomycin, tigecycline and fusidic acid.

[0052] For different antibiotics / bacteria, the corresponding third preset threshold needs to be adjusted accordingly, and the third preset threshold can be obtained by using a population sample.

[0053] Compared with the prior art, the present application has the following beneficial effects: Using the method, system, device and medium of the present application for single bacterial identification has the advantages of high speed and high precision. Further used for bacterial drug sensitivity detection, the proliferation of bacteria can be obtained in a short time, and then the minimum inhibitory concentration of antibiotics can be obtained, which has very great application value.

[0054] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0055] The above and other objects, features and advantages of the exemplary embodiments of the present application will be more apparent from the following detailed description read in conjunction with the accompanying drawings, in which: Figure 1 A flowchart of image processing and single bacterial identification for a lensless image in Embodiment 2 of the present application is shown; Figure 2The abnormal pixel removal effects of different values in Embodiment 2 of the present application are shown. A: before removal, B: Figure 3 The effects of using different features for pseudo-target identification and screening in Embodiment 2 of the present application are shown. Figure 4 The bacterial microscopic images obtained based on lensless imaging of the highest antibiotic concentration group and the control group in Embodiment 3 of the present application are shown. Figure 5 The images after microscopic image processing and single-bacterium identification of the highest antibiotic concentration group and the control group in Embodiment 3 of the present application are shown. Figure 6 The E. coli growth curves at different antibiotic concentrations in Embodiment 3 of the present application are shown. DETAILED DESCRIPTION

[0056] Unless otherwise defined, all parts and percentages used herein are on a weight basis, and all tests and measurements are made in accordance with methods standard at the time of filing this application. Where applicable, the contents of any patent, patent application or publication referred to herein are incorporated by reference in their entirety, and equivalents thereof are also incorporated by reference, particularly with respect to the definitions of terms that are consistent between this application and the documents incorporated by reference. If a definition of a term in the prior art is inconsistent with any definition provided herein, the definition provided herein shall control.

[0057] In order to make the technical problems, technical solutions and beneficial effects solved by the present application clearer, the present application is further described in detail below in combination with embodiments.

[0058] The following examples are presented to demonstrate preferred embodiments of the present application. Those skilled in the art will appreciate that the technology disclosed in the following examples represents the inventors' own best efforts to use the technology in carrying out the present application, and therefore can be considered as preferred ways of practicing the present application. However, those skilled in the art will appreciate, based on the present specification, that the particular examples disclosed herein can be modified in many ways, and still obtain the same or similar results, without departing from the spirit or scope of the present application.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs, and the materials referred to in this disclosure are incorporated by reference in their entirety.

[0060] ​​​​Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many technical equivalents to the specific embodiments of the invention described herein. Such equivalents are intended to be encompassed by the claims.

[0061] The experimental methods in the following examples, unless otherwise specified, are all conventional methods. The instruments and equipment used in the following examples, unless otherwise specified, are all conventional laboratory instruments and equipment; the experimental materials used in the following examples, unless otherwise specified, are all purchased from conventional biochemical reagent stores.

[0062] Example 1 Acquisition of Lensless Imaging Images of Escherichia coli Liquid The detection cavity was prepared using polydimethylsiloxane (PDMS): first, the PDMS monomer and the cross-linking agent (DOWCORNING) were mixed in a mass ratio of 10:1, stirred evenly, and allowed to stand to remove bubbles. Then, the PDMS glue with all bubbles removed was poured into a plastic culture dish with a flat surface and a diameter of 9 cm, and baked at 75°C on a hot plate for 1.5 hours. After peeling off the PDMS film, it was cut into 10mm×10mm square blocks. The thickness of the PDMS film was about 2mm. A hole puncher was used to punch holes in the cut PDMS film to make the detection cavity. The detection cavity size was 3.76mm×2.74mm.

[0063] A PDMS membrane containing a detection cavity is placed on a sterile glass slide, and a lensless image sensor is placed at the bottom of each detection cavity. In the present invention, the lensless image sensor is obtained by removing the optical lens of an OV5647 (Omnivision) CMOS camera.

[0064] Use an optical density meter to prepare a 0.5 McFarland initial bacterial solution of Escherichia coli (ATCC No. 25922) (concentration of about 1.5×10 8 CFU / mL), and the initial bacterial solution was diluted to 1×10 5 CFU / mL, aspirate 20 μL and add it to the detection chamber and incubate at 35°C.

[0065] After 60 minutes of incubation, the bacterial image in the detection chamber was acquired by a lensless image sensor, namely, the lensless imaging image.

[0066] Example 2 Single Bacteria Identification Based on Lensless Imaging of Bacterial Liquid refer to Figure 1 The following steps are used to perform automated image processing and single bacteria identification and counting on the lens-free imaging image of the bacterial liquid obtained in Example 1.

[0067] 1. Color space dimensionality reduction (grayscale) Based on the CIE 1931 color space conversion model, the data fusion of the RGB three channels of the bacterial lens-free microscopic image is realized by the weighted average method:

[0068] wherein, represents the original gray value of the pixel point with coordinates , R , G and B represent the R value, G value and B value corresponding to the pixel point respectively.

[0069] The process converts the 24-bit true color image into an 8-bit gray scale image (dynamic range 0-255), which reduces the data dimension while retaining the texture characteristics, so as to quantify the spatial phenotype characteristics of the bacterial image in the subsequent steps.

[0070] 2. Spatiotemporal filtering denoising A convolution algorithm (first Gaussian filter) of a large-scale anisotropic Gaussian kernel is used to construct a background field estimator, and the foreground feature is extracted by difference operation to realize background field compensation and noise suppression:

[0071]

[0072] wherein, represents the estimated background gray value of the pixel point with coordinates , represents the first Gaussian kernel function with a standard deviation of ; represents the calculated foreground gray value of the pixel point.

[0073] In this embodiment, the first standard deviation value is confirmed according to the typical size of the bacterial image (the bacterial radius is used to represent it), and the value of is set to , for example, the bacterial radius is 5 pixels, and the value of is 10. Through the kernel function, the spatial non-uniformity characteristics in the bacterial culture solution can be effectively captured.

[0074] To avoid signal aliasing phenomenon caused by spatial high-frequency sampling, the filter kernel size selected in this application is more than 3 times the diameter of the bacteria, i.e. , so as to ensure that the covered background area is much larger than the area of the bacteria.

[0075] 3. Abnormal pixel correction In view of the pulse noise interference problem existing in microscopic imaging, the embodiment proposes an abnormal pixel correction algorithm based on spatial range outlier removal to break through the limitation of traditional nonlinear filtering (such as the image blurring caused by traditional median filtering method, which reduces data accuracy), and realizes accurate discrimination and repair of noise by constructing a local statistical feature space.

[0076] First, a ring-shaped sampling window with a radius much smaller than the typical size of the bacterial image is established for each pixel (i.e. , for example ) to calculate the median and standard deviation of its gray scale statistics:

[0077]

[0078] wherein, represents the median of the foreground gray scale value of the pixel point with coordinates , and represents the standard deviation of the foreground gray scale value of the pixel point.

[0079] In order to maximize the ratio of the target bacterial foreground intensity to the background intensity, a first threshold is set to remove outliers, specifically: for any pixel point , the absolute value of the difference between the foreground gray scale value and the median is compared with the product of and the standard deviation, and if the former is larger, the pixel point is identified as an outlier and replaced by the median. That is:

[0080] wherein, represents the corrected gray scale value of the pixel point after replacing the abnormal value.

[0081] Finally, the window is traversed across the entire image to remove all abnormal pixels caused by pulse noise and to retain the original target data.

[0082] wherein, the threshold is statistically obtained according to a large number of experiments, by comparing the original data intensity with the background noise intensity, and finally obtaining the optimal reasonable value. For the E. coli in the embodiment, when takes different values, the abnormal pixel removal results are significantly different, as shown in Figure 2 . When takes a value of 2, the bacteria will also be removed; when takes a value of 20, the denoising is not sufficient; when takes a value of 4-5, for example, takes a value of 4, the abnormal pixel removal is very ideal.

[0083] 4. Signal-to-noise ratio enhancement modeling The low-illumination annular feature generated by the refractive effect of the bacterial cell wall in bright-field microscopic imaging can be used to construct a signal-to-noise ratio enhancement model based on gradient field reconstruction. First, an improved Sobel operator is used for anisotropic edge detection to obtain an edge detection image. For any pixel point, the edge gray value is obtained using the following formula:

[0084]

[0085]

[0086] wherein, and are defined as the convolution kernel function of the Sobel operator, represents the edge gray value of the pixel point.

[0087] In order to obtain the shape of the low-illumination annular image of the bacteria, the inventors first set a second threshold value to binarize the bacterial edge of the detection image:

[0088] That is, if the gray value (0~255 range) of the pixel point is not less than , it is directly assigned as 0, and otherwise, it is directly assigned as 255.

[0089] wherein, represents the edge gray value of the pixel point. The value of is determined according to the following steps: set an initial value (default 1) and binarize using the above formula; The bright spots in the binarized image are divided into two types: small-area bright spots (background noise points) and large-area bright spots with an annular outer ring (target bacterial points); If the initial value of is set, if the radius of the background noise point is not greater than 2 pixel points, and the radius difference between the outer ring and the inner ring of the target bacterial point is not greater than 4 pixel points, the value is selected as the second preset threshold value, otherwise, 1 is added to the initial value, and the above steps are repeated until the radius of the background noise point is not greater than 2 pixel points, and the radius difference (annular width) between the outer ring and the inner ring of the target bacterial point is not greater than 4 pixel points.

[0090] In this embodiment, the final value is 60.

[0091] The low-brightness annular image is completed by morphological closing operation, and the redundant white point noise is removed by morphological opening operation, so as to obtain a complete bacterial annular image after noise reduction.

[0092]

[0093]

[0094] wherein, represents the closing operation gray value after completing the low brightness, represents the opening operation gray value after removing the redundant white point noise, and represents a disc structure with a radius of 2 pixels.

[0095] Finally, the corrected gray value is subtracted by the opening operation gray value to obtain an enhanced gray value, so as to further enhance the signal-to-noise ratio.

[0096]

[0097] 5. Automatic identification of bacterial single particles based on image segmentation The contrast between the bacterial body and the edge is enhanced by the 4th step, so that the peak value of the extreme point of the bacteria is higher and the response is larger.

[0098] Based on the scale space theory, an isotropic filter is constructed, The target of the filter is to find the spot-like structures (i.e. target bacteria) in the image, which are usually brighter than the surrounding area and approximately circular. The filter combines Gaussian smoothing and Laplacian second derivative:

[0099]

[0100]

[0101]

[0102] Firstly, a second Gaussian filter is used to convolve the image, aiming to suppress noise. The Gaussian filter is a weighted average filter, and the weight is determined by the Gaussian function. The farther away from the center, the smaller the weight. The degree of smoothing is controlled by the second standard deviation of the Gaussian function. The larger the second standard deviation, the more blurred the image, and the larger the size of the detectable spot.

[0103] Next, the Laplace (second-order spatial derivative) of the Gaussian-smoothed image is calculated. The Laplace operator is very sensitive to rapid changes in grayscale (edges) in the image. It gives a strong negative response (for bright spots) or a positive response (for dark spots) at the center of the spot (i.e., the point of local intensity maximum or minimum), while giving a response of the opposite sign at the edge of the spot. These strong response points can be used to determine the coordinates of the extreme points, namely the bacterial coordinates.

[0104] Experiments have shown that when the LoG operator The value is such that Able to be with bacterial radius When matching, the response at the extreme point coordinates is the strongest, which is beneficial to bacteria detection. , that is, the Gaussian kernel parameters are obtained.

[0105] 6. Outlier Removal To eliminate false targets and ensure accurate bacterial identification, the detected targets need to be further screened. Using the spatial phenotypic characteristics of each bacterial particle obtained in the previous step, false targets can be screened by setting multiple reasonable thresholds for their signal-to-noise ratio, contrast, minimum brightness, and brightness variance. This allows the image detection results to approach the true value, resulting in an accurate bacterial count within the field of view.

[0106]

[0107] in SNR represents the signal-to-noise ratio, C Indicates contrast, I min Indicates the lowest brightness (minimum value), STD Represents variance.

[0108] For E. coli, the effects of using the above characteristics to identify and screen out E. coli are as follows: Figure 3 shown.

[0109] Example 3 Sensitivity test of Escherichia coli to amikacin This example tests the sensitivity of Escherichia coli quality control strain ATCC No. 25922 to the antibiotic amikacin.

[0110] Similarly, use an optical density meter to prepare a 0.5 McFarland initial bacterial solution (concentration is about 1.5×10 8 CFU / mL), and the initial bacterial solution was diluted to 1×10 5CFU / mL as the initial bacteria solution for drug sensitivity detection, and amikacin solution was used to configure CaMHB culture medium at concentrations of 0.125 μg / mL, 0.25 μg / mL, 0.5 μg / mL, 1 μg / mL, 2 μg / mL, 4 μg / mL and 8 μg / mL.

[0111] 1 μL of the bacteria solution was added to each detection chamber, and the above amikacin solution at different concentrations was added to different detection chambers (20 μL was added to each detection chamber, and one detection chamber corresponded to one concentration), and a detection chamber with an equal amount of blank CaMHB culture medium was used as a control.

[0112] The detection chambers were placed in a 35°C incubator. At the beginning of the incubation (0 min) and every 30 min, the bacterial images of each detection chamber were obtained by a lens-free image sensor (the microscopic images of the highest antibiotic concentration group and the control group are shown in FIG. 5), until the incubation was performed for 120 min. The image processing and single-bacterium recognition were performed by the method of Example 2 (the single-bacterium recognition images of the highest antibiotic concentration group and the control group are shown in FIG. 6), so as to complete the bacterial counting in each detection chamber. Figure 4 Figure 5

[0113] In this embodiment, the growth curves of each group are shown in FIG. 7, and it can be seen that when the concentration of amikacin is greater than 2 μg / mL, the growth of E. coli is inhibited, so that the minimum inhibitory concentration (MIC) of amikacin to E. coli is 2 μg / mL.

[0114] In this embodiment, the growth curves of each group are shown in FIG. 7, and it can be seen that when the concentration of amikacin is greater than 2 μg / mL, the growth of E. coli is inhibited, so that the minimum inhibitory concentration (MIC) of amikacin to E. coli is 2 μg / mL. Figure 6

[0115] It can be seen that the drug sensitivity detection by the method of the present application can be completed within 2 hours, which is very fast and convenient.

[0116] In addition, it should be understood that, after reading the above teachings of the present application, those skilled in the art can make various modifications or changes to the present application, and these equivalent forms also fall within the scope defined by the claims attached to the present application.​​​

Claims

1. A method for single bacterium identification based on lensless imaging, characterized in that, The method processes a microscopic image of a bacterial liquid obtained based on lensless imaging to identify single bacteria, comprising the following steps: gray processing: the microscopic image is grayed to obtain a gray image; edge detection: the image is edge detected using a Sobel operator; single bacterium identification: the image is first smoothed using a second Gaussian filter, and then the smoothed image is convolved using a Laplace filter to obtain the target bacteria in the image.

2. The method of claim 1, wherein, After the gray processing step and before the edge detection step, the following steps are further included: background removal: a first Gaussian filter is used to convolve the image to obtain a background gray value, and a foreground gray value is obtained by difference operation with the original gray value.

3. The method of claim 2, wherein, After the background removal step and before the edge detection step, the following steps are further included: abnormal pixel correction: for each pixel point, the gray values of all pixels in a region around the pixel point not greater than the size of the target bacteria are obtained, and the median and standard deviation are calculated, to judge the size of the following two values: ① the absolute value of the difference between the gray value of the pixel point and the median; ② the product of the standard deviation and a first preset threshold, If ①>②, the pixel point is identified as an outlier, and the median is replaced.

4. The method according to any one of claims 1 to 3, characterized in that, After the edge detection step and before the single bacterium identification step, the following steps are further included: signal enhancement: for any edge pixel point, if the gray value is not less than a second preset threshold, the gray value of the pixel point is set to 0, otherwise it is set to 255; then close operation and open operation are performed to obtain the enhanced edge.

5. The method according to any one of claims 1 to 3, characterized in that, After the single bacterium identification step, the following steps are further included: outlier exclusion: by setting a threshold for at least one of the signal-to-noise ratio, contrast, minimum brightness and brightness variance, false target bacteria are removed.

6. A system for single bacterium identification based on lensless imaging, characterized in that, It includes the following modules: an image acquisition module for obtaining a microscopic image of a bacterial liquid obtained based on lensless imaging; a gray processing module connected with the image acquisition module, for gray processing of the microscopic image to obtain a gray image; an edge detection module connected with the gray processing module, for edge detection of the image using a Sobel operator; a single bacterium identification module connected with the edge detection module, for first smoothing the image using a second Gaussian filter, and then convolving the smoothed image using a Laplace filter to obtain the target bacteria in the image.

7. A computer device, comprising: It includes: a memory for storing a computer program; a processor for executing the computer program to implement the steps of the method of any one of claims 1-5.

8. A computer readable storage medium, characterized in that, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the method of any one of claims 1-5.

9. A bacterial drug sensitivity detection method, characterized in that: The following steps are included: exposing the bacteria to be tested to different concentrations of antibiotics in a detection chamber, with a lensless image sensor placed at the bottom of the detection chamber; before and after the bacteria to be tested are exposed to different concentrations of antibiotics for a period of time, the microscopic images of the bacterial liquid in each detection chamber are obtained using the lensless image sensor; The method of any one of claims 1-5, the system of claim 6, the computer device of claim 7, or the computer-readable storage medium of claim 8 are used to identify and count single bacteria in the microscopic image; If the proliferation rate of the bacteria to be tested before exposure to the antibiotic at a certain concentration and after exposure for a period of time is less than a third preset threshold, and the proliferation rate of the bacteria to be tested before exposure to the antibiotic at a concentration lower than the certain concentration and after exposure for a period of time is not less than the third preset threshold, the certain concentration is the minimum inhibitory concentration of the antibiotic to the bacteria.

10. The method of susceptibility testing according to claim 9, wherein, The antibiotic is selected from at least one of a beta-lactam, an aminoglycoside, a macrolide, a tetracycline, a quinolone, a sulfonamide, a glycopeptide, a lincosamide, a nitroimidazole, and a polypeptide antibiotic.

Images