CN110675386A

CN110675386A - Detection system of B-group streptococcus

Info

Publication number: CN110675386A
Application number: CN201910915252.XA
Authority: CN
Inventors: 黄磊; 吴桐; 孙立颖; 李海霞
Original assignee: Peking University First Hospital
Current assignee: Peking University First Hospital
Priority date: 2019-09-26
Filing date: 2019-09-26
Publication date: 2020-01-10
Anticipated expiration: 2039-09-26
Also published as: CN110675386B

Abstract

The embodiment of the invention discloses a detection system of group B streptococcus, which relates to the field of clinical microbiology inspection, and comprises: a plurality of microbial colonies to be screened grow in the microbial colony culture dish; the shooting equipment is used for shooting the microbial colony culture dish to obtain a microbial colony culture dish image containing a plurality of microbial colony images to be screened; the communication equipment is used for sending the microbial colony culture dish image containing the multiple microbial colony images to be screened to the cloud analysis device; and the cloud analysis device is used for analyzing the multiple microbial colony images to be screened in the microbial colony culture dish images shot by the shooting equipment and determining whether the B-family streptococcus colonies exist in the multiple microbial colonies to be screened. The group B streptococcus image recognition method and device based on the image recognition greatly reduce labor cost and equipment cost on the basis of ensuring screening accuracy.

Description

Detection system of B-group streptococcus

Technical Field

The embodiment of the invention relates to the field of clinical microbiology inspection, in particular to a detection system for group B streptococcus.

Background

Group B Streptococcus (GBS) is an aerobic gram-positive coccus that has been considered the causative bacterium of invasive neonatal infections since the 70's of the 20 th century and can cause severe infections such as neonatal sepsis, pneumonia and meningitis. The most important risk factor for the newborn to progress to invasive infection is maternal colonization of the urogenital or gastrointestinal tract by GBS, and GBS infection in most newborns can be effectively avoided by antibiotic prophylaxis for at least 4 hours prior to delivery. The U.S. CDC issued recommendations for prevention of neonatal GBS infection, greatly reducing neonatal GBS infection rates. Chinese experts also give statement comments to emphasize the importance of carrying out GBS screening and prevention in the perinatal pregnant women in China.

GBS screening should be performed at 35-37 weeks of gestation, collecting vaginal and rectal swabs, and conventionally inoculating in Todd-Hewitt broth (containing antibiotics for inhibiting the growth of infectious microbes), incubating at 35 deg.C for 24 hr, inoculating in Columbia Blood Agar (CBA) plate, incubating at 35 deg.C for 24-48 hr, observing whether suspicious GBS colonies (with narrow beta hemolytic ring and white and smooth colony with gradually changed boundary) exist on the CBA plate, selecting suspicious colonies, and further performing strain identification by means of 16SrDNA gene sequencing, automatic bacteria identification instrument, or matrix-assisted laser desorption ionization-time-of-flight mass spectrometry (MALDI-TOFMS). Other GBS detection methods also include fluorescent quantitative PCR detection of GBS, and GBS chromogenic medium containing special substrates.

However, the above identification methods all require experienced technicians to perform primary screening on suspicious colonies on a CBA plate, and then further identification requires expensive instruments and equipment such as a mass spectrometer, an automatic bacteria identification instrument, a fluorescence quantitative PCR instrument or a gene sequencer, so that the cost of a commercialized chromogenic medium is also high, and primary hospitals are generally powerless, and thus the methods are more suitable for being developed in large hospitals with better economic conditions. In the vast primary hospitals and women and children health care hospitals with numerous pregnant women, the popularization of GBS screening is limited by the two aspects of the technology and the cost.

Disclosure of Invention

The detection system for the group B streptococcus provided by the embodiment of the invention solves the problem that the group B streptococcus is difficult to screen and prevent in perinatal pregnant women due to the limitation of the technology and cost in most primary hospitals and maternal and child care hospitals.

The detection system for the group B streptococcus provided by the embodiment of the invention comprises:

a plurality of microbial colonies to be screened grow in the microbial colony culture dish;

the photographing device is used for photographing the microbial colony culture dish to obtain a microbial colony culture dish image containing a plurality of microbial colony images to be screened;

the communication equipment is used for sending the microbial colony culture dish image containing the multiple microbial colony images to be screened to the cloud analysis device;

and the cloud analysis device is used for analyzing the multiple microbial colony images to be screened in the microbial colony culture dish images shot by the shooting equipment and determining whether the B-family streptococcus colonies exist in the multiple microbial colonies to be screened.

Preferably, the cloud analysis device includes:

the image recognition device is used for screening a plurality of microbial colony images of suspected B-group streptococcus colonies from the plurality of microbial colony images to be screened and marking the plurality of microbial colony images of the suspected B-group streptococcus;

and the colony analysis device is used for analyzing the plurality of microbial colony images of the suspected B-group streptococcus marked by the image recognition device by using an artificial neural network to determine whether the plurality of microbial colony images of the suspected B-group streptococcus marked by the image recognition device are B-group streptococcus colony images.

Preferably, the image recognition device is configured to screen out a plurality of microbial colony images of suspected group B streptococcus colonies from the plurality of microbial colony images to be screened, and specifically includes:

the colony characteristic analysis module is used for analyzing each microbial colony image to be screened in the microbial colony culture dish image to obtain a microbial colony characteristic value in each microbial colony image;

and the group B streptococcus colony primary screening module is used for determining whether each microbial colony image is a suspected group B streptococcus microbial colony image or not according to the microbial colony characteristic value in each microbial colony image and a preset group B streptococcus colony characteristic threshold range.

Preferably, the characteristic value of the microbial colony includes size, color and gradient of color change from center to edge of the microbial colony, and correspondingly, the preset threshold range of colony characteristic of group B streptococcus includes the preset threshold range of colony size, the preset threshold range of colony color and the preset threshold range of gradient of color change from center to edge of the colony of group B streptococcus.

Preferably, for each microbial colony, the image recognition device determines that each microbial colony image is a microbial colony image of suspected group B streptococcus when the size, color and colony center-to-edge color change gradient of the microbial colony are within the preset colony size threshold range, colony color threshold range and colony center-to-edge color change gradient threshold range of the group B streptococcus, respectively.

Preferably, the artificial neural network is a convolutional neural network comprising a convolutional layer, a modified linear unit layer, a pooling layer and a complete connection layer, and the colony analysis device analyzes the suspected group B streptococcus colony images marked by the image recognition device by using the convolutional neural network comprising the convolutional layer, the modified linear unit layer, the pooling layer and the complete connection layer, and determines whether the suspected group B streptococcus colony images marked by the image recognition device are group B streptococcus colony images.

Preferably, the system further comprises a photographing assisting device for photographing the microbial colony, wherein the photographing assisting device comprises:

a box body having a top plate, a bottom plate and side plates;

the supporting seat is arranged above the bottom plate;

the lamp shell of the bottom light source is arranged on the supporting seat and can rotate relative to the bottom plate;

and the culture dish fixing clamp is arranged on the upper part of the lamp housing and used for clamping the microbial colony culture dish.

Preferably, the photographing auxiliary device further comprises a movable arm which is arranged above the top plate and can rotate or bend relative to the top plate, and a photographing fixing clamp which is arranged at the extending end of the movable arm and is used for clamping the photographing equipment.

Preferably, the photographing assisting apparatus further includes: the plane scattering light source is arranged on the lower surface of the top plate, the annular light source is arranged on the inner wall of the side plate, and the ultraviolet lamp disinfection device is arranged on the inner wall of the side plate.

The technical scheme provided by the embodiment of the invention has the following beneficial effects:

the embodiment of the invention identifies the group B streptococcus based on the image, neither needs an experienced technician to perform preliminary screening nor needs to purchase expensive instruments and equipment, greatly reduces the labor cost and the equipment cost on the basis of ensuring the screening accuracy, and is suitable for the pregnant woman GBS screening and prevention in wide primary hospitals and women and child care hospitals.

Drawings

FIG. 1 is a schematic block diagram of a group B streptococcus detection system according to an embodiment of the present invention;

FIG. 2 is a schematic block diagram of another group B streptococcus detection system provided by an embodiment of the present invention;

fig. 3 is a schematic block diagram of the cloud analysis device shown in fig. 1 or fig. 2;

FIG. 4 is a schematic view of a photographing assistant device of the microorganism colony culture dish shown in FIG. 1 or FIG. 2;

FIGS. 5a and 5b are a pure GBS colony plot and an undivided GBS colony plot of a clinical specimen, respectively;

FIG. 6 is a schematic block diagram of a group B streptococcus detection system according to an embodiment of the present invention;

FIG. 7 is a flow chart of single colony image segmentation (labeling) provided by an embodiment of the present invention;

FIG. 8 is a flowchart for detecting whether a single colony that has been split (labeled) is GBS according to an embodiment of the present invention;

FIG. 9 is a flow chart of GBS screening after application of the system according to an embodiment of the present invention.

Detailed Description

The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, and it should be understood that the preferred embodiments described below are only for the purpose of illustrating and explaining the present invention, and are not to be construed as limiting the present invention.

Fig. 1 is a schematic structural block diagram of a group B streptococcus detection system provided in an embodiment of the present invention, and as shown in fig. 1, the system may include:

a microbial colony culture dish, such as a CBA plate or the like, in which a plurality of microbial colonies to be screened grow;

the photographing device, such as a camera, a mobile phone camera and the like, is used for photographing the microbial colony culture dish to obtain a microbial colony culture dish image containing a plurality of microbial colony images to be screened;

the communication equipment, such as a WiFi module, a 3, 4, 5G module, etc., is used for sending the microbial colony culture dish image containing the multiple microbial colony images to be screened to the cloud analysis device;

In this embodiment, the photographing device and the communication device may be implemented by a camera module and a communication module of a mobile terminal (e.g., a doctor's mobile phone). Therefore, after the cloud analysis device analyzes and determines whether a result of the group B streptococcus colony exists in the plurality of microbial colonies to be screened, the mobile terminal (e.g., a doctor mobile phone) may obtain the result from the cloud analysis device, so that the doctor can view the result on the mobile terminal.

Fig. 2 is a schematic structural block diagram of another detection system for group B streptococcus provided in an embodiment of the present invention, as shown in fig. 2, based on the embodiment shown in fig. 1, the system may further include a doctor computer, the microbial colony culture dish image including a plurality of microbial colony images to be screened, which is taken by the doctor mobile phone, may be directly uploaded to the cloud analysis device by the communication device on the doctor mobile phone, or may be uploaded to the cloud analysis device by the communication device on the doctor mobile phone via the doctor computer, and similarly, both the doctor mobile phone and the doctor terminal may obtain a result analyzed and determined by the cloud analysis device from the cloud analysis device.

The system provided by the embodiment of fig. 1 and 2 utilizes the photographing device to photograph a microorganism colony culture dish on which a plurality of microorganism colonies to be screened grow, so as to obtain a microorganism colony culture dish image containing a plurality of microorganism colony images to be screened, and sending the microbial colony culture dish image containing the plurality of microbial colony images to be screened to the cloud analysis device by using the communication equipment, analyzing the plurality of microbial colony images to be screened in the microbial colony culture dish image shot by the photographing equipment by using the cloud analysis device, and determining whether group B streptococcus colonies exist in the plurality of microbial colonies to be screened, and returning the result of whether the group B streptococcus colony exists in the microbial colonies to be screened to the communication equipment for the communication equipment to transmit to a doctor for viewing. Like this, primary hospital and the maternal and child health care institute do not need experienced technical staff to screen for the first time, also need not purchase expensive instrument and equipment, as long as the doctor shoots the microbial colony culture dish image of a plurality of microbial colony images of treating the screening and uploads to the high in the clouds, just can obtain the analysis and detection result in the high in the clouds, greatly reduced primary hospital and the pregnant woman GBS of maternal and child health care institute screening's human cost and equipment cost.

Fig. 3 is a schematic block diagram of the cloud analysis apparatus shown in fig. 1 or fig. 2, and as shown in fig. 3, the cloud analysis apparatus may include:

In one embodiment, the image recognition apparatus of fig. 3 may include:

The characteristic value of the microbial colony comprises the size and the color of the microbial colony and a gradient change from the center of the bacterial colony to the edge of the microbial colony, and correspondingly, the range of the characteristic threshold value of the bacterial colony of the preset group B streptococcus comprises the range of the threshold value of the size of the bacterial colony of the preset group B streptococcus, the range of the threshold value of the color of the bacterial colony and the range of the threshold value of the gradient change from the center of the bacterial colony to the edge of the bacterial colony. In this way, for each microbial colony, the image recognition device may determine that each microbial colony image is a microbial colony image of suspected group B streptococcus when the size, color, and gradient of color change from center to edge of the microbial colony are within the preset threshold range of colony size, threshold range of colony color, and threshold range of gradient of color change from center to edge of the colony of group B streptococcus, respectively.

In one embodiment, the artificial neural network employed by the colony analysis apparatus described in FIG. 3 may be a convolutional neural network comprising convolutional layers, modified linear unit layers, pooling layers, and fully-connected layers. Let CNN be well-trained CNN, i.e. the weights of each layer are known. In order to ensure the detection accuracy of the colony analysis equipment for GBS mixed in normal flora, the present embodiment performs the following operations:

1. an input layer: 200 x 3, i.e. 200 pixels x 3 dimensions (i.e. three dimensions of RGB).

The value of each pixel point in each dimension (e.g., the dimension corresponding to red) is the product of the red value and the darkness of the pixel point;

2. and (3) rolling layers: 3 x 100, convolution layers use 100 convolution kernels of 3 x 3.

Each convolution kernel focuses on an image feature, such as a vertical edge, a horizontal edge, a color, a texture, etc., so that 100 convolution kernels are a feature extractor set of the whole image, and thus, after convolution, image feature data of a x a 100 (the size of a is related to the convolution step size), that is, 100 sets of image feature data of a x a, can be obtained.

3. And correcting the linear unit layers, and resetting the negative number in the image feature data of a x a 100 to 0 to obtain the image feature data of a x a 100.

4. The pooling layer performs dimensionality reduction processing on the image feature data of a x 100 by using a 2 x 2 filter, preferably a maximum pooling method, and retains information with scale invariance.

And 5, repeatedly performing convolution, linear correction and dimensionality reduction until 2 x 100 image feature data, namely 100 groups of 2 x 2 image feature data, are obtained.

6. Complete connection layer: 2 x 100, i.e. the complete connection layer, the 2 x 100 image feature data is processed by using 100 x 2 convolution kernels, and 1 x 2 data, i.e. the GBS value and the value other than GBS, is obtained and sent to the output layer.

7. The output layer can be considered as a classifier that finally decides whether it is GBS or not, based on the values of GBS and not.

In practice, after arranging the 2 × 100 image feature data into 1 × 400 column data, each value participates in voting, and determines whether there is a GBS, a voting list composed of voting results of whether there is a GBS corresponding to each value may be obtained, and finally, whether there is a GBS may be determined according to the voting list composed of voting results of whether there is a GBS corresponding to each value.

One of ordinary skill in the art will appreciate that the functional modules/units in the cloud analytics device disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.

On the basis of the embodiment, in order to obtain better shooting effect and higher picture definition, the system further comprises a shooting auxiliary device for shooting the microbial colony. FIG. 4 is a schematic view of the photo aid for the colony culture dish of FIG. 1 or FIG. 2, as shown in FIG. 4, including:

a box body 1 having a top plate, a bottom plate and side plates;

the supporting seat 10 is arranged above the bottom plate;

a bottom light source 2, the lamp housing of which is mounted on the support base 10 and can rotate relative to the bottom plate;

and the culture dish fixing clamp 4 is arranged on the upper part of the lamp housing and used for clamping the microbial colony culture dish.

Wherein, the through-hole that is used for shooing is seted up in the middle part of the roof of box 1.

The lamp housing of the bottom light source 2 can be provided with a handle 3 for pushing the lamp housing to change the angle, so as to adjust the angle of the bottom light source 2 relative to the bottom plate.

The structure of the supporting seat can adopt a connecting part in the prior art, and the details are not repeated herein.

The structure of the culture dish fixing clamp 4 can adopt at least one group of clamps in the prior art, and details are not repeated herein.

This embodiment installs supporting seat 10 in the bottom plate top of box 1 to just support the bottom light source 2 to the hole of shooing through supporting seat 10, so that the light that bottom light source 2 launches from settle in bottom light source 2 top the microorganism bacterial colony culture dish bottom upwards transmits away, the setoff and brighten microorganism bacterial colony in the microorganism bacterial colony culture dish makes the hemolytic ring (alpha hemolysis, beta hemolysis) of microorganism bacterial colony different grade type easily distinguish, especially can make the narrow beta hemolysis ring of GBS bacterial colony easily identify, thereby usable equipment of shooing clearly shoots the microorganism bacterial colony, and then do benefit to the follow-up accurate analysis of carrying out the bacterial colony.

In addition to the above-mentioned structure of the photographing assisting device, the photographing assisting device may further include: the plane scattering light source 6 is arranged on the lower surface of the top plate, the annular light source 5 is arranged on the inner wall of the side plate, and at least one of the ultraviolet lamp disinfection devices is arranged on the inner wall of the side plate, so that reflection of the surface of the microorganism colony culture dish due to reflection is prevented to the maximum extent, and the effect similar to a shadowless lamp is achieved.

The light sources of the embodiment can adopt light sources which can emit three light colors of natural light, cold light and warm light, such as LED lamps, and the brightness and the light color of the light sources can be adjusted by adopting a circuit which can adjust the brightness and the light color in the prior art, so that the light intensity of the light sources in the box body from top to bottom can be adjusted, the light color can be selected, the photographing requirements under the conditions of different types of culture media (such as CBA flat plates, Chinese blue flat plates, chocolate flat plates and the like) or different colony colors (white, gray, yellow and the like) can be met, and the optimal photographing effect can be achieved.

Because the problem of blurred shot images caused by shaking hands exists when the shooting equipment is held by hands, the embodiment can further mount a movable arm 7 which can rotate or bend relative to the top plate above the top plate on the basis of the structure of the shooting auxiliary device, and mount a shooting fixing clamp 8 for clamping the shooting equipment at the extending end of the movable arm 7.

Wherein, the angle of relative roof can be changed to the mounting fixture 8 of shooing to can carry out multi-angle, three-dimensional shooing to colony characteristics such as arch, sunken according to the different conditions of colony.

Three common types (namely traditional CNN, AlexNet and Autoencor) of a Convolutional Neural Network (CNN) are adopted to classify and identify 18 most common clinical bacterial colony images, the results of bacteria automatic identification instrument and mass spectrum identification are used as 'gold standard', and the total coincidence rate of the CNN three types of algorithms is 73%. This preliminarily demonstrates the feasibility of bacteria classification and identification by colony image recognition. However, the bacterial colonies identified in the above study were all images of single colonies that were passaged and purified, as shown in FIG. 5a, rather than images of clinical specimens inoculated directly into CBA plates. In practice, the swabs used for GBS screening usually contain normal flora of the female reproductive tract, in which suspicious GBS colonies are often mixed, as shown in fig. 5 b. Identification of such colony images is therefore more complex and challenging.

To this end, the present invention designs a system for screening GBS of a pregnant woman based on an image recognition technology, fig. 6 is a schematic block diagram of a detection system for detecting streptococcus group B according to an embodiment of the present invention, and as shown in fig. 6, the system may include:

first, CBA flat plate

Second, auxiliary device shoots

The photographing auxiliary device fixes the CBA plate, so that narrow beta hemolytic rings around GBS bacterial colonies are more obvious.

Third, photographing equipment

The optimal position of the fixed photographing equipment is arranged above the photographing auxiliary device so as to achieve the optimal photographing effect and definition.

Fourth, cloud server

The image recognition device can operate image recognition software, firstly, effective single colony images in the whole culture dish picture are segmented (marked), so that the colony analysis device compares and detects the single colonies with standard GBS pure colonies in a 'machine learning' database, and judges whether the segmented (marked) single colonies are GBS or not, and the specific steps are as follows.

(1) First, the image recognition apparatus performs image segmentation (labeling) using a threshold segmentation method.

Specifically, three parameters of colony size (size), colony color (Hue), and gradient of change in color from center to edge of colony (gradient) are set. The threshold values of the three parameters are adjusted and set according to the characteristics of the GBS colonies, and colonies meeting the requirements can be automatically segmented (marked). The specific parameter setting process is determined by using a known GBS bacterial colony in a pre-experiment, namely, all GBS bacterial colonies and similar bacterial colonies can be marked to the maximum extent by optimizing the optimal parameter range aiming at the characteristics of the GBS bacterial colonies, and a foundation is laid for the next judgment.

For example, the following steps are carried out: the diameter of the colony is set to be 1mm-5mm, the color of the colony is within the hue change range from pure white to gray, and the color change gradient from the center of the colony to the edge is 50-80 (namely, the change is large, the color is set according to 0-100, 0 represents that the color of the center of the colony is consistent with that of the edge, and 100 represents that the color of the center of the colony is completely different from that of the edge). Colonies that do not meet any one or more of the three parameters are not marked, as individual colonies meeting the three parameters within the threshold range are segmented (marked). The labeled colonies were stored as several individual colony pictures, as shown in the individual colony image segmentation (labeling) flow chart of fig. 7.

This example allows screening of a portion of non-GBS colonies by image segmentation (labeling).

(2) Then, the colony analyzer detects the single colony divided (marked) by the CNN method to detect whether the single colony is GBS, and a flowchart for detecting whether the divided (marked) single colony is GBS is shown in fig. 8.

The overall architecture of CNN consists of a number of different layers (layers) that transform the data of the input layer into the data of the output layer by performing different functions. The dimensions of each picture in the Input layer (Input layer) are represented by three-dimensional numbers, i.e. "length, width, RGB colors". The input layer is an image of a single colony, and in order to highlight the characteristics of gradual change and narrow beta hemolytic ring of the GBS colony boundary, the parameter of 'length × width × RGB color' adopted in the embodiment is 200 × 200 × 3. The second layer is a Convolutional layer (Convolutional layer), and the parameter "length × width × number of layers" of the layer moving frame is set to 3 × 3 × 100. The third layer is a corrected linear unit layer (corrected linear unit layer) that changes all negative lattices in the convolutional layer to zero. Since the convolutional layer generates a large amount of data, the fourth layer is a Pooling layer (Pooling layer) for reducing the amount of data for operation and further fitting without losing the original effective information, and the parameters of this layer are set to 2 × 2 × 100. The process then loops back from the fourth level to the second level, and the original 200 × 200 × 3 colony images are converted into a large number of 2 × 2 × 100 datasets. The fifth layer is a Fully connected layer (full connected layer), the above-mentioned 2 × 2 × 100 dataset is first divided into 1 × 1 × 400 datasets (the grid contains the result of the previous operation) according to small grids, the 1 × 1 × 400 datasets are arranged in a row, votes (votes) are performed according to numerical values, for example, a grid with a numerical value ≧ 1 is cast "GBS", and a grid with a numerical value <1 is cast "not GBS". The final voting result is the Output layer (Output layer). Thus, the judgment of whether the image of the single colony is GBS is completed. According to the embodiment, whether GBS is mixed in the normal flora of the vaginal/rectal swab sample of the pregnant woman can be detected, the result of bacteria automatic identification instrument and mass spectrum identification is used as the 'gold standard', and the compliance rate of the detection system can reach 80% -85%.

Fig. 9 is a GBS screening flowchart after applying the system according to the embodiment of the present invention, and as shown in fig. 9, the detection process of the system is as follows: 1. inoculating the pregnant woman genital tract swab in Todd-Hewitt broth, transferring the pregnant woman genital tract swab to a CBA plate the next day, and then putting the CBA plate into a photographing auxiliary device after incubating for 24-48 hours at 35 ℃; 2. fixing a photographing device (a smart phone and the like) provided with GBS screening software at the top of the photographing auxiliary device; 3. adjusting light rays, angles and the like, and shooting a clear colony picture; 4. uploading the pictures to a cloud database through software; 5. dividing the picture at the cloud, comparing the picture with a standard GBS colony picture in a database, and detecting; 6. the terminal obtains a detection result, namely whether GBS bacterial colonies are detected in the CBA plate or not; 7. the GBS screening results are reported to the doctor/pregnant woman.

The rise of Artificial Neural Networks (ANN) provides a new possibility for GBS screening, namely GBS screening is realized by colony image recognition of bacteria. As an important component of artificial intelligence (ArtificialIntelligence) and Machine Learning (Machine Learning), ANN has appeared in the last 50 centuries, and in recent years, ANN has been gradually applied to various fields of medicine with the development of big data and the dramatic improvement of computer performance. In the field of clinical microbiological examination, the growth characteristics of bacterial colonies in a culture medium (including colony size, color, appearance, edge morphology, luster, hemolytic cycle and the like) are important bases for classifying and identifying bacteria. Screening pregnant woman GBS based on ANN image recognition technology has the advantages of low cost, simplicity and convenience in operation and high accuracy, and clear colony pictures are shot by matching the shooting auxiliary device with the shooting device (a smart phone, a smart pad, a camera and the like) and then uploaded to a cloud database for comparison, so that the GBS detection results can be obtained in real time by the terminal. The GBS screening system based on image recognition improves the accuracy, objectivity and repeatability of screening, does not need to be screened by experienced technicians and expensive instruments and equipment, greatly reduces the detection cost, has wide application range, and is particularly suitable for the GBS screening of pregnant women in wide primary hospitals and maternal and child care hospitals.

Although the present invention has been described in detail hereinabove, the present invention is not limited thereto, and various modifications can be made by those skilled in the art in light of the principle of the present invention. Thus, modifications made in accordance with the principles of the present invention should be understood to fall within the scope of the present invention.

Claims

1. A group B streptococcus detection system, comprising:

2. The system of claim 1, wherein the cloud analytics means comprises:

3. The system according to claim 2, wherein the image recognition device is configured to screen a plurality of microbial colony images of suspected group B streptococcus colonies from the plurality of microbial colony images to be screened, and specifically comprises:

4. The system according to claim 3, wherein the characteristic values of the microbial colony include a size, a color and a gradient of a center-to-edge color change of the microbial colony, and the threshold range of the colony characteristics of the predetermined group B streptococci includes a threshold range of the size of the colony, a threshold range of the color of the colony and a threshold range of the gradient of the center-to-edge color change of the colony of the predetermined group B streptococci.

5. The system of claim 4, wherein for each microbial colony, the image recognition device determines that each microbial colony image is a microbial colony image of a suspected group B streptococcus when the size, color, and colony center-to-edge color change gradient of the microbial colony are within the preset colony size threshold range, colony color threshold range, and colony center-to-edge color change gradient threshold range of the group B streptococcus, respectively.

6. The system according to claim 2, wherein the artificial neural network is a convolutional neural network comprising convolutional layers, modified linear unit layers, pooling layers and fully-connected layers, and the colony analysis device analyzes the number of microbial colony images of the suspected group B streptococcus marked by the image recognition device using the convolutional neural network comprising convolutional layers, modified linear unit layers, pooling layers and fully-connected layers to determine whether the number of microbial colony images of the suspected group B streptococcus marked by the image recognition device are group B streptococcus colony images.

7. The system according to any one of claims 1 to 6, wherein the system further comprises a photographing aid for photographing the microbial colony, comprising:

a box body having a top plate, a bottom plate and side plates;

the supporting seat is arranged above the bottom plate;

8. The system of claim 7, wherein the photographing assisting device further comprises a movable arm mounted above the top plate and capable of rotating or bending relative to the top plate, and a photographing fixture mounted at an extending end of the movable arm for holding the photographing apparatus.

9. The system of claim 7, wherein the photographing assistant device further comprises: the plane scattering light source is arranged on the lower surface of the top plate, the annular light source is arranged on the inner wall of the side plate, and the ultraviolet lamp disinfection device is arranged on the inner wall of the side plate.