CN113588521A - Blood detector, blood detection identification system and identification method - Google Patents
Blood detector, blood detection identification system and identification method Download PDFInfo
- Publication number
- CN113588521A CN113588521A CN202110782448.3A CN202110782448A CN113588521A CN 113588521 A CN113588521 A CN 113588521A CN 202110782448 A CN202110782448 A CN 202110782448A CN 113588521 A CN113588521 A CN 113588521A
- Authority
- CN
- China
- Prior art keywords
- image
- blood
- blood cell
- identification
- hydrogel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 210000004369 blood Anatomy 0.000 title claims abstract description 73
- 239000008280 blood Substances 0.000 title claims abstract description 73
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 15
- 210000000601 blood cell Anatomy 0.000 claims abstract description 131
- 239000000017 hydrogel Substances 0.000 claims abstract description 60
- 230000005540 biological transmission Effects 0.000 claims abstract description 39
- 230000009347 mechanical transmission Effects 0.000 claims abstract description 21
- 238000003825 pressing Methods 0.000 claims abstract description 10
- 239000002243 precursor Substances 0.000 claims abstract description 8
- 239000007788 liquid Substances 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 76
- 238000013145 classification model Methods 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 23
- 238000007781 pre-processing Methods 0.000 claims description 22
- 230000003287 optical effect Effects 0.000 claims description 14
- 238000003384 imaging method Methods 0.000 claims description 12
- 230000000877 morphologic effect Effects 0.000 claims description 11
- 238000009534 blood test Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 125000006850 spacer group Chemical group 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 210000003743 erythrocyte Anatomy 0.000 description 8
- 238000009826 distribution Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 210000004027 cell Anatomy 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000009977 dual effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 206010002065 Anaemia megaloblastic Diseases 0.000 description 2
- 208000015710 Iron-Deficiency Anemia Diseases 0.000 description 2
- 208000000682 Megaloblastic Anemia Diseases 0.000 description 2
- 208000002903 Thalassemia Diseases 0.000 description 2
- 206010043561 Thrombocytopenic purpura Diseases 0.000 description 2
- XECAHXYUAAWDEL-UHFFFAOYSA-N acrylonitrile butadiene styrene Chemical compound C=CC=C.C=CC#N.C=CC1=CC=CC=C1 XECAHXYUAAWDEL-UHFFFAOYSA-N 0.000 description 2
- 229920000122 acrylonitrile butadiene styrene Polymers 0.000 description 2
- 239000004676 acrylonitrile butadiene styrene Substances 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000004205 dimethyl polysiloxane Substances 0.000 description 2
- 235000013870 dimethyl polysiloxane Nutrition 0.000 description 2
- 208000014951 hematologic disease Diseases 0.000 description 2
- 231100001016 megaloblastic anemia Toxicity 0.000 description 2
- 206010028537 myelofibrosis Diseases 0.000 description 2
- 229920000435 poly(dimethylsiloxane) Polymers 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- 238000010989 Bland-Altman Methods 0.000 description 1
- 208000019838 Blood disease Diseases 0.000 description 1
- 230000003872 anastomosis Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 208000018706 hematopoietic system disease Diseases 0.000 description 1
- 238000007561 laser diffraction method Methods 0.000 description 1
- 238000001459 lithography Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- CXQXSVUQTKDNFP-UHFFFAOYSA-N octamethyltrisiloxane Chemical compound C[Si](C)(C)O[Si](C)(C)O[Si](C)(C)C CXQXSVUQTKDNFP-UHFFFAOYSA-N 0.000 description 1
- 238000004987 plasma desorption mass spectroscopy Methods 0.000 description 1
- -1 polydimethylsiloxane Polymers 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume, or surface-area of porous materials
- G01N15/10—Investigating individual particles
-
- 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
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume, or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N2015/1006—Investigating individual particles for cytology
-
- G01N2015/1022—
Abstract
The invention belongs to the technical field of medical detection, and discloses a blood detector, a blood detection identification system and an identification method. Introducing blood and hydrogel precursor liquid into a chip chamber of the microfluidic chip through a chip inlet part of the microfluidic chip, wherein a micro-hydrogel column is arranged in the chip chamber, and curing blood cells in the micro-hydrogel column through blue light exposure to prepare a hydrogel actuator; acquiring and obtaining a blood cell original image through an image acquisition and transmission assembly; pressing the mechanical transmission component to brake blood cells in the hydrogel actuator; acquiring and obtaining a blood cell deformation image through an image acquisition and transmission assembly; transmitting the blood cell original image and the blood cell deformation image to identification equipment through an image acquisition and transmission assembly; and obtaining classification identification result information through the identification equipment. The invention solves the problems of larger volume, higher cost and more complex operation of the blood detection device in the prior art.
Description
Technical Field
The invention belongs to the technical field of medical detection, and particularly relates to a blood detector, a blood detection and identification system and an identification method.
Background
Existing blood tests or analyses are typically performed in hospitals or laboratories, and the test equipment employed is typically bulky, costly, and complex to operate. It remains a challenge in the art to provide a portable blood test meter that can be used to perform a high-precision, low-cost, and easy-to-operate multi-function blood test.
Disclosure of Invention
The invention provides a blood detector, a blood detection and identification system and an identification method, and solves the problems of large volume, high cost and complex operation of a blood detection device in the prior art.
The present invention provides a blood detector, comprising: the device comprises a micro-fluidic chip, a mechanical transmission assembly, an image acquisition transmission assembly and a shell;
the micro-fluidic chip comprises a chip inlet part, a chip outlet part, a chip chamber and a micro-hydrogel column;
the micro-fluidic chip and the image acquisition and transmission assembly are arranged in the shell; the mechanical transmission assembly is arranged on the shell and is arranged above the micro-hydrogel column;
the microfluidic chip is used for providing an imaging platform for blood cells; leading blood and hydrogel precursor liquid into the chip chamber through the chip inlet part, positioning the micro-hydrogel column in the chip chamber, and solidifying blood cells in the micro-hydrogel column through blue light exposure to prepare a hydrogel actuator;
the mechanical transmission component is used for transmitting the force generated by external pressing to the hydrogel actuator so as to brake blood cells in the hydrogel actuator;
the image acquisition and transmission assembly is used for acquiring and acquiring blood cell original images and blood cell deformation images and transmitting the blood cell original images and the blood cell deformation images to external identification equipment.
Preferably, the mechanical transmission assembly comprises: springs, buttons and spacers;
one end of the spring is connected with the gasket, and the spring is arranged above the gasket; the button is connected with the other end of the spring and arranged above the spring; the lower surface of the gasket is tightly attached to the upper surface of the micro-hydrogel column.
Preferably, the image acquisition and transmission assembly comprises: the device comprises a patch type light source module, an optical lens, an image acquisition module and an image transmission module;
the patch type light source module is arranged above the microfluidic chip, the optical lens, the image acquisition module and the image transmission module are all arranged below the microfluidic chip, and the image acquisition module is respectively connected with the image transmission module and the optical lens;
the patch type light source module is used for providing a light source for blood cell imaging; the optical lens is used for carrying out focusing adjustment on blood cell imaging; the image acquisition module is used for acquiring the blood cell original image and the blood cell deformation image; the image transmission module is used for transmitting the blood cell original image and the blood cell deformation image to external identification equipment.
The invention provides a blood detection and identification system, comprising: an identification device, and the blood test meter described above;
the identification equipment is connected with the blood detector through a data line; the identification equipment is used for receiving the blood cell original image and the blood cell deformation image and obtaining classification identification result information according to the blood cell original image and the blood cell deformation image.
Preferably, the recognition device comprises an image preprocessing module, a training optimization module and a classification recognition module;
the image preprocessing module is used for preprocessing the obtained blood cell original image and the blood cell deformation image to obtain an image vector and a parameter vector of the blood cell; the image vectors comprise original image vectors and deformation image vectors, and the parameter vectors comprise morphological parameter vectors and mechanical parameter vectors;
the training optimization module is used for training and optimizing a pre-constructed blood detection classification model to obtain a trained blood detection classification model;
and the classification and identification module is used for preprocessing the blood cell original image to be classified and identified and the corresponding blood cell deformation image, inputting the preprocessed blood cell original image and the preprocessed blood cell deformation image into the trained blood detection and classification model, and acquiring classification and identification result information.
Preferably, the blood detection classification model is constructed based on a deep convolutional neural network, and comprises six convolutional layers and three full-connection layers; the three fully-connected layers contain 40, 64 and 20 vectors, respectively, with the first fully-connected layer containing 32 image vectors and 8 parameter vectors.
Preferably, the pretreatment comprises: converting the original image into a gray image; converting the gray image into a binary image based on a set threshold; filling the outline of the binary image by adopting filling hole operation; and carrying out pixel analysis on the filled image to obtain the parameter vector.
Preferably, the identification device is a smart phone or a tablet computer, and the identification device obtains the classification identification result information based on cloud computing.
The invention provides a blood detection and identification method, which comprises the following steps:
and 6, obtaining classification recognition result information through the recognition equipment.
Preferably, said step 6 comprises the following sub-steps:
6.1, preprocessing the obtained blood cell original image and the blood cell deformation image through an image preprocessing module in the identification equipment to obtain an image vector and a parameter vector of the blood cell; the image vectors comprise original image vectors and deformation image vectors, and the parameter vectors comprise morphological parameter vectors and mechanical parameter vectors;
6.2, training and optimizing a pre-constructed blood detection classification model through a training optimization module in the recognition equipment to obtain a trained blood detection classification model;
step 6.3, preprocessing the blood cell original image to be classified and recognized and the corresponding blood cell deformation image through a classification recognition module in the recognition equipment, and inputting the preprocessed blood cell original image and the preprocessed blood cell deformation image into a trained blood detection classification model to obtain classification recognition result information;
the blood detection classification model is constructed on the basis of a deep convolutional neural network, and comprises six convolutional layers and three full-connection layers; the three fully-connected layers contain 40, 64 and 20 vectors, respectively, wherein the first fully-connected layer contains 32 image vectors and 8 parameter vectors;
and the identification equipment obtains the classification identification result information based on cloud computing.
One or more technical schemes provided by the invention at least have the following technical effects or advantages:
in the invention, the provided blood detector utilizes the hydrogel actuator to accurately control the deformation of blood cells in blood through continuous pressure and maintain stable detection, and can realize high-precision, easy-to-operate and low-cost blood detection and blood quality monitoring. And by combining the identification equipment, classification identification result information can be obtained according to the blood cell original image and the blood cell deformation image, so that the effect of accurately identifying the blood cells is achieved.
Drawings
Fig. 1 is a schematic structural diagram of a blood detection and identification system according to an embodiment of the present invention;
fig. 2 is a comparison graph of monitoring performance between a blood detection and identification system provided by an embodiment of the present invention and a laser diffraction-based erythrocyte deformation analyzer in the prior art;
fig. 3 is a schematic diagram of a blood detection and identification method combining a neural network and cloud computing according to an embodiment of the present invention.
The device comprises a micro-fluidic chip 1, a mechanical transmission component 2, a surface mount type light source module 3, an optical lens 4, an image transmission module 5, an image acquisition module 6, an upper cover part 7, a lower cover part 8 and a clamp part 9;
11-chip inlet part, 12-chip outlet part, 13-chip chamber and 14-micro hydrogel column;
21-spring, 22-button, 23-spacer.
Detailed Description
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Example 1:
Wherein the mechanical transmission assembly 2 comprises: a spring 21, a button 22 and a washer 23. One end of the spring 21 is connected with the gasket 23, and the spring 21 is arranged above the gasket 23; the button 22 is connected with the other end of the spring 21, and the button 22 is arranged above the spring 21; the lower surface of the spacer 23 is closely attached to the upper surface of the micro-hydrogel column 14.
The image acquisition transmission assembly comprises: the device comprises a patch type light source module 3, an optical lens 4, an image acquisition module 6 and an image transmission module 5. The patch type light source module 3 is arranged above the micro-fluidic chip 1, the optical lens 4, the image acquisition module 6 and the image transmission module 5 are all arranged below the micro-fluidic chip 1, and the image acquisition module 6 is respectively connected with the image transmission module 5 and the optical lens 4. The patch type light source module 3 is used for providing a light source for blood cell imaging; the optical lens 4 is used for carrying out focusing adjustment on blood cell imaging; the image acquisition module 6 is used for acquiring the blood cell original image and the blood cell deformation image; the image transmission module 5 is configured to transmit the blood cell original image and the blood cell deformation image to an external identification device.
The housing includes an upper cover portion 7, a lower cover portion 8, and a clamp portion 9. The upper cover part 7 and the lower cover part 8 form a main space of the shell, the microfluidic chip 1 and the image acquisition and transmission assembly are arranged in the space, the clamp part 9 is arranged above the upper cover part 7, and the mechanical transmission assembly 2 is arranged on the clamp part 9.
For example, the housing is manufactured by a 3D printing process using ABS material, the template of the microfluidic chip 1 is manufactured by uv lithography, and the microfluidic chip 1 is made of polydimethylsiloxane (PDMS, refractive index 1.406).
The button 22 is an acrylonitrile-butadiene-styrene copolymer with a diameter of 1.3 cm; the stiffness coefficient of the spring 21 is 5N/cm; the diameter of the gasket 23 is 1cm, and a glass gasket is specifically adopted.
Example 2:
The recognition device comprises an image preprocessing module, a training optimization module and a classification recognition module. The image preprocessing module is used for preprocessing the obtained blood cell original image and the blood cell deformation image to obtain an image vector and a parameter vector of the blood cell; the image vectors comprise original image vectors and deformation image vectors, and the parameter vectors comprise morphological parameter vectors and mechanical parameter vectors. The training optimization module is used for training and optimizing a pre-constructed blood detection classification model to obtain a trained blood detection classification model. And the classification identification module is used for preprocessing the blood cell original image to be classified and identified and the corresponding blood cell deformation image, inputting the preprocessed blood cell original image and the preprocessed blood cell deformation image into the trained blood detection classification model, and acquiring classification identification result information.
Specifically, the blood detection classification model is constructed based on a deep convolutional neural network, and comprises six convolutional layers and three full-connection layers; the three fully-connected layers contain 40, 64 and 20 vectors, respectively, with the first fully-connected layer containing 32 image vectors and 8 parameter vectors.
The pretreatment comprises the following steps: converting the original image into a gray image; converting the gray level image into a binary image based on a set threshold value; filling the outline of the binary image by adopting filling hole operation; and carrying out pixel analysis on the filled image to obtain the parameter vector.
The identification device adopts a smart phone or a tablet personal computer, and the identification device obtains the classification identification result information based on cloud computing.
Example 3:
and 6, obtaining classification recognition result information through the recognition equipment.
Wherein the step 6 comprises the following substeps:
6.1, preprocessing the obtained blood cell original image and the blood cell deformation image through an image preprocessing module in the identification equipment to obtain an image vector and a parameter vector of the blood cell; the image vectors comprise original image vectors and deformation image vectors, and the parameter vectors comprise morphological parameter vectors and mechanical parameter vectors;
6.2, training and optimizing a pre-constructed blood detection classification model through a training optimization module in the recognition equipment to obtain a trained blood detection classification model;
and 6.3, preprocessing the blood cell original image to be classified and recognized and the corresponding blood cell deformation image through a classification recognition module in the recognition equipment, and inputting the preprocessed blood cell original image and the preprocessed blood cell deformation image into a trained blood detection classification model to obtain classification recognition result information.
The blood detection classification model is constructed on the basis of a deep convolutional neural network, and comprises six convolutional layers and three full-connection layers; the three fully-connected layers contain 40, 64 and 20 vectors, respectively, wherein the first fully-connected layer contains 32 image vectors and 8 parameter vectors; and the identification equipment obtains the classification identification result information based on cloud computing.
For example, the ratio of blood to hydrogel precursor is 1: 100; exposure was performed by blue light (Flashlight, FENIX TK25RB) under a photomask (Filin film, jixiangungdian).
The present invention is further described below.
The blood detection and identification system provided by the invention can realize accurate cell identification based on dual marks of the shape and mechanics of the hydrogel actuator, the hydrogel actuator is operated by utilizing the mechanics transmission component, so that the shape (diameter, roundness, axial ratio and corresponding distribution width) and the mechanics parameters (deformability and distribution width) of blood cells are changed, an adjustable imaging platform is designed to capture blood cell images on different focusing surfaces, and the collected blood cell images are processed by utilizing identification equipment, so that the blood cells are accurately identified by combining the shape and the mechanics dual identification.
For example, a smartphone is adopted to collect blood cell images in a 360-micron × 360-micron micro-hydrogel column field through an optical lens, and the images are converted into 8-bit grayscale images; after the software automatically adjusts the light intensity and the contrast, the blood cell image is converted into a binary image through threshold operation; a threshold is set for clearing cell debris and stacking; then, the outline is filled by adopting filling hole operation, so that the calculation precision is improved; and finally, calculating the area and the perimeter through software pixel analysis. Accurate cell identification is achieved through multivariate assistance of morphological parameters (diameter, roundness, axial ratio and corresponding distribution width) and mechanical parameters (deformability and distribution width thereof).
The invention realizes the blood classification recognition based on deep learning by introducing cloud computing, takes data (including dual variable parameters of morphology and mechanics) integrated by a smart phone as the input of the cloud computing, converts the data into a vector table, loads the vector table into an image vector, and performs the classification recognition of blood disease types according to a trained neural network. Wherein the deep convolutional neural network can handle a flexible number of input images.
Cloud computing based on deep learning: firstly, data enhancement is carried out on an original image through random rotation, cutting and overturning to obtain an input image. Training was then performed on the ImageNet dataset using AlexNet with pre-training weight coefficients. The layer before the last layer is set to have 32 neurons to meet the accuracy and time consuming requirements. After training is finished, the vectors are extracted as feature vectors in an embedded space for neural network learning. All inputs were adjusted to 224 x 224 pixels for cell imaging in the hydrogel actuators, the scale of the image was 0.1 mm x 0.1 mm, and the image should be cropped to the same scale-0.1 mm x 0.1 mm before being used as an input. The 32-dimensional feature vectors extracted in the images are combined with the 8-dimensional mechanical and morphological data obtained from the imaging analysis and the combined feature vectors to train a neural network with two hidden fully connected layers. A conjugate method is adopted in the training process so as to avoid overfitting and improve generalization performance.
In order to verify the monitoring function of the present invention, the monitoring performance of the blood cell deformation by the blood detection and identification system provided by the present application and the laser diffraction-based red blood cell deformation analyzer in the prior art are respectively compared, see fig. 2. Specifically, fig. 2a shows scatter plots of RBC elongation index values (EI, average 0.5373, σ 0.0082) obtained by laser diffraction-based red blood cell deformation analyzer (Lorrca, shear stress 6Pa) on 63 healthy red blood cell samples and hydrogel actuator-based red blood cell deformability values (Dr, average 1.210, σ 0.0046) obtained by the present invention (stress 3 kPa). FIG. 2b shows the mean deviation of the hydrogel actuator-based red blood cell deformability values from the laser diffraction red blood cell deformability analyzer by a Bland-Altman analysis of 0.6723 with an SD of 0.0059. The limit of anastomosis (LOA) is between 0.6607 and 0.6840. Figure 2c shows that the mountain plot analysis calculated the percentile of each ranking difference in cell deformability for the laser diffraction method and the hydrogel actuator method, with the vertical dashed line representing the center of the mountain and the horizontal dashed line representing the 5 th to 95 th percentiles. Figure 2 illustrates the miniaturization of the device provided by the present invention while maintaining a high degree of accuracy.
FIG. 3 shows that images and multivariate (morphology: diameter, roundness, axial ratio and corresponding distribution width; mechanics: deformability and distribution width) collected by the smart phone are integrated and loaded to the cloud end, classification and identification are carried out based on the trained neural network, and referring to FIGS. 3a to 3d, classification and identification data are returned to the smart phone; the patient can share the classification recognition result and the detailed parameters with the doctor through cloud sharing. Referring to fig. 3e to 3j, five typical hematological diseases including Megaloblastic Anemia (MA), Myelofibrosis (MF), Iron Deficiency Anemia (IDA), thrombocytopenic purpura (TTP), and Thalassemia (THAL), and corresponding models in healthy state were constructed. FIG. 3j shows the performance of the blood test classification model after being trained by three training methods, the first is morphological training, the second is morphological combined image training, and the third is combined morphological, mechanical and image training. By comparison, the classification model combining the image, morphology and mechanical parameters achieves 100% of classification recognition accuracy in six classifications (n-432).
In conclusion, the invention can realize blood detection and blood quality monitoring with high precision, easy operation and low cost. The combination identification device can obtain classification identification result information according to the blood cell original image and the blood cell deformation image, and achieves the effect of accurately identifying the blood cells.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to examples, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (10)
1. A blood test meter, comprising: the device comprises a micro-fluidic chip, a mechanical transmission assembly, an image acquisition transmission assembly and a shell;
the micro-fluidic chip comprises a chip inlet part, a chip outlet part, a chip chamber and a micro-hydrogel column;
the micro-fluidic chip and the image acquisition and transmission assembly are arranged in the shell; the mechanical transmission assembly is arranged on the shell and is arranged above the micro-hydrogel column;
the microfluidic chip is used for providing an imaging platform for blood cells; leading blood and hydrogel precursor liquid into the chip chamber through the chip inlet part, positioning the micro-hydrogel column in the chip chamber, and solidifying blood cells in the micro-hydrogel column through blue light exposure to prepare a hydrogel actuator;
the mechanical transmission component is used for transmitting the force generated by external pressing to the hydrogel actuator so as to brake blood cells in the hydrogel actuator;
the image acquisition and transmission assembly is used for acquiring and acquiring a blood cell original image and a blood cell deformation image and transmitting the blood cell original image and the blood cell deformation image to external identification equipment.
2. The blood testing instrument of claim 1, wherein the mechanical transmission assembly comprises: springs, buttons and spacers;
one end of the spring is connected with the gasket, and the spring is arranged above the gasket; the button is connected with the other end of the spring and arranged above the spring; the lower surface of the gasket is tightly attached to the upper surface of the micro-hydrogel column.
3. The blood testing instrument of claim 1, wherein the image capture and transmission assembly comprises: the device comprises a patch type light source module, an optical lens, an image acquisition module and an image transmission module;
the patch type light source module is arranged above the microfluidic chip, the optical lens, the image acquisition module and the image transmission module are all arranged below the microfluidic chip, and the image acquisition module is respectively connected with the image transmission module and the optical lens;
the patch type light source module is used for providing a light source for blood cell imaging; the optical lens is used for carrying out focusing adjustment on blood cell imaging; the image acquisition module is used for acquiring the blood cell original image and the blood cell deformation image; the image transmission module is used for transmitting the blood cell original image and the blood cell deformation image to external identification equipment.
4. A blood detection and identification system, comprising: an identification device, and a blood detector according to any of claims 1-3;
the identification equipment is connected with the blood detector through a data line; the identification equipment is used for receiving the blood cell original image and the blood cell deformation image and obtaining classification identification result information according to the blood cell original image and the blood cell deformation image.
5. The blood detection and identification system according to claim 4, wherein the identification device comprises an image preprocessing module, a training optimization module and a classification identification module;
the image preprocessing module is used for preprocessing the obtained blood cell original image and the blood cell deformation image to obtain an image vector and a parameter vector of the blood cell; the image vectors comprise original image vectors and deformation image vectors, and the parameter vectors comprise morphological parameter vectors and mechanical parameter vectors;
the training optimization module is used for training and optimizing a pre-constructed blood detection classification model to obtain a trained blood detection classification model;
and the classification and identification module is used for preprocessing the blood cell original image to be classified and identified and the corresponding blood cell deformation image, inputting the preprocessed blood cell original image and the preprocessed blood cell deformation image into the trained blood detection and classification model, and acquiring classification and identification result information.
6. The blood detection and identification system of claim 5, wherein the blood detection classification model is constructed based on a deep convolutional neural network, and comprises six convolutional layers and three fully-connected layers; the three fully-connected layers contain 40, 64 and 20 vectors, respectively, with the first fully-connected layer containing 32 image vectors and 8 parameter vectors.
7. The blood detection and identification system of claim 5, wherein the preprocessing comprises: converting the original image into a gray image; converting the gray image into a binary image based on the set threshold; filling the outline of the binary image by adopting filling hole operation; and carrying out pixel analysis on the filled image to obtain the parameter vector.
8. The blood detection and identification system according to claim 4, wherein the identification device is a smartphone or a tablet computer, and the identification device obtains the classification and identification result information based on cloud computing.
9. A blood detection and identification method is characterized by comprising the following steps:
step 1, introducing blood and hydrogel precursor liquid into a chip chamber of a microfluidic chip through a chip inlet part of the microfluidic chip, wherein a micro hydrogel column is arranged in the chip chamber, and curing blood cells in the micro hydrogel column through blue light exposure to prepare a hydrogel actuator;
step 2, acquiring and obtaining a blood cell original image through an image acquisition and transmission assembly;
step 3, pressing the mechanical transmission component, and transmitting the force generated by external pressing to the hydrogel actuator through the mechanical transmission component so as to brake blood cells in the hydrogel actuator;
step 4, acquiring and obtaining a blood cell deformation image through the image acquisition and transmission assembly;
step 5, transmitting the blood cell original image and the blood cell deformation image to an identification device through the image acquisition and transmission assembly;
and 6, obtaining classification recognition result information through the recognition equipment.
10. The blood detection and identification method according to claim 9, wherein the step 6 comprises the substeps of:
6.1, preprocessing the obtained blood cell original image and the blood cell deformation image through an image preprocessing module in the identification equipment to obtain an image vector and a parameter vector of the blood cell; the image vectors comprise original image vectors and deformation image vectors, and the parameter vectors comprise morphological parameter vectors and mechanical parameter vectors;
6.2, training and optimizing a pre-constructed blood detection classification model through a training optimization module in the recognition equipment to obtain a trained blood detection classification model;
step 6.3, preprocessing the blood cell original image to be classified and recognized and the corresponding blood cell deformation image through a classification recognition module in the recognition equipment, and inputting the preprocessed blood cell original image and the preprocessed blood cell deformation image into a trained blood detection classification model to obtain classification recognition result information;
the blood detection classification model is constructed on the basis of a deep convolutional neural network and comprises six convolutional layers and three full-connection layers; the three fully-connected layers contain 40, 64 and 20 vectors, respectively, wherein the first fully-connected layer contains 32 image vectors and 8 parameter vectors;
and the identification equipment obtains the classification identification result information based on cloud computing.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110782448.3A CN113588521B (en) | 2021-07-12 | 2021-07-12 | Blood detector, blood detection identification system and identification method |
| PCT/CN2021/120218 WO2023284117A1 (en) | 2021-07-12 | 2021-09-24 | Blood testing instrument, and blood testing and recognition system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110782448.3A CN113588521B (en) | 2021-07-12 | 2021-07-12 | Blood detector, blood detection identification system and identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113588521A true CN113588521A (en) | 2021-11-02 |
| CN113588521B CN113588521B (en) | 2022-09-06 |
Family
ID=78246976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110782448.3A Active CN113588521B (en) | 2021-07-12 | 2021-07-12 | Blood detector, blood detection identification system and identification method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113588521B (en) |
| WO (1) | WO2023284117A1 (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102836751A (en) * | 2012-09-28 | 2012-12-26 | 重庆大学 | Hydrogel micro-fluidic chip and processing method thereof |
| US20150093823A1 (en) * | 2013-10-02 | 2015-04-02 | President And Fellows Of Harvard College | Environmentally Responsive Microstructured Hybrid Actuator Assemblies For Use in Mechanical Stimulation of Cells |
| CN104819119A (en) * | 2004-12-14 | 2015-08-05 | 麦德医像公司 | Actuator pump system |
| CN106977649A (en) * | 2017-04-21 | 2017-07-25 | 北京航空航天大学 | It is a kind of to deform controllable hydrogel actuator preparation method |
| CN108961249A (en) * | 2018-07-19 | 2018-12-07 | 厦门理工学院 | One cervical cancer cells identifying and diagnosing method again |
| CN110452801A (en) * | 2019-07-04 | 2019-11-15 | 中国科学技术大学 | A kind of micro-fluidic chip and preparation method thereof and catching method |
| CN111044735A (en) * | 2019-12-31 | 2020-04-21 | 武汉大学 | Method for measuring follicle stimulating hormone |
| CN113008765A (en) * | 2021-03-03 | 2021-06-22 | 北京理工大学 | Cancer cell dynamic behavior detection system adopting deformable microchannel |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108855256B (en) * | 2018-04-25 | 2020-06-02 | 南开大学 | Microfluidic chip and method for detecting deformability of red blood cells |
| RU2732895C1 (en) * | 2019-05-27 | 2020-09-24 | Общество с ограниченной ответственностью "ПЛАТФОРМА ТРЕТЬЕ МНЕНИЕ" | Method for isolating and classifying blood cell types using deep convolution neural networks |
| CN112986063B (en) * | 2021-01-18 | 2022-04-15 | 西北大学 | High-throughput chromosome and cytoskeleton strain flow analyzer and implementation method |
| CN113008766B (en) * | 2021-03-03 | 2022-08-23 | 北京理工大学 | Cancer cell dynamic behavior detection system based on microfluidic multi-extrusion |
| CN113607609B (en) * | 2021-06-01 | 2022-08-16 | 武汉大学 | Intelligent mobile phone imaging analysis system based on finger-pressure type micro-fluidic platform and application thereof |
-
2021
- 2021-07-12 CN CN202110782448.3A patent/CN113588521B/en active Active
- 2021-09-24 WO PCT/CN2021/120218 patent/WO2023284117A1/en unknown
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104819119A (en) * | 2004-12-14 | 2015-08-05 | 麦德医像公司 | Actuator pump system |
| CN102836751A (en) * | 2012-09-28 | 2012-12-26 | 重庆大学 | Hydrogel micro-fluidic chip and processing method thereof |
| US20150093823A1 (en) * | 2013-10-02 | 2015-04-02 | President And Fellows Of Harvard College | Environmentally Responsive Microstructured Hybrid Actuator Assemblies For Use in Mechanical Stimulation of Cells |
| CN106977649A (en) * | 2017-04-21 | 2017-07-25 | 北京航空航天大学 | It is a kind of to deform controllable hydrogel actuator preparation method |
| CN108961249A (en) * | 2018-07-19 | 2018-12-07 | 厦门理工学院 | One cervical cancer cells identifying and diagnosing method again |
| CN110452801A (en) * | 2019-07-04 | 2019-11-15 | 中国科学技术大学 | A kind of micro-fluidic chip and preparation method thereof and catching method |
| CN111044735A (en) * | 2019-12-31 | 2020-04-21 | 武汉大学 | Method for measuring follicle stimulating hormone |
| CN113008765A (en) * | 2021-03-03 | 2021-06-22 | 北京理工大学 | Cancer cell dynamic behavior detection system adopting deformable microchannel |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023284117A1 (en) | 2023-01-19 |
| CN113588521B (en) | 2022-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7261414B2 (en) | Analysis method | |
| KR102311654B1 (en) | Smart skin disease discrimination platform system constituting API engine for discrimination of skin disease using artificial intelligence deep run based on skin image | |
| Pirone et al. | Speeding up reconstruction of 3D tomograms in holographic flow cytometry via deep learning | |
| US9881373B2 (en) | Image generating apparatus and image generating method | |
| Huang et al. | Machine learning based single-frame super-resolution processing for lensless blood cell counting | |
| CN109740560B (en) | Automatic human body cell protein identification method and system based on convolutional neural network | |
| AU2019346843B2 (en) | Automated evaluation of sperm morphology | |
| Tania et al. | Intelligent image-based colourimetric tests using machine learning framework for lateral flow assays | |
| EP3124953B1 (en) | Evaluation method of spheroid and spheroid evaluation apparatus | |
| US11733151B2 (en) | Assay detection, accuracy and reliability improvement | |
| Salido et al. | A low-cost automated digital microscopy platform for automatic identification of diatoms | |
| EP3844477A1 (en) | Assay accuracy improvement | |
| Chen et al. | Touchable cell biophysics property recognition platforms enable multifunctional blood smart health care | |
| JP2021535369A (en) | Image-based assay with intelligent monitoring structure | |
| Parab et al. | Red blood cell classification using image processing and CNN | |
| Suwannaphong et al. | Parasitic egg detection and classification in low-cost microscopic images using transfer learning | |
| CN110728312A (en) | Dry eye grading system based on regional self-adaptive attention network | |
| CN116580394A (en) | White blood cell detection method based on multi-scale fusion and deformable self-attention | |
| CN110728666B (en) | Typing method and system for chronic nasosinusitis based on digital pathological slide | |
| CN114332572B (en) | Method for extracting breast lesion ultrasonic image multi-scale fusion characteristic parameters based on saliency map-guided hierarchical dense characteristic fusion network | |
| CN113588521B (en) | Blood detector, blood detection identification system and identification method | |
| Haeffele et al. | Generative optical modeling of whole blood for detecting platelets in lens-free images | |
| CN113176230B (en) | Erythrocyte identification and attitude estimation method based on microfluidic lens-free imaging | |
| Dai et al. | Cell image reconstruction for a lens-free imaging system based on linear array sensor | |
| TWI699532B (en) | Equipment for testing biological specimens |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |