CN112633370B - Detection method, device, equipment and medium for filamentous fungus morphology - Google Patents
Detection method, device, equipment and medium for filamentous fungus morphology Download PDFInfo
- Publication number
- CN112633370B CN112633370B CN202011523426.7A CN202011523426A CN112633370B CN 112633370 B CN112633370 B CN 112633370B CN 202011523426 A CN202011523426 A CN 202011523426A CN 112633370 B CN112633370 B CN 112633370B
- Authority
- CN
- China
- Prior art keywords
- image
- filamentous fungi
- microscopic
- neural network
- module
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Apparatus Associated With Microorganisms And Enzymes (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention provides a detection method, a device, equipment and a medium for filamentous fungus morphology, wherein the method comprises the steps of establishing a microscopic image database of various filamentous fungi; preprocessing the microscopic image of the filamentous fungi by a high information area evaluation algorithm; constructing a neural network model based on ResNet, and performing feature extraction on the preprocessed microscopic image serving as a test sample; adjusting the neural network model; and preprocessing the image to be detected with the structural characteristics of the filamentous fungi, and inputting the preprocessed image into the trained neural network model to obtain the strain category and morphological description of the filamentous fungi in the image to be detected. By introducing artificial intelligence technologies such as computer image understanding and machine learning, the detection rate of the filamentous fungi can be greatly improved, and the machine can obtain image identification capability similar to or even higher than that of a human.
Description
Technical Field
The invention relates to the field of medical detection and image processing, in particular to a detection method, a device, equipment and a medium for filamentous fungus morphology.
Background
The filamentous fungus, i.e. brown rot fungus, is filamentous and has no photosynthesis, heterotrophic eukaryotic microorganisms are developed, hyphae are relatively developed, a large fleshy fruiting body structure is not generated, the hyphae are filamentous or long tubular structures and are coated by a hard cell wall containing chitin, the colorless transparent width is generally 3-10 um and is several times to dozens of times of the width of bacteria, and cells in the hyphae contain a large number of organelles of the eukaryotic organisms. The cytoplasmic components within the hyphae tend to concentrate toward the growth site, with the older portions of the hyphae having a large number of vacuoles and possibly being laterally separated from the younger regions, the hyphae having bifurcations, and the branched hyphae being interleaved with one another to form a mycelium population.
The direct smear of body fluid or tissue specimens of infected patients is examined under a microscope in the identification, identification and diagnosis process of fungi in primary hospitals and sites, which is an irreplaceable routine clinical diagnosis means. The infection status can be rapidly determined according to the observed pathogens, cell morphology and staining characters, so that the microscopic examination is an important basis for determining the subsequent detection path. However, there are several problems associated with performing an under-the-mirror test in the clinical microbiology department: 1. the labor intensity is high, each visual field under the observation mirror is difficult to be omitted in manual inspection, and missed diagnosis is easy to be caused after visual fatigue; 2. the requirement on the professional skills of the examining physicians is high, and the examining needs experienced physicians to carry out the examination.
Convolutional Neural Networks (CNN) are a type of feed-forward Neural network that includes convolution calculations and has a deep structure, and are one of the representative algorithms for deep learning. Convolutional neural networks have long been one of the core algorithms in the field of image recognition and have stable performance when the learning data is sufficient. For a general large-scale image classification problem, the convolutional neural network can be used for constructing a hierarchical classifier, and can also be used for extracting the distinguishing features of the image in fine classification recognition so as to be used for other classifiers to learn.
Therefore, because the identification, identification and diagnosis capabilities of fungi in the field and primary hospitals are very poor, and the channels for requesting consultation support of large hospitals are limited or untimely, the existing diagnosis technology is poor, and the system is suitable for the problems that the fungi serology technology of the current situation that primary hospitals lack people and equipment is to be developed and the like.
Disclosure of Invention
In order to solve the problems, the invention provides a detection method, a device, equipment and a medium aiming at the morphology of the filamentous fungi, which can greatly improve the detection rate of the filamentous fungi by introducing artificial intelligence technologies such as computer image understanding, machine learning and the like, so that a machine can obtain the image identification capability similar to that of a human or even higher than that of the human, and can be rapidly popularized to various hospitals by copying.
In order to achieve the purpose, the invention provides the following specific technical scheme:
in a first aspect, the present application provides a method for detecting morphology in a filamentous fungus, the method comprising:
s1, establishing a microscopic image database of various filamentous fungi;
s2, preprocessing the microscopic image of the filamentous fungi by a high information area evaluation algorithm;
s3, constructing a neural network model based on ResNet, and performing feature extraction on the preprocessed microscopic image serving as a test sample;
s4, adjusting the neural network model in the step S3;
s5, preprocessing the image to be detected with the structural characteristics of the filamentous fungi, and inputting the preprocessed image into the trained neural network model to obtain the strain type and morphological description of the filamentous fungi in the image to be detected.
In a second aspect, the present application also provides a device for detecting the morphology of a filamentous fungus, comprising:
the storage module is used for storing microscopic image data of various filamentous fungi;
the pretreatment module is used for pretreating microscopic images of various filamentous fungi;
the training module is used for constructing a neural network model based on ResNet and extracting the characteristics of the preprocessed microscopic image serving as a test sample;
and the detection module is used for preprocessing the image to be detected with the structural characteristics of the filamentous fungi and inputting the preprocessed image into the trained neural network model to obtain the strain category and morphological description of the filamentous fungi in the image to be detected.
In a third aspect, the present application further provides a computer device comprising a memory and a processor;
the memory is used for storing a computer program;
the processor is used for executing the computer program and realizing the detection method for the morphology of the filamentous fungi when the computer program is executed.
In a fourth aspect, the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, causes the processor to carry out the method of detecting morphology of a filamentous fungus as described above.
The invention has the advantages that a method, a device, equipment and a medium for detecting the morphology of the filamentous fungi are provided, a database containing various filamentous fungi microscopic images is established, the microscopic images are preprocessed through a chrominance equalization algorithm and an information density evaluation algorithm, the preprocessed filamentous fungi microscopic images are input into a neural network model for training, the neural network model is adjusted to improve the recognition precision, and finally the images to be detected are input into the trained neural network model to complete the detection of filamentous fungi strains.
The method and the device can perform quick preliminary screening on the training samples through the high information area evaluation algorithm, are favorable for quick convergence of the network, and reduce the iteration times. The convolutional neural network-residual error network algorithm can better extract the texture characteristics of the filamentous fungi and solve the problem of degradation caused by too deep network layers; the weakly supervised end-to-end learning mode is more beneficial for non-clinical examination professional model engineers to participate in model training; the extraction of morphological characteristics of the filamentous fungi is automatically finished by a network, and the knowledge gap between every two disciplines can be spanned to a certain extent.
Furthermore, the method and the device can reduce the threshold of the microbial detection technology and lay the technical foundation for the comprehensive realization of automation of microbial detection. The microbial medical image can be automatically recognized by a machine, so that the labor intensity can be greatly reduced, and the detection rate can be improved. And because machine intelligence is easy to copy, the image identification capability similar to that of a human or even higher than that of the human can be obtained. The technology for detecting the morphology of the filamentous fungi can be rapidly popularized to hospitals at all levels by copying. The implementation of national grading diagnosis and treatment policies is facilitated, the personnel investment is reduced, the diagnosis and treatment cost is reduced, and the aims of accurate medical treatment and the like are fulfilled.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
FIG. 1 is a schematic flow chart of a method for detecting morphology of a filamentous fungus according to a preferred embodiment of the present application;
FIG. 2 is a schematic block diagram of a detection device for filamentous fungus morphology according to a preferred embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
The embodiment of the application provides a detection method, a device, equipment and a medium aiming at the morphology of filamentous fungi, and by introducing artificial intelligence technologies such as computer image understanding and machine learning, the detection rate of the filamentous fungi can be greatly improved, so that a machine can obtain image identification capability similar to that of a human or even higher than that of the human, and the method can be rapidly popularized to various hospitals by copying.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic flow chart of a detection method for morphology of a filamentous fungus, which specifically includes steps S101 to S105, according to an embodiment of the present application.
S101, establishing a microscopic image database of various filamentous fungi;
first, a specimen of filamentous fungi is prepared: filamentous fungi were cultured on a Sabouraud agar SDA medium, a potato dextrose agar PDA medium or a Swedier agar CDA medium for 3 days, smeared with a tape method, and stained with gossypol blue lactate while the specimen species types were rechecked by a DNA detection method or a protein mass spectrometry detection method.
Then placing the strain under a 400X microscope and connecting the strain with a computer, and carrying out layered scanning by an automatic film feeding device or manually acquiring images with structural characteristics of the filamentous fungi to establish a microscopic image database containing various strains.
Specifically, the filamentous fungi include Aspergillus fumigatus complex, Aspergillus flavus/Aspergillus oryzae, Aspergillus terreus, Aspergillus niger complex, Aspergillus nidulans, Aspergillus polyvidus, Aspergillus versicolor, Fusarium, Penicillium citrinum, Penicillium oxalicum, and Coptomyces racemosus.
S102, preprocessing the microscopic image of the filamentous fungi through a high information area evaluation algorithm, and removing an unclear layer, a blank area and an impurity area;
furthermore, the high information area evaluation algorithm comprises a chromaticity balance algorithm and an information density evaluation algorithm, which is beneficial to the rapid convergence of the network and reduces the iteration times; the algorithm does not evaluate the entropy value of the image, and the calculation of the verified entropy value can not effectively filter out the non-clear image and the nonsense image and is sensitive to image noise. The method specifically comprises the following steps:
respectively extracting images of various strains in a microscopic image database and carrying out image normalization processing; the image normalization processing comprises image size normalization and image chromaticity normalization; the image size normalization comprises normalizing the number of pixels on an X axis and scaling the pixels on a Y axis in an equal ratio; and the image chromaticity normalization is carried out by an automatic color balance algorithm ACE to normalize the image and unify the background color.
Performing Laplace transform on the normalized image to calculate an image edge;
dividing the edge image into small blocks, respectively calculating image variance and returning to a maximum value, wherein the image variance is used for detecting whether the edge of the image is sharp, namely whether the image is fuzzy;
dividing an original image into small blocks, and respectively calculating the standard difference of image brightness for detecting whether the image has large-area bright and dark images;
converting an image color space from RGB to HSL;
manually selecting images of various filamentous fungi meeting the requirements according to the information density evaluation value, whether the images have typical characteristics and other requirements, calculating the edge variance range, the original image brightness standard deviation range and the chromaticity range of the images, screening 2000-10000 visual fields of the images as condition screening neural network training samples, and labeling strains.
S103, constructing a neural network model based on ResNet, and performing feature extraction on the preprocessed microscopic image serving as a test sample;
specifically, ResNet can better extract the texture characteristics of filamentous fungi, and solve the problem of degradation caused by too deep network layer number; the weakly supervised end-to-end learning mode is more beneficial for non-clinical examination professional model engineers to participate in model training; the morphological feature extraction of the filamentous fungi is automatically completed by a network; specifically, the construction formula of the neural network model of ResNet is as follows:
convolution layer formula for the first layer:
ci＝f(w·xi:i+h-1+b)
c＝[c1，c2，...，cn-h+1]
and Ci represents i elements in a convolution feature vector calculated according to a certain convolution in the first layer.
C, a whole convolution feature vector.
CNN Block after:
first layer in CNN Block:
second layer in CNN Block:
the third layer, which constitutes the residual structure, here the output of CNN Block:
s104, adjusting the neural network model in the step S103;
the method specifically comprises the following steps: increasing the amount of training samples for poor classification according to the classification result of the test samples, and performing error classification to remove part of the training samples; performing data normalization operation on the training image; and carrying out iterative training on the model.
And S105, preprocessing the image to be detected with the structural characteristics of the filamentous fungi, and inputting the preprocessed image into the trained neural network model to obtain the strain category and morphological description of the filamentous fungi in the image to be detected.
As shown in fig. 2, fig. 2 provides a detection device 200 for detecting the morphology of a filamentous fungus according to an embodiment of the present application, including:
the storage module 201 is used for storing microscopic image data of various filamentous fungi;
the preprocessing module 202 is used for preprocessing microscopic images of various filamentous fungi;
the training module 203 is used for constructing a neural network model based on ResNet and extracting the characteristics of the preprocessed microscopic image serving as a test sample;
the detection module 204 is configured to perform the preprocessing on the image to be detected with the structural features of the filamentous fungi, and input the preprocessed image into the trained neural network model to obtain the strain type and morphological description of the filamentous fungi in the image to be detected.
In a preferred embodiment of the present application, there is also included a computer device comprising a memory and a processor;
the memory is used for storing a computer program;
the processor is used for executing the computer program and realizing the detection method for the morphology of the filamentous fungi when the computer program is executed.
In another preferred embodiment of the present application, the method further comprises a step of storing a computer program, which when executed by a processor causes the processor to implement the method for detecting morphology of a filamentous fungus as described above.
By verifying the identification accuracy of the detection method, the detection device, the detection equipment and the detection medium for filamentous fungi morphology, 1161 test samples are correctly identified by 1129 test samples under the same acquisition environment and detection condition, the minimum identification accuracy of single classification is 87%, and the average identification accuracy is 97%.
Compared with the prior art, the beneficial effect of this application lies in:
the method and the device can perform quick preliminary screening on the training samples through the high information area evaluation algorithm, are favorable for quick convergence of the network, and reduce the iteration times. The convolutional neural network-residual error network algorithm can better extract the texture characteristics of the filamentous fungi and solve the problem of degradation caused by too deep network layers; the weakly supervised end-to-end learning mode is more beneficial for non-clinical examination professional model engineers to participate in model training; the extraction of morphological characteristics of the filamentous fungi is automatically finished by a network, and the knowledge gap between every two disciplines can be spanned to a certain extent.
Furthermore, the method and the device can reduce the technical threshold of the microbial detection, and lay the technical foundation for the comprehensive realization of automation of the microbial detection. The microbial medical image can be automatically recognized by a machine, so that the labor intensity can be greatly reduced, and the detection rate can be improved. And because machine intelligence is easy to copy, the image identification capability similar to that of a human or even higher than that of the human can be obtained. The technology for detecting the morphology of the filamentous fungi can be rapidly popularized to hospitals at all levels by copying. The implementation of national grading diagnosis and treatment policies is facilitated, the personnel investment is reduced, the diagnosis and treatment cost is reduced, and the aims of accurate medical treatment and the like are fulfilled.
The foregoing description shows and describes several preferred embodiments of the application, but as aforementioned, it is to be understood that the application is not limited to the forms disclosed herein, but is not to be construed as excluding other embodiments and is capable of use in various other combinations, modifications, and environments and is capable of changes within the scope of the application as expressed herein, commensurate with the above teachings, or the skill or knowledge of the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the application, which is to be protected by the claims appended hereto.
Claims (7)
1. A method for detecting morphology in a filamentous fungus, the method comprising:
s1, establishing a microscopic image database of various filamentous fungi;
s2, preprocessing the microscopic image of the filamentous fungi by a high information area evaluation algorithm;
s3, constructing a neural network model based on ResNet, and performing feature extraction on the preprocessed microscopic image serving as a test sample;
s4, adjusting the neural network model in the step S3;
s5, preprocessing the image to be detected with the structural characteristics of the filamentous fungi, and inputting the preprocessed image into the trained neural network model to obtain the strain type and morphological description of the filamentous fungi in the image to be detected, wherein S2 specifically comprises the following steps:
respectively extracting images of various strains in a microscopic image database and carrying out image normalization processing;
performing Laplace transform on the normalized image to calculate an image edge;
dividing the edge image into small blocks, respectively calculating image variance and returning to a maximum value;
dividing the original image into small blocks and respectively calculating the standard deviation of the image brightness;
converting an image color space from RGB to HSL;
and selecting images of various filamentous fungi meeting the requirements as statistical samples, and labeling strains.
2. The method according to claim 1, wherein S1 specifically comprises the steps of:
establishing a strain library, preparing a gossypol blue lactate staining specimen after culturing and maturing strains of filamentous fungi, and rechecking the strain type of the specimen by a DNA detection method or a protein mass spectrometry detection method;
and (3) the automatic acquisition equipment scans the microscopic images of the filamentous fungus staining specimen in a layering manner, and a microscopic image database of various filamentous fungi is established.
3. The method according to claim 2, wherein the image normalization process comprises image size normalization and image chromaticity normalization; the image size normalization comprises normalizing the number of pixels on an X axis and scaling the pixels on a Y axis in an equal ratio; and the image chromaticity normalization is used for carrying out image normalization and unifying background colors through an automatic color balance algorithm.
4. The method according to claim 3, wherein S4 specifically comprises the steps of:
increasing the amount of training samples for poor classification according to the classification result of the test samples, and performing error classification to remove part of the training samples;
performing data normalization operation on the training image;
and carrying out iterative training on the model.
5. A device for detecting morphology in a filamentous fungus, comprising:
the storage module is used for storing microscopic image data of various filamentous fungi;
the pretreatment module is used for pretreating microscopic images of various filamentous fungi;
the training module is used for constructing a neural network model based on ResNet and extracting the characteristics of the preprocessed microscopic image serving as a test sample;
the detection module is used for preprocessing the image to be detected with the structural characteristics of the filamentous fungi and inputting the preprocessed image into the trained neural network model to obtain the strain type and morphological description of the filamentous fungi in the image to be detected, and the preprocessing module comprises the following modules:
a module for respectively extracting images of various strains in the microscopic image database and carrying out image normalization processing;
a module for performing Laplace transform on the normalized image to calculate the image edge;
a module for dividing the edge image into small blocks, respectively calculating the image variance and returning to the maximum value;
a module for dividing the original image into small blocks and respectively calculating the standard deviation of the image brightness;
a module for converting RGB into HSL for image color space;
and selecting images of various filamentous fungi meeting the requirements as statistical samples, and carrying out strain labeling.
6. A computer device, wherein the computer device comprises a memory and a processor;
the memory is used for storing a computer program;
the processor for executing the computer program and implementing the detection method for morphology of a filamentous fungus according to any one of claims 1-4 when the computer program is executed.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to carry out the method for detecting morphology of a filamentous fungus according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011523426.7A CN112633370B (en) | 2020-12-22 | 2020-12-22 | Detection method, device, equipment and medium for filamentous fungus morphology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011523426.7A CN112633370B (en) | 2020-12-22 | 2020-12-22 | Detection method, device, equipment and medium for filamentous fungus morphology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112633370A CN112633370A (en) | 2021-04-09 |
| CN112633370B true CN112633370B (en) | 2022-01-14 |
Family
ID=75320996
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011523426.7A Active CN112633370B (en) | 2020-12-22 | 2020-12-22 | Detection method, device, equipment and medium for filamentous fungus morphology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112633370B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114581909A (en) * | 2022-02-28 | 2022-06-03 | 广西壮族自治区人民医院 | Infectious keratopathy living pathogenic bacteria detection method combining deep learning and cornea living confocal microscopy |
| CN116908178B (en) * | 2023-09-13 | 2024-03-08 | 吉林农业大学 | Hypha phenotype acquisition device and method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103077508A (en) * | 2013-01-25 | 2013-05-01 | 西安电子科技大学 | Transform domain non local and minimum mean square error-based SAR (Synthetic Aperture Radar) image denoising method |
| CN108875913A (en) * | 2018-05-30 | 2018-11-23 | 江苏大学 | A kind of matsutake Fast nondestructive evaluation system and method based on convolutional neural networks |
| CN111489833A (en) * | 2019-12-19 | 2020-08-04 | 上海杏脉信息科技有限公司 | Lung cell pathology rapid on-site evaluation system and method and computer readable storage medium |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470896A (en) * | 2007-12-24 | 2009-07-01 | 南京理工大学 | Automotive target flight mode prediction technique based on video analysis |
| US20130309716A1 (en) * | 2012-05-17 | 2013-11-21 | Biomerieux Inc. | Methods For Inactiviation And/or Extraction of A Fungus Test Sample For Characterization And/or Identification Using Mass Spectrometry |
| CN103577195B (en) * | 2013-11-14 | 2016-10-12 | 中国联合网络通信集团有限公司 | A kind of software requirement analysis quantization method and system |
| US20190371426A1 (en) * | 2016-12-28 | 2019-12-05 | Ascus Biosciences, Inc. | Methods, apparatuses, and systems for analyzing microorganism strains in complex heterogeneous communities, determining functional relationships and interactions thereof, and diagnostics and biostate management and biostate temporal forecasting based thereon |
| CN107358193A (en) * | 2017-07-07 | 2017-11-17 | 南京天数信息科技有限公司 | Dermatophyte recognition detection method based on InceptionV3+ fully-connected networks |
| JP2021509212A (en) * | 2017-10-27 | 2021-03-18 | 国立交通大学 | Disease prediction and control methods and their systems |
| CN108030494B (en) * | 2017-11-08 | 2019-11-15 | 华南理工大学 | Electrocardiosignal error flag training sample recognition methods based on cross validation |
| CN108520206B (en) * | 2018-03-22 | 2020-09-29 | 南京大学 | Fungus microscopic image identification method based on full convolution neural network |
| CN110796661B (en) * | 2018-08-01 | 2022-05-31 | 华中科技大学 | Fungal microscopic image segmentation detection method and system based on convolutional neural network |
| CN110793946A (en) * | 2018-08-01 | 2020-02-14 | 华中科技大学 | Fungus sample microscopic imaging and intelligent identification system and method |
| CN109614856A (en) * | 2018-10-31 | 2019-04-12 | 西安理工大学 | Fungi image classification method based on convolutional neural networks |
| CN110205399A (en) * | 2019-06-17 | 2019-09-06 | 颐保医疗科技(上海)有限公司 | A kind of collecting method of the fungi based on the good culture of Kerma (unit of kinetic energy) |
| CN110263863B (en) * | 2019-06-24 | 2021-09-10 | 南京农业大学 | Fine-grained fungus phenotype identification method based on transfer learning and bilinear InceptionResNet V2 |
| CN110632191B (en) * | 2019-09-10 | 2023-04-18 | 福建工程学院 | Transformer chromatographic peak qualitative method and system based on decision tree algorithm |
| CN111754457B (en) * | 2020-05-15 | 2023-08-18 | 中山大学 | Mycelium screening system based on cornea confocal image |
| CN111881948A (en) * | 2020-07-10 | 2020-11-03 | 马上消费金融股份有限公司 | Training method and device of neural network model, and data classification method and device |
| CN112102232B (en) * | 2020-07-31 | 2021-11-02 | 深圳大学 | Method and device for automatically evaluating colony quality of induced pluripotent stem cells |
-
2020
- 2020-12-22 CN CN202011523426.7A patent/CN112633370B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103077508A (en) * | 2013-01-25 | 2013-05-01 | 西安电子科技大学 | Transform domain non local and minimum mean square error-based SAR (Synthetic Aperture Radar) image denoising method |
| CN108875913A (en) * | 2018-05-30 | 2018-11-23 | 江苏大学 | A kind of matsutake Fast nondestructive evaluation system and method based on convolutional neural networks |
| CN111489833A (en) * | 2019-12-19 | 2020-08-04 | 上海杏脉信息科技有限公司 | Lung cell pathology rapid on-site evaluation system and method and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| Deep learning approach to description and classification of fungi microscopic;Bartosz Zeliński 等;《PLoS ONE》;20200630;第15卷(第6期);1-22 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112633370A (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112633370B (en) | Detection method, device, equipment and medium for filamentous fungus morphology | |
| CN112102229A (en) | Intelligent industrial CT detection defect identification method based on deep learning | |
| CN110796661B (en) | Fungal microscopic image segmentation detection method and system based on convolutional neural network | |
| CN111079620A (en) | Leukocyte image detection and identification model construction method based on transfer learning and application | |
| CN110148126B (en) | Blood leukocyte segmentation method based on color component combination and contour fitting | |
| Hiremath et al. | Automatic identification and classification of bacilli bacterial cell growth phases | |
| US20240335156A1 (en) | Measurement method and system based on image electroencephalogram sensitivity data for built environment dominant color | |
| CN112330613B (en) | Evaluation method and system for cytopathology digital image quality | |
| CN114782948B (en) | Global interpretation method and system for cervical fluid-based cytological smear | |
| CN117975170B (en) | Medical information processing method and system based on big data | |
| CN113192022A (en) | Pathogenic spore identification and counting method and device based on deep learning | |
| CN112419335B (en) | Shape loss calculation method of cell nucleus segmentation network | |
| CN116844696A (en) | Facial image traditional Chinese medicine constitution identification method based on deep neural network | |
| CN114445408B (en) | Improved circulation-oriented filtering algorithm-based pathogen detection promoting method, equipment and storage medium | |
| CN115731419A (en) | Cell growth state discrimination method and system based on intelligent discrimination algorithm | |
| CN115359031A (en) | Digital pathological image slice quality evaluation method | |
| CN113505784A (en) | Automatic nail annotation analysis method and device, electronic equipment and storage medium | |
| CN114120035A (en) | Medical image recognition training method | |
| EP4323912A1 (en) | Analyzing microscope images of microalgae culture samples | |
| Sloan et al. | Estimating phenotypic characteristics of tuberculosis bacteria | |
| CN118072115B (en) | Medical cell detection method and system | |
| CN117496276B (en) | Lung cancer cell morphology analysis and identification method and computer readable storage medium | |
| Hidayah et al. | Detection of rubber (Heavea brasialiensis) leaf diseases using image processing techniques | |
| CN118052814B (en) | AI technology-based full-automatic specimen pretreatment system and method | |
| CN118314411B (en) | Microorganism detection method, system, equipment and medium based on image analysis |
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 |