CN116612471A - Open field imaging detection analysis method and system for organoid vitality analysis - Google Patents
Open field imaging detection analysis method and system for organoid vitality analysis Download PDFInfo
- Publication number
- CN116612471A CN116612471A CN202310598781.8A CN202310598781A CN116612471A CN 116612471 A CN116612471 A CN 116612471A CN 202310598781 A CN202310598781 A CN 202310598781A CN 116612471 A CN116612471 A CN 116612471A
- Authority
- CN
- China
- Prior art keywords
- organoid
- bright field
- vitality
- analysis
- image
- 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.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 166
- 210000002220 organoid Anatomy 0.000 title claims abstract description 147
- 238000003384 imaging method Methods 0.000 title claims abstract description 36
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 72
- 238000012795 verification Methods 0.000 claims description 18
- 238000010586 diagram Methods 0.000 claims description 17
- 230000005856 abnormality Effects 0.000 claims description 10
- 230000035899 viability Effects 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 231100000747 viability assay Toxicity 0.000 claims 7
- 238000003026 viability measurement method Methods 0.000 claims 7
- 238000003556 assay Methods 0.000 claims 3
- 230000005540 biological transmission Effects 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 19
- 210000000056 organ Anatomy 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 description 10
- 230000000694 effects Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 210000000130 stem cell Anatomy 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000000338 in vitro Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
Abstract
The application belongs to the technical field of organ vitality analysis, and particularly relates to a bright field imaging detection analysis method and system for organoid vitality analysis, wherein the method comprises the following steps: acquiring a plurality of bright field images of the organoid; selecting a plurality of first target bright field images from all the bright field images based on the similarity; obtaining a training set for training an organoid vitality analysis model according to the selected first target bright field image; training the organoid vitality analysis model based on the training set to obtain a trained organoid vitality analysis model; and inputting the to-be-analyzed bright field image of the organoid into a trained organoid vitality analysis model to obtain a vitality analysis result of the organoid. The method can intelligently analyze the vitality of the organoids, avoids subjective influence caused by manual analysis, improves the objectivity and accuracy of the vitality analysis result, and further improves the accuracy of the vitality analysis result through higher imaging precision of the bright field image.
Description
Technical Field
The application relates to the technical field of organ vitality analysis, in particular to a bright field imaging detection analysis method and system for organoid vitality analysis.
Background
Organoids (organoids) are three-dimensional cell complexes that are similar in structure and function to the target organ or tissue, formed by in vitro induced differentiation of stem cells or organ progenitor cells by 3D culture techniques, and at present, the viability of organoids is often analyzed manually, with a great subjective impact, and cannot be objectively analyzed.
Disclosure of Invention
Aiming at the defects of the prior art, the application provides a bright field imaging detection analysis method and a bright field imaging detection analysis system for organoid vitality analysis.
The technical scheme of the bright field imaging detection analysis method for the organoid vitality analysis is as follows:
acquiring a plurality of bright field images of the organoid;
selecting a plurality of first target bright field images from all the bright field images based on the similarity;
obtaining a training set for training an organoid vitality analysis model according to the selected first target bright field image;
training the organoid vitality analysis model based on a training set to obtain a trained organoid vitality analysis model;
and inputting the to-be-analyzed bright field image of the organoid into the trained organoid vitality analysis model to obtain a vitality analysis result of the organoid.
The bright field imaging detection analysis method for the organoid vitality analysis has the following beneficial effects:
the method can intelligently analyze the vitality of the organoids, avoids subjective influence caused by manual analysis, improves the objectivity and accuracy of the vitality analysis result, and further improves the accuracy of the vitality analysis result through higher imaging precision of the bright field image.
On the basis of the scheme, the bright field imaging detection analysis method for the organoid vitality analysis can be improved as follows.
Further, the method further comprises the following steps:
expanding a blank area on a bright field image to be analyzed of the organoid, and filling a vitality analysis result of the organoid in the blank area to obtain a result image;
vectorizing the result image to obtain a vector image, and generating a short link pointing to the vector image;
and sending the short link to an intelligent terminal of the user.
The beneficial effects of adopting the further scheme are as follows: on the one hand, the user can directly check the bright field image to be analyzed and the vitality analysis result thereof through the vector image, the method is more convenient, the user experience degree is improved, and on the other hand, when the user checks the vector image in an amplified manner, distortion cannot occur, and the user experience degree is further improved.
Further, the method further comprises the following steps:
when the vigor analysis result of the organoid is verified manually and a verification result is obtained, the short links of the vector diagram are simultaneously directed to the verification result and the vector diagram.
The beneficial effects of adopting the further scheme are as follows: the user can obtain the verification result and the vector diagram without resending the short link, and the user experience is further improved.
Further, the training organoid vitality analysis model is a deep convolutional neural network.
Further, according to the selected first target bright field image, a training set for training the organoid vitality analysis model is obtained, including:
screening the selected first target bright field image to remove the first target bright field image with abnormality to obtain a plurality of second target bright field images;
and (3) carrying out artificial type judgment on each second target bright field image, and grading the vitality one by one to form a training set for training the organoid vitality analysis model.
The beneficial effects of adopting the further scheme are as follows: by removing the first target bright field image with the abnormality, the sample quality in the training set can be improved, and the training quality of the organoid vitality analysis model is further improved.
Further, based on the similarity, selecting a plurality of first target bright field images from all bright field images, including:
calculating the similarity between every two bright field images, dividing all the bright field images into a plurality of groups according to the calculated similarity, wherein the similarity between every two bright field images in each group exceeds a preset similarity threshold;
and acquiring any bright field image from each group as a first target bright field image to obtain a plurality of first target bright field images.
The beneficial effects of adopting the further scheme are as follows: because the features extracted from the bright field images with high similarity are similar, the effect of improving the accuracy of the trained organoid vitality analysis model is limited, so that any bright field image is obtained from each group and used as a first target bright field image, the organoid vitality analysis model can quickly learn more features, and the training speed can be greatly improved under the condition of ensuring the accuracy of the trained organoid vitality analysis model.
The technical scheme of the bright field imaging detection analysis system for organoid vitality analysis is as follows:
the device comprises a first acquisition module, a selection module, a second acquisition module, a training module and an analysis module;
the first acquisition module is used for: acquiring a plurality of bright field images of the organoid;
the selecting module is used for: selecting a plurality of first target bright field images from all the bright field images based on the similarity;
the second acquisition module is used for: obtaining a training set for training an organoid vitality analysis model according to the selected first target bright field image;
the training module is used for: training the organoid vitality analysis model based on a training set to obtain a trained organoid vitality analysis model;
the analysis module is used for: and inputting the to-be-analyzed bright field image of the organoid into the trained organoid vitality analysis model to obtain a vitality analysis result of the organoid.
The bright field imaging detection analysis system for organoid vitality analysis has the following beneficial effects:
the method can intelligently analyze the vitality of the organoids, avoids subjective influence caused by manual analysis, improves the objectivity and accuracy of the vitality analysis result, and further improves the accuracy of the vitality analysis result through higher imaging precision of the bright field image.
Based on the scheme, the bright field imaging detection analysis system for the organoid vitality analysis can be improved as follows.
Further, the system also comprises an expansion filling module, a generating module and a sending module;
the expansion filling module is used for: expanding a blank area on a bright field image to be analyzed of the organoid, and filling a vitality analysis result of the organoid in the blank area to obtain a result image;
the generating module is used for: vectorizing the result image to obtain a vector image, and generating a short link pointing to the vector image;
the sending module is used for: and sending the short link to an intelligent terminal of the user.
The beneficial effects of adopting the further scheme are as follows: on the one hand, the user can directly check the bright field image to be analyzed and the vitality analysis result thereof through the vector image, the method is more convenient, the user experience degree is improved, and on the other hand, when the user checks the vector image in an amplified manner, distortion cannot occur, and the user experience degree is further improved.
Further, the generating module is further configured to:
when the vigor analysis result of the organoid is verified manually and a verification result is obtained, the short links of the vector diagram are simultaneously directed to the verification result and the vector diagram.
The beneficial effects of adopting the further scheme are as follows: the user can obtain the verification result and the vector diagram without resending the short link, and the user experience is further improved.
Further, the training organoid vitality analysis model is a deep convolutional neural network.
Further, the second obtaining module is specifically configured to:
screening the selected first target bright field image to remove the first target bright field image with abnormality to obtain a plurality of second target bright field images;
and (3) carrying out artificial type judgment on each second target bright field image, and grading the vitality one by one to form a training set for training the organoid vitality analysis model.
The beneficial effects of adopting the further scheme are as follows: by removing the first target bright field image with the abnormality, the sample quality in the training set can be improved, and the training quality of the organoid vitality analysis model is further improved.
Further, the selecting module is specifically configured to:
calculating the similarity between every two bright field images, dividing all the bright field images into a plurality of groups according to the calculated similarity, wherein the similarity between every two bright field images in each group exceeds a preset similarity threshold;
and acquiring any bright field image from each group as a first target bright field image to obtain a plurality of first target bright field images.
The beneficial effects of adopting the further scheme are as follows: because the features extracted from the bright field images with high similarity are similar, the effect of improving the accuracy of the trained organoid vitality analysis model is limited, so that any bright field image is obtained from each group and used as a first target bright field image, the organoid vitality analysis model can quickly learn more features, and the training speed can be greatly improved under the condition of ensuring the accuracy of the trained organoid vitality analysis model.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the following drawings in which:
FIG. 1 is a schematic flow chart of a bright field imaging detection analysis method for organoid viability analysis according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a bright field imaging detection analysis system for organoid viability analysis according to an embodiment of the present application.
Detailed Description
As shown in fig. 1, a bright field imaging detection analysis method for organoid vitality analysis according to an embodiment of the present application includes the following steps:
s1, acquiring a plurality of bright field images of an organoid, specifically:
multiple bright field images of the organoid are acquired using an electron microscope or an existing bright field imaging device.
S2, selecting a plurality of first target bright field images from all the bright field images based on the similarity;
s3, obtaining a training set for training the organoid vitality analysis model according to the selected first target bright field image;
the organoid vitality analysis model is a neural network, and can be specifically a deep convolutional neural network, and other deep learning models can be selected as organoid vitality analysis models according to actual conditions.
S4, training the organoid vitality analysis model based on the training set to obtain a trained organoid vitality analysis model, wherein the organoid vitality analysis model can be specifically trained by a supervised learning method or by other training modes according to actual conditions.
S5, inputting the to-be-analyzed bright field image of the organoid into a trained organoid vitality analysis model to obtain a vitality analysis result of the organoid, wherein the vitality analysis result comprises the following steps: and sending a prompt to a user when the vigor score is lower than a preset vigor score threshold value.
According to the method and the device for analyzing the vigor of the organoids, the vigor of the organoids can be intelligently analyzed, subjective influence caused by manual analysis is avoided, objectivity and accuracy of a vigor analysis result are improved, and in addition, the accuracy of the vigor analysis result is further improved through higher imaging precision of a bright field image.
Optionally, in the above technical solution, the method further includes:
s6, expanding a blank area on the bright field image to be analyzed of the organoid, and filling the vitality analysis result of the organoid in the blank area to obtain a result image;
the position and size of the blank area can be set according to practical situations.
S7, vectorizing the result image to obtain a vector image, and generating a short link pointing to the vector image;
the specific data format of the short link may be set according to practical situations, and will not be described herein.
And S8, sending the short link to the intelligent terminal of the user.
In this embodiment, on the one hand, the user is convenient to directly view the bright field image to be analyzed and the activity analysis result thereof through the vector image, and is more convenient, and the user experience degree is improved.
Optionally, in the above technical solution, the method further includes:
s9, when the activity analysis result of the organoid is verified in a manual mode and a verification result is obtained, the short links of the vector diagram are simultaneously pointed to the verification result and the vector diagram. The user can obtain the verification result and the vector diagram without resending the short link, and the user experience is further improved.
It should be noted that, manual sampling inspection may also be performed on the vigor analysis results of the organoids, for example, by means of manual sampling inspection, and the vigor analysis results of 100 organoids are verified, so that:
1) If the verification result is that the inaccurate duty ratio does not exceed the preset duty ratio threshold, judging that the accuracy of the trained organoid vitality analysis model is high, and continuously applying the trained organoid vitality analysis model;
2) If the verification result is that the inaccurate duty ratio exceeds the preset duty ratio threshold, the accuracy of the trained organoid vitality analysis model can be judged to be low, and at the moment, the organoid vitality analysis model can be trained again by adding a training set or improving the structure of the organoid vitality analysis model so as to obtain a new trained organoid vitality analysis model and be applied.
The preset duty ratio threshold value can be 10% or 20%, and the like, and can be set according to actual conditions.
Optionally, in the above technical solution, the training organoid vitality analysis model is a deep convolutional neural network.
Optionally, in the above technical solution, in S3, obtaining a training set for training an organoid vitality analysis model according to the selected first target bright field image includes:
s30, screening the selected first target bright field images to remove the first target bright field images with the abnormality to obtain a plurality of second target bright field images;
wherein the abnormal first target bright field image refers to: there is a first target bright field image with local unclear or a first target bright field image with defects, and the screening process can be realized by an image recognition mode or a manual mode.
S31, performing artificial type judgment on each second target bright field image, and scoring the vitality one by one to form a training set for training the organoid vitality analysis model.
According to the method, the first target bright field image with the abnormality is removed, so that the sample quality in a training set can be improved, and further the training quality of the organoid vitality analysis model is improved.
Optionally, in the above technical solution, in S4, selecting, based on the similarity, a plurality of first target bright field images from all bright field images includes:
s40, calculating the similarity between every two bright field images, dividing all the bright field images into a plurality of groups according to the calculated similarity, wherein the similarity between every two bright field images in each group exceeds a preset similarity threshold;
the similarity may be cosine similarity or euclidean distance, and the preset similarity threshold may be set according to actual situations.
S41, any bright field image is acquired from each group and used as a first target bright field image, and a plurality of first target bright field images are obtained.
If there are bright field images that are not grouped, all bright field images that are not grouped may be regarded as the first target bright field image.
Because the features extracted from the bright field images with high similarity are similar, the effect of improving the accuracy of the trained organoid vitality analysis model is limited, so that any bright field image is obtained from each group and used as a first target bright field image, the organoid vitality analysis model can quickly learn more features, and the training speed can be greatly improved under the condition of ensuring the accuracy of the trained organoid vitality analysis model.
In the above embodiments, although steps S1, S2, etc. are numbered, only specific embodiments of the present application are given, and those skilled in the art may adjust the execution sequence of S1, S2, etc. according to the actual situation, which is also within the scope of the present application, and it is understood that some embodiments may include some or all of the above embodiments.
As shown in fig. 2, a bright field imaging detection analysis system 200 for organoid viability analysis according to an embodiment of the present application includes a first acquisition module 210, a selection module 220, a second acquisition module 230, a training module 240, and an analysis module 250;
the first acquisition module 210 is configured to: acquiring a plurality of bright field images of the organoid;
the selecting module 220 is configured to: selecting a plurality of first target bright field images from all the bright field images based on the similarity;
the second acquisition module 230 is configured to: obtaining a training set for training an organoid vitality analysis model according to the selected first target bright field image;
the training module 240 is configured to: training the organoid vitality analysis model based on the training set to obtain a trained organoid vitality analysis model;
the analysis module 250 is configured to: and inputting the to-be-analyzed bright field image of the organoid into a trained organoid vitality analysis model to obtain a vitality analysis result of the organoid.
The method can intelligently analyze the vitality of the organoids, avoids subjective influence caused by manual analysis, improves the objectivity and accuracy of the vitality analysis result, and further improves the accuracy of the vitality analysis result through higher imaging precision of the bright field image.
Optionally, in the above technical solution, the system further includes an expansion filling module, a generating module and a sending module;
the expansion filling module is used for: expanding a blank area on a bright field image to be analyzed of the organoid, and filling a vitality analysis result of the organoid in the blank area to obtain a result image;
the generation module is used for: vectorizing the result image to obtain a vector image, and generating a short link pointing to the vector image;
the sending module is used for: and sending the short link to the intelligent terminal of the user.
On the one hand, the user can directly check the bright field image to be analyzed and the vitality analysis result thereof through the vector image, the method is more convenient, the user experience degree is improved, and on the other hand, when the user checks the vector image in an amplified manner, distortion cannot occur, and the user experience degree is further improved.
Optionally, in the above technical solution, the generating module is further configured to:
when the vigor analysis result of the organoid is verified manually and a verification result is obtained, short links of the vector diagram are simultaneously directed to the verification result and the vector diagram. The user can obtain the verification result and the vector diagram without resending the short link, and the user experience is further improved.
Optionally, in the above technical solution, the training organoid vitality analysis model is a deep convolutional neural network.
Optionally, in the above technical solution, the second obtaining module 230 is specifically configured to:
screening the selected first target bright field image to remove the first target bright field image with abnormality to obtain a plurality of second target bright field images;
and (3) carrying out artificial type judgment on each second target bright field image, and grading the vitality one by one to form a training set for training the organoid vitality analysis model.
By removing the first target bright field image with the abnormality, the sample quality in the training set can be improved, and the training quality of the organoid vitality analysis model is further improved.
Optionally, in the above technical solution, the selecting module 220 is specifically configured to:
calculating the similarity between every two bright field images, dividing all the bright field images into a plurality of groups according to the calculated similarity, wherein the similarity between every two bright field images in each group exceeds a preset similarity threshold;
and acquiring any bright field image from each group as a first target bright field image to obtain a plurality of first target bright field images.
Because the features extracted from the bright field images with high similarity are similar, the effect of improving the accuracy of the trained organoid vitality analysis model is limited, so that any bright field image is obtained from each group and used as a first target bright field image, the organoid vitality analysis model can quickly learn more features, and the training speed can be greatly improved under the condition of ensuring the accuracy of the trained organoid vitality analysis model.
The steps for realizing the corresponding functions of the parameters and the unit modules in the bright field imaging detection analysis system for the organoid vitality analysis according to the present application can refer to the parameters and the steps in the embodiment of the bright field imaging detection analysis method for the organoid vitality analysis according to the present application, and are not described herein.
An electronic device according to an embodiment of the present application includes a memory, a processor, and a program stored in the memory and running on the processor, where the processor implements the steps of any one of the above-implemented methods for performing a bright field imaging detection analysis of an organoid viability analysis when the processor executes the program.
The electronic device may be a computer, a mobile phone, or the like, and the program is corresponding to computer software or mobile phone APP, and the parameters and steps in the above electronic device according to the present application may refer to the parameters and steps in the above embodiment of a bright field imaging detection analysis method for organ-like activity analysis, which are not described herein.
Those skilled in the art will appreciate that the present application may be implemented as a system, method, or computer program product.
Accordingly, the present disclosure may be embodied in the following forms, namely: either entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or entirely software, or a combination of hardware and software, referred to herein generally as a "circuit," module "or" system. Furthermore, in some embodiments, the application may also be embodied in the form of a computer program product in one or more computer-readable media, which contain computer-readable program code.
Any combination of one or more computer readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (10)
1. A bright field imaging detection assay for organoid viability assay comprising:
acquiring a plurality of bright field images of the organoid;
selecting a plurality of first target bright field images from all the bright field images based on the similarity;
obtaining a training set for training an organoid vitality analysis model according to the selected first target bright field image;
training the organoid vitality analysis model based on a training set to obtain a trained organoid vitality analysis model;
and inputting the to-be-analyzed bright field image of the organoid into the trained organoid vitality analysis model to obtain a vitality analysis result of the organoid.
2. A bright field imaging detection assay for organoid viability assay according to claim 1, further comprising:
expanding a blank area on a bright field image to be analyzed of the organoid, and filling a vitality analysis result of the organoid in the blank area to obtain a result image;
vectorizing the result image to obtain a vector image, and generating a short link pointing to the vector image;
and sending the short link to an intelligent terminal of the user.
3. A bright field imaging detection assay for organoid viability assay according to claim 2, further comprising:
when the vigor analysis result of the organoid is verified manually and a verification result is obtained, the short links of the vector diagram are simultaneously directed to the verification result and the vector diagram.
4. A bright field imaging detection analysis method for organoid viability analysis according to any of claims 1 to 3, wherein the training organoid viability analysis model is a deep convolutional neural network.
5. A bright field imaging detection analysis method for use in an organoid viability assay according to any of claims 1 to 3, wherein deriving a training set for training an organoid viability assay model from the selected first target bright field image comprises:
screening the selected first target bright field image to remove the first target bright field image with abnormality to obtain a plurality of second target bright field images;
and (3) carrying out artificial type judgment on each second target bright field image, and grading the vitality one by one to form a training set for training the organoid vitality analysis model.
6. The bright field imaging detection analysis system for the organoid vitality analysis is characterized by comprising a first acquisition module, a selection module, a second acquisition module, a training module and an analysis module;
the first acquisition module is used for: acquiring a plurality of bright field images of the organoid;
the selecting module is used for: selecting a plurality of first target bright field images from all the bright field images based on the similarity;
the second acquisition module is used for: obtaining a training set for training an organoid vitality analysis model according to the selected first target bright field image;
the training module is used for: training the organoid vitality analysis model based on a training set to obtain a trained organoid vitality analysis model;
the analysis module is used for: and inputting the to-be-analyzed bright field image of the organoid into the trained organoid vitality analysis model to obtain a vitality analysis result of the organoid.
7. The bright field imaging detection analysis system for organoid viability analysis of claim 6, further comprising an extended fill module, a generation module, and a transmission module;
the expansion filling module is used for: expanding a blank area on a bright field image to be analyzed of the organoid, and filling a vitality analysis result of the organoid in the blank area to obtain a result image;
the generating module is used for: vectorizing the result image to obtain a vector image, and generating a short link pointing to the vector image;
the sending module is used for: and sending the short link to an intelligent terminal of the user.
8. The bright field imaging detection analysis system for use in organoid viability analysis of claim 7, wherein the generation module is further configured to:
when the vigor analysis result of the organoid is verified manually and a verification result is obtained, the short links of the vector diagram are simultaneously directed to the verification result and the vector diagram.
9. A bright field imaging detection analysis system for use in an organoid viability assay according to any of claims 6 to 8, wherein the training organoid viability assay model is a deep convolutional neural network.
10. A bright field imaging detection analysis system for use in an organoid viability analysis according to any of claims 6 to 8, wherein the second acquisition module is specifically configured to:
screening the selected first target bright field image to remove the first target bright field image with abnormality to obtain a plurality of second target bright field images;
and (3) carrying out artificial type judgment on each second target bright field image, and grading the vitality one by one to form a training set for training the organoid vitality analysis model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310598781.8A CN116612471A (en) | 2023-05-22 | 2023-05-22 | Open field imaging detection analysis method and system for organoid vitality analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310598781.8A CN116612471A (en) | 2023-05-22 | 2023-05-22 | Open field imaging detection analysis method and system for organoid vitality analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116612471A true CN116612471A (en) | 2023-08-18 |
Family
ID=87685042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310598781.8A Pending CN116612471A (en) | 2023-05-22 | 2023-05-22 | Open field imaging detection analysis method and system for organoid vitality analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116612471A (en) |
-
2023
- 2023-05-22 CN CN202310598781.8A patent/CN116612471A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7030423B2 (en) | How to manufacture image analysis methods, equipment, programs and deep learning algorithms | |
| EP3848887A1 (en) | Gan network-based vehicle damage image enhancement method and apparatus | |
| CN111178197A (en) | Mass R-CNN and Soft-NMS fusion based group-fed adherent pig example segmentation method | |
| CN109086780B (en) | Method and device for detecting electrode plate burrs | |
| CN107368671A (en) | System and method are supported in benign gastritis pathological diagnosis based on big data deep learning | |
| CN111814741A (en) | Method for detecting embryo-sheltered pronucleus and blastomere based on attention mechanism | |
| JP2019050376A5 (en) | ||
| CN112052836B (en) | Real-time monitoring system and method for open and close states of plant leaf air holes | |
| CN104347071B (en) | Method and system for generating reference answers of spoken language test | |
| CN111161272B (en) | Embryo tissue segmentation method based on generation of confrontation network | |
| CN109815870B (en) | High-throughput functional gene screening method and system for quantitative analysis of cell phenotype image | |
| CN111931751A (en) | Deep learning training method, target object identification method, system and storage medium | |
| CN110738658B (en) | Image quality evaluation method | |
| CN111814832A (en) | Target detection method, device and storage medium | |
| CN113378831A (en) | Mouse embryo organ identification and scoring method and system | |
| CN116612471A (en) | Open field imaging detection analysis method and system for organoid vitality analysis | |
| CN108615235B (en) | Method and device for processing temporal ear image | |
| CN116563205A (en) | Wheat spike counting detection method based on small target detection and improved YOLOv5 | |
| CN113792104B (en) | Medical data error detection method and device based on artificial intelligence and storage medium | |
| CN117115816B (en) | Identification method and system for clue cells in leucorrhea microscopic image | |
| CN112184708B (en) | Sperm survival rate detection method and device | |
| CN117351240B (en) | Positive sample sampling method, system, storage medium and electronic equipment | |
| CN111291657B (en) | Crowd counting model training method based on difficult case mining and application | |
| CN117789078B (en) | Experiment operation evaluation method and system based on AI visual recognition | |
| CN110223307B (en) | Blood cell counting method based on image recognition |
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 |