CN116883397A - Automatic lean method and system applied to anatomic pathology - Google Patents
Automatic lean method and system applied to anatomic pathology Download PDFInfo
- Publication number
- CN116883397A CN116883397A CN202311143465.8A CN202311143465A CN116883397A CN 116883397 A CN116883397 A CN 116883397A CN 202311143465 A CN202311143465 A CN 202311143465A CN 116883397 A CN116883397 A CN 116883397A
- Authority
- CN
- China
- Prior art keywords
- pathology
- tissue
- anatomic
- dyed
- dyed tissue
- 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
- 230000007170 pathology Effects 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000004458 analytical method Methods 0.000 claims abstract description 39
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 35
- 238000013334 tissue model Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 30
- 239000013598 vector Substances 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 7
- 238000010827 pathological analysis Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 108010034145 Helminth Proteins Proteins 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 244000000013 helminth Species 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 230000003902 lesion Effects 0.000 claims 1
- 238000000605 extraction Methods 0.000 abstract 1
- 238000000926 separation method Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 230000036285 pathological change Effects 0.000 description 2
- 231100000915 pathological change Toxicity 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an automatic lean method and system applied to anatomic pathology, which belongs to the technical field of anatomic pathology and specifically comprises the following steps: acquiring anatomic image data based on optics and X-rays, and preprocessing the anatomic image after acquisition; identifying a dyed tissue image in the anatomic image based on a convolutional neural network, and acquiring specific anchor point parameters of the dyed tissue image; three-dimensional reconstruction is carried out on single dyed tissue based on multi-eye vision through a plurality of angle dyed tissue images to obtain a single dyed tissue model, separation and extraction are carried out on a dyed tissue structure, and a plurality of independent dyed tissue models are combined to generate a complete dyed tissue model; constructing a pathology analysis model, acquiring internal section images of the dyed tissue at different angles from the dyed tissue model, inputting the internal section images into the pathology analysis model, and outputting a pathology analysis result; the invention improves the accurate identification of the pathology of the dyed tissue.
Description
Technical Field
The invention relates to the technical field of anatomic pathology, in particular to an automatic lean method and system applied to anatomic pathology.
Background
Anatomical pathology is an important branch in the medical field, which is the study of morphological, physiological and pathological features of tissues and organs to understand the occurrence, development and prognosis laws of the disease. In anatomical pathology research, precise analysis and accurate identification of tissue structures is critical. However, the conventional anatomic pathology research method has many problems such as complicated manual operation, low efficiency, high subjectivity and the like. Therefore, it is of great importance to develop an automated anatomic pathology analysis method.
Currently, some existing methods of anatomic pathology analysis rely mainly on manual procedures, such as microscopic observation, tissue slice preparation, and the like. Although these methods can achieve analysis of tissue structures to some extent, there are still problems such as complicated operations, long time consumption, low efficiency, and the like. To overcome these problems, researchers have proposed an anatomic pathology analysis method based on an automated lean method and system.
Disclosure of Invention
The invention aims to provide an automatic lean method and system applied to anatomic pathology, which solve the following technical problems:
the above problems become particularly relevant as the volume of daily processed biological tissue samples increases. In fact, the increase in volume results in a significant inherent increase in errors that various participants may experience. The increase in volume of the tissue sample also produces an increase in the differences in the steps to which the sample is subjected as part of the anatomical pathology diagnostic procedure.
The aim of the invention can be achieved by the following technical scheme:
an automated lean method and system for use in anatomic pathology comprising:
1. an automatic lean method and system for anatomic pathology, comprising:
the image acquisition module is used for acquiring anatomic image data based on optics and X-rays and preprocessing the anatomic image after acquisition;
the tissue identification module is used for identifying dyed tissue images and non-dyed tissue images in the anatomic image based on the convolutional neural network, scanning the dyed tissue images and obtaining specific anchor point parameters of the dyed tissue images;
the three-dimensional reconstruction module is used for three-dimensionally reconstructing a single dyed tissue based on multi-view through a plurality of angle dyed tissue images to obtain a single dyed tissue model, separating and extracting a dyed tissue structure, and combining a plurality of independent dyed tissue models to generate a complete dyed tissue model;
the pathology analysis module is used for constructing a pathology analysis model, acquiring internal section images of the dyed tissue at different angles from the dyed tissue model, inputting the internal section images into the pathology analysis model, and outputting a pathology analysis result;
the preprocessing process of the image acquisition module is as follows:
the method comprises the steps of firstly reducing noise of the anatomic image, dividing the anatomic image after primary noise reduction into a plurality of image blocks, carrying out self-adaptive histogram equalization on each image block, reallocating gray values of pixels, and carrying out secondary noise reduction on the equalized anatomic image;
the specific anchor point parameters comprise color distribution, shape characteristics and texture information of dyed tissues;
the tissue identification module segments the dyed tissue and the non-dyed tissue based on a convolutional neural network, and the calculation of the loss function of the segmentation edge of the convolutional neural network comprises the following steps:
scale loss function:；
distance loss function:；
region loss function:；
artificial loss function:；
thus, the overall loss function of the convolutional neural network:；
where x represents a pixel, ≡ Ω Representing integration in three dimensions, P represents the predicted position of x, c 1 Representing the first true position of x, c 2 Representing the second true position of x, log (η (x)) representing a logarithmic function, Φ representing a gradient function, α, β, λ, μ being preset coefficients,representing the dirichlet function, ">Representing the helminth function.
As a further scheme of the invention: the pathological analysis model is constructed based on a convolutional neural network CNN and a cyclic neural network RNN, the RNN comprises an LSTM layer, the LSTM layer is trained by a time dimension and a feature vector, a plurality of full-connection layers are arranged at the rear end of the RNN, and when each node of the last connection layer is completely and forwards connected to each node of the connection layer, the two connection layers are completely connected.
As a further scheme of the invention: the CNN network comprises a plurality of CNN layers, each CNN layer generates a multidimensional array, the dimension of the internal profile image is reduced once, but a new dimension is generated at the same time, the size of the new dimension is equal to the number of filters applied to the image, the continuous CNN layers reduce the size of the image, the size of the newly generated dimension is increased, tensors in the CNN network are converted into vectors, and the vectors are used as the input of a final full-connection layer.
As a further scheme of the invention: the pathological analysis results comprise pathological change degree of stained tissues and abnormal areas of tissue structures.
As a further scheme of the invention: the pathology analysis module further comprises a pathology database, a large number of pathology images are trained by using a machine learning technology, and a pathology analysis model is continuously optimized.
The invention has the beneficial effects that:
according to the invention, firstly, the anatomic image data is automatically acquired and processed, so that the analysis efficiency and accuracy are greatly improved; secondly, the convolutional neural network is utilized to divide and identify the dyed tissue, so that the accuracy and the reliability of analysis are improved; thirdly, modeling and separating the dyed tissue by a three-dimensional reconstruction technology, and providing more visual and comprehensive information for pathological analysis; finally, a pathology analysis model is continuously optimized by building a pathology database and training a large number of pathology images by using a machine learning technology, so that the accuracy and reliability of analysis results are improved.
Drawings
The invention is further described below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention is an automatic lean method and system for anatomical pathology, comprising:
the image acquisition module is used for acquiring anatomic image data based on optics and X-rays and preprocessing the anatomic image after acquisition;
the tissue identification module is used for identifying dyed tissue images and non-dyed tissue images in the anatomic image based on the convolutional neural network, scanning the dyed tissue images and obtaining specific anchor point parameters of the dyed tissue images;
the three-dimensional reconstruction module is used for three-dimensionally reconstructing a single dyed tissue based on multi-view through a plurality of angle dyed tissue images to obtain a single dyed tissue model, separating and extracting a dyed tissue structure, and combining a plurality of independent dyed tissue models to generate a complete dyed tissue model;
the pathology analysis module is used for constructing a pathology analysis model, obtaining internal section images of the dyed tissue at different angles from the dyed tissue model, inputting the internal section images into the pathology analysis model, and outputting a pathology analysis result.
Currently, some existing methods of anatomic pathology analysis rely mainly on manual procedures, such as microscopic observation, tissue slice preparation, and the like. Although these methods can achieve analysis of tissue structures to some extent, there are still problems such as complicated operations, long time consumption, low efficiency, and the like. To overcome these problems, researchers have proposed an anatomic pathology analysis method based on an automated lean method and system.
According to the invention, firstly, the anatomic image data is automatically acquired and processed, so that the analysis efficiency and accuracy are greatly improved; secondly, the convolutional neural network is utilized to divide and identify the dyed tissue, so that the accuracy and the reliability of analysis are improved; thirdly, modeling and separating the dyed tissue by a three-dimensional reconstruction technology, and providing more visual and comprehensive information for pathological analysis; finally, a pathology analysis model is continuously optimized by building a pathology database and training a large number of pathology images by using a machine learning technology, so that the accuracy and reliability of analysis results are improved.
In a preferred embodiment of the present invention, the preprocessing procedure of the image acquisition module is:
and carrying out primary noise reduction on the anatomic image, dividing the anatomic image after primary noise reduction into a plurality of image blocks, carrying out self-adaptive histogram equalization on each image block, reallocating the gray value of the pixel, and carrying out secondary noise reduction on the equalized anatomic image.
In another preferred embodiment of the present invention, the anchor parameters include color distribution, shape characteristics, and texture information of the stained tissue.
In another preferred embodiment of the present invention, the tissue identification module segments the stained tissue and the non-stained tissue based on a convolutional neural network, and the calculating the loss function of the segmented edge of the convolutional neural network includes:
scale loss function:；
distance loss function:；
region loss function:；
artificial loss function:；
thus, the overall loss function of the convolutional neural network:；
wherein x isRepresenting pixels, +. Ω Representing integration in three dimensions, P represents the predicted position of x, c 1 Representing the first true position of x, c 2 Representing the second true position of x, log (η (x)) representing a logarithmic function, Φ representing a gradient function, α, β, λ, μ being preset coefficients,representing the dirichlet function, ">Representing the helminth function.
In another preferred embodiment of the present invention, the pathology analysis model is constructed based on a convolutional neural network CNN and a cyclic neural network RNN, the RNN network includes an LSTM layer, the LSTM layer is trained by a matrix of two dimensions, namely a time dimension and a feature vector, a plurality of full connection layers are arranged at the back end of the RNN network, and when each node of the previous connection layer is completely connected to each node of the connection layers in the forward direction, the two connection layers are completely connected.
In a preferred case of this embodiment, the CNN network includes several CNN layers, each of which generates a multidimensional array, the dimension of the internal profile image is reduced once, but a new dimension is generated at the same time, the size of the new dimension is equal to the number of filters applied to the image, successive CNN layers reduce the image size and increase the size of the newly generated dimension, the tensor in the CNN network is converted into a vector, and the vector is used as the input of the final full-connection layer.
In another preferred embodiment of the present invention, the pathological analysis result includes a degree of pathological change of stained tissue, an abnormal region of tissue structure.
In another preferred embodiment of the present invention, the pathology analysis module further comprises creating a pathology database, training a plurality of pathology images using machine learning techniques, and continuously optimizing a pathology analysis model.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (5)
1. An automatic lean method and system for anatomic pathology, comprising:
the image acquisition module is used for acquiring anatomic image data based on optics and X-rays and preprocessing the anatomic image after acquisition;
the tissue identification module is used for identifying dyed tissue images and non-dyed tissue images in the anatomic image based on the convolutional neural network, scanning the dyed tissue images and obtaining specific anchor point parameters of the dyed tissue images;
the three-dimensional reconstruction module is used for three-dimensionally reconstructing a single dyed tissue based on multi-view through a plurality of angle dyed tissue images to obtain a single dyed tissue model, separating and extracting a dyed tissue structure, and combining a plurality of independent dyed tissue models to generate a complete dyed tissue model;
the pathology analysis module is used for constructing a pathology analysis model, acquiring internal section images of the dyed tissue at different angles from the dyed tissue model, inputting the internal section images into the pathology analysis model, and outputting a pathology analysis result;
the preprocessing process of the image acquisition module is as follows:
the method comprises the steps of firstly reducing noise of the anatomic image, dividing the anatomic image after primary noise reduction into a plurality of image blocks, carrying out self-adaptive histogram equalization on each image block, reallocating gray values of pixels, and carrying out secondary noise reduction on the equalized anatomic image;
the specific anchor point parameters comprise color distribution, shape characteristics and texture information of dyed tissues;
the tissue identification module segments the dyed tissue and the non-dyed tissue based on a convolutional neural network, and the calculation of the loss function of the segmentation edge of the convolutional neural network comprises the following steps:
scale loss function:；
distance loss function:；
region loss function:；
artificial loss function:；
thus, the overall loss function of the convolutional neural network:；
where x represents a pixel, ≡ Ω Representing integration in three dimensions, P represents the predicted position of x, c 1 Representing the first true position of x, c 2 Representing the second true position of x, log (η (x)) representing a logarithmic function, Φ representing a gradient function, α, β, λ, μ being preset coefficients,representing the dirichlet function, ">Representing the helminth function.
2. The automatic lean method and system for anatomic pathology according to claim 1, wherein the pathology analysis model is constructed based on a convolutional neural network CNN and a cyclic neural network RNN, the RNN network comprises an LSTM layer, the LSTM layer is trained by a matrix of two dimensions, namely a time dimension and a feature vector, a plurality of full connection layers are arranged at the back end of the RNN network, and when each node of the last connection layer is completely connected forward to each node of the connection layers, the two connection layers are completely connected.
3. An automated lean method and system for applying to an anatomic pathology according to claim 2, wherein the CNN network includes a plurality of CNN layers, each CNN layer generating a multi-dimensional array, the dimensions of the internal profile image being reduced once, but simultaneously generating a new dimension of a size equal to the number of filters applied to the image, successive CNN layers reducing the image size and increasing the newly generated size, converting tensors in the CNN network into vectors, the vectors being input to the final fully connected layer.
4. The method and system for automated lean application to anatomic pathology according to claim 1, wherein the pathological analysis results comprise the degree of lesions of stained tissue, abnormal areas of tissue structure.
5. The automated lean method and system for anatomic pathology according to claim 1, wherein the pathology analysis module further comprises creating a pathology database, training a plurality of pathology images using machine learning techniques, and continuously optimizing a pathology analysis model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311143465.8A CN116883397B (en) | 2023-09-06 | 2023-09-06 | Automatic lean method and system applied to anatomic pathology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311143465.8A CN116883397B (en) | 2023-09-06 | 2023-09-06 | Automatic lean method and system applied to anatomic pathology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116883397A true CN116883397A (en) | 2023-10-13 |
| CN116883397B CN116883397B (en) | 2023-12-08 |
Family
ID=88262515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311143465.8A Active CN116883397B (en) | 2023-09-06 | 2023-09-06 | Automatic lean method and system applied to anatomic pathology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116883397B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210150701A1 (en) * | 2017-06-15 | 2021-05-20 | Visiopharm A/S | Method for training a deep learning model to obtain histopathological information from images |
| JPWO2021132633A1 (en) * | 2019-12-26 | 2021-07-01 | ||
| US20220108123A1 (en) * | 2020-10-01 | 2022-04-07 | The Board Of Trustees Of The University Of Illinois | Tissue microenvironment analysis based on tiered classification and clustering analysis of digital pathology images |
| CN114708229A (en) * | 2022-04-01 | 2022-07-05 | 重庆点检生物科技有限公司 | Pathological section digital image full-hierarchy analysis system |
| CN115272196A (en) * | 2022-07-11 | 2022-11-01 | 东北林业大学 | Method for predicting lesion region in tissue pathology image |
| CN115546605A (en) * | 2022-09-16 | 2022-12-30 | 安徽省立医院(中国科学技术大学附属第一医院) | Training method and device based on image labeling and segmentation model |
| CN115578560A (en) * | 2022-10-09 | 2023-01-06 | 杭州智汇明壹医疗科技有限公司 | Cancer region segmentation method of IHC membrane plasma expression pathological image based on deep learning |
| JP7244974B1 (en) * | 2022-09-19 | 2023-03-23 | 之江実験室 | Pathological image feature extractor training method, training device, electronic device, storage medium, and pathological image classification system based on feature separation |
| CN116012353A (en) * | 2023-02-07 | 2023-04-25 | 中国科学院重庆绿色智能技术研究院 | Digital pathological tissue image recognition method based on graph convolution neural network |
| CN116468655A (en) * | 2023-02-14 | 2023-07-21 | 复旦大学 | Brain development atlas and image processing system based on fetal magnetic resonance imaging |
| CN116468690A (en) * | 2023-04-17 | 2023-07-21 | 北京透彻未来科技有限公司 | Subtype analysis system of invasive non-mucous lung adenocarcinoma based on deep learning |
| CN116524315A (en) * | 2022-01-17 | 2023-08-01 | 山东大学 | Mask R-CNN-based lung cancer pathological tissue section identification and segmentation method |
-
2023
- 2023-09-06 CN CN202311143465.8A patent/CN116883397B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210150701A1 (en) * | 2017-06-15 | 2021-05-20 | Visiopharm A/S | Method for training a deep learning model to obtain histopathological information from images |
| JPWO2021132633A1 (en) * | 2019-12-26 | 2021-07-01 | ||
| US20230045882A1 (en) * | 2019-12-26 | 2023-02-16 | Japanese Foundation For Cancer Research | Pathological diagnosis assisting method using ai, and assisting device |
| US20220108123A1 (en) * | 2020-10-01 | 2022-04-07 | The Board Of Trustees Of The University Of Illinois | Tissue microenvironment analysis based on tiered classification and clustering analysis of digital pathology images |
| CN116524315A (en) * | 2022-01-17 | 2023-08-01 | 山东大学 | Mask R-CNN-based lung cancer pathological tissue section identification and segmentation method |
| CN114708229A (en) * | 2022-04-01 | 2022-07-05 | 重庆点检生物科技有限公司 | Pathological section digital image full-hierarchy analysis system |
| CN115272196A (en) * | 2022-07-11 | 2022-11-01 | 东北林业大学 | Method for predicting lesion region in tissue pathology image |
| CN115546605A (en) * | 2022-09-16 | 2022-12-30 | 安徽省立医院(中国科学技术大学附属第一医院) | Training method and device based on image labeling and segmentation model |
| JP7244974B1 (en) * | 2022-09-19 | 2023-03-23 | 之江実験室 | Pathological image feature extractor training method, training device, electronic device, storage medium, and pathological image classification system based on feature separation |
| CN115578560A (en) * | 2022-10-09 | 2023-01-06 | 杭州智汇明壹医疗科技有限公司 | Cancer region segmentation method of IHC membrane plasma expression pathological image based on deep learning |
| CN116012353A (en) * | 2023-02-07 | 2023-04-25 | 中国科学院重庆绿色智能技术研究院 | Digital pathological tissue image recognition method based on graph convolution neural network |
| CN116468655A (en) * | 2023-02-14 | 2023-07-21 | 复旦大学 | Brain development atlas and image processing system based on fetal magnetic resonance imaging |
| CN116468690A (en) * | 2023-04-17 | 2023-07-21 | 北京透彻未来科技有限公司 | Subtype analysis system of invasive non-mucous lung adenocarcinoma based on deep learning |
Non-Patent Citations (4)
| Title |
|---|
| SONGHUI DIAO: "Computer Aided Cancer Regions Detection of Hepatocellular Carcinoma in Whole-slide Pathological Images based on Deep Learning", 2019 INTERNATIONAL CONFERENCE ON MEDICAL IMAGING PHYSICS AND ENGINEERING (ICMIPE) * |
| 孟婷;刘宇航;张凯昱;: "一种基于增强卷积神经网络的病理图像诊断算法", 激光与光电子学进展, no. 08 * |
| 张泽中;高敬阳;赵地;: "MIFNet:基于多尺度输入与特征融合的胃癌病理图像分割方法", 计算机应用, no. 2 * |
| 杜剑: "基于卷积神经网络与显微高光谱的胃癌组织分类方法研究", 光学学报, no. 06 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116883397B (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111476292B (en) | Small sample element learning training method for medical image classification processing artificial intelligence | |
| CN108052977B (en) | Mammary gland molybdenum target image deep learning classification method based on lightweight neural network | |
| CN108898160B (en) | Breast cancer histopathology grading method based on CNN and imaging omics feature fusion | |
| WO2021203795A1 (en) | Pancreas ct automatic segmentation method based on saliency dense connection expansion convolutional network | |
| CN109063710A (en) | Based on the pyramidal 3D CNN nasopharyngeal carcinoma dividing method of Analysis On Multi-scale Features | |
| CN108257135A (en) | The assistant diagnosis system of medical image features is understood based on deep learning method | |
| CN111429474B (en) | Mammary gland DCE-MRI image focus segmentation model establishment and segmentation method based on mixed convolution | |
| CN109584244B (en) | Hippocampus segmentation method based on sequence learning | |
| CN110889852A (en) | Liver segmentation method based on residual error-attention deep neural network | |
| CN112258514B (en) | Segmentation method of pulmonary blood vessels of CT (computed tomography) image | |
| CN111340812A (en) | Interactive liver image segmentation method based on deep neural network | |
| Guo et al. | Adaptive active contour model based automatic tongue image segmentation | |
| CN112348059A (en) | Deep learning-based method and system for classifying multiple dyeing pathological images | |
| CN110942464A (en) | PET image segmentation method fusing 2-dimensional and 3-dimensional models | |
| CN114596317A (en) | CT image whole heart segmentation method based on deep learning | |
| CN112288749A (en) | Skull image segmentation method based on depth iterative fusion depth learning model | |
| CN116883341A (en) | Liver tumor CT image automatic segmentation method based on deep learning | |
| CN114972254A (en) | Cervical cell image segmentation method based on convolutional neural network | |
| CN115471701A (en) | Lung adenocarcinoma histology subtype classification method based on deep learning and transfer learning | |
| CN115527657A (en) | Image and image multi-mode reconstruction, imaging and labeling based on medical digital imaging and communication | |
| CN109919216B (en) | Counterlearning method for computer-aided diagnosis of prostate cancer | |
| CN115100123A (en) | Brain extraction method combining UNet and active contour model | |
| CN114565601A (en) | Improved liver CT image segmentation algorithm based on DeepLabV3+ | |
| CN114445328A (en) | Medical image brain tumor detection method and system based on improved Faster R-CNN | |
| WO2024104035A1 (en) | Long short-term memory self-attention model-based three-dimensional medical image segmentation method and system |
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 |