CN108288506A - A kind of cancer pathology aided diagnosis method based on artificial intelligence technology - Google Patents
A kind of cancer pathology aided diagnosis method based on artificial intelligence technology Download PDFInfo
- Publication number
- CN108288506A CN108288506A CN201810066011.8A CN201810066011A CN108288506A CN 108288506 A CN108288506 A CN 108288506A CN 201810066011 A CN201810066011 A CN 201810066011A CN 108288506 A CN108288506 A CN 108288506A
- Authority
- CN
- China
- Prior art keywords
- artificial intelligence
- pathology
- training
- digital pathological
- 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
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The present invention discloses a kind of cancer pathology aided diagnosis method based on artificial intelligence technology, includes the following steps：In several digital pathological images to computer of scanning system, and lesion region is labeled by pathology expert, forms digital pathological image database；Digital pathological image formation algorithm training data set after pretreatment, then sample collection is carried out, form training data subset；Full convolutional network is iterated trained adjusting parameter using training with data subset, builds artificial intelligence analysis's module；Diagnosis of scans pathological image, Diagnosis pathology image enter artificial intelligence analysis's module by decoding；Artificial intelligence analysis's module is diagnosed and is marked to Diagnosis pathology image, and the pathological information after label is fed back to doctor.The diagnosis accuracy of a kind of cancer pathology aided diagnosis method based on artificial intelligence technology disclosed by the invention, this kind of cancer pathology aided diagnosis method is high, effectively doctor is assisted to differentiate cancer pathological information.
Description
Technical field
The invention belongs to field of artificial intelligence, and in particular to a kind of cancer pathology auxiliary based on artificial intelligence technology
Diagnostic method.
Background technology
Conventional cancer diagnosis is the cell and tissue specimen in tumour or suspected tumor tissue based on analysis.Pass through
Tissue staining, individual cells or cell mass, which can distinguish, to be come.Routine diagnosis, which relies on, analyzes morphological feature, such as cell shape,
The change of size and dyeing character and the scrambling of institutional framework.So cancer diagnosis is to different from related normal tissue
Morphological variation a kind of subjective judgement.Correct and reliable diagnostic skill needs abundant experience.Between cancer and precancerous lesion
And the case of precancerous lesion and non-cancer lesion, even being also that one kind is chosen for most experienced virologist and cytologist
War.Due to developing complete diagnosing tumor morphologic criteria not yet, this kind of problem is also more and more.It is remotely examined according to current
Disconnected platform statistics display, the diagnostic comments of doctor and the consistent ratio of the diagnostic comments of pathology department expert are less than 60%.In order to carry
The cancer diagnosis quality for rising hospital, there is an urgent need to the computer aided diagnosing methods of more system, are diagnosed in auxiliary doctor
While, step up the diagnosis capability of doctor.
With popularizing for the cancer remote diagnosis based on digital pathological section, the quantity of digital pathological section constantly increases,
The various cases of cancer with expert diagnosis result are collected, and form ever-increasing digital pathological image database.
Computer aided diagnosing method currently popular is mostly based on conventional machines learning method, and such method is to a large amount of known diseases
After the digital pathological image of change type is learnt, has the ability diagnosed to unknown digital pathological image.But due to
Algorithm model is different, differs by the degree for learning and training, and the ability level diagnosed to unknown digital pathological image is not
One.Currently, existing algorithm model is not high to the accuracy rate of cancer number pathological diagnosis, therefore, it is necessary to develop a kind of accuracy compared with
High algorithm model is the target that those skilled in the art urgently seek.
Invention content
The cancer pathology auxiliary diagnosis based on artificial intelligence technology that the technical problem to be solved by the invention is to provide a kind of
Method can solve the technical problem not high to the accuracy rate of cancer number pathological diagnosis of machine learning in the prior art.
In order to solve the above technical problems, the technical solution adopted by the present invention：A kind of cancer based on artificial intelligence technology
Manage aided diagnosis method, which is characterized in that include the following steps：
Step 1：A number of digital pathological image is scanned into computer by scanning system, and special by pathology
Family is labeled for the lesion region in digital pathological image, forms digital pathological image database；
Step 2：Digital pathological image in digital pathological image database is located in advance through image input and preprocessing module
After reason, formation algorithm training data set, then sample collection is carried out with data set to algorithm training, form several training data
Subset；
Step 3：It is iterated trained adjusting parameter with data subset using training by full convolutional network, builds artificial intelligence
It can analysis module；
Step 4：By scanning system by Diagnosis pathology image scanning to computer, Diagnosis pathology image passes through solution
Code enters artificial intelligence analysis's module；
Step 5：Artificial intelligence analysis's module is diagnosed and is marked to Diagnosis pathology image, and by the disease after label
Reason information feeds back to doctor, and auxiliary doctor diagnoses.
Preferably, in step 2, the pretreatment includes the following steps：
Step 21：It identifies the digital pathological image in digital pathological image database, rejects the number that can not be distinguished
Pathological image, and pretreatment is normalized to the digital pathological image after deletion；
Step 22：Pretreated digital pathological image will be normalized to handle by data enhancing algorithm, calculated
Method training data set；
Step 23：By in algorithm training data set digital pathological image and mark corresponding with the digital pathological image
It notes information and carries out sample collection, the sample of acquisition is divided into training set in proportion, three training of verification collection and test set are used
Data subset, to training artificial intelligence analysis's module.
Preferably, in step 21, normalization pretreatment include successively scaling step, sample-by-sample subtract mean value step,
Characteristic normalization step.
Preferably, in step 22, data enhancing algorithm include digital pathological image is rotated, level is turned over
Turn, flip vertical, noise, blurring, the combination of one or more of distortion or displacement step.
Preferably, in step 23, the sample collection includes that positive sample acquisition, negative sample acquisition or edge samples are adopted
Collection.
Preferably, training adjustment relevant parameter is iterated with data subset using training by full convolutional network and builds people
The step of work intelligent analysis module includes：Parameter initialization is carried out to the model, while by the image in training data subset
Data and cancerous region segmentation mask input in the model of the initialization, and are trained to the model and parameter adjustment.
Preferably, the full convolutional network using empty convolution, transposition convolution, can be in deformation convolution, multiple dimensioned convolution
One or more combination.
Preferably, the full convolutional network carries out data training using coding-decoding structure.
Preferably, the full convolutional network carries out data training using end-to-end framework.
Beneficial effects of the present invention：A kind of cancer pathology auxiliary diagnosis side based on artificial intelligence technology disclosed by the invention
Method, by the pretreatment to digital pathological image to optimize the quality of sample data and increase the diversity of sample data；It creates
Full convolutional network model, training is iterated by pretreated training with data subset to the full convolutional network model of establishment,
Parameter in the full convolutional network model of adjusting and optimizing, and form artificial intelligence analysis's module, artificial intelligence analysis's module are treated point
The digital pathological image of analysis carries out pathological analysis and mark, and the pathological information after label is fed back to doctor, auxiliary doctor into
Row diagnosis.The diagnosis accuracy of this kind of cancer pathology aided diagnosis method is high, effectively doctor is assisted to differentiate cancer pathological information.
Description of the drawings
Fig. 1 is the cancer pathology aided diagnosis method flow diagram based on artificial intelligence technology.
Specific implementation mode
The following is a clear and complete description of the technical scheme in the embodiments of the invention, it is clear that described embodiment
Only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, the common skill in this field
The every other embodiment that art personnel are obtained without making creative work belongs to the model that the present invention protects
It encloses.
As shown in Figure 1, a kind of cancer pathology aided diagnosis method based on artificial intelligence technology, includes the following steps：
Step 1：Using slide scanner or pathological tissue scanning system by a number of digital pathological image scan to
It in computer, and is labeled for the lesion region in digital pathological image by pathology expert, forms digital pathological image
Database；
Step 2：Digital pathological image in digital pathological image database is located in advance through image input and preprocessing module
After reason, formation algorithm training data set, then sample collection is carried out with data set to algorithm training, form several training data
Subset；
Wherein, pretreatment includes the following steps：
Step 21：Identify the digital pathological image data in digital pathological image database, what rejecting can not be distinguished
Digital pathological image data, and pretreatment is normalized to remaining digital pathological image data after deletion；In the present embodiment,
Normalization pretreatment include successively step is zoomed in and out to digital pathological image data, sample-by-sample subtracts mean value step, characteristic
Normalization step；
Step 22：Pretreated digital pathological image data will be normalized to handle by data enhancing algorithm, obtained
To algorithm training data set；In the present embodiment, data enhancing algorithm includes carrying out multi-angle rotary (such as to digital pathological image
45 °, 90 °, 120 °, 180 ° etc.), flip horizontal, flip vertical and to digital pathological image carry out denoising, sharpening, torsion
Bent and displacement operation, and retain the digital case image information of each operation, obtain algorithm training data set.It adopts
The quality to optimize sample data is handled with data enhancing algorithm and increases the diversity of sample data；
Step 23：By in algorithm training data set digital pathological image and mark corresponding with the digital pathological image
It notes information and carries out sample collection, the sample of acquisition is divided into training set in proportion, three training of verification collection and test set are used
Data subset, to training artificial intelligence analysis's module.In the present embodiment, sample collection mode is as follows：6 scalings of design
The scale of scale inputs, and collects the digital pathological image data set that short side is { 480,576,688,864,1200,1400 } scale,
And positive sample 40%, negative sample 30% and edge negative sample 30% are acquired according to markup information, sample data is generated with this,
The sample data is divided into training set, verification collection and three training data subsets of test set according still further to 7: 2: 1 ratio.
Step 3：It is iterated trained adjusting parameter with data subset using training by full convolutional network, builds artificial intelligence
It can analysis module；It is as follows：
Parameter initialization carried out to the full convolutional network model, while by the image data and cancer in training data subset
Become region segmentation mask to input in the model of the initialization, and the model is trained and parameter adjustment.It needs to illustrate
It is that the update of artificial intelligence analysis's module can be carried out using the digital pathological image newly marked by pathology expert, it is specific
The same previous step of method.
Step 4：After full convolutional network parameter regulation, forms artificial intelligence analysis's module and come into operation.By sweeping
System is retouched by Diagnosis pathology image scanning to computer, Diagnosis pathology image enters artificial intelligence analysis's mould by decoding
Block；
Step 5：The algorithm model parameter generated using the training stage, algorithm model can directly handle same type problem
Completely new data, and analysis result is provided automatically, you can to input completely new Cancer pathologies picture, artificial intelligence analysis's module
Diagnosis pathology image is diagnosed and marked, and provides the segmentation result in cancerous issue region, and by the disease after label
Reason information feeds back to doctor, and auxiliary doctor diagnoses.
Specific data analysis step is as follows：
Step 51：Full convolutional network reads the unique network parameter obtained via training step, calculates full convolutional network
Method model is initialized；
Step 52：Full convolutional network read it is decoded after Diagnosis pathology image data, and with unique parameters
Full convolutional network progress feature extraction organizing, being made of different levels, generates the dense feature figure of different scale；
Step 53：Using empty convolution technique, an intensive pixel prediction figure is generated；
Step 54：Intensive pixel prediction figure is up-sampled using transposition convolution technique, and uses full convolutional network
The output of different levels carries out intensive pixel prediction figure successively secondary details reparation；
Step 55：By transposition convolution successively, dense feature figure is restored to the Diagnosis pathology image phase with input
Same size to produce a prediction to each pixel in dense feature figure, while remaining the diagnosis being originally inputted
Spatial information in pathological image is finally carried out pixel-by-pixel on the dense feature figure of up-sampling using softmax graders
Classification, obtains classification results；
Step 56：The lesion region on Diagnosis pathology image is determined according to classification results pixel-by-pixel, later different face
Lesion region is inferred that data matrix utilizes the channels Alpha by color, and translucent cover type is generated on Diagnosis pathology image and is covered
Code is conducive to observation of the researcher to lesion region, and doctor and researcher is assisted to do final diagnosis.
In the present embodiment, full convolutional network models coupling cavity convolution technique successively encodes-decodes structure, end-to-end frame
Frame and non-L2 regularizations weight decay technique, by the semantic information of the structure extraction digital pathological image of picture pixels point,
These semantic informations include position, shape, color, size.In the output layer of full convolutional network, full convolutional network handles these languages
Adopted information adjusts the parameter of model using stochastic gradient descent method, and the input data of model and output data is allowed to scheme with training
As data set matches as possible, in learning data set mapping principle and be translated into recognizable result.It is rolled up using cavity
Product technology improves the resolution ratio of segmentation result output figure while maintaining network node receptive field；With successively coding-decoding knot
Structure optimizes network model, is gone gradually to repair coding information with the output of coding module different levels, and in decoder module be integrated into
Both had segmentation result of the details but also with accuracy rate；Using the study and training of end-to-end framework, used residual blocks,
Assist cost function, scale pyramid to enhance the module of full convolutional network function, to generate with high-accuracy, preferably diagnosis
The algorithm model of speed；The calculating of cost function is carried out using non-L2 regularizations weight decay technique, and one, second moment is used in combination
The Adam optimization methods for estimating improving performance, are iterated the parameter in network model the update of formula.For pathology picture
Semantic segmentation task for, model generates intensive segmentation result by the full convolutional coding structure of design.Due to full convolution net
The shared characteristic that plural output node can be existed simultaneously with single propagated forward of the weights of network, it can be used to directly generate
Segmentation result figure, and there is no the requirement of size to input picture, and the network structure containing full articulamentum can only handle fixation
The input of size.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (9)
1. a kind of cancer pathology aided diagnosis method based on artificial intelligence technology, which is characterized in that include the following steps：
Step 1：A number of digital pathological image is scanned into computer by scanning system, and by pathology expert's needle
Lesion region in digital pathological image is labeled, digital pathological image database is formed；
Step 2：By the digital pathological image in digital pathological image database after image input and preprocessing module pretreatment,
Formation algorithm training data set, then sample collection is carried out with data set to algorithm training, form several training data subsets；
Step 3：By full convolutional network trained adjusting parameter, structure artificial intelligence point are iterated with data subset using training
Analyse module；
Step 4：By scanning system by Diagnosis pathology image scanning to computer, Diagnosis pathology image by decode into
Enter artificial intelligence analysis's module；
Step 5：Artificial intelligence analysis's module is diagnosed and is marked to Diagnosis pathology image, and the pathology after label is believed
Breath feeds back to doctor, and auxiliary doctor diagnoses.
2. the cancer pathology aided diagnosis method based on artificial intelligence technology according to claim 1, which is characterized in that in step
In rapid 2, the pretreatment includes the following steps：
Step 21：It identifies the digital pathological image in digital pathological image database, rejects the digital pathology that can not be distinguished
Image, and pretreatment is normalized to the digital pathological image after deletion；
Step 22：Pretreated digital pathological image will be normalized to handle by data enhancing algorithm, obtain algorithm instruction
White silk data set；
Step 23：By the digital pathological image and mark corresponding with digital pathological image letter in algorithm training data set
Breath carries out sample collection, and the sample of acquisition is divided into training set, verification collection and three training data of test set in proportion
Subset, to training artificial intelligence analysis's module.
3. the cancer pathology aided diagnosis method based on artificial intelligence technology according to claim 2, which is characterized in that in step
In rapid 21, the normalization pretreatment subtracts mean value step, characteristic normalization step including scaling step, sample-by-sample successively.
4. the cancer pathology aided diagnosis method based on artificial intelligence technology according to claim 2, which is characterized in that in step
In rapid 22, the data enhancing algorithm includes being rotated, flip horizontal, flip vertical, noise, being obscured to digital pathological image
The combination of one or more of change, distortion or displacement step.
5. the cancer pathology aided diagnosis method based on artificial intelligence technology according to claim 2, which is characterized in that in step
In rapid 23, the sample collection includes positive sample acquisition, negative sample acquisition or edge samples acquisition.
6. the cancer pathology aided diagnosis method based on artificial intelligence technology according to claim 1, which is characterized in that pass through
Full convolutional network is iterated the step that training adjustment relevant parameter builds artificial intelligence analysis's module using training with data subset
Suddenly include：To the model carry out parameter initialization, while by training data subset image data and cancerous region segmentation
Mask inputs in the model of the initialization, and is trained to the model and parameter adjustment.
7. the cancer pathology aided diagnosis method based on artificial intelligence technology according to claim 1, which is characterized in that described
Full convolutional network using empty convolution, transposition convolution, can the combination of one or more of deformation convolution, multiple dimensioned convolution.
8. the cancer pathology aided diagnosis method based on artificial intelligence technology according to claim 1, which is characterized in that described
Full convolutional network carries out data training using coding-decoding structure.
9. the cancer pathology aided diagnosis method based on artificial intelligence technology according to claim 1, which is characterized in that described
Full convolutional network carries out data training using end-to-end framework.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810066011.8A CN108288506A (en) | 2018-01-23 | 2018-01-23 | A kind of cancer pathology aided diagnosis method based on artificial intelligence technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810066011.8A CN108288506A (en) | 2018-01-23 | 2018-01-23 | A kind of cancer pathology aided diagnosis method based on artificial intelligence technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108288506A true CN108288506A (en) | 2018-07-17 |
Family
ID=62835545
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810066011.8A Pending CN108288506A (en) | 2018-01-23 | 2018-01-23 | A kind of cancer pathology aided diagnosis method based on artificial intelligence technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108288506A (en) |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034140A (en) * | 2018-09-13 | 2018-12-18 | 哈尔滨工业大学 | Industrial control network abnormal signal detection method based on deep learning structure |
| CN109117846A (en) * | 2018-08-22 | 2019-01-01 | 北京旷视科技有限公司 | A kind of image processing method, device, electronic equipment and computer-readable medium |
| CN109147938A (en) * | 2018-08-02 | 2019-01-04 | 广东工业大学 | A kind of disease intelligent diagnostics device and equipment |
| CN109147883A (en) * | 2018-07-24 | 2019-01-04 | 北京遥领医疗科技有限公司 | Original document mapping, management method and its system applied to clinical testing data |
| CN109300530A (en) * | 2018-08-08 | 2019-02-01 | 北京肿瘤医院 | The recognition methods of pathological picture and device |
| CN109346159A (en) * | 2018-11-13 | 2019-02-15 | 平安科技（深圳）有限公司 | Case image classification method, device, computer equipment and storage medium |
| CN109344883A (en) * | 2018-09-13 | 2019-02-15 | 西京学院 | Fruit tree diseases and pests recognition methods under a kind of complex background based on empty convolution |
| CN109378052A (en) * | 2018-08-31 | 2019-02-22 | 透彻影像(北京)科技有限公司 | The preprocess method and system of image labeling |
| CN109637631A (en) * | 2018-12-24 | 2019-04-16 | 杭州迪英加科技有限公司 | Sliced sheet processing method, system and slice scanning means, slice analysis device |
| CN109712705A (en) * | 2018-12-19 | 2019-05-03 | 中国石油大学(华东) | A kind of cholelithiasis intelligent diagnostics APP based on deep learning |
| CN109754879A (en) * | 2019-01-04 | 2019-05-14 | 湖南兰茜生物科技有限公司 | A kind of lung cancer computer aided detection method and system based on deep learning |
| CN109785311A (en) * | 2019-01-14 | 2019-05-21 | 深圳和而泰数据资源与云技术有限公司 | A kind of methods for the diagnosis of diseases and relevant device |
| CN109910891A (en) * | 2019-03-20 | 2019-06-21 | 奇瑞汽车股份有限公司 | Control method for vehicle and device |
| CN109961847A (en) * | 2019-03-20 | 2019-07-02 | 武汉千屏影像技术有限责任公司 | The pathology intelligent diagnosis system that a kind of picture, text and voice combine |
| CN109979546A (en) * | 2019-04-04 | 2019-07-05 | 成都大学 | Network model analysis platform and construction method based on artificial intelligence number pathology |
| CN110008992A (en) * | 2019-02-28 | 2019-07-12 | 合肥工业大学 | A kind of deep learning method for prostate cancer auxiliary diagnosis |
| CN110085315A (en) * | 2019-04-15 | 2019-08-02 | 中国人民解放军第八一医院 | Cytomorphology artificial intelligence diagnoses new method automatically |
| CN110265142A (en) * | 2019-06-11 | 2019-09-20 | 透彻影像(北京)科技有限公司 | A kind of assistant diagnosis system and method for lesion region restored map |
| CN110403572A (en) * | 2019-07-01 | 2019-11-05 | 清华大学 | The unmarked pathology imaging diagnosis method of Alzheimer's disease and device |
| CN110517256A (en) * | 2019-08-30 | 2019-11-29 | 重庆大学附属肿瘤医院 | A kind of early carcinoma assistant diagnosis system based on artificial intelligence |
| CN110729033A (en) * | 2019-09-20 | 2020-01-24 | 杭州憶盛医疗科技有限公司 | Comprehensive multifunctional pathological diagnosis system |
| CN110728666A (en) * | 2019-10-08 | 2020-01-24 | 中山大学附属第三医院 | Typing method and system for chronic nasosinusitis based on digital pathological slide |
| CN110763678A (en) * | 2019-09-12 | 2020-02-07 | 杭州迪英加科技有限公司 | Pathological section interpretation method and system |
| CN110826560A (en) * | 2019-11-06 | 2020-02-21 | 山东省计算中心（国家超级计算济南中心） | Esophageal cancer pathological image labeling method |
| CN111009308A (en) * | 2019-12-06 | 2020-04-14 | 上海国汇已丰生物科技有限公司 | Picture cutting method for remote pathological diagnosis |
| CN111834004A (en) * | 2020-05-25 | 2020-10-27 | 杭州深睿博联科技有限公司 | Unknown disease category identification method and device based on centralized space learning |
| CN111863202A (en) * | 2020-07-16 | 2020-10-30 | 梅傲科技(广州)有限公司 | Digital pathological image scanning analysis system |
| CN111863234A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning |
| CN112071422A (en) * | 2020-09-04 | 2020-12-11 | 平安科技（深圳）有限公司 | Lumbar vertebra lesion diagnosis system based on neural network |
| CN112132166A (en) * | 2019-06-24 | 2020-12-25 | 杭州迪英加科技有限公司 | Intelligent analysis method, system and device for digital cytopathology image |
| CN112200773A (en) * | 2020-09-17 | 2021-01-08 | 苏州慧维智能医疗科技有限公司 | Large intestine polyp detection method based on encoder and decoder of cavity convolution |
| CN112259223A (en) * | 2020-10-22 | 2021-01-22 | 河北工业大学 | Patient-level tumor intelligent diagnosis method based on full-field digital section |
| CN112270993A (en) * | 2020-09-22 | 2021-01-26 | 深圳市人工智能与机器人研究院 | Ultrasonic robot online decision-making method and system with diagnosis result as feedback |
| CN112334990A (en) * | 2019-06-04 | 2021-02-05 | 艾多特公司 | Automatic cervical cancer diagnosis system |
| CN112802599A (en) * | 2021-02-04 | 2021-05-14 | 湖南大学 | Artificial intelligence-based caries diagnosis system |
| CN112992336A (en) * | 2021-02-05 | 2021-06-18 | 山西医科大学 | Intelligent pathological diagnosis system |
| CN113053512A (en) * | 2019-12-27 | 2021-06-29 | 无锡祥生医疗科技股份有限公司 | Evolution learning method, system and storage medium suitable for ultrasonic diagnosis |
| CN113539476A (en) * | 2021-06-02 | 2021-10-22 | 复旦大学 | Stomach endoscopic biopsy Raman image auxiliary diagnosis method and system based on artificial intelligence |
| CN113887377A (en) * | 2021-09-18 | 2022-01-04 | 上海申挚医疗科技有限公司 | Histopathological image analysis method and system |
| WO2022028312A1 (en) * | 2020-08-05 | 2022-02-10 | Ping An Technology (Shenzhen) Co., Ltd. | User-guided domain adaptation for rapid annotation from user interactions for pathological organ segmentation |
| CN114999638A (en) * | 2022-07-19 | 2022-09-02 | 武汉蓝嵊科技有限公司 | Big data visualization processing method and system for medical diagnosis based on artificial intelligence |
| CN116705289A (en) * | 2023-05-23 | 2023-09-05 | 北京透彻未来科技有限公司 | Cervical pathology diagnosis device based on semantic segmentation network |
| CN117373695A (en) * | 2023-10-12 | 2024-01-09 | 北京透彻未来科技有限公司 | Extreme deep convolutional neural network-based diagnosis system for diagnosis of cancer disease |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105975793A (en) * | 2016-05-23 | 2016-09-28 | 麦克奥迪（厦门）医疗诊断***有限公司 | Auxiliary cancer diagnosis method based on digital pathological images |
| CN106096654A (en) * | 2016-06-13 | 2016-11-09 | 南京信息工程大学 | A kind of cell atypia automatic grading method tactful based on degree of depth study and combination |
| CN107564580A (en) * | 2017-09-11 | 2018-01-09 | 合肥工业大学 | Gastroscope visual aids processing system and method based on integrated study |
-
2018
- 2018-01-23 CN CN201810066011.8A patent/CN108288506A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105975793A (en) * | 2016-05-23 | 2016-09-28 | 麦克奥迪（厦门）医疗诊断***有限公司 | Auxiliary cancer diagnosis method based on digital pathological images |
| CN106096654A (en) * | 2016-06-13 | 2016-11-09 | 南京信息工程大学 | A kind of cell atypia automatic grading method tactful based on degree of depth study and combination |
| CN107564580A (en) * | 2017-09-11 | 2018-01-09 | 合肥工业大学 | Gastroscope visual aids processing system and method based on integrated study |
Cited By (59)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109147883A (en) * | 2018-07-24 | 2019-01-04 | 北京遥领医疗科技有限公司 | Original document mapping, management method and its system applied to clinical testing data |
| CN109147883B (en) * | 2018-07-24 | 2022-10-21 | 北京遥领医疗科技有限公司 | Original file mapping and managing method and system applied to clinical test data |
| CN109147938A (en) * | 2018-08-02 | 2019-01-04 | 广东工业大学 | A kind of disease intelligent diagnostics device and equipment |
| CN109300530A (en) * | 2018-08-08 | 2019-02-01 | 北京肿瘤医院 | The recognition methods of pathological picture and device |
| CN109117846A (en) * | 2018-08-22 | 2019-01-01 | 北京旷视科技有限公司 | A kind of image processing method, device, electronic equipment and computer-readable medium |
| CN109378052A (en) * | 2018-08-31 | 2019-02-22 | 透彻影像(北京)科技有限公司 | The preprocess method and system of image labeling |
| CN109344883A (en) * | 2018-09-13 | 2019-02-15 | 西京学院 | Fruit tree diseases and pests recognition methods under a kind of complex background based on empty convolution |
| CN109034140B (en) * | 2018-09-13 | 2021-05-04 | 哈尔滨工业大学 | Industrial control network signal abnormity detection method based on deep learning structure |
| CN109034140A (en) * | 2018-09-13 | 2018-12-18 | 哈尔滨工业大学 | Industrial control network abnormal signal detection method based on deep learning structure |
| CN109346159A (en) * | 2018-11-13 | 2019-02-15 | 平安科技（深圳）有限公司 | Case image classification method, device, computer equipment and storage medium |
| CN109346159B (en) * | 2018-11-13 | 2024-02-13 | 平安科技（深圳）有限公司 | Case image classification method, device, computer equipment and storage medium |
| CN109712705A (en) * | 2018-12-19 | 2019-05-03 | 中国石油大学(华东) | A kind of cholelithiasis intelligent diagnostics APP based on deep learning |
| CN109637631A (en) * | 2018-12-24 | 2019-04-16 | 杭州迪英加科技有限公司 | Sliced sheet processing method, system and slice scanning means, slice analysis device |
| CN109754879A (en) * | 2019-01-04 | 2019-05-14 | 湖南兰茜生物科技有限公司 | A kind of lung cancer computer aided detection method and system based on deep learning |
| CN109785311B (en) * | 2019-01-14 | 2021-06-04 | 深圳和而泰数据资源与云技术有限公司 | Disease diagnosis device, electronic equipment and storage medium |
| CN109785311A (en) * | 2019-01-14 | 2019-05-21 | 深圳和而泰数据资源与云技术有限公司 | A kind of methods for the diagnosis of diseases and relevant device |
| CN110008992A (en) * | 2019-02-28 | 2019-07-12 | 合肥工业大学 | A kind of deep learning method for prostate cancer auxiliary diagnosis |
| CN110008992B (en) * | 2019-02-28 | 2023-04-11 | 合肥工业大学 | Deep learning method for prostate cancer auxiliary diagnosis |
| CN109961847A (en) * | 2019-03-20 | 2019-07-02 | 武汉千屏影像技术有限责任公司 | The pathology intelligent diagnosis system that a kind of picture, text and voice combine |
| CN109910891A (en) * | 2019-03-20 | 2019-06-21 | 奇瑞汽车股份有限公司 | Control method for vehicle and device |
| CN109979546A (en) * | 2019-04-04 | 2019-07-05 | 成都大学 | Network model analysis platform and construction method based on artificial intelligence number pathology |
| CN110085315A (en) * | 2019-04-15 | 2019-08-02 | 中国人民解放军第八一医院 | Cytomorphology artificial intelligence diagnoses new method automatically |
| CN111863234A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning |
| CN112334990A (en) * | 2019-06-04 | 2021-02-05 | 艾多特公司 | Automatic cervical cancer diagnosis system |
| CN110265142A (en) * | 2019-06-11 | 2019-09-20 | 透彻影像(北京)科技有限公司 | A kind of assistant diagnosis system and method for lesion region restored map |
| CN110265142B (en) * | 2019-06-11 | 2020-06-09 | 透彻影像(北京)科技有限公司 | Auxiliary diagnosis system for restoration image of lesion area |
| CN112132166A (en) * | 2019-06-24 | 2020-12-25 | 杭州迪英加科技有限公司 | Intelligent analysis method, system and device for digital cytopathology image |
| CN112132166B (en) * | 2019-06-24 | 2024-04-19 | 杭州迪英加科技有限公司 | Intelligent analysis method, system and device for digital cell pathology image |
| CN110403572A (en) * | 2019-07-01 | 2019-11-05 | 清华大学 | The unmarked pathology imaging diagnosis method of Alzheimer's disease and device |
| CN110517256B (en) * | 2019-08-30 | 2022-02-15 | 重庆大学附属肿瘤医院 | Early cancer auxiliary diagnosis system based on artificial intelligence |
| CN110517256A (en) * | 2019-08-30 | 2019-11-29 | 重庆大学附属肿瘤医院 | A kind of early carcinoma assistant diagnosis system based on artificial intelligence |
| CN110763678A (en) * | 2019-09-12 | 2020-02-07 | 杭州迪英加科技有限公司 | Pathological section interpretation method and system |
| CN110729033A (en) * | 2019-09-20 | 2020-01-24 | 杭州憶盛医疗科技有限公司 | Comprehensive multifunctional pathological diagnosis system |
| CN110728666A (en) * | 2019-10-08 | 2020-01-24 | 中山大学附属第三医院 | Typing method and system for chronic nasosinusitis based on digital pathological slide |
| CN110826560B (en) * | 2019-11-06 | 2023-10-27 | 山东省计算中心（国家超级计算济南中心） | Esophageal cancer pathological image labeling method |
| CN110826560A (en) * | 2019-11-06 | 2020-02-21 | 山东省计算中心（国家超级计算济南中心） | Esophageal cancer pathological image labeling method |
| CN111009308A (en) * | 2019-12-06 | 2020-04-14 | 上海国汇已丰生物科技有限公司 | Picture cutting method for remote pathological diagnosis |
| CN113053512B (en) * | 2019-12-27 | 2024-04-09 | 无锡祥生医疗科技股份有限公司 | Evolutionary learning method, system and storage medium suitable for ultrasonic diagnosis |
| CN113053512A (en) * | 2019-12-27 | 2021-06-29 | 无锡祥生医疗科技股份有限公司 | Evolution learning method, system and storage medium suitable for ultrasonic diagnosis |
| CN111834004A (en) * | 2020-05-25 | 2020-10-27 | 杭州深睿博联科技有限公司 | Unknown disease category identification method and device based on centralized space learning |
| CN111863202A (en) * | 2020-07-16 | 2020-10-30 | 梅傲科技(广州)有限公司 | Digital pathological image scanning analysis system |
| CN111863202B (en) * | 2020-07-16 | 2023-12-22 | 梅傲科技(广州)有限公司 | Digital pathological image scanning analysis system |
| WO2022028312A1 (en) * | 2020-08-05 | 2022-02-10 | Ping An Technology (Shenzhen) Co., Ltd. | User-guided domain adaptation for rapid annotation from user interactions for pathological organ segmentation |
| CN112071422B (en) * | 2020-09-04 | 2024-05-03 | 平安科技（深圳）有限公司 | Lumbar vertebra lesion diagnosis system based on neural network |
| CN112071422A (en) * | 2020-09-04 | 2020-12-11 | 平安科技（深圳）有限公司 | Lumbar vertebra lesion diagnosis system based on neural network |
| CN112200773A (en) * | 2020-09-17 | 2021-01-08 | 苏州慧维智能医疗科技有限公司 | Large intestine polyp detection method based on encoder and decoder of cavity convolution |
| CN112270993B (en) * | 2020-09-22 | 2023-12-05 | 深圳市人工智能与机器人研究院 | Ultrasonic robot online decision-making method and system taking diagnosis result as feedback |
| CN112270993A (en) * | 2020-09-22 | 2021-01-26 | 深圳市人工智能与机器人研究院 | Ultrasonic robot online decision-making method and system with diagnosis result as feedback |
| CN112259223B (en) * | 2020-10-22 | 2022-08-30 | 河北工业大学 | Patient-level tumor intelligent diagnosis method based on full-field digital section |
| CN112259223A (en) * | 2020-10-22 | 2021-01-22 | 河北工业大学 | Patient-level tumor intelligent diagnosis method based on full-field digital section |
| CN112802599A (en) * | 2021-02-04 | 2021-05-14 | 湖南大学 | Artificial intelligence-based caries diagnosis system |
| CN112992336A (en) * | 2021-02-05 | 2021-06-18 | 山西医科大学 | Intelligent pathological diagnosis system |
| CN113539476A (en) * | 2021-06-02 | 2021-10-22 | 复旦大学 | Stomach endoscopic biopsy Raman image auxiliary diagnosis method and system based on artificial intelligence |
| CN113887377A (en) * | 2021-09-18 | 2022-01-04 | 上海申挚医疗科技有限公司 | Histopathological image analysis method and system |
| CN114999638A (en) * | 2022-07-19 | 2022-09-02 | 武汉蓝嵊科技有限公司 | Big data visualization processing method and system for medical diagnosis based on artificial intelligence |
| CN116705289B (en) * | 2023-05-23 | 2023-12-19 | 北京透彻未来科技有限公司 | Cervical pathology diagnosis device based on semantic segmentation network |
| CN116705289A (en) * | 2023-05-23 | 2023-09-05 | 北京透彻未来科技有限公司 | Cervical pathology diagnosis device based on semantic segmentation network |
| CN117373695A (en) * | 2023-10-12 | 2024-01-09 | 北京透彻未来科技有限公司 | Extreme deep convolutional neural network-based diagnosis system for diagnosis of cancer disease |
| CN117373695B (en) * | 2023-10-12 | 2024-05-17 | 北京透彻未来科技有限公司 | Extreme deep convolutional neural network-based diagnosis system for diagnosis of cancer disease |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108288506A (en) | A kind of cancer pathology aided diagnosis method based on artificial intelligence technology | |
| US11842556B2 (en) | Image analysis method, apparatus, program, and learned deep learning algorithm | |
| CN111784671B (en) | Pathological image focus region detection method based on multi-scale deep learning | |
| CN103518224B (en) | Method for analysing microbial growth | |
| JP7458519B2 (en) | Image analysis method, image analysis device, program, method for producing trained deep learning algorithm, and trained deep learning algorithm | |
| CN112101451B (en) | Breast cancer tissue pathological type classification method based on generation of antagonism network screening image block | |
| Kromp et al. | Evaluation of deep learning architectures for complex immunofluorescence nuclear image segmentation | |
| CN108257135A (en) | The assistant diagnosis system of medical image features is understood based on deep learning method | |
| CN108305249A (en) | The quick diagnosis and methods of marking of full size pathological section based on deep learning | |
| CN112132166B (en) | Intelligent analysis method, system and device for digital cell pathology image | |
| CN115909006B (en) | Mammary tissue image classification method and system based on convolution transducer | |
| CN110728666B (en) | Typing method and system for chronic nasosinusitis based on digital pathological slide | |
| CN112508953B (en) | Meningioma rapid segmentation qualitative method based on deep neural network | |
| CN110853009A (en) | Retina pathology image analysis system based on machine learning | |
| CN110189293A (en) | Cell image processing method, device, storage medium and computer equipment | |
| CN108305253A (en) | A kind of pathology full slice diagnostic method based on more multiplying power deep learnings | |
| CN113724842B (en) | Cervical tissue pathology auxiliary diagnosis method based on attention mechanism | |
| CN112990214A (en) | Medical image feature recognition prediction model | |
| CN113470041A (en) | Immunohistochemical cell image cell nucleus segmentation and counting method and system | |
| Kromp et al. | Deep Learning architectures for generalized immunofluorescence based nuclear image segmentation | |
| CN115206495A (en) | Renal cancer pathological image analysis method and system based on CoAtNet deep learning and intelligent microscopic device | |
| CN114140437A (en) | Fundus hard exudate segmentation method based on deep learning | |
| CN113643297A (en) | Computer-aided age analysis method based on neural network | |
| CN115880245A (en) | Self-supervision-based breast cancer disease classification method | |
| CN115661029A (en) | Pulmonary nodule detection and identification system based on YOLOv5 |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191212 Address after: 200082, 2nd Floor, 100 Guokang Road, Yangpu District, Shanghai (Centralized Registration Place) Applicant after: Yunkun medical technology (Shanghai) Co., Ltd Address before: 200080 room No. 1388, Hongkou District water circuit, Shanghai, Shanghai Applicant before: Rain sound intelligent technology (Shanghai) Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180717 |
|
| WD01 | Invention patent application deemed withdrawn after publication |