CN108670285A - A kind of CT pulmonary tuberculosis detection artificial intelligence diagnosis and therapy system - Google Patents
A kind of CT pulmonary tuberculosis detection artificial intelligence diagnosis and therapy system Download PDFInfo
- Publication number
- CN108670285A CN108670285A CN201810569856.9A CN201810569856A CN108670285A CN 108670285 A CN108670285 A CN 108670285A CN 201810569856 A CN201810569856 A CN 201810569856A CN 108670285 A CN108670285 A CN 108670285A
- Authority
- CN
- China
- Prior art keywords
- module
- study
- study module
- artificial intelligence
- convolutional neural
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 26
- 208000008128 pulmonary tuberculosis Diseases 0.000 title claims abstract description 25
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 238000002560 therapeutic procedure Methods 0.000 title claims abstract description 15
- 208000020816 lung neoplasm Diseases 0.000 claims abstract description 35
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 24
- 230000002685 pulmonary effect Effects 0.000 claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 210000004204 blood vessel Anatomy 0.000 claims description 4
- 238000002156 mixing Methods 0.000 claims description 4
- 210000000621 bronchi Anatomy 0.000 claims description 3
- 210000005036 nerve Anatomy 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 abstract description 5
- 238000013461 design Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 abstract description 2
- 230000000505 pernicious effect Effects 0.000 abstract description 2
- 210000004072 lung Anatomy 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 238000012360 testing method Methods 0.000 description 6
- 238000000034 method Methods 0.000 description 4
- 208000015181 infectious disease Diseases 0.000 description 3
- 230000003902 lesion Effects 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 2
- 206010036790 Productive cough Diseases 0.000 description 2
- 229910052791 calcium Inorganic materials 0.000 description 2
- 239000011575 calcium Substances 0.000 description 2
- 230000001684 chronic effect Effects 0.000 description 2
- 239000005337 ground glass Substances 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 208000024794 sputum Diseases 0.000 description 2
- 210000003802 sputum Anatomy 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 201000008827 tuberculosis Diseases 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 208000035473 Communicable disease Diseases 0.000 description 1
- 206010014561 Emphysema Diseases 0.000 description 1
- 230000005526 G1 to G0 transition Effects 0.000 description 1
- 241000521257 Hydrops Species 0.000 description 1
- 206010020751 Hypersensitivity Diseases 0.000 description 1
- ZOKXTWBITQBERF-UHFFFAOYSA-N Molybdenum Chemical compound [Mo] ZOKXTWBITQBERF-UHFFFAOYSA-N 0.000 description 1
- 241000186359 Mycobacterium Species 0.000 description 1
- 241000187479 Mycobacterium tuberculosis Species 0.000 description 1
- 206010030113 Oedema Diseases 0.000 description 1
- 208000002151 Pleural effusion Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 235000002493 Salix babylonica Nutrition 0.000 description 1
- 241000734985 Salix x sepulcralis Species 0.000 description 1
- 206010045104 Tuberculous pleurisy Diseases 0.000 description 1
- 208000036981 active tuberculosis Diseases 0.000 description 1
- 208000026935 allergic disease Diseases 0.000 description 1
- 230000007815 allergy Effects 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002308 calcification Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 210000000038 chest Anatomy 0.000 description 1
- 230000001447 compensatory effect Effects 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 229910052750 molybdenum Inorganic materials 0.000 description 1
- 239000011733 molybdenum Substances 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 201000010098 pleural tuberculosis Diseases 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002062 proliferating effect Effects 0.000 description 1
- 239000003381 stabilizer Substances 0.000 description 1
- 210000001364 upper extremity Anatomy 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/032—Transmission computed tomography [CT]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Radiology & Medical Imaging (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- High Energy & Nuclear Physics (AREA)
- Veterinary Medicine (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Optics & Photonics (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Pulmonology (AREA)
- Theoretical Computer Science (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a kind of CT pulmonary tuberculosis to detect artificial intelligence diagnosis and therapy system, including feature samples library, for neuroid study module, depth convolutional neural networks study module, output module and terminal, the great amount of samples for neuroid study module and the study of depth convolutional neural networks study module is provided in the feature samples library.It is of the invention novel in design, operating aspect, the disconnected system of Lung neoplasm artificial intelligence diagnosis and treatment makes neuroid study module and depth convolutional neural networks study module to markd image carries out deep learning in feature samples library, obtain accurately pulmonary nodule classification policy, and then realize the detection of pulmonary nodule, tubercle size and form and good pernicious judgement, and structured report is provided automatically and is referred to for doctor, thus intelligent diagosis, assisting in diagnosis and treatment function based on Lung neoplasm image are provided for doctor, diagnosis and treatment suggestion is provided for doctor.
Description
Technical field
The present invention relates to field of medical technology more particularly to a kind of CT pulmonary tuberculosis to detect artificial intelligence diagnosis and therapy system.
Background technology
Tuberculosis is the chronic infectious disease caused by mycobacterium tuberculosis, can be invaded and many internal organs, is infected with pulmonary Mycobacterium
It is most commonly seen.Excreter is its important infection sources.It not necessarily falls ill after human infection tulase, when resistance reduction or cell
When the allergy of mediation increases, it is likely to cause clinical onset.Infiltrative pulmonary tuberculosis, x-ray are often that clouding or strip are soaked
Profit shade, edge blurry (exudative) or tubercle, rope strip (proliferative) lesion, large stretch of consolidation or spheroid pathological changes (caseous-
It can be seen that cavity) or calcification, chronic fibro-cavitative pulmonary tuberculosis be also unilateral side mostly on two lung tops, a large amount of fibroplasias, wherein
Cavity is formed, and in broken flocculence, lung tissue is shunk, and is carried on hilus pulumonis, and hilar shadow changes in " weeping willow sample ", and pachynsis pleurae, thorax collapses
Fall into, local compensatory pulmonary emphysema, tuberculous pleurisy (IV type) disease side pleural effusion shoals for rib diaphragm angle in a small amount, moderate with
Upper hydrops is dense shadow, and upper limb is arc-shaped, can be divided into progressive stage, upward swing and stabilizer, progressive stage by dividing by stages：Newly
It was found that active tuberculosis, lesion increases increase in follow-up, cavity or cavity occurs and expands, and Sputum inspection turns the positive, fever
Etc. clinical symptoms aggravate, upward swing：Lesion, which absorbs, in follow-up improves, and cavity reduces or disappears, and sputum bacteria is turned out cloudy, and clinical symptoms change
It is kind, stationary phase.
Through retrieval, Chinese patent discloses a kind of pulmonary tuberculosis intelligent identification Method and system based on DR, (Authorization Notice No.
107729911 A of CN), which discloses a kind of pulmonary tuberculosis intelligent identification Method and system based on DR, by big
It measures the sample manually marked to form deep neural network to train, the depth nerve net is special by autonomous learning pulmonary tuberculosis image
Sign, and pulmonary tuberculosis image feature in DR images is identified with this.Thus the pulmonary tuberculosis intelligent recognition scheme constituted can be realized pair
Pulmonary tuberculosis image feature in DR images carries out automatic identification, it can be achieved that the automatic screening of pulmonary tuberculosis based on DR, effectively reduces
Screening cost.Furthermore this programme recognition efficiency is high, and accuracy of identification is high, the phenomenon for effectively avoiding missing inspection unidentified, effectively solve existing
There is the problems of technology, still, does not use pulmonary parenchyma segmentation, extraction area-of-interest and characteristic parameter extraction step
The CT images of discriminant classification different quality and all kinds of tubercles are carried out to Lung neoplasm, and without using multichannel, isomery Three dimensional convolution
Blending algorithm, difference improve the detection sensitivity and accuracy of different scale, different shape Lung neoplasm.Therefore, art technology
Personnel provide a kind of CT pulmonary tuberculosis detection artificial intelligence diagnosis and therapy system, to solve the problems mentioned in the above background technology.
Invention content
The purpose of the present invention is to provide a kind of CT pulmonary tuberculosis to detect artificial intelligence diagnosis and therapy system, can solve above-mentioned background
The problem of being proposed in technology.
To achieve the goals above, present invention employs following technical solutions：A kind of CT pulmonary tuberculosis detection artificial intelligence is examined
Treatment system, including feature samples library, for neuroid study module, depth convolutional neural networks study module, output module
And terminal, it is provided with for neuroid study module and depth convolutional neural networks in the feature samples library
The great amount of samples of study module study, neuroid study module is by can obtain diagnostic data and raw video after study
The image of module is diagnosed automatically, and diagnostic result is passed to output module, and depth convolutional neural networks study module is logical
It crosses after study and pulmonary parenchyma segmentation, extraction area-of-interest and characteristic parameter is carried out successively to the image of raw video acquisition module
Discriminant classification obtains Lung neoplasm after extraction step, and testing result is passed to output module, and output module passes detection data
Pass terminal.
As a further solution of the present invention：The depth convolutional neural networks study module includes being carried out in advance to CT images
The image pre-processing unit of processing, the two-dimensional convolution neural network unet and prediction Lung neoplasm of prediction Lung neoplasm segmentation image are true
The residual neural network Resnet3D of three dimensional depth of false positive probability.
As further scheme of the invention：The feature samples library includes a large amount of normal person's rabat images and lung
The rabat image of tubercle patient filters out candidate samples from historical sample data first in mark, then to candidate samples into
Row audit.
As further scheme of the invention：The neuroid unit is rolled up using multichannel, isomery three-dimensional
Product blending algorithm.
As further scheme of the invention：Area-of-interest refers to tubercle and knot in the extraction area-of-interest
Save the similar blood vessel of feature and bronchus.
As further scheme of the invention：The input terminal of the output module passes through data line and neuron net respectively
The output end of network study module and depth convolutional neural networks study module is electrically connected, and the output end and meter of output module
The input terminal of calculation machine terminal passes through data line electrical connection.
Compared with prior art, the beneficial effects of the invention are as follows：Novel design of the invention, operating aspect, Lung neoplasm are artificial
The disconnected system of intelligent diagnosis and treatment makes neuroid study module and depth convolutional neural networks study module in feature samples library
Markd image carries out deep learning, obtains accurately pulmonary nodule classification policy, and then realize the detection of pulmonary nodule,
Tubercle size and form and good pernicious judgement, and provide structured report automatically and referred to for doctor, thus provided based on lung for doctor
Intelligent diagosis, the assisting in diagnosis and treatment function of tubercle image, diagnosis and treatment suggestion is provided for doctor, to promote the precision and effect of doctor diagnosed
Rate expands the service ability of doctor, reduces the labor intensity of doctor, has saved Diagnostic Time, increases patient's daily inspection
Number provides the quality time for the timely treatment of patient, reduces patient suffering.
Description of the drawings
Fig. 1 is the structural schematic diagram that a kind of CT pulmonary tuberculosis detects artificial intelligence diagnosis and therapy system.
Fig. 2 is that a kind of structure of CT pulmonary tuberculosis detection artificial intelligence diagnosis and therapy system depth convolutional neural networks study module is shown
It is intended to.
Specific implementation mode
Please refer to Fig.1~2, in the embodiment of the present invention, a kind of CT pulmonary tuberculosis detects artificial intelligence diagnosis and therapy system, including feature
Sample database, for neuroid study module, depth convolutional neural networks study module, output module and terminal, institute
State be provided in feature samples library for neuroid study module and depth convolutional neural networks study module study
Great amount of samples, feature samples library includes a large amount of normal person's rabat images and the rabat image of Lung neoplasm patient, in mark
Candidate samples are filtered out from historical sample data first, then candidate samples are audited, image has included (endoscope shadow
Picture, CT, eye-ground photography, pathology, molybdenum target, MRI), the comprehensive of feature samples library data is improved, neuroid is increased
Module and the study depth of depth convolutional neural networks study module are practised, has ensured the accuracy of inspection result.
Neuroid study module is by can carry out the image of diagnostic data and raw video acquisition module after study
Automatic diagnosis, and diagnostic result is passed into output module, neuroid unit is using multichannel, isomery Three dimensional convolution
Blending algorithm improves the detection sensitivity and accuracy to different scale, different shape Lung neoplasm, is passing through a large amount of image
And diagnostic data constantly carries out deep learning training to neuroid, the ability for promoting it to grasp " diagnosis ", it is final complete
Automatically institute's nodosity in identification CT images, discrimination is up to 98%, and calculates the medical features of tubercle, assists a physician and writes
Diagnosis report simultaneously assists carrying out last diagnostic, reduces the labor intensity of doctor, has saved Diagnostic Time, increases patient's daily test
Number is looked into, the quality time is provided for the timely treatment of patient, reduces patient suffering.
Depth convolutional neural networks study module by carrying out lung successively after study to the image of raw video acquisition module
Discriminant classification obtains Lung neoplasm after essence segmentation, extraction area-of-interest and characteristic parameter extraction step, and by testing result
Output module is passed to, area-of-interest in area-of-interest is extracted and refers to tubercle blood vessel similar with tubercle feature and branch gas
Pipe, depth convolutional neural networks study module include carrying out pretreated image pre-processing unit to CT images, predict Lung neoplasm
Divide the two-dimensional convolution neural network unet of image and predicts the residual neural network of three dimensional depth of the true and false positive probability of Lung neoplasm
Resnet3D, first image pre-processing unit pre-process CT images, keep whole CT image pixels interval unified, image pair
It is more unified than degree, it then trains two-dimensional convolution neural network unet prediction Lung neoplasms to divide image, is pushed away based on Lung neoplasm segmentation image
Candidate nodule is recommended, the true and false positive probability of the residual neural network Resnet3D predictions Lung neoplasm of three dimensional depth is finally trained, screens out vacation
The positive combines, and to improve the detection of the small state of an illness of Lung neoplasm, which is fully combined AL in medical knowledge, is adapted to not homogeneity
The CT images of amount and all kinds of tubercles, such as：Lung wall be convenient for tubercle, base of lung portion sharp corner tubercle, ground glass tubercle, edge lesser tubercle,
The Lung neoplasm of different volumes, the strange Lung neoplasm of shape, close to vertical diaphragm calcium scoring, the tubercle image of poor image quality is conventional
Lung neoplasm etc., detection accuracy may be up to 98% or so, can be as the capable auxiliary tool of image department doctor.
Detection data is passed to terminal by output module, and the input terminal of output module passes through data line and god respectively
It is electrically connected through the output end of metanetwork study module and depth convolutional neural networks study module, and the output of output module
The input terminal of end and terminal is by data line electrical connection, the self energy section directly watched from terminal convenient for doctor
The testing result of skill.
The operation principle of the present invention；Neuroid study module and depth convolutional neural networks study module are to feature
Markd image carries out deep learning in sample database, obtains accurately pulmonary nodule classification policy, then carry out to CT images
Automatic detection realizes manual intelligent, and neuroid unit first is calculated using multichannel, the fusion of isomery Three dimensional convolution
Method improves the detection sensitivity and accuracy to different scale, different shape Lung neoplasm, by a large amount of image and is examining
Disconnected data constantly carry out deep learning training to neuroid, the ability for promoting it to grasp " diagnosis ", final full automatic
Identify institute's nodosity in CT images, discrimination is up to 98%, and calculates the medical features of tubercle, assists a physician and writes diagnosis report
It accuses and assists carrying out last diagnostic, reduce the labor intensity of doctor, saved Diagnostic Time, increase patient daily inspection people
Number provides the quality time for the timely treatment of patient, reduces patient suffering, then depth convolutional neural networks study module
Joined by carrying out pulmonary parenchyma segmentation, extraction area-of-interest and feature successively to the image of raw video acquisition module after study
Discriminant classification obtains Lung neoplasm after number extraction step, and testing result is passed to output module, extracts and feels in area-of-interest
Interest region refers to that tubercle blood vessel similar with tubercle feature and bronchus, depth convolutional neural networks study module include pair
CT images carry out pretreated image pre-processing unit, the two-dimensional convolution neural network unet of prediction Lung neoplasm segmentation image and
Predict the residual neural network Resnet3D of three dimensional depth of the true and false positive probability of Lung neoplasm, image pre-processing unit is to CT images first
It is pre-processed, keeps whole CT image pixels interval unified, picture contrast is unified, then trains two-dimensional convolution neural network
Unet predicts that Lung neoplasm divides image, divides image recommended candidate tubercle based on Lung neoplasm, finally trains the residual nerve of three dimensional depth
The true and false positive probability of network Resnet3D prediction Lung neoplasms, screens out false positive combination, to improve the detection of the small state of an illness of Lung neoplasm,
AL is fully combined by the technology in medical knowledge, is adapted to the CT images of different quality and all kinds of tubercles, such as：Lung wall is convenient for knot
Section, base of lung portion sharp corner tubercle, ground glass tubercle, edge lesser tubercle, the Lung neoplasm of different volumes, the strange Lung neoplasm of shape,
Close to vertical diaphragm calcium scoring, the tubercle image of poor image quality, conventional Lung neoplasm etc., it is left that detection accuracy may be up to 98%
The right side finally can have output module that detection data is passed to terminal as the capable auxiliary tool of image department doctor,
Convenient for the testing result for the self energy science and technology that doctor directly watches from terminal.
Claims (6)
1. a kind of CT pulmonary tuberculosis detects artificial intelligence diagnosis and therapy system, including feature samples library, for neuroid study module, depth
Spend convolutional neural networks study module, output module and terminal, which is characterized in that be provided in the feature samples library
For the great amount of samples that neuroid study module and depth convolutional neural networks study module learn, neuroid
Module is practised by can automatically be diagnosed to diagnostic data and the image of raw video acquisition module after study, and by diagnostic result
Pass to output module, depth convolutional neural networks study module by after study to the image of raw video acquisition module successively
Discriminant classification obtains Lung neoplasm after the segmentation of progress pulmonary parenchyma, extraction area-of-interest and characteristic parameter extraction step, and will inspection
It surveys result and passes to output module, detection data is passed to terminal by output module.
2. a kind of CT pulmonary tuberculosis according to claim 1 detects artificial intelligence diagnosis and therapy system, which is characterized in that the depth
Convolutional neural networks study module includes carrying out pretreated image pre-processing unit to CT images, and prediction Lung neoplasm divides image
Two-dimensional convolution neural network unet and predict the true and false positive probability of Lung neoplasm the residual neural network Resnet3D of three dimensional depth.
3. a kind of CT pulmonary tuberculosis according to claim 1 detects artificial intelligence diagnosis and therapy system, which is characterized in that the feature
Sample database includes a large amount of normal person's rabat images and the rabat image of Lung neoplasm patient, in mark first from historical sample
Candidate samples are filtered out in data, then candidate samples are audited.
4. a kind of CT pulmonary tuberculosis according to claim 1 detects artificial intelligence diagnosis and therapy system, which is characterized in that the nerve
Metanetwork unit is using multichannel, isomery Three dimensional convolution blending algorithm.
5. a kind of CT pulmonary tuberculosis according to claim 1 detects artificial intelligence diagnosis and therapy system, which is characterized in that the extraction
Area-of-interest refers to tubercle blood vessel similar with tubercle feature and bronchus in area-of-interest.
6. a kind of CT pulmonary tuberculosis according to claim 1 detects artificial intelligence diagnosis and therapy system, which is characterized in that the output
The input terminal of module passes through the defeated of data line and neuroid study module and depth convolutional neural networks study module respectively
Outlet is electrically connected, and the output end of output module and the input terminal of terminal pass through data line electrical connection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810569856.9A CN108670285A (en) | 2018-06-05 | 2018-06-05 | A kind of CT pulmonary tuberculosis detection artificial intelligence diagnosis and therapy system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810569856.9A CN108670285A (en) | 2018-06-05 | 2018-06-05 | A kind of CT pulmonary tuberculosis detection artificial intelligence diagnosis and therapy system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108670285A true CN108670285A (en) | 2018-10-19 |
Family
ID=63809782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810569856.9A Pending CN108670285A (en) | 2018-06-05 | 2018-06-05 | A kind of CT pulmonary tuberculosis detection artificial intelligence diagnosis and therapy system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108670285A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109727260A (en) * | 2019-01-24 | 2019-05-07 | 杭州英库医疗科技有限公司 | A kind of three-dimensional lobe of the lung dividing method based on CT images |
| CN109727253A (en) * | 2018-11-14 | 2019-05-07 | 西安大数据与人工智能研究院 | Divide the aided detection method of Lung neoplasm automatically based on depth convolutional neural networks |
| CN109785963A (en) * | 2019-01-16 | 2019-05-21 | 成都蓝景信息技术有限公司 | Lung neoplasm screening algorithm based on depth learning technology |
| CN110164559A (en) * | 2019-04-28 | 2019-08-23 | 万达信息股份有限公司 | A kind of lunger's early warning system based on electronic health record data |
| CN110782441A (en) * | 2019-10-22 | 2020-02-11 | 浙江大学 | DR image pulmonary tuberculosis intelligent segmentation and detection method based on deep learning |
| CN111179269A (en) * | 2019-11-11 | 2020-05-19 | 浙江工业大学 | PET image segmentation method based on multi-view and 3-dimensional convolution fusion strategy |
| CN111311589A (en) * | 2020-03-05 | 2020-06-19 | 上海市肺科医院（上海市职业病防治院） | Pulmonary nodule detection and property judgment system and method |
| CN111798437A (en) * | 2020-07-09 | 2020-10-20 | 兴义民族师范学院 | Novel coronavirus pneumonia AI rapid diagnosis method based on CT image |
| CN111816314A (en) * | 2020-07-01 | 2020-10-23 | 深圳市职业病防治院 | Method for selecting, marking and verifying pneumoconiosis chest radiograph through artificial intelligence screening |
| CN112116603A (en) * | 2020-09-14 | 2020-12-22 | 中国科学院大学宁波华美医院 | Pulmonary nodule false positive screening method based on multitask learning |
| CN112635069A (en) * | 2020-12-14 | 2021-04-09 | 内蒙古卫数数据科技有限公司 | Intelligent pulmonary tuberculosis identification method based on conventional test data |
| CN112669320A (en) * | 2021-03-22 | 2021-04-16 | 四川大学 | SPECT thyroid imaging intelligent identification method based on deep neural network |
| CN112734741A (en) * | 2021-01-19 | 2021-04-30 | 浙江飞图影像科技有限公司 | Image processing method and system for pneumonia CT image |
| CN112950534A (en) * | 2021-01-22 | 2021-06-11 | 华东师范大学 | Portable ultrasonic pneumonia auxiliary diagnosis system based on artificial intelligence |
| CN114255198A (en) * | 2019-03-28 | 2022-03-29 | 芨影(厦门)科技有限公司 | Artificial intelligence modeling and identification system for medical graphic image AI |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700118A (en) * | 2015-03-18 | 2015-06-10 | 中国科学院自动化研究所 | Pulmonary nodule benignity and malignancy predicting method based on convolutional neural networks |
| CN106780460A (en) * | 2016-12-13 | 2017-05-31 | 杭州健培科技有限公司 | A kind of Lung neoplasm automatic checkout system for chest CT image |
| CN107016665A (en) * | 2017-02-16 | 2017-08-04 | 浙江大学 | A kind of CT pulmonary nodule detection methods based on depth convolutional neural networks |
| CN107563123A (en) * | 2017-09-27 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for marking medical image |
-
2018
- 2018-06-05 CN CN201810569856.9A patent/CN108670285A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700118A (en) * | 2015-03-18 | 2015-06-10 | 中国科学院自动化研究所 | Pulmonary nodule benignity and malignancy predicting method based on convolutional neural networks |
| CN106780460A (en) * | 2016-12-13 | 2017-05-31 | 杭州健培科技有限公司 | A kind of Lung neoplasm automatic checkout system for chest CT image |
| CN107016665A (en) * | 2017-02-16 | 2017-08-04 | 浙江大学 | A kind of CT pulmonary nodule detection methods based on depth convolutional neural networks |
| CN107563123A (en) * | 2017-09-27 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for marking medical image |
Non-Patent Citations (1)
| Title |
|---|
| 科技大兔子: "阿里云人工智能ET夺肺结节诊断世界冠军", 《阿里云人工智能ET夺肺结节诊断世界冠军》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109727253A (en) * | 2018-11-14 | 2019-05-07 | 西安大数据与人工智能研究院 | Divide the aided detection method of Lung neoplasm automatically based on depth convolutional neural networks |
| CN109785963A (en) * | 2019-01-16 | 2019-05-21 | 成都蓝景信息技术有限公司 | Lung neoplasm screening algorithm based on depth learning technology |
| CN109727260A (en) * | 2019-01-24 | 2019-05-07 | 杭州英库医疗科技有限公司 | A kind of three-dimensional lobe of the lung dividing method based on CT images |
| CN114255198A (en) * | 2019-03-28 | 2022-03-29 | 芨影(厦门)科技有限公司 | Artificial intelligence modeling and identification system for medical graphic image AI |
| CN110164559A (en) * | 2019-04-28 | 2019-08-23 | 万达信息股份有限公司 | A kind of lunger's early warning system based on electronic health record data |
| CN110782441A (en) * | 2019-10-22 | 2020-02-11 | 浙江大学 | DR image pulmonary tuberculosis intelligent segmentation and detection method based on deep learning |
| CN111179269A (en) * | 2019-11-11 | 2020-05-19 | 浙江工业大学 | PET image segmentation method based on multi-view and 3-dimensional convolution fusion strategy |
| CN111179269B (en) * | 2019-11-11 | 2023-07-11 | 浙江工业大学 | PET image segmentation method based on multi-view and three-dimensional convolution fusion strategy |
| CN111311589A (en) * | 2020-03-05 | 2020-06-19 | 上海市肺科医院（上海市职业病防治院） | Pulmonary nodule detection and property judgment system and method |
| CN111816314A (en) * | 2020-07-01 | 2020-10-23 | 深圳市职业病防治院 | Method for selecting, marking and verifying pneumoconiosis chest radiograph through artificial intelligence screening |
| CN111816314B (en) * | 2020-07-01 | 2023-10-20 | 深圳市职业病防治院 | Chest card selection, labeling and verification method for artificial intelligent screening of pneumoconiosis |
| CN111798437A (en) * | 2020-07-09 | 2020-10-20 | 兴义民族师范学院 | Novel coronavirus pneumonia AI rapid diagnosis method based on CT image |
| CN112116603A (en) * | 2020-09-14 | 2020-12-22 | 中国科学院大学宁波华美医院 | Pulmonary nodule false positive screening method based on multitask learning |
| CN112635069A (en) * | 2020-12-14 | 2021-04-09 | 内蒙古卫数数据科技有限公司 | Intelligent pulmonary tuberculosis identification method based on conventional test data |
| CN112734741A (en) * | 2021-01-19 | 2021-04-30 | 浙江飞图影像科技有限公司 | Image processing method and system for pneumonia CT image |
| CN112950534A (en) * | 2021-01-22 | 2021-06-11 | 华东师范大学 | Portable ultrasonic pneumonia auxiliary diagnosis system based on artificial intelligence |
| CN112669320A (en) * | 2021-03-22 | 2021-04-16 | 四川大学 | SPECT thyroid imaging intelligent identification method based on deep neural network |
| CN112669320B (en) * | 2021-03-22 | 2021-08-13 | 四川大学 | SPECT thyroid imaging intelligent identification method based on deep neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108670285A (en) | A kind of CT pulmonary tuberculosis detection artificial intelligence diagnosis and therapy system | |
| CN104414636B (en) | Cerebral microbleeds computer-aided detection system based on MRI | |
| CN112088394A (en) | Computerized classification of biological tissue | |
| CN104299242B (en) | Fluoroscopic visualization eye fundus image extracting method based on NGC ACM | |
| Al Mubarok et al. | Pneumonia detection with deep convolutional architecture | |
| CN113420826B (en) | Liver focus image processing system and image processing method | |
| CN110991536B (en) | Training method of early warning model of primary liver cancer | |
| Tang et al. | CNN-based qualitative detection of bone mineral density via diagnostic CT slices for osteoporosis screening | |
| CN111598868B (en) | Lung ultrasonic image identification method and system | |
| CN115564741A (en) | Device for quantifying esophageal and gastric fundus varices based on CT (computed tomography) images | |
| Bassiouny et al. | An interpretable object detection-based model for the diagnosis of neonatal lung diseases using ultrasound images | |
| Magna et al. | Adaptive classification model based on artificial immune system for breast cancer detection | |
| Gao et al. | CCE-Net: a rib fracture diagnosis network based on contralateral, contextual, and edge enhanced modules | |
| Li et al. | Preliminary study on artificial intelligence diagnosis of pulmonary embolism based on computer in-depth study | |
| CN110390678A (en) | A kind of organization type dividing method of colorectal cancer IHC dye image | |
| CN114332910A (en) | Human body part segmentation method for similar feature calculation of far infrared image | |
| CN108960305A (en) | A kind of scope scope interpretation system and method | |
| Hussain et al. | An iris based lungs pre-diagnostic system | |
| CN116934683A (en) | Method for assisting ultrasonic diagnosis of spleen wound by artificial intelligence | |
| CN108596877B (en) | Rib CT data analysis system | |
| CN116630680A (en) | Dual-mode image classification method and system combining X-ray photography and ultrasound | |
| CN116188424A (en) | Method for establishing artificial intelligence assisted ultrasonic diagnosis spleen and liver wound model | |
| KR102384083B1 (en) | Apparatus and Method for Diagnosing Sacroiliac Arthritis and Evaluating the Degree of Inflammation using Magnetic Resonance Imaging | |
| CN115035086A (en) | Intelligent tuberculosis skin test screening and analyzing method and device based on deep learning | |
| CN112807008A (en) | Method and system for identifying actual mycoplasma pneumoniae and streptococcus pneumoniae of children based on imaging omics |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181019 |