CN111920440A - Early lung cancer detection and classification integrated equipment and system based on deep learning - Google Patents
Early lung cancer detection and classification integrated equipment and system based on deep learning Download PDFInfo
- Publication number
- CN111920440A CN111920440A CN202011008825.XA CN202011008825A CN111920440A CN 111920440 A CN111920440 A CN 111920440A CN 202011008825 A CN202011008825 A CN 202011008825A CN 111920440 A CN111920440 A CN 111920440A
- Authority
- CN
- China
- Prior art keywords
- lung
- image
- module
- nodule
- lung cancer
- 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.)
- Withdrawn
Links
- 206010058467 Lung neoplasm malignant Diseases 0.000 title claims abstract description 48
- 201000005202 lung cancer Diseases 0.000 title claims abstract description 48
- 208000020816 lung neoplasm Diseases 0.000 title claims abstract description 48
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 238000013135 deep learning Methods 0.000 title claims abstract description 19
- 206010056342 Pulmonary mass Diseases 0.000 claims abstract description 50
- 210000004072 lung Anatomy 0.000 claims abstract description 45
- 230000002685 pulmonary effect Effects 0.000 claims abstract description 44
- 238000005259 measurement Methods 0.000 claims abstract description 25
- 238000012216 screening Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 230000037237 body shape Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000002591 computed tomography Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 230000006866 deterioration Effects 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 3
- 201000011510 cancer Diseases 0.000 abstract description 6
- 206010028980 Neoplasm Diseases 0.000 abstract description 5
- 230000036210 malignancy Effects 0.000 abstract description 5
- 238000010191 image analysis Methods 0.000 abstract description 2
- 210000001519 tissue Anatomy 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 210000003205 muscle Anatomy 0.000 description 3
- 210000004879 pulmonary tissue Anatomy 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Images
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
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
-
- 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
- A61B6/5229—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- 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
- G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
-
- 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
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30061—Lung
- G06T2207/30064—Lung nodule
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Surgery (AREA)
- Data Mining & Analysis (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Optics & Photonics (AREA)
- High Energy & Nuclear Physics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Analysis (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Automation & Control Theory (AREA)
- Pulmonology (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Mathematical Optimization (AREA)
Abstract
The invention relates to the field of image analysis, in particular to an early lung cancer detection and classification integrated system based on deep learning, which comprises a lung CT image acquisition module, a CT image preprocessing module, a lung image identification module, a lung nodule measurement module and a lung cancer screening module, wherein the lung image identification module realizes the detection and identification of lung nodules and lung nodule holes in lung images based on a DSSD _ Xconcentration model and intercepts lung nodule regions; the pulmonary nodule measurement module is used for measuring pulmonary nodules and pulmonary nodule hole sizes based on the length-width ratio of the connected component circumscribed rectangle and outputting measurement results; the lung cancer screening module is used for screening early lung cancer based on preset screening standards according to the measurement result of lung nodules. The method can automatically detect the type and probability of the early lung cancer, and can accurately identify the type, size, position and malignancy of the lung nodule.
Description
Technical Field
The invention relates to the field of image analysis, in particular to early lung cancer detection and classification integrated equipment and system based on deep learning.
Background
The lung cancer is the malignant tumor with the highest morbidity and mortality, the early symptoms are not obvious, and the lung cancer in the middle and late stages is extremely difficult to cure, so the early lung cancer detection is the main means for prolonging the life cycle of a patient and reducing the mortality. Early lung cancer is mostly represented by lung nodules, is large in number and small in size, low in contrast and easy to be confused with other tissues; at present, pulmonary nodule diagnosis is mainly carried out by adopting a pulmonary CT examination mode, doctors need to judge the malignancy degree of pulmonary nodules according to the size and the shape of the pulmonary nodules in CT images of patients, the number of CT images of a lung cancer patient is hundreds of levels, the workload of the doctors is heavy, the evaluation accuracy can be influenced by subjective factors such as doctor experience, fatigue degree, personal emotion and the like, meanwhile, the resource distribution of specialist doctors in each region is uneven, and missed diagnosis and misdiagnosis are easy to occur by adopting a traditional diagnosis and treatment mode.
In recent years, with the improvement of computer computing power and the stepwise increase of data volume, the deep learning technology is rapidly developed and is widely applied to the medical field, and scholars and research institutions at home and abroad make a great deal of research work on computer-aided systems for early lung cancer detection, the main technical steps include data preprocessing and lung nodule detection by using a convolution network, but the methods mainly focus on identifying lung nodule regions and non-lung nodule regions, on one hand, the categories of the lung nodules are not finely distinguished, on the other hand, the types and the probability of the lung nodule canceration are closely related to the types, the sizes, the shapes and other characteristics of the lung nodules, the traditional detection convolution network can only obtain the total probability of lung cancer of a patient, the specific types of the lung cancer cannot be distinguished, therefore, doctors are often required to evaluate the lung cancer, and integration of early lung cancer detection procedures is not realized.
Disclosure of Invention
In order to solve the problems, the invention provides early lung cancer detection and classification integrated equipment and system based on deep learning, which can automatically detect the type and probability of early lung cancer and accurately identify the type, size, position and malignancy of lung nodules.
In order to achieve the purpose, the invention adopts the technical scheme that:
an early lung cancer detection and classification integrated system based on deep learning comprises:
the lung CT image acquisition module is used for acquiring a lung CT image through a high-resolution computed tomography technology;
the CT image preprocessing module is used for positioning a target region based on a Faster R-CNN model, filtering parts which are not obvious in contrast, such as ribs, muscles and the like, intercepting the region of interest, calculating and improving the significant value of lung tissues of the region of interest by combining the contrast of the region of interest, and intercepting a lung image through the obtained significant value image;
the lung image identification module is used for realizing the detection and identification of lung nodules and lung nodule holes in the lung image based on the DSSD _ Xcenter model and intercepting lung nodule areas;
the pulmonary nodule measurement module is used for measuring pulmonary nodules and pulmonary nodule hole sizes based on the length-width ratio of the connected component circumscribed rectangle and outputting measurement results;
and the lung cancer screening module is used for realizing screening of early lung cancer based on a preset screening standard according to the measurement result of the lung nodules.
Further, the DSSD _ Xception model adopts a DSSD target detection algorithm and is obtained by training based on preset lung images with lung nodules and/or lung nodule holes.
Further, the pulmonary nodule measurement module firstly realizes three-dimensional reconstruction of a pulmonary nodule region image based on MATLAB, and then measures the sizes of pulmonary nodules and pulmonary nodule holes in the three-dimensional image based on the aspect ratio of connected component circumscribed rectangles.
Further, the lung cancer screening module identifies the type and the deterioration degree of the lung nodules based on a fuzzy neural network algorithm according to the type, the position parameter, the quantity parameter and the size measurement result of the lung nodules based on preset screening standards.
Further, still include:
and the detection guiding module is used for calibrating the image acquisition position of the CT image acquisition module according to the positioning data and the body type data of the patient so as to guide the CT image acquisition module to reach the target position to finish the acquisition of the lung CT image.
Furthermore, the detection guiding module acquires positioning data of the patient through a position frame marked on the ground, the image acquisition module acquires a body shape image of the patient, binarization of the body shape image is achieved based on a maximum entropy threshold method, small-area noise is removed based on morphological region characteristics of connected components, the position of the upper half of the body of the patient is identified, and then calibration of image acquisition coordinates of the CT image acquisition module is achieved based on the position reference standard of the upper half of the lung, the identification result of the position of the upper half of the body and the positioning data of the patient.
Further, each pulmonary nodule region intercepted by the pulmonary image identification module carries the position parameter of the pulmonary nodule region in the pulmonary tissue.
The invention also provides early lung cancer detection and classification integrated equipment based on deep learning, and the detection and classification integrated system is adopted to realize the detection and classification of early lung cancer.
The invention has the following beneficial effects:
1) the method can automatically detect the type and probability of the early lung cancer, and can accurately identify the type, size, position and malignancy of the lung nodule.
2) The quality of the CT image can be improved, and a foundation is provided for the subsequent identification work of the type, size, position and malignancy degree of the lung nodule.
Drawings
Fig. 1 is a system block diagram of an early lung cancer detection and classification integrated system based on deep learning according to an embodiment of the present invention.
Fig. 2 is a system block diagram of an early lung cancer detection and classification integrated device based on deep learning according to an embodiment of the present invention.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described in detail below with reference to examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
As shown in fig. 1, an early lung cancer detection and classification integrated system based on deep learning includes:
the detection guiding module is used for calibrating the image acquisition position of the CT image acquisition module according to the positioning data and the body type data of the patient so as to guide the CT image acquisition module to reach a target position to finish acquisition of the lung CT image;
the lung CT image acquisition module is used for acquiring a lung CT image through a high-resolution computed tomography technology;
the CT image preprocessing module is used for positioning a target region based on a Faster R-CNN model, filtering parts which are not obvious in contrast, such as ribs, muscles and the like, intercepting the region of interest, calculating and improving the significant value of lung tissues of the region of interest by combining the contrast of the region of interest, and intercepting a lung image through the obtained significant value image;
the lung image identification module is used for realizing the detection and identification of lung nodules and lung nodule holes in the lung image based on the DSSD _ Xcenter model and intercepting lung nodule areas; each pulmonary nodule region intercepted by the pulmonary image identification module carries position parameters of the pulmonary nodule region in the pulmonary tissue;
the pulmonary nodule measurement module is used for measuring pulmonary nodules and pulmonary nodule hole sizes based on the length-width ratio of the connected component circumscribed rectangle and outputting measurement results;
and the lung cancer screening module is used for realizing screening of early lung cancer based on a preset screening standard according to the measurement result of the lung nodules.
In this embodiment, the DSSD _ Xception model is obtained by training based on a preset lung image with lung nodules and/or lung nodule holes by using a DSSD target detection algorithm.
In this embodiment, the pulmonary nodule measurement module first implements three-dimensional reconstruction of a pulmonary nodule region image based on MATLAB, and then measures the sizes of pulmonary nodules and pulmonary nodule holes in the three-dimensional image based on the aspect ratio of the connected component circumscribed rectangle.
In this embodiment, the lung cancer screening module identifies the type and the degree of deterioration of the lung nodules based on a fuzzy neural network algorithm based on a preset screening standard according to the type, the position parameter, the number parameter, and the size measurement result of the lung nodules.
In this embodiment, the detection guidance module acquires positioning data of a patient through a position frame marked on the ground, acquires a body shape image of the patient through the image acquisition module, realizes binarization of the body shape image based on a maximum entropy threshold method, removes small-area noise based on morphological region characteristics of connected components, completes identification of the position of the upper half of the body of the patient, and then realizes calibration of image acquisition coordinates of the CT image acquisition module based on a position reference standard of the upper half of the lung, an identification result of the position of the upper half of the body, and the positioning data of the patient.
Example 2
As shown in fig. 2, an early lung cancer detection and classification integrated device based on deep learning includes a detection guide module, a lung CT image acquisition module, and a lung CT image post-processing system loaded in a PC, wherein the detection guide module is configured to calibrate an image acquisition position of the CT image acquisition module according to positioning data and body type data of a patient, so as to guide the CT image acquisition module to reach a target position to complete acquisition of a lung CT image; the lung CT image acquisition module is used for acquiring a lung CT image through a high-resolution computed tomography technology; the lung CT image post-processing system comprises:
the CT image preprocessing module is used for positioning a target region based on a Faster R-CNN model, filtering parts which are not obvious in contrast, such as ribs, muscles and the like, intercepting the region of interest, calculating and improving the significant value of lung tissues of the region of interest by combining the contrast of the region of interest, and intercepting a lung image through the obtained significant value image;
the lung image identification module is used for realizing the detection and identification of lung nodules and lung nodule holes in the lung image based on the DSSD _ Xcenter model and intercepting lung nodule areas; each pulmonary nodule region intercepted by the pulmonary image identification module carries position parameters of the pulmonary nodule region in the pulmonary tissue;
the pulmonary nodule measurement module is used for measuring pulmonary nodules and pulmonary nodule hole sizes based on the length-width ratio of the connected component circumscribed rectangle and outputting measurement results;
and the lung cancer screening module is used for realizing screening of early lung cancer based on a preset screening standard according to the measurement result of the lung nodules.
In this embodiment, the DSSD _ Xception model is obtained by training based on a preset lung image with lung nodules and/or lung nodule holes by using a DSSD target detection algorithm.
In this embodiment, the pulmonary nodule measurement module first implements three-dimensional reconstruction of a pulmonary nodule region image based on MATLAB, and then measures the sizes of pulmonary nodules and pulmonary nodule holes in the three-dimensional image based on the aspect ratio of the connected component circumscribed rectangle.
In this embodiment, the lung cancer screening module identifies the type and the degree of deterioration of the lung nodules based on a fuzzy neural network algorithm based on a preset screening standard according to the type, the position parameter, the number parameter, and the size measurement result of the lung nodules.
In this embodiment, the detection guidance module acquires positioning data of a patient through a position frame marked on the ground, acquires a body shape image of the patient through the image acquisition module, realizes binarization of the body shape image based on a maximum entropy threshold method, removes small-area noise based on morphological region characteristics of connected components, completes identification of the position of the upper half of the body of the patient, and then realizes calibration of image acquisition coordinates of the CT image acquisition module based on a position reference standard of the upper half of the lung, an identification result of the position of the upper half of the body, and the positioning data of the patient.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be construed as the protection scope of the present invention.
Claims (8)
1. An early lung cancer detection and classification integrated system based on deep learning is characterized by comprising:
the lung CT image acquisition module is used for acquiring a lung CT image through a high-resolution computed tomography technology;
the CT image preprocessing module is used for positioning a target region based on a Faster R-CNN model, intercepting the region of interest when the contrast is not obvious, calculating and improving the significant value of the lung tissue of the region of interest by combining the contrast of the region of interest, and intercepting the lung image through the obtained significant value image;
the lung image identification module is used for realizing the detection and identification of lung nodules and lung nodule holes in the lung image based on the DSSD _ Xcenter model and intercepting lung nodule areas;
the pulmonary nodule measurement module is used for measuring pulmonary nodules and pulmonary nodule hole sizes based on the length-width ratio of the connected component circumscribed rectangle and outputting measurement results;
and the lung cancer screening module is used for realizing screening of early lung cancer based on a preset screening standard according to the measurement result of the lung nodules.
2. The deep learning-based early lung cancer detection and classification integrated system of claim 1, wherein the DSSD _ Xception model is trained based on preset lung images with lung nodules and/or lung nodule holes by using a DSSD target detection algorithm.
3. The deep learning-based early lung cancer detection and classification integrated system as claimed in claim 1, wherein the pulmonary nodule measurement module first performs three-dimensional reconstruction of an image of a pulmonary nodule region based on MATLAB, and then performs measurement of sizes of pulmonary nodules and pulmonary nodule holes in the three-dimensional image based on an aspect ratio of a connected component bounding rectangle.
4. The deep learning-based early lung cancer detection and classification integrated system as claimed in claim 1, wherein the lung cancer screening module is based on a fuzzy neural network algorithm to identify the type and the deterioration degree of lung nodules according to the type, the location parameter, the number parameter and the size measurement result of the lung nodules based on preset screening criteria.
5. The deep learning-based early lung cancer detection and classification integrated system according to claim 1, further comprising:
and the detection guiding module is used for calibrating the image acquisition position of the CT image acquisition module according to the positioning data and the body type data of the patient so as to guide the CT image acquisition module to reach the target position to finish the acquisition of the lung CT image.
6. The system as claimed in claim 5, wherein the detection guidance module obtains the positioning data of the patient through a position frame marked on the ground, the image acquisition module acquires the body shape image of the patient, the binarization of the body shape image is realized based on a maximum entropy threshold method, the small area noise is removed based on the morphological region characteristics of the connected components, the identification of the position of the upper half of the body of the patient is completed, and then the calibration of the image acquisition coordinates of the CT image acquisition module is realized based on the position reference standard of the upper half of the lung, the identification result of the position of the upper half of the body and the positioning data of the patient.
7. The deep learning-based early lung cancer detection and classification integrated system as claimed in claim 1, wherein each lung nodule region intercepted by the lung image recognition module carries the location parameter of the lung tissue in which the lung nodule region is located.
8. The utility model provides an early lung cancer detects categorised integration equipment based on deep learning which characterized in that: the detection and classification integration system of any one of claims 1-7 is used for early stage lung cancer detection and classification.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011008825.XA CN111920440A (en) | 2020-09-23 | 2020-09-23 | Early lung cancer detection and classification integrated equipment and system based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011008825.XA CN111920440A (en) | 2020-09-23 | 2020-09-23 | Early lung cancer detection and classification integrated equipment and system based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111920440A true CN111920440A (en) | 2020-11-13 |
Family
ID=73334024
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011008825.XA Withdrawn CN111920440A (en) | 2020-09-23 | 2020-09-23 | Early lung cancer detection and classification integrated equipment and system based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111920440A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112529894A (en) * | 2020-12-22 | 2021-03-19 | 徐州医科大学 | Thyroid nodule diagnosis method based on deep learning network |
CN113591791A (en) * | 2021-08-16 | 2021-11-02 | 郑州大学 | Lung cancer automatic identification system based on self-learning artificial intelligence |
CN117532216A (en) * | 2023-12-21 | 2024-02-09 | 重庆工业设备安装集团有限公司 | Steel structure welding robot |
-
2020
- 2020-09-23 CN CN202011008825.XA patent/CN111920440A/en not_active Withdrawn
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112529894A (en) * | 2020-12-22 | 2021-03-19 | 徐州医科大学 | Thyroid nodule diagnosis method based on deep learning network |
CN112529894B (en) * | 2020-12-22 | 2022-02-15 | 徐州医科大学 | Thyroid nodule diagnosis method based on deep learning network |
CN113591791A (en) * | 2021-08-16 | 2021-11-02 | 郑州大学 | Lung cancer automatic identification system based on self-learning artificial intelligence |
CN117532216A (en) * | 2023-12-21 | 2024-02-09 | 重庆工业设备安装集团有限公司 | Steel structure welding robot |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110060774B (en) | Thyroid nodule identification method based on generative confrontation network | |
Zhou et al. | A radiomics approach with CNN for shear-wave elastography breast tumor classification | |
CN111920440A (en) | Early lung cancer detection and classification integrated equipment and system based on deep learning | |
Huang et al. | Computer‐aided diagnosis using morphological features for classifying breast lesions on ultrasound | |
CN109727243A (en) | Breast ultrasound image recognition analysis method and system | |
CN113506294B (en) | Medical image evaluation method, system, computer equipment and storage medium | |
US9177379B1 (en) | Method and system for identifying anomalies in medical images | |
JP4184842B2 (en) | Image discrimination device, method and program | |
US9401021B1 (en) | Method and system for identifying anomalies in medical images especially those including body parts having symmetrical properties | |
US9779504B1 (en) | Method and system for identifying anomalies in medical images especially those including one of a pair of symmetric body parts | |
US9092867B2 (en) | Methods for segmenting images and detecting specific structures | |
CN101103924A (en) | Galactophore cancer computer auxiliary diagnosis method based on galactophore X-ray radiography and system thereof | |
KR20180022607A (en) | Determination of result data on the basis of medical measurement data from various measurements | |
CN105654490A (en) | Lesion region extraction method and device based on ultrasonic elastic image | |
TWI810498B (en) | Liver Tumor Intelligent Analysis Device | |
US9014447B2 (en) | System and method for detection of lesions in three-dimensional digital medical image | |
CN110033432B (en) | Urinary calculus component analysis method and system based on machine learning and energy spectrum CT | |
Heine et al. | A statistical methodology for mammographic density detection | |
CN112071418B (en) | Gastric cancer peritoneal metastasis prediction system and method based on enhanced CT image histology | |
CN212853503U (en) | Intelligent liver tumor analysis device | |
Zhang et al. | Comparison of multiple feature extractors on Faster RCNN for breast tumor detection | |
Wijata et al. | Unbiased validation of the algorithms for automatic needle localization in ultrasound-guided breast biopsies | |
Saroğlu et al. | Machine learning, IoT and 5G technologies for breast cancer studies: A review | |
US20140094679A1 (en) | Systems and methods for performing organ detection | |
CN116309551A (en) | Method, device, electronic equipment and readable medium for determining focus sampling area |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201113 |
|
WW01 | Invention patent application withdrawn after publication |