CN111160413A - Thyroid nodule classification method based on multi-scale feature fusion - Google Patents
Thyroid nodule classification method based on multi-scale feature fusion Download PDFInfo
- Publication number
- CN111160413A CN111160413A CN201911271119.1A CN201911271119A CN111160413A CN 111160413 A CN111160413 A CN 111160413A CN 201911271119 A CN201911271119 A CN 201911271119A CN 111160413 A CN111160413 A CN 111160413A
- Authority
- CN
- China
- Prior art keywords
- thyroid nodule
- network
- residual error
- scale
- data set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 39
- 208000009453 Thyroid Nodule Diseases 0.000 title claims abstract description 37
- 208000024770 Thyroid neoplasm Diseases 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000002604 ultrasonography Methods 0.000 claims abstract description 17
- 238000004140 cleaning Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims abstract description 6
- 210000001685 thyroid gland Anatomy 0.000 claims abstract description 6
- 230000000694 effects Effects 0.000 claims abstract description 5
- 230000002093 peripheral effect Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 230000017531 blood circulation Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 abstract description 3
- 238000013507 mapping Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 230000003211 malignant effect Effects 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 201000002510 thyroid cancer Diseases 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002059 diagnostic imaging 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
- 210000000750 endocrine system Anatomy 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Abstract
The invention relates to a thyroid nodule classification method based on multi-scale feature fusion, which is characterized by comprising the following steps of: the method comprises the following steps: 1) acquiring an original thyroid ultrasound image data set, and processing each ultrasound image; 2) cleaning an original ultrasonic image data set, and removing images which do not meet the requirements to obtain a data set containing 2000 high-quality thyroid nodule ultrasonic images; 3) constructing a thyroid nodule ultrasonic image classification network based on a residual error network; 4) replacing the residual error module with a multi-scale fusion module; 5) adding a high-resolution channel on the basis of a residual error network; 6) and analyzing the classification effect of the network model based on the multi-scale feature fusion and the high-resolution channel. The invention has scientific and reasonable design, designs a mechanism combining multi-scale features and high-resolution channels and improves the network performance.
Description
Technical Field
The invention belongs to the field of deep learning and medical image processing, relates to a data cleaning technology and a convolutional neural network technology of an ultrasonic image data set of thyroid nodules, and particularly relates to a thyroid nodule classification method based on multi-scale feature fusion.
Background
Thyroid nodules are a common disease of the endocrine system, and are carried in 18% of adults. Although the vast majority of thyroid nodules are benign, 10% of patients develop malignant thyroid nodules, primarily thyroid cancer. In recent years, the incidence of thyroid cancer has rapidly increased, and the thyroid cancer is the seventh of the incidence of cancer in China at present. Ultrasound diagnosis is a common means of examining thyroid nodules for benign and malignant status. However, since doctors generally rely on subjective judgment, objective criteria are lacking, and mistakes are easily made.
The breakthrough of deep learning, particularly the convolutional neural network, in medical imaging proves its effectiveness in solving the problem of practical imaging. On one hand, the convolutional neural network can extract features from medical images through a multilayer network, and the accuracy rate far surpasses that of other methods on the aspect of relevant medical problems is obtained by utilizing the features; on the other hand, the depth learning method based on medical images can efficiently assist imaging doctors and greatly reduce the workload of doctors.
Most of the previous work was to use convolutional neural networks for feature extraction or fine-tune the ImageNet. The methods neglect the importance of end-to-end training, and do not design a network structure aiming at the characteristics of the thyroid nodule ultrasonic image. In addition, due to the problem of data confidentiality, the ultrasound images of most researchers are not public, and public large thyroid nodule ultrasound image data sets are urgently needed to be used by researchers.
Through a search for a patent publication, no patent publication similar to the present patent application is found.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a thyroid nodule classification method based on multi-scale feature fusion.
The technical problem to be solved by the invention is realized by the following technical scheme:
a thyroid nodule classification method based on multi-scale feature fusion is characterized by comprising the following steps: the method comprises the following steps:
1) acquiring an original thyroid ultrasound image data set, and processing each ultrasound image;
2) cleaning an original ultrasonic image data set, and removing images which do not meet the requirements to obtain a data set containing 2000 high-quality thyroid nodule ultrasonic images;
3) constructing a thyroid nodule ultrasonic image classification network based on a residual error network;
4) replacing the residual error module with a multi-scale fusion module;
5) adding a high-resolution channel on the basis of a residual error network;
6) and analyzing the classification effect of the network model based on the multi-scale feature fusion and the high-resolution channel.
In addition, the peripheral boundary regions in the original ultrasonic image in the step 1) contain privacy information, and the boundary regions are cut out.
Moreover, the peripheral boundary region in the original ultrasound image in step 1) contains privacy information, the boundary region is cut off, and the color doppler blood flow image exists in the original ultrasound image data set in step 2), and a color operator is required to screen out the color doppler blood flow image and divide the data set into a training set and a test set.
And moreover, in the step 1), the peripheral boundary region in the original ultrasonic image contains privacy information, the boundary region is cut off, and in the step 3), the data set in the step 2) is used, and the network model based on the residual error network is trained end to end.
And moreover, in the step 1), the peripheral boundary regions in the original ultrasonic image contain privacy information, the boundary regions are cut off, in the step 4), in the residual error network in the step 3), a residual error module is replaced by a multi-scale information fusion module, and the module performs information fusion by using cavity convolution and example regularization.
And moreover, the peripheral boundary region in the original ultrasonic image in the step 1) contains privacy information, the boundary region is cut off, and in the step 5), a high-resolution channel is added on the basis of the residual error network in the step 3), and the high-resolution channel is internally composed of a multi-scale information fusion module.
The invention has the advantages and beneficial effects that:
1. the thyroid nodule classification method based on multi-scale feature fusion provides a brand-new high-resolution thyroid nodule ultrasonic image data set, can help researchers build network models to a great extent, and is favorable for the researchers to visually evaluate the work.
2. According to the thyroid nodule classification method based on multi-scale feature fusion, the end-to-end training method is adopted, feature extraction or feature engineering is not needed, and the training difficulty is greatly reduced; the invention provides a multi-scale information fusion module which can be used for extracting global features irrelevant to the image style and the appearance in a network shallow layer. The adaptability and robustness of the network domain are improved to a certain extent; meanwhile, the characteristics are extracted together by combining batch regularization, so that the classification performance of the network is improved.
3. According to the thyroid nodule classification method based on multi-scale feature fusion, a plurality of cavity convolutions with different cavity rates are used in a module in parallel, the network receptive field is improved, more multi-scale context information is captured, various multi-scale information is fused through an information fusion mechanism, and the network new energy is improved on the basis of not greatly improving the network parameters.
4. The thyroid nodule classification method based on multi-scale feature fusion disclosed by the invention is characterized in that a high-resolution channel is designed on the basis of a residual error network to keep high-resolution information, and meanwhile, a multi-scale feature fusion module is combined, so that more abundant multi-scale feature information and the performance of a large-range high network can be obtained.
Drawings
FIG. 1 is a flow chart of a classification method of the present invention;
FIG. 2 is a block diagram of the multi-scale feature fusion module of the present invention;
FIG. 3 is a schematic view of a high resolution channel of the present invention.
Detailed Description
The present invention is further illustrated by the following specific examples, which are intended to be illustrative, not limiting and are not intended to limit the scope of the invention.
A thyroid nodule classification method based on multi-scale feature fusion is characterized by comprising the following steps: the method comprises the following steps:
1) acquiring an original thyroid ultrasound image data set, and processing each ultrasound image;
2) extra marks of thyroid ultrasonic image boundaries, such as machine models, diagnosis time, ultrasonic probe emission frequency, hospital names and the like, which are irrelevant to nodule diagnosis, are removed, so that influence on benign and malignant judgment of thyroid nodules caused by peripheral information of ultrasonic images is avoided;
3) cleaning an original ultrasonic image data set, and removing images which do not meet the requirements to obtain a data set containing 2000 high-quality thyroid nodule ultrasonic images;
4) for an ultrasound image containing N pixel points, assume that R, G, B three channel values of the pixel points P (i, j) are respectively
And
the variance σ of the R, G, B three-channel values of the pixel point P (i, j)2The calculation formula of (2) is as follows:
to further determine the color operator C, the variance σ is used2Setting a threshold value η for the value size, and performing binarization processing on the pixel point P (i, j) according to the following formula;
4) in color operator C, a point with a pixel value of 255 is the region of interest. In general, the greater the total number of points 255 in a map, the higher the probability that it contains color Doppler flow imaging. Assuming that the total number of pixel points in a binary color operator image is N and the total number of points with the pixel value of 255 is K, when N/K is larger than or equal to 0.01, the image is considered to contain color Doppler blood flow imaging.
5) Manually screening out other irrelevant images, and then forming a data set;
6) constructing a thyroid nodule ultrasonic image classification model based on a residual error network: the residual network contains a total of 50 layers, where the first time is a convolution with a convolution kernel size of 7 × 7, step size of 2; followed by a 2 x 2 max pooling layer; then the network is composed of 4 residual groups, which respectively contain 3, 4, 6 and 3 residual modules, each residual module is composed of 1 × 1, 3 × 3 and 1 × 1 convolutional layers, each residual module contains identity transformation, and the last full-link layer outputs a prediction result.
7) The multi-scale feature fusion module is shown in fig. 2. Assuming that the output feature mapping obtained after the feature mapping passes through the first layer of 1 × 1 convolutional layer is X, the X is respectively subjected to batch regularization and example regularization. The following are formulas for batch and example regularization:
XBN＝BN(X)
XIN＝IN(X)
8)XBNand XINThe common convolution calculation formula for 3 × 3 performed in parallel is:
XBN1＝Fr＝1(XBN)
XIN1＝Fr＝1(XIN)
9) mixing XBNAnd XINIs the same as XBN1And XIN1After the features are fused, performing 3 × 3 hole convolution with a hole rate of 2, wherein the calculation formula is as follows:
10) and adding the obtained four feature mappings to obtain an output Y with rich multi-scale information, wherein the calculation formula is as follows:
Y＝XBN1+XBN2+XIN1+XIN2
11) assuming input feature mapping
Respectively transmitting the data to the high-resolution channels, and keeping the resolution and the number of the channels unchanged in the high-resolution channels in the common resolution channels to obtain output characteristic mapping
The ordinary resolution channel carries out convolution operation with the step length of 2 on the first convolution layer, the width and the height of the feature mapping are reduced to 1/2, and the number of the channels is changed to 2 times of the original number; obtaining feature outputs after passing through a common resolution channel
Performing pooling operation on the feature mapping Y to obtain
Finally, carrying out Y' and ZA splicing operation of obtaining an output H by calculating the following formula, wherein
Feature stitching is represented.
12) Analyzing the classification effect of the network model based on the multi-scale feature fusion and the high-resolution channel: the trained network is used for analyzing a test set, main indexes of evaluation include Accuracy (Accuracy), Sensitivity (Sensitivity), Sensitivity (Specificity) and F1 scores, and the calculation modes are as follows:
wherein TP indicates true positive, FN indicates false negative, FP indicates false positive, and TN indicates true negative.
Table 1 shows the experimental results of the network, from which it can be seen that the network model proposed by the present invention all achieves the best results, which are optimal.
Table 1 table of network experiment results
The invention provides a method for collecting, cleaning and screening high-quality thyroid nodule images, aiming at the problem that the current thyroid nodule ultrasonic image diagnosis field lacks available public data sets for researchers to use. A high quality thyroid nodule ultrasound image data set was collected for use by the investigator. Meanwhile, possible application of multi-scale feature fusion in the field of thyroid ultrasound image classification is discussed. A multi-scale feature fusion module is designed on the basis of a residual error module of a residual error network, and an excellent multi-scale feature fusion effect is achieved. In addition, a mechanism of fusing a high-resolution channel and a low-resolution channel is designed on the basis of a residual error network structure, so that the classification performance of the network model is improved.
Although the embodiments of the present invention and the accompanying drawings are disclosed for illustrative purposes, those skilled in the art will appreciate that: various substitutions, changes and modifications are possible without departing from the spirit and scope of the invention and the appended claims, and therefore the scope of the invention is not limited to the disclosure of the embodiments and the accompanying drawings.
Claims (6)
1. A thyroid nodule classification method based on multi-scale feature fusion is characterized by comprising the following steps: the method comprises the following steps:
1) acquiring an original thyroid ultrasound image data set, and processing each ultrasound image;
2) cleaning an original ultrasonic image data set, and removing images which do not meet the requirements to obtain a data set containing 2000 high-quality thyroid nodule ultrasonic images;
3) constructing a thyroid nodule ultrasonic image classification network based on a residual error network;
4) replacing the residual error module with a multi-scale fusion module;
5) adding a high-resolution channel on the basis of a residual error network;
6) and analyzing the classification effect of the network model based on the multi-scale feature fusion and the high-resolution channel.
2. The method for thyroid nodule classification based on multi-scale feature fusion according to claim 1, wherein: in the step 1), the peripheral boundary regions in the original ultrasonic image contain privacy information, and the boundary regions are cut out.
3. The method for thyroid nodule classification based on multi-scale feature fusion according to claim 1, wherein: in the step 2), a color doppler blood flow image exists in the original ultrasound image data set, and the color doppler blood flow image needs to be screened out by using a color operator and the data set is divided into a training set and a test set.
4. The method for thyroid nodule classification based on multi-scale feature fusion according to claim 1, wherein: and 3) training the network model based on the residual error network end to end by using the data set in the step 2).
5. The method for thyroid nodule classification based on multi-scale feature fusion according to claim 1, wherein: and 4) in the residual error network in the step 3), replacing a residual error module with a multi-scale information fusion module, and performing information fusion by using cavity convolution and instance regularization by using the multi-scale information fusion module.
6. The method for thyroid nodule classification based on multi-scale feature fusion according to claim 1, wherein: and 5) adding a high-resolution channel on the basis of the residual error network in the step 3), wherein the high-resolution channel is internally composed of a multi-scale information fusion module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911271119.1A CN111160413B (en) | 2019-12-12 | 2019-12-12 | Thyroid nodule classification method based on multi-scale feature fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911271119.1A CN111160413B (en) | 2019-12-12 | 2019-12-12 | Thyroid nodule classification method based on multi-scale feature fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111160413A true CN111160413A (en) | 2020-05-15 |
| CN111160413B CN111160413B (en) | 2023-11-17 |
Family
ID=70557076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911271119.1A Active CN111160413B (en) | 2019-12-12 | 2019-12-12 | Thyroid nodule classification method based on multi-scale feature fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111160413B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724343A (en) * | 2020-05-18 | 2020-09-29 | 天津大学 | Thyroid nodule ultrasonic image data set enhancing method based on antagonistic learning |
| CN112785586A (en) * | 2021-02-04 | 2021-05-11 | 天津大学 | Multi-scale self-attention unsupervised domain self-adaptive algorithm |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610194A (en) * | 2017-08-14 | 2018-01-19 | 成都大学 | MRI super resolution ratio reconstruction method based on Multiscale Fusion CNN |
| CN107680678A (en) * | 2017-10-18 | 2018-02-09 | 北京航空航天大学 | Based on multiple dimensioned convolutional neural networks Thyroid ultrasound image tubercle auto-check system |
| CN108010013A (en) * | 2017-11-03 | 2018-05-08 | 天津大学 | A kind of lung CT image pulmonary nodule detection methods |
| CN108268870A (en) * | 2018-01-29 | 2018-07-10 | 重庆理工大学 | Multi-scale feature fusion ultrasonoscopy semantic segmentation method based on confrontation study |
| CN108537731A (en) * | 2017-12-29 | 2018-09-14 | 西安电子科技大学 | Image super-resolution rebuilding method based on compression multi-scale feature fusion network |
| CN108734659A (en) * | 2018-05-17 | 2018-11-02 | 华中科技大学 | A kind of sub-pix convolved image super resolution ratio reconstruction method based on multiple dimensioned label |
| CN108734660A (en) * | 2018-05-25 | 2018-11-02 | 上海通途半导体科技有限公司 | A kind of image super-resolution rebuilding method and device based on deep learning |
| CN109064405A (en) * | 2018-08-23 | 2018-12-21 | 武汉嫦娥医学抗衰机器人股份有限公司 | A kind of multi-scale image super-resolution method based on dual path network |
| CN109165667A (en) * | 2018-07-06 | 2019-01-08 | 中国科学院自动化研究所 | Based on the cerebral disease categorizing system from attention mechanism |
| CN109242839A (en) * | 2018-08-29 | 2019-01-18 | 上海市肺科医院 | A kind of good pernicious classification method of CT images Lung neoplasm based on new neural network model |
| CN109389556A (en) * | 2018-09-21 | 2019-02-26 | 五邑大学 | The multiple dimensioned empty convolutional neural networks ultra-resolution ratio reconstructing method of one kind and device |
| CN109493333A (en) * | 2018-11-08 | 2019-03-19 | 四川大学 | Ultrasonic Calcification in Thyroid Node point extraction algorithm based on convolutional neural networks |
| CN109598269A (en) * | 2018-11-14 | 2019-04-09 | 天津大学 | A kind of semantic segmentation method based on multiresolution input with pyramid expansion convolution |
| CN110020606A (en) * | 2019-03-13 | 2019-07-16 | 北京工业大学 | A kind of crowd density estimation method based on multiple dimensioned convolutional neural networks |
| CN110047069A (en) * | 2019-04-22 | 2019-07-23 | 北京青燕祥云科技有限公司 | A kind of image detection device |
| CN110059730A (en) * | 2019-03-27 | 2019-07-26 | 天津大学 | A kind of thyroid nodule ultrasound image classification method based on capsule network |
| CN110197468A (en) * | 2019-06-06 | 2019-09-03 | 天津工业大学 | A kind of single image Super-resolution Reconstruction algorithm based on multiple dimensioned residual error learning network |
| CN110276721A (en) * | 2019-04-28 | 2019-09-24 | 天津大学 | Image super-resolution rebuilding method based on cascade residual error convolutional neural networks |
| CN110309880A (en) * | 2019-07-01 | 2019-10-08 | 天津工业大学 | A kind of 5 days and 9 days hatching egg embryo's image classification methods based on attention mechanism CNN |
| CN110363134A (en) * | 2019-07-10 | 2019-10-22 | 电子科技大学 | A kind of face blocked area localization method based on semantic segmentation |
| KR20190119261A (en) * | 2018-04-12 | 2019-10-22 | 가천대학교 산학협력단 | Apparatus and method for segmenting of semantic image using fully convolutional neural network based on multi scale image and multi scale dilated convolution |
| CN110415170A (en) * | 2019-06-24 | 2019-11-05 | 武汉大学 | A kind of image super-resolution method based on multiple dimensioned attention convolutional neural networks |
-
2019
- 2019-12-12 CN CN201911271119.1A patent/CN111160413B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610194A (en) * | 2017-08-14 | 2018-01-19 | 成都大学 | MRI super resolution ratio reconstruction method based on Multiscale Fusion CNN |
| CN107680678A (en) * | 2017-10-18 | 2018-02-09 | 北京航空航天大学 | Based on multiple dimensioned convolutional neural networks Thyroid ultrasound image tubercle auto-check system |
| CN108010013A (en) * | 2017-11-03 | 2018-05-08 | 天津大学 | A kind of lung CT image pulmonary nodule detection methods |
| CN108537731A (en) * | 2017-12-29 | 2018-09-14 | 西安电子科技大学 | Image super-resolution rebuilding method based on compression multi-scale feature fusion network |
| CN108268870A (en) * | 2018-01-29 | 2018-07-10 | 重庆理工大学 | Multi-scale feature fusion ultrasonoscopy semantic segmentation method based on confrontation study |
| KR20190119261A (en) * | 2018-04-12 | 2019-10-22 | 가천대학교 산학협력단 | Apparatus and method for segmenting of semantic image using fully convolutional neural network based on multi scale image and multi scale dilated convolution |
| CN108734659A (en) * | 2018-05-17 | 2018-11-02 | 华中科技大学 | A kind of sub-pix convolved image super resolution ratio reconstruction method based on multiple dimensioned label |
| CN108734660A (en) * | 2018-05-25 | 2018-11-02 | 上海通途半导体科技有限公司 | A kind of image super-resolution rebuilding method and device based on deep learning |
| CN109165667A (en) * | 2018-07-06 | 2019-01-08 | 中国科学院自动化研究所 | Based on the cerebral disease categorizing system from attention mechanism |
| CN109064405A (en) * | 2018-08-23 | 2018-12-21 | 武汉嫦娥医学抗衰机器人股份有限公司 | A kind of multi-scale image super-resolution method based on dual path network |
| CN109242839A (en) * | 2018-08-29 | 2019-01-18 | 上海市肺科医院 | A kind of good pernicious classification method of CT images Lung neoplasm based on new neural network model |
| CN109389556A (en) * | 2018-09-21 | 2019-02-26 | 五邑大学 | The multiple dimensioned empty convolutional neural networks ultra-resolution ratio reconstructing method of one kind and device |
| CN109493333A (en) * | 2018-11-08 | 2019-03-19 | 四川大学 | Ultrasonic Calcification in Thyroid Node point extraction algorithm based on convolutional neural networks |
| CN109598269A (en) * | 2018-11-14 | 2019-04-09 | 天津大学 | A kind of semantic segmentation method based on multiresolution input with pyramid expansion convolution |
| CN110020606A (en) * | 2019-03-13 | 2019-07-16 | 北京工业大学 | A kind of crowd density estimation method based on multiple dimensioned convolutional neural networks |
| CN110059730A (en) * | 2019-03-27 | 2019-07-26 | 天津大学 | A kind of thyroid nodule ultrasound image classification method based on capsule network |
| CN110047069A (en) * | 2019-04-22 | 2019-07-23 | 北京青燕祥云科技有限公司 | A kind of image detection device |
| CN110276721A (en) * | 2019-04-28 | 2019-09-24 | 天津大学 | Image super-resolution rebuilding method based on cascade residual error convolutional neural networks |
| CN110197468A (en) * | 2019-06-06 | 2019-09-03 | 天津工业大学 | A kind of single image Super-resolution Reconstruction algorithm based on multiple dimensioned residual error learning network |
| CN110415170A (en) * | 2019-06-24 | 2019-11-05 | 武汉大学 | A kind of image super-resolution method based on multiple dimensioned attention convolutional neural networks |
| CN110309880A (en) * | 2019-07-01 | 2019-10-08 | 天津工业大学 | A kind of 5 days and 9 days hatching egg embryo's image classification methods based on attention mechanism CNN |
| CN110363134A (en) * | 2019-07-10 | 2019-10-22 | 电子科技大学 | A kind of face blocked area localization method based on semantic segmentation |
Non-Patent Citations (2)
| Title |
|---|
| LI XUEWEI: "Fully Convolutional Networks for Ultrasound Image Segmentation of Thyroid Nodules" * |
| 王昊;彭博;陈琴;杨燕;: "基于多尺度融合的甲状腺结节图像特征提取", 数据采集与处理, no. 05 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724343A (en) * | 2020-05-18 | 2020-09-29 | 天津大学 | Thyroid nodule ultrasonic image data set enhancing method based on antagonistic learning |
| CN112785586A (en) * | 2021-02-04 | 2021-05-11 | 天津大学 | Multi-scale self-attention unsupervised domain self-adaptive algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111160413B (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886273B (en) | CMR image segmentation and classification system | |
| CN108446730B (en) | CT pulmonary nodule detection device based on deep learning | |
| Chen et al. | Transattunet: Multi-level attention-guided u-net with transformer for medical image segmentation | |
| CN109670510B (en) | Deep learning-based gastroscope biopsy pathological data screening system | |
| CN112489061B (en) | Deep learning intestinal polyp segmentation method based on multi-scale information and parallel attention mechanism | |
| CN101403743B (en) | Automatic separating method for X type overlapping and adhering chromosome | |
| CN112508850B (en) | Deep learning-based method for detecting malignant area of thyroid cell pathological section | |
| CN108305253B (en) | Pathological image classification method based on multiple-time rate deep learning | |
| CN111951246B (en) | Multidirectional X-ray chest radiography pneumonia diagnosis method based on deep learning | |
| CN108305241B (en) | SD-OCT image GA lesion segmentation method based on depth voting model | |
| Ding et al. | A lightweight U-Net architecture multi-scale convolutional network for pediatric hand bone segmentation in X-ray image | |
| CN109949297B (en) | Lung nodule detection method based on recection and fast R-CNN | |
| CN113768519B (en) | Method for analyzing consciousness level of patient based on deep learning and resting state electroencephalogram data | |
| CN111160413A (en) | Thyroid nodule classification method based on multi-scale feature fusion | |
| CN116030306A (en) | Pulmonary tissue pathology image type auxiliary classification method based on multilayer perceptron | |
| CN114372962A (en) | Laparoscopic surgery stage identification method and system based on double-particle time convolution | |
| CN113538435A (en) | Pancreatic cancer pathological image classification method and system based on deep learning | |
| CN114187181A (en) | Double-path lung CT image super-resolution method based on residual information refining | |
| Yang et al. | Ultrasound image-based diagnosis of cirrhosis with an end-to-end deep learning model | |
| CN117237269A (en) | Lung CT anomaly detection method based on multi-scale clipping and self-supervision reconstruction | |
| Liu et al. | Multi-task learning improves the brain stoke lesion segmentation | |
| CN115222637A (en) | Multi-modal medical image fusion method based on global optimization model | |
| CN114022494A (en) | Automatic segmentation method of traditional Chinese medicine tongue image based on light convolutional neural network and knowledge distillation | |
| CN113920108A (en) | Training method for training U-Net model for processing cell image | |
| Sharma et al. | Keyframe selection from colonoscopy videos to enhance visualization for polyp detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |