CN105913075A - Endoscopic image focus identification method based on pulse coupling nerve network - Google Patents
Endoscopic image focus identification method based on pulse coupling nerve network Download PDFInfo
- Publication number
- CN105913075A CN105913075A CN201610207950.0A CN201610207950A CN105913075A CN 105913075 A CN105913075 A CN 105913075A CN 201610207950 A CN201610207950 A CN 201610207950A CN 105913075 A CN105913075 A CN 105913075A
- Authority
- CN
- China
- Prior art keywords
- input
- focus
- image
- vector
- icm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F18/211—Selection of the most significant subset of features
- G06F18/2111—Selection of the most significant subset of features by using evolutionary computational techniques, e.g. genetic algorithms
Abstract
The invention relates to an endoscopic image focus identification method based on the pulse coupling nerve network. The method comprises steps of video framing, image preprocessing, visual-perception-oriented color space conversion, suspected focus area positioning, characteristic vector construction, mode identification through employing the pulse coupling nerve network, area transfer, accomplishment of all-suspected-focus identification, focus image classification extraction and repetition of all the steps till accomplishment of identification of endoscopic images of a whole video file. Through the method, on the basis of focus area positioning of the human visual attention mechanism and the pulse coupling nerve network, mode identification is carried out, focus mode identification accuracy is improved, focus mode endoscopic image extraction accuracy is further improved, and workload of clinical doctors is reduced.
Description
Technical field
The present invention relates to medical image pattern recognition analysis field, peep detection particularly in a kind of human gastrointestinal tract
The lesion image mode identification method of system.
Background technology
Digestive tract disease threatens the health of the mankind increasingly severely, and the disease of other numerous species all may be used simultaneously
Directly or indirectly can be caused by the disease of gi system, the inspection of digestive tract disease and the diagnosis health to the mankind
Situation has very important meaning.Detection digestive tract disease the best way is exactly directly to observe gastrointestinal tract, institute
It is the most effective method with endoscope.But traditional plug-in type endoscope such as intestinal mirror, gastroscope etc., by
Intestinal cannot be goed deep in the reason being mechanically inserted, make small intestine become check frequency, be inserted simultaneously into formula endoscope
In-convenience in use, pain can be brought to patient, and have the danger of intestinal perforation.Along with semiconductor technology, sensing
Technology, LED illumination technology, radio communication and the development of Micro-control Technology, going out for Wireless capsule endoscope
Now lay a good foundation with universal.Wireless capsule endoscope is by miniature image sensor, lighting module, wireless transmit
Module, power management module etc. form.Patient swallow after under human gastrointestinal tract creeping effect capsule endoscope suitable
Digestion intestinal to move downward.In motor process, the bell glass of capsule front end struts intestinal and is close to intestinal wall,
Lighting module illuminates the intestinal wall in visual field, and imageing sensor obtains the figure of intestinal inwall by short-focus lens simultaneously
Picture, and view data is launched external.Gastrointestinal tract image is spread out of external by capsule endoscope constantly, until
Human body is naturally drained by anus.Whole process without manual intervention, will not for patient bring any pain with not
Just, and there is not check frequency, it is achieved that painless noinvasive all-digestive tract detect.Just because of these advantage glue
Capsule endoscope is applied more and more as a kind of novel digestive tract detection technique in clinic.
The capsule endoscope working time in human body is about 8 hours, when suffering from people's metabolism of gastroenteropathy
Between can longer, so one-time detection will produce at least 2 × 3600 × 8=57600 two field picture.In such enormous quantity
Video image in find focus or pathological characters be the work taken time and effort very much, even experienced
Expert the most at least to spend time of 2 hours.This not only loses time, and owing to visual fatigue there will be
The situation of missing inspection.So utilizing image processing and pattern recognition to realize the hemorrhage image recognition of computer intelligence it is
The trend of one certainty.Owing to endoscopic picture is human body alimentary canal image, situation is extremely complex, and focus feature is also
Changeable, use conventional Digital Image Processing and algorithm for pattern recognition to be difficult to deal with complicated endoscopic picture and changeable
Focus.Pulse Coupled Neural Network comes from the working mechanism that mammalian visual is neural, relative to traditional
The neural network models such as BP, RBF, this model has inherent innate advantage in image processing field,
And in certain applications, shown advantage, focus Intelligent Recognition has huge applications potentiality.
Existing all concentrate on capsule endoscope detection body for peeping detection technique in human gastrointestinal tract, and sick
The process of stove image relatively lags behind with pattern identification research, it has also become the restriction bottle of capsule endoscope detecting system
Neck.And image focus identification technology all concentrates in the pattern knowledge of concrete focus, but due to the polytropy of focus,
Even its feature of same kind of focus is the most changeable.And the Digital Image Processing of routine and pattern recognition
Algorithm is also difficult to tackle the endoscopic picture that content is complicated, causes recognition methods specificity and sensitivity the highest.
Summary of the invention
The difficult problem extracted to overcome existing focus pattern to be difficult to, the present invention is based on Pulse Coupled Neural Network
With the localization method of vision noticing mechanism, the particular type of focus will not differentiated between, it is provided that a kind of based on pulse coupling
Closing focus recognition methods in the endoscopic picture of neutral net, endoscopic picture can be categorized as normally by the method exactly
Pattern and focus pattern, and the endoscopic picture focal area of identification is marked does further for clinician
Judge, reduce the workload of clinician.
The technical scheme provided to solve above-mentioned technical problem is:
Focus recognition methods in a kind of endoscopic picture based on Pulse Coupled Neural Network, described recognition methods includes
Following steps:
A. video framing
Peeping detection video file input by interior, framing obtains the single width endoscopic picture of bitmap format;
B. Image semantic classification
By the bitmap images obtained by step a by the visual field parameter of endoscope by smooth for the edge black surround of image place
Reason, obtains sharply marginated endoscopic picture, then uses high pass filter (such as Bart irrigates husband's high pass filter)
Filtering and noise reduction, then use median filter to be filtered strengthening, remove the noise of pending image-region and retain
Image HFS;
C. towards the color space conversion of visually-perceptible
The bitmap images obtained in step b is device oriented RGB color, converts it to towards vision
The Luv color space of perception;
D. suspected abnormality zone location
U, v component of the Luv color space image obtained using step c, as input, calculates color characteristic notable
(c, s), (c s), then uses Laplce to figure uv significantly to scheme L using L * component as input calculating brightness
Mapping algorithm and virtually connect method, obtains the border area of notable content in image, and calculating contour feature is significantly schemed
(c, s) (c, s), obtained color characteristic is significantly schemed uv, and (c, s), brightness is special with the notable T of textural characteristics figure for O
Levy and significantly scheme L (c, s), contour feature significantly schemes O, and (c s) significantly schemes T with textural characteristics (c, s) respectively multiple dimensioned
Under carry out regularization computing and merge, obtain the saliency map S of image, then use etching algorithm to filter out face
Long-pending less marking area, then according to order arrangement the significance degree, i.e. suspected abnormality of region area size
Region;
E. structural feature vector
With the notable figure S obtained by step d for input, construct in suspected abnormality region pixel color feature to
Amount V (uv) and brightness vector V (L), calculate and structure realm Outline Feature Vector V (O) texture feature vector
V(T);
F. focal area carries out pattern recognition
Using the characteristic vector constructed by step e as input, Pulse Coupled Neural Network is used to carry out pattern recognition,
Obtain the focus pattern of suspicious region to be identified, i.e. normal mode and focus pattern;
G. zone-transfer
It is identified respectively according to the order of suspected abnormality area size in image, if also having other suspected abnormality
Region, repetition step e, f carry out pattern recognition, until all suspected abnormality region recognition terminate;
H. lesion image classification is extracted
The model results in suspected abnormality regions all in endoscopic picture is carried out or computing, obtains this width endoscopic picture
Classification mode, i.e. image normal mode and image focus pattern, if focus mode flag focal area;
I. step b, c, d, e, f, g, h are repeated, until the endoscopic picture end of identification of whole video file.
Further, in described step e, in endoscopic picture significantly schemes the marking area of S, construct pixel color
Characteristic vector V ' (uv) and brightness vector V ' (L), be then mapped to higher-dimension by Sigmoid kernel function empty
Between, use the method for principal component analysis (PCA) to extract the core principle component feature of characteristic, obtain dimensionality reduction
Color feature vector V (uv) and brightness vector V (L), calculate and structure realm profile in region meanwhile
Characteristic vector V (O) texture feature vector V (T), sets up eigenmatrix, carries out the pattern recognition of focus.
Further, in described step f, Pulse Coupled Neural Network is by input layer, the cortex model (ICM) that intersects
Neuronal layers, competition output layer composition;
Described input layer is inputted by color characteristic, brightness inputs, contour feature inputs, textural characteristics input
Totally four input channels, intersect cortex model neuronal layers use four ICM neurons, competition output layer by
Competition neurons weight matrix LW and competitive function C composition;
Color characteristic input, brightness input channel and No. 1 ICM of ICM neuronal layers of described input layer
Neuron input connects, contour feature input, textural characteristics input channel and No. 2 ICM of ICM neuronal layers
Neuron input connects, and No. 1 and No. 2 ICM neurons input mutual with No. 3 and No. 4 ICM neurons respectively
Connect, No. 3, No. 4 ICM neurons input with the competition neurons weight matrix LW of competition output layer and be connected,
The output of competition neurons weight matrix LW is connected with competition layer neuron competitive function C input;
Further, described ICM neuron includes two coupled oscillators, connects weighting coefficient matrix and sets
It is set to W.
Described competition neurons weight matrix LW is 2 n dimensional vector ns, and only one of which element is 1 simultaneously, and other is all
It is 0, and, competition layer neuron competitive function uses Gaussian function, exports the vector of one 2 dimension, wherein
The element that pattern class of likelihood probability maximum is corresponding is arranged to 1, and other is all 0,1 position occurred
Put the classification that would indicate that input feature vector matrix is identified, i.e. normal mode or focus pattern.
Compared with prior art, the invention has the beneficial effects as follows:
1, the endoscopic picture of the present invention have employed in focus mode identification method and doubt based on human visual attention mechanism
Positioning like focal area, this location will greatly reduce the amount of calculation of artificial neural network, Jin Erti in endoscopic picture
The accuracy of focus pattern recognition in high endoscopic picture.
2, the image processing method of the present invention is at the color Luv space of view-based access control model perception, at utmost land productivity
With the colouring information of endoscopic picture, and colouring information is the important information of focal area diagnosis, improves focus
Accuracy that region determines and specificity.
3, the mode identification method of the present invention does not differentiates between the particular type of focus, is focus mould by all territorial classifications
Formula and normal mode, and use Pulse Coupled Neural Network, in the endoscopic picture standard of focus identification will be greatly improved
Really property and practicality, reduces the workload of clinician.
Accompanying drawing explanation
Fig. 1 is the focus recognition methods flow chart based on Pulse Coupled Neural Network of the present invention.
Fig. 2 is the structure chart of Pulse Coupled Neural Network.
Fig. 3 is ICM neuronal structure figure.
Detailed description of the invention
Below in conjunction with the accompanying drawings embodiments of the invention are elaborated.
With reference to Fig. 1~Fig. 3, focus recognition methods in a kind of endoscopic picture based on Pulse Coupled Neural Network, bag
Include following steps:
A. video framing
Use the detection video file of the capsule endoscope detecting system of Given company, by endoscope check video
Input, framing obtains the single width endoscopic picture of bitmap format;
B. Image semantic classification
By the bitmap images obtained by step a by the visual field parameter of endoscope by smooth for the edge black surround of image place
Reason, obtains sharply marginated endoscopic picture, then uses Bart to irrigate husband's high pass filter filters and uses intermediate value to filter again
Ripple device is filtered, and removes the noise of pending image-region and retains image HFS;
C. towards the color space conversion of visually-perceptible
The bitmap images obtained in step b is device oriented RGB color, converts it to towards vision
The Luv color space of perception;
D. suspected abnormality zone location
U, v component of the Luv color space image obtained using step c, as input, calculates color characteristic notable
(c, s), (c s), then uses Laplce to figure uv significantly to scheme L using L * component as input calculating brightness
Mapping algorithm and virtually connect method, obtains the border area of notable content in image, and calculating contour feature is significantly schemed
(c, s) (c, s), obtained color characteristic is significantly schemed uv, and (c, s), brightness is special with the notable T of textural characteristics figure for O
Levy and significantly scheme L (c, s), contour feature significantly schemes O, and (c s) significantly schemes T with textural characteristics (c, s) respectively multiple dimensioned
Under carry out regularization computing and merge, obtain the saliency map S of image, then use etching algorithm to filter out face
Long-pending less marking area, then according to order arrangement the significance degree, i.e. suspected abnormality of region area size
Region;
E. structural feature vector
With the notable figure S obtained by step d for input, construct in suspected abnormality region pixel color feature to
Amount V (uv) and brightness vector V (L), calculate and structure realm Outline Feature Vector V (O) texture feature vector
V(T);
F. focal area carries out pattern recognition
Using the characteristic vector constructed by step e as input, Pulse Coupled Neural Network is used to carry out pattern recognition,
Obtain the focus pattern of suspicious region to be identified, i.e. normal mode and focus pattern;
G. zone-transfer
It is identified respectively according to the order of suspected abnormality area size in image, if also having other suspected abnormality
Region, repetition step e, f carry out pattern recognition, until all suspected abnormality region recognition terminate;
H. lesion image classification is extracted
The model results in suspected abnormality regions all in endoscopic picture is carried out or computing, obtains this width endoscopic picture
Classification mode, i.e. image normal mode and image focus pattern, if focus mode flag focal area;
I. step b, c, d, e, f, g, h are repeated, until the endoscopic picture end of identification of whole video file.
Further, in described step e, in endoscopic picture significantly schemes the marking area of S, construct pixel color
Characteristic vector V ' (uv) and brightness vector V ' (L), be then mapped to higher-dimension by Sigmoid kernel function empty
Between, use the method for principal component analysis (PCA) to extract the core principle component feature of characteristic, obtain dimensionality reduction
Color feature vector V (uv) and brightness vector V (L), calculate and structure realm profile in region meanwhile
Characteristic vector V (O) texture feature vector V (T), sets up eigenmatrix, carries out the pattern recognition of focus.
Further, in described step f, Pulse Coupled Neural Network is by input layer, the cortex model (ICM) that intersects
Neuronal layers, competition output layer composition;
Described input layer is inputted by color characteristic, brightness inputs, contour feature inputs, textural characteristics input
Totally four input channels, ICM neuronal layers uses four ICM neurons, and competition output layer is by competition neurons
Weight matrix LW and competitive function C composition;
Color characteristic input, brightness input channel and No. 1 ICM of ICM neuronal layers of described input layer
Neuron input connects, contour feature input, textural characteristics input channel and No. 2 ICM of ICM neuronal layers
Neuron input connects, and No. 1 and No. 2 ICM neurons input mutual with No. 3 and No. 4 ICM neurons respectively
Connect, No. 3, No. 4 ICM neurons input with the competition neurons weight matrix LW of competition output layer and be connected,
The output of competition neurons weight matrix LW is connected with competition layer neuron competitive function C input;
Further, described ICM neuron includes two coupled oscillators, connects weighting coefficient matrix and arranges
For W.
Described competition neurons weight matrix LW is 2 n dimensional vector ns, and only one of which element is 1 simultaneously, and other is all
It is 0, and, competition layer neuron competitive function uses Gaussian function, exports the vector of one 2 dimension, wherein
The element that pattern class of likelihood probability maximum is corresponding is arranged to 1, and other is all 0,1 position occurred
Put the classification that would indicate that input feature vector matrix is identified, i.e. normal mode or focus pattern.
Finally, in addition it is also necessary to be only the specific embodiment of the present invention it is noted that listed above.Obviously,
The invention is not restricted to above example, it is also possible to have many deformation.Those of ordinary skill in the art can be from this
All deformation that bright disclosure directly derives or associates, are all considered as protection scope of the present invention.
Claims (5)
1. focus recognition methods in an endoscopic picture based on Pulse Coupled Neural Network, it is characterised in that: described
Recognition methods comprises the steps:
A. video framing
Peeping detection video file input by interior, framing obtains the single width endoscopic picture of bitmap format;
B. Image semantic classification
By the bitmap images obtained by step a by the visual field parameter of endoscope by smooth for the edge black surround of image place
Reason, obtains sharply marginated endoscopic picture, then uses high pass filter filters denoising, then use medium filtering
Device is filtered strengthening, and removes the noise of pending image-region and retains image HFS;
C. towards the color space conversion of visually-perceptible
The bitmap images obtained in step b is device oriented RGB color, converts it to towards vision
The Luv color space of perception;
D. suspected abnormality zone location
U, v component of the Luv color space image obtained using step c, as input, calculates color characteristic notable
(c, s), (c s), then uses Laplce to figure uv significantly to scheme L using L * component as input calculating brightness
Mapping algorithm and virtually connect method, obtains the border area of notable content in image, and calculating contour feature is significantly schemed
(c, s) (c, s), obtained color characteristic is significantly schemed uv, and (c, s), brightness is special with the notable T of textural characteristics figure for O
Levy and significantly scheme L (c, s), contour feature significantly schemes O, and (c s) significantly schemes T with textural characteristics (c, s) respectively multiple dimensioned
Under carry out regularization computing and merge, obtain the saliency map S of image, then use etching algorithm to filter out face
Long-pending less marking area, then according to order arrangement the significance degree, i.e. suspected abnormality of region area size
Region;
E. structural feature vector
With the notable figure S obtained by step d for input, construct in suspected abnormality region pixel color feature to
Amount V (uv) and brightness vector V (L), calculate and structure realm Outline Feature Vector V (O) texture feature vector
V(T);
F. focal area carries out pattern recognition
Using the characteristic vector constructed by step e as input, Pulse Coupled Neural Network is used to carry out pattern recognition,
Obtain the focus pattern of suspicious region to be identified, i.e. normal mode and focus pattern;
G. zone-transfer
It is identified respectively according to the order of suspected abnormality area size in image, if also having other suspected abnormality
Region, repetition step e, f carry out pattern recognition, until all suspected abnormality region recognition terminate;
H. lesion image classification is extracted
The model results in suspected abnormality regions all in endoscopic picture is carried out or computing, obtains this width endoscopic picture
Classification mode, i.e. image normal mode and image focus pattern, if focus mode flag focal area;
I. step b, c, d, e, f, g, h are repeated, until the endoscopic picture end of identification of whole video file.
2. focus recognition methods in endoscopic picture based on Pulse Coupled Neural Network as claimed in claim 1, its
It is characterised by: in described step e, in endoscopic picture significantly schemes the marking area of S, constructs preliminary pixel face
Color characteristic vector V ' (uv) and preliminary brightness vector V ' (L), be then mapped to height by Sigmoid kernel function
Dimension space, uses the method for principal component analysis to extract the core principle component feature of characteristic, obtains the color of dimensionality reduction
Characteristic vector V (uv) and brightness vector V (L), calculate and structure realm contour feature in region meanwhile
Vector V (O) texture feature vector V (T), sets up eigenmatrix, carries out the pattern recognition of focus.
3. focus recognition methods in endoscopic picture based on Pulse Coupled Neural Network as claimed in claim 1 or 2,
It is characterized in that: in described step f, Pulse Coupled Neural Network is by input layer, the cortex model neuron that intersects
Layer and competition output layer composition;
Described input layer is inputted by color characteristic, brightness inputs, contour feature inputs, textural characteristics input
Totally four input channels, intersect cortex model neuronal layers use four ICM neurons, competition output layer by
Competition neurons weight matrix LW and competitive function C composition;
Color characteristic input, brightness input channel and No. 1 ICM nerve of neuronal layers of described input layer
Unit's input connects, the input of described contour feature, textural characteristics input channel and No. 2 ICM nerves of neuronal layers
Unit's input connects, and No. 1 and No. 2 ICM neurons input be connected with each other with No. 3 and No. 4 ICM neurons respectively,
No. 3, No. 4 ICM neurons is connected with the competition neurons weight matrix LW input of competition output layer, compete
The output of neuron weight matrix LW is connected with the input of competition layer neuron competitive function C.
4. focus recognition methods in endoscopic picture based on Pulse Coupled Neural Network as claimed in claim 3, its
It is characterised by: described ICM neuron includes two coupled oscillators, connects weighting coefficient matrix and be set to W.
5. focus recognition methods in endoscopic picture based on Pulse Coupled Neural Network as claimed in claim 3, its
It is characterised by: described competition neurons weight matrix LW is 2 n dimensional vector ns, and only one of which element is 1 simultaneously,
Other is all 0, and, competition layer neuron competitive function C uses Gaussian function, export one 2 dimension to
Amount, the element that wherein that pattern class of likelihood probability maximum is corresponding is arranged to 1, and other is all 0,1 institute
The position occurred would indicate that the classification that input feature vector matrix is identified, i.e. normal mode or focus pattern.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610207950.0A CN105913075A (en) | 2016-04-05 | 2016-04-05 | Endoscopic image focus identification method based on pulse coupling nerve network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610207950.0A CN105913075A (en) | 2016-04-05 | 2016-04-05 | Endoscopic image focus identification method based on pulse coupling nerve network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105913075A true CN105913075A (en) | 2016-08-31 |
Family
ID=56745336
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610207950.0A Pending CN105913075A (en) | 2016-04-05 | 2016-04-05 | Endoscopic image focus identification method based on pulse coupling nerve network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105913075A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107274428A (en) * | 2017-08-03 | 2017-10-20 | 汕头市超声仪器研究所有限公司 | Multi-target three-dimensional ultrasonic image partition method based on emulation and measured data |
CN107705852A (en) * | 2017-12-06 | 2018-02-16 | 北京华信佳音医疗科技发展有限责任公司 | Real-time the lesion intelligent identification Method and device of a kind of medical electronic endoscope |
CN109241898A (en) * | 2018-08-29 | 2019-01-18 | 合肥工业大学 | Object localization method and system, the storage medium of hysteroscope video |
CN109411084A (en) * | 2018-11-28 | 2019-03-01 | 武汉大学人民医院(湖北省人民医院) | A kind of intestinal tuberculosis assistant diagnosis system and method based on deep learning |
CN110706220A (en) * | 2019-09-27 | 2020-01-17 | 贵州大学 | Capsule endoscope image processing and analyzing method |
CN110706225A (en) * | 2019-10-14 | 2020-01-17 | 山东省肿瘤防治研究院(山东省肿瘤医院) | Tumor identification system based on artificial intelligence |
CN110705440A (en) * | 2019-09-27 | 2020-01-17 | 贵州大学 | Capsule endoscopy image recognition model based on neural network feature fusion |
CN110910325A (en) * | 2019-11-22 | 2020-03-24 | 深圳信息职业技术学院 | Medical image processing method and device based on artificial butterfly optimization algorithm |
CN111507454A (en) * | 2019-01-30 | 2020-08-07 | 兰州交通大学 | Improved cross cortical neural network model for remote sensing image fusion |
CN111784683A (en) * | 2020-07-10 | 2020-10-16 | 天津大学 | Pathological section detection method and device, computer equipment and storage medium |
CN112184837A (en) * | 2020-09-30 | 2021-01-05 | 百度(中国)有限公司 | Image detection method and device, electronic equipment and storage medium |
CN113920042A (en) * | 2021-09-24 | 2022-01-11 | 深圳市资福医疗技术有限公司 | Image processing system and capsule endoscope |
CN114240941A (en) * | 2022-02-25 | 2022-03-25 | 浙江华诺康科技有限公司 | Endoscope image noise reduction method, device, electronic apparatus, and storage medium |
CN115798725A (en) * | 2022-10-27 | 2023-03-14 | 佛山读图科技有限公司 | Method for making lesion-containing human body simulation image data for nuclear medicine |
-
2016
- 2016-04-05 CN CN201610207950.0A patent/CN105913075A/en active Pending
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107274428A (en) * | 2017-08-03 | 2017-10-20 | 汕头市超声仪器研究所有限公司 | Multi-target three-dimensional ultrasonic image partition method based on emulation and measured data |
WO2019023819A1 (en) * | 2017-08-03 | 2019-02-07 | 汕头市超声仪器研究所有限公司 | Simulated and measured data-based multi-target three-dimensional ultrasound image segmentation method |
US11282204B2 (en) | 2017-08-03 | 2022-03-22 | Shantou Institute Of Ultrasonic Instruments Co., Ltd. | Simulated and measured data-based multi-target three-dimensional ultrasound image segmentation method |
CN107705852A (en) * | 2017-12-06 | 2018-02-16 | 北京华信佳音医疗科技发展有限责任公司 | Real-time the lesion intelligent identification Method and device of a kind of medical electronic endoscope |
CN109241898A (en) * | 2018-08-29 | 2019-01-18 | 合肥工业大学 | Object localization method and system, the storage medium of hysteroscope video |
CN109241898B (en) * | 2018-08-29 | 2020-09-22 | 合肥工业大学 | Method and system for positioning target of endoscopic video and storage medium |
CN109411084A (en) * | 2018-11-28 | 2019-03-01 | 武汉大学人民医院(湖北省人民医院) | A kind of intestinal tuberculosis assistant diagnosis system and method based on deep learning |
CN111507454A (en) * | 2019-01-30 | 2020-08-07 | 兰州交通大学 | Improved cross cortical neural network model for remote sensing image fusion |
CN111507454B (en) * | 2019-01-30 | 2022-09-06 | 兰州交通大学 | Improved cross cortical neural network model for remote sensing image fusion |
CN110706220A (en) * | 2019-09-27 | 2020-01-17 | 贵州大学 | Capsule endoscope image processing and analyzing method |
CN110705440A (en) * | 2019-09-27 | 2020-01-17 | 贵州大学 | Capsule endoscopy image recognition model based on neural network feature fusion |
CN110706220B (en) * | 2019-09-27 | 2023-04-18 | 贵州大学 | Capsule endoscope image processing and analyzing method |
CN110705440B (en) * | 2019-09-27 | 2022-11-01 | 贵州大学 | Capsule endoscopy image recognition model based on neural network feature fusion |
CN110706225A (en) * | 2019-10-14 | 2020-01-17 | 山东省肿瘤防治研究院(山东省肿瘤医院) | Tumor identification system based on artificial intelligence |
CN110910325A (en) * | 2019-11-22 | 2020-03-24 | 深圳信息职业技术学院 | Medical image processing method and device based on artificial butterfly optimization algorithm |
CN111784683B (en) * | 2020-07-10 | 2022-05-17 | 天津大学 | Pathological section detection method and device, computer equipment and storage medium |
CN111784683A (en) * | 2020-07-10 | 2020-10-16 | 天津大学 | Pathological section detection method and device, computer equipment and storage medium |
CN112184837A (en) * | 2020-09-30 | 2021-01-05 | 百度(中国)有限公司 | Image detection method and device, electronic equipment and storage medium |
CN113920042A (en) * | 2021-09-24 | 2022-01-11 | 深圳市资福医疗技术有限公司 | Image processing system and capsule endoscope |
CN113920042B (en) * | 2021-09-24 | 2023-04-18 | 深圳市资福医疗技术有限公司 | Image processing system and capsule endoscope |
CN114240941A (en) * | 2022-02-25 | 2022-03-25 | 浙江华诺康科技有限公司 | Endoscope image noise reduction method, device, electronic apparatus, and storage medium |
CN114240941B (en) * | 2022-02-25 | 2022-05-31 | 浙江华诺康科技有限公司 | Endoscope image noise reduction method, device, electronic apparatus, and storage medium |
CN115798725A (en) * | 2022-10-27 | 2023-03-14 | 佛山读图科技有限公司 | Method for making lesion-containing human body simulation image data for nuclear medicine |
CN115798725B (en) * | 2022-10-27 | 2024-03-26 | 佛山读图科技有限公司 | Method for manufacturing human body simulation image data with lesion for nuclear medicine |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105913075A (en) | Endoscopic image focus identification method based on pulse coupling nerve network | |
CN106934799B (en) | Capsule endoscope visual aids diagosis system and method | |
Shin et al. | Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification | |
Li et al. | Computer-aided detection of bleeding regions for capsule endoscopy images | |
Li et al. | Computer-based detection of bleeding and ulcer in wireless capsule endoscopy images by chromaticity moments | |
EP1997074B1 (en) | Device, system and method for automatic detection of contractile activity in an image frame | |
Li et al. | Computer-aided small bowel tumor detection for capsule endoscopy | |
CN108470359A (en) | A kind of diabetic retinal eye fundus image lesion detection method | |
JP7270626B2 (en) | Medical image processing apparatus, medical image processing system, operating method of medical image processing apparatus, program, and storage medium | |
JP7062068B2 (en) | Image processing method and image processing device | |
Li et al. | Comparison of several texture features for tumor detection in CE images | |
CN109241963B (en) | Adaboost machine learning-based intelligent identification method for bleeding point in capsule gastroscope image | |
Eskandari et al. | Polyp detection in Wireless Capsule Endoscopy images by using region-based active contour model | |
Guan et al. | Segmentation of thermal breast images using convolutional and deconvolutional neural networks | |
US20230377147A1 (en) | Method and system for detecting fundus image based on dynamic weighted attention mechanism | |
Lei et al. | Automated detection of retinopathy of prematurity by deep attention network | |
Xing et al. | A saliency-aware hybrid dense network for bleeding detection in wireless capsule endoscopy images | |
Ghosh et al. | Block based histogram feature extraction method for bleeding detection in wireless capsule endoscopy | |
Ay et al. | Automated classification of nasal polyps in endoscopy video-frames using handcrafted and CNN features | |
Zhuang et al. | APRNet: A 3D anisotropic pyramidal reversible network with multi-modal cross-dimension attention for brain tissue segmentation in MR images | |
AU2021425940A1 (en) | System and method of using right and left eardrum otoscopy images for automated otoscopy image analysis to diagnose ear pathology | |
CN110969603B (en) | Relative positioning method and device for lesion position and terminal equipment | |
CN112419246A (en) | Depth detection network for quantifying esophageal mucosa IPCLs blood vessel morphological distribution | |
Liao et al. | A case study on computer-aided diagnosis of nonerosive reflux disease using deep learning techniques | |
CN115994999A (en) | Goblet cell semantic segmentation method and system based on boundary gradient attention network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160831 |
|
RJ01 | Rejection of invention patent application after publication |