CN113436139A - Small intestine nuclear magnetic resonance image identification and physiological information extraction system and method based on deep learning - Google Patents
Small intestine nuclear magnetic resonance image identification and physiological information extraction system and method based on deep learning Download PDFInfo
- Publication number
- CN113436139A CN113436139A CN202110506227.3A CN202110506227A CN113436139A CN 113436139 A CN113436139 A CN 113436139A CN 202110506227 A CN202110506227 A CN 202110506227A CN 113436139 A CN113436139 A CN 113436139A
- Authority
- CN
- China
- Prior art keywords
- image
- small intestine
- magnetic resonance
- deep learning
- information extraction
- 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
Images
Classifications
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- 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
- 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
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- 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
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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
- G06T2207/30028—Colon; Small intestine
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Artificial Intelligence (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Evolutionary Computation (AREA)
- Surgery (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Mathematical Physics (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Image Processing (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Signal Processing (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention relates to a system and a method for small intestine nuclear magnetic resonance image recognition and physiological information extraction based on deep learning, wherein the system comprises a small intestine nuclear magnetic resonance image, a sample database, an image segmentation module, an image analysis module and a result output module, wherein the small intestine nuclear magnetic resonance image is used for obtaining an original image; the sample database is used for obtaining an identification image; the image segmentation module is used for obtaining a normalized standard size image sequence; the image analysis module is used for obtaining the diameter size of the small intestine in the original image; and the result output module is used for outputting the result of the diameter size and the position information of the small intestine in the original image. The small intestine nuclear magnetic resonance image identification and physiological information extraction system and method based on deep learning provided by the invention realize that pixel-level evaluation indexes are used for evaluating output results, and the accuracy in the small intestine diagnosis process is improved.
Description
Technical Field
The invention relates to the field of computers and medicine, in particular to a system and a method for small intestine nuclear magnetic resonance image recognition and physiological information extraction based on deep learning.
Background
Nowadays, with the rapid development of artificial intelligence, the intelligent medical field is also rapidly developed. The intelligent identification and diagnosis technology based on nuclear magnetic resonance image development is widely applied to the medical field.
The small intestine plays an important role in digesting food and absorbing nutrition. The peristaltic function of the small intestine is essential for mixing, grinding and transporting the intestinal contents. Gastroenterologists often view these motion data to determine whether a patient is at risk for gastrointestinal disease, such as crohn's disease. To assess the peristaltic capacity of the small intestine, there are several radiological methods, such as magnetic resonance imaging. Depending on the observation method, various types of data, typically images, can be generated, which provide rich information about the internal state of the small intestine. Traditional radiologists use these data and manual measurements to assess small bowel motility, which is inefficient. Some researchers have been exploring automated methods that mimic the work of human experts. In recent years, with the development of deep learning, some neural network structures have effectively replicated this work, even beyond the actual radiologist in some medical fields.
Currently, nuclear magnetic resonance images are involved in small intestine disease examination, and there is a certain defect in manual judgment of results: the size, diameter and properties of the small intestine are visually observed, so that the different sizes and properties obtained by doctors with different experiences have different deviations, and real and objective data cannot be accurately obtained. Therefore, it is necessary to use a diagnosis method using a deep learning-based small intestine mri image-assisted treatment.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide a system and a method for small intestine mri image recognition and physiological information extraction based on deep learning, which achieve pixel-level evaluation indexes to evaluate output results and improve accuracy in the small intestine diagnosis process.
In order to achieve the purpose, the invention adopts the following technical scheme:
the utility model provides a small intestine nuclear magnetic resonance image recognition and physiology information extraction system based on deep learning, includes small intestine nuclear magnetic resonance image, sample database, image segmentation module, image analysis module and result output module, wherein:
small intestine nuclear magnetic resonance imaging: the method comprises the steps of acquiring an image of an intestinal tract area to obtain an original image;
a sample database: the method is used for identifying the original image by adopting a supervised learning method to obtain an identified image;
an image segmentation module: the image processing device is used for slicing the identification image to obtain a normalized standard size image sequence;
an image analysis module: the method is used for calculating the diameter size of the small intestine in the original image after performing convolution operation and attention coding and decoding transformation on the standard-size image sequence;
a result output module: and the method is used for outputting the result of the small intestine diameter size and position information in the original image.
Further, the original image is acquired by a nuclear magnetic resonance spectrometer.
Furthermore, the result output module is in signal connection with a display screen and a printer.
The invention also provides a method for small intestine nuclear magnetic resonance image recognition and physiological information extraction based on deep learning, which comprises the following steps:
s100, collecting an original image: acquiring an original image of a small intestine region of a human body through a nuclear magnetic resonance spectrometer, and transmitting the original image to a sample database;
s200, identifying image acquisition: the sample database identifies the original image by adopting a supervised learning method to obtain an identification image, and transmits the obtained identification image to the image segmentation module;
s300, image sequence generation: the image segmentation module is used for carrying out slicing processing on the identification image to obtain a normalized standard-size image sequence and transmitting the generated image sequence to the image analysis module;
s400, image sequence analysis: the image analysis module carries out convolution operation and attention coding and decoding transformation on the standard-size image sequence in sequence, then obtains the diameter size of the small intestine in the original image through principal component regression analysis and calculation, and transmits related data to the result output module;
s500, displaying an analysis result: and the result output module outputs the diameter size and the position information of the small intestine in the original image, displays the result through a display screen and prints and outputs a report result through a printer.
Further, in step S100, before the original image is input into the sample database, the original image is marked with a starting point of interest and a region of interest.
Further, in step S300, the slice processing of the identification image specifically includes the following steps:
s301, dividing the identification image into square subset images with the array size of 20x 20;
s302, turning and shifting operations are applied to each subset image.
Further, in step S400, the convolution operation includes the following steps:
s401, extracting preliminary feature mapping after dynamic convolution;
s402, transforming feature mapping through upsampling;
and S403, adjusting feature mapping through standard convolution to obtain a feature sequence.
Through the technical scheme, the invention has the following effects:
the system provided by the invention is reasonable in structural design, the sample database is utilized for supervised learning, the segmented image sequence is sent to the computing system, the real size of the small intestine is finally calculated, a doctor is assisted in carrying out further diagnosis and treatment, the pixel-level evaluation index can be realized to evaluate an output result, and compared with the manual judgment of the result according to the nuclear magnetic resonance influence, the accuracy in the small intestine diagnosis process is greatly improved.
Drawings
FIG. 1 is a block diagram of the system for small intestine MRI image recognition and physiological information extraction based on deep learning according to the present invention;
FIG. 2 is a block diagram of a flow chart of the method for small intestine magnetic resonance image recognition and physiological information extraction based on deep learning according to the present invention;
FIG. 3 is a schematic diagram of a two-channel image sequence in the method for small intestine magnetic resonance image identification and physiological information extraction based on deep learning according to the present invention;
FIG. 4 is a schematic diagram of convolution in the method for small intestine magnetic resonance image identification and physiological information extraction based on deep learning according to the present invention;
FIG. 5 is a graph showing the evaluation results of the present invention.
Detailed Description
The deep learning-based small intestine mri image recognition and physiological information extraction system and method of the present invention will be described in more detail with reference to the accompanying schematic drawings, which illustrate preferred embodiments of the invention and will be understood by those skilled in the art to which the invention pertains, and to which the advantageous effects of the invention are still implemented. Accordingly, the following description should be construed as broadly as possible to those skilled in the art and not as limiting the invention.
As shown in fig. 1, an embodiment of the present invention provides a system for small intestine nuclear magnetic resonance image recognition and physiological information extraction based on deep learning, including a small intestine nuclear magnetic resonance image, a sample database, an image segmentation module, an image analysis module, and a result output module, where:
small intestine nuclear magnetic resonance imaging: the method comprises the steps of acquiring an image of an intestinal tract area to obtain an original image;
a sample database: the method is used for identifying the original image by adopting a supervised learning method to obtain an identified image;
an image segmentation module: the image processing device is used for slicing the identification image to obtain a normalized standard size image sequence;
an image analysis module: the method is used for calculating the diameter size of the small intestine in the original image after performing convolution operation and attention coding and decoding transformation on the standard-size image sequence;
a result output module: and the method is used for outputting the result of the small intestine diameter size and position information in the original image.
In this embodiment, the raw image is acquired by a nuclear magnetic resonance apparatus. The principle of nuclear magnetic resonance apparatus is that human body is placed in special magnetic field, the radio-frequency pulse is used to excite hydrogen nucleus in human body to make hydrogen nucleus resonate and absorb energy, after the radio-frequency pulse is stopped, the hydrogen nucleus can give out radio-frequency signal according to specific frequency and release the absorbed energy, and can be recorded by external receiver, and processed by electronic computer to obtain image, and the information quantity provided by the image produced by nuclear magnetic resonance is greater than that provided by other imaging operations in medical imaging science, and is different from existent imaging operation, so that it possesses large potential superiority for diagnosing disease.
In this embodiment, the result output module is in signal connection with a display screen and a printer. The display screen and the printer are connected through the signal of the setting result output module, screen display and document printing of the diagnosis report are achieved, and analysis of the report by medical personnel is facilitated.
As shown in fig. 2, an embodiment of the present invention provides a method for small intestine mri image recognition and physiological information extraction based on deep learning, including the following steps:
s100, collecting an original image: acquiring an original image of a small intestine region of a human body through a nuclear magnetic resonance spectrometer, and transmitting the original image to a sample database;
specifically, before an original image is input into a sample database, a doctor needs to mark an interest starting point and an interest area of the original image, aiming at explaining a value target area of the image;
s200, identifying image acquisition: the sample database identifies the original image by adopting a supervised learning method to obtain an identification image, and transmits the obtained identification image to the image segmentation module;
specifically, after the marked original image is input into the sample database, the marked original image and the sample reference image in the sample database are merged and superimposed into a dual-channel image sequence, as shown in fig. 3;
s300, image sequence generation: the image segmentation module is used for carrying out slicing processing on the identification image to obtain a normalized standard-size image sequence and transmitting the generated image sequence to the image analysis module;
the slice processing for identifying the image specifically comprises the following steps:
s301, dividing the identification image into square subset images with the array size of 20x 20;
s302, applying turning and shifting operations to each subset image; and each subset image is subjected to turning and displacement operation, so that the overfitting condition of the image analysis module is eliminated, and the capability of the image analysis module in identifying image characteristics is enhanced.
S400, image sequence analysis: the image analysis module carries out convolution operation and attention coding and decoding transformation on the standard-size image sequence in sequence, then obtains the diameter size of the small intestine in the original image through principal component regression analysis and calculation, and transmits related data to the result output module;
specifically, the purpose of the convolution operation is to extract a necessary feature sequence of an image, and the convolution operation includes the following steps:
s401, extracting preliminary feature mapping after dynamic convolution;
s402, transforming feature mapping through upsampling;
s403, adjusting feature mapping through standard convolution to obtain a feature sequence, as shown in FIG. 4;
the feature sequence obtained by convolution operation is subjected to attention coding and decoding transformation, the scale dependence of the subset sequence is further captured, the correlation between the sequences is better captured by using an attention mechanism, and the image analysis capability of the module and the evaluation accuracy of the small intestine size are greatly improved.
S500, displaying an analysis result: and the result output module outputs the diameter size and the position information of the small intestine in the original image, displays the result through a display screen and prints and outputs a report result through a printer.
Specifically, the display screen displays the analysis result, as shown in fig. 5, and is matched with the report printed by the printer, so that the doctor can refer to and diagnose the disease conveniently.
The specific operation flow of the invention on the computer is as follows:
(1) opening an image annotation tool, clicking a button to select a picture, and clicking to confirm;
(2) marking the area with a mouse and then saving the change;
(3) opening an image analysis system tool, clicking a button to select a picture of a region to be evaluated, and clicking for confirmation;
(4) clicking an image analysis button, and automatically analyzing and evaluating the picture by the tool;
(5) and the tool pops up a dialog box after analysis and clicks for confirmation. The tool will display the results of the analysis for the good size.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (7)
1. The utility model provides a small intestine magnetic resonance image discernment and physiology information extraction system based on degree of deep learning, its characterized in that includes small intestine magnetic resonance image, sample database, image segmentation module, image analysis module and result output module, wherein:
small intestine nuclear magnetic resonance imaging: the method comprises the steps of acquiring an image of an intestinal tract area to obtain an original image;
a sample database: the method is used for identifying the original image by adopting a supervised learning method to obtain an identified image;
an image segmentation module: the image processing device is used for slicing the identification image to obtain a normalized standard size image sequence;
an image analysis module: the method is used for calculating the diameter size of the small intestine in the original image after performing convolution operation and attention coding and decoding transformation on the standard-size image sequence;
a result output module: and the method is used for outputting the result of the small intestine diameter size and position information in the original image.
2. The deep learning-based small intestine mri image recognition and physiological information extraction system according to claim 1, wherein said raw images are acquired by means of an mri scanner.
3. The deep learning-based small intestine magnetic resonance image recognition and physiological information extraction system as claimed in claim 1, wherein the result output module is connected with a display screen and a printer through signals.
4. A method for small intestine magnetic resonance image recognition and physiological information extraction based on deep learning is characterized by comprising the following steps:
s100, collecting an original image: acquiring an original image of a small intestine region of a human body through a nuclear magnetic resonance spectrometer, and transmitting the original image to a sample database;
s200, identifying image acquisition: the sample database identifies the original image by adopting a supervised learning method to obtain an identification image, and transmits the obtained identification image to the image segmentation module;
s300, image sequence generation: the image segmentation module is used for carrying out slicing processing on the identification image to obtain a normalized standard-size image sequence and transmitting the generated image sequence to the image analysis module;
s400, image sequence analysis: the image analysis module carries out convolution operation and attention coding and decoding transformation on the standard-size image sequence in sequence, then obtains the diameter size of the small intestine in the original image through principal component regression analysis and calculation, and transmits related data to the result output module;
s500, displaying an analysis result: and the result output module outputs the diameter size and the position information of the small intestine in the original image, displays the result through a display screen and prints and outputs a report result through a printer.
5. The method for small intestine MRI image recognition and physiological information extraction based on deep learning as claimed in claim 4, wherein in step S100, the original image is marked with the interest starting point and the interest region before being input into the sample database.
6. The method for small intestine magnetic resonance image recognition and physiological information extraction based on deep learning of claim 4, wherein in step S300, the slice processing of the recognition image comprises the following steps:
s301, dividing the identification image into square subset images with the array size of 20x 20;
s302, turning and shifting operations are applied to each subset image.
7. The deep learning-based small intestine magnetic resonance image recognition and physiological information extraction method according to claim 4, wherein in step S400, the convolution operation comprises the following steps:
s401, extracting preliminary feature mapping after dynamic convolution;
s402, transforming feature mapping through upsampling;
and S403, adjusting feature mapping through standard convolution to obtain a feature sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110506227.3A CN113436139A (en) | 2021-05-10 | 2021-05-10 | Small intestine nuclear magnetic resonance image identification and physiological information extraction system and method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110506227.3A CN113436139A (en) | 2021-05-10 | 2021-05-10 | Small intestine nuclear magnetic resonance image identification and physiological information extraction system and method based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113436139A true CN113436139A (en) | 2021-09-24 |
Family
ID=77753164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110506227.3A Pending CN113436139A (en) | 2021-05-10 | 2021-05-10 | Small intestine nuclear magnetic resonance image identification and physiological information extraction system and method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113436139A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114067154A (en) * | 2021-11-12 | 2022-02-18 | 深圳大学 | Crohn's disease fibrosis classification method based on multi-sequence MRI and related equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529468A (en) * | 2016-11-07 | 2017-03-22 | 重庆工商大学 | Finger vein identification method and system based on convolutional neural network |
| CN106683104A (en) * | 2017-01-06 | 2017-05-17 | 西北工业大学 | Prostate magnetic resonance image segmentation method based on integrated depth convolution neural network |
| CN109741395A (en) * | 2018-12-14 | 2019-05-10 | 北京市商汤科技开发有限公司 | Biventricular quantization method, device, electronic equipment and storage medium |
| CN110853051A (en) * | 2019-10-24 | 2020-02-28 | 北京航空航天大学 | Cerebrovascular image segmentation method based on multi-attention dense connection generation countermeasure network |
| CN111179227A (en) * | 2019-12-16 | 2020-05-19 | 西北工业大学 | Mammary gland ultrasonic image quality evaluation method based on auxiliary diagnosis and subjective aesthetics |
| CN111488887A (en) * | 2020-04-09 | 2020-08-04 | 腾讯科技（深圳）有限公司 | Image processing method and device based on artificial intelligence |
| CN111583204A (en) * | 2020-04-27 | 2020-08-25 | 天津大学 | Organ positioning method of two-dimensional sequence magnetic resonance image based on network model |
| CN111932550A (en) * | 2020-07-01 | 2020-11-13 | 浙江大学 | 3D ventricle nuclear magnetic resonance video segmentation system based on deep learning |
| CN112348774A (en) * | 2020-09-29 | 2021-02-09 | 深圳市罗湖区人民医院 | CT image segmentation method, terminal and storage medium suitable for bladder cancer |
| CN112669319A (en) * | 2021-03-22 | 2021-04-16 | 四川大学 | Multi-view multi-scale lymph node false positive inhibition modeling method |
-
2021
- 2021-05-10 CN CN202110506227.3A patent/CN113436139A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529468A (en) * | 2016-11-07 | 2017-03-22 | 重庆工商大学 | Finger vein identification method and system based on convolutional neural network |
| CN106683104A (en) * | 2017-01-06 | 2017-05-17 | 西北工业大学 | Prostate magnetic resonance image segmentation method based on integrated depth convolution neural network |
| CN109741395A (en) * | 2018-12-14 | 2019-05-10 | 北京市商汤科技开发有限公司 | Biventricular quantization method, device, electronic equipment and storage medium |
| CN110853051A (en) * | 2019-10-24 | 2020-02-28 | 北京航空航天大学 | Cerebrovascular image segmentation method based on multi-attention dense connection generation countermeasure network |
| CN111179227A (en) * | 2019-12-16 | 2020-05-19 | 西北工业大学 | Mammary gland ultrasonic image quality evaluation method based on auxiliary diagnosis and subjective aesthetics |
| CN111488887A (en) * | 2020-04-09 | 2020-08-04 | 腾讯科技（深圳）有限公司 | Image processing method and device based on artificial intelligence |
| CN111583204A (en) * | 2020-04-27 | 2020-08-25 | 天津大学 | Organ positioning method of two-dimensional sequence magnetic resonance image based on network model |
| CN111932550A (en) * | 2020-07-01 | 2020-11-13 | 浙江大学 | 3D ventricle nuclear magnetic resonance video segmentation system based on deep learning |
| CN112348774A (en) * | 2020-09-29 | 2021-02-09 | 深圳市罗湖区人民医院 | CT image segmentation method, terminal and storage medium suitable for bladder cancer |
| CN112669319A (en) * | 2021-03-22 | 2021-04-16 | 四川大学 | Multi-view multi-scale lymph node false positive inhibition modeling method |
Non-Patent Citations (4)
| Title |
|---|
| JOONHYUNG LEE 等: "Deep Learning Fast MRI Using Channel Attention in Magnitude Domain", 《IEEE》 * |
| TADASHI KONDO 等: "The 3-Dimensional Medical Image Recognition of Right and Left Kidneys by Deep GMDH-type Neural Network", 《ICIIBMS》 * |
| 曾于珍 等: "深度卷积神经网络用于小肠胶囊内镜检查诊断的研究进展", 《上海医药》 * |
| 齐惠颖: "《医学信息资源智能管理》", 31 October 2019, 湖北科学技术出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114067154A (en) * | 2021-11-12 | 2022-02-18 | 深圳大学 | Crohn's disease fibrosis classification method based on multi-sequence MRI and related equipment |
| CN114067154B (en) * | 2021-11-12 | 2022-07-08 | 深圳大学 | Crohn's disease fibrosis classification method based on multi-sequence MRI and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zebari et al. | Improved threshold based and trainable fully automated segmentation for breast cancer boundary and pectoral muscle in mammogram images | |
| Zhang et al. | Detection of ovarian tumors in obstetric ultrasound imaging using logistic regression classifier with an advanced machine learning approach | |
| US9081877B2 (en) | Medical image interpretation system | |
| US8799013B2 (en) | Mammography information system | |
| Dong et al. | One step further into the blackbox: a pilot study of how to build more confidence around an AI-based decision system of breast nodule assessment in 2D ultrasound | |
| CN109829889A (en) | A kind of ultrasound image processing method and its system, equipment, storage medium | |
| WO2022110525A1 (en) | Comprehensive detection apparatus and method for cancerous region | |
| CN112309566A (en) | Remote automatic diagnosis system and method for intelligent image recognition and intelligent medical reasoning | |
| CN111079901A (en) | Acute stroke lesion segmentation method based on small sample learning | |
| CN114998674A (en) | Device and method for tumor focus boundary identification and grade classification based on contrast enhanced ultrasonic image | |
| US20040024292A1 (en) | System and method for assigning a computer aided detection application to a digital image | |
| Ghantasala et al. | Identification of Normal and Abnormal Mammographic Images Using Deep Neural Network | |
| CN115761365A (en) | Intraoperative hemorrhage condition determination method and device and electronic equipment | |
| CN113436139A (en) | Small intestine nuclear magnetic resonance image identification and physiological information extraction system and method based on deep learning | |
| CN114897760A (en) | Rib CT image fracture detection segmentation auxiliary film reading method and system based on deep learning | |
| EP1887487A2 (en) | Use of archived data in interpretation of medical images | |
| CN116797889B (en) | Updating method and device of medical image recognition model and computer equipment | |
| CN113706518A (en) | Femoral head necrosis stage analysis method and system based on artificial intelligence | |
| CN112002407A (en) | Breast cancer diagnosis device and method based on ultrasonic video | |
| Azli et al. | Ultrasound image segmentation using a combination of edge enhancement and kirsch’s template method for detecting follicles in ovaries | |
| CN109840564A (en) | A kind of categorizing system based on ultrasonic contrast image uniform degree | |
| Sridar et al. | An automated framework for large scale retrospective analysis of ultrasound images | |
| CN106667524A (en) | B ultrasonic imaging system | |
| CN116721240B (en) | AI system and analysis method for skin scar measurement and subcutaneous hard mass perception test | |
| WO2022054530A1 (en) | Ultrasound imaging device, method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210924 |