CN116758336A - Medical image intelligent analysis system based on artificial intelligence - Google Patents
Medical image intelligent analysis system based on artificial intelligence Download PDFInfo
- Publication number
- CN116758336A CN116758336A CN202310606560.0A CN202310606560A CN116758336A CN 116758336 A CN116758336 A CN 116758336A CN 202310606560 A CN202310606560 A CN 202310606560A CN 116758336 A CN116758336 A CN 116758336A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- medical image
- unit
- images
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 42
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 19
- 238000000605 extraction Methods 0.000 claims abstract description 30
- 238000003745 diagnosis Methods 0.000 claims abstract description 27
- 230000001575 pathological effect Effects 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 34
- 238000012360 testing method Methods 0.000 claims description 25
- 238000013527 convolutional neural network Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 13
- 238000003709 image segmentation Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 210000003484 anatomy Anatomy 0.000 claims description 6
- 230000003902 lesion Effects 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000012512 characterization method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012633 leachable Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
Abstract
The invention relates to the technical field of intelligent analysis of medical images, in particular to an intelligent analysis system of medical images based on artificial intelligence, which comprises an image acquisition unit, a preprocessing unit, a feature extraction unit, a classification and identification unit and a diagnosis output unit, wherein the image acquisition unit is used for acquiring pathological positions of patients and obtaining medical images of the pathological positions; the preprocessing unit is used for receiving the medical image output by the image acquisition unit and preprocessing the medical image to obtain a denoised, enhanced, smooth and contrast-enhanced medical image, the feature extraction unit is used for dividing the received preprocessed image to form a feature image, extracting the feature image at the same time, reducing the recognition analysis of unnecessary images, the classification recognition unit is used for classifying and recognizing the feature image, and the depth convolution neural network is used for accurately classifying and recognizing the features and modes of the image learned from a large amount of medical image data.
Description
Technical Field
The invention relates to the technical field of intelligent analysis of medical images, in particular to an intelligent analysis system of medical images based on artificial intelligence.
Background
Along with technological development, intelligent analysis of medical images is a technology aiming at assisting doctors in diagnosing and treating diseases by analyzing medical images through technologies such as image processing, computer vision, machine learning and the like, and along with continuous development of artificial intelligence technology, intelligent analysis of medical images is more and more concerned and applied, however, the traditional intelligent analysis system of medical images often has low accuracy due to image recognition, so that the analysis system is easy to misjudge when extracting, analyzing and judging the lesions and physiological structures, and the traditional diagnosis system has low system diagnosis efficiency when classifying and recognizing medical images, and patients wait for diagnosis results for a long time and has low diagnosis efficiency.
In order to address the above problems, there is a need for an artificial intelligence based medical image intelligent analysis system.
Disclosure of Invention
The invention aims to provide an artificial intelligence-based medical image intelligent analysis system so as to solve the problems in the background technology.
In order to achieve the above purpose, an artificial intelligence-based medical image intelligent analysis system is provided, which comprises an image acquisition unit, a preprocessing unit, a feature extraction unit, a classification and identification unit and a diagnosis output unit;
the image acquisition unit is used for acquiring the pathological position of a patient and obtaining a medical image of the pathological position; the preprocessing unit is used for receiving the medical image output by the image acquisition unit and preprocessing the medical image to obtain a medical image with denoising, enhancement, smoothness and contrast enhancement; the feature extraction unit is used for dividing the received preprocessed image to form a feature image, extracting the feature image and reducing the recognition analysis of unnecessary images; the classification and identification unit is used for classifying and identifying characteristic images, learning the characteristics and modes of the images from a large amount of medical image data through a deep convolutional neural network, and accurately classifying and identifying the characteristics and modes; the diagnosis output unit is used for receiving the analysis diagnosis result of the classification recognition unit and outputting the analysis diagnosis result in the form of characters or images.
As a further improvement of the technical scheme, the image acquisition unit comprises an angle adjusting module and an image acquisition module;
the angle adjusting module is used for adjusting the angle of the image acquisition device and accurately acquiring medical images of pathological parts of a patient;
the image acquisition module is used for acquiring images of pathological positions of patients, and the angle of the images is adjusted by the angle adjusting module, so that the images acquired by the image acquisition module are clear and complete.
As a further improvement of the technical scheme, the preprocessing unit comprises a contour scanning module and an image optimizing module;
the profile scanning module is used for scanning the whole profile of the medical image and determining the processing range of the medical image;
the image optimization module is used for denoising, enhancing, smoothing and contrast enhancing the medical image and improving the definition of the medical image.
As a further improvement of the technical scheme, the feature extraction unit comprises an image segmentation module and an information extraction module;
the image segmentation module is used for segmenting a medical image area;
the information extraction module is used for extracting quantitative features representing the focus, the physiological structure or the anatomical structure which are segmented by the image segmentation module.
As a further improvement of the technical scheme, the information extraction module adopts a local binary pattern to extract quantitative features, and the extraction formula is as follows:
LBP_{P,R}＝\sum_{n＝0}^{P-1}s(g_n-g_c)2^n
wherein P represents the number of neighborhood points, R represents the neighborhood radius, gc is the gray value of the central pixel point, g_n is the gray value of the nth pixel point in the neighborhood, s (x) is a sign function, specifically, the local binary pattern algorithm firstly compares the central pixel point with the neighborhood pixel point, calculates the difference between the gray value of the neighborhood pixel point and the gray value of the central pixel point to obtain a binary sequence, then converts the binary sequence into a decimal value, and the decimal value is the local binary pattern value.
As a further improvement of the technical scheme, the classification and identification unit comprises a feature selection module and a training test module;
the feature selection module is used for selecting medical images with quantitative features representing lesions, physiological structures or anatomical structures;
the training test module is used for training and testing the medical images selected by the feature selection module, optimizing specific medical image classification tasks, performing model training by adopting a deep convolutional neural network model in the training process, classifying and identifying by adopting the training model in the testing process, and accurately analyzing a large amount of image data in a short time through the training test module.
As a further improvement of the technical scheme, the training test module trains the deep convolutional neural network model adopted in the process, and the deep convolutional neural network model comprises a convolutional layer, an activation function, a pooling layer and a full-connection layer.
As a further improvement of the technical scheme, the classification and identification unit further comprises an intelligent analysis module, wherein the intelligent analysis module is used for sorting the data information summarized by the training and testing module and automatically diagnosing the pathological problems of the medical images.
As a further improvement of the technical scheme, the diagnosis output unit comprises a word arrangement module and an image processing module; the character arrangement module is used for outputting characters in diagnosis; the image processing module is used for outputting images in diagnosis.
Compared with the prior art, the invention has the beneficial effects that:
1. in the medical image intelligent analysis system based on artificial intelligence, the body posture of a patient is regulated through an image acquisition unit, medical image acquisition is carried out, the acquired medical image is preprocessed through a preprocessing unit, so that a medical image with denoising, enhancement, smoothness and contrast enhancement is obtained, image definition is improved, the system is convenient for accurately analyzing the medical image characterization focus and physiological structure, the preprocessed image is received through a feature extraction unit to divide the medical image characterization focus and physiological structure, the divided image feature part is extracted, the feature part image is classified and identified through a classification and identification unit, the pathological part is rapidly analyzed and diagnosed, the diagnosis result is output in the form of characters or images, the medical image intelligent analysis system can rapidly carry out operations such as image preprocessing, feature extraction, classification and identification, and the like, the waiting time of the patient is shortened, and the diagnosis efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of the overall structure of the present invention;
FIG. 2 is a schematic diagram of an image acquisition unit according to the present invention;
FIG. 3 is a schematic diagram of a pretreatment unit according to the present invention;
FIG. 4 is a schematic diagram of a feature extraction unit according to the present invention;
FIG. 5 is a schematic diagram of a classification and identification unit according to the present invention;
fig. 6 is a schematic diagram of a diagnostic output unit of the present invention.
The meaning of each reference sign in the figure is:
100. an image acquisition unit; 110. an angle adjusting module; 120. an image acquisition module;
200. a preprocessing unit; 210. a profile scanning module; 220. an image optimization module;
300. a feature extraction unit; 310. an image segmentation module; 320. an information extraction module;
400. a classification and identification unit; 410. a feature selection module; 420. training a test module; 430. an intelligent analysis module; 500. a diagnostic output unit; 510. a word arrangement module; 520. and an image processing module.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1 to 6, an artificial intelligence based medical image intelligent analysis system is provided, which includes an image acquisition unit 100, a preprocessing unit 200, a feature extraction unit 300, a classification recognition unit 400, and a diagnosis output unit 500;
the image acquisition unit 100 is used for acquiring the pathological position of a patient and obtaining a medical image of the pathological position; the image acquisition unit 100 comprises an angle adjusting module 110 and an image acquisition module 120;
the angle adjusting module 110 is used for adjusting the angle of the image capturing device, accurately capturing the medical image of the pathological part of the patient, and by adjusting the angle of the image capturing device, the medical image captured by the image capturing module 120 is clear and complete, and the image capturing efficiency is improved.
The preprocessing unit 200 is configured to receive the medical image output by the image acquisition unit 100, perform preprocessing, and obtain a medical image with denoising, enhancement, smoothing, and contrast enhancement; the preprocessing unit 200 includes a contour scanning module 210 and an image optimization module 220;
the contour scanning module 210 is used for scanning the whole contour of the medical image and determining the processing range of the medical image; the image optimization module 220 is used for denoising, enhancing, smoothing, contrast enhancement and improving the definition of the medical image.
In particular use, the contour scanning module 210 scans the medical image to determine the contour range of the medical image, and the image optimization module 220 performs a filtering operation on the medical image through a filter to make the image clearer, clearer or reduce noise. The filter works in principle: in an image, different objects and tissues have different textures and color distributions that contain various information, but also with noise, the image filter can improve the sharpness and accuracy of the image by removing the noise and enhancing the signal of the target area.
The feature extraction unit 300 is used for dividing the received preprocessed image to form a feature image, extracting the feature image, and reducing the recognition analysis of unnecessary images; the feature extraction unit 300 includes an image segmentation module 310 and an information extraction module 320;
the image segmentation module 310 is used for segmenting the medical image region;
the information extraction module 320 is configured to extract quantified features representing a lesion, a physiological structure, or an anatomical structure segmented by the image segmentation module 310; the information extraction module 320 extracts quantitative features using a local binary pattern, the extraction formula being as follows:
LBP_{P,R}＝\sum_{n＝0}^{P-1}s(g_n-g_c)2^n
wherein P represents the number of neighborhood points, R represents the neighborhood radius, gc is the gray value of the central pixel point, g_n is the gray value of the nth pixel point in the neighborhood, s (x) is a sign function, specifically, the local binary pattern algorithm firstly compares the central pixel point with the neighborhood pixel point, calculates the difference between the gray value of the neighborhood pixel point and the gray value of the central pixel point to obtain a binary sequence, then converts the binary sequence into a decimal value, and the decimal value is the local binary pattern value.
When the method is specifically used, the image segmentation module 310 segments the medical image, the information extraction module 320 extracts the information of the medical image segmented by the image segmentation module 310, and the local binary pattern technology is adopted in the extraction process, so that key features of the image can be extracted as the basis of classification and identification, and meanwhile, the selection and optimization of the features can be performed according to specific conditions so as to improve the accuracy of classification and identification.
The classification and identification unit 400 is used for classifying and identifying characteristic images, learning the characteristics and modes of the images from a large amount of medical image data through a deep convolutional neural network, and accurately classifying and identifying the images; the classification and identification unit 400 comprises a feature selection module 410 and a training test module 420;
the feature selection module 410 is used to select a medical image having quantified features that characterize a lesion, physiological structure, or anatomical structure;
the training test module 420 is used for training and testing the medical images selected by the feature selection module 410, optimizing the medical images according to specific medical image classification tasks, performing model training by using a deep convolutional neural network model in the training process, classifying and identifying by using a training model in the testing process, and accurately analyzing a large amount of image data in a short time through the training test module 420; the training test module 420 trains the deep convolutional neural network model adopted in the process, and the deep convolutional neural network model comprises a convolutional layer, an activation function, a pooling layer and a full connection layer, and the technical principle is as follows:
convolution layer: the convolution layer is the basis of a deep convolutional neural network, and performs convolution operation on an input feature map by using a convolution kernel so as to extract local features of input data, wherein the local features are also components of overall features. Meanwhile, the convolution kernel can be used for realizing parameter sharing, so that the number of parameters needing training is greatly reduced.
Activation function: an activation function is added behind each convolution layer and the full connection layer, the function is used for performing nonlinear transformation on output data of a network, nonlinear characteristic expression capacity of a model is improved, and ReLU, sigmoid, tanh is a common activation function.
Pooling layer: the pooling layer is mainly used for reducing the dimension of the output of the convolution layer, thereby reducing the complexity of a model and reducing the possibility of overfitting.
Full tie layer: the full connection layer is a common layer in the neural network, and uses matrix multiplication to fully connect different features in the feature map to obtain final classification output, and the full connection layer can be regarded as a process of combining feature vectors in the feature map so as to obtain classification probability corresponding to input data.
The classification recognition unit 400 further includes an intelligent analysis module 430, where the intelligent analysis module 430 is configured to sort the data information summarized by the training test module 420, and automatically diagnose the pathological problem of the medical image.
During specific use, the feature selection module 410 is used for selecting the pathological positions of the segmented medical images, the training test module 420 is used for training and testing the medical images, accuracy of pathological information analysis is improved, and meanwhile, the training test module 420 is used for model training by adopting a deep convolutional neural network model, so that the diagnosis efficiency of the medical images is improved, and waiting time of a patient is saved.
Deep convolutional neural network theory of operation: the method comprises the steps of performing multi-layer convolution and pooling operation on an input image, converting the image into higher-level characteristic representation, classifying or regressing the characteristics through a full-connection layer, wherein the deep convolution neural network is a core part of the neural network, extracting the characteristics of the image through convolution operation, the convolution layer consists of a group of leachable filters or convolution kernels, each convolution kernel input image performs one convolution operation and generates a characteristic image, each characteristic image is obtained after a plurality of two-dimensional convolution kernel input images are convolved, and all convolution kernel parameters are optimized and learned in a training process, so that the analysis efficiency of medical images is improved.
The diagnosis output unit 500 comprises a word sorting module 510 and an image processing module 520; the word arrangement module 510 is used for arranging and outputting words; the image processing module 520 is configured to output the image arrangement, so as to facilitate detailed output of the diagnosis inside and rapidly analyze the pathology of the medical image, and therefore, the diagnosis result is output in a graphic-text combination through the text arrangement module 510 and the image processing module 520, so that the diagnosis result is easy to be understood.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. An artificial intelligence-based medical image intelligent analysis system is characterized in that: comprises an image acquisition unit (100), a preprocessing unit (200), a feature extraction unit (300), a classification and identification unit (400) and a diagnosis output unit (500);
the image acquisition unit (100) is used for acquiring the pathological position of a patient and obtaining a medical image of the pathological position; the preprocessing unit (200) is used for receiving the medical image output by the image acquisition unit (100) and preprocessing the medical image to obtain a medical image with denoising, enhancement, smoothness and contrast enhancement; the feature extraction unit (300) is used for dividing the received preprocessed image to form a feature image, extracting the feature image and reducing the recognition analysis of unnecessary images; the classification and identification unit (400) is used for classifying and identifying characteristic images, learning the characteristics and modes of the images from a large amount of medical image data through a deep convolutional neural network, and accurately classifying and identifying the characteristics and modes; the diagnosis output unit (500) is used for receiving the analysis diagnosis result of the classification recognition unit (400) and outputting the analysis diagnosis result in the form of characters or images.
2. The artificial intelligence based medical image intelligent analysis system of claim 1, wherein: the image acquisition unit (100) comprises an angle adjusting module (110) and an image acquisition module (120);
the angle adjusting module (110) is used for adjusting the angle of the image acquisition device and accurately acquiring medical images of pathological parts of a patient;
the image acquisition module (120) is used for acquiring images of pathological positions of patients, and the angle of the images is adjusted by the angle adjustment module (110), so that the images acquired by the image acquisition module (120) are clear and complete.
3. The artificial intelligence based medical image intelligent analysis system of claim 1, wherein: the preprocessing unit (200) comprises a contour scanning module (210) and an image optimizing module (220);
the profile scanning module (210) is used for scanning the whole profile of the medical image and determining the processing range of the medical image;
the image optimization module (220) is used for denoising, enhancing, smoothing, contrast enhancement and improving medical image definition.
4. The artificial intelligence based medical image intelligent analysis system of claim 1, wherein: the characteristic extraction unit (300) comprises an image segmentation module (310) and an information extraction module (320);
the image segmentation module (310) is for segmenting a medical image region;
the information extraction module (320) is used for extracting quantitative features representing lesions, physiological structures or anatomical structures segmented by the image segmentation module (310).
5. The artificial intelligence based medical image intelligent analysis system according to claim 4, wherein: the information extraction module (320) adopts a local binary pattern to extract quantitative features, and the extraction formula is as follows:
LBP_{P,R}＝\sum_{n＝0}^{P-1}s(g_n-g_c)2^n
wherein P represents the number of neighborhood points, R represents the neighborhood radius, gc is the gray value of the central pixel point, g_n is the gray value of the nth pixel point in the neighborhood, s (x) is a sign function, specifically, the local binary pattern algorithm firstly compares the central pixel point with the neighborhood pixel point, calculates the difference between the gray value of the neighborhood pixel point and the gray value of the central pixel point to obtain a binary sequence, then converts the binary sequence into a decimal value, and the decimal value is the local binary pattern value.
6. The artificial intelligence based medical image intelligent analysis system of claim 1, wherein: the classification and identification unit (400) comprises a characteristic selection module (410) and a training test module (420);
the feature selection module (410) is for selecting a medical image having quantified features that characterize a lesion, a physiological structure, or an anatomical structure;
the training test module (420) is used for training and testing the medical images selected by the feature selection module (410) and optimizing the medical images aiming at specific medical image classification tasks, a deep convolutional neural network model is adopted in the training process for model training, a training model is adopted in the testing process for classification and identification, and a large amount of image data can be accurately analyzed in a short time through the training test module (420).
7. The artificial intelligence based medical image intelligent analysis system according to claim 6, wherein: the training test module (420) trains a deep convolutional neural network model adopted in the process, wherein the deep convolutional neural network model comprises a convolutional layer, an activation function, a pooling layer and a full connection layer.
8. The artificial intelligence based medical image intelligent analysis system according to claim 6, wherein: the classification and identification unit (400) further comprises an intelligent analysis module (430), wherein the intelligent analysis module (430) is used for sorting data information summarized by the training and testing module (420) and simultaneously automatically diagnosing pathological problems of medical images.
9. The artificial intelligence based medical image intelligent analysis system of claim 1, wherein: the diagnosis output unit (500) comprises a word arrangement module (510) and an image processing module (520); the word arrangement module (510) is used for outputting words in diagnosis; the image processing module (520) is configured to output an image in a diagnosis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310606560.0A CN116758336A (en) | 2023-05-26 | 2023-05-26 | Medical image intelligent analysis system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310606560.0A CN116758336A (en) | 2023-05-26 | 2023-05-26 | Medical image intelligent analysis system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116758336A true CN116758336A (en) | 2023-09-15 |
Family
ID=87948814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310606560.0A Pending CN116758336A (en) | 2023-05-26 | 2023-05-26 | Medical image intelligent analysis system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116758336A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958128A (en) * | 2023-09-18 | 2023-10-27 | 中南大学 | Medical image automatic positioning method based on deep learning |
| CN117398231A (en) * | 2023-11-30 | 2024-01-16 | 西安好博士医疗科技有限公司 | Medical liquid storage device temperature control system and method based on data analysis |
-
2023
- 2023-05-26 CN CN202310606560.0A patent/CN116758336A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958128A (en) * | 2023-09-18 | 2023-10-27 | 中南大学 | Medical image automatic positioning method based on deep learning |
| CN116958128B (en) * | 2023-09-18 | 2023-12-26 | 中南大学 | Medical image automatic positioning method based on deep learning |
| CN117398231A (en) * | 2023-11-30 | 2024-01-16 | 西安好博士医疗科技有限公司 | Medical liquid storage device temperature control system and method based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886273B (en) | CMR image segmentation and classification system | |
| Xiuqin et al. | A fundus retinal vessels segmentation scheme based on the improved deep learning U-Net model | |
| CN107644420B (en) | Blood vessel image segmentation method based on centerline extraction and nuclear magnetic resonance imaging system | |
| CN108985345B (en) | Detection apparatus based on lung medical image fusion classification | |
| CN108154519A (en) | Dividing method, device and the storage medium of eye fundus image medium vessels | |
| CN116758336A (en) | Medical image intelligent analysis system based on artificial intelligence | |
| CN112862808A (en) | Deep learning-based interpretability identification method of breast cancer ultrasonic image | |
| CN112348059A (en) | Deep learning-based method and system for classifying multiple dyeing pathological images | |
| CN114758137B (en) | Ultrasonic image segmentation method and device and computer readable storage medium | |
| Hermawati et al. | Combination of aggregated channel features (ACF) detector and faster R-CNN to improve object detection performance in fetal ultrasound images | |
| CN115359066B (en) | Focus detection method and device for endoscope, electronic device and storage medium | |
| Zhao et al. | Attention residual convolution neural network based on U-net (AttentionResU-Net) for retina vessel segmentation | |
| CN113344933B (en) | Glandular cell segmentation method based on multi-level feature fusion network | |
| CN108230341B (en) | Eyeground image blood vessel segmentation method based on layered matting algorithm | |
| CN116188786B (en) | Image segmentation system for hepatic duct and biliary tract calculus | |
| CN111899272A (en) | Fundus image blood vessel segmentation method based on coupling neural network and line connector | |
| Parraga et al. | A review of image-based deep learning algorithms for cervical cancer screening | |
| CN115689993A (en) | Skin cancer image segmentation method and system based on attention and multi-feature fusion | |
| CN115239695A (en) | Pulmonary nodule identification system and method based on time sequence image | |
| CN114140830A (en) | Repeated identification inhibition method based on circulating tumor cell image | |
| CN116524315A (en) | Mask R-CNN-based lung cancer pathological tissue section identification and segmentation method | |
| Mahmoud et al. | Novel feature extraction methodology based on histopathalogical images and subsequent classification by Support Vector Machine | |
| Arroyo et al. | 5 Comparison of Image Processing Techniques for Reticular Pattern | |
| Kurian et al. | An improved deep neural learning classifier for brain tumor detection | |
| Pavel et al. | Cancer detection using image processing techniques based on cell counting, cell area measurement and clump 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 |