A Multi-Layer Consistent Collaborative Method for Feature Extraction of Brain Imaging Medical Records
A feature extraction and brain imaging technology, applied in the field of medical information intelligent processing, can solve the problems of low precision, time-consuming, and difficult training.
Active Publication Date: 2019-06-14
南通大学技术转移中心有限公司
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Due to the internal similarity of brain imaging medical records, it is difficult to distinguish fine-grained images. Existing algorithms have problems such as time-consuming, difficult training and low precision in feature extraction of brain imaging medical records. We need to further propose some An efficient method to reveal the imaging neural mechanism and internal structure of brain diseases, improve its classification accuracy, and provide objective indicators for the diagnosis and evaluation of brain diseases
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach
[0068] Such as Figure 1-Figure 4 Shown is a specific implementation of a multi-layer consistent collaborative method for feature extraction of brain imaging medical records: comprising the following steps:
[0069] A. Design an efficient multi-layer collaborative MapReduce model, construct the preference relationship matrix PE between each elite and the adjacency matrix P, and carry out multi-layer correlation feature identification on the indivisible brain imaging medical records with multiple associations in the collaborative meme group, and find The elite transfer matrix ECM is obtained, and its eigenvector Cov is minimized; specifically, the following steps are included:
[0070] a. Construct the i-th memegroup Memeplex of the evolutionary population i The parallel Map / Reduce operation operator of i , value i >, the specific definition is as follows:
[0071]
[0072]
[0073] where f Elitisti is the i-th meme group Memeplex i The local optimal fitness of the m...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a multi-layer consistent collaborative method for feature extraction of brain imaging medical records. Firstly, a multi-layer collaborative MapReduce model is constructed to identify the features of indivisible related brain imaging medical records, and the brain medical records with multiple related features are processed. Effective classification; then design a brain imaging medical record feature consistency and compatibility aggregation method, so that the local solution and global dominant solution of the brain imaging medical record feature extracted by the collaborative meme group can achieve an effective balance; secondly, use the multi-decision consistency optimization matrix to further detect Cooperate with the non-cooperative MapReduce behavior of the meme group, so as to effectively obtain the consistent Nash equilibrium of the feature set; finally evaluate the accuracy of feature extraction of brain imaging medical records, and output the optimal feature selection set. The invention provides important image feature basis for clinical diagnosis and treatment of related diseases.
Description
Technical field: [0001] The invention relates to the field of intelligent processing of medical information, in particular to a multi-layer consistent collaborative method for feature extraction of brain imaging medical records. Background technique: [0002] The image structure of brain imaging medical records is extremely complex, and many features are not obvious. It has the characteristics of huge amount of information, various formats, fast access speed and high application value. At present, there is no objective index for early diagnosis of hidden disease symptoms in brain imaging medical records. , risk assessment and treatment options. Brain image feature extraction mainly involves complex information analysis models and methods. At present, magnetic resonance brain imaging is mainly used to provide functional and structural image information, and to detect brain functional activity characteristics, functional and structural network characteristics, etc. Due to the...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/232G06F18/2133
Inventor 丁卫平陆琰管致锦王杰华陈森博董建成程学云张晓峰胡彬沈学华余利国景炜张琼
Owner 南通大学技术转移中心有限公司