Alzheimer's disease classification method based on fusion network
A technology that integrates networks and classification methods, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problems of poor model generalization and accuracy that need to be further improved, and achieve good classification results
Active Publication Date: 2020-06-05
WENZHOU UNIVERSITY
View PDF5 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
These models that use the base network based on deep learning to achieve AD classification show good results compared with traditional machine learning methods, but there are problems with poor generalization of the model, and the accuracy rate needs to be further improved
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
Embodiment Construction
[0026] In order to describe the technical solutions in the embodiments of the present invention completely and clearly, further details will be described below in conjunction with the drawings in the embodiments of the present invention. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0027] see figure 1 , the present invention provides a technical solution: a fusion network-based Alzheimer's disease classification method, comprising the following steps:
[0028] Step S1: Obtain the subject's magnetic resonance image dataset from the public dataset of ADNI (http: / / adni.loni.usc.edu / ), which is a t1-weighted structural MRI scan, after specific image preprocessing steps , including multiplanar reconstruction (MPR), grayscale bias (GradWarp), B1 non-uniformity correction, and N3 intensity normalization. The dataset contains MRI images and subject labels, where labels are e...
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 an Alzheimer's disease classification method based on a fusion network, and the method comprises the following steps: 1, giving a tested magnetic resonance image data set, andcarrying out the preprocessing; 2, dividing the samples into a training set and a test set, and carrying out image amplification and normalization operation; 3, inputting the training set into a training network; 4, performing feature extraction and feature fusion on the sample; 5, fusing the classification decision of each base network and the classification decision of feature fusion; 6, carrying out error calculation on the output label, and carrying out parameter updating through back propagation; 7, evaluating the classification model and obtaining an optimal model, and repeating the steps 3-7 until iteration is finished; 8, inputting the pre-processed tested magnetic resonance image data into the trained optimal model to obtain a tested label. According to the Alzheimer's disease classification method, the row convolutional neural network is used, the Alzheimer's disease classification method effectively using the tested magnetic resonance image data is realized, and the robustness is relatively good.
Description
technical field [0001] The invention belongs to the interdisciplinary field of brain imaging and computer science, relates to the technical field of image classification, and in particular relates to a fusion network-based classification method for Alzheimer's disease. Background technique [0002] With the rapid development of artificial intelligence and neuroimaging technology, medical image processing, as one of the fields most closely related to medical science and technology, is booming. The classification of Alzheimer's disease is an important research direction in the field of medical image classification, and it is of great significance in computer-aided diagnosis. The analysis of magnetic resonance images by machine learning can realize the rapid and accurate classification of Alzheimer's disease (AD). In some cases, this approach demonstrated better classification accuracy than clinicians. Computer-aided diagnosis based on machine learning has developed into an i...
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 Applications(China)
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/08G06F18/251G06F18/254G06F18/253
Inventor 胡众义陈昌足吴奇
Owner WENZHOU UNIVERSITY